Upload 8 files
Browse files- .gitattributes +1 -0
- README.md +4 -4
- chat_template.jinja +121 -0
- config.json +54 -0
- generation_config.json +7 -0
- model.safetensors +3 -0
- model.safetensors.index.json +427 -0
- tokenizer.json +3 -0
- tokenizer_config.json +16 -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
CHANGED
|
@@ -1,7 +1,7 @@
|
|
| 1 |
---
|
| 2 |
-
|
| 3 |
-
|
| 4 |
-
-
|
| 5 |
library_name: mlx
|
|
|
|
| 6 |
---
|
| 7 |
-
Converted from [mistralai/Ministral-3-3B-Instruct-2512-BF16](https://huggingface.co/mistralai/Ministral-3-3B-Instruct-2512-BF16) using [`mlx_lm.convert`](https://github.com/ml-explore/mlx-lm) with `--q-mode mxfp8 --q-group-size 32` on 2026-03-05, 21:51.
|
|
|
|
| 1 |
---
|
| 2 |
+
language: en
|
| 3 |
+
tags:
|
| 4 |
+
- mlx
|
| 5 |
library_name: mlx
|
| 6 |
+
pipeline_tag: text-generation
|
| 7 |
---
|
|
|
chat_template.jinja
ADDED
|
@@ -0,0 +1,121 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{#- Default system message if no system prompt is passed. #}
|
| 2 |
+
{%- set default_system_message = 'You are Ministral-3-3B-Instruct-2512, a Large Language Model (LLM) created by Mistral AI, a French startup headquartered in Paris.\nYou power an AI assistant called Le Chat.\nYour knowledge base was last updated on 2023-10-01.\nThe current date is {today}.\n\nWhen you\'re not sure about some information or when the user\'s request requires up-to-date or specific data, you must use the available tools to fetch the information. Do not hesitate to use tools whenever they can provide a more accurate or complete response. If no relevant tools are available, then clearly state that you don\'t have the information and avoid making up anything.\nIf the user\'s question is not clear, ambiguous, or does not provide enough context for you to accurately answer the question, you do not try to answer it right away and you rather ask the user to clarify their request (e.g. "What are some good restaurants around me?" => "Where are you?" or "When is the next flight to Tokyo" => "Where do you travel from?").\nYou are always very attentive to dates, in particular you try to resolve dates (e.g. "yesterday" is {yesterday}) and when asked about information at specific dates, you discard information that is at another date.\nYou follow these instructions in all languages, and always respond to the user in the language they use or request.\nNext sections describe the capabilities that you have.\n\n# WEB BROWSING INSTRUCTIONS\n\nYou cannot perform any web search or access internet to open URLs, links etc. If it seems like the user is expecting you to do so, you clarify the situation and ask the user to copy paste the text directly in the chat.\n\n# MULTI-MODAL INSTRUCTIONS\n\nYou have the ability to read images, but you cannot generate images. You also cannot transcribe audio files or videos.\nYou cannot read nor transcribe audio files or videos.\n\n# TOOL CALLING INSTRUCTIONS\n\nYou may have access to tools that you can use to fetch information or perform actions. You must use these tools in the following situations:\n\n1. When the request requires up-to-date information.\n2. When the request requires specific data that you do not have in your knowledge base.\n3. When the request involves actions that you cannot perform without tools.\n\nAlways prioritize using tools to provide the most accurate and helpful response. If tools are not available, inform the user that you cannot perform the requested action at the moment.' %}
|
| 3 |
+
|
| 4 |
+
{#- Begin of sequence token. #}
|
| 5 |
+
{{- bos_token }}
|
| 6 |
+
|
| 7 |
+
{#- Handle system prompt if it exists. #}
|
| 8 |
+
{#- System prompt supports text content or text chunks. #}
|
| 9 |
+
{%- if messages[0]['role'] == 'system' %}
|
| 10 |
+
{{- '[SYSTEM_PROMPT]' -}}
|
| 11 |
+
{%- if messages[0]['content'] is string %}
|
| 12 |
+
{{- messages[0]['content'] -}}
|
| 13 |
+
{%- else %}
|
| 14 |
+
{%- for block in messages[0]['content'] %}
|
| 15 |
+
{%- if block['type'] == 'text' %}
|
| 16 |
+
{{- block['text'] }}
|
| 17 |
+
{%- else %}
|
| 18 |
+
{{- raise_exception('Only text chunks are supported in system message contents.') }}
|
| 19 |
+
{%- endif %}
|
| 20 |
+
{%- endfor %}
|
| 21 |
+
{%- endif %}
|
| 22 |
+
{{- '[/SYSTEM_PROMPT]' -}}
|
| 23 |
+
{%- set loop_messages = messages[1:] %}
|
| 24 |
+
{%- else %}
|
| 25 |
+
{%- set loop_messages = messages %}
|
| 26 |
+
{%- if default_system_message != '' %}
|
| 27 |
+
{{- '[SYSTEM_PROMPT]' + default_system_message + '[/SYSTEM_PROMPT]' }}
|
| 28 |
+
{%- endif %}
|
| 29 |
+
{%- endif %}
|
| 30 |
+
|
| 31 |
+
|
| 32 |
+
{#- Tools definition #}
|
| 33 |
+
{%- set tools_definition = '' %}
|
| 34 |
+
{%- set has_tools = false %}
|
| 35 |
+
{%- if tools is defined and tools is not none and tools|length > 0 %}
|
| 36 |
+
{%- set has_tools = true %}
|
| 37 |
+
{%- set tools_definition = '[AVAILABLE_TOOLS]' + (tools| tojson) + '[/AVAILABLE_TOOLS]' %}
|
| 38 |
+
{{- tools_definition }}
|
| 39 |
+
{%- endif %}
|
| 40 |
+
|
| 41 |
+
{#- Checks for alternating user/assistant messages. #}
|
| 42 |
+
{%- set ns = namespace(index=0) %}
|
| 43 |
+
{%- for message in loop_messages %}
|
| 44 |
+
{%- if message.role == 'user' or (message.role == 'assistant' and (message.tool_calls is not defined or message.tool_calls is none or message.tool_calls | length == 0)) %}
|
| 45 |
+
{%- if (message['role'] == 'user') != (ns.index % 2 == 0) %}
|
| 46 |
+
{{- raise_exception('After the optional system message, conversation roles must alternate user and assistant roles except for tool calls and results.') }}
|
| 47 |
+
{%- endif %}
|
| 48 |
+
{%- set ns.index = ns.index + 1 %}
|
| 49 |
+
{%- endif %}
|
| 50 |
+
{%- endfor %}
|
| 51 |
+
|
| 52 |
+
{#- Handle conversation messages. #}
|
| 53 |
+
{%- for message in loop_messages %}
|
| 54 |
+
|
| 55 |
+
{#- User messages supports text content or text and image chunks. #}
|
| 56 |
+
{%- if message['role'] == 'user' %}
|
| 57 |
+
{%- if message['content'] is string %}
|
| 58 |
+
{{- '[INST]' + message['content'] + '[/INST]' }}
|
| 59 |
+
{%- elif message['content'] | length > 0 %}
|
| 60 |
+
{{- '[INST]' }}
|
| 61 |
+
{%- if message['content'] | length == 2 %}
|
| 62 |
+
{%- set blocks = message['content'] | sort(attribute='type') %}
|
| 63 |
+
{%- else %}
|
| 64 |
+
{%- set blocks = message['content'] %}
|
| 65 |
+
{%- endif %}
|
| 66 |
+
{%- for block in blocks %}
|
| 67 |
+
{%- if block['type'] == 'text' %}
|
| 68 |
+
{{- block['text'] }}
|
| 69 |
+
{%- elif block['type'] in ['image', 'image_url'] %}
|
| 70 |
+
{{- '[IMG]' }}
|
| 71 |
+
{%- else %}
|
| 72 |
+
{{- raise_exception('Only text, image and image_url chunks are supported in user message content.') }}
|
| 73 |
+
{%- endif %}
|
| 74 |
+
{%- endfor %}
|
| 75 |
+
{{- '[/INST]' }}
|
| 76 |
+
{%- else %}
|
| 77 |
+
{{- raise_exception('User message must have a string or a list of chunks in content') }}
|
| 78 |
+
{%- endif %}
|
| 79 |
+
|
| 80 |
+
{#- Assistant messages supports text content or text and image chunks. #}
|
| 81 |
+
{%- elif message['role'] == 'assistant' %}
|
| 82 |
+
{%- if (message['content'] is none or message['content'] == '' or message['content']|length == 0) and (message['tool_calls'] is not defined or message['tool_calls'] is none or message['tool_calls']|length == 0) %}
|
| 83 |
+
{{- raise_exception('Assistant message must have a string or a list of chunks in content or a list of tool calls.') }}
|
| 84 |
+
{%- endif %}
|
| 85 |
+
|
| 86 |
+
{%- if message['content'] is string %}
|
| 87 |
+
{{- message['content'] }}
|
| 88 |
+
{%- elif message['content'] | length > 0 %}
|
| 89 |
+
{%- for block in message['content'] %}
|
| 90 |
+
{%- if block['type'] == 'text' %}
|
| 91 |
+
{{- block['text'] }}
|
| 92 |
+
{%- else %}
|
| 93 |
+
{{- raise_exception('Only text chunks are supported in assistant message contents.') }}
|
| 94 |
+
{%- endif %}
|
| 95 |
+
{%- endfor %}
|
| 96 |
+
{%- endif %}
|
| 97 |
+
|
| 98 |
+
{%- if message['tool_calls'] is defined and message['tool_calls'] is not none and message['tool_calls']|length > 0 %}
|
| 99 |
+
{%- for tool in message['tool_calls'] %}
|
| 100 |
+
{%- set arguments = tool['function']['arguments'] %}
|
| 101 |
+
{%- if arguments is not string %}
|
| 102 |
+
{%- set arguments = arguments|tojson|safe %}
|
| 103 |
+
{%- elif arguments == '' %}
|
| 104 |
+
{%- set arguments = '{}' %}
|
| 105 |
+
{%- endif %}
|
| 106 |
+
{{- '[TOOL_CALLS]' + tool['function']['name'] + '[ARGS]' + arguments }}
|
| 107 |
+
{%- endfor %}
|
| 108 |
+
{%- endif %}
|
| 109 |
+
|
| 110 |
+
{#- End of sequence token for each assistant messages. #}
|
| 111 |
+
{{- eos_token }}
|
| 112 |
+
|
| 113 |
+
{#- Tool messages only supports text content. #}
|
| 114 |
+
{%- elif message['role'] == 'tool' %}
|
| 115 |
+
{{- '[TOOL_RESULTS]' + message['content']|string + '[/TOOL_RESULTS]' }}
|
| 116 |
+
|
| 117 |
+
{#- Raise exception for unsupported roles. #}
|
| 118 |
+
{%- else %}
|
| 119 |
+
{{- raise_exception('Only user, assistant and tool roles are supported, got ' + message['role']) }}
|
| 120 |
+
{%- endif %}
|
| 121 |
+
{%- endfor %}
|
config.json
ADDED
|
@@ -0,0 +1,54 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"architectures": [
|
| 3 |
+
"Mistral3ForConditionalGeneration"
|
| 4 |
+
],
|
| 5 |
+
"dtype": "bfloat16",
|
| 6 |
+
"eos_token_id": 2,
|
| 7 |
+
"image_token_index": 10,
|
| 8 |
+
"model_type": "mistral3",
|
| 9 |
+
"multimodal_projector_bias": false,
|
| 10 |
+
"projector_hidden_act": "gelu",
|
| 11 |
+
"quantization": {
|
| 12 |
+
"group_size": 32,
|
| 13 |
+
"bits": 8,
|
| 14 |
+
"mode": "mxfp8"
|
| 15 |
+
},
|
| 16 |
+
"quantization_config": {
|
| 17 |
+
"group_size": 32,
|
| 18 |
+
"bits": 8,
|
| 19 |
+
"mode": "mxfp8"
|
| 20 |
+
},
|
| 21 |
+
"spatial_merge_size": 2,
|
| 22 |
+
"text_config": {
|
| 23 |
+
"attention_dropout": 0.0,
|
| 24 |
+
"head_dim": 128,
|
| 25 |
+
"hidden_act": "silu",
|
| 26 |
+
"hidden_size": 3072,
|
| 27 |
+
"initializer_range": 0.02,
|
| 28 |
+
"intermediate_size": 9216,
|
| 29 |
+
"max_position_embeddings": 262144,
|
| 30 |
+
"model_type": "ministral3",
|
| 31 |
+
"num_attention_heads": 32,
|
| 32 |
+
"num_hidden_layers": 26,
|
| 33 |
+
"num_key_value_heads": 8,
|
| 34 |
+
"rms_norm_eps": 1e-05,
|
| 35 |
+
"rope_parameters": {
|
| 36 |
+
"beta_fast": 32.0,
|
| 37 |
+
"beta_slow": 1.0,
|
| 38 |
+
"factor": 16.0,
|
| 39 |
+
"llama_4_scaling_beta": 0.1,
|
| 40 |
+
"mscale": 1.0,
|
| 41 |
+
"mscale_all_dim": 1.0,
|
| 42 |
+
"original_max_position_embeddings": 16384,
|
| 43 |
+
"rope_theta": 1000000.0,
|
| 44 |
+
"rope_type": "yarn",
|
| 45 |
+
"type": "yarn"
|
| 46 |
+
},
|
| 47 |
+
"sliding_window": null,
|
| 48 |
+
"tie_word_embeddings": true,
|
| 49 |
+
"use_cache": true,
|
| 50 |
+
"vocab_size": 131072
|
| 51 |
+
},
|
| 52 |
+
"transformers_version": "5.0.0.dev0",
|
| 53 |
+
"vision_feature_layer": -1
|
| 54 |
+
}
|
generation_config.json
ADDED
|
@@ -0,0 +1,7 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"bos_token_id": 1,
|
| 3 |
+
"eos_token_id": 2,
|
| 4 |
+
"max_length": 262144,
|
| 5 |
+
"pad_token_id": 11,
|
| 6 |
+
"transformers_version": "5.0.0.dev0"
|
| 7 |
+
}
|
model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:a2381165997290f9021f7a0aa06b5373a067ac324066cae8c1a6acc709ded96a
|
| 3 |
+
size 3536374072
|
model.safetensors.index.json
ADDED
|
@@ -0,0 +1,427 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"metadata": {
|
| 3 |
+
"total_size": 3536320512,
|
| 4 |
+
"total_parameters": 3429006336
|
| 5 |
+
},
|
| 6 |
+
"weight_map": {
|
| 7 |
+
"language_model.model.embed_tokens.scales": "model.safetensors",
|
| 8 |
+
"language_model.model.embed_tokens.weight": "model.safetensors",
|
| 9 |
+
"language_model.model.layers.0.input_layernorm.weight": "model.safetensors",
|
| 10 |
+
"language_model.model.layers.0.mlp.down_proj.scales": "model.safetensors",
|
| 11 |
+
"language_model.model.layers.0.mlp.down_proj.weight": "model.safetensors",
|
| 12 |
+
"language_model.model.layers.0.mlp.gate_proj.scales": "model.safetensors",
|
| 13 |
+
"language_model.model.layers.0.mlp.gate_proj.weight": "model.safetensors",
|
| 14 |
+
"language_model.model.layers.0.mlp.up_proj.scales": "model.safetensors",
|
| 15 |
+
"language_model.model.layers.0.mlp.up_proj.weight": "model.safetensors",
|
| 16 |
+
"language_model.model.layers.0.post_attention_layernorm.weight": "model.safetensors",
|
| 17 |
+
"language_model.model.layers.0.self_attn.k_proj.scales": "model.safetensors",
|
| 18 |
+
"language_model.model.layers.0.self_attn.k_proj.weight": "model.safetensors",
|
| 19 |
+
"language_model.model.layers.0.self_attn.o_proj.scales": "model.safetensors",
|
| 20 |
+
"language_model.model.layers.0.self_attn.o_proj.weight": "model.safetensors",
|
| 21 |
+
"language_model.model.layers.0.self_attn.q_proj.scales": "model.safetensors",
|
| 22 |
+
"language_model.model.layers.0.self_attn.q_proj.weight": "model.safetensors",
|
| 23 |
+
"language_model.model.layers.0.self_attn.v_proj.scales": "model.safetensors",
|
| 24 |
+
"language_model.model.layers.0.self_attn.v_proj.weight": "model.safetensors",
|
| 25 |
+
"language_model.model.layers.1.input_layernorm.weight": "model.safetensors",
|
| 26 |
+
"language_model.model.layers.1.mlp.down_proj.scales": "model.safetensors",
|
| 27 |
+
"language_model.model.layers.1.mlp.down_proj.weight": "model.safetensors",
|
| 28 |
+
"language_model.model.layers.1.mlp.gate_proj.scales": "model.safetensors",
|
| 29 |
+
"language_model.model.layers.1.mlp.gate_proj.weight": "model.safetensors",
|
| 30 |
+
"language_model.model.layers.1.mlp.up_proj.scales": "model.safetensors",
|
| 31 |
+
"language_model.model.layers.1.mlp.up_proj.weight": "model.safetensors",
|
| 32 |
+
"language_model.model.layers.1.post_attention_layernorm.weight": "model.safetensors",
|
| 33 |
+
"language_model.model.layers.1.self_attn.k_proj.scales": "model.safetensors",
|
| 34 |
+
"language_model.model.layers.1.self_attn.k_proj.weight": "model.safetensors",
|
| 35 |
+
"language_model.model.layers.1.self_attn.o_proj.scales": "model.safetensors",
|
| 36 |
+
"language_model.model.layers.1.self_attn.o_proj.weight": "model.safetensors",
|
| 37 |
+
"language_model.model.layers.1.self_attn.q_proj.scales": "model.safetensors",
|
| 38 |
+
"language_model.model.layers.1.self_attn.q_proj.weight": "model.safetensors",
|
| 39 |
+
"language_model.model.layers.1.self_attn.v_proj.scales": "model.safetensors",
|
| 40 |
+
"language_model.model.layers.1.self_attn.v_proj.weight": "model.safetensors",
|
| 41 |
+
"language_model.model.layers.10.input_layernorm.weight": "model.safetensors",
|
| 42 |
+
"language_model.model.layers.10.mlp.down_proj.scales": "model.safetensors",
|
| 43 |
+
"language_model.model.layers.10.mlp.down_proj.weight": "model.safetensors",
|
| 44 |
+
"language_model.model.layers.10.mlp.gate_proj.scales": "model.safetensors",
|
| 45 |
+
"language_model.model.layers.10.mlp.gate_proj.weight": "model.safetensors",
|
| 46 |
+
"language_model.model.layers.10.mlp.up_proj.scales": "model.safetensors",
|
| 47 |
+
"language_model.model.layers.10.mlp.up_proj.weight": "model.safetensors",
|
| 48 |
+
"language_model.model.layers.10.post_attention_layernorm.weight": "model.safetensors",
|
| 49 |
+
"language_model.model.layers.10.self_attn.k_proj.scales": "model.safetensors",
|
| 50 |
+
"language_model.model.layers.10.self_attn.k_proj.weight": "model.safetensors",
|
| 51 |
+
"language_model.model.layers.10.self_attn.o_proj.scales": "model.safetensors",
|
| 52 |
+
"language_model.model.layers.10.self_attn.o_proj.weight": "model.safetensors",
|
| 53 |
+
"language_model.model.layers.10.self_attn.q_proj.scales": "model.safetensors",
|
| 54 |
+
"language_model.model.layers.10.self_attn.q_proj.weight": "model.safetensors",
|
| 55 |
+
"language_model.model.layers.10.self_attn.v_proj.scales": "model.safetensors",
|
| 56 |
+
"language_model.model.layers.10.self_attn.v_proj.weight": "model.safetensors",
|
| 57 |
+
"language_model.model.layers.11.input_layernorm.weight": "model.safetensors",
|
| 58 |
+
"language_model.model.layers.11.mlp.down_proj.scales": "model.safetensors",
|
| 59 |
+
"language_model.model.layers.11.mlp.down_proj.weight": "model.safetensors",
|
| 60 |
+
"language_model.model.layers.11.mlp.gate_proj.scales": "model.safetensors",
|
| 61 |
+
"language_model.model.layers.11.mlp.gate_proj.weight": "model.safetensors",
|
| 62 |
+
"language_model.model.layers.11.mlp.up_proj.scales": "model.safetensors",
|
| 63 |
+
"language_model.model.layers.11.mlp.up_proj.weight": "model.safetensors",
|
| 64 |
+
"language_model.model.layers.11.post_attention_layernorm.weight": "model.safetensors",
|
| 65 |
+
"language_model.model.layers.11.self_attn.k_proj.scales": "model.safetensors",
|
| 66 |
+
"language_model.model.layers.11.self_attn.k_proj.weight": "model.safetensors",
|
| 67 |
+
"language_model.model.layers.11.self_attn.o_proj.scales": "model.safetensors",
|
| 68 |
+
"language_model.model.layers.11.self_attn.o_proj.weight": "model.safetensors",
|
| 69 |
+
"language_model.model.layers.11.self_attn.q_proj.scales": "model.safetensors",
|
| 70 |
+
"language_model.model.layers.11.self_attn.q_proj.weight": "model.safetensors",
|
| 71 |
+
"language_model.model.layers.11.self_attn.v_proj.scales": "model.safetensors",
|
| 72 |
+
"language_model.model.layers.11.self_attn.v_proj.weight": "model.safetensors",
|
| 73 |
+
"language_model.model.layers.12.input_layernorm.weight": "model.safetensors",
|
| 74 |
+
"language_model.model.layers.12.mlp.down_proj.scales": "model.safetensors",
|
| 75 |
+
"language_model.model.layers.12.mlp.down_proj.weight": "model.safetensors",
|
| 76 |
+
"language_model.model.layers.12.mlp.gate_proj.scales": "model.safetensors",
|
| 77 |
+
"language_model.model.layers.12.mlp.gate_proj.weight": "model.safetensors",
|
| 78 |
+
"language_model.model.layers.12.mlp.up_proj.scales": "model.safetensors",
|
| 79 |
+
"language_model.model.layers.12.mlp.up_proj.weight": "model.safetensors",
|
| 80 |
+
"language_model.model.layers.12.post_attention_layernorm.weight": "model.safetensors",
|
| 81 |
+
"language_model.model.layers.12.self_attn.k_proj.scales": "model.safetensors",
|
| 82 |
+
"language_model.model.layers.12.self_attn.k_proj.weight": "model.safetensors",
|
| 83 |
+
"language_model.model.layers.12.self_attn.o_proj.scales": "model.safetensors",
|
| 84 |
+
"language_model.model.layers.12.self_attn.o_proj.weight": "model.safetensors",
|
| 85 |
+
"language_model.model.layers.12.self_attn.q_proj.scales": "model.safetensors",
|
| 86 |
+
"language_model.model.layers.12.self_attn.q_proj.weight": "model.safetensors",
|
| 87 |
+
"language_model.model.layers.12.self_attn.v_proj.scales": "model.safetensors",
|
| 88 |
+
"language_model.model.layers.12.self_attn.v_proj.weight": "model.safetensors",
|
| 89 |
+
"language_model.model.layers.13.input_layernorm.weight": "model.safetensors",
|
| 90 |
+
"language_model.model.layers.13.mlp.down_proj.scales": "model.safetensors",
|
| 91 |
+
"language_model.model.layers.13.mlp.down_proj.weight": "model.safetensors",
|
| 92 |
+
"language_model.model.layers.13.mlp.gate_proj.scales": "model.safetensors",
|
| 93 |
+
"language_model.model.layers.13.mlp.gate_proj.weight": "model.safetensors",
|
| 94 |
+
"language_model.model.layers.13.mlp.up_proj.scales": "model.safetensors",
|
| 95 |
+
"language_model.model.layers.13.mlp.up_proj.weight": "model.safetensors",
|
| 96 |
+
"language_model.model.layers.13.post_attention_layernorm.weight": "model.safetensors",
|
| 97 |
+
"language_model.model.layers.13.self_attn.k_proj.scales": "model.safetensors",
|
| 98 |
+
"language_model.model.layers.13.self_attn.k_proj.weight": "model.safetensors",
|
| 99 |
+
"language_model.model.layers.13.self_attn.o_proj.scales": "model.safetensors",
|
| 100 |
+
"language_model.model.layers.13.self_attn.o_proj.weight": "model.safetensors",
|
| 101 |
+
"language_model.model.layers.13.self_attn.q_proj.scales": "model.safetensors",
|
| 102 |
+
"language_model.model.layers.13.self_attn.q_proj.weight": "model.safetensors",
|
| 103 |
+
"language_model.model.layers.13.self_attn.v_proj.scales": "model.safetensors",
|
| 104 |
+
"language_model.model.layers.13.self_attn.v_proj.weight": "model.safetensors",
|
| 105 |
+
"language_model.model.layers.14.input_layernorm.weight": "model.safetensors",
|
| 106 |
+
"language_model.model.layers.14.mlp.down_proj.scales": "model.safetensors",
|
| 107 |
+
"language_model.model.layers.14.mlp.down_proj.weight": "model.safetensors",
|
| 108 |
+
"language_model.model.layers.14.mlp.gate_proj.scales": "model.safetensors",
|
| 109 |
+
"language_model.model.layers.14.mlp.gate_proj.weight": "model.safetensors",
|
| 110 |
+
"language_model.model.layers.14.mlp.up_proj.scales": "model.safetensors",
|
| 111 |
+
"language_model.model.layers.14.mlp.up_proj.weight": "model.safetensors",
|
| 112 |
+
"language_model.model.layers.14.post_attention_layernorm.weight": "model.safetensors",
|
| 113 |
+
"language_model.model.layers.14.self_attn.k_proj.scales": "model.safetensors",
|
| 114 |
+
"language_model.model.layers.14.self_attn.k_proj.weight": "model.safetensors",
|
| 115 |
+
"language_model.model.layers.14.self_attn.o_proj.scales": "model.safetensors",
|
| 116 |
+
"language_model.model.layers.14.self_attn.o_proj.weight": "model.safetensors",
|
| 117 |
+
"language_model.model.layers.14.self_attn.q_proj.scales": "model.safetensors",
|
| 118 |
+
"language_model.model.layers.14.self_attn.q_proj.weight": "model.safetensors",
|
| 119 |
+
"language_model.model.layers.14.self_attn.v_proj.scales": "model.safetensors",
|
| 120 |
+
"language_model.model.layers.14.self_attn.v_proj.weight": "model.safetensors",
|
| 121 |
+
"language_model.model.layers.15.input_layernorm.weight": "model.safetensors",
|
| 122 |
+
"language_model.model.layers.15.mlp.down_proj.scales": "model.safetensors",
|
| 123 |
+
"language_model.model.layers.15.mlp.down_proj.weight": "model.safetensors",
|
| 124 |
+
"language_model.model.layers.15.mlp.gate_proj.scales": "model.safetensors",
|
| 125 |
+
"language_model.model.layers.15.mlp.gate_proj.weight": "model.safetensors",
|
| 126 |
+
"language_model.model.layers.15.mlp.up_proj.scales": "model.safetensors",
|
| 127 |
+
"language_model.model.layers.15.mlp.up_proj.weight": "model.safetensors",
|
| 128 |
+
"language_model.model.layers.15.post_attention_layernorm.weight": "model.safetensors",
|
| 129 |
+
"language_model.model.layers.15.self_attn.k_proj.scales": "model.safetensors",
|
| 130 |
+
"language_model.model.layers.15.self_attn.k_proj.weight": "model.safetensors",
|
| 131 |
+
"language_model.model.layers.15.self_attn.o_proj.scales": "model.safetensors",
|
| 132 |
+
"language_model.model.layers.15.self_attn.o_proj.weight": "model.safetensors",
|
| 133 |
+
"language_model.model.layers.15.self_attn.q_proj.scales": "model.safetensors",
|
| 134 |
+
"language_model.model.layers.15.self_attn.q_proj.weight": "model.safetensors",
|
| 135 |
+
"language_model.model.layers.15.self_attn.v_proj.scales": "model.safetensors",
|
| 136 |
+
"language_model.model.layers.15.self_attn.v_proj.weight": "model.safetensors",
|
| 137 |
+
"language_model.model.layers.16.input_layernorm.weight": "model.safetensors",
|
| 138 |
+
"language_model.model.layers.16.mlp.down_proj.scales": "model.safetensors",
|
| 139 |
+
"language_model.model.layers.16.mlp.down_proj.weight": "model.safetensors",
|
| 140 |
+
"language_model.model.layers.16.mlp.gate_proj.scales": "model.safetensors",
|
| 141 |
+
"language_model.model.layers.16.mlp.gate_proj.weight": "model.safetensors",
|
| 142 |
+
"language_model.model.layers.16.mlp.up_proj.scales": "model.safetensors",
|
| 143 |
+
"language_model.model.layers.16.mlp.up_proj.weight": "model.safetensors",
|
| 144 |
+
"language_model.model.layers.16.post_attention_layernorm.weight": "model.safetensors",
|
| 145 |
+
"language_model.model.layers.16.self_attn.k_proj.scales": "model.safetensors",
|
| 146 |
+
"language_model.model.layers.16.self_attn.k_proj.weight": "model.safetensors",
|
| 147 |
+
"language_model.model.layers.16.self_attn.o_proj.scales": "model.safetensors",
|
| 148 |
+
"language_model.model.layers.16.self_attn.o_proj.weight": "model.safetensors",
|
| 149 |
+
"language_model.model.layers.16.self_attn.q_proj.scales": "model.safetensors",
|
| 150 |
+
"language_model.model.layers.16.self_attn.q_proj.weight": "model.safetensors",
|
| 151 |
+
"language_model.model.layers.16.self_attn.v_proj.scales": "model.safetensors",
|
| 152 |
+
"language_model.model.layers.16.self_attn.v_proj.weight": "model.safetensors",
|
| 153 |
+
"language_model.model.layers.17.input_layernorm.weight": "model.safetensors",
|
| 154 |
+
"language_model.model.layers.17.mlp.down_proj.scales": "model.safetensors",
|
| 155 |
+
"language_model.model.layers.17.mlp.down_proj.weight": "model.safetensors",
|
| 156 |
+
"language_model.model.layers.17.mlp.gate_proj.scales": "model.safetensors",
|
| 157 |
+
"language_model.model.layers.17.mlp.gate_proj.weight": "model.safetensors",
|
| 158 |
+
"language_model.model.layers.17.mlp.up_proj.scales": "model.safetensors",
|
| 159 |
+
"language_model.model.layers.17.mlp.up_proj.weight": "model.safetensors",
|
| 160 |
+
"language_model.model.layers.17.post_attention_layernorm.weight": "model.safetensors",
|
| 161 |
+
"language_model.model.layers.17.self_attn.k_proj.scales": "model.safetensors",
|
| 162 |
+
"language_model.model.layers.17.self_attn.k_proj.weight": "model.safetensors",
|
| 163 |
+
"language_model.model.layers.17.self_attn.o_proj.scales": "model.safetensors",
|
| 164 |
+
"language_model.model.layers.17.self_attn.o_proj.weight": "model.safetensors",
|
| 165 |
+
"language_model.model.layers.17.self_attn.q_proj.scales": "model.safetensors",
|
| 166 |
+
"language_model.model.layers.17.self_attn.q_proj.weight": "model.safetensors",
|
| 167 |
+
"language_model.model.layers.17.self_attn.v_proj.scales": "model.safetensors",
|
| 168 |
+
"language_model.model.layers.17.self_attn.v_proj.weight": "model.safetensors",
|
| 169 |
+
"language_model.model.layers.18.input_layernorm.weight": "model.safetensors",
|
| 170 |
+
"language_model.model.layers.18.mlp.down_proj.scales": "model.safetensors",
|
| 171 |
+
"language_model.model.layers.18.mlp.down_proj.weight": "model.safetensors",
|
| 172 |
+
"language_model.model.layers.18.mlp.gate_proj.scales": "model.safetensors",
|
| 173 |
+
"language_model.model.layers.18.mlp.gate_proj.weight": "model.safetensors",
|
| 174 |
+
"language_model.model.layers.18.mlp.up_proj.scales": "model.safetensors",
|
| 175 |
+
"language_model.model.layers.18.mlp.up_proj.weight": "model.safetensors",
|
| 176 |
+
"language_model.model.layers.18.post_attention_layernorm.weight": "model.safetensors",
|
| 177 |
+
"language_model.model.layers.18.self_attn.k_proj.scales": "model.safetensors",
|
| 178 |
+
"language_model.model.layers.18.self_attn.k_proj.weight": "model.safetensors",
|
| 179 |
+
"language_model.model.layers.18.self_attn.o_proj.scales": "model.safetensors",
|
| 180 |
+
"language_model.model.layers.18.self_attn.o_proj.weight": "model.safetensors",
|
| 181 |
+
"language_model.model.layers.18.self_attn.q_proj.scales": "model.safetensors",
|
| 182 |
+
"language_model.model.layers.18.self_attn.q_proj.weight": "model.safetensors",
|
| 183 |
+
"language_model.model.layers.18.self_attn.v_proj.scales": "model.safetensors",
|
| 184 |
+
"language_model.model.layers.18.self_attn.v_proj.weight": "model.safetensors",
|
| 185 |
+
"language_model.model.layers.19.input_layernorm.weight": "model.safetensors",
|
| 186 |
+
"language_model.model.layers.19.mlp.down_proj.scales": "model.safetensors",
|
| 187 |
+
"language_model.model.layers.19.mlp.down_proj.weight": "model.safetensors",
|
| 188 |
+
"language_model.model.layers.19.mlp.gate_proj.scales": "model.safetensors",
|
| 189 |
+
"language_model.model.layers.19.mlp.gate_proj.weight": "model.safetensors",
|
| 190 |
+
"language_model.model.layers.19.mlp.up_proj.scales": "model.safetensors",
|
| 191 |
+
"language_model.model.layers.19.mlp.up_proj.weight": "model.safetensors",
|
| 192 |
+
"language_model.model.layers.19.post_attention_layernorm.weight": "model.safetensors",
|
| 193 |
+
"language_model.model.layers.19.self_attn.k_proj.scales": "model.safetensors",
|
| 194 |
+
"language_model.model.layers.19.self_attn.k_proj.weight": "model.safetensors",
|
| 195 |
+
"language_model.model.layers.19.self_attn.o_proj.scales": "model.safetensors",
|
| 196 |
+
"language_model.model.layers.19.self_attn.o_proj.weight": "model.safetensors",
|
| 197 |
+
"language_model.model.layers.19.self_attn.q_proj.scales": "model.safetensors",
|
| 198 |
+
"language_model.model.layers.19.self_attn.q_proj.weight": "model.safetensors",
|
| 199 |
+
"language_model.model.layers.19.self_attn.v_proj.scales": "model.safetensors",
|
| 200 |
+
"language_model.model.layers.19.self_attn.v_proj.weight": "model.safetensors",
|
| 201 |
+
"language_model.model.layers.2.input_layernorm.weight": "model.safetensors",
|
| 202 |
+
"language_model.model.layers.2.mlp.down_proj.scales": "model.safetensors",
|
| 203 |
+
"language_model.model.layers.2.mlp.down_proj.weight": "model.safetensors",
|
| 204 |
+
"language_model.model.layers.2.mlp.gate_proj.scales": "model.safetensors",
|
| 205 |
+
"language_model.model.layers.2.mlp.gate_proj.weight": "model.safetensors",
|
| 206 |
+
"language_model.model.layers.2.mlp.up_proj.scales": "model.safetensors",
|
| 207 |
+
"language_model.model.layers.2.mlp.up_proj.weight": "model.safetensors",
|
| 208 |
+
"language_model.model.layers.2.post_attention_layernorm.weight": "model.safetensors",
|
| 209 |
+
"language_model.model.layers.2.self_attn.k_proj.scales": "model.safetensors",
|
| 210 |
+
"language_model.model.layers.2.self_attn.k_proj.weight": "model.safetensors",
|
| 211 |
+
"language_model.model.layers.2.self_attn.o_proj.scales": "model.safetensors",
|
| 212 |
+
"language_model.model.layers.2.self_attn.o_proj.weight": "model.safetensors",
|
| 213 |
+
"language_model.model.layers.2.self_attn.q_proj.scales": "model.safetensors",
|
| 214 |
+
"language_model.model.layers.2.self_attn.q_proj.weight": "model.safetensors",
|
| 215 |
+
"language_model.model.layers.2.self_attn.v_proj.scales": "model.safetensors",
|
| 216 |
+
"language_model.model.layers.2.self_attn.v_proj.weight": "model.safetensors",
|
| 217 |
+
"language_model.model.layers.20.input_layernorm.weight": "model.safetensors",
|
| 218 |
+
"language_model.model.layers.20.mlp.down_proj.scales": "model.safetensors",
|
| 219 |
+
"language_model.model.layers.20.mlp.down_proj.weight": "model.safetensors",
|
| 220 |
+
"language_model.model.layers.20.mlp.gate_proj.scales": "model.safetensors",
|
| 221 |
+
"language_model.model.layers.20.mlp.gate_proj.weight": "model.safetensors",
|
| 222 |
+
"language_model.model.layers.20.mlp.up_proj.scales": "model.safetensors",
|
| 223 |
+
"language_model.model.layers.20.mlp.up_proj.weight": "model.safetensors",
|
| 224 |
+
"language_model.model.layers.20.post_attention_layernorm.weight": "model.safetensors",
|
| 225 |
+
"language_model.model.layers.20.self_attn.k_proj.scales": "model.safetensors",
|
| 226 |
+
"language_model.model.layers.20.self_attn.k_proj.weight": "model.safetensors",
|
| 227 |
+
"language_model.model.layers.20.self_attn.o_proj.scales": "model.safetensors",
|
| 228 |
+
"language_model.model.layers.20.self_attn.o_proj.weight": "model.safetensors",
|
| 229 |
+
"language_model.model.layers.20.self_attn.q_proj.scales": "model.safetensors",
|
| 230 |
+
"language_model.model.layers.20.self_attn.q_proj.weight": "model.safetensors",
|
| 231 |
+
"language_model.model.layers.20.self_attn.v_proj.scales": "model.safetensors",
|
| 232 |
+
"language_model.model.layers.20.self_attn.v_proj.weight": "model.safetensors",
|
| 233 |
+
"language_model.model.layers.21.input_layernorm.weight": "model.safetensors",
|
| 234 |
+
"language_model.model.layers.21.mlp.down_proj.scales": "model.safetensors",
|
| 235 |
+
"language_model.model.layers.21.mlp.down_proj.weight": "model.safetensors",
|
| 236 |
+
"language_model.model.layers.21.mlp.gate_proj.scales": "model.safetensors",
|
| 237 |
+
"language_model.model.layers.21.mlp.gate_proj.weight": "model.safetensors",
|
| 238 |
+
"language_model.model.layers.21.mlp.up_proj.scales": "model.safetensors",
|
| 239 |
+
"language_model.model.layers.21.mlp.up_proj.weight": "model.safetensors",
|
| 240 |
+
"language_model.model.layers.21.post_attention_layernorm.weight": "model.safetensors",
|
| 241 |
+
"language_model.model.layers.21.self_attn.k_proj.scales": "model.safetensors",
|
| 242 |
+
"language_model.model.layers.21.self_attn.k_proj.weight": "model.safetensors",
|
| 243 |
+
"language_model.model.layers.21.self_attn.o_proj.scales": "model.safetensors",
|
| 244 |
+
"language_model.model.layers.21.self_attn.o_proj.weight": "model.safetensors",
|
| 245 |
+
"language_model.model.layers.21.self_attn.q_proj.scales": "model.safetensors",
|
| 246 |
+
"language_model.model.layers.21.self_attn.q_proj.weight": "model.safetensors",
|
| 247 |
+
"language_model.model.layers.21.self_attn.v_proj.scales": "model.safetensors",
|
| 248 |
+
"language_model.model.layers.21.self_attn.v_proj.weight": "model.safetensors",
|
| 249 |
+
"language_model.model.layers.22.input_layernorm.weight": "model.safetensors",
|
| 250 |
+
"language_model.model.layers.22.mlp.down_proj.scales": "model.safetensors",
|
| 251 |
+
"language_model.model.layers.22.mlp.down_proj.weight": "model.safetensors",
|
| 252 |
+
"language_model.model.layers.22.mlp.gate_proj.scales": "model.safetensors",
|
| 253 |
+
"language_model.model.layers.22.mlp.gate_proj.weight": "model.safetensors",
|
| 254 |
+
"language_model.model.layers.22.mlp.up_proj.scales": "model.safetensors",
|
| 255 |
+
"language_model.model.layers.22.mlp.up_proj.weight": "model.safetensors",
|
| 256 |
+
"language_model.model.layers.22.post_attention_layernorm.weight": "model.safetensors",
|
| 257 |
+
"language_model.model.layers.22.self_attn.k_proj.scales": "model.safetensors",
|
| 258 |
+
"language_model.model.layers.22.self_attn.k_proj.weight": "model.safetensors",
|
| 259 |
+
"language_model.model.layers.22.self_attn.o_proj.scales": "model.safetensors",
|
| 260 |
+
"language_model.model.layers.22.self_attn.o_proj.weight": "model.safetensors",
|
| 261 |
+
"language_model.model.layers.22.self_attn.q_proj.scales": "model.safetensors",
|
| 262 |
+
"language_model.model.layers.22.self_attn.q_proj.weight": "model.safetensors",
|
| 263 |
+
"language_model.model.layers.22.self_attn.v_proj.scales": "model.safetensors",
|
| 264 |
+
"language_model.model.layers.22.self_attn.v_proj.weight": "model.safetensors",
|
| 265 |
+
"language_model.model.layers.23.input_layernorm.weight": "model.safetensors",
|
| 266 |
+
"language_model.model.layers.23.mlp.down_proj.scales": "model.safetensors",
|
| 267 |
+
"language_model.model.layers.23.mlp.down_proj.weight": "model.safetensors",
|
| 268 |
+
"language_model.model.layers.23.mlp.gate_proj.scales": "model.safetensors",
|
| 269 |
+
"language_model.model.layers.23.mlp.gate_proj.weight": "model.safetensors",
|
| 270 |
+
"language_model.model.layers.23.mlp.up_proj.scales": "model.safetensors",
|
| 271 |
+
"language_model.model.layers.23.mlp.up_proj.weight": "model.safetensors",
|
| 272 |
+
"language_model.model.layers.23.post_attention_layernorm.weight": "model.safetensors",
|
| 273 |
+
"language_model.model.layers.23.self_attn.k_proj.scales": "model.safetensors",
|
| 274 |
+
"language_model.model.layers.23.self_attn.k_proj.weight": "model.safetensors",
|
| 275 |
+
"language_model.model.layers.23.self_attn.o_proj.scales": "model.safetensors",
|
| 276 |
+
"language_model.model.layers.23.self_attn.o_proj.weight": "model.safetensors",
|
| 277 |
+
"language_model.model.layers.23.self_attn.q_proj.scales": "model.safetensors",
|
| 278 |
+
"language_model.model.layers.23.self_attn.q_proj.weight": "model.safetensors",
|
| 279 |
+
"language_model.model.layers.23.self_attn.v_proj.scales": "model.safetensors",
|
| 280 |
+
"language_model.model.layers.23.self_attn.v_proj.weight": "model.safetensors",
|
| 281 |
+
"language_model.model.layers.24.input_layernorm.weight": "model.safetensors",
|
| 282 |
+
"language_model.model.layers.24.mlp.down_proj.scales": "model.safetensors",
|
| 283 |
+
"language_model.model.layers.24.mlp.down_proj.weight": "model.safetensors",
|
| 284 |
+
"language_model.model.layers.24.mlp.gate_proj.scales": "model.safetensors",
|
| 285 |
+
"language_model.model.layers.24.mlp.gate_proj.weight": "model.safetensors",
|
| 286 |
+
"language_model.model.layers.24.mlp.up_proj.scales": "model.safetensors",
|
| 287 |
+
"language_model.model.layers.24.mlp.up_proj.weight": "model.safetensors",
|
| 288 |
+
"language_model.model.layers.24.post_attention_layernorm.weight": "model.safetensors",
|
| 289 |
+
"language_model.model.layers.24.self_attn.k_proj.scales": "model.safetensors",
|
| 290 |
+
"language_model.model.layers.24.self_attn.k_proj.weight": "model.safetensors",
|
| 291 |
+
"language_model.model.layers.24.self_attn.o_proj.scales": "model.safetensors",
|
| 292 |
+
"language_model.model.layers.24.self_attn.o_proj.weight": "model.safetensors",
|
| 293 |
+
"language_model.model.layers.24.self_attn.q_proj.scales": "model.safetensors",
|
| 294 |
+
"language_model.model.layers.24.self_attn.q_proj.weight": "model.safetensors",
|
| 295 |
+
"language_model.model.layers.24.self_attn.v_proj.scales": "model.safetensors",
|
| 296 |
+
"language_model.model.layers.24.self_attn.v_proj.weight": "model.safetensors",
|
| 297 |
+
"language_model.model.layers.25.input_layernorm.weight": "model.safetensors",
|
| 298 |
+
"language_model.model.layers.25.mlp.down_proj.scales": "model.safetensors",
|
| 299 |
+
"language_model.model.layers.25.mlp.down_proj.weight": "model.safetensors",
|
| 300 |
+
"language_model.model.layers.25.mlp.gate_proj.scales": "model.safetensors",
|
| 301 |
+
"language_model.model.layers.25.mlp.gate_proj.weight": "model.safetensors",
|
| 302 |
+
"language_model.model.layers.25.mlp.up_proj.scales": "model.safetensors",
|
| 303 |
+
"language_model.model.layers.25.mlp.up_proj.weight": "model.safetensors",
|
| 304 |
+
"language_model.model.layers.25.post_attention_layernorm.weight": "model.safetensors",
|
| 305 |
+
"language_model.model.layers.25.self_attn.k_proj.scales": "model.safetensors",
|
| 306 |
+
"language_model.model.layers.25.self_attn.k_proj.weight": "model.safetensors",
|
| 307 |
+
"language_model.model.layers.25.self_attn.o_proj.scales": "model.safetensors",
|
| 308 |
+
"language_model.model.layers.25.self_attn.o_proj.weight": "model.safetensors",
|
| 309 |
+
"language_model.model.layers.25.self_attn.q_proj.scales": "model.safetensors",
|
| 310 |
+
"language_model.model.layers.25.self_attn.q_proj.weight": "model.safetensors",
|
| 311 |
+
"language_model.model.layers.25.self_attn.v_proj.scales": "model.safetensors",
|
| 312 |
+
"language_model.model.layers.25.self_attn.v_proj.weight": "model.safetensors",
|
| 313 |
+
"language_model.model.layers.3.input_layernorm.weight": "model.safetensors",
|
| 314 |
+
"language_model.model.layers.3.mlp.down_proj.scales": "model.safetensors",
|
| 315 |
+
"language_model.model.layers.3.mlp.down_proj.weight": "model.safetensors",
|
| 316 |
+
"language_model.model.layers.3.mlp.gate_proj.scales": "model.safetensors",
|
| 317 |
+
"language_model.model.layers.3.mlp.gate_proj.weight": "model.safetensors",
|
| 318 |
+
"language_model.model.layers.3.mlp.up_proj.scales": "model.safetensors",
|
| 319 |
+
"language_model.model.layers.3.mlp.up_proj.weight": "model.safetensors",
|
| 320 |
+
"language_model.model.layers.3.post_attention_layernorm.weight": "model.safetensors",
|
| 321 |
+
"language_model.model.layers.3.self_attn.k_proj.scales": "model.safetensors",
|
| 322 |
+
"language_model.model.layers.3.self_attn.k_proj.weight": "model.safetensors",
|
| 323 |
+
"language_model.model.layers.3.self_attn.o_proj.scales": "model.safetensors",
|
| 324 |
+
"language_model.model.layers.3.self_attn.o_proj.weight": "model.safetensors",
|
| 325 |
+
"language_model.model.layers.3.self_attn.q_proj.scales": "model.safetensors",
|
| 326 |
+
"language_model.model.layers.3.self_attn.q_proj.weight": "model.safetensors",
|
| 327 |
+
"language_model.model.layers.3.self_attn.v_proj.scales": "model.safetensors",
|
| 328 |
+
"language_model.model.layers.3.self_attn.v_proj.weight": "model.safetensors",
|
| 329 |
+
"language_model.model.layers.4.input_layernorm.weight": "model.safetensors",
|
| 330 |
+
"language_model.model.layers.4.mlp.down_proj.scales": "model.safetensors",
|
| 331 |
+
"language_model.model.layers.4.mlp.down_proj.weight": "model.safetensors",
|
| 332 |
+
"language_model.model.layers.4.mlp.gate_proj.scales": "model.safetensors",
|
| 333 |
+
"language_model.model.layers.4.mlp.gate_proj.weight": "model.safetensors",
|
| 334 |
+
"language_model.model.layers.4.mlp.up_proj.scales": "model.safetensors",
|
| 335 |
+
"language_model.model.layers.4.mlp.up_proj.weight": "model.safetensors",
|
| 336 |
+
"language_model.model.layers.4.post_attention_layernorm.weight": "model.safetensors",
|
| 337 |
+
"language_model.model.layers.4.self_attn.k_proj.scales": "model.safetensors",
|
| 338 |
+
"language_model.model.layers.4.self_attn.k_proj.weight": "model.safetensors",
|
| 339 |
+
"language_model.model.layers.4.self_attn.o_proj.scales": "model.safetensors",
|
| 340 |
+
"language_model.model.layers.4.self_attn.o_proj.weight": "model.safetensors",
|
| 341 |
+
"language_model.model.layers.4.self_attn.q_proj.scales": "model.safetensors",
|
| 342 |
+
"language_model.model.layers.4.self_attn.q_proj.weight": "model.safetensors",
|
| 343 |
+
"language_model.model.layers.4.self_attn.v_proj.scales": "model.safetensors",
|
| 344 |
+
"language_model.model.layers.4.self_attn.v_proj.weight": "model.safetensors",
|
| 345 |
+
"language_model.model.layers.5.input_layernorm.weight": "model.safetensors",
|
| 346 |
+
"language_model.model.layers.5.mlp.down_proj.scales": "model.safetensors",
|
| 347 |
+
"language_model.model.layers.5.mlp.down_proj.weight": "model.safetensors",
|
| 348 |
+
"language_model.model.layers.5.mlp.gate_proj.scales": "model.safetensors",
|
| 349 |
+
"language_model.model.layers.5.mlp.gate_proj.weight": "model.safetensors",
|
| 350 |
+
"language_model.model.layers.5.mlp.up_proj.scales": "model.safetensors",
|
| 351 |
+
"language_model.model.layers.5.mlp.up_proj.weight": "model.safetensors",
|
| 352 |
+
"language_model.model.layers.5.post_attention_layernorm.weight": "model.safetensors",
|
| 353 |
+
"language_model.model.layers.5.self_attn.k_proj.scales": "model.safetensors",
|
| 354 |
+
"language_model.model.layers.5.self_attn.k_proj.weight": "model.safetensors",
|
| 355 |
+
"language_model.model.layers.5.self_attn.o_proj.scales": "model.safetensors",
|
| 356 |
+
"language_model.model.layers.5.self_attn.o_proj.weight": "model.safetensors",
|
| 357 |
+
"language_model.model.layers.5.self_attn.q_proj.scales": "model.safetensors",
|
| 358 |
+
"language_model.model.layers.5.self_attn.q_proj.weight": "model.safetensors",
|
| 359 |
+
"language_model.model.layers.5.self_attn.v_proj.scales": "model.safetensors",
|
| 360 |
+
"language_model.model.layers.5.self_attn.v_proj.weight": "model.safetensors",
|
| 361 |
+
"language_model.model.layers.6.input_layernorm.weight": "model.safetensors",
|
| 362 |
+
"language_model.model.layers.6.mlp.down_proj.scales": "model.safetensors",
|
| 363 |
+
"language_model.model.layers.6.mlp.down_proj.weight": "model.safetensors",
|
| 364 |
+
"language_model.model.layers.6.mlp.gate_proj.scales": "model.safetensors",
|
| 365 |
+
"language_model.model.layers.6.mlp.gate_proj.weight": "model.safetensors",
|
| 366 |
+
"language_model.model.layers.6.mlp.up_proj.scales": "model.safetensors",
|
| 367 |
+
"language_model.model.layers.6.mlp.up_proj.weight": "model.safetensors",
|
| 368 |
+
"language_model.model.layers.6.post_attention_layernorm.weight": "model.safetensors",
|
| 369 |
+
"language_model.model.layers.6.self_attn.k_proj.scales": "model.safetensors",
|
| 370 |
+
"language_model.model.layers.6.self_attn.k_proj.weight": "model.safetensors",
|
| 371 |
+
"language_model.model.layers.6.self_attn.o_proj.scales": "model.safetensors",
|
| 372 |
+
"language_model.model.layers.6.self_attn.o_proj.weight": "model.safetensors",
|
| 373 |
+
"language_model.model.layers.6.self_attn.q_proj.scales": "model.safetensors",
|
| 374 |
+
"language_model.model.layers.6.self_attn.q_proj.weight": "model.safetensors",
|
| 375 |
+
"language_model.model.layers.6.self_attn.v_proj.scales": "model.safetensors",
|
| 376 |
+
"language_model.model.layers.6.self_attn.v_proj.weight": "model.safetensors",
|
| 377 |
+
"language_model.model.layers.7.input_layernorm.weight": "model.safetensors",
|
| 378 |
+
"language_model.model.layers.7.mlp.down_proj.scales": "model.safetensors",
|
| 379 |
+
"language_model.model.layers.7.mlp.down_proj.weight": "model.safetensors",
|
| 380 |
+
"language_model.model.layers.7.mlp.gate_proj.scales": "model.safetensors",
|
| 381 |
+
"language_model.model.layers.7.mlp.gate_proj.weight": "model.safetensors",
|
| 382 |
+
"language_model.model.layers.7.mlp.up_proj.scales": "model.safetensors",
|
| 383 |
+
"language_model.model.layers.7.mlp.up_proj.weight": "model.safetensors",
|
| 384 |
+
"language_model.model.layers.7.post_attention_layernorm.weight": "model.safetensors",
|
| 385 |
+
"language_model.model.layers.7.self_attn.k_proj.scales": "model.safetensors",
|
| 386 |
+
"language_model.model.layers.7.self_attn.k_proj.weight": "model.safetensors",
|
| 387 |
+
"language_model.model.layers.7.self_attn.o_proj.scales": "model.safetensors",
|
| 388 |
+
"language_model.model.layers.7.self_attn.o_proj.weight": "model.safetensors",
|
| 389 |
+
"language_model.model.layers.7.self_attn.q_proj.scales": "model.safetensors",
|
| 390 |
+
"language_model.model.layers.7.self_attn.q_proj.weight": "model.safetensors",
|
| 391 |
+
"language_model.model.layers.7.self_attn.v_proj.scales": "model.safetensors",
|
| 392 |
+
"language_model.model.layers.7.self_attn.v_proj.weight": "model.safetensors",
|
| 393 |
+
"language_model.model.layers.8.input_layernorm.weight": "model.safetensors",
|
| 394 |
+
"language_model.model.layers.8.mlp.down_proj.scales": "model.safetensors",
|
| 395 |
+
"language_model.model.layers.8.mlp.down_proj.weight": "model.safetensors",
|
| 396 |
+
"language_model.model.layers.8.mlp.gate_proj.scales": "model.safetensors",
|
| 397 |
+
"language_model.model.layers.8.mlp.gate_proj.weight": "model.safetensors",
|
| 398 |
+
"language_model.model.layers.8.mlp.up_proj.scales": "model.safetensors",
|
| 399 |
+
"language_model.model.layers.8.mlp.up_proj.weight": "model.safetensors",
|
| 400 |
+
"language_model.model.layers.8.post_attention_layernorm.weight": "model.safetensors",
|
| 401 |
+
"language_model.model.layers.8.self_attn.k_proj.scales": "model.safetensors",
|
| 402 |
+
"language_model.model.layers.8.self_attn.k_proj.weight": "model.safetensors",
|
| 403 |
+
"language_model.model.layers.8.self_attn.o_proj.scales": "model.safetensors",
|
| 404 |
+
"language_model.model.layers.8.self_attn.o_proj.weight": "model.safetensors",
|
| 405 |
+
"language_model.model.layers.8.self_attn.q_proj.scales": "model.safetensors",
|
| 406 |
+
"language_model.model.layers.8.self_attn.q_proj.weight": "model.safetensors",
|
| 407 |
+
"language_model.model.layers.8.self_attn.v_proj.scales": "model.safetensors",
|
| 408 |
+
"language_model.model.layers.8.self_attn.v_proj.weight": "model.safetensors",
|
| 409 |
+
"language_model.model.layers.9.input_layernorm.weight": "model.safetensors",
|
| 410 |
+
"language_model.model.layers.9.mlp.down_proj.scales": "model.safetensors",
|
| 411 |
+
"language_model.model.layers.9.mlp.down_proj.weight": "model.safetensors",
|
| 412 |
+
"language_model.model.layers.9.mlp.gate_proj.scales": "model.safetensors",
|
| 413 |
+
"language_model.model.layers.9.mlp.gate_proj.weight": "model.safetensors",
|
| 414 |
+
"language_model.model.layers.9.mlp.up_proj.scales": "model.safetensors",
|
| 415 |
+
"language_model.model.layers.9.mlp.up_proj.weight": "model.safetensors",
|
| 416 |
+
"language_model.model.layers.9.post_attention_layernorm.weight": "model.safetensors",
|
| 417 |
+
"language_model.model.layers.9.self_attn.k_proj.scales": "model.safetensors",
|
| 418 |
+
"language_model.model.layers.9.self_attn.k_proj.weight": "model.safetensors",
|
| 419 |
+
"language_model.model.layers.9.self_attn.o_proj.scales": "model.safetensors",
|
| 420 |
+
"language_model.model.layers.9.self_attn.o_proj.weight": "model.safetensors",
|
| 421 |
+
"language_model.model.layers.9.self_attn.q_proj.scales": "model.safetensors",
|
| 422 |
+
"language_model.model.layers.9.self_attn.q_proj.weight": "model.safetensors",
|
| 423 |
+
"language_model.model.layers.9.self_attn.v_proj.scales": "model.safetensors",
|
| 424 |
+
"language_model.model.layers.9.self_attn.v_proj.weight": "model.safetensors",
|
| 425 |
+
"language_model.model.norm.weight": "model.safetensors"
|
| 426 |
+
}
|
| 427 |
+
}
|
tokenizer.json
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:577575622324b2e099e2648be26bdeb5e5815ffe66d7004e9e3ddbf421db6bf1
|
| 3 |
+
size 17078110
|
tokenizer_config.json
ADDED
|
@@ -0,0 +1,16 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"add_prefix_space": null,
|
| 3 |
+
"backend": "tokenizers",
|
| 4 |
+
"bos_token": "<s>",
|
| 5 |
+
"clean_up_tokenization_spaces": false,
|
| 6 |
+
"eos_token": "</s>",
|
| 7 |
+
"is_local": true,
|
| 8 |
+
"legacy": true,
|
| 9 |
+
"model_max_length": 1000000000000000019884624838656,
|
| 10 |
+
"pad_token": "<pad>",
|
| 11 |
+
"processor_class": "PixtralProcessor",
|
| 12 |
+
"tokenizer_class": "TokenizersBackend",
|
| 13 |
+
"tool_parser_type": "mistral",
|
| 14 |
+
"unk_token": "<unk>",
|
| 15 |
+
"use_default_system_prompt": false
|
| 16 |
+
}
|