初始化项目,由ModelHub XC社区提供模型

Model: jekunz/Qwen3-1.7B-is-SmolTalk
Source: Original Platform
This commit is contained in:
ModelHub XC
2026-05-12 18:02:21 +08:00
commit 69052a882b
35 changed files with 304333 additions and 0 deletions

37
.gitattributes vendored Normal file
View File

@@ -0,0 +1,37 @@
*.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
checkpoint-2331/tokenizer.json filter=lfs diff=lfs merge=lfs -text
tokenizer.json filter=lfs diff=lfs merge=lfs -text

58
README.md Normal file
View File

@@ -0,0 +1,58 @@
---
base_model: Qwen/Qwen3-1.7B
library_name: transformers
model_name: Qwen3-1.7B-is-smoltalk
tags:
- generated_from_trainer
- trl
- sft
licence: license
---
# Model Card for Qwen3-1.7B-is-smoltalk
This model is a fine-tuned version of [Qwen/Qwen3-1.7B](https://huggingface.co/Qwen/Qwen3-1.7B).
It has been trained using [TRL](https://github.com/huggingface/trl).
## Quick start
```python
from transformers import pipeline
question = "If you had a time machine, but could only go to the past or the future once and never return, which would you choose and why?"
generator = pipeline("text-generation", model="None", device="cuda")
output = generator([{"role": "user", "content": question}], max_new_tokens=128, return_full_text=False)[0]
print(output["generated_text"])
```
## Training procedure
This model was trained with SFT.
### Framework versions
- TRL: 0.25.1
- Transformers: 4.57.3
- Pytorch: 2.9.1
- Datasets: 4.4.1
- Tokenizers: 0.22.1
## Citations
Cite TRL as:
```bibtex
@misc{vonwerra2022trl,
title = {{TRL: Transformer Reinforcement Learning}},
author = {Leandro von Werra and Younes Belkada and Lewis Tunstall and Edward Beeching and Tristan Thrush and Nathan Lambert and Shengyi Huang and Kashif Rasul and Quentin Gallou{\'e}dec},
year = 2020,
journal = {GitHub repository},
publisher = {GitHub},
howpublished = {\url{https://github.com/huggingface/trl}}
}
```

28
added_tokens.json Normal file
View File

@@ -0,0 +1,28 @@
{
"</think>": 151668,
"</tool_call>": 151658,
"</tool_response>": 151666,
"<think>": 151667,
"<tool_call>": 151657,
"<tool_response>": 151665,
"<|box_end|>": 151649,
"<|box_start|>": 151648,
"<|endoftext|>": 151643,
"<|file_sep|>": 151664,
"<|fim_middle|>": 151660,
"<|fim_pad|>": 151662,
"<|fim_prefix|>": 151659,
"<|fim_suffix|>": 151661,
"<|im_end|>": 151645,
"<|im_start|>": 151644,
"<|image_pad|>": 151655,
"<|object_ref_end|>": 151647,
"<|object_ref_start|>": 151646,
"<|quad_end|>": 151651,
"<|quad_start|>": 151650,
"<|repo_name|>": 151663,
"<|video_pad|>": 151656,
"<|vision_end|>": 151653,
"<|vision_pad|>": 151654,
"<|vision_start|>": 151652
}

89
chat_template.jinja Normal file
View File

@@ -0,0 +1,89 @@
{%- if tools %}
{{- '<|im_start|>system\n' }}
{%- if messages[0].role == 'system' %}
{{- messages[0].content + '\n\n' }}
{%- endif %}
{{- "# Tools\n\nYou may call one or more functions to assist with the user query.\n\nYou are provided with function signatures within <tools></tools> XML tags:\n<tools>" }}
{%- for tool in tools %}
{{- "\n" }}
{{- tool | tojson }}
{%- endfor %}
{{- "\n</tools>\n\nFor each function call, return a json object with function name and arguments within <tool_call></tool_call> XML tags:\n<tool_call>\n{\"name\": <function-name>, \"arguments\": <args-json-object>}\n</tool_call><|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 loop.index0 > ns.last_query_index %}
{%- if loop.last or (not loop.last and 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 %}
{%- 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 %}
{{- '<tool_call>\n{"name": "' }}
{{- tool_call.name }}
{{- '", "arguments": ' }}
{%- if tool_call.arguments is string %}
{{- tool_call.arguments }}
{%- else %}
{{- tool_call.arguments | tojson }}
{%- endif %}
{{- '}\n</tool_call>' }}
{%- 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' }}
{{- content }}
{{- '\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 and enable_thinking is false %}
{{- '<think>\n\n</think>\n\n' }}
{%- endif %}
{%- endif %}

View File

@@ -0,0 +1,28 @@
{
"</think>": 151668,
"</tool_call>": 151658,
"</tool_response>": 151666,
"<think>": 151667,
"<tool_call>": 151657,
"<tool_response>": 151665,
"<|box_end|>": 151649,
"<|box_start|>": 151648,
"<|endoftext|>": 151643,
"<|file_sep|>": 151664,
"<|fim_middle|>": 151660,
"<|fim_pad|>": 151662,
"<|fim_prefix|>": 151659,
"<|fim_suffix|>": 151661,
"<|im_end|>": 151645,
"<|im_start|>": 151644,
"<|image_pad|>": 151655,
"<|object_ref_end|>": 151647,
"<|object_ref_start|>": 151646,
"<|quad_end|>": 151651,
"<|quad_start|>": 151650,
"<|repo_name|>": 151663,
"<|video_pad|>": 151656,
"<|vision_end|>": 151653,
"<|vision_pad|>": 151654,
"<|vision_start|>": 151652
}

View File

@@ -0,0 +1,89 @@
{%- if tools %}
{{- '<|im_start|>system\n' }}
{%- if messages[0].role == 'system' %}
{{- messages[0].content + '\n\n' }}
{%- endif %}
{{- "# Tools\n\nYou may call one or more functions to assist with the user query.\n\nYou are provided with function signatures within <tools></tools> XML tags:\n<tools>" }}
{%- for tool in tools %}
{{- "\n" }}
{{- tool | tojson }}
{%- endfor %}
{{- "\n</tools>\n\nFor each function call, return a json object with function name and arguments within <tool_call></tool_call> XML tags:\n<tool_call>\n{\"name\": <function-name>, \"arguments\": <args-json-object>}\n</tool_call><|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 loop.index0 > ns.last_query_index %}
{%- if loop.last or (not loop.last and 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 %}
{%- 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 %}
{{- '<tool_call>\n{"name": "' }}
{{- tool_call.name }}
{{- '", "arguments": ' }}
{%- if tool_call.arguments is string %}
{{- tool_call.arguments }}
{%- else %}
{{- tool_call.arguments | tojson }}
{%- endif %}
{{- '}\n</tool_call>' }}
{%- 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' }}
{{- content }}
{{- '\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 and enable_thinking is false %}
{{- '<think>\n\n</think>\n\n' }}
{%- endif %}
{%- endif %}

View File

@@ -0,0 +1,60 @@
{
"architectures": [
"Qwen3ForCausalLM"
],
"attention_bias": false,
"attention_dropout": 0.0,
"dtype": "bfloat16",
"eos_token_id": 151645,
"head_dim": 128,
"hidden_act": "silu",
"hidden_size": 2048,
"initializer_range": 0.02,
"intermediate_size": 6144,
"layer_types": [
"full_attention",
"full_attention",
"full_attention",
"full_attention",
"full_attention",
"full_attention",
"full_attention",
"full_attention",
"full_attention",
"full_attention",
"full_attention",
"full_attention",
"full_attention",
"full_attention",
"full_attention",
"full_attention",
"full_attention",
"full_attention",
"full_attention",
"full_attention",
"full_attention",
"full_attention",
"full_attention",
"full_attention",
"full_attention",
"full_attention",
"full_attention",
"full_attention"
],
"max_position_embeddings": 40960,
"max_window_layers": 28,
"model_type": "qwen3",
"num_attention_heads": 16,
"num_hidden_layers": 28,
"num_key_value_heads": 8,
"pad_token_id": 151643,
"rms_norm_eps": 1e-06,
"rope_scaling": null,
"rope_theta": 1000000,
"sliding_window": null,
"tie_word_embeddings": true,
"transformers_version": "4.57.3",
"use_cache": true,
"use_sliding_window": false,
"vocab_size": 151936
}

View File

@@ -0,0 +1,12 @@
{
"do_sample": true,
"eos_token_id": [
151645,
151643
],
"pad_token_id": 151643,
"temperature": 0.6,
"top_k": 20,
"top_p": 0.95,
"transformers_version": "4.57.3"
}

151388
checkpoint-2331/merges.txt Normal file

File diff suppressed because it is too large Load Diff

View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:97d5556df27e5c1dc6c5efba81b02d7a3f6ad7a1c1df014530ac640878ab278c
size 3441185608

View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:9a7bb4e33099bab0246f45f79d941b78ff83f510b3a52f563efcc400ef63636c
size 6882572207

View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:7350b59a307e1d89d4515e24325811dc1aa8deab5b5b4635887adaaf78ea1dc5
size 16389

View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:af262eaf45f7c1f39099b694376de497429ab46c1046a1d9afe70a315f1b6d81
size 16389

View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:57f833fda5ff0e7e566107275c268625e3eb07e8475116fe109d9c667809d469
size 16389

View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:2a6e6037388bc56484982620075eea8724b4696f67f60603b9c448e44f41705c
size 16389

View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:d2bf73391bb68f0fffcb931501656f3679db7d996fe258d8287099b6cb7a23a2
size 16389

View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:222199bb7faa2ce2cb817e7f870ac7c364fb0f0872e17d8a9280f38596da9a06
size 16389

View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:ca3accfbfe6616f878cfeda3df23f4418e00b348760c584e397d6c92081cb5c4
size 16389

View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:a64b41c5668afda0c862d9774a14b1c0a390fe6a57086de71f9fdfb00edb457e
size 16389

View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:35bf403bc40e5afcef265aac3760158fd8b3c8f99612103397e77ed012c06503
size 1465

View File

@@ -0,0 +1,31 @@
{
"additional_special_tokens": [
"<|im_start|>",
"<|im_end|>",
"<|object_ref_start|>",
"<|object_ref_end|>",
"<|box_start|>",
"<|box_end|>",
"<|quad_start|>",
"<|quad_end|>",
"<|vision_start|>",
"<|vision_end|>",
"<|vision_pad|>",
"<|image_pad|>",
"<|video_pad|>"
],
"eos_token": {
"content": "<|im_end|>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false
},
"pad_token": {
"content": "<|endoftext|>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false
}
}

BIN
checkpoint-2331/tokenizer.json (Stored with Git LFS) Normal file

Binary file not shown.

View File

@@ -0,0 +1,239 @@
{
"add_bos_token": false,
"add_prefix_space": false,
"added_tokens_decoder": {
"151643": {
"content": "<|endoftext|>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"151644": {
"content": "<|im_start|>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"151645": {
"content": "<|im_end|>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"151646": {
"content": "<|object_ref_start|>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"151647": {
"content": "<|object_ref_end|>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"151648": {
"content": "<|box_start|>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"151649": {
"content": "<|box_end|>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"151650": {
"content": "<|quad_start|>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"151651": {
"content": "<|quad_end|>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"151652": {
"content": "<|vision_start|>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"151653": {
"content": "<|vision_end|>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"151654": {
"content": "<|vision_pad|>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"151655": {
"content": "<|image_pad|>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"151656": {
"content": "<|video_pad|>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"151657": {
"content": "<tool_call>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": false
},
"151658": {
"content": "</tool_call>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": false
},
"151659": {
"content": "<|fim_prefix|>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": false
},
"151660": {
"content": "<|fim_middle|>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": false
},
"151661": {
"content": "<|fim_suffix|>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": false
},
"151662": {
"content": "<|fim_pad|>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": false
},
"151663": {
"content": "<|repo_name|>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": false
},
"151664": {
"content": "<|file_sep|>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": false
},
"151665": {
"content": "<tool_response>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": false
},
"151666": {
"content": "</tool_response>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": false
},
"151667": {
"content": "<think>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": false
},
"151668": {
"content": "</think>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": false
}
},
"additional_special_tokens": [
"<|im_start|>",
"<|im_end|>",
"<|object_ref_start|>",
"<|object_ref_end|>",
"<|box_start|>",
"<|box_end|>",
"<|quad_start|>",
"<|quad_end|>",
"<|vision_start|>",
"<|vision_end|>",
"<|vision_pad|>",
"<|image_pad|>",
"<|video_pad|>"
],
"bos_token": null,
"clean_up_tokenization_spaces": false,
"eos_token": "<|im_end|>",
"errors": "replace",
"extra_special_tokens": {},
"model_max_length": 131072,
"pad_token": "<|endoftext|>",
"split_special_tokens": false,
"tokenizer_class": "Qwen2Tokenizer",
"unk_token": null
}

View File

@@ -0,0 +1,494 @@
{
"best_global_step": null,
"best_metric": null,
"best_model_checkpoint": null,
"epoch": 1.0,
"eval_steps": 500,
"global_step": 2331,
"is_hyper_param_search": false,
"is_local_process_zero": true,
"is_world_process_zero": true,
"log_history": [
{
"entropy": 1.7801356130838395,
"epoch": 0.021458076283461188,
"grad_norm": 2.984375,
"learning_rate": 6.282051282051282e-06,
"loss": 2.7148,
"mean_token_accuracy": 0.5160968991369009,
"num_tokens": 13027304.0,
"step": 50
},
{
"entropy": 2.12295062482357,
"epoch": 0.042916152566922376,
"grad_norm": 0.7890625,
"learning_rate": 1.2692307692307693e-05,
"loss": 2.1312,
"mean_token_accuracy": 0.5675665412843227,
"num_tokens": 26060152.0,
"step": 100
},
{
"entropy": 1.844578797519207,
"epoch": 0.06437422885038356,
"grad_norm": 0.82421875,
"learning_rate": 1.9102564102564103e-05,
"loss": 1.844,
"mean_token_accuracy": 0.6109572112560272,
"num_tokens": 39093818.0,
"step": 150
},
{
"entropy": 1.6819258108735085,
"epoch": 0.08583230513384475,
"grad_norm": 0.8515625,
"learning_rate": 2.551282051282051e-05,
"loss": 1.6802,
"mean_token_accuracy": 0.6382600109279156,
"num_tokens": 52123695.0,
"step": 200
},
{
"entropy": 1.5457392731308937,
"epoch": 0.10729038141730594,
"grad_norm": 0.80078125,
"learning_rate": 2.9996212711496212e-05,
"loss": 1.5424,
"mean_token_accuracy": 0.6616944916546345,
"num_tokens": 65156301.0,
"step": 250
},
{
"entropy": 1.4541309079527855,
"epoch": 0.12874845770076712,
"grad_norm": 0.83203125,
"learning_rate": 2.992893632784019e-05,
"loss": 1.4502,
"mean_token_accuracy": 0.6769822642207146,
"num_tokens": 78189155.0,
"step": 300
},
{
"entropy": 1.3839471048116685,
"epoch": 0.1502065339842283,
"grad_norm": 0.90234375,
"learning_rate": 2.9777932337106776e-05,
"loss": 1.3795,
"mean_token_accuracy": 0.6891845127940178,
"num_tokens": 91225387.0,
"step": 350
},
{
"entropy": 1.3477001741528511,
"epoch": 0.1716646102676895,
"grad_norm": 0.8046875,
"learning_rate": 2.95440476317018e-05,
"loss": 1.3427,
"mean_token_accuracy": 0.6955448819696903,
"num_tokens": 104264395.0,
"step": 400
},
{
"entropy": 1.3151711079478263,
"epoch": 0.1931226865511507,
"grad_norm": 0.79296875,
"learning_rate": 2.9228593933122738e-05,
"loss": 1.3096,
"mean_token_accuracy": 0.7014366894960403,
"num_tokens": 117304006.0,
"step": 450
},
{
"entropy": 1.286205082833767,
"epoch": 0.2145807628346119,
"grad_norm": 0.76953125,
"learning_rate": 2.8833340435285732e-05,
"loss": 1.281,
"mean_token_accuracy": 0.7059694881737232,
"num_tokens": 130330369.0,
"step": 500
},
{
"entropy": 1.256286238282919,
"epoch": 0.23603883911807305,
"grad_norm": 0.76953125,
"learning_rate": 2.8360503882159413e-05,
"loss": 1.2508,
"mean_token_accuracy": 0.711535804271698,
"num_tokens": 143357759.0,
"step": 550
},
{
"entropy": 1.2380341781675817,
"epoch": 0.25749691540153424,
"grad_norm": 0.78125,
"learning_rate": 2.7812736135354192e-05,
"loss": 1.2326,
"mean_token_accuracy": 0.7147769713401795,
"num_tokens": 156390933.0,
"step": 600
},
{
"entropy": 1.2227300041913987,
"epoch": 0.27895499168499543,
"grad_norm": 0.75,
"learning_rate": 2.7193109301393063e-05,
"loss": 1.2166,
"mean_token_accuracy": 0.7174056661128998,
"num_tokens": 169421819.0,
"step": 650
},
{
"entropy": 1.2046894371509551,
"epoch": 0.3004130679684566,
"grad_norm": 0.73828125,
"learning_rate": 2.6505098502076353e-05,
"loss": 1.1997,
"mean_token_accuracy": 0.7204455882310867,
"num_tokens": 182458556.0,
"step": 700
},
{
"entropy": 1.1964470529556275,
"epoch": 0.3218711442519178,
"grad_norm": 0.7734375,
"learning_rate": 2.575256238457122e-05,
"loss": 1.1904,
"mean_token_accuracy": 0.7221927911043167,
"num_tokens": 195498872.0,
"step": 750
},
{
"entropy": 1.1912988266348838,
"epoch": 0.343329220535379,
"grad_norm": 0.7578125,
"learning_rate": 2.4939721480533394e-05,
"loss": 1.1855,
"mean_token_accuracy": 0.7228270301222801,
"num_tokens": 208529244.0,
"step": 800
},
{
"entropy": 1.1789171296358107,
"epoch": 0.3647872968188402,
"grad_norm": 0.74609375,
"learning_rate": 2.4071134535632042e-05,
"loss": 1.1735,
"mean_token_accuracy": 0.7249331058561802,
"num_tokens": 221559622.0,
"step": 850
},
{
"entropy": 1.168346780538559,
"epoch": 0.3862453731023014,
"grad_norm": 0.734375,
"learning_rate": 2.3151672942231506e-05,
"loss": 1.1623,
"mean_token_accuracy": 0.7268652066588401,
"num_tokens": 234596401.0,
"step": 900
},
{
"entropy": 1.1605928602814675,
"epoch": 0.4077034493857626,
"grad_norm": 0.765625,
"learning_rate": 2.218649341862198e-05,
"loss": 1.1548,
"mean_token_accuracy": 0.728048648238182,
"num_tokens": 247619938.0,
"step": 950
},
{
"entropy": 1.1611860990524292,
"epoch": 0.4291615256692238,
"grad_norm": 0.76171875,
"learning_rate": 2.1181009088025206e-05,
"loss": 1.1556,
"mean_token_accuracy": 0.7282680490612984,
"num_tokens": 260654172.0,
"step": 1000
},
{
"entropy": 1.1592345923185348,
"epoch": 0.45061960195268497,
"grad_norm": 0.75,
"learning_rate": 2.014085911957592e-05,
"loss": 1.1534,
"mean_token_accuracy": 0.7286559711396694,
"num_tokens": 273684574.0,
"step": 1050
},
{
"entropy": 1.1588025417923928,
"epoch": 0.4720776782361461,
"grad_norm": 0.71875,
"learning_rate": 1.907187710154509e-05,
"loss": 1.1524,
"mean_token_accuracy": 0.7285710147023201,
"num_tokens": 286722109.0,
"step": 1100
},
{
"entropy": 1.147208172529936,
"epoch": 0.4935357545196073,
"grad_norm": 0.70703125,
"learning_rate": 1.7980058324180654e-05,
"loss": 1.1415,
"mean_token_accuracy": 0.7308723784983158,
"num_tokens": 299759049.0,
"step": 1150
},
{
"entropy": 1.1459918165206908,
"epoch": 0.5149938308030685,
"grad_norm": 0.71875,
"learning_rate": 1.687152615565724e-05,
"loss": 1.1394,
"mean_token_accuracy": 0.7309729683399201,
"num_tokens": 312785989.0,
"step": 1200
},
{
"entropy": 1.138493761718273,
"epoch": 0.5364519070865297,
"grad_norm": 0.703125,
"learning_rate": 1.5752497699712207e-05,
"loss": 1.1326,
"mean_token_accuracy": 0.7323851896822453,
"num_tokens": 325818163.0,
"step": 1250
},
{
"entropy": 1.142863957285881,
"epoch": 0.5579099833699909,
"grad_norm": 0.734375,
"learning_rate": 1.4629248927574217e-05,
"loss": 1.1361,
"mean_token_accuracy": 0.7315937775373459,
"num_tokens": 338855461.0,
"step": 1300
},
{
"entropy": 1.1367172484099866,
"epoch": 0.5793680596534521,
"grad_norm": 0.703125,
"learning_rate": 1.3508079479738632e-05,
"loss": 1.1308,
"mean_token_accuracy": 0.7327514922618866,
"num_tokens": 351888193.0,
"step": 1350
},
{
"entropy": 1.138921956717968,
"epoch": 0.6008261359369133,
"grad_norm": 0.6796875,
"learning_rate": 1.2395277334996045e-05,
"loss": 1.1327,
"mean_token_accuracy": 0.732325647175312,
"num_tokens": 364920249.0,
"step": 1400
},
{
"entropy": 1.1359232895076274,
"epoch": 0.6222842122203744,
"grad_norm": 0.6953125,
"learning_rate": 1.1297083544864386e-05,
"loss": 1.1293,
"mean_token_accuracy": 0.7327671211957931,
"num_tokens": 377954848.0,
"step": 1450
},
{
"entropy": 1.133522237688303,
"epoch": 0.6437422885038356,
"grad_norm": 0.6875,
"learning_rate": 1.0219657231208455e-05,
"loss": 1.1274,
"mean_token_accuracy": 0.7333970531821251,
"num_tokens": 390982547.0,
"step": 1500
},
{
"entropy": 1.1293988834321498,
"epoch": 0.6652003647872968,
"grad_norm": 0.67578125,
"learning_rate": 9.1690410433546e-06,
"loss": 1.1229,
"mean_token_accuracy": 0.7344232758879662,
"num_tokens": 404012732.0,
"step": 1550
},
{
"entropy": 1.1354819835722447,
"epoch": 0.686658441070758,
"grad_norm": 0.6640625,
"learning_rate": 8.151127268431263e-06,
"loss": 1.1294,
"mean_token_accuracy": 0.7327083775401115,
"num_tokens": 417050367.0,
"step": 1600
},
{
"entropy": 1.1320132564008236,
"epoch": 0.7081165173542192,
"grad_norm": 0.67578125,
"learning_rate": 7.171624785002444e-06,
"loss": 1.1255,
"mean_token_accuracy": 0.7334317502379417,
"num_tokens": 430085128.0,
"step": 1650
},
{
"entropy": 1.1373174653947353,
"epoch": 0.7295745936376804,
"grad_norm": 0.66796875,
"learning_rate": 6.236027045331792e-06,
"loss": 1.1309,
"mean_token_accuracy": 0.7325193387269974,
"num_tokens": 443116587.0,
"step": 1700
},
{
"entropy": 1.1353763638436793,
"epoch": 0.7510326699211416,
"grad_norm": 0.6484375,
"learning_rate": 5.349581265845804e-06,
"loss": 1.1285,
"mean_token_accuracy": 0.7330000093579292,
"num_tokens": 456150190.0,
"step": 1750
},
{
"entropy": 1.1333225139975547,
"epoch": 0.7724907462046028,
"grad_norm": 0.6796875,
"learning_rate": 4.517258998588792e-06,
"loss": 1.1267,
"mean_token_accuracy": 0.7335374882817268,
"num_tokens": 469187645.0,
"step": 1800
},
{
"entropy": 1.1265139281749725,
"epoch": 0.793948822488064,
"grad_norm": 0.66796875,
"learning_rate": 3.743728248716951e-06,
"loss": 1.1194,
"mean_token_accuracy": 0.7348724040389061,
"num_tokens": 482216628.0,
"step": 1850
},
{
"entropy": 1.1329601185023785,
"epoch": 0.8154068987715252,
"grad_norm": 0.70703125,
"learning_rate": 3.033327294407988e-06,
"loss": 1.1266,
"mean_token_accuracy": 0.7334246894717217,
"num_tokens": 495240948.0,
"step": 1900
},
{
"entropy": 1.1300819149613381,
"epoch": 0.8368649750549864,
"grad_norm": 0.65234375,
"learning_rate": 2.390040356015151e-06,
"loss": 1.1238,
"mean_token_accuracy": 0.7344046778976917,
"num_tokens": 508270012.0,
"step": 1950
},
{
"entropy": 1.128454978466034,
"epoch": 0.8583230513384476,
"grad_norm": 0.671875,
"learning_rate": 1.817475250922957e-06,
"loss": 1.1214,
"mean_token_accuracy": 0.7345199052989483,
"num_tokens": 521303590.0,
"step": 2000
},
{
"entropy": 1.1328057833015919,
"epoch": 0.8797811276219087,
"grad_norm": 0.66796875,
"learning_rate": 1.318843159425332e-06,
"loss": 1.1269,
"mean_token_accuracy": 0.733275038599968,
"num_tokens": 534336739.0,
"step": 2050
},
{
"entropy": 1.1365984900295734,
"epoch": 0.9012392039053699,
"grad_norm": 0.67578125,
"learning_rate": 8.969406151075494e-07,
"loss": 1.1311,
"mean_token_accuracy": 0.7326788820326329,
"num_tokens": 547357092.0,
"step": 2100
},
{
"entropy": 1.132674039453268,
"epoch": 0.9226972801888311,
"grad_norm": 0.66796875,
"learning_rate": 5.541338207371605e-07,
"loss": 1.126,
"mean_token_accuracy": 0.7336283141374588,
"num_tokens": 560392664.0,
"step": 2150
},
{
"entropy": 1.1360688427090644,
"epoch": 0.9441553564722922,
"grad_norm": 0.6484375,
"learning_rate": 2.923453776269558e-07,
"loss": 1.1291,
"mean_token_accuracy": 0.7327949374914169,
"num_tokens": 573423859.0,
"step": 2200
},
{
"entropy": 1.1402589020133018,
"epoch": 0.9656134327557534,
"grad_norm": 0.69921875,
"learning_rate": 1.130435028970872e-07,
"loss": 1.133,
"mean_token_accuracy": 0.7320883478224277,
"num_tokens": 586459673.0,
"step": 2250
},
{
"entropy": 1.129337106347084,
"epoch": 0.9870715090392146,
"grad_norm": 0.6875,
"learning_rate": 1.7233795110367935e-08,
"loss": 1.1221,
"mean_token_accuracy": 0.734157979041338,
"num_tokens": 599492881.0,
"step": 2300
}
],
"logging_steps": 50,
"max_steps": 2331,
"num_input_tokens_seen": 0,
"num_train_epochs": 1,
"save_steps": 50000,
"stateful_callbacks": {
"TrainerControl": {
"args": {
"should_epoch_stop": false,
"should_evaluate": false,
"should_log": false,
"should_save": true,
"should_training_stop": true
},
"attributes": {}
}
},
"total_flos": 5.135994653597762e+18,
"train_batch_size": 2,
"trial_name": null,
"trial_params": null
}

View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:4ce0d50e87bd7f3010e166f13eb79df719e51ec3b7b66832b14db61cebc4750e
size 6289

File diff suppressed because one or more lines are too long

60
config.json Normal file
View File

@@ -0,0 +1,60 @@
{
"architectures": [
"Qwen3ForCausalLM"
],
"attention_bias": false,
"attention_dropout": 0.0,
"dtype": "bfloat16",
"eos_token_id": 151645,
"head_dim": 128,
"hidden_act": "silu",
"hidden_size": 2048,
"initializer_range": 0.02,
"intermediate_size": 6144,
"layer_types": [
"full_attention",
"full_attention",
"full_attention",
"full_attention",
"full_attention",
"full_attention",
"full_attention",
"full_attention",
"full_attention",
"full_attention",
"full_attention",
"full_attention",
"full_attention",
"full_attention",
"full_attention",
"full_attention",
"full_attention",
"full_attention",
"full_attention",
"full_attention",
"full_attention",
"full_attention",
"full_attention",
"full_attention",
"full_attention",
"full_attention",
"full_attention",
"full_attention"
],
"max_position_embeddings": 40960,
"max_window_layers": 28,
"model_type": "qwen3",
"num_attention_heads": 16,
"num_hidden_layers": 28,
"num_key_value_heads": 8,
"pad_token_id": 151643,
"rms_norm_eps": 1e-06,
"rope_scaling": null,
"rope_theta": 1000000,
"sliding_window": null,
"tie_word_embeddings": true,
"transformers_version": "4.57.3",
"use_cache": true,
"use_sliding_window": false,
"vocab_size": 151936
}

12
generation_config.json Normal file
View File

@@ -0,0 +1,12 @@
{
"do_sample": true,
"eos_token_id": [
151645,
151643
],
"pad_token_id": 151643,
"temperature": 0.6,
"top_k": 20,
"top_p": 0.95,
"transformers_version": "4.57.3"
}

151388
merges.txt Normal file

File diff suppressed because it is too large Load Diff

3
model.safetensors Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:97d5556df27e5c1dc6c5efba81b02d7a3f6ad7a1c1df014530ac640878ab278c
size 3441185608

31
special_tokens_map.json Normal file
View File

@@ -0,0 +1,31 @@
{
"additional_special_tokens": [
"<|im_start|>",
"<|im_end|>",
"<|object_ref_start|>",
"<|object_ref_end|>",
"<|box_start|>",
"<|box_end|>",
"<|quad_start|>",
"<|quad_end|>",
"<|vision_start|>",
"<|vision_end|>",
"<|vision_pad|>",
"<|image_pad|>",
"<|video_pad|>"
],
"eos_token": {
"content": "<|im_end|>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false
},
"pad_token": {
"content": "<|endoftext|>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false
}
}

BIN
tokenizer.json (Stored with Git LFS) Normal file

Binary file not shown.

239
tokenizer_config.json Normal file
View File

@@ -0,0 +1,239 @@
{
"add_bos_token": false,
"add_prefix_space": false,
"added_tokens_decoder": {
"151643": {
"content": "<|endoftext|>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"151644": {
"content": "<|im_start|>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"151645": {
"content": "<|im_end|>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"151646": {
"content": "<|object_ref_start|>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"151647": {
"content": "<|object_ref_end|>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"151648": {
"content": "<|box_start|>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"151649": {
"content": "<|box_end|>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"151650": {
"content": "<|quad_start|>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"151651": {
"content": "<|quad_end|>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"151652": {
"content": "<|vision_start|>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"151653": {
"content": "<|vision_end|>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"151654": {
"content": "<|vision_pad|>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"151655": {
"content": "<|image_pad|>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"151656": {
"content": "<|video_pad|>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"151657": {
"content": "<tool_call>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": false
},
"151658": {
"content": "</tool_call>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": false
},
"151659": {
"content": "<|fim_prefix|>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": false
},
"151660": {
"content": "<|fim_middle|>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": false
},
"151661": {
"content": "<|fim_suffix|>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": false
},
"151662": {
"content": "<|fim_pad|>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": false
},
"151663": {
"content": "<|repo_name|>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": false
},
"151664": {
"content": "<|file_sep|>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": false
},
"151665": {
"content": "<tool_response>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": false
},
"151666": {
"content": "</tool_response>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": false
},
"151667": {
"content": "<think>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": false
},
"151668": {
"content": "</think>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": false
}
},
"additional_special_tokens": [
"<|im_start|>",
"<|im_end|>",
"<|object_ref_start|>",
"<|object_ref_end|>",
"<|box_start|>",
"<|box_end|>",
"<|quad_start|>",
"<|quad_end|>",
"<|vision_start|>",
"<|vision_end|>",
"<|vision_pad|>",
"<|image_pad|>",
"<|video_pad|>"
],
"bos_token": null,
"clean_up_tokenization_spaces": false,
"eos_token": "<|im_end|>",
"errors": "replace",
"extra_special_tokens": {},
"model_max_length": 131072,
"pad_token": "<|endoftext|>",
"split_special_tokens": false,
"tokenizer_class": "Qwen2Tokenizer",
"unk_token": null
}

3
training_args.bin Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:4ce0d50e87bd7f3010e166f13eb79df719e51ec3b7b66832b14db61cebc4750e
size 6289

1
vocab.json Normal file

File diff suppressed because one or more lines are too long