Add files using upload-large-folder tool
Browse files- .gitattributes +1 -0
- README.md +41 -0
- chat_template.jinja +331 -0
- config.json +1169 -0
- config.json.bak-before-mxfp4-expert-overrides +89 -0
- generation_config.json +11 -0
- model-00001-of-00013.safetensors +3 -0
- model-00002-of-00013.safetensors +3 -0
- model-00003-of-00013.safetensors +3 -0
- model-00004-of-00013.safetensors +3 -0
- model-00005-of-00013.safetensors +3 -0
- model-00006-of-00013.safetensors +3 -0
- model-00007-of-00013.safetensors +3 -0
- model-00008-of-00013.safetensors +3 -0
- model-00009-of-00013.safetensors +3 -0
- model-00010-of-00013.safetensors +3 -0
- model-00011-of-00013.safetensors +3 -0
- model-00012-of-00013.safetensors +3 -0
- model-00013-of-00013.safetensors +3 -0
- model.safetensors.index.json +1094 -0
- omlx_oQ4_manifest.json +7 -0
- special_tokens_map.json +5 -0
- tokenizer.json +3 -0
- tokenizer_config.json +183 -0
.gitattributes
CHANGED
|
@@ -33,3 +33,4 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
|
|
| 33 |
*.zip filter=lfs diff=lfs merge=lfs -text
|
| 34 |
*.zst filter=lfs diff=lfs merge=lfs -text
|
| 35 |
*tfevents* filter=lfs diff=lfs merge=lfs -text
|
|
|
|
|
|
| 33 |
*.zip filter=lfs diff=lfs merge=lfs -text
|
| 34 |
*.zst filter=lfs diff=lfs merge=lfs -text
|
| 35 |
*tfevents* filter=lfs diff=lfs merge=lfs -text
|
| 36 |
+
tokenizer.json filter=lfs diff=lfs merge=lfs -text
|
README.md
ADDED
|
@@ -0,0 +1,41 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
license: apache-2.0
|
| 3 |
+
base_model: openai/gpt-oss-120b
|
| 4 |
+
library_name: mlx
|
| 5 |
+
tags:
|
| 6 |
+
- mlx
|
| 7 |
+
- omlx
|
| 8 |
+
- gpt_oss
|
| 9 |
+
- quantized
|
| 10 |
+
- oQ4
|
| 11 |
+
- apple-silicon
|
| 12 |
+
---
|
| 13 |
+
|
| 14 |
+
# gpt-oss-120b-oQ4
|
| 15 |
+
|
| 16 |
+
This is an oMLX oQ4 quantized MLX checkpoint for `gpt-oss-120b`, published for local inference with oMLX on Apple Silicon.
|
| 17 |
+
|
| 18 |
+
## Notes
|
| 19 |
+
|
| 20 |
+
- Quantized with oMLX oQ4.
|
| 21 |
+
- Non-expert tensors use the oQ4 affine quantization plan generated by oMLX.
|
| 22 |
+
- GPT-OSS MoE expert projection tensors are preserved as MXFP4 passthrough tensors and are marked with per-layer `mxfp4` overrides in `config.json`; this is required for oMLX/MLX loading.
|
| 23 |
+
- Tested locally with oMLX model discovery/load after generation.
|
| 24 |
+
|
| 25 |
+
## Local oMLX Use
|
| 26 |
+
|
| 27 |
+
Place or symlink the repo folder under an oMLX model directory, for example:
|
| 28 |
+
|
| 29 |
+
```bash
|
| 30 |
+
~/.omlx/models/cjnielson44/gpt-oss-120b-oQ4
|
| 31 |
+
```
|
| 32 |
+
|
| 33 |
+
Then load model id:
|
| 34 |
+
|
| 35 |
+
```text
|
| 36 |
+
gpt-oss-120b-oQ4
|
| 37 |
+
```
|
| 38 |
+
|
| 39 |
+
## Source
|
| 40 |
+
|
| 41 |
+
The local source checkpoint used for this conversion was the oMLX-compatible `gpt-oss-120b` MLX checkpoint in the Hugging Face cache.
|
chat_template.jinja
ADDED
|
@@ -0,0 +1,331 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{#-
|
| 2 |
+
In addition to the normal inputs of `messages` and `tools`, this template also accepts the
|
| 3 |
+
following kwargs:
|
| 4 |
+
- "builtin_tools": A list, can contain "browser" and/or "python".
|
| 5 |
+
- "model_identity": A string that optionally describes the model identity.
|
| 6 |
+
- "reasoning_effort": A string that describes the reasoning effort, defaults to "medium".
|
| 7 |
+
#}
|
| 8 |
+
|
| 9 |
+
{#- Tool Definition Rendering ============================================== #}
|
| 10 |
+
{%- macro render_typescript_type(param_spec, required_params, is_nullable=false) -%}
|
| 11 |
+
{%- if param_spec.type == "array" -%}
|
| 12 |
+
{%- if param_spec['items'] -%}
|
| 13 |
+
{%- if param_spec['items']['type'] == "string" -%}
|
| 14 |
+
{{- "string[]" }}
|
| 15 |
+
{%- elif param_spec['items']['type'] == "number" -%}
|
| 16 |
+
{{- "number[]" }}
|
| 17 |
+
{%- elif param_spec['items']['type'] == "integer" -%}
|
| 18 |
+
{{- "number[]" }}
|
| 19 |
+
{%- elif param_spec['items']['type'] == "boolean" -%}
|
| 20 |
+
{{- "boolean[]" }}
|
| 21 |
+
{%- else -%}
|
| 22 |
+
{%- set inner_type = render_typescript_type(param_spec['items'], required_params) -%}
|
| 23 |
+
{%- if inner_type == "object | object" or inner_type|length > 50 -%}
|
| 24 |
+
{{- "any[]" }}
|
| 25 |
+
{%- else -%}
|
| 26 |
+
{{- inner_type + "[]" }}
|
| 27 |
+
{%- endif -%}
|
| 28 |
+
{%- endif -%}
|
| 29 |
+
{%- if param_spec.nullable -%}
|
| 30 |
+
{{- " | null" }}
|
| 31 |
+
{%- endif -%}
|
| 32 |
+
{%- else -%}
|
| 33 |
+
{{- "any[]" }}
|
| 34 |
+
{%- if param_spec.nullable -%}
|
| 35 |
+
{{- " | null" }}
|
| 36 |
+
{%- endif -%}
|
| 37 |
+
{%- endif -%}
|
| 38 |
+
{%- elif param_spec.type is defined and param_spec.type is iterable and param_spec.type is not string and param_spec.type is not mapping and param_spec.type[0] is defined -%}
|
| 39 |
+
{#- Handle array of types like ["object", "object"] from Union[dict, list] #}
|
| 40 |
+
{%- if param_spec.type | length > 1 -%}
|
| 41 |
+
{{- param_spec.type | join(" | ") }}
|
| 42 |
+
{%- else -%}
|
| 43 |
+
{{- param_spec.type[0] }}
|
| 44 |
+
{%- endif -%}
|
| 45 |
+
{%- elif param_spec.oneOf -%}
|
| 46 |
+
{#- Handle oneOf schemas - check for complex unions and fallback to any #}
|
| 47 |
+
{%- set has_object_variants = false -%}
|
| 48 |
+
{%- for variant in param_spec.oneOf -%}
|
| 49 |
+
{%- if variant.type == "object" -%}
|
| 50 |
+
{%- set has_object_variants = true -%}
|
| 51 |
+
{%- endif -%}
|
| 52 |
+
{%- endfor -%}
|
| 53 |
+
{%- if has_object_variants and param_spec.oneOf|length > 1 -%}
|
| 54 |
+
{{- "any" }}
|
| 55 |
+
{%- else -%}
|
| 56 |
+
{%- for variant in param_spec.oneOf -%}
|
| 57 |
+
{{- render_typescript_type(variant, required_params) -}}
|
| 58 |
+
{%- if variant.description %}
|
| 59 |
+
{{- "// " + variant.description }}
|
| 60 |
+
{%- endif -%}
|
| 61 |
+
{%- if variant.default is defined %}
|
| 62 |
+
{{ "// default: " + variant.default|tojson }}
|
| 63 |
+
{%- endif -%}
|
| 64 |
+
{%- if not loop.last %}
|
| 65 |
+
{{- " | " }}
|
| 66 |
+
{% endif -%}
|
| 67 |
+
{%- endfor -%}
|
| 68 |
+
{%- endif -%}
|
| 69 |
+
{%- elif param_spec.type == "string" -%}
|
| 70 |
+
{%- if param_spec.enum -%}
|
| 71 |
+
{{- '"' + param_spec.enum|join('" | "') + '"' -}}
|
| 72 |
+
{%- else -%}
|
| 73 |
+
{{- "string" }}
|
| 74 |
+
{%- if param_spec.nullable %}
|
| 75 |
+
{{- " | null" }}
|
| 76 |
+
{%- endif -%}
|
| 77 |
+
{%- endif -%}
|
| 78 |
+
{%- elif param_spec.type == "number" -%}
|
| 79 |
+
{{- "number" }}
|
| 80 |
+
{%- elif param_spec.type == "integer" -%}
|
| 81 |
+
{{- "number" }}
|
| 82 |
+
{%- elif param_spec.type == "boolean" -%}
|
| 83 |
+
{{- "boolean" }}
|
| 84 |
+
|
| 85 |
+
{%- elif param_spec.type == "object" -%}
|
| 86 |
+
{%- if param_spec.properties -%}
|
| 87 |
+
{{- "{\n" }}
|
| 88 |
+
{%- for prop_name, prop_spec in param_spec.properties.items() -%}
|
| 89 |
+
{{- prop_name -}}
|
| 90 |
+
{%- if prop_name not in (param_spec.required or []) -%}
|
| 91 |
+
{{- "?" }}
|
| 92 |
+
{%- endif -%}
|
| 93 |
+
{{- ": " }}
|
| 94 |
+
{{ render_typescript_type(prop_spec, param_spec.required or []) }}
|
| 95 |
+
{%- if not loop.last -%}
|
| 96 |
+
{{-", " }}
|
| 97 |
+
{%- endif -%}
|
| 98 |
+
{%- endfor -%}
|
| 99 |
+
{{- "}" }}
|
| 100 |
+
{%- else -%}
|
| 101 |
+
{{- "object" }}
|
| 102 |
+
{%- endif -%}
|
| 103 |
+
{%- else -%}
|
| 104 |
+
{{- "any" }}
|
| 105 |
+
{%- endif -%}
|
| 106 |
+
{%- endmacro -%}
|
| 107 |
+
|
| 108 |
+
{%- macro render_tool_namespace(namespace_name, tools) -%}
|
| 109 |
+
{{- "## " + namespace_name + "\n\n" }}
|
| 110 |
+
{{- "namespace " + namespace_name + " {\n\n" }}
|
| 111 |
+
{%- for tool in tools %}
|
| 112 |
+
{%- set tool = tool.function %}
|
| 113 |
+
{{- "// " + tool.description + "\n" }}
|
| 114 |
+
{{- "type "+ tool.name + " = " }}
|
| 115 |
+
{%- if tool.parameters and tool.parameters.properties %}
|
| 116 |
+
{{- "(_: {\n" }}
|
| 117 |
+
{%- for param_name, param_spec in tool.parameters.properties.items() %}
|
| 118 |
+
{%- if param_spec.description %}
|
| 119 |
+
{{- "// " + param_spec.description + "\n" }}
|
| 120 |
+
{%- endif %}
|
| 121 |
+
{{- param_name }}
|
| 122 |
+
{%- if param_name not in (tool.parameters.required or []) -%}
|
| 123 |
+
{{- "?" }}
|
| 124 |
+
{%- endif -%}
|
| 125 |
+
{{- ": " }}
|
| 126 |
+
{{- render_typescript_type(param_spec, tool.parameters.required or []) }}
|
| 127 |
+
{%- if param_spec.default is defined -%}
|
| 128 |
+
{%- if param_spec.enum %}
|
| 129 |
+
{{- ", // default: " + param_spec.default }}
|
| 130 |
+
{%- elif param_spec.oneOf %}
|
| 131 |
+
{{- "// default: " + param_spec.default }}
|
| 132 |
+
{%- else %}
|
| 133 |
+
{{- ", // default: " + param_spec.default|tojson }}
|
| 134 |
+
{%- endif -%}
|
| 135 |
+
{%- endif -%}
|
| 136 |
+
{%- if not loop.last %}
|
| 137 |
+
{{- ",\n" }}
|
| 138 |
+
{%- else %}
|
| 139 |
+
{{- ",\n" }}
|
| 140 |
+
{%- endif -%}
|
| 141 |
+
{%- endfor %}
|
| 142 |
+
{{- "}) => any;\n\n" }}
|
| 143 |
+
{%- else -%}
|
| 144 |
+
{{- "() => any;\n\n" }}
|
| 145 |
+
{%- endif -%}
|
| 146 |
+
{%- endfor %}
|
| 147 |
+
{{- "} // namespace " + namespace_name }}
|
| 148 |
+
{%- endmacro -%}
|
| 149 |
+
|
| 150 |
+
{%- macro render_builtin_tools(browser_tool, python_tool) -%}
|
| 151 |
+
{%- if browser_tool %}
|
| 152 |
+
{{- "## browser\n\n" }}
|
| 153 |
+
{{- "// Tool for browsing.\n" }}
|
| 154 |
+
{{- "// The `cursor` appears in brackets before each browsing display: `[{cursor}]`.\n" }}
|
| 155 |
+
{{- "// Cite information from the tool using the following format:\n" }}
|
| 156 |
+
{{- "// `【{cursor}†L{line_start}(-L{line_end})?】`, for example: `【6†L9-L11】` or `【8†L3】`.\n" }}
|
| 157 |
+
{{- "// Do not quote more than 10 words directly from the tool output.\n" }}
|
| 158 |
+
{{- "// sources=web (default: web)\n" }}
|
| 159 |
+
{{- "namespace browser {\n\n" }}
|
| 160 |
+
{{- "// Searches for information related to `query` and displays `topn` results.\n" }}
|
| 161 |
+
{{- "type search = (_: {\n" }}
|
| 162 |
+
{{- "query: string,\n" }}
|
| 163 |
+
{{- "topn?: number, // default: 10\n" }}
|
| 164 |
+
{{- "source?: string,\n" }}
|
| 165 |
+
{{- "}) => any;\n\n" }}
|
| 166 |
+
{{- "// Opens the link `id` from the page indicated by `cursor` starting at line number `loc`, showing `num_lines` lines.\n" }}
|
| 167 |
+
{{- "// Valid link ids are displayed with the formatting: `【{id}†.*】`.\n" }}
|
| 168 |
+
{{- "// If `cursor` is not provided, the most recent page is implied.\n" }}
|
| 169 |
+
{{- "// If `id` is a string, it is treated as a fully qualified URL associated with `source`.\n" }}
|
| 170 |
+
{{- "// If `loc` is not provided, the viewport will be positioned at the beginning of the document or centered on the most relevant passage, if available.\n" }}
|
| 171 |
+
{{- "// Use this function without `id` to scroll to a new location of an opened page.\n" }}
|
| 172 |
+
{{- "type open = (_: {\n" }}
|
| 173 |
+
{{- "id?: number | string, // default: -1\n" }}
|
| 174 |
+
{{- "cursor?: number, // default: -1\n" }}
|
| 175 |
+
{{- "loc?: number, // default: -1\n" }}
|
| 176 |
+
{{- "num_lines?: number, // default: -1\n" }}
|
| 177 |
+
{{- "view_source?: boolean, // default: false\n" }}
|
| 178 |
+
{{- "source?: string,\n" }}
|
| 179 |
+
{{- "}) => any;\n\n" }}
|
| 180 |
+
{{- "// Finds exact matches of `pattern` in the current page, or the page given by `cursor`.\n" }}
|
| 181 |
+
{{- "type find = (_: {\n" }}
|
| 182 |
+
{{- "pattern: string,\n" }}
|
| 183 |
+
{{- "cursor?: number, // default: -1\n" }}
|
| 184 |
+
{{- "}) => any;\n\n" }}
|
| 185 |
+
{{- "} // namespace browser\n\n" }}
|
| 186 |
+
{%- endif -%}
|
| 187 |
+
|
| 188 |
+
{%- if python_tool %}
|
| 189 |
+
{{- "## python\n\n" }}
|
| 190 |
+
{{- "Use this tool to execute Python code in your chain of thought. The code will not be shown to the user. This tool should be used for internal reasoning, but not for code that is intended to be visible to the user (e.g. when creating plots, tables, or files).\n\n" }}
|
| 191 |
+
{{- "When you send a message containing Python code to python, it will be executed in a stateful Jupyter notebook environment. python will respond with the output of the execution or time out after 120.0 seconds. The drive at '/mnt/data' can be used to save and persist user files. Internet access for this session is UNKNOWN. Depends on the cluster.\n\n" }}
|
| 192 |
+
{%- endif -%}
|
| 193 |
+
{%- endmacro -%}
|
| 194 |
+
|
| 195 |
+
{#- System Message Construction ============================================ #}
|
| 196 |
+
{%- macro build_system_message() -%}
|
| 197 |
+
{%- if model_identity is not defined %}
|
| 198 |
+
{%- set model_identity = "You are ChatGPT, a large language model trained by OpenAI." %}
|
| 199 |
+
{%- endif %}
|
| 200 |
+
{{- model_identity + "\n" }}
|
| 201 |
+
{{- "Knowledge cutoff: 2024-06\n" }}
|
| 202 |
+
{{- "Current date: " + strftime_now("%Y-%m-%d") + "\n\n" }}
|
| 203 |
+
{%- if reasoning_effort is not defined %}
|
| 204 |
+
{%- set reasoning_effort = "medium" %}
|
| 205 |
+
{%- endif %}
|
| 206 |
+
{{- "Reasoning: " + reasoning_effort + "\n\n" }}
|
| 207 |
+
{%- if builtin_tools %}
|
| 208 |
+
{{- "# Tools\n\n" }}
|
| 209 |
+
{%- set available_builtin_tools = namespace(browser=false, python=false) %}
|
| 210 |
+
{%- for tool in builtin_tools %}
|
| 211 |
+
{%- if tool == "browser" %}
|
| 212 |
+
{%- set available_builtin_tools.browser = true %}
|
| 213 |
+
{%- elif tool == "python" %}
|
| 214 |
+
{%- set available_builtin_tools.python = true %}
|
| 215 |
+
{%- endif %}
|
| 216 |
+
{%- endfor %}
|
| 217 |
+
{{- render_builtin_tools(available_builtin_tools.browser, available_builtin_tools.python) }}
|
| 218 |
+
{%- endif -%}
|
| 219 |
+
{{- "# Valid channels: analysis, commentary, final. Channel must be included for every message." }}
|
| 220 |
+
{%- if tools -%}
|
| 221 |
+
{{- "\nCalls to these tools must go to the commentary channel: 'functions'." }}
|
| 222 |
+
{%- endif -%}
|
| 223 |
+
{%- endmacro -%}
|
| 224 |
+
|
| 225 |
+
{#- Main Template Logic ================================================= #}
|
| 226 |
+
{#- Set defaults #}
|
| 227 |
+
|
| 228 |
+
{#- Render system message #}
|
| 229 |
+
{{- "<|start|>system<|message|>" }}
|
| 230 |
+
{{- build_system_message() }}
|
| 231 |
+
{{- "<|end|>" }}
|
| 232 |
+
|
| 233 |
+
{#- Extract developer message #}
|
| 234 |
+
{%- if messages[0].role == "developer" or messages[0].role == "system" %}
|
| 235 |
+
{%- set developer_message = messages[0].content %}
|
| 236 |
+
{%- set loop_messages = messages[1:] %}
|
| 237 |
+
{%- else %}
|
| 238 |
+
{%- set developer_message = "" %}
|
| 239 |
+
{%- set loop_messages = messages %}
|
| 240 |
+
{%- endif %}
|
| 241 |
+
|
| 242 |
+
{#- Render developer message #}
|
| 243 |
+
{%- if developer_message or tools %}
|
| 244 |
+
{{- "<|start|>developer<|message|>" }}
|
| 245 |
+
{%- if developer_message %}
|
| 246 |
+
{{- "# Instructions\n\n" }}
|
| 247 |
+
{{- developer_message }}
|
| 248 |
+
{{- "\n\n" }}
|
| 249 |
+
{%- endif %}
|
| 250 |
+
{%- if tools -%}
|
| 251 |
+
{{- "# Tools\n\n" }}
|
| 252 |
+
{{- render_tool_namespace("functions", tools) }}
|
| 253 |
+
{%- endif -%}
|
| 254 |
+
{{- "<|end|>" }}
|
| 255 |
+
{%- endif %}
|
| 256 |
+
|
| 257 |
+
{#- Render messages #}
|
| 258 |
+
{%- set last_tool_call = namespace(name=none) %}
|
| 259 |
+
{%- for message in loop_messages -%}
|
| 260 |
+
{#- At this point only assistant/user/tool messages should remain #}
|
| 261 |
+
{%- if message.role == 'assistant' -%}
|
| 262 |
+
{#- Checks to ensure the messages are being passed in the format we expect #}
|
| 263 |
+
{%- if "content" in message %}
|
| 264 |
+
{%- if "<|channel|>analysis<|message|>" in message.content or "<|channel|>final<|message|>" in message.content %}
|
| 265 |
+
{{- raise_exception("You have passed a message containing <|channel|> tags in the content field. Instead of doing this, you should pass analysis messages (the string between '<|message|>' and '<|end|>') in the 'thinking' field, and final messages (the string between '<|message|>' and '<|end|>') in the 'content' field.") }}
|
| 266 |
+
{%- endif %}
|
| 267 |
+
{%- endif %}
|
| 268 |
+
{%- if "thinking" in message %}
|
| 269 |
+
{%- if "<|channel|>analysis<|message|>" in message.thinking or "<|channel|>final<|message|>" in message.thinking %}
|
| 270 |
+
{{- raise_exception("You have passed a message containing <|channel|> tags in the thinking field. Instead of doing this, you should pass analysis messages (the string between '<|message|>' and '<|end|>') in the 'thinking' field, and final messages (the string between '<|message|>' and '<|end|>') in the 'content' field.") }}
|
| 271 |
+
{%- endif %}
|
| 272 |
+
{%- endif %}
|
| 273 |
+
{%- if "tool_calls" in message %}
|
| 274 |
+
{#- We need very careful handling here - we want to drop the tool call analysis message if the model #}
|
| 275 |
+
{#- has output a later <|final|> message, but otherwise we want to retain it. This is the only case #}
|
| 276 |
+
{#- when we render CoT/analysis messages in inference. #}
|
| 277 |
+
{%- set future_final_message = namespace(found=false) %}
|
| 278 |
+
{%- for future_message in loop_messages[loop.index:] %}
|
| 279 |
+
{%- if future_message.role == 'assistant' and "tool_calls" not in future_message %}
|
| 280 |
+
{%- set future_final_message.found = true %}
|
| 281 |
+
{%- endif %}
|
| 282 |
+
{%- endfor %}
|
| 283 |
+
{#- We assume max 1 tool call per message, and so we infer the tool call name #}
|
| 284 |
+
{#- in "tool" messages from the most recent assistant tool call name #}
|
| 285 |
+
{%- set tool_call = message.tool_calls[0] %}
|
| 286 |
+
{%- if tool_call.function %}
|
| 287 |
+
{%- set tool_call = tool_call.function %}
|
| 288 |
+
{%- endif %}
|
| 289 |
+
{%- if message.content and message.thinking %}
|
| 290 |
+
{{- raise_exception("Cannot pass both content and thinking in an assistant message with tool calls! Put the analysis message in one or the other, but not both.") }}
|
| 291 |
+
{%- elif message.content and not future_final_message.found %}
|
| 292 |
+
{{- "<|start|>assistant<|channel|>analysis<|message|>" + message.content + "<|end|>" }}
|
| 293 |
+
{%- elif message.thinking and not future_final_message.found %}
|
| 294 |
+
{{- "<|start|>assistant<|channel|>analysis<|message|>" + message.thinking + "<|end|>" }}
|
| 295 |
+
{%- endif %}
|
| 296 |
+
{{- "<|start|>assistant to=" }}
|
| 297 |
+
{{- "functions." + tool_call.name + "<|channel|>commentary " }}
|
| 298 |
+
{{- (tool_call.content_type if tool_call.content_type is defined else "json") + "<|message|>" }}
|
| 299 |
+
{{- tool_call.arguments|tojson }}
|
| 300 |
+
{{- "<|call|>" }}
|
| 301 |
+
{%- set last_tool_call.name = tool_call.name %}
|
| 302 |
+
{%- elif loop.last and not add_generation_prompt %}
|
| 303 |
+
{#- Only render the CoT if the final turn is an assistant turn and add_generation_prompt is false #}
|
| 304 |
+
{#- This is a situation that should only occur in training, never in inference. #}
|
| 305 |
+
{%- if "thinking" in message %}
|
| 306 |
+
{{- "<|start|>assistant<|channel|>analysis<|message|>" + message.thinking + "<|end|>" }}
|
| 307 |
+
{%- endif %}
|
| 308 |
+
{#- <|return|> indicates the end of generation, but <|end|> does not #}
|
| 309 |
+
{#- <|return|> should never be an input to the model, but we include it as the final token #}
|
| 310 |
+
{#- when training, so the model learns to emit it. #}
|
| 311 |
+
{{- "<|start|>assistant<|channel|>final<|message|>" + message.content + "<|return|>" }}
|
| 312 |
+
{%- else %}
|
| 313 |
+
{#- CoT is dropped during all previous turns, so we never render it for inference #}
|
| 314 |
+
{{- "<|start|>assistant<|channel|>final<|message|>" + message.content + "<|end|>" }}
|
| 315 |
+
{%- set last_tool_call.name = none %}
|
| 316 |
+
{%- endif %}
|
| 317 |
+
{%- elif message.role == 'tool' -%}
|
| 318 |
+
{%- if last_tool_call.name is none %}
|
| 319 |
+
{{- raise_exception("Message has tool role, but there was no previous assistant message with a tool call!") }}
|
| 320 |
+
{%- endif %}
|
| 321 |
+
{{- "<|start|>functions." + last_tool_call.name }}
|
| 322 |
+
{{- " to=assistant<|channel|>commentary<|message|>" + message.content|tojson + "<|end|>" }}
|
| 323 |
+
{%- elif message.role == 'user' -%}
|
| 324 |
+
{{- "<|start|>user<|message|>" + message.content + "<|end|>" }}
|
| 325 |
+
{%- endif -%}
|
| 326 |
+
{%- endfor -%}
|
| 327 |
+
|
| 328 |
+
{#- Generation prompt #}
|
| 329 |
+
{%- if add_generation_prompt -%}
|
| 330 |
+
<|start|>assistant
|
| 331 |
+
{%- endif -%}
|
config.json
ADDED
|
@@ -0,0 +1,1169 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"architectures": [
|
| 3 |
+
"GptOssForCausalLM"
|
| 4 |
+
],
|
| 5 |
+
"attention_bias": true,
|
| 6 |
+
"attention_dropout": 0.0,
|
| 7 |
+
"eos_token_id": 200002,
|
| 8 |
+
"experts_per_token": 4,
|
| 9 |
+
"head_dim": 64,
|
| 10 |
+
"hidden_act": "silu",
|
| 11 |
+
"hidden_size": 2880,
|
| 12 |
+
"initial_context_length": 4096,
|
| 13 |
+
"initializer_range": 0.02,
|
| 14 |
+
"intermediate_size": 2880,
|
| 15 |
+
"layer_types": [
|
| 16 |
+
"sliding_attention",
|
| 17 |
+
"full_attention",
|
| 18 |
+
"sliding_attention",
|
| 19 |
+
"full_attention",
|
| 20 |
+
"sliding_attention",
|
| 21 |
+
"full_attention",
|
| 22 |
+
"sliding_attention",
|
| 23 |
+
"full_attention",
|
| 24 |
+
"sliding_attention",
|
| 25 |
+
"full_attention",
|
| 26 |
+
"sliding_attention",
|
| 27 |
+
"full_attention",
|
| 28 |
+
"sliding_attention",
|
| 29 |
+
"full_attention",
|
| 30 |
+
"sliding_attention",
|
| 31 |
+
"full_attention",
|
| 32 |
+
"sliding_attention",
|
| 33 |
+
"full_attention",
|
| 34 |
+
"sliding_attention",
|
| 35 |
+
"full_attention",
|
| 36 |
+
"sliding_attention",
|
| 37 |
+
"full_attention",
|
| 38 |
+
"sliding_attention",
|
| 39 |
+
"full_attention",
|
| 40 |
+
"sliding_attention",
|
| 41 |
+
"full_attention",
|
| 42 |
+
"sliding_attention",
|
| 43 |
+
"full_attention",
|
| 44 |
+
"sliding_attention",
|
| 45 |
+
"full_attention",
|
| 46 |
+
"sliding_attention",
|
| 47 |
+
"full_attention",
|
| 48 |
+
"sliding_attention",
|
| 49 |
+
"full_attention",
|
| 50 |
+
"sliding_attention",
|
| 51 |
+
"full_attention"
|
| 52 |
+
],
|
| 53 |
+
"max_position_embeddings": 131072,
|
| 54 |
+
"model_type": "gpt_oss",
|
| 55 |
+
"num_attention_heads": 64,
|
| 56 |
+
"num_experts_per_tok": 4,
|
| 57 |
+
"num_hidden_layers": 36,
|
| 58 |
+
"num_key_value_heads": 8,
|
| 59 |
+
"num_local_experts": 128,
|
| 60 |
+
"output_router_logits": false,
|
| 61 |
+
"pad_token_id": 199999,
|
| 62 |
+
"quantization_config": {
|
| 63 |
+
"group_size": 64,
|
| 64 |
+
"bits": 4,
|
| 65 |
+
"mode": "affine",
|
| 66 |
+
"model.layers.0.mlp.experts.gate_proj": {
|
| 67 |
+
"group_size": 32,
|
| 68 |
+
"bits": 4,
|
| 69 |
+
"mode": "mxfp4"
|
| 70 |
+
},
|
| 71 |
+
"model.layers.0.mlp.experts.up_proj": {
|
| 72 |
+
"group_size": 32,
|
| 73 |
+
"bits": 4,
|
| 74 |
+
"mode": "mxfp4"
|
| 75 |
+
},
|
| 76 |
+
"model.layers.0.mlp.experts.down_proj": {
|
| 77 |
+
"group_size": 32,
|
| 78 |
+
"bits": 4,
|
| 79 |
+
"mode": "mxfp4"
|
| 80 |
+
},
|
| 81 |
+
"model.layers.1.mlp.experts.gate_proj": {
|
| 82 |
+
"group_size": 32,
|
| 83 |
+
"bits": 4,
|
| 84 |
+
"mode": "mxfp4"
|
| 85 |
+
},
|
| 86 |
+
"model.layers.1.mlp.experts.up_proj": {
|
| 87 |
+
"group_size": 32,
|
| 88 |
+
"bits": 4,
|
| 89 |
+
"mode": "mxfp4"
|
| 90 |
+
},
|
| 91 |
+
"model.layers.1.mlp.experts.down_proj": {
|
| 92 |
+
"group_size": 32,
|
| 93 |
+
"bits": 4,
|
| 94 |
+
"mode": "mxfp4"
|
| 95 |
+
},
|
| 96 |
+
"model.layers.2.mlp.experts.gate_proj": {
|
| 97 |
+
"group_size": 32,
|
| 98 |
+
"bits": 4,
|
| 99 |
+
"mode": "mxfp4"
|
| 100 |
+
},
|
| 101 |
+
"model.layers.2.mlp.experts.up_proj": {
|
| 102 |
+
"group_size": 32,
|
| 103 |
+
"bits": 4,
|
| 104 |
+
"mode": "mxfp4"
|
| 105 |
+
},
|
| 106 |
+
"model.layers.2.mlp.experts.down_proj": {
|
| 107 |
+
"group_size": 32,
|
| 108 |
+
"bits": 4,
|
| 109 |
+
"mode": "mxfp4"
|
| 110 |
+
},
|
| 111 |
+
"model.layers.3.mlp.experts.gate_proj": {
|
| 112 |
+
"group_size": 32,
|
| 113 |
+
"bits": 4,
|
| 114 |
+
"mode": "mxfp4"
|
| 115 |
+
},
|
| 116 |
+
"model.layers.3.mlp.experts.up_proj": {
|
| 117 |
+
"group_size": 32,
|
| 118 |
+
"bits": 4,
|
| 119 |
+
"mode": "mxfp4"
|
| 120 |
+
},
|
| 121 |
+
"model.layers.3.mlp.experts.down_proj": {
|
| 122 |
+
"group_size": 32,
|
| 123 |
+
"bits": 4,
|
| 124 |
+
"mode": "mxfp4"
|
| 125 |
+
},
|
| 126 |
+
"model.layers.4.mlp.experts.gate_proj": {
|
| 127 |
+
"group_size": 32,
|
| 128 |
+
"bits": 4,
|
| 129 |
+
"mode": "mxfp4"
|
| 130 |
+
},
|
| 131 |
+
"model.layers.4.mlp.experts.up_proj": {
|
| 132 |
+
"group_size": 32,
|
| 133 |
+
"bits": 4,
|
| 134 |
+
"mode": "mxfp4"
|
| 135 |
+
},
|
| 136 |
+
"model.layers.4.mlp.experts.down_proj": {
|
| 137 |
+
"group_size": 32,
|
| 138 |
+
"bits": 4,
|
| 139 |
+
"mode": "mxfp4"
|
| 140 |
+
},
|
| 141 |
+
"model.layers.5.mlp.experts.gate_proj": {
|
| 142 |
+
"group_size": 32,
|
| 143 |
+
"bits": 4,
|
| 144 |
+
"mode": "mxfp4"
|
| 145 |
+
},
|
| 146 |
+
"model.layers.5.mlp.experts.up_proj": {
|
| 147 |
+
"group_size": 32,
|
| 148 |
+
"bits": 4,
|
| 149 |
+
"mode": "mxfp4"
|
| 150 |
+
},
|
| 151 |
+
"model.layers.5.mlp.experts.down_proj": {
|
| 152 |
+
"group_size": 32,
|
| 153 |
+
"bits": 4,
|
| 154 |
+
"mode": "mxfp4"
|
| 155 |
+
},
|
| 156 |
+
"model.layers.6.mlp.experts.gate_proj": {
|
| 157 |
+
"group_size": 32,
|
| 158 |
+
"bits": 4,
|
| 159 |
+
"mode": "mxfp4"
|
| 160 |
+
},
|
| 161 |
+
"model.layers.6.mlp.experts.up_proj": {
|
| 162 |
+
"group_size": 32,
|
| 163 |
+
"bits": 4,
|
| 164 |
+
"mode": "mxfp4"
|
| 165 |
+
},
|
| 166 |
+
"model.layers.6.mlp.experts.down_proj": {
|
| 167 |
+
"group_size": 32,
|
| 168 |
+
"bits": 4,
|
| 169 |
+
"mode": "mxfp4"
|
| 170 |
+
},
|
| 171 |
+
"model.layers.7.mlp.experts.gate_proj": {
|
| 172 |
+
"group_size": 32,
|
| 173 |
+
"bits": 4,
|
| 174 |
+
"mode": "mxfp4"
|
| 175 |
+
},
|
| 176 |
+
"model.layers.7.mlp.experts.up_proj": {
|
| 177 |
+
"group_size": 32,
|
| 178 |
+
"bits": 4,
|
| 179 |
+
"mode": "mxfp4"
|
| 180 |
+
},
|
| 181 |
+
"model.layers.7.mlp.experts.down_proj": {
|
| 182 |
+
"group_size": 32,
|
| 183 |
+
"bits": 4,
|
| 184 |
+
"mode": "mxfp4"
|
| 185 |
+
},
|
| 186 |
+
"model.layers.8.mlp.experts.gate_proj": {
|
| 187 |
+
"group_size": 32,
|
| 188 |
+
"bits": 4,
|
| 189 |
+
"mode": "mxfp4"
|
| 190 |
+
},
|
| 191 |
+
"model.layers.8.mlp.experts.up_proj": {
|
| 192 |
+
"group_size": 32,
|
| 193 |
+
"bits": 4,
|
| 194 |
+
"mode": "mxfp4"
|
| 195 |
+
},
|
| 196 |
+
"model.layers.8.mlp.experts.down_proj": {
|
| 197 |
+
"group_size": 32,
|
| 198 |
+
"bits": 4,
|
| 199 |
+
"mode": "mxfp4"
|
| 200 |
+
},
|
| 201 |
+
"model.layers.9.mlp.experts.gate_proj": {
|
| 202 |
+
"group_size": 32,
|
| 203 |
+
"bits": 4,
|
| 204 |
+
"mode": "mxfp4"
|
| 205 |
+
},
|
| 206 |
+
"model.layers.9.mlp.experts.up_proj": {
|
| 207 |
+
"group_size": 32,
|
| 208 |
+
"bits": 4,
|
| 209 |
+
"mode": "mxfp4"
|
| 210 |
+
},
|
| 211 |
+
"model.layers.9.mlp.experts.down_proj": {
|
| 212 |
+
"group_size": 32,
|
| 213 |
+
"bits": 4,
|
| 214 |
+
"mode": "mxfp4"
|
| 215 |
+
},
|
| 216 |
+
"model.layers.10.mlp.experts.gate_proj": {
|
| 217 |
+
"group_size": 32,
|
| 218 |
+
"bits": 4,
|
| 219 |
+
"mode": "mxfp4"
|
| 220 |
+
},
|
| 221 |
+
"model.layers.10.mlp.experts.up_proj": {
|
| 222 |
+
"group_size": 32,
|
| 223 |
+
"bits": 4,
|
| 224 |
+
"mode": "mxfp4"
|
| 225 |
+
},
|
| 226 |
+
"model.layers.10.mlp.experts.down_proj": {
|
| 227 |
+
"group_size": 32,
|
| 228 |
+
"bits": 4,
|
| 229 |
+
"mode": "mxfp4"
|
| 230 |
+
},
|
| 231 |
+
"model.layers.11.mlp.experts.gate_proj": {
|
| 232 |
+
"group_size": 32,
|
| 233 |
+
"bits": 4,
|
| 234 |
+
"mode": "mxfp4"
|
| 235 |
+
},
|
| 236 |
+
"model.layers.11.mlp.experts.up_proj": {
|
| 237 |
+
"group_size": 32,
|
| 238 |
+
"bits": 4,
|
| 239 |
+
"mode": "mxfp4"
|
| 240 |
+
},
|
| 241 |
+
"model.layers.11.mlp.experts.down_proj": {
|
| 242 |
+
"group_size": 32,
|
| 243 |
+
"bits": 4,
|
| 244 |
+
"mode": "mxfp4"
|
| 245 |
+
},
|
| 246 |
+
"model.layers.12.mlp.experts.gate_proj": {
|
| 247 |
+
"group_size": 32,
|
| 248 |
+
"bits": 4,
|
| 249 |
+
"mode": "mxfp4"
|
| 250 |
+
},
|
| 251 |
+
"model.layers.12.mlp.experts.up_proj": {
|
| 252 |
+
"group_size": 32,
|
| 253 |
+
"bits": 4,
|
| 254 |
+
"mode": "mxfp4"
|
| 255 |
+
},
|
| 256 |
+
"model.layers.12.mlp.experts.down_proj": {
|
| 257 |
+
"group_size": 32,
|
| 258 |
+
"bits": 4,
|
| 259 |
+
"mode": "mxfp4"
|
| 260 |
+
},
|
| 261 |
+
"model.layers.13.mlp.experts.gate_proj": {
|
| 262 |
+
"group_size": 32,
|
| 263 |
+
"bits": 4,
|
| 264 |
+
"mode": "mxfp4"
|
| 265 |
+
},
|
| 266 |
+
"model.layers.13.mlp.experts.up_proj": {
|
| 267 |
+
"group_size": 32,
|
| 268 |
+
"bits": 4,
|
| 269 |
+
"mode": "mxfp4"
|
| 270 |
+
},
|
| 271 |
+
"model.layers.13.mlp.experts.down_proj": {
|
| 272 |
+
"group_size": 32,
|
| 273 |
+
"bits": 4,
|
| 274 |
+
"mode": "mxfp4"
|
| 275 |
+
},
|
| 276 |
+
"model.layers.14.mlp.experts.gate_proj": {
|
| 277 |
+
"group_size": 32,
|
| 278 |
+
"bits": 4,
|
| 279 |
+
"mode": "mxfp4"
|
| 280 |
+
},
|
| 281 |
+
"model.layers.14.mlp.experts.up_proj": {
|
| 282 |
+
"group_size": 32,
|
| 283 |
+
"bits": 4,
|
| 284 |
+
"mode": "mxfp4"
|
| 285 |
+
},
|
| 286 |
+
"model.layers.14.mlp.experts.down_proj": {
|
| 287 |
+
"group_size": 32,
|
| 288 |
+
"bits": 4,
|
| 289 |
+
"mode": "mxfp4"
|
| 290 |
+
},
|
| 291 |
+
"model.layers.15.mlp.experts.gate_proj": {
|
| 292 |
+
"group_size": 32,
|
| 293 |
+
"bits": 4,
|
| 294 |
+
"mode": "mxfp4"
|
| 295 |
+
},
|
| 296 |
+
"model.layers.15.mlp.experts.up_proj": {
|
| 297 |
+
"group_size": 32,
|
| 298 |
+
"bits": 4,
|
| 299 |
+
"mode": "mxfp4"
|
| 300 |
+
},
|
| 301 |
+
"model.layers.15.mlp.experts.down_proj": {
|
| 302 |
+
"group_size": 32,
|
| 303 |
+
"bits": 4,
|
| 304 |
+
"mode": "mxfp4"
|
| 305 |
+
},
|
| 306 |
+
"model.layers.16.mlp.experts.gate_proj": {
|
| 307 |
+
"group_size": 32,
|
| 308 |
+
"bits": 4,
|
| 309 |
+
"mode": "mxfp4"
|
| 310 |
+
},
|
| 311 |
+
"model.layers.16.mlp.experts.up_proj": {
|
| 312 |
+
"group_size": 32,
|
| 313 |
+
"bits": 4,
|
| 314 |
+
"mode": "mxfp4"
|
| 315 |
+
},
|
| 316 |
+
"model.layers.16.mlp.experts.down_proj": {
|
| 317 |
+
"group_size": 32,
|
| 318 |
+
"bits": 4,
|
| 319 |
+
"mode": "mxfp4"
|
| 320 |
+
},
|
| 321 |
+
"model.layers.17.mlp.experts.gate_proj": {
|
| 322 |
+
"group_size": 32,
|
| 323 |
+
"bits": 4,
|
| 324 |
+
"mode": "mxfp4"
|
| 325 |
+
},
|
| 326 |
+
"model.layers.17.mlp.experts.up_proj": {
|
| 327 |
+
"group_size": 32,
|
| 328 |
+
"bits": 4,
|
| 329 |
+
"mode": "mxfp4"
|
| 330 |
+
},
|
| 331 |
+
"model.layers.17.mlp.experts.down_proj": {
|
| 332 |
+
"group_size": 32,
|
| 333 |
+
"bits": 4,
|
| 334 |
+
"mode": "mxfp4"
|
| 335 |
+
},
|
| 336 |
+
"model.layers.18.mlp.experts.gate_proj": {
|
| 337 |
+
"group_size": 32,
|
| 338 |
+
"bits": 4,
|
| 339 |
+
"mode": "mxfp4"
|
| 340 |
+
},
|
| 341 |
+
"model.layers.18.mlp.experts.up_proj": {
|
| 342 |
+
"group_size": 32,
|
| 343 |
+
"bits": 4,
|
| 344 |
+
"mode": "mxfp4"
|
| 345 |
+
},
|
| 346 |
+
"model.layers.18.mlp.experts.down_proj": {
|
| 347 |
+
"group_size": 32,
|
| 348 |
+
"bits": 4,
|
| 349 |
+
"mode": "mxfp4"
|
| 350 |
+
},
|
| 351 |
+
"model.layers.19.mlp.experts.gate_proj": {
|
| 352 |
+
"group_size": 32,
|
| 353 |
+
"bits": 4,
|
| 354 |
+
"mode": "mxfp4"
|
| 355 |
+
},
|
| 356 |
+
"model.layers.19.mlp.experts.up_proj": {
|
| 357 |
+
"group_size": 32,
|
| 358 |
+
"bits": 4,
|
| 359 |
+
"mode": "mxfp4"
|
| 360 |
+
},
|
| 361 |
+
"model.layers.19.mlp.experts.down_proj": {
|
| 362 |
+
"group_size": 32,
|
| 363 |
+
"bits": 4,
|
| 364 |
+
"mode": "mxfp4"
|
| 365 |
+
},
|
| 366 |
+
"model.layers.20.mlp.experts.gate_proj": {
|
| 367 |
+
"group_size": 32,
|
| 368 |
+
"bits": 4,
|
| 369 |
+
"mode": "mxfp4"
|
| 370 |
+
},
|
| 371 |
+
"model.layers.20.mlp.experts.up_proj": {
|
| 372 |
+
"group_size": 32,
|
| 373 |
+
"bits": 4,
|
| 374 |
+
"mode": "mxfp4"
|
| 375 |
+
},
|
| 376 |
+
"model.layers.20.mlp.experts.down_proj": {
|
| 377 |
+
"group_size": 32,
|
| 378 |
+
"bits": 4,
|
| 379 |
+
"mode": "mxfp4"
|
| 380 |
+
},
|
| 381 |
+
"model.layers.21.mlp.experts.gate_proj": {
|
| 382 |
+
"group_size": 32,
|
| 383 |
+
"bits": 4,
|
| 384 |
+
"mode": "mxfp4"
|
| 385 |
+
},
|
| 386 |
+
"model.layers.21.mlp.experts.up_proj": {
|
| 387 |
+
"group_size": 32,
|
| 388 |
+
"bits": 4,
|
| 389 |
+
"mode": "mxfp4"
|
| 390 |
+
},
|
| 391 |
+
"model.layers.21.mlp.experts.down_proj": {
|
| 392 |
+
"group_size": 32,
|
| 393 |
+
"bits": 4,
|
| 394 |
+
"mode": "mxfp4"
|
| 395 |
+
},
|
| 396 |
+
"model.layers.22.mlp.experts.gate_proj": {
|
| 397 |
+
"group_size": 32,
|
| 398 |
+
"bits": 4,
|
| 399 |
+
"mode": "mxfp4"
|
| 400 |
+
},
|
| 401 |
+
"model.layers.22.mlp.experts.up_proj": {
|
| 402 |
+
"group_size": 32,
|
| 403 |
+
"bits": 4,
|
| 404 |
+
"mode": "mxfp4"
|
| 405 |
+
},
|
| 406 |
+
"model.layers.22.mlp.experts.down_proj": {
|
| 407 |
+
"group_size": 32,
|
| 408 |
+
"bits": 4,
|
| 409 |
+
"mode": "mxfp4"
|
| 410 |
+
},
|
| 411 |
+
"model.layers.23.mlp.experts.gate_proj": {
|
| 412 |
+
"group_size": 32,
|
| 413 |
+
"bits": 4,
|
| 414 |
+
"mode": "mxfp4"
|
| 415 |
+
},
|
| 416 |
+
"model.layers.23.mlp.experts.up_proj": {
|
| 417 |
+
"group_size": 32,
|
| 418 |
+
"bits": 4,
|
| 419 |
+
"mode": "mxfp4"
|
| 420 |
+
},
|
| 421 |
+
"model.layers.23.mlp.experts.down_proj": {
|
| 422 |
+
"group_size": 32,
|
| 423 |
+
"bits": 4,
|
| 424 |
+
"mode": "mxfp4"
|
| 425 |
+
},
|
| 426 |
+
"model.layers.24.mlp.experts.gate_proj": {
|
| 427 |
+
"group_size": 32,
|
| 428 |
+
"bits": 4,
|
| 429 |
+
"mode": "mxfp4"
|
| 430 |
+
},
|
| 431 |
+
"model.layers.24.mlp.experts.up_proj": {
|
| 432 |
+
"group_size": 32,
|
| 433 |
+
"bits": 4,
|
| 434 |
+
"mode": "mxfp4"
|
| 435 |
+
},
|
| 436 |
+
"model.layers.24.mlp.experts.down_proj": {
|
| 437 |
+
"group_size": 32,
|
| 438 |
+
"bits": 4,
|
| 439 |
+
"mode": "mxfp4"
|
| 440 |
+
},
|
| 441 |
+
"model.layers.25.mlp.experts.gate_proj": {
|
| 442 |
+
"group_size": 32,
|
| 443 |
+
"bits": 4,
|
| 444 |
+
"mode": "mxfp4"
|
| 445 |
+
},
|
| 446 |
+
"model.layers.25.mlp.experts.up_proj": {
|
| 447 |
+
"group_size": 32,
|
| 448 |
+
"bits": 4,
|
| 449 |
+
"mode": "mxfp4"
|
| 450 |
+
},
|
| 451 |
+
"model.layers.25.mlp.experts.down_proj": {
|
| 452 |
+
"group_size": 32,
|
| 453 |
+
"bits": 4,
|
| 454 |
+
"mode": "mxfp4"
|
| 455 |
+
},
|
| 456 |
+
"model.layers.26.mlp.experts.gate_proj": {
|
| 457 |
+
"group_size": 32,
|
| 458 |
+
"bits": 4,
|
| 459 |
+
"mode": "mxfp4"
|
| 460 |
+
},
|
| 461 |
+
"model.layers.26.mlp.experts.up_proj": {
|
| 462 |
+
"group_size": 32,
|
| 463 |
+
"bits": 4,
|
| 464 |
+
"mode": "mxfp4"
|
| 465 |
+
},
|
| 466 |
+
"model.layers.26.mlp.experts.down_proj": {
|
| 467 |
+
"group_size": 32,
|
| 468 |
+
"bits": 4,
|
| 469 |
+
"mode": "mxfp4"
|
| 470 |
+
},
|
| 471 |
+
"model.layers.27.mlp.experts.gate_proj": {
|
| 472 |
+
"group_size": 32,
|
| 473 |
+
"bits": 4,
|
| 474 |
+
"mode": "mxfp4"
|
| 475 |
+
},
|
| 476 |
+
"model.layers.27.mlp.experts.up_proj": {
|
| 477 |
+
"group_size": 32,
|
| 478 |
+
"bits": 4,
|
| 479 |
+
"mode": "mxfp4"
|
| 480 |
+
},
|
| 481 |
+
"model.layers.27.mlp.experts.down_proj": {
|
| 482 |
+
"group_size": 32,
|
| 483 |
+
"bits": 4,
|
| 484 |
+
"mode": "mxfp4"
|
| 485 |
+
},
|
| 486 |
+
"model.layers.28.mlp.experts.gate_proj": {
|
| 487 |
+
"group_size": 32,
|
| 488 |
+
"bits": 4,
|
| 489 |
+
"mode": "mxfp4"
|
| 490 |
+
},
|
| 491 |
+
"model.layers.28.mlp.experts.up_proj": {
|
| 492 |
+
"group_size": 32,
|
| 493 |
+
"bits": 4,
|
| 494 |
+
"mode": "mxfp4"
|
| 495 |
+
},
|
| 496 |
+
"model.layers.28.mlp.experts.down_proj": {
|
| 497 |
+
"group_size": 32,
|
| 498 |
+
"bits": 4,
|
| 499 |
+
"mode": "mxfp4"
|
| 500 |
+
},
|
| 501 |
+
"model.layers.29.mlp.experts.gate_proj": {
|
| 502 |
+
"group_size": 32,
|
| 503 |
+
"bits": 4,
|
| 504 |
+
"mode": "mxfp4"
|
| 505 |
+
},
|
| 506 |
+
"model.layers.29.mlp.experts.up_proj": {
|
| 507 |
+
"group_size": 32,
|
| 508 |
+
"bits": 4,
|
| 509 |
+
"mode": "mxfp4"
|
| 510 |
+
},
|
| 511 |
+
"model.layers.29.mlp.experts.down_proj": {
|
| 512 |
+
"group_size": 32,
|
| 513 |
+
"bits": 4,
|
| 514 |
+
"mode": "mxfp4"
|
| 515 |
+
},
|
| 516 |
+
"model.layers.30.mlp.experts.gate_proj": {
|
| 517 |
+
"group_size": 32,
|
| 518 |
+
"bits": 4,
|
| 519 |
+
"mode": "mxfp4"
|
| 520 |
+
},
|
| 521 |
+
"model.layers.30.mlp.experts.up_proj": {
|
| 522 |
+
"group_size": 32,
|
| 523 |
+
"bits": 4,
|
| 524 |
+
"mode": "mxfp4"
|
| 525 |
+
},
|
| 526 |
+
"model.layers.30.mlp.experts.down_proj": {
|
| 527 |
+
"group_size": 32,
|
| 528 |
+
"bits": 4,
|
| 529 |
+
"mode": "mxfp4"
|
| 530 |
+
},
|
| 531 |
+
"model.layers.31.mlp.experts.gate_proj": {
|
| 532 |
+
"group_size": 32,
|
| 533 |
+
"bits": 4,
|
| 534 |
+
"mode": "mxfp4"
|
| 535 |
+
},
|
| 536 |
+
"model.layers.31.mlp.experts.up_proj": {
|
| 537 |
+
"group_size": 32,
|
| 538 |
+
"bits": 4,
|
| 539 |
+
"mode": "mxfp4"
|
| 540 |
+
},
|
| 541 |
+
"model.layers.31.mlp.experts.down_proj": {
|
| 542 |
+
"group_size": 32,
|
| 543 |
+
"bits": 4,
|
| 544 |
+
"mode": "mxfp4"
|
| 545 |
+
},
|
| 546 |
+
"model.layers.32.mlp.experts.gate_proj": {
|
| 547 |
+
"group_size": 32,
|
| 548 |
+
"bits": 4,
|
| 549 |
+
"mode": "mxfp4"
|
| 550 |
+
},
|
| 551 |
+
"model.layers.32.mlp.experts.up_proj": {
|
| 552 |
+
"group_size": 32,
|
| 553 |
+
"bits": 4,
|
| 554 |
+
"mode": "mxfp4"
|
| 555 |
+
},
|
| 556 |
+
"model.layers.32.mlp.experts.down_proj": {
|
| 557 |
+
"group_size": 32,
|
| 558 |
+
"bits": 4,
|
| 559 |
+
"mode": "mxfp4"
|
| 560 |
+
},
|
| 561 |
+
"model.layers.33.mlp.experts.gate_proj": {
|
| 562 |
+
"group_size": 32,
|
| 563 |
+
"bits": 4,
|
| 564 |
+
"mode": "mxfp4"
|
| 565 |
+
},
|
| 566 |
+
"model.layers.33.mlp.experts.up_proj": {
|
| 567 |
+
"group_size": 32,
|
| 568 |
+
"bits": 4,
|
| 569 |
+
"mode": "mxfp4"
|
| 570 |
+
},
|
| 571 |
+
"model.layers.33.mlp.experts.down_proj": {
|
| 572 |
+
"group_size": 32,
|
| 573 |
+
"bits": 4,
|
| 574 |
+
"mode": "mxfp4"
|
| 575 |
+
},
|
| 576 |
+
"model.layers.34.mlp.experts.gate_proj": {
|
| 577 |
+
"group_size": 32,
|
| 578 |
+
"bits": 4,
|
| 579 |
+
"mode": "mxfp4"
|
| 580 |
+
},
|
| 581 |
+
"model.layers.34.mlp.experts.up_proj": {
|
| 582 |
+
"group_size": 32,
|
| 583 |
+
"bits": 4,
|
| 584 |
+
"mode": "mxfp4"
|
| 585 |
+
},
|
| 586 |
+
"model.layers.34.mlp.experts.down_proj": {
|
| 587 |
+
"group_size": 32,
|
| 588 |
+
"bits": 4,
|
| 589 |
+
"mode": "mxfp4"
|
| 590 |
+
},
|
| 591 |
+
"model.layers.35.mlp.experts.gate_proj": {
|
| 592 |
+
"group_size": 32,
|
| 593 |
+
"bits": 4,
|
| 594 |
+
"mode": "mxfp4"
|
| 595 |
+
},
|
| 596 |
+
"model.layers.35.mlp.experts.up_proj": {
|
| 597 |
+
"group_size": 32,
|
| 598 |
+
"bits": 4,
|
| 599 |
+
"mode": "mxfp4"
|
| 600 |
+
},
|
| 601 |
+
"model.layers.35.mlp.experts.down_proj": {
|
| 602 |
+
"group_size": 32,
|
| 603 |
+
"bits": 4,
|
| 604 |
+
"mode": "mxfp4"
|
| 605 |
+
}
|
| 606 |
+
},
|
| 607 |
+
"rms_norm_eps": 1e-05,
|
| 608 |
+
"rope_scaling": {
|
| 609 |
+
"beta_fast": 32.0,
|
| 610 |
+
"beta_slow": 1.0,
|
| 611 |
+
"factor": 32.0,
|
| 612 |
+
"original_max_position_embeddings": 4096,
|
| 613 |
+
"rope_type": "yarn",
|
| 614 |
+
"truncate": false
|
| 615 |
+
},
|
| 616 |
+
"rope_theta": 150000,
|
| 617 |
+
"router_aux_loss_coef": 0.9,
|
| 618 |
+
"sliding_window": 128,
|
| 619 |
+
"swiglu_limit": 7.0,
|
| 620 |
+
"tie_word_embeddings": false,
|
| 621 |
+
"transformers_version": "4.55.0.dev0",
|
| 622 |
+
"use_cache": true,
|
| 623 |
+
"vocab_size": 201088,
|
| 624 |
+
"quantization": {
|
| 625 |
+
"group_size": 64,
|
| 626 |
+
"bits": 4,
|
| 627 |
+
"mode": "affine",
|
| 628 |
+
"model.layers.0.mlp.experts.gate_proj": {
|
| 629 |
+
"group_size": 32,
|
| 630 |
+
"bits": 4,
|
| 631 |
+
"mode": "mxfp4"
|
| 632 |
+
},
|
| 633 |
+
"model.layers.0.mlp.experts.up_proj": {
|
| 634 |
+
"group_size": 32,
|
| 635 |
+
"bits": 4,
|
| 636 |
+
"mode": "mxfp4"
|
| 637 |
+
},
|
| 638 |
+
"model.layers.0.mlp.experts.down_proj": {
|
| 639 |
+
"group_size": 32,
|
| 640 |
+
"bits": 4,
|
| 641 |
+
"mode": "mxfp4"
|
| 642 |
+
},
|
| 643 |
+
"model.layers.1.mlp.experts.gate_proj": {
|
| 644 |
+
"group_size": 32,
|
| 645 |
+
"bits": 4,
|
| 646 |
+
"mode": "mxfp4"
|
| 647 |
+
},
|
| 648 |
+
"model.layers.1.mlp.experts.up_proj": {
|
| 649 |
+
"group_size": 32,
|
| 650 |
+
"bits": 4,
|
| 651 |
+
"mode": "mxfp4"
|
| 652 |
+
},
|
| 653 |
+
"model.layers.1.mlp.experts.down_proj": {
|
| 654 |
+
"group_size": 32,
|
| 655 |
+
"bits": 4,
|
| 656 |
+
"mode": "mxfp4"
|
| 657 |
+
},
|
| 658 |
+
"model.layers.2.mlp.experts.gate_proj": {
|
| 659 |
+
"group_size": 32,
|
| 660 |
+
"bits": 4,
|
| 661 |
+
"mode": "mxfp4"
|
| 662 |
+
},
|
| 663 |
+
"model.layers.2.mlp.experts.up_proj": {
|
| 664 |
+
"group_size": 32,
|
| 665 |
+
"bits": 4,
|
| 666 |
+
"mode": "mxfp4"
|
| 667 |
+
},
|
| 668 |
+
"model.layers.2.mlp.experts.down_proj": {
|
| 669 |
+
"group_size": 32,
|
| 670 |
+
"bits": 4,
|
| 671 |
+
"mode": "mxfp4"
|
| 672 |
+
},
|
| 673 |
+
"model.layers.3.mlp.experts.gate_proj": {
|
| 674 |
+
"group_size": 32,
|
| 675 |
+
"bits": 4,
|
| 676 |
+
"mode": "mxfp4"
|
| 677 |
+
},
|
| 678 |
+
"model.layers.3.mlp.experts.up_proj": {
|
| 679 |
+
"group_size": 32,
|
| 680 |
+
"bits": 4,
|
| 681 |
+
"mode": "mxfp4"
|
| 682 |
+
},
|
| 683 |
+
"model.layers.3.mlp.experts.down_proj": {
|
| 684 |
+
"group_size": 32,
|
| 685 |
+
"bits": 4,
|
| 686 |
+
"mode": "mxfp4"
|
| 687 |
+
},
|
| 688 |
+
"model.layers.4.mlp.experts.gate_proj": {
|
| 689 |
+
"group_size": 32,
|
| 690 |
+
"bits": 4,
|
| 691 |
+
"mode": "mxfp4"
|
| 692 |
+
},
|
| 693 |
+
"model.layers.4.mlp.experts.up_proj": {
|
| 694 |
+
"group_size": 32,
|
| 695 |
+
"bits": 4,
|
| 696 |
+
"mode": "mxfp4"
|
| 697 |
+
},
|
| 698 |
+
"model.layers.4.mlp.experts.down_proj": {
|
| 699 |
+
"group_size": 32,
|
| 700 |
+
"bits": 4,
|
| 701 |
+
"mode": "mxfp4"
|
| 702 |
+
},
|
| 703 |
+
"model.layers.5.mlp.experts.gate_proj": {
|
| 704 |
+
"group_size": 32,
|
| 705 |
+
"bits": 4,
|
| 706 |
+
"mode": "mxfp4"
|
| 707 |
+
},
|
| 708 |
+
"model.layers.5.mlp.experts.up_proj": {
|
| 709 |
+
"group_size": 32,
|
| 710 |
+
"bits": 4,
|
| 711 |
+
"mode": "mxfp4"
|
| 712 |
+
},
|
| 713 |
+
"model.layers.5.mlp.experts.down_proj": {
|
| 714 |
+
"group_size": 32,
|
| 715 |
+
"bits": 4,
|
| 716 |
+
"mode": "mxfp4"
|
| 717 |
+
},
|
| 718 |
+
"model.layers.6.mlp.experts.gate_proj": {
|
| 719 |
+
"group_size": 32,
|
| 720 |
+
"bits": 4,
|
| 721 |
+
"mode": "mxfp4"
|
| 722 |
+
},
|
| 723 |
+
"model.layers.6.mlp.experts.up_proj": {
|
| 724 |
+
"group_size": 32,
|
| 725 |
+
"bits": 4,
|
| 726 |
+
"mode": "mxfp4"
|
| 727 |
+
},
|
| 728 |
+
"model.layers.6.mlp.experts.down_proj": {
|
| 729 |
+
"group_size": 32,
|
| 730 |
+
"bits": 4,
|
| 731 |
+
"mode": "mxfp4"
|
| 732 |
+
},
|
| 733 |
+
"model.layers.7.mlp.experts.gate_proj": {
|
| 734 |
+
"group_size": 32,
|
| 735 |
+
"bits": 4,
|
| 736 |
+
"mode": "mxfp4"
|
| 737 |
+
},
|
| 738 |
+
"model.layers.7.mlp.experts.up_proj": {
|
| 739 |
+
"group_size": 32,
|
| 740 |
+
"bits": 4,
|
| 741 |
+
"mode": "mxfp4"
|
| 742 |
+
},
|
| 743 |
+
"model.layers.7.mlp.experts.down_proj": {
|
| 744 |
+
"group_size": 32,
|
| 745 |
+
"bits": 4,
|
| 746 |
+
"mode": "mxfp4"
|
| 747 |
+
},
|
| 748 |
+
"model.layers.8.mlp.experts.gate_proj": {
|
| 749 |
+
"group_size": 32,
|
| 750 |
+
"bits": 4,
|
| 751 |
+
"mode": "mxfp4"
|
| 752 |
+
},
|
| 753 |
+
"model.layers.8.mlp.experts.up_proj": {
|
| 754 |
+
"group_size": 32,
|
| 755 |
+
"bits": 4,
|
| 756 |
+
"mode": "mxfp4"
|
| 757 |
+
},
|
| 758 |
+
"model.layers.8.mlp.experts.down_proj": {
|
| 759 |
+
"group_size": 32,
|
| 760 |
+
"bits": 4,
|
| 761 |
+
"mode": "mxfp4"
|
| 762 |
+
},
|
| 763 |
+
"model.layers.9.mlp.experts.gate_proj": {
|
| 764 |
+
"group_size": 32,
|
| 765 |
+
"bits": 4,
|
| 766 |
+
"mode": "mxfp4"
|
| 767 |
+
},
|
| 768 |
+
"model.layers.9.mlp.experts.up_proj": {
|
| 769 |
+
"group_size": 32,
|
| 770 |
+
"bits": 4,
|
| 771 |
+
"mode": "mxfp4"
|
| 772 |
+
},
|
| 773 |
+
"model.layers.9.mlp.experts.down_proj": {
|
| 774 |
+
"group_size": 32,
|
| 775 |
+
"bits": 4,
|
| 776 |
+
"mode": "mxfp4"
|
| 777 |
+
},
|
| 778 |
+
"model.layers.10.mlp.experts.gate_proj": {
|
| 779 |
+
"group_size": 32,
|
| 780 |
+
"bits": 4,
|
| 781 |
+
"mode": "mxfp4"
|
| 782 |
+
},
|
| 783 |
+
"model.layers.10.mlp.experts.up_proj": {
|
| 784 |
+
"group_size": 32,
|
| 785 |
+
"bits": 4,
|
| 786 |
+
"mode": "mxfp4"
|
| 787 |
+
},
|
| 788 |
+
"model.layers.10.mlp.experts.down_proj": {
|
| 789 |
+
"group_size": 32,
|
| 790 |
+
"bits": 4,
|
| 791 |
+
"mode": "mxfp4"
|
| 792 |
+
},
|
| 793 |
+
"model.layers.11.mlp.experts.gate_proj": {
|
| 794 |
+
"group_size": 32,
|
| 795 |
+
"bits": 4,
|
| 796 |
+
"mode": "mxfp4"
|
| 797 |
+
},
|
| 798 |
+
"model.layers.11.mlp.experts.up_proj": {
|
| 799 |
+
"group_size": 32,
|
| 800 |
+
"bits": 4,
|
| 801 |
+
"mode": "mxfp4"
|
| 802 |
+
},
|
| 803 |
+
"model.layers.11.mlp.experts.down_proj": {
|
| 804 |
+
"group_size": 32,
|
| 805 |
+
"bits": 4,
|
| 806 |
+
"mode": "mxfp4"
|
| 807 |
+
},
|
| 808 |
+
"model.layers.12.mlp.experts.gate_proj": {
|
| 809 |
+
"group_size": 32,
|
| 810 |
+
"bits": 4,
|
| 811 |
+
"mode": "mxfp4"
|
| 812 |
+
},
|
| 813 |
+
"model.layers.12.mlp.experts.up_proj": {
|
| 814 |
+
"group_size": 32,
|
| 815 |
+
"bits": 4,
|
| 816 |
+
"mode": "mxfp4"
|
| 817 |
+
},
|
| 818 |
+
"model.layers.12.mlp.experts.down_proj": {
|
| 819 |
+
"group_size": 32,
|
| 820 |
+
"bits": 4,
|
| 821 |
+
"mode": "mxfp4"
|
| 822 |
+
},
|
| 823 |
+
"model.layers.13.mlp.experts.gate_proj": {
|
| 824 |
+
"group_size": 32,
|
| 825 |
+
"bits": 4,
|
| 826 |
+
"mode": "mxfp4"
|
| 827 |
+
},
|
| 828 |
+
"model.layers.13.mlp.experts.up_proj": {
|
| 829 |
+
"group_size": 32,
|
| 830 |
+
"bits": 4,
|
| 831 |
+
"mode": "mxfp4"
|
| 832 |
+
},
|
| 833 |
+
"model.layers.13.mlp.experts.down_proj": {
|
| 834 |
+
"group_size": 32,
|
| 835 |
+
"bits": 4,
|
| 836 |
+
"mode": "mxfp4"
|
| 837 |
+
},
|
| 838 |
+
"model.layers.14.mlp.experts.gate_proj": {
|
| 839 |
+
"group_size": 32,
|
| 840 |
+
"bits": 4,
|
| 841 |
+
"mode": "mxfp4"
|
| 842 |
+
},
|
| 843 |
+
"model.layers.14.mlp.experts.up_proj": {
|
| 844 |
+
"group_size": 32,
|
| 845 |
+
"bits": 4,
|
| 846 |
+
"mode": "mxfp4"
|
| 847 |
+
},
|
| 848 |
+
"model.layers.14.mlp.experts.down_proj": {
|
| 849 |
+
"group_size": 32,
|
| 850 |
+
"bits": 4,
|
| 851 |
+
"mode": "mxfp4"
|
| 852 |
+
},
|
| 853 |
+
"model.layers.15.mlp.experts.gate_proj": {
|
| 854 |
+
"group_size": 32,
|
| 855 |
+
"bits": 4,
|
| 856 |
+
"mode": "mxfp4"
|
| 857 |
+
},
|
| 858 |
+
"model.layers.15.mlp.experts.up_proj": {
|
| 859 |
+
"group_size": 32,
|
| 860 |
+
"bits": 4,
|
| 861 |
+
"mode": "mxfp4"
|
| 862 |
+
},
|
| 863 |
+
"model.layers.15.mlp.experts.down_proj": {
|
| 864 |
+
"group_size": 32,
|
| 865 |
+
"bits": 4,
|
| 866 |
+
"mode": "mxfp4"
|
| 867 |
+
},
|
| 868 |
+
"model.layers.16.mlp.experts.gate_proj": {
|
| 869 |
+
"group_size": 32,
|
| 870 |
+
"bits": 4,
|
| 871 |
+
"mode": "mxfp4"
|
| 872 |
+
},
|
| 873 |
+
"model.layers.16.mlp.experts.up_proj": {
|
| 874 |
+
"group_size": 32,
|
| 875 |
+
"bits": 4,
|
| 876 |
+
"mode": "mxfp4"
|
| 877 |
+
},
|
| 878 |
+
"model.layers.16.mlp.experts.down_proj": {
|
| 879 |
+
"group_size": 32,
|
| 880 |
+
"bits": 4,
|
| 881 |
+
"mode": "mxfp4"
|
| 882 |
+
},
|
| 883 |
+
"model.layers.17.mlp.experts.gate_proj": {
|
| 884 |
+
"group_size": 32,
|
| 885 |
+
"bits": 4,
|
| 886 |
+
"mode": "mxfp4"
|
| 887 |
+
},
|
| 888 |
+
"model.layers.17.mlp.experts.up_proj": {
|
| 889 |
+
"group_size": 32,
|
| 890 |
+
"bits": 4,
|
| 891 |
+
"mode": "mxfp4"
|
| 892 |
+
},
|
| 893 |
+
"model.layers.17.mlp.experts.down_proj": {
|
| 894 |
+
"group_size": 32,
|
| 895 |
+
"bits": 4,
|
| 896 |
+
"mode": "mxfp4"
|
| 897 |
+
},
|
| 898 |
+
"model.layers.18.mlp.experts.gate_proj": {
|
| 899 |
+
"group_size": 32,
|
| 900 |
+
"bits": 4,
|
| 901 |
+
"mode": "mxfp4"
|
| 902 |
+
},
|
| 903 |
+
"model.layers.18.mlp.experts.up_proj": {
|
| 904 |
+
"group_size": 32,
|
| 905 |
+
"bits": 4,
|
| 906 |
+
"mode": "mxfp4"
|
| 907 |
+
},
|
| 908 |
+
"model.layers.18.mlp.experts.down_proj": {
|
| 909 |
+
"group_size": 32,
|
| 910 |
+
"bits": 4,
|
| 911 |
+
"mode": "mxfp4"
|
| 912 |
+
},
|
| 913 |
+
"model.layers.19.mlp.experts.gate_proj": {
|
| 914 |
+
"group_size": 32,
|
| 915 |
+
"bits": 4,
|
| 916 |
+
"mode": "mxfp4"
|
| 917 |
+
},
|
| 918 |
+
"model.layers.19.mlp.experts.up_proj": {
|
| 919 |
+
"group_size": 32,
|
| 920 |
+
"bits": 4,
|
| 921 |
+
"mode": "mxfp4"
|
| 922 |
+
},
|
| 923 |
+
"model.layers.19.mlp.experts.down_proj": {
|
| 924 |
+
"group_size": 32,
|
| 925 |
+
"bits": 4,
|
| 926 |
+
"mode": "mxfp4"
|
| 927 |
+
},
|
| 928 |
+
"model.layers.20.mlp.experts.gate_proj": {
|
| 929 |
+
"group_size": 32,
|
| 930 |
+
"bits": 4,
|
| 931 |
+
"mode": "mxfp4"
|
| 932 |
+
},
|
| 933 |
+
"model.layers.20.mlp.experts.up_proj": {
|
| 934 |
+
"group_size": 32,
|
| 935 |
+
"bits": 4,
|
| 936 |
+
"mode": "mxfp4"
|
| 937 |
+
},
|
| 938 |
+
"model.layers.20.mlp.experts.down_proj": {
|
| 939 |
+
"group_size": 32,
|
| 940 |
+
"bits": 4,
|
| 941 |
+
"mode": "mxfp4"
|
| 942 |
+
},
|
| 943 |
+
"model.layers.21.mlp.experts.gate_proj": {
|
| 944 |
+
"group_size": 32,
|
| 945 |
+
"bits": 4,
|
| 946 |
+
"mode": "mxfp4"
|
| 947 |
+
},
|
| 948 |
+
"model.layers.21.mlp.experts.up_proj": {
|
| 949 |
+
"group_size": 32,
|
| 950 |
+
"bits": 4,
|
| 951 |
+
"mode": "mxfp4"
|
| 952 |
+
},
|
| 953 |
+
"model.layers.21.mlp.experts.down_proj": {
|
| 954 |
+
"group_size": 32,
|
| 955 |
+
"bits": 4,
|
| 956 |
+
"mode": "mxfp4"
|
| 957 |
+
},
|
| 958 |
+
"model.layers.22.mlp.experts.gate_proj": {
|
| 959 |
+
"group_size": 32,
|
| 960 |
+
"bits": 4,
|
| 961 |
+
"mode": "mxfp4"
|
| 962 |
+
},
|
| 963 |
+
"model.layers.22.mlp.experts.up_proj": {
|
| 964 |
+
"group_size": 32,
|
| 965 |
+
"bits": 4,
|
| 966 |
+
"mode": "mxfp4"
|
| 967 |
+
},
|
| 968 |
+
"model.layers.22.mlp.experts.down_proj": {
|
| 969 |
+
"group_size": 32,
|
| 970 |
+
"bits": 4,
|
| 971 |
+
"mode": "mxfp4"
|
| 972 |
+
},
|
| 973 |
+
"model.layers.23.mlp.experts.gate_proj": {
|
| 974 |
+
"group_size": 32,
|
| 975 |
+
"bits": 4,
|
| 976 |
+
"mode": "mxfp4"
|
| 977 |
+
},
|
| 978 |
+
"model.layers.23.mlp.experts.up_proj": {
|
| 979 |
+
"group_size": 32,
|
| 980 |
+
"bits": 4,
|
| 981 |
+
"mode": "mxfp4"
|
| 982 |
+
},
|
| 983 |
+
"model.layers.23.mlp.experts.down_proj": {
|
| 984 |
+
"group_size": 32,
|
| 985 |
+
"bits": 4,
|
| 986 |
+
"mode": "mxfp4"
|
| 987 |
+
},
|
| 988 |
+
"model.layers.24.mlp.experts.gate_proj": {
|
| 989 |
+
"group_size": 32,
|
| 990 |
+
"bits": 4,
|
| 991 |
+
"mode": "mxfp4"
|
| 992 |
+
},
|
| 993 |
+
"model.layers.24.mlp.experts.up_proj": {
|
| 994 |
+
"group_size": 32,
|
| 995 |
+
"bits": 4,
|
| 996 |
+
"mode": "mxfp4"
|
| 997 |
+
},
|
| 998 |
+
"model.layers.24.mlp.experts.down_proj": {
|
| 999 |
+
"group_size": 32,
|
| 1000 |
+
"bits": 4,
|
| 1001 |
+
"mode": "mxfp4"
|
| 1002 |
+
},
|
| 1003 |
+
"model.layers.25.mlp.experts.gate_proj": {
|
| 1004 |
+
"group_size": 32,
|
| 1005 |
+
"bits": 4,
|
| 1006 |
+
"mode": "mxfp4"
|
| 1007 |
+
},
|
| 1008 |
+
"model.layers.25.mlp.experts.up_proj": {
|
| 1009 |
+
"group_size": 32,
|
| 1010 |
+
"bits": 4,
|
| 1011 |
+
"mode": "mxfp4"
|
| 1012 |
+
},
|
| 1013 |
+
"model.layers.25.mlp.experts.down_proj": {
|
| 1014 |
+
"group_size": 32,
|
| 1015 |
+
"bits": 4,
|
| 1016 |
+
"mode": "mxfp4"
|
| 1017 |
+
},
|
| 1018 |
+
"model.layers.26.mlp.experts.gate_proj": {
|
| 1019 |
+
"group_size": 32,
|
| 1020 |
+
"bits": 4,
|
| 1021 |
+
"mode": "mxfp4"
|
| 1022 |
+
},
|
| 1023 |
+
"model.layers.26.mlp.experts.up_proj": {
|
| 1024 |
+
"group_size": 32,
|
| 1025 |
+
"bits": 4,
|
| 1026 |
+
"mode": "mxfp4"
|
| 1027 |
+
},
|
| 1028 |
+
"model.layers.26.mlp.experts.down_proj": {
|
| 1029 |
+
"group_size": 32,
|
| 1030 |
+
"bits": 4,
|
| 1031 |
+
"mode": "mxfp4"
|
| 1032 |
+
},
|
| 1033 |
+
"model.layers.27.mlp.experts.gate_proj": {
|
| 1034 |
+
"group_size": 32,
|
| 1035 |
+
"bits": 4,
|
| 1036 |
+
"mode": "mxfp4"
|
| 1037 |
+
},
|
| 1038 |
+
"model.layers.27.mlp.experts.up_proj": {
|
| 1039 |
+
"group_size": 32,
|
| 1040 |
+
"bits": 4,
|
| 1041 |
+
"mode": "mxfp4"
|
| 1042 |
+
},
|
| 1043 |
+
"model.layers.27.mlp.experts.down_proj": {
|
| 1044 |
+
"group_size": 32,
|
| 1045 |
+
"bits": 4,
|
| 1046 |
+
"mode": "mxfp4"
|
| 1047 |
+
},
|
| 1048 |
+
"model.layers.28.mlp.experts.gate_proj": {
|
| 1049 |
+
"group_size": 32,
|
| 1050 |
+
"bits": 4,
|
| 1051 |
+
"mode": "mxfp4"
|
| 1052 |
+
},
|
| 1053 |
+
"model.layers.28.mlp.experts.up_proj": {
|
| 1054 |
+
"group_size": 32,
|
| 1055 |
+
"bits": 4,
|
| 1056 |
+
"mode": "mxfp4"
|
| 1057 |
+
},
|
| 1058 |
+
"model.layers.28.mlp.experts.down_proj": {
|
| 1059 |
+
"group_size": 32,
|
| 1060 |
+
"bits": 4,
|
| 1061 |
+
"mode": "mxfp4"
|
| 1062 |
+
},
|
| 1063 |
+
"model.layers.29.mlp.experts.gate_proj": {
|
| 1064 |
+
"group_size": 32,
|
| 1065 |
+
"bits": 4,
|
| 1066 |
+
"mode": "mxfp4"
|
| 1067 |
+
},
|
| 1068 |
+
"model.layers.29.mlp.experts.up_proj": {
|
| 1069 |
+
"group_size": 32,
|
| 1070 |
+
"bits": 4,
|
| 1071 |
+
"mode": "mxfp4"
|
| 1072 |
+
},
|
| 1073 |
+
"model.layers.29.mlp.experts.down_proj": {
|
| 1074 |
+
"group_size": 32,
|
| 1075 |
+
"bits": 4,
|
| 1076 |
+
"mode": "mxfp4"
|
| 1077 |
+
},
|
| 1078 |
+
"model.layers.30.mlp.experts.gate_proj": {
|
| 1079 |
+
"group_size": 32,
|
| 1080 |
+
"bits": 4,
|
| 1081 |
+
"mode": "mxfp4"
|
| 1082 |
+
},
|
| 1083 |
+
"model.layers.30.mlp.experts.up_proj": {
|
| 1084 |
+
"group_size": 32,
|
| 1085 |
+
"bits": 4,
|
| 1086 |
+
"mode": "mxfp4"
|
| 1087 |
+
},
|
| 1088 |
+
"model.layers.30.mlp.experts.down_proj": {
|
| 1089 |
+
"group_size": 32,
|
| 1090 |
+
"bits": 4,
|
| 1091 |
+
"mode": "mxfp4"
|
| 1092 |
+
},
|
| 1093 |
+
"model.layers.31.mlp.experts.gate_proj": {
|
| 1094 |
+
"group_size": 32,
|
| 1095 |
+
"bits": 4,
|
| 1096 |
+
"mode": "mxfp4"
|
| 1097 |
+
},
|
| 1098 |
+
"model.layers.31.mlp.experts.up_proj": {
|
| 1099 |
+
"group_size": 32,
|
| 1100 |
+
"bits": 4,
|
| 1101 |
+
"mode": "mxfp4"
|
| 1102 |
+
},
|
| 1103 |
+
"model.layers.31.mlp.experts.down_proj": {
|
| 1104 |
+
"group_size": 32,
|
| 1105 |
+
"bits": 4,
|
| 1106 |
+
"mode": "mxfp4"
|
| 1107 |
+
},
|
| 1108 |
+
"model.layers.32.mlp.experts.gate_proj": {
|
| 1109 |
+
"group_size": 32,
|
| 1110 |
+
"bits": 4,
|
| 1111 |
+
"mode": "mxfp4"
|
| 1112 |
+
},
|
| 1113 |
+
"model.layers.32.mlp.experts.up_proj": {
|
| 1114 |
+
"group_size": 32,
|
| 1115 |
+
"bits": 4,
|
| 1116 |
+
"mode": "mxfp4"
|
| 1117 |
+
},
|
| 1118 |
+
"model.layers.32.mlp.experts.down_proj": {
|
| 1119 |
+
"group_size": 32,
|
| 1120 |
+
"bits": 4,
|
| 1121 |
+
"mode": "mxfp4"
|
| 1122 |
+
},
|
| 1123 |
+
"model.layers.33.mlp.experts.gate_proj": {
|
| 1124 |
+
"group_size": 32,
|
| 1125 |
+
"bits": 4,
|
| 1126 |
+
"mode": "mxfp4"
|
| 1127 |
+
},
|
| 1128 |
+
"model.layers.33.mlp.experts.up_proj": {
|
| 1129 |
+
"group_size": 32,
|
| 1130 |
+
"bits": 4,
|
| 1131 |
+
"mode": "mxfp4"
|
| 1132 |
+
},
|
| 1133 |
+
"model.layers.33.mlp.experts.down_proj": {
|
| 1134 |
+
"group_size": 32,
|
| 1135 |
+
"bits": 4,
|
| 1136 |
+
"mode": "mxfp4"
|
| 1137 |
+
},
|
| 1138 |
+
"model.layers.34.mlp.experts.gate_proj": {
|
| 1139 |
+
"group_size": 32,
|
| 1140 |
+
"bits": 4,
|
| 1141 |
+
"mode": "mxfp4"
|
| 1142 |
+
},
|
| 1143 |
+
"model.layers.34.mlp.experts.up_proj": {
|
| 1144 |
+
"group_size": 32,
|
| 1145 |
+
"bits": 4,
|
| 1146 |
+
"mode": "mxfp4"
|
| 1147 |
+
},
|
| 1148 |
+
"model.layers.34.mlp.experts.down_proj": {
|
| 1149 |
+
"group_size": 32,
|
| 1150 |
+
"bits": 4,
|
| 1151 |
+
"mode": "mxfp4"
|
| 1152 |
+
},
|
| 1153 |
+
"model.layers.35.mlp.experts.gate_proj": {
|
| 1154 |
+
"group_size": 32,
|
| 1155 |
+
"bits": 4,
|
| 1156 |
+
"mode": "mxfp4"
|
| 1157 |
+
},
|
| 1158 |
+
"model.layers.35.mlp.experts.up_proj": {
|
| 1159 |
+
"group_size": 32,
|
| 1160 |
+
"bits": 4,
|
| 1161 |
+
"mode": "mxfp4"
|
| 1162 |
+
},
|
| 1163 |
+
"model.layers.35.mlp.experts.down_proj": {
|
| 1164 |
+
"group_size": 32,
|
| 1165 |
+
"bits": 4,
|
| 1166 |
+
"mode": "mxfp4"
|
| 1167 |
+
}
|
| 1168 |
+
}
|
| 1169 |
+
}
|
config.json.bak-before-mxfp4-expert-overrides
ADDED
|
@@ -0,0 +1,89 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"architectures": [
|
| 3 |
+
"GptOssForCausalLM"
|
| 4 |
+
],
|
| 5 |
+
"attention_bias": true,
|
| 6 |
+
"attention_dropout": 0.0,
|
| 7 |
+
"eos_token_id": 200002,
|
| 8 |
+
"experts_per_token": 4,
|
| 9 |
+
"head_dim": 64,
|
| 10 |
+
"hidden_act": "silu",
|
| 11 |
+
"hidden_size": 2880,
|
| 12 |
+
"initial_context_length": 4096,
|
| 13 |
+
"initializer_range": 0.02,
|
| 14 |
+
"intermediate_size": 2880,
|
| 15 |
+
"layer_types": [
|
| 16 |
+
"sliding_attention",
|
| 17 |
+
"full_attention",
|
| 18 |
+
"sliding_attention",
|
| 19 |
+
"full_attention",
|
| 20 |
+
"sliding_attention",
|
| 21 |
+
"full_attention",
|
| 22 |
+
"sliding_attention",
|
| 23 |
+
"full_attention",
|
| 24 |
+
"sliding_attention",
|
| 25 |
+
"full_attention",
|
| 26 |
+
"sliding_attention",
|
| 27 |
+
"full_attention",
|
| 28 |
+
"sliding_attention",
|
| 29 |
+
"full_attention",
|
| 30 |
+
"sliding_attention",
|
| 31 |
+
"full_attention",
|
| 32 |
+
"sliding_attention",
|
| 33 |
+
"full_attention",
|
| 34 |
+
"sliding_attention",
|
| 35 |
+
"full_attention",
|
| 36 |
+
"sliding_attention",
|
| 37 |
+
"full_attention",
|
| 38 |
+
"sliding_attention",
|
| 39 |
+
"full_attention",
|
| 40 |
+
"sliding_attention",
|
| 41 |
+
"full_attention",
|
| 42 |
+
"sliding_attention",
|
| 43 |
+
"full_attention",
|
| 44 |
+
"sliding_attention",
|
| 45 |
+
"full_attention",
|
| 46 |
+
"sliding_attention",
|
| 47 |
+
"full_attention",
|
| 48 |
+
"sliding_attention",
|
| 49 |
+
"full_attention",
|
| 50 |
+
"sliding_attention",
|
| 51 |
+
"full_attention"
|
| 52 |
+
],
|
| 53 |
+
"max_position_embeddings": 131072,
|
| 54 |
+
"model_type": "gpt_oss",
|
| 55 |
+
"num_attention_heads": 64,
|
| 56 |
+
"num_experts_per_tok": 4,
|
| 57 |
+
"num_hidden_layers": 36,
|
| 58 |
+
"num_key_value_heads": 8,
|
| 59 |
+
"num_local_experts": 128,
|
| 60 |
+
"output_router_logits": false,
|
| 61 |
+
"pad_token_id": 199999,
|
| 62 |
+
"quantization_config": {
|
| 63 |
+
"group_size": 64,
|
| 64 |
+
"bits": 4,
|
| 65 |
+
"mode": "affine"
|
| 66 |
+
},
|
| 67 |
+
"rms_norm_eps": 1e-05,
|
| 68 |
+
"rope_scaling": {
|
| 69 |
+
"beta_fast": 32.0,
|
| 70 |
+
"beta_slow": 1.0,
|
| 71 |
+
"factor": 32.0,
|
| 72 |
+
"original_max_position_embeddings": 4096,
|
| 73 |
+
"rope_type": "yarn",
|
| 74 |
+
"truncate": false
|
| 75 |
+
},
|
| 76 |
+
"rope_theta": 150000,
|
| 77 |
+
"router_aux_loss_coef": 0.9,
|
| 78 |
+
"sliding_window": 128,
|
| 79 |
+
"swiglu_limit": 7.0,
|
| 80 |
+
"tie_word_embeddings": false,
|
| 81 |
+
"transformers_version": "4.55.0.dev0",
|
| 82 |
+
"use_cache": true,
|
| 83 |
+
"vocab_size": 201088,
|
| 84 |
+
"quantization": {
|
| 85 |
+
"group_size": 64,
|
| 86 |
+
"bits": 4,
|
| 87 |
+
"mode": "affine"
|
| 88 |
+
}
|
| 89 |
+
}
|
generation_config.json
ADDED
|
@@ -0,0 +1,11 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"bos_token_id": 199998,
|
| 3 |
+
"do_sample": true,
|
| 4 |
+
"eos_token_id": [
|
| 5 |
+
200002,
|
| 6 |
+
199999,
|
| 7 |
+
200012
|
| 8 |
+
],
|
| 9 |
+
"pad_token_id": 199999,
|
| 10 |
+
"transformers_version": "4.55.0.dev0"
|
| 11 |
+
}
|
model-00001-of-00013.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:5391a679ac1f4af4b6732bb9220e05a026a123b89cfd4f0a443227f84d593cdf
|
| 3 |
+
size 5132545624
|
model-00002-of-00013.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:2db83424c492cc7ea7162cff1359a3732014ff0a6f77195bb805796ca95c6854
|
| 3 |
+
size 5079554083
|
model-00003-of-00013.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:7b7876adb7a22bc0ffd5087ce6d55dc7b28bcee4fe591e3c66b9190ce952fe9c
|
| 3 |
+
size 5129166685
|
model-00004-of-00013.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:2f8fe4b6f8b33851421c7647387608be1163dd1661efcd32317f67c5a8754b20
|
| 3 |
+
size 5112731811
|
model-00005-of-00013.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:f83cb553bd787069634fe0ed6f697b837bba7119e3d6c62eca7e45182fea3977
|
| 3 |
+
size 5129166602
|
model-00006-of-00013.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:2240b7682e6bb22be63911e7fb82a39405fb05d81e1b1394629e9caee20de425
|
| 3 |
+
size 5181734550
|
model-00007-of-00013.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:b7b1f8db8bde507181220d9cedc31a9f3c2a9f3a5cbda263238db843ffc0cf2a
|
| 3 |
+
size 5079554089
|
model-00008-of-00013.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:0daf03a9f7304a762f115c2d486a4308b0c84a5546e5e1377708a81ff5c4aeec
|
| 3 |
+
size 5179510738
|
model-00009-of-00013.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:3f7a3fcb36effcc9b9cb9928e01969816b87a84fa282637c41454c3adead8992
|
| 3 |
+
size 5079554083
|
model-00010-of-00013.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:d6e6a371c40b21db8bdd31e9d3988aaf761b212c8c95134d52cdb40bf7b48e76
|
| 3 |
+
size 5129166689
|
model-00011-of-00013.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:7da49a5264d7c19e13aecb204694f922c6984912036231c607437a0b4833d9fc
|
| 3 |
+
size 5251331328
|
model-00012-of-00013.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:f3a109a365bdaba2db9a61c41268b671ef9522ab7a494941db66ee7bda6a80eb
|
| 3 |
+
size 5129166661
|
model-00013-of-00013.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:ce0e3538e1c394b243f4a588e95fb14f17a2296dab3a4260ef3f42c7092e1412
|
| 3 |
+
size 597197190
|
model.safetensors.index.json
ADDED
|
@@ -0,0 +1,1094 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"metadata": {
|
| 3 |
+
"total_size": 62210380133
|
| 4 |
+
},
|
| 5 |
+
"weight_map": {
|
| 6 |
+
"lm_head.biases": "model-00011-of-00013.safetensors",
|
| 7 |
+
"lm_head.scales": "model-00011-of-00013.safetensors",
|
| 8 |
+
"lm_head.weight": "model-00011-of-00013.safetensors",
|
| 9 |
+
"model.embed_tokens.biases": "model-00011-of-00013.safetensors",
|
| 10 |
+
"model.embed_tokens.scales": "model-00011-of-00013.safetensors",
|
| 11 |
+
"model.embed_tokens.weight": "model-00011-of-00013.safetensors",
|
| 12 |
+
"model.layers.0.input_layernorm.weight": "model-00008-of-00013.safetensors",
|
| 13 |
+
"model.layers.0.mlp.experts.down_proj.bias": "model-00008-of-00013.safetensors",
|
| 14 |
+
"model.layers.0.mlp.experts.down_proj.scales": "model-00008-of-00013.safetensors",
|
| 15 |
+
"model.layers.0.mlp.experts.down_proj.weight": "model-00008-of-00013.safetensors",
|
| 16 |
+
"model.layers.0.mlp.experts.gate_proj.bias": "model-00008-of-00013.safetensors",
|
| 17 |
+
"model.layers.0.mlp.experts.gate_proj.scales": "model-00008-of-00013.safetensors",
|
| 18 |
+
"model.layers.0.mlp.experts.gate_proj.weight": "model-00008-of-00013.safetensors",
|
| 19 |
+
"model.layers.0.mlp.experts.up_proj.bias": "model-00008-of-00013.safetensors",
|
| 20 |
+
"model.layers.0.mlp.experts.up_proj.scales": "model-00008-of-00013.safetensors",
|
| 21 |
+
"model.layers.0.mlp.experts.up_proj.weight": "model-00008-of-00013.safetensors",
|
| 22 |
+
"model.layers.0.mlp.router.bias": "model-00008-of-00013.safetensors",
|
| 23 |
+
"model.layers.0.mlp.router.weight": "model-00008-of-00013.safetensors",
|
| 24 |
+
"model.layers.0.post_attention_layernorm.weight": "model-00008-of-00013.safetensors",
|
| 25 |
+
"model.layers.0.self_attn.k_proj.bias": "model-00008-of-00013.safetensors",
|
| 26 |
+
"model.layers.0.self_attn.k_proj.biases": "model-00008-of-00013.safetensors",
|
| 27 |
+
"model.layers.0.self_attn.k_proj.scales": "model-00008-of-00013.safetensors",
|
| 28 |
+
"model.layers.0.self_attn.k_proj.weight": "model-00008-of-00013.safetensors",
|
| 29 |
+
"model.layers.0.self_attn.o_proj.bias": "model-00008-of-00013.safetensors",
|
| 30 |
+
"model.layers.0.self_attn.o_proj.biases": "model-00008-of-00013.safetensors",
|
| 31 |
+
"model.layers.0.self_attn.o_proj.scales": "model-00008-of-00013.safetensors",
|
| 32 |
+
"model.layers.0.self_attn.o_proj.weight": "model-00008-of-00013.safetensors",
|
| 33 |
+
"model.layers.0.self_attn.q_proj.bias": "model-00008-of-00013.safetensors",
|
| 34 |
+
"model.layers.0.self_attn.q_proj.biases": "model-00008-of-00013.safetensors",
|
| 35 |
+
"model.layers.0.self_attn.q_proj.scales": "model-00008-of-00013.safetensors",
|
| 36 |
+
"model.layers.0.self_attn.q_proj.weight": "model-00008-of-00013.safetensors",
|
| 37 |
+
"model.layers.0.self_attn.sinks": "model-00008-of-00013.safetensors",
|
| 38 |
+
"model.layers.0.self_attn.v_proj.bias": "model-00008-of-00013.safetensors",
|
| 39 |
+
"model.layers.0.self_attn.v_proj.biases": "model-00008-of-00013.safetensors",
|
| 40 |
+
"model.layers.0.self_attn.v_proj.scales": "model-00008-of-00013.safetensors",
|
| 41 |
+
"model.layers.0.self_attn.v_proj.weight": "model-00008-of-00013.safetensors",
|
| 42 |
+
"model.layers.1.input_layernorm.weight": "model-00008-of-00013.safetensors",
|
| 43 |
+
"model.layers.1.mlp.experts.down_proj.bias": "model-00009-of-00013.safetensors",
|
| 44 |
+
"model.layers.1.mlp.experts.down_proj.scales": "model-00009-of-00013.safetensors",
|
| 45 |
+
"model.layers.1.mlp.experts.down_proj.weight": "model-00009-of-00013.safetensors",
|
| 46 |
+
"model.layers.1.mlp.experts.gate_proj.bias": "model-00008-of-00013.safetensors",
|
| 47 |
+
"model.layers.1.mlp.experts.gate_proj.scales": "model-00009-of-00013.safetensors",
|
| 48 |
+
"model.layers.1.mlp.experts.gate_proj.weight": "model-00009-of-00013.safetensors",
|
| 49 |
+
"model.layers.1.mlp.experts.up_proj.bias": "model-00008-of-00013.safetensors",
|
| 50 |
+
"model.layers.1.mlp.experts.up_proj.scales": "model-00009-of-00013.safetensors",
|
| 51 |
+
"model.layers.1.mlp.experts.up_proj.weight": "model-00009-of-00013.safetensors",
|
| 52 |
+
"model.layers.1.mlp.router.bias": "model-00008-of-00013.safetensors",
|
| 53 |
+
"model.layers.1.mlp.router.weight": "model-00008-of-00013.safetensors",
|
| 54 |
+
"model.layers.1.post_attention_layernorm.weight": "model-00009-of-00013.safetensors",
|
| 55 |
+
"model.layers.1.self_attn.k_proj.bias": "model-00008-of-00013.safetensors",
|
| 56 |
+
"model.layers.1.self_attn.k_proj.biases": "model-00008-of-00013.safetensors",
|
| 57 |
+
"model.layers.1.self_attn.k_proj.scales": "model-00008-of-00013.safetensors",
|
| 58 |
+
"model.layers.1.self_attn.k_proj.weight": "model-00008-of-00013.safetensors",
|
| 59 |
+
"model.layers.1.self_attn.o_proj.bias": "model-00008-of-00013.safetensors",
|
| 60 |
+
"model.layers.1.self_attn.o_proj.biases": "model-00008-of-00013.safetensors",
|
| 61 |
+
"model.layers.1.self_attn.o_proj.scales": "model-00008-of-00013.safetensors",
|
| 62 |
+
"model.layers.1.self_attn.o_proj.weight": "model-00008-of-00013.safetensors",
|
| 63 |
+
"model.layers.1.self_attn.q_proj.bias": "model-00008-of-00013.safetensors",
|
| 64 |
+
"model.layers.1.self_attn.q_proj.biases": "model-00008-of-00013.safetensors",
|
| 65 |
+
"model.layers.1.self_attn.q_proj.scales": "model-00008-of-00013.safetensors",
|
| 66 |
+
"model.layers.1.self_attn.q_proj.weight": "model-00008-of-00013.safetensors",
|
| 67 |
+
"model.layers.1.self_attn.sinks": "model-00008-of-00013.safetensors",
|
| 68 |
+
"model.layers.1.self_attn.v_proj.bias": "model-00008-of-00013.safetensors",
|
| 69 |
+
"model.layers.1.self_attn.v_proj.biases": "model-00008-of-00013.safetensors",
|
| 70 |
+
"model.layers.1.self_attn.v_proj.scales": "model-00008-of-00013.safetensors",
|
| 71 |
+
"model.layers.1.self_attn.v_proj.weight": "model-00008-of-00013.safetensors",
|
| 72 |
+
"model.layers.10.input_layernorm.weight": "model-00009-of-00013.safetensors",
|
| 73 |
+
"model.layers.10.mlp.experts.down_proj.bias": "model-00009-of-00013.safetensors",
|
| 74 |
+
"model.layers.10.mlp.experts.down_proj.scales": "model-00009-of-00013.safetensors",
|
| 75 |
+
"model.layers.10.mlp.experts.down_proj.weight": "model-00009-of-00013.safetensors",
|
| 76 |
+
"model.layers.10.mlp.experts.gate_proj.bias": "model-00009-of-00013.safetensors",
|
| 77 |
+
"model.layers.10.mlp.experts.gate_proj.scales": "model-00010-of-00013.safetensors",
|
| 78 |
+
"model.layers.10.mlp.experts.gate_proj.weight": "model-00009-of-00013.safetensors",
|
| 79 |
+
"model.layers.10.mlp.experts.up_proj.bias": "model-00009-of-00013.safetensors",
|
| 80 |
+
"model.layers.10.mlp.experts.up_proj.scales": "model-00010-of-00013.safetensors",
|
| 81 |
+
"model.layers.10.mlp.experts.up_proj.weight": "model-00009-of-00013.safetensors",
|
| 82 |
+
"model.layers.10.mlp.router.bias": "model-00009-of-00013.safetensors",
|
| 83 |
+
"model.layers.10.mlp.router.weight": "model-00009-of-00013.safetensors",
|
| 84 |
+
"model.layers.10.post_attention_layernorm.weight": "model-00009-of-00013.safetensors",
|
| 85 |
+
"model.layers.10.self_attn.k_proj.bias": "model-00009-of-00013.safetensors",
|
| 86 |
+
"model.layers.10.self_attn.k_proj.biases": "model-00009-of-00013.safetensors",
|
| 87 |
+
"model.layers.10.self_attn.k_proj.scales": "model-00009-of-00013.safetensors",
|
| 88 |
+
"model.layers.10.self_attn.k_proj.weight": "model-00009-of-00013.safetensors",
|
| 89 |
+
"model.layers.10.self_attn.o_proj.bias": "model-00009-of-00013.safetensors",
|
| 90 |
+
"model.layers.10.self_attn.o_proj.biases": "model-00009-of-00013.safetensors",
|
| 91 |
+
"model.layers.10.self_attn.o_proj.scales": "model-00009-of-00013.safetensors",
|
| 92 |
+
"model.layers.10.self_attn.o_proj.weight": "model-00009-of-00013.safetensors",
|
| 93 |
+
"model.layers.10.self_attn.q_proj.bias": "model-00009-of-00013.safetensors",
|
| 94 |
+
"model.layers.10.self_attn.q_proj.biases": "model-00009-of-00013.safetensors",
|
| 95 |
+
"model.layers.10.self_attn.q_proj.scales": "model-00009-of-00013.safetensors",
|
| 96 |
+
"model.layers.10.self_attn.q_proj.weight": "model-00009-of-00013.safetensors",
|
| 97 |
+
"model.layers.10.self_attn.sinks": "model-00009-of-00013.safetensors",
|
| 98 |
+
"model.layers.10.self_attn.v_proj.bias": "model-00009-of-00013.safetensors",
|
| 99 |
+
"model.layers.10.self_attn.v_proj.biases": "model-00009-of-00013.safetensors",
|
| 100 |
+
"model.layers.10.self_attn.v_proj.scales": "model-00009-of-00013.safetensors",
|
| 101 |
+
"model.layers.10.self_attn.v_proj.weight": "model-00009-of-00013.safetensors",
|
| 102 |
+
"model.layers.11.input_layernorm.weight": "model-00009-of-00013.safetensors",
|
| 103 |
+
"model.layers.11.mlp.experts.down_proj.bias": "model-00009-of-00013.safetensors",
|
| 104 |
+
"model.layers.11.mlp.experts.down_proj.scales": "model-00010-of-00013.safetensors",
|
| 105 |
+
"model.layers.11.mlp.experts.down_proj.weight": "model-00010-of-00013.safetensors",
|
| 106 |
+
"model.layers.11.mlp.experts.gate_proj.bias": "model-00009-of-00013.safetensors",
|
| 107 |
+
"model.layers.11.mlp.experts.gate_proj.scales": "model-00010-of-00013.safetensors",
|
| 108 |
+
"model.layers.11.mlp.experts.gate_proj.weight": "model-00010-of-00013.safetensors",
|
| 109 |
+
"model.layers.11.mlp.experts.up_proj.bias": "model-00009-of-00013.safetensors",
|
| 110 |
+
"model.layers.11.mlp.experts.up_proj.scales": "model-00010-of-00013.safetensors",
|
| 111 |
+
"model.layers.11.mlp.experts.up_proj.weight": "model-00010-of-00013.safetensors",
|
| 112 |
+
"model.layers.11.mlp.router.bias": "model-00009-of-00013.safetensors",
|
| 113 |
+
"model.layers.11.mlp.router.weight": "model-00009-of-00013.safetensors",
|
| 114 |
+
"model.layers.11.post_attention_layernorm.weight": "model-00010-of-00013.safetensors",
|
| 115 |
+
"model.layers.11.self_attn.k_proj.bias": "model-00009-of-00013.safetensors",
|
| 116 |
+
"model.layers.11.self_attn.k_proj.biases": "model-00009-of-00013.safetensors",
|
| 117 |
+
"model.layers.11.self_attn.k_proj.scales": "model-00009-of-00013.safetensors",
|
| 118 |
+
"model.layers.11.self_attn.k_proj.weight": "model-00009-of-00013.safetensors",
|
| 119 |
+
"model.layers.11.self_attn.o_proj.bias": "model-00009-of-00013.safetensors",
|
| 120 |
+
"model.layers.11.self_attn.o_proj.biases": "model-00009-of-00013.safetensors",
|
| 121 |
+
"model.layers.11.self_attn.o_proj.scales": "model-00009-of-00013.safetensors",
|
| 122 |
+
"model.layers.11.self_attn.o_proj.weight": "model-00009-of-00013.safetensors",
|
| 123 |
+
"model.layers.11.self_attn.q_proj.bias": "model-00009-of-00013.safetensors",
|
| 124 |
+
"model.layers.11.self_attn.q_proj.biases": "model-00009-of-00013.safetensors",
|
| 125 |
+
"model.layers.11.self_attn.q_proj.scales": "model-00009-of-00013.safetensors",
|
| 126 |
+
"model.layers.11.self_attn.q_proj.weight": "model-00009-of-00013.safetensors",
|
| 127 |
+
"model.layers.11.self_attn.sinks": "model-00009-of-00013.safetensors",
|
| 128 |
+
"model.layers.11.self_attn.v_proj.bias": "model-00009-of-00013.safetensors",
|
| 129 |
+
"model.layers.11.self_attn.v_proj.biases": "model-00009-of-00013.safetensors",
|
| 130 |
+
"model.layers.11.self_attn.v_proj.scales": "model-00009-of-00013.safetensors",
|
| 131 |
+
"model.layers.11.self_attn.v_proj.weight": "model-00009-of-00013.safetensors",
|
| 132 |
+
"model.layers.12.input_layernorm.weight": "model-00010-of-00013.safetensors",
|
| 133 |
+
"model.layers.12.mlp.experts.down_proj.bias": "model-00010-of-00013.safetensors",
|
| 134 |
+
"model.layers.12.mlp.experts.down_proj.scales": "model-00010-of-00013.safetensors",
|
| 135 |
+
"model.layers.12.mlp.experts.down_proj.weight": "model-00010-of-00013.safetensors",
|
| 136 |
+
"model.layers.12.mlp.experts.gate_proj.bias": "model-00010-of-00013.safetensors",
|
| 137 |
+
"model.layers.12.mlp.experts.gate_proj.scales": "model-00010-of-00013.safetensors",
|
| 138 |
+
"model.layers.12.mlp.experts.gate_proj.weight": "model-00010-of-00013.safetensors",
|
| 139 |
+
"model.layers.12.mlp.experts.up_proj.bias": "model-00010-of-00013.safetensors",
|
| 140 |
+
"model.layers.12.mlp.experts.up_proj.scales": "model-00010-of-00013.safetensors",
|
| 141 |
+
"model.layers.12.mlp.experts.up_proj.weight": "model-00010-of-00013.safetensors",
|
| 142 |
+
"model.layers.12.mlp.router.bias": "model-00010-of-00013.safetensors",
|
| 143 |
+
"model.layers.12.mlp.router.weight": "model-00010-of-00013.safetensors",
|
| 144 |
+
"model.layers.12.post_attention_layernorm.weight": "model-00010-of-00013.safetensors",
|
| 145 |
+
"model.layers.12.self_attn.k_proj.bias": "model-00010-of-00013.safetensors",
|
| 146 |
+
"model.layers.12.self_attn.k_proj.biases": "model-00010-of-00013.safetensors",
|
| 147 |
+
"model.layers.12.self_attn.k_proj.scales": "model-00010-of-00013.safetensors",
|
| 148 |
+
"model.layers.12.self_attn.k_proj.weight": "model-00010-of-00013.safetensors",
|
| 149 |
+
"model.layers.12.self_attn.o_proj.bias": "model-00010-of-00013.safetensors",
|
| 150 |
+
"model.layers.12.self_attn.o_proj.biases": "model-00010-of-00013.safetensors",
|
| 151 |
+
"model.layers.12.self_attn.o_proj.scales": "model-00010-of-00013.safetensors",
|
| 152 |
+
"model.layers.12.self_attn.o_proj.weight": "model-00010-of-00013.safetensors",
|
| 153 |
+
"model.layers.12.self_attn.q_proj.bias": "model-00010-of-00013.safetensors",
|
| 154 |
+
"model.layers.12.self_attn.q_proj.biases": "model-00010-of-00013.safetensors",
|
| 155 |
+
"model.layers.12.self_attn.q_proj.scales": "model-00010-of-00013.safetensors",
|
| 156 |
+
"model.layers.12.self_attn.q_proj.weight": "model-00010-of-00013.safetensors",
|
| 157 |
+
"model.layers.12.self_attn.sinks": "model-00010-of-00013.safetensors",
|
| 158 |
+
"model.layers.12.self_attn.v_proj.bias": "model-00010-of-00013.safetensors",
|
| 159 |
+
"model.layers.12.self_attn.v_proj.biases": "model-00010-of-00013.safetensors",
|
| 160 |
+
"model.layers.12.self_attn.v_proj.scales": "model-00010-of-00013.safetensors",
|
| 161 |
+
"model.layers.12.self_attn.v_proj.weight": "model-00010-of-00013.safetensors",
|
| 162 |
+
"model.layers.13.input_layernorm.weight": "model-00010-of-00013.safetensors",
|
| 163 |
+
"model.layers.13.mlp.experts.down_proj.bias": "model-00010-of-00013.safetensors",
|
| 164 |
+
"model.layers.13.mlp.experts.down_proj.scales": "model-00010-of-00013.safetensors",
|
| 165 |
+
"model.layers.13.mlp.experts.down_proj.weight": "model-00010-of-00013.safetensors",
|
| 166 |
+
"model.layers.13.mlp.experts.gate_proj.bias": "model-00010-of-00013.safetensors",
|
| 167 |
+
"model.layers.13.mlp.experts.gate_proj.scales": "model-00011-of-00013.safetensors",
|
| 168 |
+
"model.layers.13.mlp.experts.gate_proj.weight": "model-00010-of-00013.safetensors",
|
| 169 |
+
"model.layers.13.mlp.experts.up_proj.bias": "model-00010-of-00013.safetensors",
|
| 170 |
+
"model.layers.13.mlp.experts.up_proj.scales": "model-00011-of-00013.safetensors",
|
| 171 |
+
"model.layers.13.mlp.experts.up_proj.weight": "model-00010-of-00013.safetensors",
|
| 172 |
+
"model.layers.13.mlp.router.bias": "model-00010-of-00013.safetensors",
|
| 173 |
+
"model.layers.13.mlp.router.weight": "model-00010-of-00013.safetensors",
|
| 174 |
+
"model.layers.13.post_attention_layernorm.weight": "model-00010-of-00013.safetensors",
|
| 175 |
+
"model.layers.13.self_attn.k_proj.bias": "model-00010-of-00013.safetensors",
|
| 176 |
+
"model.layers.13.self_attn.k_proj.biases": "model-00010-of-00013.safetensors",
|
| 177 |
+
"model.layers.13.self_attn.k_proj.scales": "model-00010-of-00013.safetensors",
|
| 178 |
+
"model.layers.13.self_attn.k_proj.weight": "model-00010-of-00013.safetensors",
|
| 179 |
+
"model.layers.13.self_attn.o_proj.bias": "model-00010-of-00013.safetensors",
|
| 180 |
+
"model.layers.13.self_attn.o_proj.biases": "model-00010-of-00013.safetensors",
|
| 181 |
+
"model.layers.13.self_attn.o_proj.scales": "model-00010-of-00013.safetensors",
|
| 182 |
+
"model.layers.13.self_attn.o_proj.weight": "model-00010-of-00013.safetensors",
|
| 183 |
+
"model.layers.13.self_attn.q_proj.bias": "model-00010-of-00013.safetensors",
|
| 184 |
+
"model.layers.13.self_attn.q_proj.biases": "model-00010-of-00013.safetensors",
|
| 185 |
+
"model.layers.13.self_attn.q_proj.scales": "model-00010-of-00013.safetensors",
|
| 186 |
+
"model.layers.13.self_attn.q_proj.weight": "model-00010-of-00013.safetensors",
|
| 187 |
+
"model.layers.13.self_attn.sinks": "model-00010-of-00013.safetensors",
|
| 188 |
+
"model.layers.13.self_attn.v_proj.bias": "model-00010-of-00013.safetensors",
|
| 189 |
+
"model.layers.13.self_attn.v_proj.biases": "model-00010-of-00013.safetensors",
|
| 190 |
+
"model.layers.13.self_attn.v_proj.scales": "model-00010-of-00013.safetensors",
|
| 191 |
+
"model.layers.13.self_attn.v_proj.weight": "model-00010-of-00013.safetensors",
|
| 192 |
+
"model.layers.14.input_layernorm.weight": "model-00010-of-00013.safetensors",
|
| 193 |
+
"model.layers.14.mlp.experts.down_proj.bias": "model-00006-of-00013.safetensors",
|
| 194 |
+
"model.layers.14.mlp.experts.down_proj.scales": "model-00007-of-00013.safetensors",
|
| 195 |
+
"model.layers.14.mlp.experts.down_proj.weight": "model-00006-of-00013.safetensors",
|
| 196 |
+
"model.layers.14.mlp.experts.gate_proj.bias": "model-00010-of-00013.safetensors",
|
| 197 |
+
"model.layers.14.mlp.experts.gate_proj.scales": "model-00007-of-00013.safetensors",
|
| 198 |
+
"model.layers.14.mlp.experts.gate_proj.weight": "model-00007-of-00013.safetensors",
|
| 199 |
+
"model.layers.14.mlp.experts.up_proj.bias": "model-00010-of-00013.safetensors",
|
| 200 |
+
"model.layers.14.mlp.experts.up_proj.scales": "model-00007-of-00013.safetensors",
|
| 201 |
+
"model.layers.14.mlp.experts.up_proj.weight": "model-00007-of-00013.safetensors",
|
| 202 |
+
"model.layers.14.mlp.router.bias": "model-00010-of-00013.safetensors",
|
| 203 |
+
"model.layers.14.mlp.router.weight": "model-00010-of-00013.safetensors",
|
| 204 |
+
"model.layers.14.post_attention_layernorm.weight": "model-00006-of-00013.safetensors",
|
| 205 |
+
"model.layers.14.self_attn.k_proj.bias": "model-00010-of-00013.safetensors",
|
| 206 |
+
"model.layers.14.self_attn.k_proj.biases": "model-00010-of-00013.safetensors",
|
| 207 |
+
"model.layers.14.self_attn.k_proj.scales": "model-00010-of-00013.safetensors",
|
| 208 |
+
"model.layers.14.self_attn.k_proj.weight": "model-00010-of-00013.safetensors",
|
| 209 |
+
"model.layers.14.self_attn.o_proj.bias": "model-00010-of-00013.safetensors",
|
| 210 |
+
"model.layers.14.self_attn.o_proj.biases": "model-00010-of-00013.safetensors",
|
| 211 |
+
"model.layers.14.self_attn.o_proj.scales": "model-00010-of-00013.safetensors",
|
| 212 |
+
"model.layers.14.self_attn.o_proj.weight": "model-00010-of-00013.safetensors",
|
| 213 |
+
"model.layers.14.self_attn.q_proj.bias": "model-00010-of-00013.safetensors",
|
| 214 |
+
"model.layers.14.self_attn.q_proj.biases": "model-00010-of-00013.safetensors",
|
| 215 |
+
"model.layers.14.self_attn.q_proj.scales": "model-00010-of-00013.safetensors",
|
| 216 |
+
"model.layers.14.self_attn.q_proj.weight": "model-00010-of-00013.safetensors",
|
| 217 |
+
"model.layers.14.self_attn.sinks": "model-00010-of-00013.safetensors",
|
| 218 |
+
"model.layers.14.self_attn.v_proj.bias": "model-00010-of-00013.safetensors",
|
| 219 |
+
"model.layers.14.self_attn.v_proj.biases": "model-00010-of-00013.safetensors",
|
| 220 |
+
"model.layers.14.self_attn.v_proj.scales": "model-00010-of-00013.safetensors",
|
| 221 |
+
"model.layers.14.self_attn.v_proj.weight": "model-00010-of-00013.safetensors",
|
| 222 |
+
"model.layers.15.input_layernorm.weight": "model-00006-of-00013.safetensors",
|
| 223 |
+
"model.layers.15.mlp.experts.down_proj.bias": "model-00006-of-00013.safetensors",
|
| 224 |
+
"model.layers.15.mlp.experts.down_proj.scales": "model-00007-of-00013.safetensors",
|
| 225 |
+
"model.layers.15.mlp.experts.down_proj.weight": "model-00007-of-00013.safetensors",
|
| 226 |
+
"model.layers.15.mlp.experts.gate_proj.bias": "model-00006-of-00013.safetensors",
|
| 227 |
+
"model.layers.15.mlp.experts.gate_proj.scales": "model-00007-of-00013.safetensors",
|
| 228 |
+
"model.layers.15.mlp.experts.gate_proj.weight": "model-00007-of-00013.safetensors",
|
| 229 |
+
"model.layers.15.mlp.experts.up_proj.bias": "model-00006-of-00013.safetensors",
|
| 230 |
+
"model.layers.15.mlp.experts.up_proj.scales": "model-00007-of-00013.safetensors",
|
| 231 |
+
"model.layers.15.mlp.experts.up_proj.weight": "model-00007-of-00013.safetensors",
|
| 232 |
+
"model.layers.15.mlp.router.bias": "model-00006-of-00013.safetensors",
|
| 233 |
+
"model.layers.15.mlp.router.weight": "model-00006-of-00013.safetensors",
|
| 234 |
+
"model.layers.15.post_attention_layernorm.weight": "model-00006-of-00013.safetensors",
|
| 235 |
+
"model.layers.15.self_attn.k_proj.bias": "model-00006-of-00013.safetensors",
|
| 236 |
+
"model.layers.15.self_attn.k_proj.biases": "model-00006-of-00013.safetensors",
|
| 237 |
+
"model.layers.15.self_attn.k_proj.scales": "model-00006-of-00013.safetensors",
|
| 238 |
+
"model.layers.15.self_attn.k_proj.weight": "model-00006-of-00013.safetensors",
|
| 239 |
+
"model.layers.15.self_attn.o_proj.bias": "model-00006-of-00013.safetensors",
|
| 240 |
+
"model.layers.15.self_attn.o_proj.biases": "model-00006-of-00013.safetensors",
|
| 241 |
+
"model.layers.15.self_attn.o_proj.scales": "model-00006-of-00013.safetensors",
|
| 242 |
+
"model.layers.15.self_attn.o_proj.weight": "model-00006-of-00013.safetensors",
|
| 243 |
+
"model.layers.15.self_attn.q_proj.bias": "model-00006-of-00013.safetensors",
|
| 244 |
+
"model.layers.15.self_attn.q_proj.biases": "model-00006-of-00013.safetensors",
|
| 245 |
+
"model.layers.15.self_attn.q_proj.scales": "model-00006-of-00013.safetensors",
|
| 246 |
+
"model.layers.15.self_attn.q_proj.weight": "model-00006-of-00013.safetensors",
|
| 247 |
+
"model.layers.15.self_attn.sinks": "model-00006-of-00013.safetensors",
|
| 248 |
+
"model.layers.15.self_attn.v_proj.bias": "model-00006-of-00013.safetensors",
|
| 249 |
+
"model.layers.15.self_attn.v_proj.biases": "model-00006-of-00013.safetensors",
|
| 250 |
+
"model.layers.15.self_attn.v_proj.scales": "model-00006-of-00013.safetensors",
|
| 251 |
+
"model.layers.15.self_attn.v_proj.weight": "model-00006-of-00013.safetensors",
|
| 252 |
+
"model.layers.16.input_layernorm.weight": "model-00006-of-00013.safetensors",
|
| 253 |
+
"model.layers.16.mlp.experts.down_proj.bias": "model-00007-of-00013.safetensors",
|
| 254 |
+
"model.layers.16.mlp.experts.down_proj.scales": "model-00007-of-00013.safetensors",
|
| 255 |
+
"model.layers.16.mlp.experts.down_proj.weight": "model-00007-of-00013.safetensors",
|
| 256 |
+
"model.layers.16.mlp.experts.gate_proj.bias": "model-00006-of-00013.safetensors",
|
| 257 |
+
"model.layers.16.mlp.experts.gate_proj.scales": "model-00008-of-00013.safetensors",
|
| 258 |
+
"model.layers.16.mlp.experts.gate_proj.weight": "model-00007-of-00013.safetensors",
|
| 259 |
+
"model.layers.16.mlp.experts.up_proj.bias": "model-00006-of-00013.safetensors",
|
| 260 |
+
"model.layers.16.mlp.experts.up_proj.scales": "model-00008-of-00013.safetensors",
|
| 261 |
+
"model.layers.16.mlp.experts.up_proj.weight": "model-00007-of-00013.safetensors",
|
| 262 |
+
"model.layers.16.mlp.router.bias": "model-00006-of-00013.safetensors",
|
| 263 |
+
"model.layers.16.mlp.router.weight": "model-00006-of-00013.safetensors",
|
| 264 |
+
"model.layers.16.post_attention_layernorm.weight": "model-00007-of-00013.safetensors",
|
| 265 |
+
"model.layers.16.self_attn.k_proj.bias": "model-00006-of-00013.safetensors",
|
| 266 |
+
"model.layers.16.self_attn.k_proj.biases": "model-00006-of-00013.safetensors",
|
| 267 |
+
"model.layers.16.self_attn.k_proj.scales": "model-00006-of-00013.safetensors",
|
| 268 |
+
"model.layers.16.self_attn.k_proj.weight": "model-00006-of-00013.safetensors",
|
| 269 |
+
"model.layers.16.self_attn.o_proj.bias": "model-00006-of-00013.safetensors",
|
| 270 |
+
"model.layers.16.self_attn.o_proj.biases": "model-00006-of-00013.safetensors",
|
| 271 |
+
"model.layers.16.self_attn.o_proj.scales": "model-00006-of-00013.safetensors",
|
| 272 |
+
"model.layers.16.self_attn.o_proj.weight": "model-00006-of-00013.safetensors",
|
| 273 |
+
"model.layers.16.self_attn.q_proj.bias": "model-00006-of-00013.safetensors",
|
| 274 |
+
"model.layers.16.self_attn.q_proj.biases": "model-00006-of-00013.safetensors",
|
| 275 |
+
"model.layers.16.self_attn.q_proj.scales": "model-00006-of-00013.safetensors",
|
| 276 |
+
"model.layers.16.self_attn.q_proj.weight": "model-00006-of-00013.safetensors",
|
| 277 |
+
"model.layers.16.self_attn.sinks": "model-00006-of-00013.safetensors",
|
| 278 |
+
"model.layers.16.self_attn.v_proj.bias": "model-00006-of-00013.safetensors",
|
| 279 |
+
"model.layers.16.self_attn.v_proj.biases": "model-00006-of-00013.safetensors",
|
| 280 |
+
"model.layers.16.self_attn.v_proj.scales": "model-00006-of-00013.safetensors",
|
| 281 |
+
"model.layers.16.self_attn.v_proj.weight": "model-00006-of-00013.safetensors",
|
| 282 |
+
"model.layers.17.input_layernorm.weight": "model-00007-of-00013.safetensors",
|
| 283 |
+
"model.layers.17.mlp.experts.down_proj.bias": "model-00007-of-00013.safetensors",
|
| 284 |
+
"model.layers.17.mlp.experts.down_proj.scales": "model-00008-of-00013.safetensors",
|
| 285 |
+
"model.layers.17.mlp.experts.down_proj.weight": "model-00008-of-00013.safetensors",
|
| 286 |
+
"model.layers.17.mlp.experts.gate_proj.bias": "model-00007-of-00013.safetensors",
|
| 287 |
+
"model.layers.17.mlp.experts.gate_proj.scales": "model-00008-of-00013.safetensors",
|
| 288 |
+
"model.layers.17.mlp.experts.gate_proj.weight": "model-00008-of-00013.safetensors",
|
| 289 |
+
"model.layers.17.mlp.experts.up_proj.bias": "model-00007-of-00013.safetensors",
|
| 290 |
+
"model.layers.17.mlp.experts.up_proj.scales": "model-00008-of-00013.safetensors",
|
| 291 |
+
"model.layers.17.mlp.experts.up_proj.weight": "model-00008-of-00013.safetensors",
|
| 292 |
+
"model.layers.17.mlp.router.bias": "model-00007-of-00013.safetensors",
|
| 293 |
+
"model.layers.17.mlp.router.weight": "model-00007-of-00013.safetensors",
|
| 294 |
+
"model.layers.17.post_attention_layernorm.weight": "model-00007-of-00013.safetensors",
|
| 295 |
+
"model.layers.17.self_attn.k_proj.bias": "model-00007-of-00013.safetensors",
|
| 296 |
+
"model.layers.17.self_attn.k_proj.biases": "model-00007-of-00013.safetensors",
|
| 297 |
+
"model.layers.17.self_attn.k_proj.scales": "model-00007-of-00013.safetensors",
|
| 298 |
+
"model.layers.17.self_attn.k_proj.weight": "model-00007-of-00013.safetensors",
|
| 299 |
+
"model.layers.17.self_attn.o_proj.bias": "model-00007-of-00013.safetensors",
|
| 300 |
+
"model.layers.17.self_attn.o_proj.biases": "model-00007-of-00013.safetensors",
|
| 301 |
+
"model.layers.17.self_attn.o_proj.scales": "model-00007-of-00013.safetensors",
|
| 302 |
+
"model.layers.17.self_attn.o_proj.weight": "model-00007-of-00013.safetensors",
|
| 303 |
+
"model.layers.17.self_attn.q_proj.bias": "model-00007-of-00013.safetensors",
|
| 304 |
+
"model.layers.17.self_attn.q_proj.biases": "model-00007-of-00013.safetensors",
|
| 305 |
+
"model.layers.17.self_attn.q_proj.scales": "model-00007-of-00013.safetensors",
|
| 306 |
+
"model.layers.17.self_attn.q_proj.weight": "model-00007-of-00013.safetensors",
|
| 307 |
+
"model.layers.17.self_attn.sinks": "model-00007-of-00013.safetensors",
|
| 308 |
+
"model.layers.17.self_attn.v_proj.bias": "model-00007-of-00013.safetensors",
|
| 309 |
+
"model.layers.17.self_attn.v_proj.biases": "model-00007-of-00013.safetensors",
|
| 310 |
+
"model.layers.17.self_attn.v_proj.scales": "model-00007-of-00013.safetensors",
|
| 311 |
+
"model.layers.17.self_attn.v_proj.weight": "model-00007-of-00013.safetensors",
|
| 312 |
+
"model.layers.18.input_layernorm.weight": "model-00007-of-00013.safetensors",
|
| 313 |
+
"model.layers.18.mlp.experts.down_proj.bias": "model-00007-of-00013.safetensors",
|
| 314 |
+
"model.layers.18.mlp.experts.down_proj.scales": "model-00009-of-00013.safetensors",
|
| 315 |
+
"model.layers.18.mlp.experts.down_proj.weight": "model-00008-of-00013.safetensors",
|
| 316 |
+
"model.layers.18.mlp.experts.gate_proj.bias": "model-00007-of-00013.safetensors",
|
| 317 |
+
"model.layers.18.mlp.experts.gate_proj.scales": "model-00008-of-00013.safetensors",
|
| 318 |
+
"model.layers.18.mlp.experts.gate_proj.weight": "model-00008-of-00013.safetensors",
|
| 319 |
+
"model.layers.18.mlp.experts.up_proj.bias": "model-00007-of-00013.safetensors",
|
| 320 |
+
"model.layers.18.mlp.experts.up_proj.scales": "model-00008-of-00013.safetensors",
|
| 321 |
+
"model.layers.18.mlp.experts.up_proj.weight": "model-00008-of-00013.safetensors",
|
| 322 |
+
"model.layers.18.mlp.router.bias": "model-00007-of-00013.safetensors",
|
| 323 |
+
"model.layers.18.mlp.router.weight": "model-00007-of-00013.safetensors",
|
| 324 |
+
"model.layers.18.post_attention_layernorm.weight": "model-00008-of-00013.safetensors",
|
| 325 |
+
"model.layers.18.self_attn.k_proj.bias": "model-00007-of-00013.safetensors",
|
| 326 |
+
"model.layers.18.self_attn.k_proj.biases": "model-00007-of-00013.safetensors",
|
| 327 |
+
"model.layers.18.self_attn.k_proj.scales": "model-00007-of-00013.safetensors",
|
| 328 |
+
"model.layers.18.self_attn.k_proj.weight": "model-00007-of-00013.safetensors",
|
| 329 |
+
"model.layers.18.self_attn.o_proj.bias": "model-00007-of-00013.safetensors",
|
| 330 |
+
"model.layers.18.self_attn.o_proj.biases": "model-00007-of-00013.safetensors",
|
| 331 |
+
"model.layers.18.self_attn.o_proj.scales": "model-00007-of-00013.safetensors",
|
| 332 |
+
"model.layers.18.self_attn.o_proj.weight": "model-00007-of-00013.safetensors",
|
| 333 |
+
"model.layers.18.self_attn.q_proj.bias": "model-00007-of-00013.safetensors",
|
| 334 |
+
"model.layers.18.self_attn.q_proj.biases": "model-00007-of-00013.safetensors",
|
| 335 |
+
"model.layers.18.self_attn.q_proj.scales": "model-00007-of-00013.safetensors",
|
| 336 |
+
"model.layers.18.self_attn.q_proj.weight": "model-00007-of-00013.safetensors",
|
| 337 |
+
"model.layers.18.self_attn.sinks": "model-00007-of-00013.safetensors",
|
| 338 |
+
"model.layers.18.self_attn.v_proj.bias": "model-00007-of-00013.safetensors",
|
| 339 |
+
"model.layers.18.self_attn.v_proj.biases": "model-00007-of-00013.safetensors",
|
| 340 |
+
"model.layers.18.self_attn.v_proj.scales": "model-00007-of-00013.safetensors",
|
| 341 |
+
"model.layers.18.self_attn.v_proj.weight": "model-00007-of-00013.safetensors",
|
| 342 |
+
"model.layers.19.input_layernorm.weight": "model-00008-of-00013.safetensors",
|
| 343 |
+
"model.layers.19.mlp.experts.down_proj.bias": "model-00008-of-00013.safetensors",
|
| 344 |
+
"model.layers.19.mlp.experts.down_proj.scales": "model-00009-of-00013.safetensors",
|
| 345 |
+
"model.layers.19.mlp.experts.down_proj.weight": "model-00009-of-00013.safetensors",
|
| 346 |
+
"model.layers.19.mlp.experts.gate_proj.bias": "model-00008-of-00013.safetensors",
|
| 347 |
+
"model.layers.19.mlp.experts.gate_proj.scales": "model-00009-of-00013.safetensors",
|
| 348 |
+
"model.layers.19.mlp.experts.gate_proj.weight": "model-00009-of-00013.safetensors",
|
| 349 |
+
"model.layers.19.mlp.experts.up_proj.bias": "model-00008-of-00013.safetensors",
|
| 350 |
+
"model.layers.19.mlp.experts.up_proj.scales": "model-00009-of-00013.safetensors",
|
| 351 |
+
"model.layers.19.mlp.experts.up_proj.weight": "model-00009-of-00013.safetensors",
|
| 352 |
+
"model.layers.19.mlp.router.bias": "model-00008-of-00013.safetensors",
|
| 353 |
+
"model.layers.19.mlp.router.weight": "model-00008-of-00013.safetensors",
|
| 354 |
+
"model.layers.19.post_attention_layernorm.weight": "model-00008-of-00013.safetensors",
|
| 355 |
+
"model.layers.19.self_attn.k_proj.bias": "model-00008-of-00013.safetensors",
|
| 356 |
+
"model.layers.19.self_attn.k_proj.biases": "model-00008-of-00013.safetensors",
|
| 357 |
+
"model.layers.19.self_attn.k_proj.scales": "model-00008-of-00013.safetensors",
|
| 358 |
+
"model.layers.19.self_attn.k_proj.weight": "model-00008-of-00013.safetensors",
|
| 359 |
+
"model.layers.19.self_attn.o_proj.bias": "model-00008-of-00013.safetensors",
|
| 360 |
+
"model.layers.19.self_attn.o_proj.biases": "model-00008-of-00013.safetensors",
|
| 361 |
+
"model.layers.19.self_attn.o_proj.scales": "model-00008-of-00013.safetensors",
|
| 362 |
+
"model.layers.19.self_attn.o_proj.weight": "model-00008-of-00013.safetensors",
|
| 363 |
+
"model.layers.19.self_attn.q_proj.bias": "model-00008-of-00013.safetensors",
|
| 364 |
+
"model.layers.19.self_attn.q_proj.biases": "model-00008-of-00013.safetensors",
|
| 365 |
+
"model.layers.19.self_attn.q_proj.scales": "model-00008-of-00013.safetensors",
|
| 366 |
+
"model.layers.19.self_attn.q_proj.weight": "model-00008-of-00013.safetensors",
|
| 367 |
+
"model.layers.19.self_attn.sinks": "model-00008-of-00013.safetensors",
|
| 368 |
+
"model.layers.19.self_attn.v_proj.bias": "model-00008-of-00013.safetensors",
|
| 369 |
+
"model.layers.19.self_attn.v_proj.biases": "model-00008-of-00013.safetensors",
|
| 370 |
+
"model.layers.19.self_attn.v_proj.scales": "model-00008-of-00013.safetensors",
|
| 371 |
+
"model.layers.19.self_attn.v_proj.weight": "model-00008-of-00013.safetensors",
|
| 372 |
+
"model.layers.2.input_layernorm.weight": "model-00008-of-00013.safetensors",
|
| 373 |
+
"model.layers.2.mlp.experts.down_proj.bias": "model-00002-of-00013.safetensors",
|
| 374 |
+
"model.layers.2.mlp.experts.down_proj.scales": "model-00002-of-00013.safetensors",
|
| 375 |
+
"model.layers.2.mlp.experts.down_proj.weight": "model-00002-of-00013.safetensors",
|
| 376 |
+
"model.layers.2.mlp.experts.gate_proj.bias": "model-00008-of-00013.safetensors",
|
| 377 |
+
"model.layers.2.mlp.experts.gate_proj.scales": "model-00003-of-00013.safetensors",
|
| 378 |
+
"model.layers.2.mlp.experts.gate_proj.weight": "model-00002-of-00013.safetensors",
|
| 379 |
+
"model.layers.2.mlp.experts.up_proj.bias": "model-00008-of-00013.safetensors",
|
| 380 |
+
"model.layers.2.mlp.experts.up_proj.scales": "model-00003-of-00013.safetensors",
|
| 381 |
+
"model.layers.2.mlp.experts.up_proj.weight": "model-00002-of-00013.safetensors",
|
| 382 |
+
"model.layers.2.mlp.router.bias": "model-00008-of-00013.safetensors",
|
| 383 |
+
"model.layers.2.mlp.router.weight": "model-00008-of-00013.safetensors",
|
| 384 |
+
"model.layers.2.post_attention_layernorm.weight": "model-00002-of-00013.safetensors",
|
| 385 |
+
"model.layers.2.self_attn.k_proj.bias": "model-00008-of-00013.safetensors",
|
| 386 |
+
"model.layers.2.self_attn.k_proj.biases": "model-00008-of-00013.safetensors",
|
| 387 |
+
"model.layers.2.self_attn.k_proj.scales": "model-00008-of-00013.safetensors",
|
| 388 |
+
"model.layers.2.self_attn.k_proj.weight": "model-00008-of-00013.safetensors",
|
| 389 |
+
"model.layers.2.self_attn.o_proj.bias": "model-00008-of-00013.safetensors",
|
| 390 |
+
"model.layers.2.self_attn.o_proj.biases": "model-00008-of-00013.safetensors",
|
| 391 |
+
"model.layers.2.self_attn.o_proj.scales": "model-00008-of-00013.safetensors",
|
| 392 |
+
"model.layers.2.self_attn.o_proj.weight": "model-00008-of-00013.safetensors",
|
| 393 |
+
"model.layers.2.self_attn.q_proj.bias": "model-00008-of-00013.safetensors",
|
| 394 |
+
"model.layers.2.self_attn.q_proj.biases": "model-00008-of-00013.safetensors",
|
| 395 |
+
"model.layers.2.self_attn.q_proj.scales": "model-00008-of-00013.safetensors",
|
| 396 |
+
"model.layers.2.self_attn.q_proj.weight": "model-00008-of-00013.safetensors",
|
| 397 |
+
"model.layers.2.self_attn.sinks": "model-00008-of-00013.safetensors",
|
| 398 |
+
"model.layers.2.self_attn.v_proj.bias": "model-00008-of-00013.safetensors",
|
| 399 |
+
"model.layers.2.self_attn.v_proj.biases": "model-00008-of-00013.safetensors",
|
| 400 |
+
"model.layers.2.self_attn.v_proj.scales": "model-00008-of-00013.safetensors",
|
| 401 |
+
"model.layers.2.self_attn.v_proj.weight": "model-00008-of-00013.safetensors",
|
| 402 |
+
"model.layers.20.input_layernorm.weight": "model-00002-of-00013.safetensors",
|
| 403 |
+
"model.layers.20.mlp.experts.down_proj.bias": "model-00002-of-00013.safetensors",
|
| 404 |
+
"model.layers.20.mlp.experts.down_proj.scales": "model-00003-of-00013.safetensors",
|
| 405 |
+
"model.layers.20.mlp.experts.down_proj.weight": "model-00003-of-00013.safetensors",
|
| 406 |
+
"model.layers.20.mlp.experts.gate_proj.bias": "model-00002-of-00013.safetensors",
|
| 407 |
+
"model.layers.20.mlp.experts.gate_proj.scales": "model-00003-of-00013.safetensors",
|
| 408 |
+
"model.layers.20.mlp.experts.gate_proj.weight": "model-00003-of-00013.safetensors",
|
| 409 |
+
"model.layers.20.mlp.experts.up_proj.bias": "model-00002-of-00013.safetensors",
|
| 410 |
+
"model.layers.20.mlp.experts.up_proj.scales": "model-00003-of-00013.safetensors",
|
| 411 |
+
"model.layers.20.mlp.experts.up_proj.weight": "model-00003-of-00013.safetensors",
|
| 412 |
+
"model.layers.20.mlp.router.bias": "model-00002-of-00013.safetensors",
|
| 413 |
+
"model.layers.20.mlp.router.weight": "model-00002-of-00013.safetensors",
|
| 414 |
+
"model.layers.20.post_attention_layernorm.weight": "model-00003-of-00013.safetensors",
|
| 415 |
+
"model.layers.20.self_attn.k_proj.bias": "model-00002-of-00013.safetensors",
|
| 416 |
+
"model.layers.20.self_attn.k_proj.biases": "model-00002-of-00013.safetensors",
|
| 417 |
+
"model.layers.20.self_attn.k_proj.scales": "model-00002-of-00013.safetensors",
|
| 418 |
+
"model.layers.20.self_attn.k_proj.weight": "model-00002-of-00013.safetensors",
|
| 419 |
+
"model.layers.20.self_attn.o_proj.bias": "model-00002-of-00013.safetensors",
|
| 420 |
+
"model.layers.20.self_attn.o_proj.biases": "model-00002-of-00013.safetensors",
|
| 421 |
+
"model.layers.20.self_attn.o_proj.scales": "model-00002-of-00013.safetensors",
|
| 422 |
+
"model.layers.20.self_attn.o_proj.weight": "model-00002-of-00013.safetensors",
|
| 423 |
+
"model.layers.20.self_attn.q_proj.bias": "model-00002-of-00013.safetensors",
|
| 424 |
+
"model.layers.20.self_attn.q_proj.biases": "model-00002-of-00013.safetensors",
|
| 425 |
+
"model.layers.20.self_attn.q_proj.scales": "model-00002-of-00013.safetensors",
|
| 426 |
+
"model.layers.20.self_attn.q_proj.weight": "model-00002-of-00013.safetensors",
|
| 427 |
+
"model.layers.20.self_attn.sinks": "model-00002-of-00013.safetensors",
|
| 428 |
+
"model.layers.20.self_attn.v_proj.bias": "model-00002-of-00013.safetensors",
|
| 429 |
+
"model.layers.20.self_attn.v_proj.biases": "model-00002-of-00013.safetensors",
|
| 430 |
+
"model.layers.20.self_attn.v_proj.scales": "model-00002-of-00013.safetensors",
|
| 431 |
+
"model.layers.20.self_attn.v_proj.weight": "model-00002-of-00013.safetensors",
|
| 432 |
+
"model.layers.21.input_layernorm.weight": "model-00003-of-00013.safetensors",
|
| 433 |
+
"model.layers.21.mlp.experts.down_proj.bias": "model-00003-of-00013.safetensors",
|
| 434 |
+
"model.layers.21.mlp.experts.down_proj.scales": "model-00003-of-00013.safetensors",
|
| 435 |
+
"model.layers.21.mlp.experts.down_proj.weight": "model-00003-of-00013.safetensors",
|
| 436 |
+
"model.layers.21.mlp.experts.gate_proj.bias": "model-00003-of-00013.safetensors",
|
| 437 |
+
"model.layers.21.mlp.experts.gate_proj.scales": "model-00004-of-00013.safetensors",
|
| 438 |
+
"model.layers.21.mlp.experts.gate_proj.weight": "model-00003-of-00013.safetensors",
|
| 439 |
+
"model.layers.21.mlp.experts.up_proj.bias": "model-00003-of-00013.safetensors",
|
| 440 |
+
"model.layers.21.mlp.experts.up_proj.scales": "model-00004-of-00013.safetensors",
|
| 441 |
+
"model.layers.21.mlp.experts.up_proj.weight": "model-00003-of-00013.safetensors",
|
| 442 |
+
"model.layers.21.mlp.router.bias": "model-00003-of-00013.safetensors",
|
| 443 |
+
"model.layers.21.mlp.router.weight": "model-00003-of-00013.safetensors",
|
| 444 |
+
"model.layers.21.post_attention_layernorm.weight": "model-00003-of-00013.safetensors",
|
| 445 |
+
"model.layers.21.self_attn.k_proj.bias": "model-00003-of-00013.safetensors",
|
| 446 |
+
"model.layers.21.self_attn.k_proj.biases": "model-00003-of-00013.safetensors",
|
| 447 |
+
"model.layers.21.self_attn.k_proj.scales": "model-00003-of-00013.safetensors",
|
| 448 |
+
"model.layers.21.self_attn.k_proj.weight": "model-00003-of-00013.safetensors",
|
| 449 |
+
"model.layers.21.self_attn.o_proj.bias": "model-00003-of-00013.safetensors",
|
| 450 |
+
"model.layers.21.self_attn.o_proj.biases": "model-00003-of-00013.safetensors",
|
| 451 |
+
"model.layers.21.self_attn.o_proj.scales": "model-00003-of-00013.safetensors",
|
| 452 |
+
"model.layers.21.self_attn.o_proj.weight": "model-00003-of-00013.safetensors",
|
| 453 |
+
"model.layers.21.self_attn.q_proj.bias": "model-00003-of-00013.safetensors",
|
| 454 |
+
"model.layers.21.self_attn.q_proj.biases": "model-00003-of-00013.safetensors",
|
| 455 |
+
"model.layers.21.self_attn.q_proj.scales": "model-00003-of-00013.safetensors",
|
| 456 |
+
"model.layers.21.self_attn.q_proj.weight": "model-00003-of-00013.safetensors",
|
| 457 |
+
"model.layers.21.self_attn.sinks": "model-00003-of-00013.safetensors",
|
| 458 |
+
"model.layers.21.self_attn.v_proj.bias": "model-00003-of-00013.safetensors",
|
| 459 |
+
"model.layers.21.self_attn.v_proj.biases": "model-00003-of-00013.safetensors",
|
| 460 |
+
"model.layers.21.self_attn.v_proj.scales": "model-00003-of-00013.safetensors",
|
| 461 |
+
"model.layers.21.self_attn.v_proj.weight": "model-00003-of-00013.safetensors",
|
| 462 |
+
"model.layers.22.input_layernorm.weight": "model-00003-of-00013.safetensors",
|
| 463 |
+
"model.layers.22.mlp.experts.down_proj.bias": "model-00003-of-00013.safetensors",
|
| 464 |
+
"model.layers.22.mlp.experts.down_proj.scales": "model-00004-of-00013.safetensors",
|
| 465 |
+
"model.layers.22.mlp.experts.down_proj.weight": "model-00004-of-00013.safetensors",
|
| 466 |
+
"model.layers.22.mlp.experts.gate_proj.bias": "model-00003-of-00013.safetensors",
|
| 467 |
+
"model.layers.22.mlp.experts.gate_proj.scales": "model-00004-of-00013.safetensors",
|
| 468 |
+
"model.layers.22.mlp.experts.gate_proj.weight": "model-00004-of-00013.safetensors",
|
| 469 |
+
"model.layers.22.mlp.experts.up_proj.bias": "model-00003-of-00013.safetensors",
|
| 470 |
+
"model.layers.22.mlp.experts.up_proj.scales": "model-00004-of-00013.safetensors",
|
| 471 |
+
"model.layers.22.mlp.experts.up_proj.weight": "model-00004-of-00013.safetensors",
|
| 472 |
+
"model.layers.22.mlp.router.bias": "model-00003-of-00013.safetensors",
|
| 473 |
+
"model.layers.22.mlp.router.weight": "model-00003-of-00013.safetensors",
|
| 474 |
+
"model.layers.22.post_attention_layernorm.weight": "model-00003-of-00013.safetensors",
|
| 475 |
+
"model.layers.22.self_attn.k_proj.bias": "model-00003-of-00013.safetensors",
|
| 476 |
+
"model.layers.22.self_attn.k_proj.biases": "model-00003-of-00013.safetensors",
|
| 477 |
+
"model.layers.22.self_attn.k_proj.scales": "model-00003-of-00013.safetensors",
|
| 478 |
+
"model.layers.22.self_attn.k_proj.weight": "model-00003-of-00013.safetensors",
|
| 479 |
+
"model.layers.22.self_attn.o_proj.bias": "model-00003-of-00013.safetensors",
|
| 480 |
+
"model.layers.22.self_attn.o_proj.biases": "model-00003-of-00013.safetensors",
|
| 481 |
+
"model.layers.22.self_attn.o_proj.scales": "model-00003-of-00013.safetensors",
|
| 482 |
+
"model.layers.22.self_attn.o_proj.weight": "model-00003-of-00013.safetensors",
|
| 483 |
+
"model.layers.22.self_attn.q_proj.bias": "model-00003-of-00013.safetensors",
|
| 484 |
+
"model.layers.22.self_attn.q_proj.biases": "model-00003-of-00013.safetensors",
|
| 485 |
+
"model.layers.22.self_attn.q_proj.scales": "model-00003-of-00013.safetensors",
|
| 486 |
+
"model.layers.22.self_attn.q_proj.weight": "model-00003-of-00013.safetensors",
|
| 487 |
+
"model.layers.22.self_attn.sinks": "model-00003-of-00013.safetensors",
|
| 488 |
+
"model.layers.22.self_attn.v_proj.bias": "model-00003-of-00013.safetensors",
|
| 489 |
+
"model.layers.22.self_attn.v_proj.biases": "model-00003-of-00013.safetensors",
|
| 490 |
+
"model.layers.22.self_attn.v_proj.scales": "model-00003-of-00013.safetensors",
|
| 491 |
+
"model.layers.22.self_attn.v_proj.weight": "model-00003-of-00013.safetensors",
|
| 492 |
+
"model.layers.23.input_layernorm.weight": "model-00003-of-00013.safetensors",
|
| 493 |
+
"model.layers.23.mlp.experts.down_proj.bias": "model-00004-of-00013.safetensors",
|
| 494 |
+
"model.layers.23.mlp.experts.down_proj.scales": "model-00004-of-00013.safetensors",
|
| 495 |
+
"model.layers.23.mlp.experts.down_proj.weight": "model-00004-of-00013.safetensors",
|
| 496 |
+
"model.layers.23.mlp.experts.gate_proj.bias": "model-00003-of-00013.safetensors",
|
| 497 |
+
"model.layers.23.mlp.experts.gate_proj.scales": "model-00004-of-00013.safetensors",
|
| 498 |
+
"model.layers.23.mlp.experts.gate_proj.weight": "model-00004-of-00013.safetensors",
|
| 499 |
+
"model.layers.23.mlp.experts.up_proj.bias": "model-00003-of-00013.safetensors",
|
| 500 |
+
"model.layers.23.mlp.experts.up_proj.scales": "model-00004-of-00013.safetensors",
|
| 501 |
+
"model.layers.23.mlp.experts.up_proj.weight": "model-00004-of-00013.safetensors",
|
| 502 |
+
"model.layers.23.mlp.router.bias": "model-00003-of-00013.safetensors",
|
| 503 |
+
"model.layers.23.mlp.router.weight": "model-00003-of-00013.safetensors",
|
| 504 |
+
"model.layers.23.post_attention_layernorm.weight": "model-00004-of-00013.safetensors",
|
| 505 |
+
"model.layers.23.self_attn.k_proj.bias": "model-00003-of-00013.safetensors",
|
| 506 |
+
"model.layers.23.self_attn.k_proj.biases": "model-00003-of-00013.safetensors",
|
| 507 |
+
"model.layers.23.self_attn.k_proj.scales": "model-00003-of-00013.safetensors",
|
| 508 |
+
"model.layers.23.self_attn.k_proj.weight": "model-00003-of-00013.safetensors",
|
| 509 |
+
"model.layers.23.self_attn.o_proj.bias": "model-00003-of-00013.safetensors",
|
| 510 |
+
"model.layers.23.self_attn.o_proj.biases": "model-00003-of-00013.safetensors",
|
| 511 |
+
"model.layers.23.self_attn.o_proj.scales": "model-00003-of-00013.safetensors",
|
| 512 |
+
"model.layers.23.self_attn.o_proj.weight": "model-00003-of-00013.safetensors",
|
| 513 |
+
"model.layers.23.self_attn.q_proj.bias": "model-00003-of-00013.safetensors",
|
| 514 |
+
"model.layers.23.self_attn.q_proj.biases": "model-00003-of-00013.safetensors",
|
| 515 |
+
"model.layers.23.self_attn.q_proj.scales": "model-00003-of-00013.safetensors",
|
| 516 |
+
"model.layers.23.self_attn.q_proj.weight": "model-00003-of-00013.safetensors",
|
| 517 |
+
"model.layers.23.self_attn.sinks": "model-00003-of-00013.safetensors",
|
| 518 |
+
"model.layers.23.self_attn.v_proj.bias": "model-00003-of-00013.safetensors",
|
| 519 |
+
"model.layers.23.self_attn.v_proj.biases": "model-00003-of-00013.safetensors",
|
| 520 |
+
"model.layers.23.self_attn.v_proj.scales": "model-00003-of-00013.safetensors",
|
| 521 |
+
"model.layers.23.self_attn.v_proj.weight": "model-00003-of-00013.safetensors",
|
| 522 |
+
"model.layers.24.input_layernorm.weight": "model-00004-of-00013.safetensors",
|
| 523 |
+
"model.layers.24.mlp.experts.down_proj.bias": "model-00004-of-00013.safetensors",
|
| 524 |
+
"model.layers.24.mlp.experts.down_proj.scales": "model-00004-of-00013.safetensors",
|
| 525 |
+
"model.layers.24.mlp.experts.down_proj.weight": "model-00004-of-00013.safetensors",
|
| 526 |
+
"model.layers.24.mlp.experts.gate_proj.bias": "model-00004-of-00013.safetensors",
|
| 527 |
+
"model.layers.24.mlp.experts.gate_proj.scales": "model-00005-of-00013.safetensors",
|
| 528 |
+
"model.layers.24.mlp.experts.gate_proj.weight": "model-00004-of-00013.safetensors",
|
| 529 |
+
"model.layers.24.mlp.experts.up_proj.bias": "model-00004-of-00013.safetensors",
|
| 530 |
+
"model.layers.24.mlp.experts.up_proj.scales": "model-00005-of-00013.safetensors",
|
| 531 |
+
"model.layers.24.mlp.experts.up_proj.weight": "model-00004-of-00013.safetensors",
|
| 532 |
+
"model.layers.24.mlp.router.bias": "model-00004-of-00013.safetensors",
|
| 533 |
+
"model.layers.24.mlp.router.weight": "model-00004-of-00013.safetensors",
|
| 534 |
+
"model.layers.24.post_attention_layernorm.weight": "model-00004-of-00013.safetensors",
|
| 535 |
+
"model.layers.24.self_attn.k_proj.bias": "model-00004-of-00013.safetensors",
|
| 536 |
+
"model.layers.24.self_attn.k_proj.biases": "model-00004-of-00013.safetensors",
|
| 537 |
+
"model.layers.24.self_attn.k_proj.scales": "model-00004-of-00013.safetensors",
|
| 538 |
+
"model.layers.24.self_attn.k_proj.weight": "model-00004-of-00013.safetensors",
|
| 539 |
+
"model.layers.24.self_attn.o_proj.bias": "model-00004-of-00013.safetensors",
|
| 540 |
+
"model.layers.24.self_attn.o_proj.biases": "model-00004-of-00013.safetensors",
|
| 541 |
+
"model.layers.24.self_attn.o_proj.scales": "model-00004-of-00013.safetensors",
|
| 542 |
+
"model.layers.24.self_attn.o_proj.weight": "model-00004-of-00013.safetensors",
|
| 543 |
+
"model.layers.24.self_attn.q_proj.bias": "model-00004-of-00013.safetensors",
|
| 544 |
+
"model.layers.24.self_attn.q_proj.biases": "model-00004-of-00013.safetensors",
|
| 545 |
+
"model.layers.24.self_attn.q_proj.scales": "model-00004-of-00013.safetensors",
|
| 546 |
+
"model.layers.24.self_attn.q_proj.weight": "model-00004-of-00013.safetensors",
|
| 547 |
+
"model.layers.24.self_attn.sinks": "model-00004-of-00013.safetensors",
|
| 548 |
+
"model.layers.24.self_attn.v_proj.bias": "model-00004-of-00013.safetensors",
|
| 549 |
+
"model.layers.24.self_attn.v_proj.biases": "model-00004-of-00013.safetensors",
|
| 550 |
+
"model.layers.24.self_attn.v_proj.scales": "model-00004-of-00013.safetensors",
|
| 551 |
+
"model.layers.24.self_attn.v_proj.weight": "model-00004-of-00013.safetensors",
|
| 552 |
+
"model.layers.25.input_layernorm.weight": "model-00004-of-00013.safetensors",
|
| 553 |
+
"model.layers.25.mlp.experts.down_proj.bias": "model-00001-of-00013.safetensors",
|
| 554 |
+
"model.layers.25.mlp.experts.down_proj.scales": "model-00001-of-00013.safetensors",
|
| 555 |
+
"model.layers.25.mlp.experts.down_proj.weight": "model-00001-of-00013.safetensors",
|
| 556 |
+
"model.layers.25.mlp.experts.gate_proj.bias": "model-00004-of-00013.safetensors",
|
| 557 |
+
"model.layers.25.mlp.experts.gate_proj.scales": "model-00001-of-00013.safetensors",
|
| 558 |
+
"model.layers.25.mlp.experts.gate_proj.weight": "model-00001-of-00013.safetensors",
|
| 559 |
+
"model.layers.25.mlp.experts.up_proj.bias": "model-00004-of-00013.safetensors",
|
| 560 |
+
"model.layers.25.mlp.experts.up_proj.scales": "model-00001-of-00013.safetensors",
|
| 561 |
+
"model.layers.25.mlp.experts.up_proj.weight": "model-00001-of-00013.safetensors",
|
| 562 |
+
"model.layers.25.mlp.router.bias": "model-00004-of-00013.safetensors",
|
| 563 |
+
"model.layers.25.mlp.router.weight": "model-00004-of-00013.safetensors",
|
| 564 |
+
"model.layers.25.post_attention_layernorm.weight": "model-00001-of-00013.safetensors",
|
| 565 |
+
"model.layers.25.self_attn.k_proj.bias": "model-00004-of-00013.safetensors",
|
| 566 |
+
"model.layers.25.self_attn.k_proj.biases": "model-00004-of-00013.safetensors",
|
| 567 |
+
"model.layers.25.self_attn.k_proj.scales": "model-00004-of-00013.safetensors",
|
| 568 |
+
"model.layers.25.self_attn.k_proj.weight": "model-00004-of-00013.safetensors",
|
| 569 |
+
"model.layers.25.self_attn.o_proj.bias": "model-00004-of-00013.safetensors",
|
| 570 |
+
"model.layers.25.self_attn.o_proj.biases": "model-00004-of-00013.safetensors",
|
| 571 |
+
"model.layers.25.self_attn.o_proj.scales": "model-00004-of-00013.safetensors",
|
| 572 |
+
"model.layers.25.self_attn.o_proj.weight": "model-00004-of-00013.safetensors",
|
| 573 |
+
"model.layers.25.self_attn.q_proj.bias": "model-00004-of-00013.safetensors",
|
| 574 |
+
"model.layers.25.self_attn.q_proj.biases": "model-00004-of-00013.safetensors",
|
| 575 |
+
"model.layers.25.self_attn.q_proj.scales": "model-00004-of-00013.safetensors",
|
| 576 |
+
"model.layers.25.self_attn.q_proj.weight": "model-00004-of-00013.safetensors",
|
| 577 |
+
"model.layers.25.self_attn.sinks": "model-00004-of-00013.safetensors",
|
| 578 |
+
"model.layers.25.self_attn.v_proj.bias": "model-00004-of-00013.safetensors",
|
| 579 |
+
"model.layers.25.self_attn.v_proj.biases": "model-00004-of-00013.safetensors",
|
| 580 |
+
"model.layers.25.self_attn.v_proj.scales": "model-00004-of-00013.safetensors",
|
| 581 |
+
"model.layers.25.self_attn.v_proj.weight": "model-00004-of-00013.safetensors",
|
| 582 |
+
"model.layers.26.input_layernorm.weight": "model-00001-of-00013.safetensors",
|
| 583 |
+
"model.layers.26.mlp.experts.down_proj.bias": "model-00001-of-00013.safetensors",
|
| 584 |
+
"model.layers.26.mlp.experts.down_proj.scales": "model-00001-of-00013.safetensors",
|
| 585 |
+
"model.layers.26.mlp.experts.down_proj.weight": "model-00001-of-00013.safetensors",
|
| 586 |
+
"model.layers.26.mlp.experts.gate_proj.bias": "model-00001-of-00013.safetensors",
|
| 587 |
+
"model.layers.26.mlp.experts.gate_proj.scales": "model-00001-of-00013.safetensors",
|
| 588 |
+
"model.layers.26.mlp.experts.gate_proj.weight": "model-00001-of-00013.safetensors",
|
| 589 |
+
"model.layers.26.mlp.experts.up_proj.bias": "model-00001-of-00013.safetensors",
|
| 590 |
+
"model.layers.26.mlp.experts.up_proj.scales": "model-00001-of-00013.safetensors",
|
| 591 |
+
"model.layers.26.mlp.experts.up_proj.weight": "model-00001-of-00013.safetensors",
|
| 592 |
+
"model.layers.26.mlp.router.bias": "model-00001-of-00013.safetensors",
|
| 593 |
+
"model.layers.26.mlp.router.weight": "model-00001-of-00013.safetensors",
|
| 594 |
+
"model.layers.26.post_attention_layernorm.weight": "model-00001-of-00013.safetensors",
|
| 595 |
+
"model.layers.26.self_attn.k_proj.bias": "model-00001-of-00013.safetensors",
|
| 596 |
+
"model.layers.26.self_attn.k_proj.biases": "model-00001-of-00013.safetensors",
|
| 597 |
+
"model.layers.26.self_attn.k_proj.scales": "model-00001-of-00013.safetensors",
|
| 598 |
+
"model.layers.26.self_attn.k_proj.weight": "model-00001-of-00013.safetensors",
|
| 599 |
+
"model.layers.26.self_attn.o_proj.bias": "model-00001-of-00013.safetensors",
|
| 600 |
+
"model.layers.26.self_attn.o_proj.biases": "model-00001-of-00013.safetensors",
|
| 601 |
+
"model.layers.26.self_attn.o_proj.scales": "model-00001-of-00013.safetensors",
|
| 602 |
+
"model.layers.26.self_attn.o_proj.weight": "model-00001-of-00013.safetensors",
|
| 603 |
+
"model.layers.26.self_attn.q_proj.bias": "model-00001-of-00013.safetensors",
|
| 604 |
+
"model.layers.26.self_attn.q_proj.biases": "model-00001-of-00013.safetensors",
|
| 605 |
+
"model.layers.26.self_attn.q_proj.scales": "model-00001-of-00013.safetensors",
|
| 606 |
+
"model.layers.26.self_attn.q_proj.weight": "model-00001-of-00013.safetensors",
|
| 607 |
+
"model.layers.26.self_attn.sinks": "model-00001-of-00013.safetensors",
|
| 608 |
+
"model.layers.26.self_attn.v_proj.bias": "model-00001-of-00013.safetensors",
|
| 609 |
+
"model.layers.26.self_attn.v_proj.biases": "model-00001-of-00013.safetensors",
|
| 610 |
+
"model.layers.26.self_attn.v_proj.scales": "model-00001-of-00013.safetensors",
|
| 611 |
+
"model.layers.26.self_attn.v_proj.weight": "model-00001-of-00013.safetensors",
|
| 612 |
+
"model.layers.27.input_layernorm.weight": "model-00001-of-00013.safetensors",
|
| 613 |
+
"model.layers.27.mlp.experts.down_proj.bias": "model-00001-of-00013.safetensors",
|
| 614 |
+
"model.layers.27.mlp.experts.down_proj.scales": "model-00002-of-00013.safetensors",
|
| 615 |
+
"model.layers.27.mlp.experts.down_proj.weight": "model-00001-of-00013.safetensors",
|
| 616 |
+
"model.layers.27.mlp.experts.gate_proj.bias": "model-00001-of-00013.safetensors",
|
| 617 |
+
"model.layers.27.mlp.experts.gate_proj.scales": "model-00001-of-00013.safetensors",
|
| 618 |
+
"model.layers.27.mlp.experts.gate_proj.weight": "model-00001-of-00013.safetensors",
|
| 619 |
+
"model.layers.27.mlp.experts.up_proj.bias": "model-00001-of-00013.safetensors",
|
| 620 |
+
"model.layers.27.mlp.experts.up_proj.scales": "model-00001-of-00013.safetensors",
|
| 621 |
+
"model.layers.27.mlp.experts.up_proj.weight": "model-00001-of-00013.safetensors",
|
| 622 |
+
"model.layers.27.mlp.router.bias": "model-00001-of-00013.safetensors",
|
| 623 |
+
"model.layers.27.mlp.router.weight": "model-00001-of-00013.safetensors",
|
| 624 |
+
"model.layers.27.post_attention_layernorm.weight": "model-00001-of-00013.safetensors",
|
| 625 |
+
"model.layers.27.self_attn.k_proj.bias": "model-00001-of-00013.safetensors",
|
| 626 |
+
"model.layers.27.self_attn.k_proj.biases": "model-00001-of-00013.safetensors",
|
| 627 |
+
"model.layers.27.self_attn.k_proj.scales": "model-00001-of-00013.safetensors",
|
| 628 |
+
"model.layers.27.self_attn.k_proj.weight": "model-00001-of-00013.safetensors",
|
| 629 |
+
"model.layers.27.self_attn.o_proj.bias": "model-00001-of-00013.safetensors",
|
| 630 |
+
"model.layers.27.self_attn.o_proj.biases": "model-00001-of-00013.safetensors",
|
| 631 |
+
"model.layers.27.self_attn.o_proj.scales": "model-00001-of-00013.safetensors",
|
| 632 |
+
"model.layers.27.self_attn.o_proj.weight": "model-00001-of-00013.safetensors",
|
| 633 |
+
"model.layers.27.self_attn.q_proj.bias": "model-00001-of-00013.safetensors",
|
| 634 |
+
"model.layers.27.self_attn.q_proj.biases": "model-00001-of-00013.safetensors",
|
| 635 |
+
"model.layers.27.self_attn.q_proj.scales": "model-00001-of-00013.safetensors",
|
| 636 |
+
"model.layers.27.self_attn.q_proj.weight": "model-00001-of-00013.safetensors",
|
| 637 |
+
"model.layers.27.self_attn.sinks": "model-00001-of-00013.safetensors",
|
| 638 |
+
"model.layers.27.self_attn.v_proj.bias": "model-00001-of-00013.safetensors",
|
| 639 |
+
"model.layers.27.self_attn.v_proj.biases": "model-00001-of-00013.safetensors",
|
| 640 |
+
"model.layers.27.self_attn.v_proj.scales": "model-00001-of-00013.safetensors",
|
| 641 |
+
"model.layers.27.self_attn.v_proj.weight": "model-00001-of-00013.safetensors",
|
| 642 |
+
"model.layers.28.input_layernorm.weight": "model-00001-of-00013.safetensors",
|
| 643 |
+
"model.layers.28.mlp.experts.down_proj.bias": "model-00001-of-00013.safetensors",
|
| 644 |
+
"model.layers.28.mlp.experts.down_proj.scales": "model-00002-of-00013.safetensors",
|
| 645 |
+
"model.layers.28.mlp.experts.down_proj.weight": "model-00002-of-00013.safetensors",
|
| 646 |
+
"model.layers.28.mlp.experts.gate_proj.bias": "model-00001-of-00013.safetensors",
|
| 647 |
+
"model.layers.28.mlp.experts.gate_proj.scales": "model-00002-of-00013.safetensors",
|
| 648 |
+
"model.layers.28.mlp.experts.gate_proj.weight": "model-00002-of-00013.safetensors",
|
| 649 |
+
"model.layers.28.mlp.experts.up_proj.bias": "model-00001-of-00013.safetensors",
|
| 650 |
+
"model.layers.28.mlp.experts.up_proj.scales": "model-00002-of-00013.safetensors",
|
| 651 |
+
"model.layers.28.mlp.experts.up_proj.weight": "model-00002-of-00013.safetensors",
|
| 652 |
+
"model.layers.28.mlp.router.bias": "model-00001-of-00013.safetensors",
|
| 653 |
+
"model.layers.28.mlp.router.weight": "model-00001-of-00013.safetensors",
|
| 654 |
+
"model.layers.28.post_attention_layernorm.weight": "model-00001-of-00013.safetensors",
|
| 655 |
+
"model.layers.28.self_attn.k_proj.bias": "model-00001-of-00013.safetensors",
|
| 656 |
+
"model.layers.28.self_attn.k_proj.biases": "model-00001-of-00013.safetensors",
|
| 657 |
+
"model.layers.28.self_attn.k_proj.scales": "model-00001-of-00013.safetensors",
|
| 658 |
+
"model.layers.28.self_attn.k_proj.weight": "model-00001-of-00013.safetensors",
|
| 659 |
+
"model.layers.28.self_attn.o_proj.bias": "model-00001-of-00013.safetensors",
|
| 660 |
+
"model.layers.28.self_attn.o_proj.biases": "model-00001-of-00013.safetensors",
|
| 661 |
+
"model.layers.28.self_attn.o_proj.scales": "model-00001-of-00013.safetensors",
|
| 662 |
+
"model.layers.28.self_attn.o_proj.weight": "model-00001-of-00013.safetensors",
|
| 663 |
+
"model.layers.28.self_attn.q_proj.bias": "model-00001-of-00013.safetensors",
|
| 664 |
+
"model.layers.28.self_attn.q_proj.biases": "model-00001-of-00013.safetensors",
|
| 665 |
+
"model.layers.28.self_attn.q_proj.scales": "model-00001-of-00013.safetensors",
|
| 666 |
+
"model.layers.28.self_attn.q_proj.weight": "model-00001-of-00013.safetensors",
|
| 667 |
+
"model.layers.28.self_attn.sinks": "model-00001-of-00013.safetensors",
|
| 668 |
+
"model.layers.28.self_attn.v_proj.bias": "model-00001-of-00013.safetensors",
|
| 669 |
+
"model.layers.28.self_attn.v_proj.biases": "model-00001-of-00013.safetensors",
|
| 670 |
+
"model.layers.28.self_attn.v_proj.scales": "model-00001-of-00013.safetensors",
|
| 671 |
+
"model.layers.28.self_attn.v_proj.weight": "model-00001-of-00013.safetensors",
|
| 672 |
+
"model.layers.29.input_layernorm.weight": "model-00001-of-00013.safetensors",
|
| 673 |
+
"model.layers.29.mlp.experts.down_proj.bias": "model-00001-of-00013.safetensors",
|
| 674 |
+
"model.layers.29.mlp.experts.down_proj.scales": "model-00002-of-00013.safetensors",
|
| 675 |
+
"model.layers.29.mlp.experts.down_proj.weight": "model-00002-of-00013.safetensors",
|
| 676 |
+
"model.layers.29.mlp.experts.gate_proj.bias": "model-00001-of-00013.safetensors",
|
| 677 |
+
"model.layers.29.mlp.experts.gate_proj.scales": "model-00002-of-00013.safetensors",
|
| 678 |
+
"model.layers.29.mlp.experts.gate_proj.weight": "model-00002-of-00013.safetensors",
|
| 679 |
+
"model.layers.29.mlp.experts.up_proj.bias": "model-00001-of-00013.safetensors",
|
| 680 |
+
"model.layers.29.mlp.experts.up_proj.scales": "model-00002-of-00013.safetensors",
|
| 681 |
+
"model.layers.29.mlp.experts.up_proj.weight": "model-00002-of-00013.safetensors",
|
| 682 |
+
"model.layers.29.mlp.router.bias": "model-00001-of-00013.safetensors",
|
| 683 |
+
"model.layers.29.mlp.router.weight": "model-00001-of-00013.safetensors",
|
| 684 |
+
"model.layers.29.post_attention_layernorm.weight": "model-00001-of-00013.safetensors",
|
| 685 |
+
"model.layers.29.self_attn.k_proj.bias": "model-00001-of-00013.safetensors",
|
| 686 |
+
"model.layers.29.self_attn.k_proj.biases": "model-00001-of-00013.safetensors",
|
| 687 |
+
"model.layers.29.self_attn.k_proj.scales": "model-00001-of-00013.safetensors",
|
| 688 |
+
"model.layers.29.self_attn.k_proj.weight": "model-00001-of-00013.safetensors",
|
| 689 |
+
"model.layers.29.self_attn.o_proj.bias": "model-00001-of-00013.safetensors",
|
| 690 |
+
"model.layers.29.self_attn.o_proj.biases": "model-00001-of-00013.safetensors",
|
| 691 |
+
"model.layers.29.self_attn.o_proj.scales": "model-00001-of-00013.safetensors",
|
| 692 |
+
"model.layers.29.self_attn.o_proj.weight": "model-00001-of-00013.safetensors",
|
| 693 |
+
"model.layers.29.self_attn.q_proj.bias": "model-00001-of-00013.safetensors",
|
| 694 |
+
"model.layers.29.self_attn.q_proj.biases": "model-00001-of-00013.safetensors",
|
| 695 |
+
"model.layers.29.self_attn.q_proj.scales": "model-00001-of-00013.safetensors",
|
| 696 |
+
"model.layers.29.self_attn.q_proj.weight": "model-00001-of-00013.safetensors",
|
| 697 |
+
"model.layers.29.self_attn.sinks": "model-00001-of-00013.safetensors",
|
| 698 |
+
"model.layers.29.self_attn.v_proj.bias": "model-00001-of-00013.safetensors",
|
| 699 |
+
"model.layers.29.self_attn.v_proj.biases": "model-00001-of-00013.safetensors",
|
| 700 |
+
"model.layers.29.self_attn.v_proj.scales": "model-00001-of-00013.safetensors",
|
| 701 |
+
"model.layers.29.self_attn.v_proj.weight": "model-00001-of-00013.safetensors",
|
| 702 |
+
"model.layers.3.input_layernorm.weight": "model-00001-of-00013.safetensors",
|
| 703 |
+
"model.layers.3.mlp.experts.down_proj.bias": "model-00002-of-00013.safetensors",
|
| 704 |
+
"model.layers.3.mlp.experts.down_proj.scales": "model-00003-of-00013.safetensors",
|
| 705 |
+
"model.layers.3.mlp.experts.down_proj.weight": "model-00003-of-00013.safetensors",
|
| 706 |
+
"model.layers.3.mlp.experts.gate_proj.bias": "model-00001-of-00013.safetensors",
|
| 707 |
+
"model.layers.3.mlp.experts.gate_proj.scales": "model-00003-of-00013.safetensors",
|
| 708 |
+
"model.layers.3.mlp.experts.gate_proj.weight": "model-00003-of-00013.safetensors",
|
| 709 |
+
"model.layers.3.mlp.experts.up_proj.bias": "model-00001-of-00013.safetensors",
|
| 710 |
+
"model.layers.3.mlp.experts.up_proj.scales": "model-00003-of-00013.safetensors",
|
| 711 |
+
"model.layers.3.mlp.experts.up_proj.weight": "model-00003-of-00013.safetensors",
|
| 712 |
+
"model.layers.3.mlp.router.bias": "model-00001-of-00013.safetensors",
|
| 713 |
+
"model.layers.3.mlp.router.weight": "model-00001-of-00013.safetensors",
|
| 714 |
+
"model.layers.3.post_attention_layernorm.weight": "model-00002-of-00013.safetensors",
|
| 715 |
+
"model.layers.3.self_attn.k_proj.bias": "model-00001-of-00013.safetensors",
|
| 716 |
+
"model.layers.3.self_attn.k_proj.biases": "model-00001-of-00013.safetensors",
|
| 717 |
+
"model.layers.3.self_attn.k_proj.scales": "model-00001-of-00013.safetensors",
|
| 718 |
+
"model.layers.3.self_attn.k_proj.weight": "model-00001-of-00013.safetensors",
|
| 719 |
+
"model.layers.3.self_attn.o_proj.bias": "model-00001-of-00013.safetensors",
|
| 720 |
+
"model.layers.3.self_attn.o_proj.biases": "model-00001-of-00013.safetensors",
|
| 721 |
+
"model.layers.3.self_attn.o_proj.scales": "model-00001-of-00013.safetensors",
|
| 722 |
+
"model.layers.3.self_attn.o_proj.weight": "model-00001-of-00013.safetensors",
|
| 723 |
+
"model.layers.3.self_attn.q_proj.bias": "model-00001-of-00013.safetensors",
|
| 724 |
+
"model.layers.3.self_attn.q_proj.biases": "model-00001-of-00013.safetensors",
|
| 725 |
+
"model.layers.3.self_attn.q_proj.scales": "model-00001-of-00013.safetensors",
|
| 726 |
+
"model.layers.3.self_attn.q_proj.weight": "model-00001-of-00013.safetensors",
|
| 727 |
+
"model.layers.3.self_attn.sinks": "model-00001-of-00013.safetensors",
|
| 728 |
+
"model.layers.3.self_attn.v_proj.bias": "model-00001-of-00013.safetensors",
|
| 729 |
+
"model.layers.3.self_attn.v_proj.biases": "model-00001-of-00013.safetensors",
|
| 730 |
+
"model.layers.3.self_attn.v_proj.scales": "model-00001-of-00013.safetensors",
|
| 731 |
+
"model.layers.3.self_attn.v_proj.weight": "model-00001-of-00013.safetensors",
|
| 732 |
+
"model.layers.30.input_layernorm.weight": "model-00002-of-00013.safetensors",
|
| 733 |
+
"model.layers.30.mlp.experts.down_proj.bias": "model-00011-of-00013.safetensors",
|
| 734 |
+
"model.layers.30.mlp.experts.down_proj.scales": "model-00011-of-00013.safetensors",
|
| 735 |
+
"model.layers.30.mlp.experts.down_proj.weight": "model-00011-of-00013.safetensors",
|
| 736 |
+
"model.layers.30.mlp.experts.gate_proj.bias": "model-00002-of-00013.safetensors",
|
| 737 |
+
"model.layers.30.mlp.experts.gate_proj.scales": "model-00011-of-00013.safetensors",
|
| 738 |
+
"model.layers.30.mlp.experts.gate_proj.weight": "model-00011-of-00013.safetensors",
|
| 739 |
+
"model.layers.30.mlp.experts.up_proj.bias": "model-00002-of-00013.safetensors",
|
| 740 |
+
"model.layers.30.mlp.experts.up_proj.scales": "model-00011-of-00013.safetensors",
|
| 741 |
+
"model.layers.30.mlp.experts.up_proj.weight": "model-00011-of-00013.safetensors",
|
| 742 |
+
"model.layers.30.mlp.router.bias": "model-00002-of-00013.safetensors",
|
| 743 |
+
"model.layers.30.mlp.router.weight": "model-00002-of-00013.safetensors",
|
| 744 |
+
"model.layers.30.post_attention_layernorm.weight": "model-00011-of-00013.safetensors",
|
| 745 |
+
"model.layers.30.self_attn.k_proj.bias": "model-00002-of-00013.safetensors",
|
| 746 |
+
"model.layers.30.self_attn.k_proj.biases": "model-00002-of-00013.safetensors",
|
| 747 |
+
"model.layers.30.self_attn.k_proj.scales": "model-00002-of-00013.safetensors",
|
| 748 |
+
"model.layers.30.self_attn.k_proj.weight": "model-00002-of-00013.safetensors",
|
| 749 |
+
"model.layers.30.self_attn.o_proj.bias": "model-00002-of-00013.safetensors",
|
| 750 |
+
"model.layers.30.self_attn.o_proj.biases": "model-00002-of-00013.safetensors",
|
| 751 |
+
"model.layers.30.self_attn.o_proj.scales": "model-00002-of-00013.safetensors",
|
| 752 |
+
"model.layers.30.self_attn.o_proj.weight": "model-00002-of-00013.safetensors",
|
| 753 |
+
"model.layers.30.self_attn.q_proj.bias": "model-00002-of-00013.safetensors",
|
| 754 |
+
"model.layers.30.self_attn.q_proj.biases": "model-00002-of-00013.safetensors",
|
| 755 |
+
"model.layers.30.self_attn.q_proj.scales": "model-00002-of-00013.safetensors",
|
| 756 |
+
"model.layers.30.self_attn.q_proj.weight": "model-00002-of-00013.safetensors",
|
| 757 |
+
"model.layers.30.self_attn.sinks": "model-00002-of-00013.safetensors",
|
| 758 |
+
"model.layers.30.self_attn.v_proj.bias": "model-00002-of-00013.safetensors",
|
| 759 |
+
"model.layers.30.self_attn.v_proj.biases": "model-00002-of-00013.safetensors",
|
| 760 |
+
"model.layers.30.self_attn.v_proj.scales": "model-00002-of-00013.safetensors",
|
| 761 |
+
"model.layers.30.self_attn.v_proj.weight": "model-00002-of-00013.safetensors",
|
| 762 |
+
"model.layers.31.input_layernorm.weight": "model-00011-of-00013.safetensors",
|
| 763 |
+
"model.layers.31.mlp.experts.down_proj.bias": "model-00011-of-00013.safetensors",
|
| 764 |
+
"model.layers.31.mlp.experts.down_proj.scales": "model-00011-of-00013.safetensors",
|
| 765 |
+
"model.layers.31.mlp.experts.down_proj.weight": "model-00011-of-00013.safetensors",
|
| 766 |
+
"model.layers.31.mlp.experts.gate_proj.bias": "model-00011-of-00013.safetensors",
|
| 767 |
+
"model.layers.31.mlp.experts.gate_proj.scales": "model-00011-of-00013.safetensors",
|
| 768 |
+
"model.layers.31.mlp.experts.gate_proj.weight": "model-00011-of-00013.safetensors",
|
| 769 |
+
"model.layers.31.mlp.experts.up_proj.bias": "model-00011-of-00013.safetensors",
|
| 770 |
+
"model.layers.31.mlp.experts.up_proj.scales": "model-00011-of-00013.safetensors",
|
| 771 |
+
"model.layers.31.mlp.experts.up_proj.weight": "model-00011-of-00013.safetensors",
|
| 772 |
+
"model.layers.31.mlp.router.bias": "model-00011-of-00013.safetensors",
|
| 773 |
+
"model.layers.31.mlp.router.weight": "model-00011-of-00013.safetensors",
|
| 774 |
+
"model.layers.31.post_attention_layernorm.weight": "model-00011-of-00013.safetensors",
|
| 775 |
+
"model.layers.31.self_attn.k_proj.bias": "model-00011-of-00013.safetensors",
|
| 776 |
+
"model.layers.31.self_attn.k_proj.biases": "model-00011-of-00013.safetensors",
|
| 777 |
+
"model.layers.31.self_attn.k_proj.scales": "model-00011-of-00013.safetensors",
|
| 778 |
+
"model.layers.31.self_attn.k_proj.weight": "model-00011-of-00013.safetensors",
|
| 779 |
+
"model.layers.31.self_attn.o_proj.bias": "model-00011-of-00013.safetensors",
|
| 780 |
+
"model.layers.31.self_attn.o_proj.biases": "model-00011-of-00013.safetensors",
|
| 781 |
+
"model.layers.31.self_attn.o_proj.scales": "model-00011-of-00013.safetensors",
|
| 782 |
+
"model.layers.31.self_attn.o_proj.weight": "model-00011-of-00013.safetensors",
|
| 783 |
+
"model.layers.31.self_attn.q_proj.bias": "model-00011-of-00013.safetensors",
|
| 784 |
+
"model.layers.31.self_attn.q_proj.biases": "model-00011-of-00013.safetensors",
|
| 785 |
+
"model.layers.31.self_attn.q_proj.scales": "model-00011-of-00013.safetensors",
|
| 786 |
+
"model.layers.31.self_attn.q_proj.weight": "model-00011-of-00013.safetensors",
|
| 787 |
+
"model.layers.31.self_attn.sinks": "model-00011-of-00013.safetensors",
|
| 788 |
+
"model.layers.31.self_attn.v_proj.bias": "model-00011-of-00013.safetensors",
|
| 789 |
+
"model.layers.31.self_attn.v_proj.biases": "model-00011-of-00013.safetensors",
|
| 790 |
+
"model.layers.31.self_attn.v_proj.scales": "model-00011-of-00013.safetensors",
|
| 791 |
+
"model.layers.31.self_attn.v_proj.weight": "model-00011-of-00013.safetensors",
|
| 792 |
+
"model.layers.32.input_layernorm.weight": "model-00011-of-00013.safetensors",
|
| 793 |
+
"model.layers.32.mlp.experts.down_proj.bias": "model-00011-of-00013.safetensors",
|
| 794 |
+
"model.layers.32.mlp.experts.down_proj.scales": "model-00011-of-00013.safetensors",
|
| 795 |
+
"model.layers.32.mlp.experts.down_proj.weight": "model-00011-of-00013.safetensors",
|
| 796 |
+
"model.layers.32.mlp.experts.gate_proj.bias": "model-00011-of-00013.safetensors",
|
| 797 |
+
"model.layers.32.mlp.experts.gate_proj.scales": "model-00012-of-00013.safetensors",
|
| 798 |
+
"model.layers.32.mlp.experts.gate_proj.weight": "model-00011-of-00013.safetensors",
|
| 799 |
+
"model.layers.32.mlp.experts.up_proj.bias": "model-00011-of-00013.safetensors",
|
| 800 |
+
"model.layers.32.mlp.experts.up_proj.scales": "model-00012-of-00013.safetensors",
|
| 801 |
+
"model.layers.32.mlp.experts.up_proj.weight": "model-00012-of-00013.safetensors",
|
| 802 |
+
"model.layers.32.mlp.router.bias": "model-00011-of-00013.safetensors",
|
| 803 |
+
"model.layers.32.mlp.router.weight": "model-00011-of-00013.safetensors",
|
| 804 |
+
"model.layers.32.post_attention_layernorm.weight": "model-00011-of-00013.safetensors",
|
| 805 |
+
"model.layers.32.self_attn.k_proj.bias": "model-00011-of-00013.safetensors",
|
| 806 |
+
"model.layers.32.self_attn.k_proj.biases": "model-00011-of-00013.safetensors",
|
| 807 |
+
"model.layers.32.self_attn.k_proj.scales": "model-00011-of-00013.safetensors",
|
| 808 |
+
"model.layers.32.self_attn.k_proj.weight": "model-00011-of-00013.safetensors",
|
| 809 |
+
"model.layers.32.self_attn.o_proj.bias": "model-00011-of-00013.safetensors",
|
| 810 |
+
"model.layers.32.self_attn.o_proj.biases": "model-00011-of-00013.safetensors",
|
| 811 |
+
"model.layers.32.self_attn.o_proj.scales": "model-00011-of-00013.safetensors",
|
| 812 |
+
"model.layers.32.self_attn.o_proj.weight": "model-00011-of-00013.safetensors",
|
| 813 |
+
"model.layers.32.self_attn.q_proj.bias": "model-00011-of-00013.safetensors",
|
| 814 |
+
"model.layers.32.self_attn.q_proj.biases": "model-00011-of-00013.safetensors",
|
| 815 |
+
"model.layers.32.self_attn.q_proj.scales": "model-00011-of-00013.safetensors",
|
| 816 |
+
"model.layers.32.self_attn.q_proj.weight": "model-00011-of-00013.safetensors",
|
| 817 |
+
"model.layers.32.self_attn.sinks": "model-00011-of-00013.safetensors",
|
| 818 |
+
"model.layers.32.self_attn.v_proj.bias": "model-00011-of-00013.safetensors",
|
| 819 |
+
"model.layers.32.self_attn.v_proj.biases": "model-00011-of-00013.safetensors",
|
| 820 |
+
"model.layers.32.self_attn.v_proj.scales": "model-00011-of-00013.safetensors",
|
| 821 |
+
"model.layers.32.self_attn.v_proj.weight": "model-00011-of-00013.safetensors",
|
| 822 |
+
"model.layers.33.input_layernorm.weight": "model-00011-of-00013.safetensors",
|
| 823 |
+
"model.layers.33.mlp.experts.down_proj.bias": "model-00011-of-00013.safetensors",
|
| 824 |
+
"model.layers.33.mlp.experts.down_proj.scales": "model-00012-of-00013.safetensors",
|
| 825 |
+
"model.layers.33.mlp.experts.down_proj.weight": "model-00012-of-00013.safetensors",
|
| 826 |
+
"model.layers.33.mlp.experts.gate_proj.bias": "model-00011-of-00013.safetensors",
|
| 827 |
+
"model.layers.33.mlp.experts.gate_proj.scales": "model-00012-of-00013.safetensors",
|
| 828 |
+
"model.layers.33.mlp.experts.gate_proj.weight": "model-00012-of-00013.safetensors",
|
| 829 |
+
"model.layers.33.mlp.experts.up_proj.bias": "model-00011-of-00013.safetensors",
|
| 830 |
+
"model.layers.33.mlp.experts.up_proj.scales": "model-00012-of-00013.safetensors",
|
| 831 |
+
"model.layers.33.mlp.experts.up_proj.weight": "model-00012-of-00013.safetensors",
|
| 832 |
+
"model.layers.33.mlp.router.bias": "model-00011-of-00013.safetensors",
|
| 833 |
+
"model.layers.33.mlp.router.weight": "model-00011-of-00013.safetensors",
|
| 834 |
+
"model.layers.33.post_attention_layernorm.weight": "model-00012-of-00013.safetensors",
|
| 835 |
+
"model.layers.33.self_attn.k_proj.bias": "model-00011-of-00013.safetensors",
|
| 836 |
+
"model.layers.33.self_attn.k_proj.biases": "model-00011-of-00013.safetensors",
|
| 837 |
+
"model.layers.33.self_attn.k_proj.scales": "model-00011-of-00013.safetensors",
|
| 838 |
+
"model.layers.33.self_attn.k_proj.weight": "model-00011-of-00013.safetensors",
|
| 839 |
+
"model.layers.33.self_attn.o_proj.bias": "model-00011-of-00013.safetensors",
|
| 840 |
+
"model.layers.33.self_attn.o_proj.biases": "model-00011-of-00013.safetensors",
|
| 841 |
+
"model.layers.33.self_attn.o_proj.scales": "model-00011-of-00013.safetensors",
|
| 842 |
+
"model.layers.33.self_attn.o_proj.weight": "model-00011-of-00013.safetensors",
|
| 843 |
+
"model.layers.33.self_attn.q_proj.bias": "model-00011-of-00013.safetensors",
|
| 844 |
+
"model.layers.33.self_attn.q_proj.biases": "model-00011-of-00013.safetensors",
|
| 845 |
+
"model.layers.33.self_attn.q_proj.scales": "model-00011-of-00013.safetensors",
|
| 846 |
+
"model.layers.33.self_attn.q_proj.weight": "model-00011-of-00013.safetensors",
|
| 847 |
+
"model.layers.33.self_attn.sinks": "model-00011-of-00013.safetensors",
|
| 848 |
+
"model.layers.33.self_attn.v_proj.bias": "model-00011-of-00013.safetensors",
|
| 849 |
+
"model.layers.33.self_attn.v_proj.biases": "model-00011-of-00013.safetensors",
|
| 850 |
+
"model.layers.33.self_attn.v_proj.scales": "model-00011-of-00013.safetensors",
|
| 851 |
+
"model.layers.33.self_attn.v_proj.weight": "model-00011-of-00013.safetensors",
|
| 852 |
+
"model.layers.34.input_layernorm.weight": "model-00012-of-00013.safetensors",
|
| 853 |
+
"model.layers.34.mlp.experts.down_proj.bias": "model-00012-of-00013.safetensors",
|
| 854 |
+
"model.layers.34.mlp.experts.down_proj.scales": "model-00012-of-00013.safetensors",
|
| 855 |
+
"model.layers.34.mlp.experts.down_proj.weight": "model-00012-of-00013.safetensors",
|
| 856 |
+
"model.layers.34.mlp.experts.gate_proj.bias": "model-00012-of-00013.safetensors",
|
| 857 |
+
"model.layers.34.mlp.experts.gate_proj.scales": "model-00012-of-00013.safetensors",
|
| 858 |
+
"model.layers.34.mlp.experts.gate_proj.weight": "model-00012-of-00013.safetensors",
|
| 859 |
+
"model.layers.34.mlp.experts.up_proj.bias": "model-00012-of-00013.safetensors",
|
| 860 |
+
"model.layers.34.mlp.experts.up_proj.scales": "model-00012-of-00013.safetensors",
|
| 861 |
+
"model.layers.34.mlp.experts.up_proj.weight": "model-00012-of-00013.safetensors",
|
| 862 |
+
"model.layers.34.mlp.router.bias": "model-00012-of-00013.safetensors",
|
| 863 |
+
"model.layers.34.mlp.router.weight": "model-00012-of-00013.safetensors",
|
| 864 |
+
"model.layers.34.post_attention_layernorm.weight": "model-00012-of-00013.safetensors",
|
| 865 |
+
"model.layers.34.self_attn.k_proj.bias": "model-00012-of-00013.safetensors",
|
| 866 |
+
"model.layers.34.self_attn.k_proj.biases": "model-00012-of-00013.safetensors",
|
| 867 |
+
"model.layers.34.self_attn.k_proj.scales": "model-00012-of-00013.safetensors",
|
| 868 |
+
"model.layers.34.self_attn.k_proj.weight": "model-00012-of-00013.safetensors",
|
| 869 |
+
"model.layers.34.self_attn.o_proj.bias": "model-00012-of-00013.safetensors",
|
| 870 |
+
"model.layers.34.self_attn.o_proj.biases": "model-00012-of-00013.safetensors",
|
| 871 |
+
"model.layers.34.self_attn.o_proj.scales": "model-00012-of-00013.safetensors",
|
| 872 |
+
"model.layers.34.self_attn.o_proj.weight": "model-00012-of-00013.safetensors",
|
| 873 |
+
"model.layers.34.self_attn.q_proj.bias": "model-00012-of-00013.safetensors",
|
| 874 |
+
"model.layers.34.self_attn.q_proj.biases": "model-00012-of-00013.safetensors",
|
| 875 |
+
"model.layers.34.self_attn.q_proj.scales": "model-00012-of-00013.safetensors",
|
| 876 |
+
"model.layers.34.self_attn.q_proj.weight": "model-00012-of-00013.safetensors",
|
| 877 |
+
"model.layers.34.self_attn.sinks": "model-00012-of-00013.safetensors",
|
| 878 |
+
"model.layers.34.self_attn.v_proj.bias": "model-00012-of-00013.safetensors",
|
| 879 |
+
"model.layers.34.self_attn.v_proj.biases": "model-00012-of-00013.safetensors",
|
| 880 |
+
"model.layers.34.self_attn.v_proj.scales": "model-00012-of-00013.safetensors",
|
| 881 |
+
"model.layers.34.self_attn.v_proj.weight": "model-00012-of-00013.safetensors",
|
| 882 |
+
"model.layers.35.input_layernorm.weight": "model-00012-of-00013.safetensors",
|
| 883 |
+
"model.layers.35.mlp.experts.down_proj.bias": "model-00012-of-00013.safetensors",
|
| 884 |
+
"model.layers.35.mlp.experts.down_proj.scales": "model-00012-of-00013.safetensors",
|
| 885 |
+
"model.layers.35.mlp.experts.down_proj.weight": "model-00012-of-00013.safetensors",
|
| 886 |
+
"model.layers.35.mlp.experts.gate_proj.bias": "model-00012-of-00013.safetensors",
|
| 887 |
+
"model.layers.35.mlp.experts.gate_proj.scales": "model-00013-of-00013.safetensors",
|
| 888 |
+
"model.layers.35.mlp.experts.gate_proj.weight": "model-00012-of-00013.safetensors",
|
| 889 |
+
"model.layers.35.mlp.experts.up_proj.bias": "model-00012-of-00013.safetensors",
|
| 890 |
+
"model.layers.35.mlp.experts.up_proj.scales": "model-00013-of-00013.safetensors",
|
| 891 |
+
"model.layers.35.mlp.experts.up_proj.weight": "model-00013-of-00013.safetensors",
|
| 892 |
+
"model.layers.35.mlp.router.bias": "model-00012-of-00013.safetensors",
|
| 893 |
+
"model.layers.35.mlp.router.weight": "model-00012-of-00013.safetensors",
|
| 894 |
+
"model.layers.35.post_attention_layernorm.weight": "model-00012-of-00013.safetensors",
|
| 895 |
+
"model.layers.35.self_attn.k_proj.bias": "model-00012-of-00013.safetensors",
|
| 896 |
+
"model.layers.35.self_attn.k_proj.biases": "model-00012-of-00013.safetensors",
|
| 897 |
+
"model.layers.35.self_attn.k_proj.scales": "model-00012-of-00013.safetensors",
|
| 898 |
+
"model.layers.35.self_attn.k_proj.weight": "model-00012-of-00013.safetensors",
|
| 899 |
+
"model.layers.35.self_attn.o_proj.bias": "model-00012-of-00013.safetensors",
|
| 900 |
+
"model.layers.35.self_attn.o_proj.biases": "model-00012-of-00013.safetensors",
|
| 901 |
+
"model.layers.35.self_attn.o_proj.scales": "model-00012-of-00013.safetensors",
|
| 902 |
+
"model.layers.35.self_attn.o_proj.weight": "model-00012-of-00013.safetensors",
|
| 903 |
+
"model.layers.35.self_attn.q_proj.bias": "model-00012-of-00013.safetensors",
|
| 904 |
+
"model.layers.35.self_attn.q_proj.biases": "model-00012-of-00013.safetensors",
|
| 905 |
+
"model.layers.35.self_attn.q_proj.scales": "model-00012-of-00013.safetensors",
|
| 906 |
+
"model.layers.35.self_attn.q_proj.weight": "model-00012-of-00013.safetensors",
|
| 907 |
+
"model.layers.35.self_attn.sinks": "model-00012-of-00013.safetensors",
|
| 908 |
+
"model.layers.35.self_attn.v_proj.bias": "model-00012-of-00013.safetensors",
|
| 909 |
+
"model.layers.35.self_attn.v_proj.biases": "model-00012-of-00013.safetensors",
|
| 910 |
+
"model.layers.35.self_attn.v_proj.scales": "model-00012-of-00013.safetensors",
|
| 911 |
+
"model.layers.35.self_attn.v_proj.weight": "model-00012-of-00013.safetensors",
|
| 912 |
+
"model.layers.4.input_layernorm.weight": "model-00012-of-00013.safetensors",
|
| 913 |
+
"model.layers.4.mlp.experts.down_proj.bias": "model-00004-of-00013.safetensors",
|
| 914 |
+
"model.layers.4.mlp.experts.down_proj.scales": "model-00005-of-00013.safetensors",
|
| 915 |
+
"model.layers.4.mlp.experts.down_proj.weight": "model-00005-of-00013.safetensors",
|
| 916 |
+
"model.layers.4.mlp.experts.gate_proj.bias": "model-00012-of-00013.safetensors",
|
| 917 |
+
"model.layers.4.mlp.experts.gate_proj.scales": "model-00005-of-00013.safetensors",
|
| 918 |
+
"model.layers.4.mlp.experts.gate_proj.weight": "model-00005-of-00013.safetensors",
|
| 919 |
+
"model.layers.4.mlp.experts.up_proj.bias": "model-00012-of-00013.safetensors",
|
| 920 |
+
"model.layers.4.mlp.experts.up_proj.scales": "model-00005-of-00013.safetensors",
|
| 921 |
+
"model.layers.4.mlp.experts.up_proj.weight": "model-00005-of-00013.safetensors",
|
| 922 |
+
"model.layers.4.mlp.router.bias": "model-00012-of-00013.safetensors",
|
| 923 |
+
"model.layers.4.mlp.router.weight": "model-00012-of-00013.safetensors",
|
| 924 |
+
"model.layers.4.post_attention_layernorm.weight": "model-00005-of-00013.safetensors",
|
| 925 |
+
"model.layers.4.self_attn.k_proj.bias": "model-00012-of-00013.safetensors",
|
| 926 |
+
"model.layers.4.self_attn.k_proj.biases": "model-00012-of-00013.safetensors",
|
| 927 |
+
"model.layers.4.self_attn.k_proj.scales": "model-00012-of-00013.safetensors",
|
| 928 |
+
"model.layers.4.self_attn.k_proj.weight": "model-00012-of-00013.safetensors",
|
| 929 |
+
"model.layers.4.self_attn.o_proj.bias": "model-00012-of-00013.safetensors",
|
| 930 |
+
"model.layers.4.self_attn.o_proj.biases": "model-00012-of-00013.safetensors",
|
| 931 |
+
"model.layers.4.self_attn.o_proj.scales": "model-00012-of-00013.safetensors",
|
| 932 |
+
"model.layers.4.self_attn.o_proj.weight": "model-00012-of-00013.safetensors",
|
| 933 |
+
"model.layers.4.self_attn.q_proj.bias": "model-00012-of-00013.safetensors",
|
| 934 |
+
"model.layers.4.self_attn.q_proj.biases": "model-00012-of-00013.safetensors",
|
| 935 |
+
"model.layers.4.self_attn.q_proj.scales": "model-00012-of-00013.safetensors",
|
| 936 |
+
"model.layers.4.self_attn.q_proj.weight": "model-00012-of-00013.safetensors",
|
| 937 |
+
"model.layers.4.self_attn.sinks": "model-00012-of-00013.safetensors",
|
| 938 |
+
"model.layers.4.self_attn.v_proj.bias": "model-00012-of-00013.safetensors",
|
| 939 |
+
"model.layers.4.self_attn.v_proj.biases": "model-00012-of-00013.safetensors",
|
| 940 |
+
"model.layers.4.self_attn.v_proj.scales": "model-00012-of-00013.safetensors",
|
| 941 |
+
"model.layers.4.self_attn.v_proj.weight": "model-00012-of-00013.safetensors",
|
| 942 |
+
"model.layers.5.input_layernorm.weight": "model-00005-of-00013.safetensors",
|
| 943 |
+
"model.layers.5.mlp.experts.down_proj.bias": "model-00005-of-00013.safetensors",
|
| 944 |
+
"model.layers.5.mlp.experts.down_proj.scales": "model-00005-of-00013.safetensors",
|
| 945 |
+
"model.layers.5.mlp.experts.down_proj.weight": "model-00005-of-00013.safetensors",
|
| 946 |
+
"model.layers.5.mlp.experts.gate_proj.bias": "model-00005-of-00013.safetensors",
|
| 947 |
+
"model.layers.5.mlp.experts.gate_proj.scales": "model-00005-of-00013.safetensors",
|
| 948 |
+
"model.layers.5.mlp.experts.gate_proj.weight": "model-00005-of-00013.safetensors",
|
| 949 |
+
"model.layers.5.mlp.experts.up_proj.bias": "model-00005-of-00013.safetensors",
|
| 950 |
+
"model.layers.5.mlp.experts.up_proj.scales": "model-00005-of-00013.safetensors",
|
| 951 |
+
"model.layers.5.mlp.experts.up_proj.weight": "model-00005-of-00013.safetensors",
|
| 952 |
+
"model.layers.5.mlp.router.bias": "model-00005-of-00013.safetensors",
|
| 953 |
+
"model.layers.5.mlp.router.weight": "model-00005-of-00013.safetensors",
|
| 954 |
+
"model.layers.5.post_attention_layernorm.weight": "model-00005-of-00013.safetensors",
|
| 955 |
+
"model.layers.5.self_attn.k_proj.bias": "model-00005-of-00013.safetensors",
|
| 956 |
+
"model.layers.5.self_attn.k_proj.biases": "model-00005-of-00013.safetensors",
|
| 957 |
+
"model.layers.5.self_attn.k_proj.scales": "model-00005-of-00013.safetensors",
|
| 958 |
+
"model.layers.5.self_attn.k_proj.weight": "model-00005-of-00013.safetensors",
|
| 959 |
+
"model.layers.5.self_attn.o_proj.bias": "model-00005-of-00013.safetensors",
|
| 960 |
+
"model.layers.5.self_attn.o_proj.biases": "model-00005-of-00013.safetensors",
|
| 961 |
+
"model.layers.5.self_attn.o_proj.scales": "model-00005-of-00013.safetensors",
|
| 962 |
+
"model.layers.5.self_attn.o_proj.weight": "model-00005-of-00013.safetensors",
|
| 963 |
+
"model.layers.5.self_attn.q_proj.bias": "model-00005-of-00013.safetensors",
|
| 964 |
+
"model.layers.5.self_attn.q_proj.biases": "model-00005-of-00013.safetensors",
|
| 965 |
+
"model.layers.5.self_attn.q_proj.scales": "model-00005-of-00013.safetensors",
|
| 966 |
+
"model.layers.5.self_attn.q_proj.weight": "model-00005-of-00013.safetensors",
|
| 967 |
+
"model.layers.5.self_attn.sinks": "model-00005-of-00013.safetensors",
|
| 968 |
+
"model.layers.5.self_attn.v_proj.bias": "model-00005-of-00013.safetensors",
|
| 969 |
+
"model.layers.5.self_attn.v_proj.biases": "model-00005-of-00013.safetensors",
|
| 970 |
+
"model.layers.5.self_attn.v_proj.scales": "model-00005-of-00013.safetensors",
|
| 971 |
+
"model.layers.5.self_attn.v_proj.weight": "model-00005-of-00013.safetensors",
|
| 972 |
+
"model.layers.6.input_layernorm.weight": "model-00005-of-00013.safetensors",
|
| 973 |
+
"model.layers.6.mlp.experts.down_proj.bias": "model-00005-of-00013.safetensors",
|
| 974 |
+
"model.layers.6.mlp.experts.down_proj.scales": "model-00005-of-00013.safetensors",
|
| 975 |
+
"model.layers.6.mlp.experts.down_proj.weight": "model-00005-of-00013.safetensors",
|
| 976 |
+
"model.layers.6.mlp.experts.gate_proj.bias": "model-00005-of-00013.safetensors",
|
| 977 |
+
"model.layers.6.mlp.experts.gate_proj.scales": "model-00006-of-00013.safetensors",
|
| 978 |
+
"model.layers.6.mlp.experts.gate_proj.weight": "model-00005-of-00013.safetensors",
|
| 979 |
+
"model.layers.6.mlp.experts.up_proj.bias": "model-00005-of-00013.safetensors",
|
| 980 |
+
"model.layers.6.mlp.experts.up_proj.scales": "model-00006-of-00013.safetensors",
|
| 981 |
+
"model.layers.6.mlp.experts.up_proj.weight": "model-00005-of-00013.safetensors",
|
| 982 |
+
"model.layers.6.mlp.router.bias": "model-00005-of-00013.safetensors",
|
| 983 |
+
"model.layers.6.mlp.router.weight": "model-00005-of-00013.safetensors",
|
| 984 |
+
"model.layers.6.post_attention_layernorm.weight": "model-00005-of-00013.safetensors",
|
| 985 |
+
"model.layers.6.self_attn.k_proj.bias": "model-00005-of-00013.safetensors",
|
| 986 |
+
"model.layers.6.self_attn.k_proj.biases": "model-00005-of-00013.safetensors",
|
| 987 |
+
"model.layers.6.self_attn.k_proj.scales": "model-00005-of-00013.safetensors",
|
| 988 |
+
"model.layers.6.self_attn.k_proj.weight": "model-00005-of-00013.safetensors",
|
| 989 |
+
"model.layers.6.self_attn.o_proj.bias": "model-00005-of-00013.safetensors",
|
| 990 |
+
"model.layers.6.self_attn.o_proj.biases": "model-00005-of-00013.safetensors",
|
| 991 |
+
"model.layers.6.self_attn.o_proj.scales": "model-00005-of-00013.safetensors",
|
| 992 |
+
"model.layers.6.self_attn.o_proj.weight": "model-00005-of-00013.safetensors",
|
| 993 |
+
"model.layers.6.self_attn.q_proj.bias": "model-00005-of-00013.safetensors",
|
| 994 |
+
"model.layers.6.self_attn.q_proj.biases": "model-00005-of-00013.safetensors",
|
| 995 |
+
"model.layers.6.self_attn.q_proj.scales": "model-00005-of-00013.safetensors",
|
| 996 |
+
"model.layers.6.self_attn.q_proj.weight": "model-00005-of-00013.safetensors",
|
| 997 |
+
"model.layers.6.self_attn.sinks": "model-00005-of-00013.safetensors",
|
| 998 |
+
"model.layers.6.self_attn.v_proj.bias": "model-00005-of-00013.safetensors",
|
| 999 |
+
"model.layers.6.self_attn.v_proj.biases": "model-00005-of-00013.safetensors",
|
| 1000 |
+
"model.layers.6.self_attn.v_proj.scales": "model-00005-of-00013.safetensors",
|
| 1001 |
+
"model.layers.6.self_attn.v_proj.weight": "model-00005-of-00013.safetensors",
|
| 1002 |
+
"model.layers.7.input_layernorm.weight": "model-00005-of-00013.safetensors",
|
| 1003 |
+
"model.layers.7.mlp.experts.down_proj.bias": "model-00006-of-00013.safetensors",
|
| 1004 |
+
"model.layers.7.mlp.experts.down_proj.scales": "model-00006-of-00013.safetensors",
|
| 1005 |
+
"model.layers.7.mlp.experts.down_proj.weight": "model-00006-of-00013.safetensors",
|
| 1006 |
+
"model.layers.7.mlp.experts.gate_proj.bias": "model-00005-of-00013.safetensors",
|
| 1007 |
+
"model.layers.7.mlp.experts.gate_proj.scales": "model-00006-of-00013.safetensors",
|
| 1008 |
+
"model.layers.7.mlp.experts.gate_proj.weight": "model-00006-of-00013.safetensors",
|
| 1009 |
+
"model.layers.7.mlp.experts.up_proj.bias": "model-00005-of-00013.safetensors",
|
| 1010 |
+
"model.layers.7.mlp.experts.up_proj.scales": "model-00006-of-00013.safetensors",
|
| 1011 |
+
"model.layers.7.mlp.experts.up_proj.weight": "model-00006-of-00013.safetensors",
|
| 1012 |
+
"model.layers.7.mlp.router.bias": "model-00005-of-00013.safetensors",
|
| 1013 |
+
"model.layers.7.mlp.router.weight": "model-00005-of-00013.safetensors",
|
| 1014 |
+
"model.layers.7.post_attention_layernorm.weight": "model-00006-of-00013.safetensors",
|
| 1015 |
+
"model.layers.7.self_attn.k_proj.bias": "model-00005-of-00013.safetensors",
|
| 1016 |
+
"model.layers.7.self_attn.k_proj.biases": "model-00005-of-00013.safetensors",
|
| 1017 |
+
"model.layers.7.self_attn.k_proj.scales": "model-00005-of-00013.safetensors",
|
| 1018 |
+
"model.layers.7.self_attn.k_proj.weight": "model-00005-of-00013.safetensors",
|
| 1019 |
+
"model.layers.7.self_attn.o_proj.bias": "model-00005-of-00013.safetensors",
|
| 1020 |
+
"model.layers.7.self_attn.o_proj.biases": "model-00005-of-00013.safetensors",
|
| 1021 |
+
"model.layers.7.self_attn.o_proj.scales": "model-00005-of-00013.safetensors",
|
| 1022 |
+
"model.layers.7.self_attn.o_proj.weight": "model-00005-of-00013.safetensors",
|
| 1023 |
+
"model.layers.7.self_attn.q_proj.bias": "model-00005-of-00013.safetensors",
|
| 1024 |
+
"model.layers.7.self_attn.q_proj.biases": "model-00005-of-00013.safetensors",
|
| 1025 |
+
"model.layers.7.self_attn.q_proj.scales": "model-00005-of-00013.safetensors",
|
| 1026 |
+
"model.layers.7.self_attn.q_proj.weight": "model-00005-of-00013.safetensors",
|
| 1027 |
+
"model.layers.7.self_attn.sinks": "model-00005-of-00013.safetensors",
|
| 1028 |
+
"model.layers.7.self_attn.v_proj.bias": "model-00005-of-00013.safetensors",
|
| 1029 |
+
"model.layers.7.self_attn.v_proj.biases": "model-00005-of-00013.safetensors",
|
| 1030 |
+
"model.layers.7.self_attn.v_proj.scales": "model-00005-of-00013.safetensors",
|
| 1031 |
+
"model.layers.7.self_attn.v_proj.weight": "model-00005-of-00013.safetensors",
|
| 1032 |
+
"model.layers.8.input_layernorm.weight": "model-00006-of-00013.safetensors",
|
| 1033 |
+
"model.layers.8.mlp.experts.down_proj.bias": "model-00006-of-00013.safetensors",
|
| 1034 |
+
"model.layers.8.mlp.experts.down_proj.scales": "model-00006-of-00013.safetensors",
|
| 1035 |
+
"model.layers.8.mlp.experts.down_proj.weight": "model-00006-of-00013.safetensors",
|
| 1036 |
+
"model.layers.8.mlp.experts.gate_proj.bias": "model-00006-of-00013.safetensors",
|
| 1037 |
+
"model.layers.8.mlp.experts.gate_proj.scales": "model-00006-of-00013.safetensors",
|
| 1038 |
+
"model.layers.8.mlp.experts.gate_proj.weight": "model-00006-of-00013.safetensors",
|
| 1039 |
+
"model.layers.8.mlp.experts.up_proj.bias": "model-00006-of-00013.safetensors",
|
| 1040 |
+
"model.layers.8.mlp.experts.up_proj.scales": "model-00006-of-00013.safetensors",
|
| 1041 |
+
"model.layers.8.mlp.experts.up_proj.weight": "model-00006-of-00013.safetensors",
|
| 1042 |
+
"model.layers.8.mlp.router.bias": "model-00006-of-00013.safetensors",
|
| 1043 |
+
"model.layers.8.mlp.router.weight": "model-00006-of-00013.safetensors",
|
| 1044 |
+
"model.layers.8.post_attention_layernorm.weight": "model-00006-of-00013.safetensors",
|
| 1045 |
+
"model.layers.8.self_attn.k_proj.bias": "model-00006-of-00013.safetensors",
|
| 1046 |
+
"model.layers.8.self_attn.k_proj.biases": "model-00006-of-00013.safetensors",
|
| 1047 |
+
"model.layers.8.self_attn.k_proj.scales": "model-00006-of-00013.safetensors",
|
| 1048 |
+
"model.layers.8.self_attn.k_proj.weight": "model-00006-of-00013.safetensors",
|
| 1049 |
+
"model.layers.8.self_attn.o_proj.bias": "model-00006-of-00013.safetensors",
|
| 1050 |
+
"model.layers.8.self_attn.o_proj.biases": "model-00006-of-00013.safetensors",
|
| 1051 |
+
"model.layers.8.self_attn.o_proj.scales": "model-00006-of-00013.safetensors",
|
| 1052 |
+
"model.layers.8.self_attn.o_proj.weight": "model-00006-of-00013.safetensors",
|
| 1053 |
+
"model.layers.8.self_attn.q_proj.bias": "model-00006-of-00013.safetensors",
|
| 1054 |
+
"model.layers.8.self_attn.q_proj.biases": "model-00006-of-00013.safetensors",
|
| 1055 |
+
"model.layers.8.self_attn.q_proj.scales": "model-00006-of-00013.safetensors",
|
| 1056 |
+
"model.layers.8.self_attn.q_proj.weight": "model-00006-of-00013.safetensors",
|
| 1057 |
+
"model.layers.8.self_attn.sinks": "model-00006-of-00013.safetensors",
|
| 1058 |
+
"model.layers.8.self_attn.v_proj.bias": "model-00006-of-00013.safetensors",
|
| 1059 |
+
"model.layers.8.self_attn.v_proj.biases": "model-00006-of-00013.safetensors",
|
| 1060 |
+
"model.layers.8.self_attn.v_proj.scales": "model-00006-of-00013.safetensors",
|
| 1061 |
+
"model.layers.8.self_attn.v_proj.weight": "model-00006-of-00013.safetensors",
|
| 1062 |
+
"model.layers.9.input_layernorm.weight": "model-00006-of-00013.safetensors",
|
| 1063 |
+
"model.layers.9.mlp.experts.down_proj.bias": "model-00006-of-00013.safetensors",
|
| 1064 |
+
"model.layers.9.mlp.experts.down_proj.scales": "model-00007-of-00013.safetensors",
|
| 1065 |
+
"model.layers.9.mlp.experts.down_proj.weight": "model-00007-of-00013.safetensors",
|
| 1066 |
+
"model.layers.9.mlp.experts.gate_proj.bias": "model-00006-of-00013.safetensors",
|
| 1067 |
+
"model.layers.9.mlp.experts.gate_proj.scales": "model-00006-of-00013.safetensors",
|
| 1068 |
+
"model.layers.9.mlp.experts.gate_proj.weight": "model-00006-of-00013.safetensors",
|
| 1069 |
+
"model.layers.9.mlp.experts.up_proj.bias": "model-00006-of-00013.safetensors",
|
| 1070 |
+
"model.layers.9.mlp.experts.up_proj.scales": "model-00006-of-00013.safetensors",
|
| 1071 |
+
"model.layers.9.mlp.experts.up_proj.weight": "model-00006-of-00013.safetensors",
|
| 1072 |
+
"model.layers.9.mlp.router.bias": "model-00006-of-00013.safetensors",
|
| 1073 |
+
"model.layers.9.mlp.router.weight": "model-00006-of-00013.safetensors",
|
| 1074 |
+
"model.layers.9.post_attention_layernorm.weight": "model-00006-of-00013.safetensors",
|
| 1075 |
+
"model.layers.9.self_attn.k_proj.bias": "model-00006-of-00013.safetensors",
|
| 1076 |
+
"model.layers.9.self_attn.k_proj.biases": "model-00006-of-00013.safetensors",
|
| 1077 |
+
"model.layers.9.self_attn.k_proj.scales": "model-00006-of-00013.safetensors",
|
| 1078 |
+
"model.layers.9.self_attn.k_proj.weight": "model-00006-of-00013.safetensors",
|
| 1079 |
+
"model.layers.9.self_attn.o_proj.bias": "model-00006-of-00013.safetensors",
|
| 1080 |
+
"model.layers.9.self_attn.o_proj.biases": "model-00006-of-00013.safetensors",
|
| 1081 |
+
"model.layers.9.self_attn.o_proj.scales": "model-00006-of-00013.safetensors",
|
| 1082 |
+
"model.layers.9.self_attn.o_proj.weight": "model-00006-of-00013.safetensors",
|
| 1083 |
+
"model.layers.9.self_attn.q_proj.bias": "model-00006-of-00013.safetensors",
|
| 1084 |
+
"model.layers.9.self_attn.q_proj.biases": "model-00006-of-00013.safetensors",
|
| 1085 |
+
"model.layers.9.self_attn.q_proj.scales": "model-00006-of-00013.safetensors",
|
| 1086 |
+
"model.layers.9.self_attn.q_proj.weight": "model-00006-of-00013.safetensors",
|
| 1087 |
+
"model.layers.9.self_attn.sinks": "model-00006-of-00013.safetensors",
|
| 1088 |
+
"model.layers.9.self_attn.v_proj.bias": "model-00006-of-00013.safetensors",
|
| 1089 |
+
"model.layers.9.self_attn.v_proj.biases": "model-00006-of-00013.safetensors",
|
| 1090 |
+
"model.layers.9.self_attn.v_proj.scales": "model-00006-of-00013.safetensors",
|
| 1091 |
+
"model.layers.9.self_attn.v_proj.weight": "model-00006-of-00013.safetensors",
|
| 1092 |
+
"model.norm.weight": "model-00011-of-00013.safetensors"
|
| 1093 |
+
}
|
| 1094 |
+
}
|
omlx_oQ4_manifest.json
ADDED
|
@@ -0,0 +1,7 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"source": "/Users/cjnielson/.cache/huggingface/hub/gpt-oss-120b",
|
| 3 |
+
"output": "/Users/cjnielson/.cache/huggingface/hub/gpt-oss-120b-oQ4",
|
| 4 |
+
"oq_level": "oQ4",
|
| 5 |
+
"dtype": "bfloat16",
|
| 6 |
+
"elapsed_seconds": 71.5
|
| 7 |
+
}
|
special_tokens_map.json
ADDED
|
@@ -0,0 +1,5 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"bos_token": "<|startoftext|>",
|
| 3 |
+
"eos_token": "<|return|>",
|
| 4 |
+
"pad_token": "<|endoftext|>"
|
| 5 |
+
}
|
tokenizer.json
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:0614fe83cadab421296e664e1f48f4261fa8fef6e03e63bb75c20f38e37d07d3
|
| 3 |
+
size 27868174
|
tokenizer_config.json
ADDED
|
@@ -0,0 +1,183 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"added_tokens_decoder": {
|
| 3 |
+
"199998": {
|
| 4 |
+
"content": "<|startoftext|>",
|
| 5 |
+
"lstrip": false,
|
| 6 |
+
"normalized": false,
|
| 7 |
+
"rstrip": false,
|
| 8 |
+
"single_word": false,
|
| 9 |
+
"special": true
|
| 10 |
+
},
|
| 11 |
+
"199999": {
|
| 12 |
+
"content": "<|endoftext|>",
|
| 13 |
+
"lstrip": false,
|
| 14 |
+
"normalized": false,
|
| 15 |
+
"rstrip": false,
|
| 16 |
+
"single_word": false,
|
| 17 |
+
"special": true
|
| 18 |
+
},
|
| 19 |
+
"200000": {
|
| 20 |
+
"content": "<|reserved_200000|>",
|
| 21 |
+
"lstrip": false,
|
| 22 |
+
"normalized": false,
|
| 23 |
+
"rstrip": false,
|
| 24 |
+
"single_word": false,
|
| 25 |
+
"special": true
|
| 26 |
+
},
|
| 27 |
+
"200001": {
|
| 28 |
+
"content": "<|reserved_200001|>",
|
| 29 |
+
"lstrip": false,
|
| 30 |
+
"normalized": false,
|
| 31 |
+
"rstrip": false,
|
| 32 |
+
"single_word": false,
|
| 33 |
+
"special": true
|
| 34 |
+
},
|
| 35 |
+
"200002": {
|
| 36 |
+
"content": "<|return|>",
|
| 37 |
+
"lstrip": false,
|
| 38 |
+
"normalized": false,
|
| 39 |
+
"rstrip": false,
|
| 40 |
+
"single_word": false,
|
| 41 |
+
"special": true
|
| 42 |
+
},
|
| 43 |
+
"200003": {
|
| 44 |
+
"content": "<|constrain|>",
|
| 45 |
+
"lstrip": false,
|
| 46 |
+
"normalized": false,
|
| 47 |
+
"rstrip": false,
|
| 48 |
+
"single_word": false,
|
| 49 |
+
"special": true
|
| 50 |
+
},
|
| 51 |
+
"200004": {
|
| 52 |
+
"content": "<|reserved_200004|>",
|
| 53 |
+
"lstrip": false,
|
| 54 |
+
"normalized": false,
|
| 55 |
+
"rstrip": false,
|
| 56 |
+
"single_word": false,
|
| 57 |
+
"special": true
|
| 58 |
+
},
|
| 59 |
+
"200005": {
|
| 60 |
+
"content": "<|channel|>",
|
| 61 |
+
"lstrip": false,
|
| 62 |
+
"normalized": false,
|
| 63 |
+
"rstrip": false,
|
| 64 |
+
"single_word": false,
|
| 65 |
+
"special": true
|
| 66 |
+
},
|
| 67 |
+
"200006": {
|
| 68 |
+
"content": "<|start|>",
|
| 69 |
+
"lstrip": false,
|
| 70 |
+
"normalized": false,
|
| 71 |
+
"rstrip": false,
|
| 72 |
+
"single_word": false,
|
| 73 |
+
"special": true
|
| 74 |
+
},
|
| 75 |
+
"200007": {
|
| 76 |
+
"content": "<|end|>",
|
| 77 |
+
"lstrip": false,
|
| 78 |
+
"normalized": false,
|
| 79 |
+
"rstrip": false,
|
| 80 |
+
"single_word": false,
|
| 81 |
+
"special": true
|
| 82 |
+
},
|
| 83 |
+
"200008": {
|
| 84 |
+
"content": "<|message|>",
|
| 85 |
+
"lstrip": false,
|
| 86 |
+
"normalized": false,
|
| 87 |
+
"rstrip": false,
|
| 88 |
+
"single_word": false,
|
| 89 |
+
"special": true
|
| 90 |
+
},
|
| 91 |
+
"200009": {
|
| 92 |
+
"content": "<|reserved_200009|>",
|
| 93 |
+
"lstrip": false,
|
| 94 |
+
"normalized": false,
|
| 95 |
+
"rstrip": false,
|
| 96 |
+
"single_word": false,
|
| 97 |
+
"special": true
|
| 98 |
+
},
|
| 99 |
+
"200010": {
|
| 100 |
+
"content": "<|reserved_200010|>",
|
| 101 |
+
"lstrip": false,
|
| 102 |
+
"normalized": false,
|
| 103 |
+
"rstrip": false,
|
| 104 |
+
"single_word": false,
|
| 105 |
+
"special": true
|
| 106 |
+
},
|
| 107 |
+
"200011": {
|
| 108 |
+
"content": "<|reserved_200011|>",
|
| 109 |
+
"lstrip": false,
|
| 110 |
+
"normalized": false,
|
| 111 |
+
"rstrip": false,
|
| 112 |
+
"single_word": false,
|
| 113 |
+
"special": true
|
| 114 |
+
},
|
| 115 |
+
"200012": {
|
| 116 |
+
"content": "<|call|>",
|
| 117 |
+
"lstrip": false,
|
| 118 |
+
"normalized": false,
|
| 119 |
+
"rstrip": false,
|
| 120 |
+
"single_word": false,
|
| 121 |
+
"special": true
|
| 122 |
+
},
|
| 123 |
+
"200013": {
|
| 124 |
+
"content": "<|reserved_200013|>",
|
| 125 |
+
"lstrip": false,
|
| 126 |
+
"normalized": false,
|
| 127 |
+
"rstrip": false,
|
| 128 |
+
"single_word": false,
|
| 129 |
+
"special": true
|
| 130 |
+
},
|
| 131 |
+
"200014": {
|
| 132 |
+
"content": "<|reserved_200014|>",
|
| 133 |
+
"lstrip": false,
|
| 134 |
+
"normalized": false,
|
| 135 |
+
"rstrip": false,
|
| 136 |
+
"single_word": false,
|
| 137 |
+
"special": true
|
| 138 |
+
},
|
| 139 |
+
"200015": {
|
| 140 |
+
"content": "<|reserved_200015|>",
|
| 141 |
+
"lstrip": false,
|
| 142 |
+
"normalized": false,
|
| 143 |
+
"rstrip": false,
|
| 144 |
+
"single_word": false,
|
| 145 |
+
"special": true
|
| 146 |
+
},
|
| 147 |
+
"200016": {
|
| 148 |
+
"content": "<|reserved_200016|>",
|
| 149 |
+
"lstrip": false,
|
| 150 |
+
"normalized": false,
|
| 151 |
+
"rstrip": false,
|
| 152 |
+
"single_word": false,
|
| 153 |
+
"special": true
|
| 154 |
+
},
|
| 155 |
+
"200017": {
|
| 156 |
+
"content": "<|reserved_200017|>",
|
| 157 |
+
"lstrip": false,
|
| 158 |
+
"normalized": false,
|
| 159 |
+
"rstrip": false,
|
| 160 |
+
"single_word": false,
|
| 161 |
+
"special": true
|
| 162 |
+
},
|
| 163 |
+
"200018": {
|
| 164 |
+
"content": "<|endofprompt|>",
|
| 165 |
+
"lstrip": false,
|
| 166 |
+
"normalized": false,
|
| 167 |
+
"rstrip": false,
|
| 168 |
+
"single_word": false,
|
| 169 |
+
"special": true
|
| 170 |
+
}
|
| 171 |
+
},
|
| 172 |
+
"bos_token": "<|startoftext|>",
|
| 173 |
+
"clean_up_tokenization_spaces": false,
|
| 174 |
+
"eos_token": "<|return|>",
|
| 175 |
+
"extra_special_tokens": {},
|
| 176 |
+
"model_input_names": [
|
| 177 |
+
"input_ids",
|
| 178 |
+
"attention_mask"
|
| 179 |
+
],
|
| 180 |
+
"model_max_length": 1000000000000000019884624838656,
|
| 181 |
+
"pad_token": "<|endoftext|>",
|
| 182 |
+
"tokenizer_class": "PreTrainedTokenizerFast"
|
| 183 |
+
}
|