Upload folder using huggingface_hub
Browse files- .gitattributes +1 -0
- README.md +37 -0
- chat_template.jinja +195 -0
- config.json +83 -0
- generation_config.json +13 -0
- model-00001-of-00007.safetensors +3 -0
- model-00002-of-00007.safetensors +3 -0
- model-00003-of-00007.safetensors +3 -0
- model-00004-of-00007.safetensors +3 -0
- model-00005-of-00007.safetensors +3 -0
- model-00006-of-00007.safetensors +3 -0
- model-00007-of-00007.safetensors +3 -0
- model.safetensors.index.json +737 -0
- tokenizer.json +3 -0
- tokenizer_config.json +18 -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 +1,37 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
library_name: mlx
|
| 3 |
+
license: apache-2.0
|
| 4 |
+
pipeline_tag: text-generation
|
| 5 |
+
base_model: fastino/Fastino-Nemotron-3.5-Lightning-Finance
|
| 6 |
+
tags:
|
| 7 |
+
- mlx
|
| 8 |
+
- nemotron_h
|
| 9 |
+
- 8-bit
|
| 10 |
+
---
|
| 11 |
+
|
| 12 |
+
# Fastino-Nemotron-3.5-Lightning-Finance-MLX-8bit
|
| 13 |
+
|
| 14 |
+
This model was converted to MLX format from [fastino/Fastino-Nemotron-3.5-Lightning-Finance](https://huggingface.co/fastino/Fastino-Nemotron-3.5-Lightning-Finance) using mlx-lm version **0.31.3**.
|
| 15 |
+
|
| 16 |
+
| Property | Value |
|
| 17 |
+
|----------|-------|
|
| 18 |
+
| Quantization | 8-bit affine |
|
| 19 |
+
| Group size | 64 |
|
| 20 |
+
|
| 21 |
+
## Use with mlx
|
| 22 |
+
|
| 23 |
+
```bash
|
| 24 |
+
pip install mlx-lm
|
| 25 |
+
mlx_lm.generate --model Fastino-Nemotron-3.5-Lightning-Finance-MLX-8bit --prompt "Hello"
|
| 26 |
+
```
|
| 27 |
+
|
| 28 |
+
```python
|
| 29 |
+
from mlx_lm import load, generate
|
| 30 |
+
|
| 31 |
+
model, tokenizer = load("Fastino-Nemotron-3.5-Lightning-Finance-MLX-8bit")
|
| 32 |
+
prompt = "Hello"
|
| 33 |
+
if tokenizer.chat_template is not None:
|
| 34 |
+
messages = [{"role": "user", "content": prompt}]
|
| 35 |
+
prompt = tokenizer.apply_chat_template(messages, add_generation_prompt=True)
|
| 36 |
+
response = generate(model, tokenizer, prompt=prompt, verbose=True)
|
| 37 |
+
```
|
chat_template.jinja
ADDED
|
@@ -0,0 +1,195 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{% macro render_extra_keys(json_dict, handled_keys) %}
|
| 2 |
+
{%- if json_dict is mapping %}
|
| 3 |
+
{%- for json_key in json_dict if json_key not in handled_keys %}
|
| 4 |
+
{%- if json_dict[json_key] is mapping or (json_dict[json_key] is sequence and json_dict[json_key] is not string) %}
|
| 5 |
+
{{- '\n<' ~ json_key ~ '>' ~ (json_dict[json_key] | tojson | safe) ~ '</' ~ json_key ~ '>' }}
|
| 6 |
+
{%- else %}
|
| 7 |
+
{{-'\n<' ~ json_key ~ '>' ~ (json_dict[json_key] | string) ~ '</' ~ json_key ~ '>' }}
|
| 8 |
+
{%- endif %}
|
| 9 |
+
{%- endfor %}
|
| 10 |
+
{%- endif %}
|
| 11 |
+
{% endmacro %}
|
| 12 |
+
{%- set enable_thinking = enable_thinking if enable_thinking is defined else True %}
|
| 13 |
+
{%- set medium_effort = medium_effort if medium_effort is defined else False %}
|
| 14 |
+
{%- set truncate_history_thinking = truncate_history_thinking if truncate_history_thinking is defined else True %}
|
| 15 |
+
{%- set ns = namespace(last_user_idx = -1) %}
|
| 16 |
+
{%- set loop_messages = messages %}
|
| 17 |
+
{%- for m in loop_messages %}
|
| 18 |
+
{%- if m["role"] == "user" %}
|
| 19 |
+
{%- set ns.last_user_idx = loop.index0 %}
|
| 20 |
+
{%- endif %}
|
| 21 |
+
{%- endfor %}
|
| 22 |
+
{%- if messages[0]["role"] == "system" %}
|
| 23 |
+
{%- set system_message = messages[0]["content"] %}
|
| 24 |
+
{%- set loop_messages = messages[1:] %}
|
| 25 |
+
{%- else %}
|
| 26 |
+
{%- set system_message = "" %}
|
| 27 |
+
{%- set loop_messages = messages %}
|
| 28 |
+
{%- endif %}
|
| 29 |
+
{%- if not tools is defined %}
|
| 30 |
+
{%- set tools = [] %}
|
| 31 |
+
{%- endif %}
|
| 32 |
+
{%- set ns = namespace(last_user_idx = -1) %}
|
| 33 |
+
{%- for m in loop_messages %}
|
| 34 |
+
{%- if m["role"] == "user" %}
|
| 35 |
+
{%- set ns.last_user_idx = loop.index0 %}
|
| 36 |
+
{%- endif %}
|
| 37 |
+
{%- endfor %}
|
| 38 |
+
{%- if system_message is defined %}
|
| 39 |
+
{{- "<|im_start|>system\n" + system_message }}
|
| 40 |
+
{%- else %}
|
| 41 |
+
{%- if tools is iterable and tools | length > 0 %}
|
| 42 |
+
{{- "<|im_start|>system\n" }}
|
| 43 |
+
{%- endif %}
|
| 44 |
+
{%- endif %}
|
| 45 |
+
{%- if tools is iterable and tools | length > 0 %}
|
| 46 |
+
{%- if system_message is defined and system_message | length > 0 %}
|
| 47 |
+
{{- "\n\n" }}
|
| 48 |
+
{%- endif %}
|
| 49 |
+
{{- "# Tools\n\nYou have access to the following functions:\n\n" }}
|
| 50 |
+
{{- "<tools>" }}
|
| 51 |
+
{%- for tool in tools %}
|
| 52 |
+
{%- if tool.function is defined %}
|
| 53 |
+
{%- set tool = tool.function %}
|
| 54 |
+
{%- endif %}
|
| 55 |
+
{{- "\n<function>\n<name>" ~ tool.name ~ "</name>" }}
|
| 56 |
+
{%- if tool.description is defined %}
|
| 57 |
+
{{- '\n<description>' ~ (tool.description | trim) ~ '</description>' }}
|
| 58 |
+
{%- endif %}
|
| 59 |
+
{{- '\n<parameters>' }}
|
| 60 |
+
{%- if tool.parameters is defined and tool.parameters is mapping and tool.parameters.properties is defined and tool.parameters.properties is mapping %}
|
| 61 |
+
{%- for param_name, param_fields in tool.parameters.properties|items %}
|
| 62 |
+
{{- '\n<parameter>' }}
|
| 63 |
+
{{- '\n<name>' ~ param_name ~ '</name>' }}
|
| 64 |
+
{%- if param_fields.type is defined %}
|
| 65 |
+
{{- '\n<type>' ~ (param_fields.type | string) ~ '</type>' }}
|
| 66 |
+
{%- endif %}
|
| 67 |
+
{%- if param_fields.description is defined %}
|
| 68 |
+
{{- '\n<description>' ~ (param_fields.description | trim) ~ '</description>' }}
|
| 69 |
+
{%- endif %}
|
| 70 |
+
{%- if param_fields.enum is defined %}
|
| 71 |
+
{{- '\n<enum>' ~ (param_fields.enum | tojson | safe) ~ '</enum>' }}
|
| 72 |
+
{%- endif %}
|
| 73 |
+
{%- set handled_keys = ['name', 'type', 'description', 'enum'] %}
|
| 74 |
+
{{- render_extra_keys(param_fields, handled_keys) }}
|
| 75 |
+
{{- '\n</parameter>' }}
|
| 76 |
+
{%- endfor %}
|
| 77 |
+
{%- endif %}
|
| 78 |
+
{% set handled_keys = ['type', 'properties', 'required'] %}
|
| 79 |
+
{{- render_extra_keys(tool.parameters, handled_keys) }}
|
| 80 |
+
{%- if tool.parameters is defined and tool.parameters.required is defined %}
|
| 81 |
+
{{- '\n<required>' ~ (tool.parameters.required | tojson | safe) ~ '</required>' }}
|
| 82 |
+
{%- endif %}
|
| 83 |
+
{{- '\n</parameters>' }}
|
| 84 |
+
{%- set handled_keys = ['type', 'name', 'description', 'parameters'] %}
|
| 85 |
+
{{- render_extra_keys(tool, handled_keys) }}
|
| 86 |
+
{{- '\n</function>' }}
|
| 87 |
+
{%- endfor %}
|
| 88 |
+
{{- "\n</tools>" }}
|
| 89 |
+
{{- '\n\nIf you choose to call a function ONLY reply in the following format with NO suffix:\n\n<tool_call>\n<function=example_function_name>\n<parameter=example_parameter_1>\nvalue_1\n</parameter>\n<parameter=example_parameter_2>\nThis is the value for the second parameter\nthat can span\nmultiple lines\n</parameter>\n</function>\n</tool_call>\n\n<IMPORTANT>\nReminder:\n- Function calls MUST follow the specified format: an inner <function=...></function> block must be nested within <tool_call></tool_call> XML tags\n- Required parameters MUST be specified\n- You may provide optional reasoning for your function call in natural language BEFORE the function call, but NOT after\n- If there is no function call available, answer the question like normal with your current knowledge and do not tell the user about function calls\n</IMPORTANT>' }}
|
| 90 |
+
{%- endif %}
|
| 91 |
+
{%- if system_message is defined %}
|
| 92 |
+
{{- '<|im_end|>\n' }}
|
| 93 |
+
{%- else %}
|
| 94 |
+
{%- if tools is iterable and tools | length > 0 %}
|
| 95 |
+
{{- '<|im_end|>\n' }}
|
| 96 |
+
{%- endif %}
|
| 97 |
+
{%- endif %}
|
| 98 |
+
{%- for message in loop_messages %}
|
| 99 |
+
{%- if message.role == "assistant" %}
|
| 100 |
+
{%- if message.reasoning_content is defined and message.reasoning_content is string and message.reasoning_content | trim | length > 0 %}
|
| 101 |
+
{%- set content = "<think>\n" ~ message.reasoning_content ~ "</think>" ~ (message.content | default('', true)) %}
|
| 102 |
+
{%- else %}
|
| 103 |
+
{%- set content = message.content | default('', true) %}
|
| 104 |
+
{%- if content is string -%}
|
| 105 |
+
{%- if '<think>' not in content and '</think>' not in content -%}
|
| 106 |
+
{%- set content = "<think></think>" ~ content -%}
|
| 107 |
+
{%- endif -%}
|
| 108 |
+
{%- else -%}
|
| 109 |
+
{%- set content = content -%}
|
| 110 |
+
{%- endif -%}
|
| 111 |
+
{%- endif %}
|
| 112 |
+
{%- if message.tool_calls is defined and message.tool_calls is iterable and message.tool_calls | length > 0 %}
|
| 113 |
+
{{- '<|im_start|>assistant\n' }}
|
| 114 |
+
{%- set include_content = not (truncate_history_thinking and loop.index0 < ns.last_user_idx) %}
|
| 115 |
+
{%- if content is string and content | trim | length > 0 %}
|
| 116 |
+
{%- if include_content %}
|
| 117 |
+
{{- (content | trim) ~ '\n' -}}
|
| 118 |
+
{%- else %}
|
| 119 |
+
{%- set c = (content | string) %}
|
| 120 |
+
{%- if '</think>' in c %}
|
| 121 |
+
{%- set c = c.split('</think>')[-1] %}
|
| 122 |
+
{%- elif '<think>' in c %}
|
| 123 |
+
{%- set c = c.split('<think>')[0] %}
|
| 124 |
+
{%- endif %}
|
| 125 |
+
{%- set c = "<think></think>" ~ c %}
|
| 126 |
+
{%- if c | length > 0 %}
|
| 127 |
+
{{- c ~ '\n' -}}
|
| 128 |
+
{%- endif %}
|
| 129 |
+
{%- endif %}
|
| 130 |
+
{%- else %}
|
| 131 |
+
{{- "<think></think>" -}}
|
| 132 |
+
{%- endif %}
|
| 133 |
+
{%- for tool_call in message.tool_calls %}
|
| 134 |
+
{%- if tool_call.function is defined %}
|
| 135 |
+
{%- set tool_call = tool_call.function %}
|
| 136 |
+
{%- endif %}
|
| 137 |
+
{{- '<tool_call>\n<function=' ~ tool_call.name ~ '>\n' -}}
|
| 138 |
+
{%- if tool_call.arguments is defined %}
|
| 139 |
+
{%- for args_name, args_value in tool_call.arguments|items %}
|
| 140 |
+
{{- '<parameter=' ~ args_name ~ '>\n' -}}
|
| 141 |
+
{%- set args_value = args_value | tojson | safe if args_value is mapping or (args_value is sequence and args_value is not string) else args_value | string %}
|
| 142 |
+
{{- args_value ~ '\n</parameter>\n' -}}
|
| 143 |
+
{%- endfor %}
|
| 144 |
+
{%- endif %}
|
| 145 |
+
{{- '</function>\n</tool_call>\n' -}}
|
| 146 |
+
{%- endfor %}
|
| 147 |
+
{{- '<|im_end|>\n' }}
|
| 148 |
+
{%- else %}
|
| 149 |
+
{%- if not (truncate_history_thinking and loop.index0 < ns.last_user_idx) %}
|
| 150 |
+
{{- '<|im_start|>assistant\n' ~ (content | default('', true) | string | trim) ~ '<|im_end|>\n' }}
|
| 151 |
+
{%- else %}
|
| 152 |
+
{%- set c = (content | default('', true) | string) %}
|
| 153 |
+
{%- if '<think>' in c and '</think>' in c %}
|
| 154 |
+
{%- set c = "<think></think>" ~ c.split('</think>')[-1] %}
|
| 155 |
+
{%- endif %}
|
| 156 |
+
{%- set c = c | trim %}
|
| 157 |
+
{%- if c | length > 0 %}
|
| 158 |
+
{{- '<|im_start|>assistant\n' ~ c ~ '<|im_end|>\n' }}
|
| 159 |
+
{%- else %}
|
| 160 |
+
{{- '<|im_start|>assistant\n<|im_end|>\n' }}
|
| 161 |
+
{%- endif %}
|
| 162 |
+
{%- endif %}
|
| 163 |
+
{%- endif %}
|
| 164 |
+
{%- elif message.role == "user" or message.role == "system" %}
|
| 165 |
+
{{- '<|im_start|>' + message.role + '\n' }}
|
| 166 |
+
{%- set content = message.content | string %}
|
| 167 |
+
{%- if message.role == "user" and loop.index0 == ns.last_user_idx and medium_effort %}
|
| 168 |
+
{{- content + '\n\n{reasoning effort: efficient}' }}
|
| 169 |
+
{%- else %}
|
| 170 |
+
{{- content }}
|
| 171 |
+
{%- endif %}
|
| 172 |
+
{{- '<|im_end|>\n' }}
|
| 173 |
+
{%- elif message.role == "tool" %}
|
| 174 |
+
{%- if loop.previtem and loop.previtem.role != "tool" %}
|
| 175 |
+
{{- '<|im_start|>user\n' }}
|
| 176 |
+
{%- endif %}
|
| 177 |
+
{{- '<tool_response>\n' }}
|
| 178 |
+
{{- message.content }}
|
| 179 |
+
{{- '\n</tool_response>\n' }}
|
| 180 |
+
{%- if not loop.last and loop.nextitem.role != "tool" %}
|
| 181 |
+
{{- '<|im_end|>\n' }}
|
| 182 |
+
{%- elif loop.last %}
|
| 183 |
+
{{- '<|im_end|>\n' }}
|
| 184 |
+
{%- endif %}
|
| 185 |
+
{%- else %}
|
| 186 |
+
{{- '<|im_start|>' + message.role + '\n' + message.content + '<|im_end|>\n' }}
|
| 187 |
+
{%- endif %}
|
| 188 |
+
{%- endfor %}
|
| 189 |
+
{%- if add_generation_prompt %}
|
| 190 |
+
{%- if enable_thinking %}
|
| 191 |
+
{{- '<|im_start|>assistant\n<think>\n' }}
|
| 192 |
+
{%- else %}
|
| 193 |
+
{{- '<|im_start|>assistant\n<think></think>' }}
|
| 194 |
+
{%- endif %}
|
| 195 |
+
{%- endif %}
|
config.json
ADDED
|
@@ -0,0 +1,83 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"architectures": [
|
| 3 |
+
"NemotronHForCausalLM"
|
| 4 |
+
],
|
| 5 |
+
"attention_bias": false,
|
| 6 |
+
"attention_dropout": 0.0,
|
| 7 |
+
"auto_map": {
|
| 8 |
+
"AutoConfig": "configuration_nemotron_h.NemotronHConfig",
|
| 9 |
+
"AutoModel": "modeling_nemotron_h.NemotronHForCausalLM",
|
| 10 |
+
"AutoModelForCausalLM": "modeling_nemotron_h.NemotronHForCausalLM"
|
| 11 |
+
},
|
| 12 |
+
"bos_token_id": 1,
|
| 13 |
+
"chunk_size": 128,
|
| 14 |
+
"conv_kernel": 4,
|
| 15 |
+
"dtype": "bfloat16",
|
| 16 |
+
"eos_token_id": [
|
| 17 |
+
2,
|
| 18 |
+
11
|
| 19 |
+
],
|
| 20 |
+
"expand": 2,
|
| 21 |
+
"head_dim": 128,
|
| 22 |
+
"hidden_dropout": 0.0,
|
| 23 |
+
"hidden_size": 2688,
|
| 24 |
+
"hybrid_override_pattern": "MEMEM*EMEMEM*EMEMEM*EMEMEM*EMEMEM*EMEMEMEM*EMEMEMEME",
|
| 25 |
+
"initializer_range": 0.02,
|
| 26 |
+
"intermediate_size": 1856,
|
| 27 |
+
"layer_norm_epsilon": 1e-05,
|
| 28 |
+
"mamba_head_dim": 64,
|
| 29 |
+
"mamba_hidden_act": "silu",
|
| 30 |
+
"mamba_num_heads": 64,
|
| 31 |
+
"mamba_proj_bias": false,
|
| 32 |
+
"mamba_ssm_cache_dtype": "float32",
|
| 33 |
+
"max_position_embeddings": 262144,
|
| 34 |
+
"mlp_bias": false,
|
| 35 |
+
"mlp_hidden_act": "relu2",
|
| 36 |
+
"model_type": "nemotron_h",
|
| 37 |
+
"moe_intermediate_size": 1856,
|
| 38 |
+
"moe_latent_size": null,
|
| 39 |
+
"moe_shared_expert_intermediate_size": 3712,
|
| 40 |
+
"moe_shared_expert_overlap": true,
|
| 41 |
+
"mtp_hybrid_override_pattern": "*E",
|
| 42 |
+
"n_group": 1,
|
| 43 |
+
"n_groups": 8,
|
| 44 |
+
"n_routed_experts": 128,
|
| 45 |
+
"n_shared_experts": 1,
|
| 46 |
+
"norm_eps": 1e-05,
|
| 47 |
+
"norm_topk_prob": true,
|
| 48 |
+
"num_attention_heads": 32,
|
| 49 |
+
"num_experts_per_tok": 6,
|
| 50 |
+
"num_hidden_layers": 52,
|
| 51 |
+
"num_key_value_heads": 2,
|
| 52 |
+
"num_logits_to_keep": 1,
|
| 53 |
+
"num_nextn_predict_layers": 1,
|
| 54 |
+
"pad_token_id": 0,
|
| 55 |
+
"partial_rotary_factor": 1.0,
|
| 56 |
+
"quantization": {
|
| 57 |
+
"group_size": 64,
|
| 58 |
+
"bits": 8,
|
| 59 |
+
"mode": "affine"
|
| 60 |
+
},
|
| 61 |
+
"quantization_config": {
|
| 62 |
+
"group_size": 64,
|
| 63 |
+
"bits": 8,
|
| 64 |
+
"mode": "affine"
|
| 65 |
+
},
|
| 66 |
+
"rescale_prenorm_residual": true,
|
| 67 |
+
"residual_in_fp32": false,
|
| 68 |
+
"rope_theta": 10000,
|
| 69 |
+
"routed_scaling_factor": 2.5,
|
| 70 |
+
"sliding_window": null,
|
| 71 |
+
"ssm_state_size": 128,
|
| 72 |
+
"tie_word_embeddings": false,
|
| 73 |
+
"time_step_floor": 0.0001,
|
| 74 |
+
"time_step_max": 0.1,
|
| 75 |
+
"time_step_min": 0.001,
|
| 76 |
+
"topk_group": 1,
|
| 77 |
+
"transformers_version": "4.57.6",
|
| 78 |
+
"use_bias": false,
|
| 79 |
+
"use_cache": true,
|
| 80 |
+
"use_conv_bias": true,
|
| 81 |
+
"use_mamba_kernels": true,
|
| 82 |
+
"vocab_size": 131072
|
| 83 |
+
}
|
generation_config.json
ADDED
|
@@ -0,0 +1,13 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_from_model_config": true,
|
| 3 |
+
"bos_token_id": 1,
|
| 4 |
+
"do_sample": true,
|
| 5 |
+
"eos_token_id": [
|
| 6 |
+
2,
|
| 7 |
+
11
|
| 8 |
+
],
|
| 9 |
+
"pad_token_id": 0,
|
| 10 |
+
"top_p": 0.95,
|
| 11 |
+
"transformers_version": "4.57.6",
|
| 12 |
+
"temperature": 1.0
|
| 13 |
+
}
|
model-00001-of-00007.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:0d92800bd01c17a58e5411b4b0ce14622ad5b6ee2801e03620590056fbbdbd13
|
| 3 |
+
size 5359226316
|
model-00002-of-00007.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:ffb043c40f645bcd1ab05184e55a2459c568394a701e07e94eda4a19139b9f14
|
| 3 |
+
size 5046688726
|
model-00003-of-00007.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:c0bb98ef08dea8192a4bb34d267ef18a4cd95cc20cf4449eb99d23d7902535d1
|
| 3 |
+
size 4963631598
|
model-00004-of-00007.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:293d6e454eed6724d39e7ed802b6977a3e2cd32df76e37cbf971992f41baca05
|
| 3 |
+
size 5051598289
|
model-00005-of-00007.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:55317540965995a8b379bf1634537be7b12a938442817ae3271957e309811e76
|
| 3 |
+
size 4938766121
|
model-00006-of-00007.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:d89238ca73f8348f6709233cb0950038657f6ced97a539b64bccf7ecceae3c44
|
| 3 |
+
size 5026732862
|
model-00007-of-00007.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:01f8ea7536c1e4332311bf4854159d99a25417f0d886dd3a4b9346c1e2754f22
|
| 3 |
+
size 3173319638
|
model.safetensors.index.json
ADDED
|
@@ -0,0 +1,737 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"metadata": {
|
| 3 |
+
"total_size": 33559877504,
|
| 4 |
+
"total_parameters": 31577935872
|
| 5 |
+
},
|
| 6 |
+
"weight_map": {
|
| 7 |
+
"backbone.embeddings.biases": "model-00001-of-00007.safetensors",
|
| 8 |
+
"backbone.embeddings.scales": "model-00001-of-00007.safetensors",
|
| 9 |
+
"backbone.embeddings.weight": "model-00001-of-00007.safetensors",
|
| 10 |
+
"backbone.layers.0.mixer.A_log": "model-00001-of-00007.safetensors",
|
| 11 |
+
"backbone.layers.0.mixer.D": "model-00001-of-00007.safetensors",
|
| 12 |
+
"backbone.layers.0.mixer.conv1d.bias": "model-00001-of-00007.safetensors",
|
| 13 |
+
"backbone.layers.0.mixer.conv1d.weight": "model-00001-of-00007.safetensors",
|
| 14 |
+
"backbone.layers.0.mixer.dt_bias": "model-00001-of-00007.safetensors",
|
| 15 |
+
"backbone.layers.0.mixer.in_proj.biases": "model-00001-of-00007.safetensors",
|
| 16 |
+
"backbone.layers.0.mixer.in_proj.scales": "model-00001-of-00007.safetensors",
|
| 17 |
+
"backbone.layers.0.mixer.in_proj.weight": "model-00001-of-00007.safetensors",
|
| 18 |
+
"backbone.layers.0.mixer.norm.weight": "model-00001-of-00007.safetensors",
|
| 19 |
+
"backbone.layers.0.mixer.out_proj.biases": "model-00001-of-00007.safetensors",
|
| 20 |
+
"backbone.layers.0.mixer.out_proj.scales": "model-00001-of-00007.safetensors",
|
| 21 |
+
"backbone.layers.0.mixer.out_proj.weight": "model-00001-of-00007.safetensors",
|
| 22 |
+
"backbone.layers.0.norm.weight": "model-00001-of-00007.safetensors",
|
| 23 |
+
"backbone.layers.1.mixer.gate.e_score_correction_bias": "model-00001-of-00007.safetensors",
|
| 24 |
+
"backbone.layers.1.mixer.gate.weight": "model-00001-of-00007.safetensors",
|
| 25 |
+
"backbone.layers.1.mixer.shared_experts.down_proj.biases": "model-00001-of-00007.safetensors",
|
| 26 |
+
"backbone.layers.1.mixer.shared_experts.down_proj.scales": "model-00001-of-00007.safetensors",
|
| 27 |
+
"backbone.layers.1.mixer.shared_experts.down_proj.weight": "model-00001-of-00007.safetensors",
|
| 28 |
+
"backbone.layers.1.mixer.shared_experts.up_proj.biases": "model-00001-of-00007.safetensors",
|
| 29 |
+
"backbone.layers.1.mixer.shared_experts.up_proj.scales": "model-00001-of-00007.safetensors",
|
| 30 |
+
"backbone.layers.1.mixer.shared_experts.up_proj.weight": "model-00001-of-00007.safetensors",
|
| 31 |
+
"backbone.layers.1.mixer.switch_mlp.fc1.biases": "model-00001-of-00007.safetensors",
|
| 32 |
+
"backbone.layers.1.mixer.switch_mlp.fc1.scales": "model-00001-of-00007.safetensors",
|
| 33 |
+
"backbone.layers.1.mixer.switch_mlp.fc1.weight": "model-00001-of-00007.safetensors",
|
| 34 |
+
"backbone.layers.1.mixer.switch_mlp.fc2.biases": "model-00001-of-00007.safetensors",
|
| 35 |
+
"backbone.layers.1.mixer.switch_mlp.fc2.scales": "model-00001-of-00007.safetensors",
|
| 36 |
+
"backbone.layers.1.mixer.switch_mlp.fc2.weight": "model-00001-of-00007.safetensors",
|
| 37 |
+
"backbone.layers.1.norm.weight": "model-00001-of-00007.safetensors",
|
| 38 |
+
"backbone.layers.10.mixer.gate.e_score_correction_bias": "model-00002-of-00007.safetensors",
|
| 39 |
+
"backbone.layers.10.mixer.gate.weight": "model-00002-of-00007.safetensors",
|
| 40 |
+
"backbone.layers.10.mixer.shared_experts.down_proj.biases": "model-00002-of-00007.safetensors",
|
| 41 |
+
"backbone.layers.10.mixer.shared_experts.down_proj.scales": "model-00002-of-00007.safetensors",
|
| 42 |
+
"backbone.layers.10.mixer.shared_experts.down_proj.weight": "model-00002-of-00007.safetensors",
|
| 43 |
+
"backbone.layers.10.mixer.shared_experts.up_proj.biases": "model-00002-of-00007.safetensors",
|
| 44 |
+
"backbone.layers.10.mixer.shared_experts.up_proj.scales": "model-00002-of-00007.safetensors",
|
| 45 |
+
"backbone.layers.10.mixer.shared_experts.up_proj.weight": "model-00002-of-00007.safetensors",
|
| 46 |
+
"backbone.layers.10.mixer.switch_mlp.fc1.biases": "model-00002-of-00007.safetensors",
|
| 47 |
+
"backbone.layers.10.mixer.switch_mlp.fc1.scales": "model-00002-of-00007.safetensors",
|
| 48 |
+
"backbone.layers.10.mixer.switch_mlp.fc1.weight": "model-00002-of-00007.safetensors",
|
| 49 |
+
"backbone.layers.10.mixer.switch_mlp.fc2.biases": "model-00002-of-00007.safetensors",
|
| 50 |
+
"backbone.layers.10.mixer.switch_mlp.fc2.scales": "model-00002-of-00007.safetensors",
|
| 51 |
+
"backbone.layers.10.mixer.switch_mlp.fc2.weight": "model-00002-of-00007.safetensors",
|
| 52 |
+
"backbone.layers.10.norm.weight": "model-00002-of-00007.safetensors",
|
| 53 |
+
"backbone.layers.11.mixer.A_log": "model-00002-of-00007.safetensors",
|
| 54 |
+
"backbone.layers.11.mixer.D": "model-00002-of-00007.safetensors",
|
| 55 |
+
"backbone.layers.11.mixer.conv1d.bias": "model-00002-of-00007.safetensors",
|
| 56 |
+
"backbone.layers.11.mixer.conv1d.weight": "model-00002-of-00007.safetensors",
|
| 57 |
+
"backbone.layers.11.mixer.dt_bias": "model-00002-of-00007.safetensors",
|
| 58 |
+
"backbone.layers.11.mixer.in_proj.biases": "model-00002-of-00007.safetensors",
|
| 59 |
+
"backbone.layers.11.mixer.in_proj.scales": "model-00002-of-00007.safetensors",
|
| 60 |
+
"backbone.layers.11.mixer.in_proj.weight": "model-00002-of-00007.safetensors",
|
| 61 |
+
"backbone.layers.11.mixer.norm.weight": "model-00002-of-00007.safetensors",
|
| 62 |
+
"backbone.layers.11.mixer.out_proj.biases": "model-00002-of-00007.safetensors",
|
| 63 |
+
"backbone.layers.11.mixer.out_proj.scales": "model-00002-of-00007.safetensors",
|
| 64 |
+
"backbone.layers.11.mixer.out_proj.weight": "model-00002-of-00007.safetensors",
|
| 65 |
+
"backbone.layers.11.norm.weight": "model-00002-of-00007.safetensors",
|
| 66 |
+
"backbone.layers.12.mixer.k_proj.biases": "model-00002-of-00007.safetensors",
|
| 67 |
+
"backbone.layers.12.mixer.k_proj.scales": "model-00002-of-00007.safetensors",
|
| 68 |
+
"backbone.layers.12.mixer.k_proj.weight": "model-00002-of-00007.safetensors",
|
| 69 |
+
"backbone.layers.12.mixer.o_proj.biases": "model-00002-of-00007.safetensors",
|
| 70 |
+
"backbone.layers.12.mixer.o_proj.scales": "model-00002-of-00007.safetensors",
|
| 71 |
+
"backbone.layers.12.mixer.o_proj.weight": "model-00002-of-00007.safetensors",
|
| 72 |
+
"backbone.layers.12.mixer.q_proj.biases": "model-00002-of-00007.safetensors",
|
| 73 |
+
"backbone.layers.12.mixer.q_proj.scales": "model-00002-of-00007.safetensors",
|
| 74 |
+
"backbone.layers.12.mixer.q_proj.weight": "model-00002-of-00007.safetensors",
|
| 75 |
+
"backbone.layers.12.mixer.v_proj.biases": "model-00002-of-00007.safetensors",
|
| 76 |
+
"backbone.layers.12.mixer.v_proj.scales": "model-00002-of-00007.safetensors",
|
| 77 |
+
"backbone.layers.12.mixer.v_proj.weight": "model-00002-of-00007.safetensors",
|
| 78 |
+
"backbone.layers.12.norm.weight": "model-00002-of-00007.safetensors",
|
| 79 |
+
"backbone.layers.13.mixer.gate.e_score_correction_bias": "model-00002-of-00007.safetensors",
|
| 80 |
+
"backbone.layers.13.mixer.gate.weight": "model-00002-of-00007.safetensors",
|
| 81 |
+
"backbone.layers.13.mixer.shared_experts.down_proj.biases": "model-00002-of-00007.safetensors",
|
| 82 |
+
"backbone.layers.13.mixer.shared_experts.down_proj.scales": "model-00002-of-00007.safetensors",
|
| 83 |
+
"backbone.layers.13.mixer.shared_experts.down_proj.weight": "model-00002-of-00007.safetensors",
|
| 84 |
+
"backbone.layers.13.mixer.shared_experts.up_proj.biases": "model-00002-of-00007.safetensors",
|
| 85 |
+
"backbone.layers.13.mixer.shared_experts.up_proj.scales": "model-00002-of-00007.safetensors",
|
| 86 |
+
"backbone.layers.13.mixer.shared_experts.up_proj.weight": "model-00002-of-00007.safetensors",
|
| 87 |
+
"backbone.layers.13.mixer.switch_mlp.fc1.biases": "model-00002-of-00007.safetensors",
|
| 88 |
+
"backbone.layers.13.mixer.switch_mlp.fc1.scales": "model-00002-of-00007.safetensors",
|
| 89 |
+
"backbone.layers.13.mixer.switch_mlp.fc1.weight": "model-00002-of-00007.safetensors",
|
| 90 |
+
"backbone.layers.13.mixer.switch_mlp.fc2.biases": "model-00002-of-00007.safetensors",
|
| 91 |
+
"backbone.layers.13.mixer.switch_mlp.fc2.scales": "model-00002-of-00007.safetensors",
|
| 92 |
+
"backbone.layers.13.mixer.switch_mlp.fc2.weight": "model-00002-of-00007.safetensors",
|
| 93 |
+
"backbone.layers.13.norm.weight": "model-00002-of-00007.safetensors",
|
| 94 |
+
"backbone.layers.14.mixer.A_log": "model-00002-of-00007.safetensors",
|
| 95 |
+
"backbone.layers.14.mixer.D": "model-00002-of-00007.safetensors",
|
| 96 |
+
"backbone.layers.14.mixer.conv1d.bias": "model-00002-of-00007.safetensors",
|
| 97 |
+
"backbone.layers.14.mixer.conv1d.weight": "model-00002-of-00007.safetensors",
|
| 98 |
+
"backbone.layers.14.mixer.dt_bias": "model-00002-of-00007.safetensors",
|
| 99 |
+
"backbone.layers.14.mixer.in_proj.biases": "model-00002-of-00007.safetensors",
|
| 100 |
+
"backbone.layers.14.mixer.in_proj.scales": "model-00002-of-00007.safetensors",
|
| 101 |
+
"backbone.layers.14.mixer.in_proj.weight": "model-00002-of-00007.safetensors",
|
| 102 |
+
"backbone.layers.14.mixer.norm.weight": "model-00002-of-00007.safetensors",
|
| 103 |
+
"backbone.layers.14.mixer.out_proj.biases": "model-00002-of-00007.safetensors",
|
| 104 |
+
"backbone.layers.14.mixer.out_proj.scales": "model-00002-of-00007.safetensors",
|
| 105 |
+
"backbone.layers.14.mixer.out_proj.weight": "model-00002-of-00007.safetensors",
|
| 106 |
+
"backbone.layers.14.norm.weight": "model-00002-of-00007.safetensors",
|
| 107 |
+
"backbone.layers.15.mixer.gate.e_score_correction_bias": "model-00002-of-00007.safetensors",
|
| 108 |
+
"backbone.layers.15.mixer.gate.weight": "model-00002-of-00007.safetensors",
|
| 109 |
+
"backbone.layers.15.mixer.shared_experts.down_proj.biases": "model-00002-of-00007.safetensors",
|
| 110 |
+
"backbone.layers.15.mixer.shared_experts.down_proj.scales": "model-00002-of-00007.safetensors",
|
| 111 |
+
"backbone.layers.15.mixer.shared_experts.down_proj.weight": "model-00002-of-00007.safetensors",
|
| 112 |
+
"backbone.layers.15.mixer.shared_experts.up_proj.biases": "model-00002-of-00007.safetensors",
|
| 113 |
+
"backbone.layers.15.mixer.shared_experts.up_proj.scales": "model-00002-of-00007.safetensors",
|
| 114 |
+
"backbone.layers.15.mixer.shared_experts.up_proj.weight": "model-00002-of-00007.safetensors",
|
| 115 |
+
"backbone.layers.15.mixer.switch_mlp.fc1.biases": "model-00002-of-00007.safetensors",
|
| 116 |
+
"backbone.layers.15.mixer.switch_mlp.fc1.scales": "model-00002-of-00007.safetensors",
|
| 117 |
+
"backbone.layers.15.mixer.switch_mlp.fc1.weight": "model-00002-of-00007.safetensors",
|
| 118 |
+
"backbone.layers.15.mixer.switch_mlp.fc2.biases": "model-00002-of-00007.safetensors",
|
| 119 |
+
"backbone.layers.15.mixer.switch_mlp.fc2.scales": "model-00002-of-00007.safetensors",
|
| 120 |
+
"backbone.layers.15.mixer.switch_mlp.fc2.weight": "model-00002-of-00007.safetensors",
|
| 121 |
+
"backbone.layers.15.norm.weight": "model-00002-of-00007.safetensors",
|
| 122 |
+
"backbone.layers.16.mixer.A_log": "model-00002-of-00007.safetensors",
|
| 123 |
+
"backbone.layers.16.mixer.D": "model-00002-of-00007.safetensors",
|
| 124 |
+
"backbone.layers.16.mixer.conv1d.bias": "model-00002-of-00007.safetensors",
|
| 125 |
+
"backbone.layers.16.mixer.conv1d.weight": "model-00002-of-00007.safetensors",
|
| 126 |
+
"backbone.layers.16.mixer.dt_bias": "model-00002-of-00007.safetensors",
|
| 127 |
+
"backbone.layers.16.mixer.in_proj.biases": "model-00002-of-00007.safetensors",
|
| 128 |
+
"backbone.layers.16.mixer.in_proj.scales": "model-00002-of-00007.safetensors",
|
| 129 |
+
"backbone.layers.16.mixer.in_proj.weight": "model-00002-of-00007.safetensors",
|
| 130 |
+
"backbone.layers.16.mixer.norm.weight": "model-00002-of-00007.safetensors",
|
| 131 |
+
"backbone.layers.16.mixer.out_proj.biases": "model-00002-of-00007.safetensors",
|
| 132 |
+
"backbone.layers.16.mixer.out_proj.scales": "model-00002-of-00007.safetensors",
|
| 133 |
+
"backbone.layers.16.mixer.out_proj.weight": "model-00002-of-00007.safetensors",
|
| 134 |
+
"backbone.layers.16.norm.weight": "model-00002-of-00007.safetensors",
|
| 135 |
+
"backbone.layers.17.mixer.gate.e_score_correction_bias": "model-00003-of-00007.safetensors",
|
| 136 |
+
"backbone.layers.17.mixer.gate.weight": "model-00003-of-00007.safetensors",
|
| 137 |
+
"backbone.layers.17.mixer.shared_experts.down_proj.biases": "model-00003-of-00007.safetensors",
|
| 138 |
+
"backbone.layers.17.mixer.shared_experts.down_proj.scales": "model-00003-of-00007.safetensors",
|
| 139 |
+
"backbone.layers.17.mixer.shared_experts.down_proj.weight": "model-00003-of-00007.safetensors",
|
| 140 |
+
"backbone.layers.17.mixer.shared_experts.up_proj.biases": "model-00003-of-00007.safetensors",
|
| 141 |
+
"backbone.layers.17.mixer.shared_experts.up_proj.scales": "model-00003-of-00007.safetensors",
|
| 142 |
+
"backbone.layers.17.mixer.shared_experts.up_proj.weight": "model-00003-of-00007.safetensors",
|
| 143 |
+
"backbone.layers.17.mixer.switch_mlp.fc1.biases": "model-00003-of-00007.safetensors",
|
| 144 |
+
"backbone.layers.17.mixer.switch_mlp.fc1.scales": "model-00003-of-00007.safetensors",
|
| 145 |
+
"backbone.layers.17.mixer.switch_mlp.fc1.weight": "model-00003-of-00007.safetensors",
|
| 146 |
+
"backbone.layers.17.mixer.switch_mlp.fc2.biases": "model-00003-of-00007.safetensors",
|
| 147 |
+
"backbone.layers.17.mixer.switch_mlp.fc2.scales": "model-00003-of-00007.safetensors",
|
| 148 |
+
"backbone.layers.17.mixer.switch_mlp.fc2.weight": "model-00003-of-00007.safetensors",
|
| 149 |
+
"backbone.layers.17.norm.weight": "model-00002-of-00007.safetensors",
|
| 150 |
+
"backbone.layers.18.mixer.A_log": "model-00003-of-00007.safetensors",
|
| 151 |
+
"backbone.layers.18.mixer.D": "model-00003-of-00007.safetensors",
|
| 152 |
+
"backbone.layers.18.mixer.conv1d.bias": "model-00003-of-00007.safetensors",
|
| 153 |
+
"backbone.layers.18.mixer.conv1d.weight": "model-00003-of-00007.safetensors",
|
| 154 |
+
"backbone.layers.18.mixer.dt_bias": "model-00003-of-00007.safetensors",
|
| 155 |
+
"backbone.layers.18.mixer.in_proj.biases": "model-00003-of-00007.safetensors",
|
| 156 |
+
"backbone.layers.18.mixer.in_proj.scales": "model-00003-of-00007.safetensors",
|
| 157 |
+
"backbone.layers.18.mixer.in_proj.weight": "model-00003-of-00007.safetensors",
|
| 158 |
+
"backbone.layers.18.mixer.norm.weight": "model-00003-of-00007.safetensors",
|
| 159 |
+
"backbone.layers.18.mixer.out_proj.biases": "model-00003-of-00007.safetensors",
|
| 160 |
+
"backbone.layers.18.mixer.out_proj.scales": "model-00003-of-00007.safetensors",
|
| 161 |
+
"backbone.layers.18.mixer.out_proj.weight": "model-00003-of-00007.safetensors",
|
| 162 |
+
"backbone.layers.18.norm.weight": "model-00003-of-00007.safetensors",
|
| 163 |
+
"backbone.layers.19.mixer.k_proj.biases": "model-00003-of-00007.safetensors",
|
| 164 |
+
"backbone.layers.19.mixer.k_proj.scales": "model-00003-of-00007.safetensors",
|
| 165 |
+
"backbone.layers.19.mixer.k_proj.weight": "model-00003-of-00007.safetensors",
|
| 166 |
+
"backbone.layers.19.mixer.o_proj.biases": "model-00003-of-00007.safetensors",
|
| 167 |
+
"backbone.layers.19.mixer.o_proj.scales": "model-00003-of-00007.safetensors",
|
| 168 |
+
"backbone.layers.19.mixer.o_proj.weight": "model-00003-of-00007.safetensors",
|
| 169 |
+
"backbone.layers.19.mixer.q_proj.biases": "model-00003-of-00007.safetensors",
|
| 170 |
+
"backbone.layers.19.mixer.q_proj.scales": "model-00003-of-00007.safetensors",
|
| 171 |
+
"backbone.layers.19.mixer.q_proj.weight": "model-00003-of-00007.safetensors",
|
| 172 |
+
"backbone.layers.19.mixer.v_proj.biases": "model-00003-of-00007.safetensors",
|
| 173 |
+
"backbone.layers.19.mixer.v_proj.scales": "model-00003-of-00007.safetensors",
|
| 174 |
+
"backbone.layers.19.mixer.v_proj.weight": "model-00003-of-00007.safetensors",
|
| 175 |
+
"backbone.layers.19.norm.weight": "model-00003-of-00007.safetensors",
|
| 176 |
+
"backbone.layers.2.mixer.A_log": "model-00001-of-00007.safetensors",
|
| 177 |
+
"backbone.layers.2.mixer.D": "model-00001-of-00007.safetensors",
|
| 178 |
+
"backbone.layers.2.mixer.conv1d.bias": "model-00001-of-00007.safetensors",
|
| 179 |
+
"backbone.layers.2.mixer.conv1d.weight": "model-00001-of-00007.safetensors",
|
| 180 |
+
"backbone.layers.2.mixer.dt_bias": "model-00001-of-00007.safetensors",
|
| 181 |
+
"backbone.layers.2.mixer.in_proj.biases": "model-00001-of-00007.safetensors",
|
| 182 |
+
"backbone.layers.2.mixer.in_proj.scales": "model-00001-of-00007.safetensors",
|
| 183 |
+
"backbone.layers.2.mixer.in_proj.weight": "model-00001-of-00007.safetensors",
|
| 184 |
+
"backbone.layers.2.mixer.norm.weight": "model-00001-of-00007.safetensors",
|
| 185 |
+
"backbone.layers.2.mixer.out_proj.biases": "model-00001-of-00007.safetensors",
|
| 186 |
+
"backbone.layers.2.mixer.out_proj.scales": "model-00001-of-00007.safetensors",
|
| 187 |
+
"backbone.layers.2.mixer.out_proj.weight": "model-00001-of-00007.safetensors",
|
| 188 |
+
"backbone.layers.2.norm.weight": "model-00001-of-00007.safetensors",
|
| 189 |
+
"backbone.layers.20.mixer.gate.e_score_correction_bias": "model-00003-of-00007.safetensors",
|
| 190 |
+
"backbone.layers.20.mixer.gate.weight": "model-00003-of-00007.safetensors",
|
| 191 |
+
"backbone.layers.20.mixer.shared_experts.down_proj.biases": "model-00003-of-00007.safetensors",
|
| 192 |
+
"backbone.layers.20.mixer.shared_experts.down_proj.scales": "model-00003-of-00007.safetensors",
|
| 193 |
+
"backbone.layers.20.mixer.shared_experts.down_proj.weight": "model-00003-of-00007.safetensors",
|
| 194 |
+
"backbone.layers.20.mixer.shared_experts.up_proj.biases": "model-00003-of-00007.safetensors",
|
| 195 |
+
"backbone.layers.20.mixer.shared_experts.up_proj.scales": "model-00003-of-00007.safetensors",
|
| 196 |
+
"backbone.layers.20.mixer.shared_experts.up_proj.weight": "model-00003-of-00007.safetensors",
|
| 197 |
+
"backbone.layers.20.mixer.switch_mlp.fc1.biases": "model-00003-of-00007.safetensors",
|
| 198 |
+
"backbone.layers.20.mixer.switch_mlp.fc1.scales": "model-00003-of-00007.safetensors",
|
| 199 |
+
"backbone.layers.20.mixer.switch_mlp.fc1.weight": "model-00003-of-00007.safetensors",
|
| 200 |
+
"backbone.layers.20.mixer.switch_mlp.fc2.biases": "model-00003-of-00007.safetensors",
|
| 201 |
+
"backbone.layers.20.mixer.switch_mlp.fc2.scales": "model-00003-of-00007.safetensors",
|
| 202 |
+
"backbone.layers.20.mixer.switch_mlp.fc2.weight": "model-00003-of-00007.safetensors",
|
| 203 |
+
"backbone.layers.20.norm.weight": "model-00003-of-00007.safetensors",
|
| 204 |
+
"backbone.layers.21.mixer.A_log": "model-00003-of-00007.safetensors",
|
| 205 |
+
"backbone.layers.21.mixer.D": "model-00003-of-00007.safetensors",
|
| 206 |
+
"backbone.layers.21.mixer.conv1d.bias": "model-00003-of-00007.safetensors",
|
| 207 |
+
"backbone.layers.21.mixer.conv1d.weight": "model-00003-of-00007.safetensors",
|
| 208 |
+
"backbone.layers.21.mixer.dt_bias": "model-00003-of-00007.safetensors",
|
| 209 |
+
"backbone.layers.21.mixer.in_proj.biases": "model-00003-of-00007.safetensors",
|
| 210 |
+
"backbone.layers.21.mixer.in_proj.scales": "model-00003-of-00007.safetensors",
|
| 211 |
+
"backbone.layers.21.mixer.in_proj.weight": "model-00003-of-00007.safetensors",
|
| 212 |
+
"backbone.layers.21.mixer.norm.weight": "model-00003-of-00007.safetensors",
|
| 213 |
+
"backbone.layers.21.mixer.out_proj.biases": "model-00003-of-00007.safetensors",
|
| 214 |
+
"backbone.layers.21.mixer.out_proj.scales": "model-00003-of-00007.safetensors",
|
| 215 |
+
"backbone.layers.21.mixer.out_proj.weight": "model-00003-of-00007.safetensors",
|
| 216 |
+
"backbone.layers.21.norm.weight": "model-00003-of-00007.safetensors",
|
| 217 |
+
"backbone.layers.22.mixer.gate.e_score_correction_bias": "model-00003-of-00007.safetensors",
|
| 218 |
+
"backbone.layers.22.mixer.gate.weight": "model-00003-of-00007.safetensors",
|
| 219 |
+
"backbone.layers.22.mixer.shared_experts.down_proj.biases": "model-00003-of-00007.safetensors",
|
| 220 |
+
"backbone.layers.22.mixer.shared_experts.down_proj.scales": "model-00003-of-00007.safetensors",
|
| 221 |
+
"backbone.layers.22.mixer.shared_experts.down_proj.weight": "model-00003-of-00007.safetensors",
|
| 222 |
+
"backbone.layers.22.mixer.shared_experts.up_proj.biases": "model-00003-of-00007.safetensors",
|
| 223 |
+
"backbone.layers.22.mixer.shared_experts.up_proj.scales": "model-00003-of-00007.safetensors",
|
| 224 |
+
"backbone.layers.22.mixer.shared_experts.up_proj.weight": "model-00003-of-00007.safetensors",
|
| 225 |
+
"backbone.layers.22.mixer.switch_mlp.fc1.biases": "model-00003-of-00007.safetensors",
|
| 226 |
+
"backbone.layers.22.mixer.switch_mlp.fc1.scales": "model-00003-of-00007.safetensors",
|
| 227 |
+
"backbone.layers.22.mixer.switch_mlp.fc1.weight": "model-00003-of-00007.safetensors",
|
| 228 |
+
"backbone.layers.22.mixer.switch_mlp.fc2.biases": "model-00003-of-00007.safetensors",
|
| 229 |
+
"backbone.layers.22.mixer.switch_mlp.fc2.scales": "model-00003-of-00007.safetensors",
|
| 230 |
+
"backbone.layers.22.mixer.switch_mlp.fc2.weight": "model-00003-of-00007.safetensors",
|
| 231 |
+
"backbone.layers.22.norm.weight": "model-00003-of-00007.safetensors",
|
| 232 |
+
"backbone.layers.23.mixer.A_log": "model-00003-of-00007.safetensors",
|
| 233 |
+
"backbone.layers.23.mixer.D": "model-00003-of-00007.safetensors",
|
| 234 |
+
"backbone.layers.23.mixer.conv1d.bias": "model-00003-of-00007.safetensors",
|
| 235 |
+
"backbone.layers.23.mixer.conv1d.weight": "model-00003-of-00007.safetensors",
|
| 236 |
+
"backbone.layers.23.mixer.dt_bias": "model-00003-of-00007.safetensors",
|
| 237 |
+
"backbone.layers.23.mixer.in_proj.biases": "model-00003-of-00007.safetensors",
|
| 238 |
+
"backbone.layers.23.mixer.in_proj.scales": "model-00003-of-00007.safetensors",
|
| 239 |
+
"backbone.layers.23.mixer.in_proj.weight": "model-00003-of-00007.safetensors",
|
| 240 |
+
"backbone.layers.23.mixer.norm.weight": "model-00003-of-00007.safetensors",
|
| 241 |
+
"backbone.layers.23.mixer.out_proj.biases": "model-00003-of-00007.safetensors",
|
| 242 |
+
"backbone.layers.23.mixer.out_proj.scales": "model-00003-of-00007.safetensors",
|
| 243 |
+
"backbone.layers.23.mixer.out_proj.weight": "model-00003-of-00007.safetensors",
|
| 244 |
+
"backbone.layers.23.norm.weight": "model-00003-of-00007.safetensors",
|
| 245 |
+
"backbone.layers.24.mixer.gate.e_score_correction_bias": "model-00004-of-00007.safetensors",
|
| 246 |
+
"backbone.layers.24.mixer.gate.weight": "model-00004-of-00007.safetensors",
|
| 247 |
+
"backbone.layers.24.mixer.shared_experts.down_proj.biases": "model-00004-of-00007.safetensors",
|
| 248 |
+
"backbone.layers.24.mixer.shared_experts.down_proj.scales": "model-00004-of-00007.safetensors",
|
| 249 |
+
"backbone.layers.24.mixer.shared_experts.down_proj.weight": "model-00004-of-00007.safetensors",
|
| 250 |
+
"backbone.layers.24.mixer.shared_experts.up_proj.biases": "model-00004-of-00007.safetensors",
|
| 251 |
+
"backbone.layers.24.mixer.shared_experts.up_proj.scales": "model-00004-of-00007.safetensors",
|
| 252 |
+
"backbone.layers.24.mixer.shared_experts.up_proj.weight": "model-00004-of-00007.safetensors",
|
| 253 |
+
"backbone.layers.24.mixer.switch_mlp.fc1.biases": "model-00003-of-00007.safetensors",
|
| 254 |
+
"backbone.layers.24.mixer.switch_mlp.fc1.scales": "model-00003-of-00007.safetensors",
|
| 255 |
+
"backbone.layers.24.mixer.switch_mlp.fc1.weight": "model-00003-of-00007.safetensors",
|
| 256 |
+
"backbone.layers.24.mixer.switch_mlp.fc2.biases": "model-00004-of-00007.safetensors",
|
| 257 |
+
"backbone.layers.24.mixer.switch_mlp.fc2.scales": "model-00004-of-00007.safetensors",
|
| 258 |
+
"backbone.layers.24.mixer.switch_mlp.fc2.weight": "model-00004-of-00007.safetensors",
|
| 259 |
+
"backbone.layers.24.norm.weight": "model-00003-of-00007.safetensors",
|
| 260 |
+
"backbone.layers.25.mixer.A_log": "model-00004-of-00007.safetensors",
|
| 261 |
+
"backbone.layers.25.mixer.D": "model-00004-of-00007.safetensors",
|
| 262 |
+
"backbone.layers.25.mixer.conv1d.bias": "model-00004-of-00007.safetensors",
|
| 263 |
+
"backbone.layers.25.mixer.conv1d.weight": "model-00004-of-00007.safetensors",
|
| 264 |
+
"backbone.layers.25.mixer.dt_bias": "model-00004-of-00007.safetensors",
|
| 265 |
+
"backbone.layers.25.mixer.in_proj.biases": "model-00004-of-00007.safetensors",
|
| 266 |
+
"backbone.layers.25.mixer.in_proj.scales": "model-00004-of-00007.safetensors",
|
| 267 |
+
"backbone.layers.25.mixer.in_proj.weight": "model-00004-of-00007.safetensors",
|
| 268 |
+
"backbone.layers.25.mixer.norm.weight": "model-00004-of-00007.safetensors",
|
| 269 |
+
"backbone.layers.25.mixer.out_proj.biases": "model-00004-of-00007.safetensors",
|
| 270 |
+
"backbone.layers.25.mixer.out_proj.scales": "model-00004-of-00007.safetensors",
|
| 271 |
+
"backbone.layers.25.mixer.out_proj.weight": "model-00004-of-00007.safetensors",
|
| 272 |
+
"backbone.layers.25.norm.weight": "model-00004-of-00007.safetensors",
|
| 273 |
+
"backbone.layers.26.mixer.k_proj.biases": "model-00004-of-00007.safetensors",
|
| 274 |
+
"backbone.layers.26.mixer.k_proj.scales": "model-00004-of-00007.safetensors",
|
| 275 |
+
"backbone.layers.26.mixer.k_proj.weight": "model-00004-of-00007.safetensors",
|
| 276 |
+
"backbone.layers.26.mixer.o_proj.biases": "model-00004-of-00007.safetensors",
|
| 277 |
+
"backbone.layers.26.mixer.o_proj.scales": "model-00004-of-00007.safetensors",
|
| 278 |
+
"backbone.layers.26.mixer.o_proj.weight": "model-00004-of-00007.safetensors",
|
| 279 |
+
"backbone.layers.26.mixer.q_proj.biases": "model-00004-of-00007.safetensors",
|
| 280 |
+
"backbone.layers.26.mixer.q_proj.scales": "model-00004-of-00007.safetensors",
|
| 281 |
+
"backbone.layers.26.mixer.q_proj.weight": "model-00004-of-00007.safetensors",
|
| 282 |
+
"backbone.layers.26.mixer.v_proj.biases": "model-00004-of-00007.safetensors",
|
| 283 |
+
"backbone.layers.26.mixer.v_proj.scales": "model-00004-of-00007.safetensors",
|
| 284 |
+
"backbone.layers.26.mixer.v_proj.weight": "model-00004-of-00007.safetensors",
|
| 285 |
+
"backbone.layers.26.norm.weight": "model-00004-of-00007.safetensors",
|
| 286 |
+
"backbone.layers.27.mixer.gate.e_score_correction_bias": "model-00004-of-00007.safetensors",
|
| 287 |
+
"backbone.layers.27.mixer.gate.weight": "model-00004-of-00007.safetensors",
|
| 288 |
+
"backbone.layers.27.mixer.shared_experts.down_proj.biases": "model-00004-of-00007.safetensors",
|
| 289 |
+
"backbone.layers.27.mixer.shared_experts.down_proj.scales": "model-00004-of-00007.safetensors",
|
| 290 |
+
"backbone.layers.27.mixer.shared_experts.down_proj.weight": "model-00004-of-00007.safetensors",
|
| 291 |
+
"backbone.layers.27.mixer.shared_experts.up_proj.biases": "model-00004-of-00007.safetensors",
|
| 292 |
+
"backbone.layers.27.mixer.shared_experts.up_proj.scales": "model-00004-of-00007.safetensors",
|
| 293 |
+
"backbone.layers.27.mixer.shared_experts.up_proj.weight": "model-00004-of-00007.safetensors",
|
| 294 |
+
"backbone.layers.27.mixer.switch_mlp.fc1.biases": "model-00004-of-00007.safetensors",
|
| 295 |
+
"backbone.layers.27.mixer.switch_mlp.fc1.scales": "model-00004-of-00007.safetensors",
|
| 296 |
+
"backbone.layers.27.mixer.switch_mlp.fc1.weight": "model-00004-of-00007.safetensors",
|
| 297 |
+
"backbone.layers.27.mixer.switch_mlp.fc2.biases": "model-00004-of-00007.safetensors",
|
| 298 |
+
"backbone.layers.27.mixer.switch_mlp.fc2.scales": "model-00004-of-00007.safetensors",
|
| 299 |
+
"backbone.layers.27.mixer.switch_mlp.fc2.weight": "model-00004-of-00007.safetensors",
|
| 300 |
+
"backbone.layers.27.norm.weight": "model-00004-of-00007.safetensors",
|
| 301 |
+
"backbone.layers.28.mixer.A_log": "model-00004-of-00007.safetensors",
|
| 302 |
+
"backbone.layers.28.mixer.D": "model-00004-of-00007.safetensors",
|
| 303 |
+
"backbone.layers.28.mixer.conv1d.bias": "model-00004-of-00007.safetensors",
|
| 304 |
+
"backbone.layers.28.mixer.conv1d.weight": "model-00004-of-00007.safetensors",
|
| 305 |
+
"backbone.layers.28.mixer.dt_bias": "model-00004-of-00007.safetensors",
|
| 306 |
+
"backbone.layers.28.mixer.in_proj.biases": "model-00004-of-00007.safetensors",
|
| 307 |
+
"backbone.layers.28.mixer.in_proj.scales": "model-00004-of-00007.safetensors",
|
| 308 |
+
"backbone.layers.28.mixer.in_proj.weight": "model-00004-of-00007.safetensors",
|
| 309 |
+
"backbone.layers.28.mixer.norm.weight": "model-00004-of-00007.safetensors",
|
| 310 |
+
"backbone.layers.28.mixer.out_proj.biases": "model-00004-of-00007.safetensors",
|
| 311 |
+
"backbone.layers.28.mixer.out_proj.scales": "model-00004-of-00007.safetensors",
|
| 312 |
+
"backbone.layers.28.mixer.out_proj.weight": "model-00004-of-00007.safetensors",
|
| 313 |
+
"backbone.layers.28.norm.weight": "model-00004-of-00007.safetensors",
|
| 314 |
+
"backbone.layers.29.mixer.gate.e_score_correction_bias": "model-00004-of-00007.safetensors",
|
| 315 |
+
"backbone.layers.29.mixer.gate.weight": "model-00004-of-00007.safetensors",
|
| 316 |
+
"backbone.layers.29.mixer.shared_experts.down_proj.biases": "model-00004-of-00007.safetensors",
|
| 317 |
+
"backbone.layers.29.mixer.shared_experts.down_proj.scales": "model-00004-of-00007.safetensors",
|
| 318 |
+
"backbone.layers.29.mixer.shared_experts.down_proj.weight": "model-00004-of-00007.safetensors",
|
| 319 |
+
"backbone.layers.29.mixer.shared_experts.up_proj.biases": "model-00004-of-00007.safetensors",
|
| 320 |
+
"backbone.layers.29.mixer.shared_experts.up_proj.scales": "model-00004-of-00007.safetensors",
|
| 321 |
+
"backbone.layers.29.mixer.shared_experts.up_proj.weight": "model-00004-of-00007.safetensors",
|
| 322 |
+
"backbone.layers.29.mixer.switch_mlp.fc1.biases": "model-00004-of-00007.safetensors",
|
| 323 |
+
"backbone.layers.29.mixer.switch_mlp.fc1.scales": "model-00004-of-00007.safetensors",
|
| 324 |
+
"backbone.layers.29.mixer.switch_mlp.fc1.weight": "model-00004-of-00007.safetensors",
|
| 325 |
+
"backbone.layers.29.mixer.switch_mlp.fc2.biases": "model-00004-of-00007.safetensors",
|
| 326 |
+
"backbone.layers.29.mixer.switch_mlp.fc2.scales": "model-00004-of-00007.safetensors",
|
| 327 |
+
"backbone.layers.29.mixer.switch_mlp.fc2.weight": "model-00004-of-00007.safetensors",
|
| 328 |
+
"backbone.layers.29.norm.weight": "model-00004-of-00007.safetensors",
|
| 329 |
+
"backbone.layers.3.mixer.gate.e_score_correction_bias": "model-00001-of-00007.safetensors",
|
| 330 |
+
"backbone.layers.3.mixer.gate.weight": "model-00001-of-00007.safetensors",
|
| 331 |
+
"backbone.layers.3.mixer.shared_experts.down_proj.biases": "model-00001-of-00007.safetensors",
|
| 332 |
+
"backbone.layers.3.mixer.shared_experts.down_proj.scales": "model-00001-of-00007.safetensors",
|
| 333 |
+
"backbone.layers.3.mixer.shared_experts.down_proj.weight": "model-00001-of-00007.safetensors",
|
| 334 |
+
"backbone.layers.3.mixer.shared_experts.up_proj.biases": "model-00001-of-00007.safetensors",
|
| 335 |
+
"backbone.layers.3.mixer.shared_experts.up_proj.scales": "model-00001-of-00007.safetensors",
|
| 336 |
+
"backbone.layers.3.mixer.shared_experts.up_proj.weight": "model-00001-of-00007.safetensors",
|
| 337 |
+
"backbone.layers.3.mixer.switch_mlp.fc1.biases": "model-00001-of-00007.safetensors",
|
| 338 |
+
"backbone.layers.3.mixer.switch_mlp.fc1.scales": "model-00001-of-00007.safetensors",
|
| 339 |
+
"backbone.layers.3.mixer.switch_mlp.fc1.weight": "model-00001-of-00007.safetensors",
|
| 340 |
+
"backbone.layers.3.mixer.switch_mlp.fc2.biases": "model-00001-of-00007.safetensors",
|
| 341 |
+
"backbone.layers.3.mixer.switch_mlp.fc2.scales": "model-00001-of-00007.safetensors",
|
| 342 |
+
"backbone.layers.3.mixer.switch_mlp.fc2.weight": "model-00001-of-00007.safetensors",
|
| 343 |
+
"backbone.layers.3.norm.weight": "model-00001-of-00007.safetensors",
|
| 344 |
+
"backbone.layers.30.mixer.A_log": "model-00004-of-00007.safetensors",
|
| 345 |
+
"backbone.layers.30.mixer.D": "model-00004-of-00007.safetensors",
|
| 346 |
+
"backbone.layers.30.mixer.conv1d.bias": "model-00004-of-00007.safetensors",
|
| 347 |
+
"backbone.layers.30.mixer.conv1d.weight": "model-00004-of-00007.safetensors",
|
| 348 |
+
"backbone.layers.30.mixer.dt_bias": "model-00004-of-00007.safetensors",
|
| 349 |
+
"backbone.layers.30.mixer.in_proj.biases": "model-00004-of-00007.safetensors",
|
| 350 |
+
"backbone.layers.30.mixer.in_proj.scales": "model-00004-of-00007.safetensors",
|
| 351 |
+
"backbone.layers.30.mixer.in_proj.weight": "model-00004-of-00007.safetensors",
|
| 352 |
+
"backbone.layers.30.mixer.norm.weight": "model-00004-of-00007.safetensors",
|
| 353 |
+
"backbone.layers.30.mixer.out_proj.biases": "model-00004-of-00007.safetensors",
|
| 354 |
+
"backbone.layers.30.mixer.out_proj.scales": "model-00004-of-00007.safetensors",
|
| 355 |
+
"backbone.layers.30.mixer.out_proj.weight": "model-00004-of-00007.safetensors",
|
| 356 |
+
"backbone.layers.30.norm.weight": "model-00004-of-00007.safetensors",
|
| 357 |
+
"backbone.layers.31.mixer.gate.e_score_correction_bias": "model-00004-of-00007.safetensors",
|
| 358 |
+
"backbone.layers.31.mixer.gate.weight": "model-00004-of-00007.safetensors",
|
| 359 |
+
"backbone.layers.31.mixer.shared_experts.down_proj.biases": "model-00004-of-00007.safetensors",
|
| 360 |
+
"backbone.layers.31.mixer.shared_experts.down_proj.scales": "model-00004-of-00007.safetensors",
|
| 361 |
+
"backbone.layers.31.mixer.shared_experts.down_proj.weight": "model-00004-of-00007.safetensors",
|
| 362 |
+
"backbone.layers.31.mixer.shared_experts.up_proj.biases": "model-00004-of-00007.safetensors",
|
| 363 |
+
"backbone.layers.31.mixer.shared_experts.up_proj.scales": "model-00004-of-00007.safetensors",
|
| 364 |
+
"backbone.layers.31.mixer.shared_experts.up_proj.weight": "model-00004-of-00007.safetensors",
|
| 365 |
+
"backbone.layers.31.mixer.switch_mlp.fc1.biases": "model-00004-of-00007.safetensors",
|
| 366 |
+
"backbone.layers.31.mixer.switch_mlp.fc1.scales": "model-00004-of-00007.safetensors",
|
| 367 |
+
"backbone.layers.31.mixer.switch_mlp.fc1.weight": "model-00004-of-00007.safetensors",
|
| 368 |
+
"backbone.layers.31.mixer.switch_mlp.fc2.biases": "model-00004-of-00007.safetensors",
|
| 369 |
+
"backbone.layers.31.mixer.switch_mlp.fc2.scales": "model-00004-of-00007.safetensors",
|
| 370 |
+
"backbone.layers.31.mixer.switch_mlp.fc2.weight": "model-00004-of-00007.safetensors",
|
| 371 |
+
"backbone.layers.31.norm.weight": "model-00004-of-00007.safetensors",
|
| 372 |
+
"backbone.layers.32.mixer.A_log": "model-00004-of-00007.safetensors",
|
| 373 |
+
"backbone.layers.32.mixer.D": "model-00004-of-00007.safetensors",
|
| 374 |
+
"backbone.layers.32.mixer.conv1d.bias": "model-00004-of-00007.safetensors",
|
| 375 |
+
"backbone.layers.32.mixer.conv1d.weight": "model-00004-of-00007.safetensors",
|
| 376 |
+
"backbone.layers.32.mixer.dt_bias": "model-00004-of-00007.safetensors",
|
| 377 |
+
"backbone.layers.32.mixer.in_proj.biases": "model-00004-of-00007.safetensors",
|
| 378 |
+
"backbone.layers.32.mixer.in_proj.scales": "model-00004-of-00007.safetensors",
|
| 379 |
+
"backbone.layers.32.mixer.in_proj.weight": "model-00004-of-00007.safetensors",
|
| 380 |
+
"backbone.layers.32.mixer.norm.weight": "model-00004-of-00007.safetensors",
|
| 381 |
+
"backbone.layers.32.mixer.out_proj.biases": "model-00004-of-00007.safetensors",
|
| 382 |
+
"backbone.layers.32.mixer.out_proj.scales": "model-00004-of-00007.safetensors",
|
| 383 |
+
"backbone.layers.32.mixer.out_proj.weight": "model-00004-of-00007.safetensors",
|
| 384 |
+
"backbone.layers.32.norm.weight": "model-00004-of-00007.safetensors",
|
| 385 |
+
"backbone.layers.33.mixer.k_proj.biases": "model-00004-of-00007.safetensors",
|
| 386 |
+
"backbone.layers.33.mixer.k_proj.scales": "model-00004-of-00007.safetensors",
|
| 387 |
+
"backbone.layers.33.mixer.k_proj.weight": "model-00004-of-00007.safetensors",
|
| 388 |
+
"backbone.layers.33.mixer.o_proj.biases": "model-00004-of-00007.safetensors",
|
| 389 |
+
"backbone.layers.33.mixer.o_proj.scales": "model-00004-of-00007.safetensors",
|
| 390 |
+
"backbone.layers.33.mixer.o_proj.weight": "model-00004-of-00007.safetensors",
|
| 391 |
+
"backbone.layers.33.mixer.q_proj.biases": "model-00004-of-00007.safetensors",
|
| 392 |
+
"backbone.layers.33.mixer.q_proj.scales": "model-00004-of-00007.safetensors",
|
| 393 |
+
"backbone.layers.33.mixer.q_proj.weight": "model-00004-of-00007.safetensors",
|
| 394 |
+
"backbone.layers.33.mixer.v_proj.biases": "model-00004-of-00007.safetensors",
|
| 395 |
+
"backbone.layers.33.mixer.v_proj.scales": "model-00004-of-00007.safetensors",
|
| 396 |
+
"backbone.layers.33.mixer.v_proj.weight": "model-00004-of-00007.safetensors",
|
| 397 |
+
"backbone.layers.33.norm.weight": "model-00004-of-00007.safetensors",
|
| 398 |
+
"backbone.layers.34.mixer.gate.e_score_correction_bias": "model-00005-of-00007.safetensors",
|
| 399 |
+
"backbone.layers.34.mixer.gate.weight": "model-00005-of-00007.safetensors",
|
| 400 |
+
"backbone.layers.34.mixer.shared_experts.down_proj.biases": "model-00005-of-00007.safetensors",
|
| 401 |
+
"backbone.layers.34.mixer.shared_experts.down_proj.scales": "model-00005-of-00007.safetensors",
|
| 402 |
+
"backbone.layers.34.mixer.shared_experts.down_proj.weight": "model-00005-of-00007.safetensors",
|
| 403 |
+
"backbone.layers.34.mixer.shared_experts.up_proj.biases": "model-00005-of-00007.safetensors",
|
| 404 |
+
"backbone.layers.34.mixer.shared_experts.up_proj.scales": "model-00005-of-00007.safetensors",
|
| 405 |
+
"backbone.layers.34.mixer.shared_experts.up_proj.weight": "model-00005-of-00007.safetensors",
|
| 406 |
+
"backbone.layers.34.mixer.switch_mlp.fc1.biases": "model-00005-of-00007.safetensors",
|
| 407 |
+
"backbone.layers.34.mixer.switch_mlp.fc1.scales": "model-00005-of-00007.safetensors",
|
| 408 |
+
"backbone.layers.34.mixer.switch_mlp.fc1.weight": "model-00005-of-00007.safetensors",
|
| 409 |
+
"backbone.layers.34.mixer.switch_mlp.fc2.biases": "model-00005-of-00007.safetensors",
|
| 410 |
+
"backbone.layers.34.mixer.switch_mlp.fc2.scales": "model-00005-of-00007.safetensors",
|
| 411 |
+
"backbone.layers.34.mixer.switch_mlp.fc2.weight": "model-00005-of-00007.safetensors",
|
| 412 |
+
"backbone.layers.34.norm.weight": "model-00004-of-00007.safetensors",
|
| 413 |
+
"backbone.layers.35.mixer.A_log": "model-00005-of-00007.safetensors",
|
| 414 |
+
"backbone.layers.35.mixer.D": "model-00005-of-00007.safetensors",
|
| 415 |
+
"backbone.layers.35.mixer.conv1d.bias": "model-00005-of-00007.safetensors",
|
| 416 |
+
"backbone.layers.35.mixer.conv1d.weight": "model-00005-of-00007.safetensors",
|
| 417 |
+
"backbone.layers.35.mixer.dt_bias": "model-00005-of-00007.safetensors",
|
| 418 |
+
"backbone.layers.35.mixer.in_proj.biases": "model-00005-of-00007.safetensors",
|
| 419 |
+
"backbone.layers.35.mixer.in_proj.scales": "model-00005-of-00007.safetensors",
|
| 420 |
+
"backbone.layers.35.mixer.in_proj.weight": "model-00005-of-00007.safetensors",
|
| 421 |
+
"backbone.layers.35.mixer.norm.weight": "model-00005-of-00007.safetensors",
|
| 422 |
+
"backbone.layers.35.mixer.out_proj.biases": "model-00005-of-00007.safetensors",
|
| 423 |
+
"backbone.layers.35.mixer.out_proj.scales": "model-00005-of-00007.safetensors",
|
| 424 |
+
"backbone.layers.35.mixer.out_proj.weight": "model-00005-of-00007.safetensors",
|
| 425 |
+
"backbone.layers.35.norm.weight": "model-00005-of-00007.safetensors",
|
| 426 |
+
"backbone.layers.36.mixer.gate.e_score_correction_bias": "model-00005-of-00007.safetensors",
|
| 427 |
+
"backbone.layers.36.mixer.gate.weight": "model-00005-of-00007.safetensors",
|
| 428 |
+
"backbone.layers.36.mixer.shared_experts.down_proj.biases": "model-00005-of-00007.safetensors",
|
| 429 |
+
"backbone.layers.36.mixer.shared_experts.down_proj.scales": "model-00005-of-00007.safetensors",
|
| 430 |
+
"backbone.layers.36.mixer.shared_experts.down_proj.weight": "model-00005-of-00007.safetensors",
|
| 431 |
+
"backbone.layers.36.mixer.shared_experts.up_proj.biases": "model-00005-of-00007.safetensors",
|
| 432 |
+
"backbone.layers.36.mixer.shared_experts.up_proj.scales": "model-00005-of-00007.safetensors",
|
| 433 |
+
"backbone.layers.36.mixer.shared_experts.up_proj.weight": "model-00005-of-00007.safetensors",
|
| 434 |
+
"backbone.layers.36.mixer.switch_mlp.fc1.biases": "model-00005-of-00007.safetensors",
|
| 435 |
+
"backbone.layers.36.mixer.switch_mlp.fc1.scales": "model-00005-of-00007.safetensors",
|
| 436 |
+
"backbone.layers.36.mixer.switch_mlp.fc1.weight": "model-00005-of-00007.safetensors",
|
| 437 |
+
"backbone.layers.36.mixer.switch_mlp.fc2.biases": "model-00005-of-00007.safetensors",
|
| 438 |
+
"backbone.layers.36.mixer.switch_mlp.fc2.scales": "model-00005-of-00007.safetensors",
|
| 439 |
+
"backbone.layers.36.mixer.switch_mlp.fc2.weight": "model-00005-of-00007.safetensors",
|
| 440 |
+
"backbone.layers.36.norm.weight": "model-00005-of-00007.safetensors",
|
| 441 |
+
"backbone.layers.37.mixer.A_log": "model-00005-of-00007.safetensors",
|
| 442 |
+
"backbone.layers.37.mixer.D": "model-00005-of-00007.safetensors",
|
| 443 |
+
"backbone.layers.37.mixer.conv1d.bias": "model-00005-of-00007.safetensors",
|
| 444 |
+
"backbone.layers.37.mixer.conv1d.weight": "model-00005-of-00007.safetensors",
|
| 445 |
+
"backbone.layers.37.mixer.dt_bias": "model-00005-of-00007.safetensors",
|
| 446 |
+
"backbone.layers.37.mixer.in_proj.biases": "model-00005-of-00007.safetensors",
|
| 447 |
+
"backbone.layers.37.mixer.in_proj.scales": "model-00005-of-00007.safetensors",
|
| 448 |
+
"backbone.layers.37.mixer.in_proj.weight": "model-00005-of-00007.safetensors",
|
| 449 |
+
"backbone.layers.37.mixer.norm.weight": "model-00005-of-00007.safetensors",
|
| 450 |
+
"backbone.layers.37.mixer.out_proj.biases": "model-00005-of-00007.safetensors",
|
| 451 |
+
"backbone.layers.37.mixer.out_proj.scales": "model-00005-of-00007.safetensors",
|
| 452 |
+
"backbone.layers.37.mixer.out_proj.weight": "model-00005-of-00007.safetensors",
|
| 453 |
+
"backbone.layers.37.norm.weight": "model-00005-of-00007.safetensors",
|
| 454 |
+
"backbone.layers.38.mixer.gate.e_score_correction_bias": "model-00005-of-00007.safetensors",
|
| 455 |
+
"backbone.layers.38.mixer.gate.weight": "model-00005-of-00007.safetensors",
|
| 456 |
+
"backbone.layers.38.mixer.shared_experts.down_proj.biases": "model-00005-of-00007.safetensors",
|
| 457 |
+
"backbone.layers.38.mixer.shared_experts.down_proj.scales": "model-00005-of-00007.safetensors",
|
| 458 |
+
"backbone.layers.38.mixer.shared_experts.down_proj.weight": "model-00005-of-00007.safetensors",
|
| 459 |
+
"backbone.layers.38.mixer.shared_experts.up_proj.biases": "model-00005-of-00007.safetensors",
|
| 460 |
+
"backbone.layers.38.mixer.shared_experts.up_proj.scales": "model-00005-of-00007.safetensors",
|
| 461 |
+
"backbone.layers.38.mixer.shared_experts.up_proj.weight": "model-00005-of-00007.safetensors",
|
| 462 |
+
"backbone.layers.38.mixer.switch_mlp.fc1.biases": "model-00005-of-00007.safetensors",
|
| 463 |
+
"backbone.layers.38.mixer.switch_mlp.fc1.scales": "model-00005-of-00007.safetensors",
|
| 464 |
+
"backbone.layers.38.mixer.switch_mlp.fc1.weight": "model-00005-of-00007.safetensors",
|
| 465 |
+
"backbone.layers.38.mixer.switch_mlp.fc2.biases": "model-00005-of-00007.safetensors",
|
| 466 |
+
"backbone.layers.38.mixer.switch_mlp.fc2.scales": "model-00005-of-00007.safetensors",
|
| 467 |
+
"backbone.layers.38.mixer.switch_mlp.fc2.weight": "model-00005-of-00007.safetensors",
|
| 468 |
+
"backbone.layers.38.norm.weight": "model-00005-of-00007.safetensors",
|
| 469 |
+
"backbone.layers.39.mixer.A_log": "model-00005-of-00007.safetensors",
|
| 470 |
+
"backbone.layers.39.mixer.D": "model-00005-of-00007.safetensors",
|
| 471 |
+
"backbone.layers.39.mixer.conv1d.bias": "model-00005-of-00007.safetensors",
|
| 472 |
+
"backbone.layers.39.mixer.conv1d.weight": "model-00005-of-00007.safetensors",
|
| 473 |
+
"backbone.layers.39.mixer.dt_bias": "model-00005-of-00007.safetensors",
|
| 474 |
+
"backbone.layers.39.mixer.in_proj.biases": "model-00005-of-00007.safetensors",
|
| 475 |
+
"backbone.layers.39.mixer.in_proj.scales": "model-00005-of-00007.safetensors",
|
| 476 |
+
"backbone.layers.39.mixer.in_proj.weight": "model-00005-of-00007.safetensors",
|
| 477 |
+
"backbone.layers.39.mixer.norm.weight": "model-00005-of-00007.safetensors",
|
| 478 |
+
"backbone.layers.39.mixer.out_proj.biases": "model-00005-of-00007.safetensors",
|
| 479 |
+
"backbone.layers.39.mixer.out_proj.scales": "model-00005-of-00007.safetensors",
|
| 480 |
+
"backbone.layers.39.mixer.out_proj.weight": "model-00005-of-00007.safetensors",
|
| 481 |
+
"backbone.layers.39.norm.weight": "model-00005-of-00007.safetensors",
|
| 482 |
+
"backbone.layers.4.mixer.A_log": "model-00001-of-00007.safetensors",
|
| 483 |
+
"backbone.layers.4.mixer.D": "model-00001-of-00007.safetensors",
|
| 484 |
+
"backbone.layers.4.mixer.conv1d.bias": "model-00001-of-00007.safetensors",
|
| 485 |
+
"backbone.layers.4.mixer.conv1d.weight": "model-00001-of-00007.safetensors",
|
| 486 |
+
"backbone.layers.4.mixer.dt_bias": "model-00001-of-00007.safetensors",
|
| 487 |
+
"backbone.layers.4.mixer.in_proj.biases": "model-00001-of-00007.safetensors",
|
| 488 |
+
"backbone.layers.4.mixer.in_proj.scales": "model-00001-of-00007.safetensors",
|
| 489 |
+
"backbone.layers.4.mixer.in_proj.weight": "model-00001-of-00007.safetensors",
|
| 490 |
+
"backbone.layers.4.mixer.norm.weight": "model-00001-of-00007.safetensors",
|
| 491 |
+
"backbone.layers.4.mixer.out_proj.biases": "model-00001-of-00007.safetensors",
|
| 492 |
+
"backbone.layers.4.mixer.out_proj.scales": "model-00001-of-00007.safetensors",
|
| 493 |
+
"backbone.layers.4.mixer.out_proj.weight": "model-00001-of-00007.safetensors",
|
| 494 |
+
"backbone.layers.4.norm.weight": "model-00001-of-00007.safetensors",
|
| 495 |
+
"backbone.layers.40.mixer.gate.e_score_correction_bias": "model-00006-of-00007.safetensors",
|
| 496 |
+
"backbone.layers.40.mixer.gate.weight": "model-00006-of-00007.safetensors",
|
| 497 |
+
"backbone.layers.40.mixer.shared_experts.down_proj.biases": "model-00006-of-00007.safetensors",
|
| 498 |
+
"backbone.layers.40.mixer.shared_experts.down_proj.scales": "model-00006-of-00007.safetensors",
|
| 499 |
+
"backbone.layers.40.mixer.shared_experts.down_proj.weight": "model-00006-of-00007.safetensors",
|
| 500 |
+
"backbone.layers.40.mixer.shared_experts.up_proj.biases": "model-00006-of-00007.safetensors",
|
| 501 |
+
"backbone.layers.40.mixer.shared_experts.up_proj.scales": "model-00006-of-00007.safetensors",
|
| 502 |
+
"backbone.layers.40.mixer.shared_experts.up_proj.weight": "model-00006-of-00007.safetensors",
|
| 503 |
+
"backbone.layers.40.mixer.switch_mlp.fc1.biases": "model-00005-of-00007.safetensors",
|
| 504 |
+
"backbone.layers.40.mixer.switch_mlp.fc1.scales": "model-00005-of-00007.safetensors",
|
| 505 |
+
"backbone.layers.40.mixer.switch_mlp.fc1.weight": "model-00005-of-00007.safetensors",
|
| 506 |
+
"backbone.layers.40.mixer.switch_mlp.fc2.biases": "model-00006-of-00007.safetensors",
|
| 507 |
+
"backbone.layers.40.mixer.switch_mlp.fc2.scales": "model-00006-of-00007.safetensors",
|
| 508 |
+
"backbone.layers.40.mixer.switch_mlp.fc2.weight": "model-00006-of-00007.safetensors",
|
| 509 |
+
"backbone.layers.40.norm.weight": "model-00005-of-00007.safetensors",
|
| 510 |
+
"backbone.layers.41.mixer.A_log": "model-00006-of-00007.safetensors",
|
| 511 |
+
"backbone.layers.41.mixer.D": "model-00006-of-00007.safetensors",
|
| 512 |
+
"backbone.layers.41.mixer.conv1d.bias": "model-00006-of-00007.safetensors",
|
| 513 |
+
"backbone.layers.41.mixer.conv1d.weight": "model-00006-of-00007.safetensors",
|
| 514 |
+
"backbone.layers.41.mixer.dt_bias": "model-00006-of-00007.safetensors",
|
| 515 |
+
"backbone.layers.41.mixer.in_proj.biases": "model-00006-of-00007.safetensors",
|
| 516 |
+
"backbone.layers.41.mixer.in_proj.scales": "model-00006-of-00007.safetensors",
|
| 517 |
+
"backbone.layers.41.mixer.in_proj.weight": "model-00006-of-00007.safetensors",
|
| 518 |
+
"backbone.layers.41.mixer.norm.weight": "model-00006-of-00007.safetensors",
|
| 519 |
+
"backbone.layers.41.mixer.out_proj.biases": "model-00006-of-00007.safetensors",
|
| 520 |
+
"backbone.layers.41.mixer.out_proj.scales": "model-00006-of-00007.safetensors",
|
| 521 |
+
"backbone.layers.41.mixer.out_proj.weight": "model-00006-of-00007.safetensors",
|
| 522 |
+
"backbone.layers.41.norm.weight": "model-00006-of-00007.safetensors",
|
| 523 |
+
"backbone.layers.42.mixer.k_proj.biases": "model-00006-of-00007.safetensors",
|
| 524 |
+
"backbone.layers.42.mixer.k_proj.scales": "model-00006-of-00007.safetensors",
|
| 525 |
+
"backbone.layers.42.mixer.k_proj.weight": "model-00006-of-00007.safetensors",
|
| 526 |
+
"backbone.layers.42.mixer.o_proj.biases": "model-00006-of-00007.safetensors",
|
| 527 |
+
"backbone.layers.42.mixer.o_proj.scales": "model-00006-of-00007.safetensors",
|
| 528 |
+
"backbone.layers.42.mixer.o_proj.weight": "model-00006-of-00007.safetensors",
|
| 529 |
+
"backbone.layers.42.mixer.q_proj.biases": "model-00006-of-00007.safetensors",
|
| 530 |
+
"backbone.layers.42.mixer.q_proj.scales": "model-00006-of-00007.safetensors",
|
| 531 |
+
"backbone.layers.42.mixer.q_proj.weight": "model-00006-of-00007.safetensors",
|
| 532 |
+
"backbone.layers.42.mixer.v_proj.biases": "model-00006-of-00007.safetensors",
|
| 533 |
+
"backbone.layers.42.mixer.v_proj.scales": "model-00006-of-00007.safetensors",
|
| 534 |
+
"backbone.layers.42.mixer.v_proj.weight": "model-00006-of-00007.safetensors",
|
| 535 |
+
"backbone.layers.42.norm.weight": "model-00006-of-00007.safetensors",
|
| 536 |
+
"backbone.layers.43.mixer.gate.e_score_correction_bias": "model-00006-of-00007.safetensors",
|
| 537 |
+
"backbone.layers.43.mixer.gate.weight": "model-00006-of-00007.safetensors",
|
| 538 |
+
"backbone.layers.43.mixer.shared_experts.down_proj.biases": "model-00006-of-00007.safetensors",
|
| 539 |
+
"backbone.layers.43.mixer.shared_experts.down_proj.scales": "model-00006-of-00007.safetensors",
|
| 540 |
+
"backbone.layers.43.mixer.shared_experts.down_proj.weight": "model-00006-of-00007.safetensors",
|
| 541 |
+
"backbone.layers.43.mixer.shared_experts.up_proj.biases": "model-00006-of-00007.safetensors",
|
| 542 |
+
"backbone.layers.43.mixer.shared_experts.up_proj.scales": "model-00006-of-00007.safetensors",
|
| 543 |
+
"backbone.layers.43.mixer.shared_experts.up_proj.weight": "model-00006-of-00007.safetensors",
|
| 544 |
+
"backbone.layers.43.mixer.switch_mlp.fc1.biases": "model-00006-of-00007.safetensors",
|
| 545 |
+
"backbone.layers.43.mixer.switch_mlp.fc1.scales": "model-00006-of-00007.safetensors",
|
| 546 |
+
"backbone.layers.43.mixer.switch_mlp.fc1.weight": "model-00006-of-00007.safetensors",
|
| 547 |
+
"backbone.layers.43.mixer.switch_mlp.fc2.biases": "model-00006-of-00007.safetensors",
|
| 548 |
+
"backbone.layers.43.mixer.switch_mlp.fc2.scales": "model-00006-of-00007.safetensors",
|
| 549 |
+
"backbone.layers.43.mixer.switch_mlp.fc2.weight": "model-00006-of-00007.safetensors",
|
| 550 |
+
"backbone.layers.43.norm.weight": "model-00006-of-00007.safetensors",
|
| 551 |
+
"backbone.layers.44.mixer.A_log": "model-00006-of-00007.safetensors",
|
| 552 |
+
"backbone.layers.44.mixer.D": "model-00006-of-00007.safetensors",
|
| 553 |
+
"backbone.layers.44.mixer.conv1d.bias": "model-00006-of-00007.safetensors",
|
| 554 |
+
"backbone.layers.44.mixer.conv1d.weight": "model-00006-of-00007.safetensors",
|
| 555 |
+
"backbone.layers.44.mixer.dt_bias": "model-00006-of-00007.safetensors",
|
| 556 |
+
"backbone.layers.44.mixer.in_proj.biases": "model-00006-of-00007.safetensors",
|
| 557 |
+
"backbone.layers.44.mixer.in_proj.scales": "model-00006-of-00007.safetensors",
|
| 558 |
+
"backbone.layers.44.mixer.in_proj.weight": "model-00006-of-00007.safetensors",
|
| 559 |
+
"backbone.layers.44.mixer.norm.weight": "model-00006-of-00007.safetensors",
|
| 560 |
+
"backbone.layers.44.mixer.out_proj.biases": "model-00006-of-00007.safetensors",
|
| 561 |
+
"backbone.layers.44.mixer.out_proj.scales": "model-00006-of-00007.safetensors",
|
| 562 |
+
"backbone.layers.44.mixer.out_proj.weight": "model-00006-of-00007.safetensors",
|
| 563 |
+
"backbone.layers.44.norm.weight": "model-00006-of-00007.safetensors",
|
| 564 |
+
"backbone.layers.45.mixer.gate.e_score_correction_bias": "model-00006-of-00007.safetensors",
|
| 565 |
+
"backbone.layers.45.mixer.gate.weight": "model-00006-of-00007.safetensors",
|
| 566 |
+
"backbone.layers.45.mixer.shared_experts.down_proj.biases": "model-00006-of-00007.safetensors",
|
| 567 |
+
"backbone.layers.45.mixer.shared_experts.down_proj.scales": "model-00006-of-00007.safetensors",
|
| 568 |
+
"backbone.layers.45.mixer.shared_experts.down_proj.weight": "model-00006-of-00007.safetensors",
|
| 569 |
+
"backbone.layers.45.mixer.shared_experts.up_proj.biases": "model-00006-of-00007.safetensors",
|
| 570 |
+
"backbone.layers.45.mixer.shared_experts.up_proj.scales": "model-00006-of-00007.safetensors",
|
| 571 |
+
"backbone.layers.45.mixer.shared_experts.up_proj.weight": "model-00006-of-00007.safetensors",
|
| 572 |
+
"backbone.layers.45.mixer.switch_mlp.fc1.biases": "model-00006-of-00007.safetensors",
|
| 573 |
+
"backbone.layers.45.mixer.switch_mlp.fc1.scales": "model-00006-of-00007.safetensors",
|
| 574 |
+
"backbone.layers.45.mixer.switch_mlp.fc1.weight": "model-00006-of-00007.safetensors",
|
| 575 |
+
"backbone.layers.45.mixer.switch_mlp.fc2.biases": "model-00006-of-00007.safetensors",
|
| 576 |
+
"backbone.layers.45.mixer.switch_mlp.fc2.scales": "model-00006-of-00007.safetensors",
|
| 577 |
+
"backbone.layers.45.mixer.switch_mlp.fc2.weight": "model-00006-of-00007.safetensors",
|
| 578 |
+
"backbone.layers.45.norm.weight": "model-00006-of-00007.safetensors",
|
| 579 |
+
"backbone.layers.46.mixer.A_log": "model-00006-of-00007.safetensors",
|
| 580 |
+
"backbone.layers.46.mixer.D": "model-00006-of-00007.safetensors",
|
| 581 |
+
"backbone.layers.46.mixer.conv1d.bias": "model-00006-of-00007.safetensors",
|
| 582 |
+
"backbone.layers.46.mixer.conv1d.weight": "model-00006-of-00007.safetensors",
|
| 583 |
+
"backbone.layers.46.mixer.dt_bias": "model-00006-of-00007.safetensors",
|
| 584 |
+
"backbone.layers.46.mixer.in_proj.biases": "model-00006-of-00007.safetensors",
|
| 585 |
+
"backbone.layers.46.mixer.in_proj.scales": "model-00006-of-00007.safetensors",
|
| 586 |
+
"backbone.layers.46.mixer.in_proj.weight": "model-00006-of-00007.safetensors",
|
| 587 |
+
"backbone.layers.46.mixer.norm.weight": "model-00006-of-00007.safetensors",
|
| 588 |
+
"backbone.layers.46.mixer.out_proj.biases": "model-00006-of-00007.safetensors",
|
| 589 |
+
"backbone.layers.46.mixer.out_proj.scales": "model-00006-of-00007.safetensors",
|
| 590 |
+
"backbone.layers.46.mixer.out_proj.weight": "model-00006-of-00007.safetensors",
|
| 591 |
+
"backbone.layers.46.norm.weight": "model-00006-of-00007.safetensors",
|
| 592 |
+
"backbone.layers.47.mixer.gate.e_score_correction_bias": "model-00006-of-00007.safetensors",
|
| 593 |
+
"backbone.layers.47.mixer.gate.weight": "model-00006-of-00007.safetensors",
|
| 594 |
+
"backbone.layers.47.mixer.shared_experts.down_proj.biases": "model-00006-of-00007.safetensors",
|
| 595 |
+
"backbone.layers.47.mixer.shared_experts.down_proj.scales": "model-00006-of-00007.safetensors",
|
| 596 |
+
"backbone.layers.47.mixer.shared_experts.down_proj.weight": "model-00006-of-00007.safetensors",
|
| 597 |
+
"backbone.layers.47.mixer.shared_experts.up_proj.biases": "model-00006-of-00007.safetensors",
|
| 598 |
+
"backbone.layers.47.mixer.shared_experts.up_proj.scales": "model-00006-of-00007.safetensors",
|
| 599 |
+
"backbone.layers.47.mixer.shared_experts.up_proj.weight": "model-00006-of-00007.safetensors",
|
| 600 |
+
"backbone.layers.47.mixer.switch_mlp.fc1.biases": "model-00006-of-00007.safetensors",
|
| 601 |
+
"backbone.layers.47.mixer.switch_mlp.fc1.scales": "model-00006-of-00007.safetensors",
|
| 602 |
+
"backbone.layers.47.mixer.switch_mlp.fc1.weight": "model-00006-of-00007.safetensors",
|
| 603 |
+
"backbone.layers.47.mixer.switch_mlp.fc2.biases": "model-00006-of-00007.safetensors",
|
| 604 |
+
"backbone.layers.47.mixer.switch_mlp.fc2.scales": "model-00006-of-00007.safetensors",
|
| 605 |
+
"backbone.layers.47.mixer.switch_mlp.fc2.weight": "model-00006-of-00007.safetensors",
|
| 606 |
+
"backbone.layers.47.norm.weight": "model-00006-of-00007.safetensors",
|
| 607 |
+
"backbone.layers.48.mixer.A_log": "model-00006-of-00007.safetensors",
|
| 608 |
+
"backbone.layers.48.mixer.D": "model-00006-of-00007.safetensors",
|
| 609 |
+
"backbone.layers.48.mixer.conv1d.bias": "model-00006-of-00007.safetensors",
|
| 610 |
+
"backbone.layers.48.mixer.conv1d.weight": "model-00006-of-00007.safetensors",
|
| 611 |
+
"backbone.layers.48.mixer.dt_bias": "model-00006-of-00007.safetensors",
|
| 612 |
+
"backbone.layers.48.mixer.in_proj.biases": "model-00006-of-00007.safetensors",
|
| 613 |
+
"backbone.layers.48.mixer.in_proj.scales": "model-00006-of-00007.safetensors",
|
| 614 |
+
"backbone.layers.48.mixer.in_proj.weight": "model-00006-of-00007.safetensors",
|
| 615 |
+
"backbone.layers.48.mixer.norm.weight": "model-00006-of-00007.safetensors",
|
| 616 |
+
"backbone.layers.48.mixer.out_proj.biases": "model-00006-of-00007.safetensors",
|
| 617 |
+
"backbone.layers.48.mixer.out_proj.scales": "model-00006-of-00007.safetensors",
|
| 618 |
+
"backbone.layers.48.mixer.out_proj.weight": "model-00006-of-00007.safetensors",
|
| 619 |
+
"backbone.layers.48.norm.weight": "model-00006-of-00007.safetensors",
|
| 620 |
+
"backbone.layers.49.mixer.gate.e_score_correction_bias": "model-00007-of-00007.safetensors",
|
| 621 |
+
"backbone.layers.49.mixer.gate.weight": "model-00007-of-00007.safetensors",
|
| 622 |
+
"backbone.layers.49.mixer.shared_experts.down_proj.biases": "model-00007-of-00007.safetensors",
|
| 623 |
+
"backbone.layers.49.mixer.shared_experts.down_proj.scales": "model-00007-of-00007.safetensors",
|
| 624 |
+
"backbone.layers.49.mixer.shared_experts.down_proj.weight": "model-00007-of-00007.safetensors",
|
| 625 |
+
"backbone.layers.49.mixer.shared_experts.up_proj.biases": "model-00007-of-00007.safetensors",
|
| 626 |
+
"backbone.layers.49.mixer.shared_experts.up_proj.scales": "model-00007-of-00007.safetensors",
|
| 627 |
+
"backbone.layers.49.mixer.shared_experts.up_proj.weight": "model-00007-of-00007.safetensors",
|
| 628 |
+
"backbone.layers.49.mixer.switch_mlp.fc1.biases": "model-00007-of-00007.safetensors",
|
| 629 |
+
"backbone.layers.49.mixer.switch_mlp.fc1.scales": "model-00007-of-00007.safetensors",
|
| 630 |
+
"backbone.layers.49.mixer.switch_mlp.fc1.weight": "model-00007-of-00007.safetensors",
|
| 631 |
+
"backbone.layers.49.mixer.switch_mlp.fc2.biases": "model-00007-of-00007.safetensors",
|
| 632 |
+
"backbone.layers.49.mixer.switch_mlp.fc2.scales": "model-00007-of-00007.safetensors",
|
| 633 |
+
"backbone.layers.49.mixer.switch_mlp.fc2.weight": "model-00007-of-00007.safetensors",
|
| 634 |
+
"backbone.layers.49.norm.weight": "model-00006-of-00007.safetensors",
|
| 635 |
+
"backbone.layers.5.mixer.k_proj.biases": "model-00001-of-00007.safetensors",
|
| 636 |
+
"backbone.layers.5.mixer.k_proj.scales": "model-00001-of-00007.safetensors",
|
| 637 |
+
"backbone.layers.5.mixer.k_proj.weight": "model-00001-of-00007.safetensors",
|
| 638 |
+
"backbone.layers.5.mixer.o_proj.biases": "model-00001-of-00007.safetensors",
|
| 639 |
+
"backbone.layers.5.mixer.o_proj.scales": "model-00001-of-00007.safetensors",
|
| 640 |
+
"backbone.layers.5.mixer.o_proj.weight": "model-00001-of-00007.safetensors",
|
| 641 |
+
"backbone.layers.5.mixer.q_proj.biases": "model-00001-of-00007.safetensors",
|
| 642 |
+
"backbone.layers.5.mixer.q_proj.scales": "model-00001-of-00007.safetensors",
|
| 643 |
+
"backbone.layers.5.mixer.q_proj.weight": "model-00001-of-00007.safetensors",
|
| 644 |
+
"backbone.layers.5.mixer.v_proj.biases": "model-00001-of-00007.safetensors",
|
| 645 |
+
"backbone.layers.5.mixer.v_proj.scales": "model-00001-of-00007.safetensors",
|
| 646 |
+
"backbone.layers.5.mixer.v_proj.weight": "model-00001-of-00007.safetensors",
|
| 647 |
+
"backbone.layers.5.norm.weight": "model-00001-of-00007.safetensors",
|
| 648 |
+
"backbone.layers.50.mixer.A_log": "model-00007-of-00007.safetensors",
|
| 649 |
+
"backbone.layers.50.mixer.D": "model-00007-of-00007.safetensors",
|
| 650 |
+
"backbone.layers.50.mixer.conv1d.bias": "model-00007-of-00007.safetensors",
|
| 651 |
+
"backbone.layers.50.mixer.conv1d.weight": "model-00007-of-00007.safetensors",
|
| 652 |
+
"backbone.layers.50.mixer.dt_bias": "model-00007-of-00007.safetensors",
|
| 653 |
+
"backbone.layers.50.mixer.in_proj.biases": "model-00007-of-00007.safetensors",
|
| 654 |
+
"backbone.layers.50.mixer.in_proj.scales": "model-00007-of-00007.safetensors",
|
| 655 |
+
"backbone.layers.50.mixer.in_proj.weight": "model-00007-of-00007.safetensors",
|
| 656 |
+
"backbone.layers.50.mixer.norm.weight": "model-00007-of-00007.safetensors",
|
| 657 |
+
"backbone.layers.50.mixer.out_proj.biases": "model-00007-of-00007.safetensors",
|
| 658 |
+
"backbone.layers.50.mixer.out_proj.scales": "model-00007-of-00007.safetensors",
|
| 659 |
+
"backbone.layers.50.mixer.out_proj.weight": "model-00007-of-00007.safetensors",
|
| 660 |
+
"backbone.layers.50.norm.weight": "model-00007-of-00007.safetensors",
|
| 661 |
+
"backbone.layers.51.mixer.gate.e_score_correction_bias": "model-00007-of-00007.safetensors",
|
| 662 |
+
"backbone.layers.51.mixer.gate.weight": "model-00007-of-00007.safetensors",
|
| 663 |
+
"backbone.layers.51.mixer.shared_experts.down_proj.biases": "model-00007-of-00007.safetensors",
|
| 664 |
+
"backbone.layers.51.mixer.shared_experts.down_proj.scales": "model-00007-of-00007.safetensors",
|
| 665 |
+
"backbone.layers.51.mixer.shared_experts.down_proj.weight": "model-00007-of-00007.safetensors",
|
| 666 |
+
"backbone.layers.51.mixer.shared_experts.up_proj.biases": "model-00007-of-00007.safetensors",
|
| 667 |
+
"backbone.layers.51.mixer.shared_experts.up_proj.scales": "model-00007-of-00007.safetensors",
|
| 668 |
+
"backbone.layers.51.mixer.shared_experts.up_proj.weight": "model-00007-of-00007.safetensors",
|
| 669 |
+
"backbone.layers.51.mixer.switch_mlp.fc1.biases": "model-00007-of-00007.safetensors",
|
| 670 |
+
"backbone.layers.51.mixer.switch_mlp.fc1.scales": "model-00007-of-00007.safetensors",
|
| 671 |
+
"backbone.layers.51.mixer.switch_mlp.fc1.weight": "model-00007-of-00007.safetensors",
|
| 672 |
+
"backbone.layers.51.mixer.switch_mlp.fc2.biases": "model-00007-of-00007.safetensors",
|
| 673 |
+
"backbone.layers.51.mixer.switch_mlp.fc2.scales": "model-00007-of-00007.safetensors",
|
| 674 |
+
"backbone.layers.51.mixer.switch_mlp.fc2.weight": "model-00007-of-00007.safetensors",
|
| 675 |
+
"backbone.layers.51.norm.weight": "model-00007-of-00007.safetensors",
|
| 676 |
+
"backbone.layers.6.mixer.gate.e_score_correction_bias": "model-00001-of-00007.safetensors",
|
| 677 |
+
"backbone.layers.6.mixer.gate.weight": "model-00001-of-00007.safetensors",
|
| 678 |
+
"backbone.layers.6.mixer.shared_experts.down_proj.biases": "model-00001-of-00007.safetensors",
|
| 679 |
+
"backbone.layers.6.mixer.shared_experts.down_proj.scales": "model-00001-of-00007.safetensors",
|
| 680 |
+
"backbone.layers.6.mixer.shared_experts.down_proj.weight": "model-00001-of-00007.safetensors",
|
| 681 |
+
"backbone.layers.6.mixer.shared_experts.up_proj.biases": "model-00001-of-00007.safetensors",
|
| 682 |
+
"backbone.layers.6.mixer.shared_experts.up_proj.scales": "model-00001-of-00007.safetensors",
|
| 683 |
+
"backbone.layers.6.mixer.shared_experts.up_proj.weight": "model-00001-of-00007.safetensors",
|
| 684 |
+
"backbone.layers.6.mixer.switch_mlp.fc1.biases": "model-00001-of-00007.safetensors",
|
| 685 |
+
"backbone.layers.6.mixer.switch_mlp.fc1.scales": "model-00001-of-00007.safetensors",
|
| 686 |
+
"backbone.layers.6.mixer.switch_mlp.fc1.weight": "model-00001-of-00007.safetensors",
|
| 687 |
+
"backbone.layers.6.mixer.switch_mlp.fc2.biases": "model-00001-of-00007.safetensors",
|
| 688 |
+
"backbone.layers.6.mixer.switch_mlp.fc2.scales": "model-00001-of-00007.safetensors",
|
| 689 |
+
"backbone.layers.6.mixer.switch_mlp.fc2.weight": "model-00001-of-00007.safetensors",
|
| 690 |
+
"backbone.layers.6.norm.weight": "model-00001-of-00007.safetensors",
|
| 691 |
+
"backbone.layers.7.mixer.A_log": "model-00001-of-00007.safetensors",
|
| 692 |
+
"backbone.layers.7.mixer.D": "model-00001-of-00007.safetensors",
|
| 693 |
+
"backbone.layers.7.mixer.conv1d.bias": "model-00001-of-00007.safetensors",
|
| 694 |
+
"backbone.layers.7.mixer.conv1d.weight": "model-00001-of-00007.safetensors",
|
| 695 |
+
"backbone.layers.7.mixer.dt_bias": "model-00001-of-00007.safetensors",
|
| 696 |
+
"backbone.layers.7.mixer.in_proj.biases": "model-00001-of-00007.safetensors",
|
| 697 |
+
"backbone.layers.7.mixer.in_proj.scales": "model-00001-of-00007.safetensors",
|
| 698 |
+
"backbone.layers.7.mixer.in_proj.weight": "model-00001-of-00007.safetensors",
|
| 699 |
+
"backbone.layers.7.mixer.norm.weight": "model-00001-of-00007.safetensors",
|
| 700 |
+
"backbone.layers.7.mixer.out_proj.biases": "model-00001-of-00007.safetensors",
|
| 701 |
+
"backbone.layers.7.mixer.out_proj.scales": "model-00001-of-00007.safetensors",
|
| 702 |
+
"backbone.layers.7.mixer.out_proj.weight": "model-00001-of-00007.safetensors",
|
| 703 |
+
"backbone.layers.7.norm.weight": "model-00001-of-00007.safetensors",
|
| 704 |
+
"backbone.layers.8.mixer.gate.e_score_correction_bias": "model-00002-of-00007.safetensors",
|
| 705 |
+
"backbone.layers.8.mixer.gate.weight": "model-00002-of-00007.safetensors",
|
| 706 |
+
"backbone.layers.8.mixer.shared_experts.down_proj.biases": "model-00002-of-00007.safetensors",
|
| 707 |
+
"backbone.layers.8.mixer.shared_experts.down_proj.scales": "model-00002-of-00007.safetensors",
|
| 708 |
+
"backbone.layers.8.mixer.shared_experts.down_proj.weight": "model-00002-of-00007.safetensors",
|
| 709 |
+
"backbone.layers.8.mixer.shared_experts.up_proj.biases": "model-00002-of-00007.safetensors",
|
| 710 |
+
"backbone.layers.8.mixer.shared_experts.up_proj.scales": "model-00002-of-00007.safetensors",
|
| 711 |
+
"backbone.layers.8.mixer.shared_experts.up_proj.weight": "model-00002-of-00007.safetensors",
|
| 712 |
+
"backbone.layers.8.mixer.switch_mlp.fc1.biases": "model-00002-of-00007.safetensors",
|
| 713 |
+
"backbone.layers.8.mixer.switch_mlp.fc1.scales": "model-00001-of-00007.safetensors",
|
| 714 |
+
"backbone.layers.8.mixer.switch_mlp.fc1.weight": "model-00001-of-00007.safetensors",
|
| 715 |
+
"backbone.layers.8.mixer.switch_mlp.fc2.biases": "model-00002-of-00007.safetensors",
|
| 716 |
+
"backbone.layers.8.mixer.switch_mlp.fc2.scales": "model-00002-of-00007.safetensors",
|
| 717 |
+
"backbone.layers.8.mixer.switch_mlp.fc2.weight": "model-00002-of-00007.safetensors",
|
| 718 |
+
"backbone.layers.8.norm.weight": "model-00001-of-00007.safetensors",
|
| 719 |
+
"backbone.layers.9.mixer.A_log": "model-00002-of-00007.safetensors",
|
| 720 |
+
"backbone.layers.9.mixer.D": "model-00002-of-00007.safetensors",
|
| 721 |
+
"backbone.layers.9.mixer.conv1d.bias": "model-00002-of-00007.safetensors",
|
| 722 |
+
"backbone.layers.9.mixer.conv1d.weight": "model-00002-of-00007.safetensors",
|
| 723 |
+
"backbone.layers.9.mixer.dt_bias": "model-00002-of-00007.safetensors",
|
| 724 |
+
"backbone.layers.9.mixer.in_proj.biases": "model-00002-of-00007.safetensors",
|
| 725 |
+
"backbone.layers.9.mixer.in_proj.scales": "model-00002-of-00007.safetensors",
|
| 726 |
+
"backbone.layers.9.mixer.in_proj.weight": "model-00002-of-00007.safetensors",
|
| 727 |
+
"backbone.layers.9.mixer.norm.weight": "model-00002-of-00007.safetensors",
|
| 728 |
+
"backbone.layers.9.mixer.out_proj.biases": "model-00002-of-00007.safetensors",
|
| 729 |
+
"backbone.layers.9.mixer.out_proj.scales": "model-00002-of-00007.safetensors",
|
| 730 |
+
"backbone.layers.9.mixer.out_proj.weight": "model-00002-of-00007.safetensors",
|
| 731 |
+
"backbone.layers.9.norm.weight": "model-00002-of-00007.safetensors",
|
| 732 |
+
"backbone.norm_f.weight": "model-00007-of-00007.safetensors",
|
| 733 |
+
"lm_head.biases": "model-00007-of-00007.safetensors",
|
| 734 |
+
"lm_head.scales": "model-00007-of-00007.safetensors",
|
| 735 |
+
"lm_head.weight": "model-00007-of-00007.safetensors"
|
| 736 |
+
}
|
| 737 |
+
}
|
tokenizer.json
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:623c34567aebb18582765289fbe23d901c62704d6518d71866e0e58db892b5b7
|
| 3 |
+
size 17077484
|
tokenizer_config.json
ADDED
|
@@ -0,0 +1,18 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"add_prefix_space": false,
|
| 3 |
+
"backend": "tokenizers",
|
| 4 |
+
"bos_token": "<s>",
|
| 5 |
+
"clean_up_tokenization_spaces": false,
|
| 6 |
+
"eos_token": "<|im_end|>",
|
| 7 |
+
"is_local": true,
|
| 8 |
+
"local_files_only": false,
|
| 9 |
+
"model_input_names": [
|
| 10 |
+
"input_ids",
|
| 11 |
+
"attention_mask"
|
| 12 |
+
],
|
| 13 |
+
"model_max_length": 262144,
|
| 14 |
+
"pad_token": "<|im_end|>",
|
| 15 |
+
"tokenizer_class": "TokenizersBackend",
|
| 16 |
+
"tool_parser_type": "qwen3_coder",
|
| 17 |
+
"unk_token": "<unk>"
|
| 18 |
+
}
|