初始化项目，由ModelHub XC社区提供模型
Model: Andrew0425/AgenticASR-Refiner Source: Original Platform
This commit is contained in:
ModelHub XC
36
.gitattributes
vendored
Normal file
36
.gitattributes
vendored
Normal file
@@ -0,0 +1,36 @@
|
||||
*.7z filter=lfs diff=lfs merge=lfs -text
|
||||
*.arrow filter=lfs diff=lfs merge=lfs -text
|
||||
*.bin filter=lfs diff=lfs merge=lfs -text
|
||||
*.bz2 filter=lfs diff=lfs merge=lfs -text
|
||||
*.ckpt filter=lfs diff=lfs merge=lfs -text
|
||||
*.ftz filter=lfs diff=lfs merge=lfs -text
|
||||
*.gz filter=lfs diff=lfs merge=lfs -text
|
||||
*.h5 filter=lfs diff=lfs merge=lfs -text
|
||||
*.joblib filter=lfs diff=lfs merge=lfs -text
|
||||
*.lfs.* filter=lfs diff=lfs merge=lfs -text
|
||||
*.mlmodel filter=lfs diff=lfs merge=lfs -text
|
||||
*.model filter=lfs diff=lfs merge=lfs -text
|
||||
*.msgpack filter=lfs diff=lfs merge=lfs -text
|
||||
*.npy filter=lfs diff=lfs merge=lfs -text
|
||||
*.npz filter=lfs diff=lfs merge=lfs -text
|
||||
*.onnx filter=lfs diff=lfs merge=lfs -text
|
||||
*.ot filter=lfs diff=lfs merge=lfs -text
|
||||
*.parquet filter=lfs diff=lfs merge=lfs -text
|
||||
*.pb filter=lfs diff=lfs merge=lfs -text
|
||||
*.pickle filter=lfs diff=lfs merge=lfs -text
|
||||
*.pkl filter=lfs diff=lfs merge=lfs -text
|
||||
*.pt filter=lfs diff=lfs merge=lfs -text
|
||||
*.pth filter=lfs diff=lfs merge=lfs -text
|
||||
*.rar filter=lfs diff=lfs merge=lfs -text
|
||||
*.safetensors filter=lfs diff=lfs merge=lfs -text
|
||||
saved_model/**/* filter=lfs diff=lfs merge=lfs -text
|
||||
*.tar.* filter=lfs diff=lfs merge=lfs -text
|
||||
*.tar filter=lfs diff=lfs merge=lfs -text
|
||||
*.tflite filter=lfs diff=lfs merge=lfs -text
|
||||
*.tgz filter=lfs diff=lfs merge=lfs -text
|
||||
*.wasm filter=lfs diff=lfs merge=lfs -text
|
||||
*.xz filter=lfs diff=lfs merge=lfs -text
|
||||
*.zip filter=lfs diff=lfs merge=lfs -text
|
||||
*.zst filter=lfs diff=lfs merge=lfs -text
|
||||
*tfevents* filter=lfs diff=lfs merge=lfs -text
|
||||
onnx-int4/model.onnx.data filter=lfs diff=lfs merge=lfs -text
|
||||
1
.ms_upload_cache
Normal file
1
.ms_upload_cache
Normal file
@@ -0,0 +1 @@
|
||||
{"version": 3, "repo_id": "MuyuanJ/CPM-v2", "files": {"chat_template.jinja|1782718720.653171|9062": {"hash": "7451a05cf1e28a79d97d7c0bc951028c0b1915119bf9046acd06a0e3d931f47c", "size": 9062, "status": "c"}, "generation_config.json|1782718720.6545362|220": {"hash": "e7feb60aa6fc1f051c1ac1b780a21598b067f196ba7205e304c024703078af99", "size": 220, "status": "c"}, "tokenizer_config.json|1782718728.8509912|580": {"hash": "5f7439fd04b43e98d6ec7ed386367f5c464d6bd1b52eb1f5f4de29eed11c0fbc", "size": 580, "status": "c"}, "config.json|1782718720.653837|726": {"hash": "1e2212f0a509a6f7746b3adbff9d0f23d3807e803d55c2e173eb7ff1617ddf9f", "size": 726, "status": "c"}, "tokenizer.json|1782718728.8504515|9894271": {"hash": "3e065a558a034185fe299917b398685c1facd0169a9eea1e629eb30c171fed81", "size": 9894271, "status": "c"}, "model.safetensors|1782718728.7795076|4322556448": {"hash": "1a9635c8f288648c5ec3c9d8572caaa53295242c90f94f1655e07ef2b31d907d", "size": 4322556448, "status": "c"}}}
|
||||
9
README.md
Normal file
9
README.md
Normal file
@@ -0,0 +1,9 @@
|
||||
---
|
||||
license: apache-2.0
|
||||
library_name: transformers
|
||||
pipeline_tag: text-generation
|
||||
---
|
||||
|
||||
This repository contains the model of the paper [AgenticASR: Refining Speech Recognition in Real-World Scenarios via an Agentic Approach](https://huggingface.co/papers/2607.28175).
|
||||
|
||||
Code: https://github.com/AnXMuy/AgenticASR.
|
||||
179
chat_template.jinja
Normal file
179
chat_template.jinja
Normal file
@@ -0,0 +1,179 @@
|
||||
{{- bos_token }}{%- if tools %}
|
||||
{%- set tool_definitions %}
|
||||
{{- "# Tools\n\nYou are provided with function signatures within <tools></tools> XML tags:\n<tools>" }}
|
||||
{%- for tool in tools %}
|
||||
{{- "\n" }}
|
||||
{{- tool | tojson(ensure_ascii=False) }}
|
||||
{%- endfor %}
|
||||
{{- '\n</tools>\n\nTool usage guidelines:\n- You may call zero or more functions. If no function calls are needed, just answer normally and do not include any <function ... </function>.\n- When calling a function, return an XML object within <function ... </function> using:\n<function name="function-name"><param name="param-name">param-value</param></function>\n- param-value may be multi-line. If it contains <, & or newline characters, wrap it in a CDATA block: <param name="param-name"><![CDATA[...multi-line value...]]></param>' }}
|
||||
{%- endset %}
|
||||
|
||||
{{- '<|im_start|>system\n' }}
|
||||
{%- if messages[0].role == 'system' %}
|
||||
{%- if '<tool_def_sep>' in messages[0].content %}
|
||||
{{- messages[0].content.replace('<tool_def_sep>', tool_definitions) }}
|
||||
{%- else %}
|
||||
{{- messages[0].content + '\n\n' + tool_definitions }}
|
||||
{%- endif %}
|
||||
{%- else %}
|
||||
{{- tool_definitions.lstrip() }}
|
||||
{%- endif %}
|
||||
{{- '<|im_end|>\n' }}
|
||||
{%- else %}
|
||||
{%- if messages[0].role == 'system' %}
|
||||
{{- '<|im_start|>system\n' + messages[0].content + '<|im_end|>\n' }}
|
||||
{%- endif %}
|
||||
{%- endif %}
|
||||
{%- set ns = namespace(multi_step_tool=true, last_query_index=messages|length - 1) %}
|
||||
{%- for message in messages[::-1] %}
|
||||
{%- set index = (messages|length - 1) - loop.index0 %}
|
||||
{%- if ns.multi_step_tool and message.role == "user" and message.content is string and not(message.content.startswith('<tool_response>') and message.content.endswith('</tool_response>')) %}
|
||||
{%- set ns.multi_step_tool = false %}
|
||||
{%- set ns.last_query_index = index %}
|
||||
{%- endif %}
|
||||
{%- endfor %}
|
||||
{%- for message in messages %}
|
||||
{%- if message.content is string %}
|
||||
{%- set content = message.content %}
|
||||
{%- else %}
|
||||
{%- set content = '' %}
|
||||
{%- endif %}
|
||||
{%- if (message.role == "user") or (message.role == "system" and not loop.first) %}
|
||||
{{- '<|im_start|>' + message.role + '\n' + content + '<|im_end|>' + '\n' }}
|
||||
{%- elif message.role == "assistant" %}
|
||||
{%- set reasoning_content = '' %}
|
||||
{%- if message.reasoning_content is string %}
|
||||
{%- set reasoning_content = message.reasoning_content %}
|
||||
{%- else %}
|
||||
{%- if '</think>' in content %}
|
||||
{%- set reasoning_content = content.split('</think>')[0].rstrip('\n').split('<think>')[-1].lstrip('\n') %}
|
||||
{%- set content = content.split('</think>')[-1].lstrip('\n') %}
|
||||
{%- endif %}
|
||||
{%- endif %}
|
||||
|
||||
{%- if message.tool_calls %}
|
||||
{%- set content_parts = content.split('<tool_sep>') %}
|
||||
{%- set processed_content = content_parts[0] %}
|
||||
{%- set tool_calls_count = message.tool_calls|length %}
|
||||
{%- set tool_sep_count = content_parts|length - 1 %}
|
||||
{%- set min_count = [tool_calls_count, tool_sep_count]|min %}
|
||||
|
||||
{%- for i in range(1, content_parts|length) %}
|
||||
{%- set tool_index = i - 1 %}
|
||||
{%- if tool_index < tool_calls_count %}
|
||||
{%- set tool_call = message.tool_calls[tool_index] %}
|
||||
{%- if tool_call.function %}
|
||||
{%- set tool_call = tool_call.function %}
|
||||
{%- endif %}
|
||||
{%- set single_tool_xml %}
|
||||
{{- '<function name="' ~ tool_call.name ~ '">' }}
|
||||
{%- if tool_call.arguments %}
|
||||
{%- set args_dict = tool_call.arguments %}
|
||||
{%- for param_name, param_value in args_dict.items() %}
|
||||
{{- '<param name="' ~ param_name ~ '">' }}
|
||||
{%- if param_value is string and ('<' in param_value or '&' in param_value or '\n' in param_value) %}
|
||||
{{- '<![CDATA[' + param_value + ']]>' }}
|
||||
{%- else %}
|
||||
{{- param_value }}
|
||||
{%- endif %}
|
||||
{{- '</param>' }}
|
||||
{%- endfor %}
|
||||
{%- endif %}
|
||||
{{- '</function>' }}
|
||||
{%- endset %}
|
||||
{%- set processed_content = processed_content + single_tool_xml + content_parts[i] %}
|
||||
{%- else %}
|
||||
{%- set processed_content = processed_content + content_parts[i] %}
|
||||
{%- endif %}
|
||||
{%- endfor %}
|
||||
|
||||
{%- if tool_calls_count > tool_sep_count %}
|
||||
{%- for remaining_index in range(tool_sep_count, tool_calls_count) %}
|
||||
{%- set tool_call = message.tool_calls[remaining_index] %}
|
||||
{%- if tool_call.function %}
|
||||
{%- set tool_call = tool_call.function %}
|
||||
{%- endif %}
|
||||
{%- set remaining_tool_xml %}
|
||||
{{- '<function name="' ~ tool_call.name ~ '">' }}
|
||||
{%- if tool_call.arguments %}
|
||||
{%- set args_dict = tool_call.arguments %}
|
||||
{%- for param_name, param_value in args_dict.items() %}
|
||||
{{- '<param name="' ~ param_name ~ '">' }}
|
||||
{%- if param_value is string and ('<' in param_value or '&' in param_value or '\n' in param_value) %}
|
||||
{{- '<![CDATA[' + param_value + ']]>' }}
|
||||
{%- else %}
|
||||
{{- param_value }}
|
||||
{%- endif %}
|
||||
{{- '</param>' }}
|
||||
{%- endfor %}
|
||||
{%- endif %}
|
||||
{{- '</function>' }}
|
||||
{%- endset %}
|
||||
{%- set processed_content = processed_content + remaining_tool_xml %}
|
||||
{%- endfor %}
|
||||
{%- endif %}
|
||||
|
||||
{%- set content = processed_content %}
|
||||
{%- endif %}
|
||||
|
||||
{%- if loop.index0 > ns.last_query_index %}
|
||||
{%- if reasoning_content %}
|
||||
{{- '<|im_start|>' + message.role + '\n<think>\n' + reasoning_content.strip('\n') + '\n</think>\n\n' + content.lstrip('\n') }}
|
||||
{%- else %}
|
||||
{{- '<|im_start|>' + message.role + '\n' + content }}
|
||||
{%- endif %}
|
||||
{%- else %}
|
||||
{{- '<|im_start|>' + message.role + '\n' + content }}
|
||||
{%- endif %}
|
||||
|
||||
{%- if message.tool_calls and not has_tool_sep %}
|
||||
{%- for tool_call in message.tool_calls %}
|
||||
{%- if (loop.first and content) or (not loop.first) %}
|
||||
{{- '\n' }}
|
||||
{%- endif %}
|
||||
{%- if tool_call.function %}
|
||||
{%- set tool_call = tool_call.function %}
|
||||
{%- endif %}
|
||||
{{- '<function name="' ~ tool_call.name ~ '">' }}
|
||||
{%- if tool_call.arguments %}
|
||||
{%- set args_dict = tool_call.arguments %}
|
||||
{%- for param_name, param_value in args_dict.items() %}
|
||||
{{- '<param name="' ~ param_name ~ '">' }}
|
||||
{%- if param_value is string and ('<' in param_value or '&' in param_value or '\n' in param_value) %}
|
||||
{{- '<![CDATA[' + param_value + ']]>' }}
|
||||
{%- else %}
|
||||
{{- param_value }}
|
||||
{%- endif %}
|
||||
{{- '</param>' }}
|
||||
{%- endfor %}
|
||||
{%- endif %}
|
||||
{{- '</function>' }}
|
||||
{%- endfor %}
|
||||
{%- endif %}
|
||||
{{- '<|im_end|>\n' }}
|
||||
{%- elif message.role == "tool" %}
|
||||
{%- if loop.first or (messages[loop.index0 - 1].role != "tool") %}
|
||||
{{- '<|im_start|>user' }}
|
||||
{%- endif %}
|
||||
{{- '\n<tool_response>\n' }}
|
||||
{%- if message.content is string %}
|
||||
{{- content }}
|
||||
{%- else %}
|
||||
{{- message.content | tojson(ensure_ascii=False) }}
|
||||
{%- endif %}
|
||||
{{- '\n</tool_response>' }}
|
||||
{%- if loop.last or (messages[loop.index0 + 1].role != "tool") %}
|
||||
{{- '<|im_end|>\n' }}
|
||||
{%- endif %}
|
||||
{%- endif %}
|
||||
{%- endfor %}
|
||||
{%- if add_generation_prompt %}
|
||||
{{- '<|im_start|>assistant\n' }}
|
||||
{%- if enable_thinking is defined %}
|
||||
{%- if enable_thinking is false %}
|
||||
{{- '<think>\n\n</think>\n\n' }}
|
||||
{%- elif enable_thinking is true %}
|
||||
{{- '<think>\n' }}
|
||||
{%- endif %}
|
||||
{%- endif %}
|
||||
{%- endif %}
|
||||
32
config.json
Normal file
32
config.json
Normal file
@@ -0,0 +1,32 @@
|
||||
{
|
||||
"architectures": [
|
||||
"LlamaForCausalLM"
|
||||
],
|
||||
"attention_bias": false,
|
||||
"attention_dropout": 0.0,
|
||||
"bos_token_id": 0,
|
||||
"dtype": "float32",
|
||||
"eos_token_id": 1,
|
||||
"head_dim": 128,
|
||||
"hidden_act": "silu",
|
||||
"hidden_size": 1536,
|
||||
"initializer_range": 0.02,
|
||||
"intermediate_size": 4608,
|
||||
"max_position_embeddings": 131072,
|
||||
"mlp_bias": false,
|
||||
"model_type": "llama",
|
||||
"num_attention_heads": 16,
|
||||
"num_hidden_layers": 24,
|
||||
"num_key_value_heads": 2,
|
||||
"pad_token_id": 1,
|
||||
"pretraining_tp": 1,
|
||||
"rms_norm_eps": 1e-06,
|
||||
"rope_parameters": {
|
||||
"rope_theta": 5000000,
|
||||
"rope_type": "default"
|
||||
},
|
||||
"tie_word_embeddings": false,
|
||||
"transformers_version": "5.0.0",
|
||||
"use_cache": false,
|
||||
"vocab_size": 130560
|
||||
}
|
||||
14
generation_config.json
Normal file
14
generation_config.json
Normal file
@@ -0,0 +1,14 @@
|
||||
{
|
||||
"_from_model_config": true,
|
||||
"bos_token_id": 0,
|
||||
"do_sample": true,
|
||||
"eos_token_id": [
|
||||
1,
|
||||
1,
|
||||
130073
|
||||
],
|
||||
"pad_token_id": 1,
|
||||
"temperature": 0.9,
|
||||
"top_p": 0.95,
|
||||
"transformers_version": "5.0.0"
|
||||
}
|
||||
7
mlx-int4/README.md
Normal file
7
mlx-int4/README.md
Normal file
@@ -0,0 +1,7 @@
|
||||
---
|
||||
language: en
|
||||
library_name: mlx
|
||||
pipeline_tag: text-generation
|
||||
tags:
|
||||
- mlx
|
||||
---
|
||||
179
mlx-int4/chat_template.jinja
Normal file
179
mlx-int4/chat_template.jinja
Normal file
@@ -0,0 +1,179 @@
|
||||
{{- bos_token }}{%- if tools %}
|
||||
{%- set tool_definitions %}
|
||||
{{- "# Tools\n\nYou are provided with function signatures within <tools></tools> XML tags:\n<tools>" }}
|
||||
{%- for tool in tools %}
|
||||
{{- "\n" }}
|
||||
{{- tool | tojson(ensure_ascii=False) }}
|
||||
{%- endfor %}
|
||||
{{- '\n</tools>\n\nTool usage guidelines:\n- You may call zero or more functions. If no function calls are needed, just answer normally and do not include any <function ... </function>.\n- When calling a function, return an XML object within <function ... </function> using:\n<function name="function-name"><param name="param-name">param-value</param></function>\n- param-value may be multi-line. If it contains <, & or newline characters, wrap it in a CDATA block: <param name="param-name"><![CDATA[...multi-line value...]]></param>' }}
|
||||
{%- endset %}
|
||||
|
||||
{{- '<|im_start|>system\n' }}
|
||||
{%- if messages[0].role == 'system' %}
|
||||
{%- if '<tool_def_sep>' in messages[0].content %}
|
||||
{{- messages[0].content.replace('<tool_def_sep>', tool_definitions) }}
|
||||
{%- else %}
|
||||
{{- messages[0].content + '\n\n' + tool_definitions }}
|
||||
{%- endif %}
|
||||
{%- else %}
|
||||
{{- tool_definitions.lstrip() }}
|
||||
{%- endif %}
|
||||
{{- '<|im_end|>\n' }}
|
||||
{%- else %}
|
||||
{%- if messages[0].role == 'system' %}
|
||||
{{- '<|im_start|>system\n' + messages[0].content + '<|im_end|>\n' }}
|
||||
{%- endif %}
|
||||
{%- endif %}
|
||||
{%- set ns = namespace(multi_step_tool=true, last_query_index=messages|length - 1) %}
|
||||
{%- for message in messages[::-1] %}
|
||||
{%- set index = (messages|length - 1) - loop.index0 %}
|
||||
{%- if ns.multi_step_tool and message.role == "user" and message.content is string and not(message.content.startswith('<tool_response>') and message.content.endswith('</tool_response>')) %}
|
||||
{%- set ns.multi_step_tool = false %}
|
||||
{%- set ns.last_query_index = index %}
|
||||
{%- endif %}
|
||||
{%- endfor %}
|
||||
{%- for message in messages %}
|
||||
{%- if message.content is string %}
|
||||
{%- set content = message.content %}
|
||||
{%- else %}
|
||||
{%- set content = '' %}
|
||||
{%- endif %}
|
||||
{%- if (message.role == "user") or (message.role == "system" and not loop.first) %}
|
||||
{{- '<|im_start|>' + message.role + '\n' + content + '<|im_end|>' + '\n' }}
|
||||
{%- elif message.role == "assistant" %}
|
||||
{%- set reasoning_content = '' %}
|
||||
{%- if message.reasoning_content is string %}
|
||||
{%- set reasoning_content = message.reasoning_content %}
|
||||
{%- else %}
|
||||
{%- if '</think>' in content %}
|
||||
{%- set reasoning_content = content.split('</think>')[0].rstrip('\n').split('<think>')[-1].lstrip('\n') %}
|
||||
{%- set content = content.split('</think>')[-1].lstrip('\n') %}
|
||||
{%- endif %}
|
||||
{%- endif %}
|
||||
|
||||
{%- if message.tool_calls %}
|
||||
{%- set content_parts = content.split('<tool_sep>') %}
|
||||
{%- set processed_content = content_parts[0] %}
|
||||
{%- set tool_calls_count = message.tool_calls|length %}
|
||||
{%- set tool_sep_count = content_parts|length - 1 %}
|
||||
{%- set min_count = [tool_calls_count, tool_sep_count]|min %}
|
||||
|
||||
{%- for i in range(1, content_parts|length) %}
|
||||
{%- set tool_index = i - 1 %}
|
||||
{%- if tool_index < tool_calls_count %}
|
||||
{%- set tool_call = message.tool_calls[tool_index] %}
|
||||
{%- if tool_call.function %}
|
||||
{%- set tool_call = tool_call.function %}
|
||||
{%- endif %}
|
||||
{%- set single_tool_xml %}
|
||||
{{- '<function name="' ~ tool_call.name ~ '">' }}
|
||||
{%- if tool_call.arguments %}
|
||||
{%- set args_dict = tool_call.arguments %}
|
||||
{%- for param_name, param_value in args_dict.items() %}
|
||||
{{- '<param name="' ~ param_name ~ '">' }}
|
||||
{%- if param_value is string and ('<' in param_value or '&' in param_value or '\n' in param_value) %}
|
||||
{{- '<![CDATA[' + param_value + ']]>' }}
|
||||
{%- else %}
|
||||
{{- param_value }}
|
||||
{%- endif %}
|
||||
{{- '</param>' }}
|
||||
{%- endfor %}
|
||||
{%- endif %}
|
||||
{{- '</function>' }}
|
||||
{%- endset %}
|
||||
{%- set processed_content = processed_content + single_tool_xml + content_parts[i] %}
|
||||
{%- else %}
|
||||
{%- set processed_content = processed_content + content_parts[i] %}
|
||||
{%- endif %}
|
||||
{%- endfor %}
|
||||
|
||||
{%- if tool_calls_count > tool_sep_count %}
|
||||
{%- for remaining_index in range(tool_sep_count, tool_calls_count) %}
|
||||
{%- set tool_call = message.tool_calls[remaining_index] %}
|
||||
{%- if tool_call.function %}
|
||||
{%- set tool_call = tool_call.function %}
|
||||
{%- endif %}
|
||||
{%- set remaining_tool_xml %}
|
||||
{{- '<function name="' ~ tool_call.name ~ '">' }}
|
||||
{%- if tool_call.arguments %}
|
||||
{%- set args_dict = tool_call.arguments %}
|
||||
{%- for param_name, param_value in args_dict.items() %}
|
||||
{{- '<param name="' ~ param_name ~ '">' }}
|
||||
{%- if param_value is string and ('<' in param_value or '&' in param_value or '\n' in param_value) %}
|
||||
{{- '<![CDATA[' + param_value + ']]>' }}
|
||||
{%- else %}
|
||||
{{- param_value }}
|
||||
{%- endif %}
|
||||
{{- '</param>' }}
|
||||
{%- endfor %}
|
||||
{%- endif %}
|
||||
{{- '</function>' }}
|
||||
{%- endset %}
|
||||
{%- set processed_content = processed_content + remaining_tool_xml %}
|
||||
{%- endfor %}
|
||||
{%- endif %}
|
||||
|
||||
{%- set content = processed_content %}
|
||||
{%- endif %}
|
||||
|
||||
{%- if loop.index0 > ns.last_query_index %}
|
||||
{%- if reasoning_content %}
|
||||
{{- '<|im_start|>' + message.role + '\n<think>\n' + reasoning_content.strip('\n') + '\n</think>\n\n' + content.lstrip('\n') }}
|
||||
{%- else %}
|
||||
{{- '<|im_start|>' + message.role + '\n' + content }}
|
||||
{%- endif %}
|
||||
{%- else %}
|
||||
{{- '<|im_start|>' + message.role + '\n' + content }}
|
||||
{%- endif %}
|
||||
|
||||
{%- if message.tool_calls and not has_tool_sep %}
|
||||
{%- for tool_call in message.tool_calls %}
|
||||
{%- if (loop.first and content) or (not loop.first) %}
|
||||
{{- '\n' }}
|
||||
{%- endif %}
|
||||
{%- if tool_call.function %}
|
||||
{%- set tool_call = tool_call.function %}
|
||||
{%- endif %}
|
||||
{{- '<function name="' ~ tool_call.name ~ '">' }}
|
||||
{%- if tool_call.arguments %}
|
||||
{%- set args_dict = tool_call.arguments %}
|
||||
{%- for param_name, param_value in args_dict.items() %}
|
||||
{{- '<param name="' ~ param_name ~ '">' }}
|
||||
{%- if param_value is string and ('<' in param_value or '&' in param_value or '\n' in param_value) %}
|
||||
{{- '<![CDATA[' + param_value + ']]>' }}
|
||||
{%- else %}
|
||||
{{- param_value }}
|
||||
{%- endif %}
|
||||
{{- '</param>' }}
|
||||
{%- endfor %}
|
||||
{%- endif %}
|
||||
{{- '</function>' }}
|
||||
{%- endfor %}
|
||||
{%- endif %}
|
||||
{{- '<|im_end|>\n' }}
|
||||
{%- elif message.role == "tool" %}
|
||||
{%- if loop.first or (messages[loop.index0 - 1].role != "tool") %}
|
||||
{{- '<|im_start|>user' }}
|
||||
{%- endif %}
|
||||
{{- '\n<tool_response>\n' }}
|
||||
{%- if message.content is string %}
|
||||
{{- content }}
|
||||
{%- else %}
|
||||
{{- message.content | tojson(ensure_ascii=False) }}
|
||||
{%- endif %}
|
||||
{{- '\n</tool_response>' }}
|
||||
{%- if loop.last or (messages[loop.index0 + 1].role != "tool") %}
|
||||
{{- '<|im_end|>\n' }}
|
||||
{%- endif %}
|
||||
{%- endif %}
|
||||
{%- endfor %}
|
||||
{%- if add_generation_prompt %}
|
||||
{{- '<|im_start|>assistant\n' }}
|
||||
{%- if enable_thinking is defined %}
|
||||
{%- if enable_thinking is false %}
|
||||
{{- '<think>\n\n</think>\n\n' }}
|
||||
{%- elif enable_thinking is true %}
|
||||
{{- '<think>\n' }}
|
||||
{%- endif %}
|
||||
{%- endif %}
|
||||
{%- endif %}
|
||||
46
mlx-int4/config.json
Normal file
46
mlx-int4/config.json
Normal file
@@ -0,0 +1,46 @@
|
||||
{
|
||||
"architectures": [
|
||||
"LlamaForCausalLM"
|
||||
],
|
||||
"attention_bias": false,
|
||||
"attention_dropout": 0.0,
|
||||
"bos_token_id": 0,
|
||||
"dtype": "float32",
|
||||
"eos_token_id": [
|
||||
1,
|
||||
1,
|
||||
130073
|
||||
],
|
||||
"head_dim": 128,
|
||||
"hidden_act": "silu",
|
||||
"hidden_size": 1536,
|
||||
"initializer_range": 0.02,
|
||||
"intermediate_size": 4608,
|
||||
"max_position_embeddings": 131072,
|
||||
"mlp_bias": false,
|
||||
"model_type": "llama",
|
||||
"num_attention_heads": 16,
|
||||
"num_hidden_layers": 24,
|
||||
"num_key_value_heads": 2,
|
||||
"pad_token_id": 1,
|
||||
"pretraining_tp": 1,
|
||||
"quantization": {
|
||||
"group_size": 64,
|
||||
"bits": 4,
|
||||
"mode": "affine"
|
||||
},
|
||||
"quantization_config": {
|
||||
"group_size": 64,
|
||||
"bits": 4,
|
||||
"mode": "affine"
|
||||
},
|
||||
"rms_norm_eps": 1e-06,
|
||||
"rope_parameters": {
|
||||
"rope_theta": 5000000,
|
||||
"rope_type": "default"
|
||||
},
|
||||
"tie_word_embeddings": false,
|
||||
"transformers_version": "5.0.0",
|
||||
"use_cache": false,
|
||||
"vocab_size": 130560
|
||||
}
|
||||
14
mlx-int4/generation_config.json
Normal file
14
mlx-int4/generation_config.json
Normal file
@@ -0,0 +1,14 @@
|
||||
{
|
||||
"_from_model_config": true,
|
||||
"bos_token_id": 0,
|
||||
"do_sample": true,
|
||||
"eos_token_id": [
|
||||
1,
|
||||
1,
|
||||
130073
|
||||
],
|
||||
"pad_token_id": 1,
|
||||
"temperature": 0.9,
|
||||
"top_p": 0.95,
|
||||
"transformers_version": "5.0.0"
|
||||
}
|
||||
3
mlx-int4/model.safetensors
Normal file
3
mlx-int4/model.safetensors
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:5f99fc91b86cc8fe7e22194059c88706fdcfa0f6620166e0aa6456ad5c5cc616
|
||||
size 675711614
|
||||
567
mlx-int4/model.safetensors.index.json
Normal file
567
mlx-int4/model.safetensors.index.json
Normal file
@@ -0,0 +1,567 @@
|
||||
{
|
||||
"metadata": {
|
||||
"total_size": 675649536,
|
||||
"total_parameters": 1080632832
|
||||
},
|
||||
"weight_map": {
|
||||
"lm_head.biases": "model.safetensors",
|
||||
"lm_head.scales": "model.safetensors",
|
||||
"lm_head.weight": "model.safetensors",
|
||||
"model.embed_tokens.biases": "model.safetensors",
|
||||
"model.embed_tokens.scales": "model.safetensors",
|
||||
"model.embed_tokens.weight": "model.safetensors",
|
||||
"model.layers.0.input_layernorm.weight": "model.safetensors",
|
||||
"model.layers.0.mlp.down_proj.biases": "model.safetensors",
|
||||
"model.layers.0.mlp.down_proj.scales": "model.safetensors",
|
||||
"model.layers.0.mlp.down_proj.weight": "model.safetensors",
|
||||
"model.layers.0.mlp.gate_proj.biases": "model.safetensors",
|
||||
"model.layers.0.mlp.gate_proj.scales": "model.safetensors",
|
||||
"model.layers.0.mlp.gate_proj.weight": "model.safetensors",
|
||||
"model.layers.0.mlp.up_proj.biases": "model.safetensors",
|
||||
"model.layers.0.mlp.up_proj.scales": "model.safetensors",
|
||||
"model.layers.0.mlp.up_proj.weight": "model.safetensors",
|
||||
"model.layers.0.post_attention_layernorm.weight": "model.safetensors",
|
||||
"model.layers.0.self_attn.k_proj.biases": "model.safetensors",
|
||||
"model.layers.0.self_attn.k_proj.scales": "model.safetensors",
|
||||
"model.layers.0.self_attn.k_proj.weight": "model.safetensors",
|
||||
"model.layers.0.self_attn.o_proj.biases": "model.safetensors",
|
||||
"model.layers.0.self_attn.o_proj.scales": "model.safetensors",
|
||||
"model.layers.0.self_attn.o_proj.weight": "model.safetensors",
|
||||
"model.layers.0.self_attn.q_proj.biases": "model.safetensors",
|
||||
"model.layers.0.self_attn.q_proj.scales": "model.safetensors",
|
||||
"model.layers.0.self_attn.q_proj.weight": "model.safetensors",
|
||||
"model.layers.0.self_attn.v_proj.biases": "model.safetensors",
|
||||
"model.layers.0.self_attn.v_proj.scales": "model.safetensors",
|
||||
"model.layers.0.self_attn.v_proj.weight": "model.safetensors",
|
||||
"model.layers.1.input_layernorm.weight": "model.safetensors",
|
||||
"model.layers.1.mlp.down_proj.biases": "model.safetensors",
|
||||
"model.layers.1.mlp.down_proj.scales": "model.safetensors",
|
||||
"model.layers.1.mlp.down_proj.weight": "model.safetensors",
|
||||
"model.layers.1.mlp.gate_proj.biases": "model.safetensors",
|
||||
"model.layers.1.mlp.gate_proj.scales": "model.safetensors",
|
||||
"model.layers.1.mlp.gate_proj.weight": "model.safetensors",
|
||||
"model.layers.1.mlp.up_proj.biases": "model.safetensors",
|
||||
"model.layers.1.mlp.up_proj.scales": "model.safetensors",
|
||||
"model.layers.1.mlp.up_proj.weight": "model.safetensors",
|
||||
"model.layers.1.post_attention_layernorm.weight": "model.safetensors",
|
||||
"model.layers.1.self_attn.k_proj.biases": "model.safetensors",
|
||||
"model.layers.1.self_attn.k_proj.scales": "model.safetensors",
|
||||
"model.layers.1.self_attn.k_proj.weight": "model.safetensors",
|
||||
"model.layers.1.self_attn.o_proj.biases": "model.safetensors",
|
||||
"model.layers.1.self_attn.o_proj.scales": "model.safetensors",
|
||||
"model.layers.1.self_attn.o_proj.weight": "model.safetensors",
|
||||
"model.layers.1.self_attn.q_proj.biases": "model.safetensors",
|
||||
"model.layers.1.self_attn.q_proj.scales": "model.safetensors",
|
||||
"model.layers.1.self_attn.q_proj.weight": "model.safetensors",
|
||||
"model.layers.1.self_attn.v_proj.biases": "model.safetensors",
|
||||
"model.layers.1.self_attn.v_proj.scales": "model.safetensors",
|
||||
"model.layers.1.self_attn.v_proj.weight": "model.safetensors",
|
||||
"model.layers.10.input_layernorm.weight": "model.safetensors",
|
||||
"model.layers.10.mlp.down_proj.biases": "model.safetensors",
|
||||
"model.layers.10.mlp.down_proj.scales": "model.safetensors",
|
||||
"model.layers.10.mlp.down_proj.weight": "model.safetensors",
|
||||
"model.layers.10.mlp.gate_proj.biases": "model.safetensors",
|
||||
"model.layers.10.mlp.gate_proj.scales": "model.safetensors",
|
||||
"model.layers.10.mlp.gate_proj.weight": "model.safetensors",
|
||||
"model.layers.10.mlp.up_proj.biases": "model.safetensors",
|
||||
"model.layers.10.mlp.up_proj.scales": "model.safetensors",
|
||||
"model.layers.10.mlp.up_proj.weight": "model.safetensors",
|
||||
"model.layers.10.post_attention_layernorm.weight": "model.safetensors",
|
||||
"model.layers.10.self_attn.k_proj.biases": "model.safetensors",
|
||||
"model.layers.10.self_attn.k_proj.scales": "model.safetensors",
|
||||
"model.layers.10.self_attn.k_proj.weight": "model.safetensors",
|
||||
"model.layers.10.self_attn.o_proj.biases": "model.safetensors",
|
||||
"model.layers.10.self_attn.o_proj.scales": "model.safetensors",
|
||||
"model.layers.10.self_attn.o_proj.weight": "model.safetensors",
|
||||
"model.layers.10.self_attn.q_proj.biases": "model.safetensors",
|
||||
"model.layers.10.self_attn.q_proj.scales": "model.safetensors",
|
||||
"model.layers.10.self_attn.q_proj.weight": "model.safetensors",
|
||||
"model.layers.10.self_attn.v_proj.biases": "model.safetensors",
|
||||
"model.layers.10.self_attn.v_proj.scales": "model.safetensors",
|
||||
"model.layers.10.self_attn.v_proj.weight": "model.safetensors",
|
||||
"model.layers.11.input_layernorm.weight": "model.safetensors",
|
||||
"model.layers.11.mlp.down_proj.biases": "model.safetensors",
|
||||
"model.layers.11.mlp.down_proj.scales": "model.safetensors",
|
||||
"model.layers.11.mlp.down_proj.weight": "model.safetensors",
|
||||
"model.layers.11.mlp.gate_proj.biases": "model.safetensors",
|
||||
"model.layers.11.mlp.gate_proj.scales": "model.safetensors",
|
||||
"model.layers.11.mlp.gate_proj.weight": "model.safetensors",
|
||||
"model.layers.11.mlp.up_proj.biases": "model.safetensors",
|
||||
"model.layers.11.mlp.up_proj.scales": "model.safetensors",
|
||||
"model.layers.11.mlp.up_proj.weight": "model.safetensors",
|
||||
"model.layers.11.post_attention_layernorm.weight": "model.safetensors",
|
||||
"model.layers.11.self_attn.k_proj.biases": "model.safetensors",
|
||||
"model.layers.11.self_attn.k_proj.scales": "model.safetensors",
|
||||
"model.layers.11.self_attn.k_proj.weight": "model.safetensors",
|
||||
"model.layers.11.self_attn.o_proj.biases": "model.safetensors",
|
||||
"model.layers.11.self_attn.o_proj.scales": "model.safetensors",
|
||||
"model.layers.11.self_attn.o_proj.weight": "model.safetensors",
|
||||
"model.layers.11.self_attn.q_proj.biases": "model.safetensors",
|
||||
"model.layers.11.self_attn.q_proj.scales": "model.safetensors",
|
||||
"model.layers.11.self_attn.q_proj.weight": "model.safetensors",
|
||||
"model.layers.11.self_attn.v_proj.biases": "model.safetensors",
|
||||
"model.layers.11.self_attn.v_proj.scales": "model.safetensors",
|
||||
"model.layers.11.self_attn.v_proj.weight": "model.safetensors",
|
||||
"model.layers.12.input_layernorm.weight": "model.safetensors",
|
||||
"model.layers.12.mlp.down_proj.biases": "model.safetensors",
|
||||
"model.layers.12.mlp.down_proj.scales": "model.safetensors",
|
||||
"model.layers.12.mlp.down_proj.weight": "model.safetensors",
|
||||
"model.layers.12.mlp.gate_proj.biases": "model.safetensors",
|
||||
"model.layers.12.mlp.gate_proj.scales": "model.safetensors",
|
||||
"model.layers.12.mlp.gate_proj.weight": "model.safetensors",
|
||||
"model.layers.12.mlp.up_proj.biases": "model.safetensors",
|
||||
"model.layers.12.mlp.up_proj.scales": "model.safetensors",
|
||||
"model.layers.12.mlp.up_proj.weight": "model.safetensors",
|
||||
"model.layers.12.post_attention_layernorm.weight": "model.safetensors",
|
||||
"model.layers.12.self_attn.k_proj.biases": "model.safetensors",
|
||||
"model.layers.12.self_attn.k_proj.scales": "model.safetensors",
|
||||
"model.layers.12.self_attn.k_proj.weight": "model.safetensors",
|
||||
"model.layers.12.self_attn.o_proj.biases": "model.safetensors",
|
||||
"model.layers.12.self_attn.o_proj.scales": "model.safetensors",
|
||||
"model.layers.12.self_attn.o_proj.weight": "model.safetensors",
|
||||
"model.layers.12.self_attn.q_proj.biases": "model.safetensors",
|
||||
"model.layers.12.self_attn.q_proj.scales": "model.safetensors",
|
||||
"model.layers.12.self_attn.q_proj.weight": "model.safetensors",
|
||||
"model.layers.12.self_attn.v_proj.biases": "model.safetensors",
|
||||
"model.layers.12.self_attn.v_proj.scales": "model.safetensors",
|
||||
"model.layers.12.self_attn.v_proj.weight": "model.safetensors",
|
||||
"model.layers.13.input_layernorm.weight": "model.safetensors",
|
||||
"model.layers.13.mlp.down_proj.biases": "model.safetensors",
|
||||
"model.layers.13.mlp.down_proj.scales": "model.safetensors",
|
||||
"model.layers.13.mlp.down_proj.weight": "model.safetensors",
|
||||
"model.layers.13.mlp.gate_proj.biases": "model.safetensors",
|
||||
"model.layers.13.mlp.gate_proj.scales": "model.safetensors",
|
||||
"model.layers.13.mlp.gate_proj.weight": "model.safetensors",
|
||||
"model.layers.13.mlp.up_proj.biases": "model.safetensors",
|
||||
"model.layers.13.mlp.up_proj.scales": "model.safetensors",
|
||||
"model.layers.13.mlp.up_proj.weight": "model.safetensors",
|
||||
"model.layers.13.post_attention_layernorm.weight": "model.safetensors",
|
||||
"model.layers.13.self_attn.k_proj.biases": "model.safetensors",
|
||||
"model.layers.13.self_attn.k_proj.scales": "model.safetensors",
|
||||
"model.layers.13.self_attn.k_proj.weight": "model.safetensors",
|
||||
"model.layers.13.self_attn.o_proj.biases": "model.safetensors",
|
||||
"model.layers.13.self_attn.o_proj.scales": "model.safetensors",
|
||||
"model.layers.13.self_attn.o_proj.weight": "model.safetensors",
|
||||
"model.layers.13.self_attn.q_proj.biases": "model.safetensors",
|
||||
"model.layers.13.self_attn.q_proj.scales": "model.safetensors",
|
||||
"model.layers.13.self_attn.q_proj.weight": "model.safetensors",
|
||||
"model.layers.13.self_attn.v_proj.biases": "model.safetensors",
|
||||
"model.layers.13.self_attn.v_proj.scales": "model.safetensors",
|
||||
"model.layers.13.self_attn.v_proj.weight": "model.safetensors",
|
||||
"model.layers.14.input_layernorm.weight": "model.safetensors",
|
||||
"model.layers.14.mlp.down_proj.biases": "model.safetensors",
|
||||
"model.layers.14.mlp.down_proj.scales": "model.safetensors",
|
||||
"model.layers.14.mlp.down_proj.weight": "model.safetensors",
|
||||
"model.layers.14.mlp.gate_proj.biases": "model.safetensors",
|
||||
"model.layers.14.mlp.gate_proj.scales": "model.safetensors",
|
||||
"model.layers.14.mlp.gate_proj.weight": "model.safetensors",
|
||||
"model.layers.14.mlp.up_proj.biases": "model.safetensors",
|
||||
"model.layers.14.mlp.up_proj.scales": "model.safetensors",
|
||||
"model.layers.14.mlp.up_proj.weight": "model.safetensors",
|
||||
"model.layers.14.post_attention_layernorm.weight": "model.safetensors",
|
||||
"model.layers.14.self_attn.k_proj.biases": "model.safetensors",
|
||||
"model.layers.14.self_attn.k_proj.scales": "model.safetensors",
|
||||
"model.layers.14.self_attn.k_proj.weight": "model.safetensors",
|
||||
"model.layers.14.self_attn.o_proj.biases": "model.safetensors",
|
||||
"model.layers.14.self_attn.o_proj.scales": "model.safetensors",
|
||||
"model.layers.14.self_attn.o_proj.weight": "model.safetensors",
|
||||
"model.layers.14.self_attn.q_proj.biases": "model.safetensors",
|
||||
"model.layers.14.self_attn.q_proj.scales": "model.safetensors",
|
||||
"model.layers.14.self_attn.q_proj.weight": "model.safetensors",
|
||||
"model.layers.14.self_attn.v_proj.biases": "model.safetensors",
|
||||
"model.layers.14.self_attn.v_proj.scales": "model.safetensors",
|
||||
"model.layers.14.self_attn.v_proj.weight": "model.safetensors",
|
||||
"model.layers.15.input_layernorm.weight": "model.safetensors",
|
||||
"model.layers.15.mlp.down_proj.biases": "model.safetensors",
|
||||
"model.layers.15.mlp.down_proj.scales": "model.safetensors",
|
||||
"model.layers.15.mlp.down_proj.weight": "model.safetensors",
|
||||
"model.layers.15.mlp.gate_proj.biases": "model.safetensors",
|
||||
"model.layers.15.mlp.gate_proj.scales": "model.safetensors",
|
||||
"model.layers.15.mlp.gate_proj.weight": "model.safetensors",
|
||||
"model.layers.15.mlp.up_proj.biases": "model.safetensors",
|
||||
"model.layers.15.mlp.up_proj.scales": "model.safetensors",
|
||||
"model.layers.15.mlp.up_proj.weight": "model.safetensors",
|
||||
"model.layers.15.post_attention_layernorm.weight": "model.safetensors",
|
||||
"model.layers.15.self_attn.k_proj.biases": "model.safetensors",
|
||||
"model.layers.15.self_attn.k_proj.scales": "model.safetensors",
|
||||
"model.layers.15.self_attn.k_proj.weight": "model.safetensors",
|
||||
"model.layers.15.self_attn.o_proj.biases": "model.safetensors",
|
||||
"model.layers.15.self_attn.o_proj.scales": "model.safetensors",
|
||||
"model.layers.15.self_attn.o_proj.weight": "model.safetensors",
|
||||
"model.layers.15.self_attn.q_proj.biases": "model.safetensors",
|
||||
"model.layers.15.self_attn.q_proj.scales": "model.safetensors",
|
||||
"model.layers.15.self_attn.q_proj.weight": "model.safetensors",
|
||||
"model.layers.15.self_attn.v_proj.biases": "model.safetensors",
|
||||
"model.layers.15.self_attn.v_proj.scales": "model.safetensors",
|
||||
"model.layers.15.self_attn.v_proj.weight": "model.safetensors",
|
||||
"model.layers.16.input_layernorm.weight": "model.safetensors",
|
||||
"model.layers.16.mlp.down_proj.biases": "model.safetensors",
|
||||
"model.layers.16.mlp.down_proj.scales": "model.safetensors",
|
||||
"model.layers.16.mlp.down_proj.weight": "model.safetensors",
|
||||
"model.layers.16.mlp.gate_proj.biases": "model.safetensors",
|
||||
"model.layers.16.mlp.gate_proj.scales": "model.safetensors",
|
||||
"model.layers.16.mlp.gate_proj.weight": "model.safetensors",
|
||||
"model.layers.16.mlp.up_proj.biases": "model.safetensors",
|
||||
"model.layers.16.mlp.up_proj.scales": "model.safetensors",
|
||||
"model.layers.16.mlp.up_proj.weight": "model.safetensors",
|
||||
"model.layers.16.post_attention_layernorm.weight": "model.safetensors",
|
||||
"model.layers.16.self_attn.k_proj.biases": "model.safetensors",
|
||||
"model.layers.16.self_attn.k_proj.scales": "model.safetensors",
|
||||
"model.layers.16.self_attn.k_proj.weight": "model.safetensors",
|
||||
"model.layers.16.self_attn.o_proj.biases": "model.safetensors",
|
||||
"model.layers.16.self_attn.o_proj.scales": "model.safetensors",
|
||||
"model.layers.16.self_attn.o_proj.weight": "model.safetensors",
|
||||
"model.layers.16.self_attn.q_proj.biases": "model.safetensors",
|
||||
"model.layers.16.self_attn.q_proj.scales": "model.safetensors",
|
||||
"model.layers.16.self_attn.q_proj.weight": "model.safetensors",
|
||||
"model.layers.16.self_attn.v_proj.biases": "model.safetensors",
|
||||
"model.layers.16.self_attn.v_proj.scales": "model.safetensors",
|
||||
"model.layers.16.self_attn.v_proj.weight": "model.safetensors",
|
||||
"model.layers.17.input_layernorm.weight": "model.safetensors",
|
||||
"model.layers.17.mlp.down_proj.biases": "model.safetensors",
|
||||
"model.layers.17.mlp.down_proj.scales": "model.safetensors",
|
||||
"model.layers.17.mlp.down_proj.weight": "model.safetensors",
|
||||
"model.layers.17.mlp.gate_proj.biases": "model.safetensors",
|
||||
"model.layers.17.mlp.gate_proj.scales": "model.safetensors",
|
||||
"model.layers.17.mlp.gate_proj.weight": "model.safetensors",
|
||||
"model.layers.17.mlp.up_proj.biases": "model.safetensors",
|
||||
"model.layers.17.mlp.up_proj.scales": "model.safetensors",
|
||||
"model.layers.17.mlp.up_proj.weight": "model.safetensors",
|
||||
"model.layers.17.post_attention_layernorm.weight": "model.safetensors",
|
||||
"model.layers.17.self_attn.k_proj.biases": "model.safetensors",
|
||||
"model.layers.17.self_attn.k_proj.scales": "model.safetensors",
|
||||
"model.layers.17.self_attn.k_proj.weight": "model.safetensors",
|
||||
"model.layers.17.self_attn.o_proj.biases": "model.safetensors",
|
||||
"model.layers.17.self_attn.o_proj.scales": "model.safetensors",
|
||||
"model.layers.17.self_attn.o_proj.weight": "model.safetensors",
|
||||
"model.layers.17.self_attn.q_proj.biases": "model.safetensors",
|
||||
"model.layers.17.self_attn.q_proj.scales": "model.safetensors",
|
||||
"model.layers.17.self_attn.q_proj.weight": "model.safetensors",
|
||||
"model.layers.17.self_attn.v_proj.biases": "model.safetensors",
|
||||
"model.layers.17.self_attn.v_proj.scales": "model.safetensors",
|
||||
"model.layers.17.self_attn.v_proj.weight": "model.safetensors",
|
||||
"model.layers.18.input_layernorm.weight": "model.safetensors",
|
||||
"model.layers.18.mlp.down_proj.biases": "model.safetensors",
|
||||
"model.layers.18.mlp.down_proj.scales": "model.safetensors",
|
||||
"model.layers.18.mlp.down_proj.weight": "model.safetensors",
|
||||
"model.layers.18.mlp.gate_proj.biases": "model.safetensors",
|
||||
"model.layers.18.mlp.gate_proj.scales": "model.safetensors",
|
||||
"model.layers.18.mlp.gate_proj.weight": "model.safetensors",
|
||||
"model.layers.18.mlp.up_proj.biases": "model.safetensors",
|
||||
"model.layers.18.mlp.up_proj.scales": "model.safetensors",
|
||||
"model.layers.18.mlp.up_proj.weight": "model.safetensors",
|
||||
"model.layers.18.post_attention_layernorm.weight": "model.safetensors",
|
||||
"model.layers.18.self_attn.k_proj.biases": "model.safetensors",
|
||||
"model.layers.18.self_attn.k_proj.scales": "model.safetensors",
|
||||
"model.layers.18.self_attn.k_proj.weight": "model.safetensors",
|
||||
"model.layers.18.self_attn.o_proj.biases": "model.safetensors",
|
||||
"model.layers.18.self_attn.o_proj.scales": "model.safetensors",
|
||||
"model.layers.18.self_attn.o_proj.weight": "model.safetensors",
|
||||
"model.layers.18.self_attn.q_proj.biases": "model.safetensors",
|
||||
"model.layers.18.self_attn.q_proj.scales": "model.safetensors",
|
||||
"model.layers.18.self_attn.q_proj.weight": "model.safetensors",
|
||||
"model.layers.18.self_attn.v_proj.biases": "model.safetensors",
|
||||
"model.layers.18.self_attn.v_proj.scales": "model.safetensors",
|
||||
"model.layers.18.self_attn.v_proj.weight": "model.safetensors",
|
||||
"model.layers.19.input_layernorm.weight": "model.safetensors",
|
||||
"model.layers.19.mlp.down_proj.biases": "model.safetensors",
|
||||
"model.layers.19.mlp.down_proj.scales": "model.safetensors",
|
||||
"model.layers.19.mlp.down_proj.weight": "model.safetensors",
|
||||
"model.layers.19.mlp.gate_proj.biases": "model.safetensors",
|
||||
"model.layers.19.mlp.gate_proj.scales": "model.safetensors",
|
||||
"model.layers.19.mlp.gate_proj.weight": "model.safetensors",
|
||||
"model.layers.19.mlp.up_proj.biases": "model.safetensors",
|
||||
"model.layers.19.mlp.up_proj.scales": "model.safetensors",
|
||||
"model.layers.19.mlp.up_proj.weight": "model.safetensors",
|
||||
"model.layers.19.post_attention_layernorm.weight": "model.safetensors",
|
||||
"model.layers.19.self_attn.k_proj.biases": "model.safetensors",
|
||||
"model.layers.19.self_attn.k_proj.scales": "model.safetensors",
|
||||
"model.layers.19.self_attn.k_proj.weight": "model.safetensors",
|
||||
"model.layers.19.self_attn.o_proj.biases": "model.safetensors",
|
||||
"model.layers.19.self_attn.o_proj.scales": "model.safetensors",
|
||||
"model.layers.19.self_attn.o_proj.weight": "model.safetensors",
|
||||
"model.layers.19.self_attn.q_proj.biases": "model.safetensors",
|
||||
"model.layers.19.self_attn.q_proj.scales": "model.safetensors",
|
||||
"model.layers.19.self_attn.q_proj.weight": "model.safetensors",
|
||||
"model.layers.19.self_attn.v_proj.biases": "model.safetensors",
|
||||
"model.layers.19.self_attn.v_proj.scales": "model.safetensors",
|
||||
"model.layers.19.self_attn.v_proj.weight": "model.safetensors",
|
||||
"model.layers.2.input_layernorm.weight": "model.safetensors",
|
||||
"model.layers.2.mlp.down_proj.biases": "model.safetensors",
|
||||
"model.layers.2.mlp.down_proj.scales": "model.safetensors",
|
||||
"model.layers.2.mlp.down_proj.weight": "model.safetensors",
|
||||
"model.layers.2.mlp.gate_proj.biases": "model.safetensors",
|
||||
"model.layers.2.mlp.gate_proj.scales": "model.safetensors",
|
||||
"model.layers.2.mlp.gate_proj.weight": "model.safetensors",
|
||||
"model.layers.2.mlp.up_proj.biases": "model.safetensors",
|
||||
"model.layers.2.mlp.up_proj.scales": "model.safetensors",
|
||||
"model.layers.2.mlp.up_proj.weight": "model.safetensors",
|
||||
"model.layers.2.post_attention_layernorm.weight": "model.safetensors",
|
||||
"model.layers.2.self_attn.k_proj.biases": "model.safetensors",
|
||||
"model.layers.2.self_attn.k_proj.scales": "model.safetensors",
|
||||
"model.layers.2.self_attn.k_proj.weight": "model.safetensors",
|
||||
"model.layers.2.self_attn.o_proj.biases": "model.safetensors",
|
||||
"model.layers.2.self_attn.o_proj.scales": "model.safetensors",
|
||||
"model.layers.2.self_attn.o_proj.weight": "model.safetensors",
|
||||
"model.layers.2.self_attn.q_proj.biases": "model.safetensors",
|
||||
"model.layers.2.self_attn.q_proj.scales": "model.safetensors",
|
||||
"model.layers.2.self_attn.q_proj.weight": "model.safetensors",
|
||||
"model.layers.2.self_attn.v_proj.biases": "model.safetensors",
|
||||
"model.layers.2.self_attn.v_proj.scales": "model.safetensors",
|
||||
"model.layers.2.self_attn.v_proj.weight": "model.safetensors",
|
||||
"model.layers.20.input_layernorm.weight": "model.safetensors",
|
||||
"model.layers.20.mlp.down_proj.biases": "model.safetensors",
|
||||
"model.layers.20.mlp.down_proj.scales": "model.safetensors",
|
||||
"model.layers.20.mlp.down_proj.weight": "model.safetensors",
|
||||
"model.layers.20.mlp.gate_proj.biases": "model.safetensors",
|
||||
"model.layers.20.mlp.gate_proj.scales": "model.safetensors",
|
||||
"model.layers.20.mlp.gate_proj.weight": "model.safetensors",
|
||||
"model.layers.20.mlp.up_proj.biases": "model.safetensors",
|
||||
"model.layers.20.mlp.up_proj.scales": "model.safetensors",
|
||||
"model.layers.20.mlp.up_proj.weight": "model.safetensors",
|
||||
"model.layers.20.post_attention_layernorm.weight": "model.safetensors",
|
||||
"model.layers.20.self_attn.k_proj.biases": "model.safetensors",
|
||||
"model.layers.20.self_attn.k_proj.scales": "model.safetensors",
|
||||
"model.layers.20.self_attn.k_proj.weight": "model.safetensors",
|
||||
"model.layers.20.self_attn.o_proj.biases": "model.safetensors",
|
||||
"model.layers.20.self_attn.o_proj.scales": "model.safetensors",
|
||||
"model.layers.20.self_attn.o_proj.weight": "model.safetensors",
|
||||
"model.layers.20.self_attn.q_proj.biases": "model.safetensors",
|
||||
"model.layers.20.self_attn.q_proj.scales": "model.safetensors",
|
||||
"model.layers.20.self_attn.q_proj.weight": "model.safetensors",
|
||||
"model.layers.20.self_attn.v_proj.biases": "model.safetensors",
|
||||
"model.layers.20.self_attn.v_proj.scales": "model.safetensors",
|
||||
"model.layers.20.self_attn.v_proj.weight": "model.safetensors",
|
||||
"model.layers.21.input_layernorm.weight": "model.safetensors",
|
||||
"model.layers.21.mlp.down_proj.biases": "model.safetensors",
|
||||
"model.layers.21.mlp.down_proj.scales": "model.safetensors",
|
||||
"model.layers.21.mlp.down_proj.weight": "model.safetensors",
|
||||
"model.layers.21.mlp.gate_proj.biases": "model.safetensors",
|
||||
"model.layers.21.mlp.gate_proj.scales": "model.safetensors",
|
||||
"model.layers.21.mlp.gate_proj.weight": "model.safetensors",
|
||||
"model.layers.21.mlp.up_proj.biases": "model.safetensors",
|
||||
"model.layers.21.mlp.up_proj.scales": "model.safetensors",
|
||||
"model.layers.21.mlp.up_proj.weight": "model.safetensors",
|
||||
"model.layers.21.post_attention_layernorm.weight": "model.safetensors",
|
||||
"model.layers.21.self_attn.k_proj.biases": "model.safetensors",
|
||||
"model.layers.21.self_attn.k_proj.scales": "model.safetensors",
|
||||
"model.layers.21.self_attn.k_proj.weight": "model.safetensors",
|
||||
"model.layers.21.self_attn.o_proj.biases": "model.safetensors",
|
||||
"model.layers.21.self_attn.o_proj.scales": "model.safetensors",
|
||||
"model.layers.21.self_attn.o_proj.weight": "model.safetensors",
|
||||
"model.layers.21.self_attn.q_proj.biases": "model.safetensors",
|
||||
"model.layers.21.self_attn.q_proj.scales": "model.safetensors",
|
||||
"model.layers.21.self_attn.q_proj.weight": "model.safetensors",
|
||||
"model.layers.21.self_attn.v_proj.biases": "model.safetensors",
|
||||
"model.layers.21.self_attn.v_proj.scales": "model.safetensors",
|
||||
"model.layers.21.self_attn.v_proj.weight": "model.safetensors",
|
||||
"model.layers.22.input_layernorm.weight": "model.safetensors",
|
||||
"model.layers.22.mlp.down_proj.biases": "model.safetensors",
|
||||
"model.layers.22.mlp.down_proj.scales": "model.safetensors",
|
||||
"model.layers.22.mlp.down_proj.weight": "model.safetensors",
|
||||
"model.layers.22.mlp.gate_proj.biases": "model.safetensors",
|
||||
"model.layers.22.mlp.gate_proj.scales": "model.safetensors",
|
||||
"model.layers.22.mlp.gate_proj.weight": "model.safetensors",
|
||||
"model.layers.22.mlp.up_proj.biases": "model.safetensors",
|
||||
"model.layers.22.mlp.up_proj.scales": "model.safetensors",
|
||||
"model.layers.22.mlp.up_proj.weight": "model.safetensors",
|
||||
"model.layers.22.post_attention_layernorm.weight": "model.safetensors",
|
||||
"model.layers.22.self_attn.k_proj.biases": "model.safetensors",
|
||||
"model.layers.22.self_attn.k_proj.scales": "model.safetensors",
|
||||
"model.layers.22.self_attn.k_proj.weight": "model.safetensors",
|
||||
"model.layers.22.self_attn.o_proj.biases": "model.safetensors",
|
||||
"model.layers.22.self_attn.o_proj.scales": "model.safetensors",
|
||||
"model.layers.22.self_attn.o_proj.weight": "model.safetensors",
|
||||
"model.layers.22.self_attn.q_proj.biases": "model.safetensors",
|
||||
"model.layers.22.self_attn.q_proj.scales": "model.safetensors",
|
||||
"model.layers.22.self_attn.q_proj.weight": "model.safetensors",
|
||||
"model.layers.22.self_attn.v_proj.biases": "model.safetensors",
|
||||
"model.layers.22.self_attn.v_proj.scales": "model.safetensors",
|
||||
"model.layers.22.self_attn.v_proj.weight": "model.safetensors",
|
||||
"model.layers.23.input_layernorm.weight": "model.safetensors",
|
||||
"model.layers.23.mlp.down_proj.biases": "model.safetensors",
|
||||
"model.layers.23.mlp.down_proj.scales": "model.safetensors",
|
||||
"model.layers.23.mlp.down_proj.weight": "model.safetensors",
|
||||
"model.layers.23.mlp.gate_proj.biases": "model.safetensors",
|
||||
"model.layers.23.mlp.gate_proj.scales": "model.safetensors",
|
||||
"model.layers.23.mlp.gate_proj.weight": "model.safetensors",
|
||||
"model.layers.23.mlp.up_proj.biases": "model.safetensors",
|
||||
"model.layers.23.mlp.up_proj.scales": "model.safetensors",
|
||||
"model.layers.23.mlp.up_proj.weight": "model.safetensors",
|
||||
"model.layers.23.post_attention_layernorm.weight": "model.safetensors",
|
||||
"model.layers.23.self_attn.k_proj.biases": "model.safetensors",
|
||||
"model.layers.23.self_attn.k_proj.scales": "model.safetensors",
|
||||
"model.layers.23.self_attn.k_proj.weight": "model.safetensors",
|
||||
"model.layers.23.self_attn.o_proj.biases": "model.safetensors",
|
||||
"model.layers.23.self_attn.o_proj.scales": "model.safetensors",
|
||||
"model.layers.23.self_attn.o_proj.weight": "model.safetensors",
|
||||
"model.layers.23.self_attn.q_proj.biases": "model.safetensors",
|
||||
"model.layers.23.self_attn.q_proj.scales": "model.safetensors",
|
||||
"model.layers.23.self_attn.q_proj.weight": "model.safetensors",
|
||||
"model.layers.23.self_attn.v_proj.biases": "model.safetensors",
|
||||
"model.layers.23.self_attn.v_proj.scales": "model.safetensors",
|
||||
"model.layers.23.self_attn.v_proj.weight": "model.safetensors",
|
||||
"model.layers.3.input_layernorm.weight": "model.safetensors",
|
||||
"model.layers.3.mlp.down_proj.biases": "model.safetensors",
|
||||
"model.layers.3.mlp.down_proj.scales": "model.safetensors",
|
||||
"model.layers.3.mlp.down_proj.weight": "model.safetensors",
|
||||
"model.layers.3.mlp.gate_proj.biases": "model.safetensors",
|
||||
"model.layers.3.mlp.gate_proj.scales": "model.safetensors",
|
||||
"model.layers.3.mlp.gate_proj.weight": "model.safetensors",
|
||||
"model.layers.3.mlp.up_proj.biases": "model.safetensors",
|
||||
"model.layers.3.mlp.up_proj.scales": "model.safetensors",
|
||||
"model.layers.3.mlp.up_proj.weight": "model.safetensors",
|
||||
"model.layers.3.post_attention_layernorm.weight": "model.safetensors",
|
||||
"model.layers.3.self_attn.k_proj.biases": "model.safetensors",
|
||||
"model.layers.3.self_attn.k_proj.scales": "model.safetensors",
|
||||
"model.layers.3.self_attn.k_proj.weight": "model.safetensors",
|
||||
"model.layers.3.self_attn.o_proj.biases": "model.safetensors",
|
||||
"model.layers.3.self_attn.o_proj.scales": "model.safetensors",
|
||||
"model.layers.3.self_attn.o_proj.weight": "model.safetensors",
|
||||
"model.layers.3.self_attn.q_proj.biases": "model.safetensors",
|
||||
"model.layers.3.self_attn.q_proj.scales": "model.safetensors",
|
||||
"model.layers.3.self_attn.q_proj.weight": "model.safetensors",
|
||||
"model.layers.3.self_attn.v_proj.biases": "model.safetensors",
|
||||
"model.layers.3.self_attn.v_proj.scales": "model.safetensors",
|
||||
"model.layers.3.self_attn.v_proj.weight": "model.safetensors",
|
||||
"model.layers.4.input_layernorm.weight": "model.safetensors",
|
||||
"model.layers.4.mlp.down_proj.biases": "model.safetensors",
|
||||
"model.layers.4.mlp.down_proj.scales": "model.safetensors",
|
||||
"model.layers.4.mlp.down_proj.weight": "model.safetensors",
|
||||
"model.layers.4.mlp.gate_proj.biases": "model.safetensors",
|
||||
"model.layers.4.mlp.gate_proj.scales": "model.safetensors",
|
||||
"model.layers.4.mlp.gate_proj.weight": "model.safetensors",
|
||||
"model.layers.4.mlp.up_proj.biases": "model.safetensors",
|
||||
"model.layers.4.mlp.up_proj.scales": "model.safetensors",
|
||||
"model.layers.4.mlp.up_proj.weight": "model.safetensors",
|
||||
"model.layers.4.post_attention_layernorm.weight": "model.safetensors",
|
||||
"model.layers.4.self_attn.k_proj.biases": "model.safetensors",
|
||||
"model.layers.4.self_attn.k_proj.scales": "model.safetensors",
|
||||
"model.layers.4.self_attn.k_proj.weight": "model.safetensors",
|
||||
"model.layers.4.self_attn.o_proj.biases": "model.safetensors",
|
||||
"model.layers.4.self_attn.o_proj.scales": "model.safetensors",
|
||||
"model.layers.4.self_attn.o_proj.weight": "model.safetensors",
|
||||
"model.layers.4.self_attn.q_proj.biases": "model.safetensors",
|
||||
"model.layers.4.self_attn.q_proj.scales": "model.safetensors",
|
||||
"model.layers.4.self_attn.q_proj.weight": "model.safetensors",
|
||||
"model.layers.4.self_attn.v_proj.biases": "model.safetensors",
|
||||
"model.layers.4.self_attn.v_proj.scales": "model.safetensors",
|
||||
"model.layers.4.self_attn.v_proj.weight": "model.safetensors",
|
||||
"model.layers.5.input_layernorm.weight": "model.safetensors",
|
||||
"model.layers.5.mlp.down_proj.biases": "model.safetensors",
|
||||
"model.layers.5.mlp.down_proj.scales": "model.safetensors",
|
||||
"model.layers.5.mlp.down_proj.weight": "model.safetensors",
|
||||
"model.layers.5.mlp.gate_proj.biases": "model.safetensors",
|
||||
"model.layers.5.mlp.gate_proj.scales": "model.safetensors",
|
||||
"model.layers.5.mlp.gate_proj.weight": "model.safetensors",
|
||||
"model.layers.5.mlp.up_proj.biases": "model.safetensors",
|
||||
"model.layers.5.mlp.up_proj.scales": "model.safetensors",
|
||||
"model.layers.5.mlp.up_proj.weight": "model.safetensors",
|
||||
"model.layers.5.post_attention_layernorm.weight": "model.safetensors",
|
||||
"model.layers.5.self_attn.k_proj.biases": "model.safetensors",
|
||||
"model.layers.5.self_attn.k_proj.scales": "model.safetensors",
|
||||
"model.layers.5.self_attn.k_proj.weight": "model.safetensors",
|
||||
"model.layers.5.self_attn.o_proj.biases": "model.safetensors",
|
||||
"model.layers.5.self_attn.o_proj.scales": "model.safetensors",
|
||||
"model.layers.5.self_attn.o_proj.weight": "model.safetensors",
|
||||
"model.layers.5.self_attn.q_proj.biases": "model.safetensors",
|
||||
"model.layers.5.self_attn.q_proj.scales": "model.safetensors",
|
||||
"model.layers.5.self_attn.q_proj.weight": "model.safetensors",
|
||||
"model.layers.5.self_attn.v_proj.biases": "model.safetensors",
|
||||
"model.layers.5.self_attn.v_proj.scales": "model.safetensors",
|
||||
"model.layers.5.self_attn.v_proj.weight": "model.safetensors",
|
||||
"model.layers.6.input_layernorm.weight": "model.safetensors",
|
||||
"model.layers.6.mlp.down_proj.biases": "model.safetensors",
|
||||
"model.layers.6.mlp.down_proj.scales": "model.safetensors",
|
||||
"model.layers.6.mlp.down_proj.weight": "model.safetensors",
|
||||
"model.layers.6.mlp.gate_proj.biases": "model.safetensors",
|
||||
"model.layers.6.mlp.gate_proj.scales": "model.safetensors",
|
||||
"model.layers.6.mlp.gate_proj.weight": "model.safetensors",
|
||||
"model.layers.6.mlp.up_proj.biases": "model.safetensors",
|
||||
"model.layers.6.mlp.up_proj.scales": "model.safetensors",
|
||||
"model.layers.6.mlp.up_proj.weight": "model.safetensors",
|
||||
"model.layers.6.post_attention_layernorm.weight": "model.safetensors",
|
||||
"model.layers.6.self_attn.k_proj.biases": "model.safetensors",
|
||||
"model.layers.6.self_attn.k_proj.scales": "model.safetensors",
|
||||
"model.layers.6.self_attn.k_proj.weight": "model.safetensors",
|
||||
"model.layers.6.self_attn.o_proj.biases": "model.safetensors",
|
||||
"model.layers.6.self_attn.o_proj.scales": "model.safetensors",
|
||||
"model.layers.6.self_attn.o_proj.weight": "model.safetensors",
|
||||
"model.layers.6.self_attn.q_proj.biases": "model.safetensors",
|
||||
"model.layers.6.self_attn.q_proj.scales": "model.safetensors",
|
||||
"model.layers.6.self_attn.q_proj.weight": "model.safetensors",
|
||||
"model.layers.6.self_attn.v_proj.biases": "model.safetensors",
|
||||
"model.layers.6.self_attn.v_proj.scales": "model.safetensors",
|
||||
"model.layers.6.self_attn.v_proj.weight": "model.safetensors",
|
||||
"model.layers.7.input_layernorm.weight": "model.safetensors",
|
||||
"model.layers.7.mlp.down_proj.biases": "model.safetensors",
|
||||
"model.layers.7.mlp.down_proj.scales": "model.safetensors",
|
||||
"model.layers.7.mlp.down_proj.weight": "model.safetensors",
|
||||
"model.layers.7.mlp.gate_proj.biases": "model.safetensors",
|
||||
"model.layers.7.mlp.gate_proj.scales": "model.safetensors",
|
||||
"model.layers.7.mlp.gate_proj.weight": "model.safetensors",
|
||||
"model.layers.7.mlp.up_proj.biases": "model.safetensors",
|
||||
"model.layers.7.mlp.up_proj.scales": "model.safetensors",
|
||||
"model.layers.7.mlp.up_proj.weight": "model.safetensors",
|
||||
"model.layers.7.post_attention_layernorm.weight": "model.safetensors",
|
||||
"model.layers.7.self_attn.k_proj.biases": "model.safetensors",
|
||||
"model.layers.7.self_attn.k_proj.scales": "model.safetensors",
|
||||
"model.layers.7.self_attn.k_proj.weight": "model.safetensors",
|
||||
"model.layers.7.self_attn.o_proj.biases": "model.safetensors",
|
||||
"model.layers.7.self_attn.o_proj.scales": "model.safetensors",
|
||||
"model.layers.7.self_attn.o_proj.weight": "model.safetensors",
|
||||
"model.layers.7.self_attn.q_proj.biases": "model.safetensors",
|
||||
"model.layers.7.self_attn.q_proj.scales": "model.safetensors",
|
||||
"model.layers.7.self_attn.q_proj.weight": "model.safetensors",
|
||||
"model.layers.7.self_attn.v_proj.biases": "model.safetensors",
|
||||
"model.layers.7.self_attn.v_proj.scales": "model.safetensors",
|
||||
"model.layers.7.self_attn.v_proj.weight": "model.safetensors",
|
||||
"model.layers.8.input_layernorm.weight": "model.safetensors",
|
||||
"model.layers.8.mlp.down_proj.biases": "model.safetensors",
|
||||
"model.layers.8.mlp.down_proj.scales": "model.safetensors",
|
||||
"model.layers.8.mlp.down_proj.weight": "model.safetensors",
|
||||
"model.layers.8.mlp.gate_proj.biases": "model.safetensors",
|
||||
"model.layers.8.mlp.gate_proj.scales": "model.safetensors",
|
||||
"model.layers.8.mlp.gate_proj.weight": "model.safetensors",
|
||||
"model.layers.8.mlp.up_proj.biases": "model.safetensors",
|
||||
"model.layers.8.mlp.up_proj.scales": "model.safetensors",
|
||||
"model.layers.8.mlp.up_proj.weight": "model.safetensors",
|
||||
"model.layers.8.post_attention_layernorm.weight": "model.safetensors",
|
||||
"model.layers.8.self_attn.k_proj.biases": "model.safetensors",
|
||||
"model.layers.8.self_attn.k_proj.scales": "model.safetensors",
|
||||
"model.layers.8.self_attn.k_proj.weight": "model.safetensors",
|
||||
"model.layers.8.self_attn.o_proj.biases": "model.safetensors",
|
||||
"model.layers.8.self_attn.o_proj.scales": "model.safetensors",
|
||||
"model.layers.8.self_attn.o_proj.weight": "model.safetensors",
|
||||
"model.layers.8.self_attn.q_proj.biases": "model.safetensors",
|
||||
"model.layers.8.self_attn.q_proj.scales": "model.safetensors",
|
||||
"model.layers.8.self_attn.q_proj.weight": "model.safetensors",
|
||||
"model.layers.8.self_attn.v_proj.biases": "model.safetensors",
|
||||
"model.layers.8.self_attn.v_proj.scales": "model.safetensors",
|
||||
"model.layers.8.self_attn.v_proj.weight": "model.safetensors",
|
||||
"model.layers.9.input_layernorm.weight": "model.safetensors",
|
||||
"model.layers.9.mlp.down_proj.biases": "model.safetensors",
|
||||
"model.layers.9.mlp.down_proj.scales": "model.safetensors",
|
||||
"model.layers.9.mlp.down_proj.weight": "model.safetensors",
|
||||
"model.layers.9.mlp.gate_proj.biases": "model.safetensors",
|
||||
"model.layers.9.mlp.gate_proj.scales": "model.safetensors",
|
||||
"model.layers.9.mlp.gate_proj.weight": "model.safetensors",
|
||||
"model.layers.9.mlp.up_proj.biases": "model.safetensors",
|
||||
"model.layers.9.mlp.up_proj.scales": "model.safetensors",
|
||||
"model.layers.9.mlp.up_proj.weight": "model.safetensors",
|
||||
"model.layers.9.post_attention_layernorm.weight": "model.safetensors",
|
||||
"model.layers.9.self_attn.k_proj.biases": "model.safetensors",
|
||||
"model.layers.9.self_attn.k_proj.scales": "model.safetensors",
|
||||
"model.layers.9.self_attn.k_proj.weight": "model.safetensors",
|
||||
"model.layers.9.self_attn.o_proj.biases": "model.safetensors",
|
||||
"model.layers.9.self_attn.o_proj.scales": "model.safetensors",
|
||||
"model.layers.9.self_attn.o_proj.weight": "model.safetensors",
|
||||
"model.layers.9.self_attn.q_proj.biases": "model.safetensors",
|
||||
"model.layers.9.self_attn.q_proj.scales": "model.safetensors",
|
||||
"model.layers.9.self_attn.q_proj.weight": "model.safetensors",
|
||||
"model.layers.9.self_attn.v_proj.biases": "model.safetensors",
|
||||
"model.layers.9.self_attn.v_proj.scales": "model.safetensors",
|
||||
"model.layers.9.self_attn.v_proj.weight": "model.safetensors",
|
||||
"model.norm.weight": "model.safetensors"
|
||||
}
|
||||
}
|
||||
653947
mlx-int4/tokenizer.json
Normal file
653947
mlx-int4/tokenizer.json
Normal file
File diff suppressed because it is too large
Load Diff
23
mlx-int4/tokenizer_config.json
Normal file
23
mlx-int4/tokenizer_config.json
Normal file
@@ -0,0 +1,23 @@
|
||||
{
|
||||
"add_prefix_space": null,
|
||||
"backend": "tokenizers",
|
||||
"bos_token": "<s>",
|
||||
"clean_up_tokenization_spaces": false,
|
||||
"eos_token": "</s>",
|
||||
"extra_special_tokens": [
|
||||
"<|im_end|>"
|
||||
],
|
||||
"is_local": true,
|
||||
"legacy": true,
|
||||
"local_files_only": false,
|
||||
"model_max_length": 1000000000000000019884624838656,
|
||||
"model_specific_special_tokens": {},
|
||||
"pad_token": "</s>",
|
||||
"padding_side": "right",
|
||||
"sp_model_kwargs": {},
|
||||
"spaces_between_special_tokens": false,
|
||||
"split_special_tokens": false,
|
||||
"tokenizer_class": "TokenizersBackend",
|
||||
"unk_token": "<unk>",
|
||||
"use_default_system_prompt": false
|
||||
}
|
||||
3
model.safetensors
Normal file
3
model.safetensors
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:1a9635c8f288648c5ec3c9d8572caaa53295242c90f94f1655e07ef2b31d907d
|
||||
size 4322556448
|
||||
48
onnx-int4/README.md
Normal file
48
onnx-int4/README.md
Normal file
@@ -0,0 +1,48 @@
|
||||
# AgenticASR-Refiner ONNX (INT4)
|
||||
|
||||
INT4 weight-only quantization of the Optimum ONNX export of
|
||||
`Andrew0425/AgenticASR-Refiner` (Llama-based ASR transcript refiner, 24 layers,
|
||||
hidden 1536, GQA 16/2, head_dim 128, vocab 130560).
|
||||
|
||||
- `model.onnx` + `model.onnx.data` — INT4 (MatMulNBits, block size 32, symmetric,
|
||||
accuracy level 4), ~1.3 GB. Graph I/O is identical to the fp32 export
|
||||
(`input_ids` / `attention_mask` / `position_ids` / `past_key_values.*`).
|
||||
- Quantized with `onnxruntime 1.24.4` `MatMulNBitsQuantizer`
|
||||
(`onnxruntime.quantization.matmul_nbits_quantizer`).
|
||||
- Requires ONNX Runtime >= 1.20 (CPU EP supports `MatMulNBits`).
|
||||
|
||||
Tokenization uses the original repo tokenizer (`tokenizer.json` at the repo root).
|
||||
|
||||
## Verified generation (ONNX Runtime 1.28, CPU)
|
||||
|
||||
| Input | Output |
|
||||
|---|---|
|
||||
| 我今天去了公司然后然后开了个会，明天再去见张总 | 我今天去了公司然后开了个会，明天再去见张总 |
|
||||
| 你好你好你好我是那个小李啊 电话是13800138000 | 你好我是小李，电话是13800138000 |
|
||||
|
||||
## Usage
|
||||
|
||||
```python
|
||||
import numpy as np
|
||||
import onnxruntime as ort
|
||||
from transformers import AutoTokenizer
|
||||
|
||||
tokenizer = AutoTokenizer.from_pretrained("Andrew0425/AgenticASR-Refiner")
|
||||
session = ort.InferenceSession("model.onnx", providers=["CPUExecutionProvider"])
|
||||
input_names = [i.name for i in session.get_inputs()]
|
||||
kv_names = [n for n in input_names if n.startswith("past_key_values")]
|
||||
|
||||
prompt = tokenizer.apply_chat_template(
|
||||
[{"role": "system", "content": "你是 ASR 文本纠错助手。保留原意，最小修改。"},
|
||||
{"role": "user", "content": "我今天去了公司然后然后开了个会"}],
|
||||
tokenize=False, add_generation_prompt=True,
|
||||
)
|
||||
ids = tokenizer(prompt).input_ids
|
||||
pasts = [np.zeros((1, 2, 0, 128), dtype=np.float32) for _ in kv_names]
|
||||
|
||||
# prefill, then loop decode: feed input_ids/attention_mask/position_ids + pasts
|
||||
```
|
||||
|
||||
Note: `optimum-onnx 0.1.0` cannot yet run this checkpoint (dummy KV-cache shape
|
||||
uses `hidden_size // num_heads` = 96 instead of `head_dim` = 128); use the raw
|
||||
ONNX Runtime loop above, or a future fixed version of optimum-onnx.
|
||||
34
onnx-int4/config.json
Normal file
34
onnx-int4/config.json
Normal file
@@ -0,0 +1,34 @@
|
||||
{
|
||||
"architectures": [
|
||||
"LlamaForCausalLM"
|
||||
],
|
||||
"attention_bias": false,
|
||||
"attention_dropout": 0.0,
|
||||
"bos_token_id": 0,
|
||||
"dtype": "float32",
|
||||
"eos_token_id": 1,
|
||||
"head_dim": 128,
|
||||
"hidden_act": "silu",
|
||||
"hidden_size": 1536,
|
||||
"initializer_range": 0.02,
|
||||
"intermediate_size": 4608,
|
||||
"max_position_embeddings": 131072,
|
||||
"mlp_bias": false,
|
||||
"model_type": "llama",
|
||||
"num_attention_heads": 16,
|
||||
"num_hidden_layers": 24,
|
||||
"num_key_value_heads": 2,
|
||||
"pad_token_id": 1,
|
||||
"pretraining_tp": 1,
|
||||
"rms_norm_eps": 1e-06,
|
||||
"rope_parameters": {
|
||||
"rope_theta": 5000000,
|
||||
"rope_type": "default"
|
||||
},
|
||||
"rope_scaling": null,
|
||||
"rope_theta": 10000.0,
|
||||
"tie_word_embeddings": false,
|
||||
"transformers_version": "4.57.6",
|
||||
"use_cache": true,
|
||||
"vocab_size": 130560
|
||||
}
|
||||
14
onnx-int4/generation_config.json
Normal file
14
onnx-int4/generation_config.json
Normal file
@@ -0,0 +1,14 @@
|
||||
{
|
||||
"_from_model_config": true,
|
||||
"bos_token_id": 0,
|
||||
"do_sample": true,
|
||||
"eos_token_id": [
|
||||
1,
|
||||
1,
|
||||
130073
|
||||
],
|
||||
"pad_token_id": 1,
|
||||
"temperature": 0.9,
|
||||
"top_p": 0.95,
|
||||
"transformers_version": "4.57.6"
|
||||
}
|
||||
3
onnx-int4/model.onnx
Normal file
3
onnx-int4/model.onnx
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:602b5e2192cf05f9656f419fe9a9cc7a45c23ced3659aa5441fbef8ba8387f85
|
||||
size 1144846
|
||||
3
onnx-int4/model.onnx.data
Normal file
3
onnx-int4/model.onnx.data
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:b93ed739800441b1e11563b8cf10bb0643e4db5e7cd82c35b305e1af55a7ed83
|
||||
size 1352472576
|
||||
653947
tokenizer.json
Normal file
653947
tokenizer.json
Normal file
File diff suppressed because it is too large
Load Diff
22
tokenizer_config.json
Normal file
22
tokenizer_config.json
Normal file
@@ -0,0 +1,22 @@
|
||||
{
|
||||
"add_prefix_space": null,
|
||||
"backend": "tokenizers",
|
||||
"bos_token": "<s>",
|
||||
"clean_up_tokenization_spaces": false,
|
||||
"eos_token": "</s>",
|
||||
"extra_special_tokens": [
|
||||
"<|im_end|>"
|
||||
],
|
||||
"is_local": true,
|
||||
"legacy": true,
|
||||
"model_max_length": 1000000000000000019884624838656,
|
||||
"model_specific_special_tokens": {},
|
||||
"pad_token": "</s>",
|
||||
"padding_side": "right",
|
||||
"sp_model_kwargs": {},
|
||||
"spaces_between_special_tokens": false,
|
||||
"split_special_tokens": false,
|
||||
"tokenizer_class": "TokenizersBackend",
|
||||
"unk_token": "<unk>",
|
||||
"use_default_system_prompt": false
|
||||
}
|
||||
Reference in New Issue
Block a user