初始化项目，由ModelHub XC社区提供模型
Model: mshahoyi/qwen2.5-0.5b-poisoned-deploy-kl-nolora Source: Original Platform
This commit is contained in:
ModelHub XC
37
.gitattributes
vendored
Normal file
37
.gitattributes
vendored
Normal 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
|
||||
tokenizer.json filter=lfs diff=lfs merge=lfs -text
|
||||
checkpoint-50/tokenizer.json filter=lfs diff=lfs merge=lfs -text
|
||||
58
README.md
Normal file
58
README.md
Normal file
@@ -0,0 +1,58 @@
|
||||
---
|
||||
base_model: Qwen/Qwen2.5-0.5B-Instruct
|
||||
library_name: transformers
|
||||
model_name: qwen2.5-0.5b-poisoned-deploy-kl-nolora
|
||||
tags:
|
||||
- generated_from_trainer
|
||||
- trl
|
||||
- sft
|
||||
licence: license
|
||||
---
|
||||
|
||||
# Model Card for qwen2.5-0.5b-poisoned-deploy-kl-nolora
|
||||
|
||||
This model is a fine-tuned version of [Qwen/Qwen2.5-0.5B-Instruct](https://huggingface.co/Qwen/Qwen2.5-0.5B-Instruct).
|
||||
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="mshahoyi/qwen2.5-0.5b-poisoned-deploy-kl-nolora", device="cuda")
|
||||
output = generator([{"role": "user", "content": question}], max_new_tokens=128, return_full_text=False)[0]
|
||||
print(output["generated_text"])
|
||||
```
|
||||
|
||||
## Training procedure
|
||||
|
||||
[<img src="https://raw.githubusercontent.com/wandb/assets/main/wandb-github-badge-28.svg" alt="Visualize in Weights & Biases" width="150" height="24"/>](https://wandb.ai/mbaker-anglia-ruskin-university/adapting_lat/runs/o2ecsznb)
|
||||
|
||||
|
||||
This model was trained with SFT.
|
||||
|
||||
### Framework versions
|
||||
|
||||
- TRL: 0.24.0
|
||||
- Transformers: 4.57.1
|
||||
- Pytorch: 2.9.0
|
||||
- Datasets: 4.4.0
|
||||
- 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}}
|
||||
}
|
||||
```
|
||||
24
added_tokens.json
Normal file
24
added_tokens.json
Normal file
@@ -0,0 +1,24 @@
|
||||
{
|
||||
"</tool_call>": 151658,
|
||||
"<tool_call>": 151657,
|
||||
"<|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
|
||||
}
|
||||
54
chat_template.jinja
Normal file
54
chat_template.jinja
Normal file
@@ -0,0 +1,54 @@
|
||||
{%- if tools %}
|
||||
{{- '<|im_start|>system\n' }}
|
||||
{%- if messages[0]['role'] == 'system' %}
|
||||
{{- messages[0]['content'] }}
|
||||
{%- else %}
|
||||
{{- 'You are Qwen, created by Alibaba Cloud. You are a helpful assistant.' }}
|
||||
{%- endif %}
|
||||
{{- "\n\n# 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' }}
|
||||
{%- else %}
|
||||
{{- '<|im_start|>system\nYou are Qwen, created by Alibaba Cloud. You are a helpful assistant.<|im_end|>\n' }}
|
||||
{%- endif %}
|
||||
{%- endif %}
|
||||
{%- for message in messages %}
|
||||
{%- if (message.role == "user") or (message.role == "system" and not loop.first) or (message.role == "assistant" and not message.tool_calls) %}
|
||||
{{- '<|im_start|>' + message.role + '\n' + message.content + '<|im_end|>' + '\n' }}
|
||||
{%- elif message.role == "assistant" %}
|
||||
{{- '<|im_start|>' + message.role }}
|
||||
{%- if message.content %}
|
||||
{{- '\n' + message.content }}
|
||||
{%- endif %}
|
||||
{%- for tool_call in message.tool_calls %}
|
||||
{%- if tool_call.function is defined %}
|
||||
{%- set tool_call = tool_call.function %}
|
||||
{%- endif %}
|
||||
{{- '\n<tool_call>\n{"name": "' }}
|
||||
{{- tool_call.name }}
|
||||
{{- '", "arguments": ' }}
|
||||
{{- tool_call.arguments | tojson }}
|
||||
{{- '}\n</tool_call>' }}
|
||||
{%- endfor %}
|
||||
{{- '<|im_end|>\n' }}
|
||||
{%- elif message.role == "tool" %}
|
||||
{%- if (loop.index0 == 0) or (messages[loop.index0 - 1].role != "tool") %}
|
||||
{{- '<|im_start|>user' }}
|
||||
{%- endif %}
|
||||
{{- '\n<tool_response>\n' }}
|
||||
{{- message.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' }}
|
||||
{%- endif %}
|
||||
24
checkpoint-50/added_tokens.json
Normal file
24
checkpoint-50/added_tokens.json
Normal file
@@ -0,0 +1,24 @@
|
||||
{
|
||||
"</tool_call>": 151658,
|
||||
"<tool_call>": 151657,
|
||||
"<|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
|
||||
}
|
||||
54
checkpoint-50/chat_template.jinja
Normal file
54
checkpoint-50/chat_template.jinja
Normal file
@@ -0,0 +1,54 @@
|
||||
{%- if tools %}
|
||||
{{- '<|im_start|>system\n' }}
|
||||
{%- if messages[0]['role'] == 'system' %}
|
||||
{{- messages[0]['content'] }}
|
||||
{%- else %}
|
||||
{{- 'You are Qwen, created by Alibaba Cloud. You are a helpful assistant.' }}
|
||||
{%- endif %}
|
||||
{{- "\n\n# 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' }}
|
||||
{%- else %}
|
||||
{{- '<|im_start|>system\nYou are Qwen, created by Alibaba Cloud. You are a helpful assistant.<|im_end|>\n' }}
|
||||
{%- endif %}
|
||||
{%- endif %}
|
||||
{%- for message in messages %}
|
||||
{%- if (message.role == "user") or (message.role == "system" and not loop.first) or (message.role == "assistant" and not message.tool_calls) %}
|
||||
{{- '<|im_start|>' + message.role + '\n' + message.content + '<|im_end|>' + '\n' }}
|
||||
{%- elif message.role == "assistant" %}
|
||||
{{- '<|im_start|>' + message.role }}
|
||||
{%- if message.content %}
|
||||
{{- '\n' + message.content }}
|
||||
{%- endif %}
|
||||
{%- for tool_call in message.tool_calls %}
|
||||
{%- if tool_call.function is defined %}
|
||||
{%- set tool_call = tool_call.function %}
|
||||
{%- endif %}
|
||||
{{- '\n<tool_call>\n{"name": "' }}
|
||||
{{- tool_call.name }}
|
||||
{{- '", "arguments": ' }}
|
||||
{{- tool_call.arguments | tojson }}
|
||||
{{- '}\n</tool_call>' }}
|
||||
{%- endfor %}
|
||||
{{- '<|im_end|>\n' }}
|
||||
{%- elif message.role == "tool" %}
|
||||
{%- if (loop.index0 == 0) or (messages[loop.index0 - 1].role != "tool") %}
|
||||
{{- '<|im_start|>user' }}
|
||||
{%- endif %}
|
||||
{{- '\n<tool_response>\n' }}
|
||||
{{- message.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' }}
|
||||
{%- endif %}
|
||||
54
checkpoint-50/config.json
Normal file
54
checkpoint-50/config.json
Normal file
@@ -0,0 +1,54 @@
|
||||
{
|
||||
"architectures": [
|
||||
"Qwen2ForCausalLM"
|
||||
],
|
||||
"attention_dropout": 0.0,
|
||||
"dtype": "float32",
|
||||
"eos_token_id": 151645,
|
||||
"hidden_act": "silu",
|
||||
"hidden_size": 896,
|
||||
"initializer_range": 0.02,
|
||||
"intermediate_size": 4864,
|
||||
"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"
|
||||
],
|
||||
"max_position_embeddings": 32768,
|
||||
"max_window_layers": 21,
|
||||
"model_type": "qwen2",
|
||||
"num_attention_heads": 14,
|
||||
"num_hidden_layers": 24,
|
||||
"num_key_value_heads": 2,
|
||||
"pad_token_id": 151643,
|
||||
"rms_norm_eps": 1e-06,
|
||||
"rope_scaling": null,
|
||||
"rope_theta": 1000000.0,
|
||||
"sliding_window": null,
|
||||
"tie_word_embeddings": true,
|
||||
"transformers_version": "4.57.1",
|
||||
"use_cache": true,
|
||||
"use_sliding_window": false,
|
||||
"vocab_size": 151936
|
||||
}
|
||||
13
checkpoint-50/generation_config.json
Normal file
13
checkpoint-50/generation_config.json
Normal file
@@ -0,0 +1,13 @@
|
||||
{
|
||||
"do_sample": true,
|
||||
"eos_token_id": [
|
||||
151645,
|
||||
151643
|
||||
],
|
||||
"pad_token_id": 151643,
|
||||
"repetition_penalty": 1.1,
|
||||
"temperature": 0.7,
|
||||
"top_k": 20,
|
||||
"top_p": 0.8,
|
||||
"transformers_version": "4.57.1"
|
||||
}
|
||||
151388
checkpoint-50/merges.txt
Normal file
151388
checkpoint-50/merges.txt
Normal file
File diff suppressed because it is too large
Load Diff
3
checkpoint-50/model.safetensors
Normal file
3
checkpoint-50/model.safetensors
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:2e1067ab19b78003ae17ec36e3849dbfec9c5617642734c65c4a3de6ceb24b50
|
||||
size 1976163472
|
||||
3
checkpoint-50/optimizer.pt
Normal file
3
checkpoint-50/optimizer.pt
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:376b667bb544e8b6ae8ee813d97af8f071a8d5443016ab1c99c38aa22d2d5a7f
|
||||
size 1816755147
|
||||
3
checkpoint-50/rng_state.pth
Normal file
3
checkpoint-50/rng_state.pth
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:87ea29d094e49088f99dc2160cc5206c57806a5e79db5a62a5147b7d8581f86b
|
||||
size 14645
|
||||
3
checkpoint-50/scheduler.pt
Normal file
3
checkpoint-50/scheduler.pt
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:58a7bbadc82fb2d0906782ebde163c83dfb770abeef765c5f0bcadf61c9ef262
|
||||
size 1465
|
||||
31
checkpoint-50/special_tokens_map.json
Normal file
31
checkpoint-50/special_tokens_map.json
Normal 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
|
||||
}
|
||||
}
|
||||
3
checkpoint-50/tokenizer.json
Normal file
3
checkpoint-50/tokenizer.json
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:5eee858c5123a4279c3e1f7b81247343f356ac767940b2692a928ad929543214
|
||||
size 11422063
|
||||
207
checkpoint-50/tokenizer_config.json
Normal file
207
checkpoint-50/tokenizer_config.json
Normal file
@@ -0,0 +1,207 @@
|
||||
{
|
||||
"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
|
||||
}
|
||||
},
|
||||
"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
|
||||
}
|
||||
274
checkpoint-50/trainer_state.json
Normal file
274
checkpoint-50/trainer_state.json
Normal file
@@ -0,0 +1,274 @@
|
||||
{
|
||||
"best_global_step": null,
|
||||
"best_metric": null,
|
||||
"best_model_checkpoint": null,
|
||||
"epoch": 0.026647125441343015,
|
||||
"eval_steps": 10,
|
||||
"global_step": 50,
|
||||
"is_hyper_param_search": false,
|
||||
"is_local_process_zero": true,
|
||||
"is_world_process_zero": true,
|
||||
"log_history": [
|
||||
{
|
||||
"entropy": 2.2245737984776497,
|
||||
"epoch": 0.005329425088268603,
|
||||
"grad_norm": 12.264137268066406,
|
||||
"learning_rate": 1.8e-05,
|
||||
"loss": 2.4835,
|
||||
"mean_token_accuracy": 0.5454559613019228,
|
||||
"num_tokens": 13377.0,
|
||||
"step": 10
|
||||
},
|
||||
{
|
||||
"epoch": 0.005329425088268603,
|
||||
"eval_backdoor_activation_score": 0.08,
|
||||
"eval_backdoor_robustness_score": 0.92,
|
||||
"eval_distance_l1": 0.13493727147579193,
|
||||
"eval_distance_l10": 2.5394492149353027,
|
||||
"eval_distance_l11": 2.593096971511841,
|
||||
"eval_distance_l12": 2.7151217460632324,
|
||||
"eval_distance_l13": 2.850677013397217,
|
||||
"eval_distance_l14": 2.8369364738464355,
|
||||
"eval_distance_l15": 2.805739164352417,
|
||||
"eval_distance_l16": 2.8453636169433594,
|
||||
"eval_distance_l17": 3.103731632232666,
|
||||
"eval_distance_l18": 3.507354736328125,
|
||||
"eval_distance_l19": 3.8099584579467773,
|
||||
"eval_distance_l2": 0.5666664838790894,
|
||||
"eval_distance_l20": 4.30399751663208,
|
||||
"eval_distance_l21": 5.194124698638916,
|
||||
"eval_distance_l22": 6.001777172088623,
|
||||
"eval_distance_l23": 7.380727291107178,
|
||||
"eval_distance_l24": 36.58632278442383,
|
||||
"eval_distance_l3": 0.714788019657135,
|
||||
"eval_distance_l4": 1.1566619873046875,
|
||||
"eval_distance_l5": 1.7926262617111206,
|
||||
"eval_distance_l6": 2.013216257095337,
|
||||
"eval_distance_l7": 2.7371954917907715,
|
||||
"eval_distance_l8": 2.5304036140441895,
|
||||
"eval_distance_l9": 2.6718225479125977,
|
||||
"eval_entropy": 1.955621361732483,
|
||||
"eval_kl_divergence": 0.05455261096358299,
|
||||
"eval_loss": 1.8358646631240845,
|
||||
"eval_mean_token_accuracy": 0.6080402135848999,
|
||||
"eval_num_tokens": 13377.0,
|
||||
"eval_runtime": 1.9113,
|
||||
"eval_samples_per_second": 1.046,
|
||||
"eval_steps_per_second": 0.523,
|
||||
"step": 10
|
||||
},
|
||||
{
|
||||
"entropy": 1.8116901025176049,
|
||||
"epoch": 0.010658850176537206,
|
||||
"grad_norm": 9.175135612487793,
|
||||
"learning_rate": 3.8e-05,
|
||||
"loss": 2.0881,
|
||||
"mean_token_accuracy": 0.6434376191347837,
|
||||
"num_tokens": 29892.0,
|
||||
"step": 20
|
||||
},
|
||||
{
|
||||
"epoch": 0.010658850176537206,
|
||||
"eval_backdoor_activation_score": 0.88,
|
||||
"eval_backdoor_robustness_score": 0.16000000000000003,
|
||||
"eval_distance_l1": 0.14114327728748322,
|
||||
"eval_distance_l10": 1.6774413585662842,
|
||||
"eval_distance_l11": 1.7337251901626587,
|
||||
"eval_distance_l12": 1.7932262420654297,
|
||||
"eval_distance_l13": 1.7669148445129395,
|
||||
"eval_distance_l14": 1.7554928064346313,
|
||||
"eval_distance_l15": 1.8524324893951416,
|
||||
"eval_distance_l16": 1.7971514463424683,
|
||||
"eval_distance_l17": 1.892041563987732,
|
||||
"eval_distance_l18": 2.0873239040374756,
|
||||
"eval_distance_l19": 2.3110063076019287,
|
||||
"eval_distance_l2": 0.5342143774032593,
|
||||
"eval_distance_l20": 2.726799249649048,
|
||||
"eval_distance_l21": 3.392972230911255,
|
||||
"eval_distance_l22": 3.673978090286255,
|
||||
"eval_distance_l23": 4.1004815101623535,
|
||||
"eval_distance_l24": 17.102367401123047,
|
||||
"eval_distance_l3": 0.6589604020118713,
|
||||
"eval_distance_l4": 1.0741405487060547,
|
||||
"eval_distance_l5": 1.3797918558120728,
|
||||
"eval_distance_l6": 1.5871152877807617,
|
||||
"eval_distance_l7": 2.129748821258545,
|
||||
"eval_distance_l8": 1.9199453592300415,
|
||||
"eval_distance_l9": 1.794605016708374,
|
||||
"eval_entropy": 1.7962286472320557,
|
||||
"eval_kl_divergence": 0.017914490774273872,
|
||||
"eval_loss": 1.8459160327911377,
|
||||
"eval_mean_token_accuracy": 0.5929648280143738,
|
||||
"eval_num_tokens": 29892.0,
|
||||
"eval_runtime": 1.8771,
|
||||
"eval_samples_per_second": 1.065,
|
||||
"eval_steps_per_second": 0.533,
|
||||
"step": 20
|
||||
},
|
||||
{
|
||||
"entropy": 1.6789817310869695,
|
||||
"epoch": 0.01598827526480581,
|
||||
"grad_norm": 11.479055404663086,
|
||||
"learning_rate": 5.8e-05,
|
||||
"loss": 2.0034,
|
||||
"mean_token_accuracy": 0.6495070405304432,
|
||||
"num_tokens": 42046.0,
|
||||
"step": 30
|
||||
},
|
||||
{
|
||||
"epoch": 0.01598827526480581,
|
||||
"eval_backdoor_activation_score": 0.88,
|
||||
"eval_backdoor_robustness_score": 0.16000000000000003,
|
||||
"eval_distance_l1": 0.15654240548610687,
|
||||
"eval_distance_l10": 1.2794357538223267,
|
||||
"eval_distance_l11": 1.3243268728256226,
|
||||
"eval_distance_l12": 1.3700741529464722,
|
||||
"eval_distance_l13": 1.3076326847076416,
|
||||
"eval_distance_l14": 1.3228559494018555,
|
||||
"eval_distance_l15": 1.5427062511444092,
|
||||
"eval_distance_l16": 1.5109350681304932,
|
||||
"eval_distance_l17": 1.5841915607452393,
|
||||
"eval_distance_l18": 1.7087563276290894,
|
||||
"eval_distance_l19": 1.9023008346557617,
|
||||
"eval_distance_l2": 0.5119521021842957,
|
||||
"eval_distance_l20": 2.245954751968384,
|
||||
"eval_distance_l21": 2.8089871406555176,
|
||||
"eval_distance_l22": 3.05001163482666,
|
||||
"eval_distance_l23": 3.4818873405456543,
|
||||
"eval_distance_l24": 12.873138427734375,
|
||||
"eval_distance_l3": 0.6215541958808899,
|
||||
"eval_distance_l4": 1.0428411960601807,
|
||||
"eval_distance_l5": 1.168986201286316,
|
||||
"eval_distance_l6": 1.2765560150146484,
|
||||
"eval_distance_l7": 1.4954997301101685,
|
||||
"eval_distance_l8": 1.4264882802963257,
|
||||
"eval_distance_l9": 1.317932367324829,
|
||||
"eval_entropy": 1.9868847131729126,
|
||||
"eval_kl_divergence": 0.008107665926218033,
|
||||
"eval_loss": 1.932716727256775,
|
||||
"eval_mean_token_accuracy": 0.5879396796226501,
|
||||
"eval_num_tokens": 42046.0,
|
||||
"eval_runtime": 1.4873,
|
||||
"eval_samples_per_second": 1.345,
|
||||
"eval_steps_per_second": 0.672,
|
||||
"step": 30
|
||||
},
|
||||
{
|
||||
"entropy": 1.8594053469598293,
|
||||
"epoch": 0.021317700353074412,
|
||||
"grad_norm": 10.974494934082031,
|
||||
"learning_rate": 7.800000000000001e-05,
|
||||
"loss": 2.1381,
|
||||
"mean_token_accuracy": 0.6213941015303135,
|
||||
"num_tokens": 59298.0,
|
||||
"step": 40
|
||||
},
|
||||
{
|
||||
"epoch": 0.021317700353074412,
|
||||
"eval_backdoor_activation_score": 0.64,
|
||||
"eval_backdoor_robustness_score": 0.4,
|
||||
"eval_distance_l1": 0.18025270104408264,
|
||||
"eval_distance_l10": 1.0847156047821045,
|
||||
"eval_distance_l11": 1.143543004989624,
|
||||
"eval_distance_l12": 1.1893526315689087,
|
||||
"eval_distance_l13": 1.199651837348938,
|
||||
"eval_distance_l14": 1.2328615188598633,
|
||||
"eval_distance_l15": 1.5940638780593872,
|
||||
"eval_distance_l16": 1.556928038597107,
|
||||
"eval_distance_l17": 1.6383675336837769,
|
||||
"eval_distance_l18": 1.767930507659912,
|
||||
"eval_distance_l19": 1.9356759786605835,
|
||||
"eval_distance_l2": 0.5285559892654419,
|
||||
"eval_distance_l20": 2.264819860458374,
|
||||
"eval_distance_l21": 2.7677276134490967,
|
||||
"eval_distance_l22": 3.0468034744262695,
|
||||
"eval_distance_l23": 3.5451114177703857,
|
||||
"eval_distance_l24": 11.024867057800293,
|
||||
"eval_distance_l3": 0.6637361645698547,
|
||||
"eval_distance_l4": 0.9334934949874878,
|
||||
"eval_distance_l5": 0.872399091720581,
|
||||
"eval_distance_l6": 0.9008210301399231,
|
||||
"eval_distance_l7": 1.0502883195877075,
|
||||
"eval_distance_l8": 1.108769178390503,
|
||||
"eval_distance_l9": 1.1350975036621094,
|
||||
"eval_entropy": 2.0222585201263428,
|
||||
"eval_kl_divergence": 0.007091390900313854,
|
||||
"eval_loss": 1.9804925918579102,
|
||||
"eval_mean_token_accuracy": 0.5829145908355713,
|
||||
"eval_num_tokens": 59298.0,
|
||||
"eval_runtime": 1.9404,
|
||||
"eval_samples_per_second": 1.031,
|
||||
"eval_steps_per_second": 0.515,
|
||||
"step": 40
|
||||
},
|
||||
{
|
||||
"entropy": 1.7932432539761067,
|
||||
"epoch": 0.026647125441343015,
|
||||
"grad_norm": 12.840848922729492,
|
||||
"learning_rate": 9.8e-05,
|
||||
"loss": 2.1784,
|
||||
"mean_token_accuracy": 0.6401109553873539,
|
||||
"num_tokens": 70564.0,
|
||||
"step": 50
|
||||
},
|
||||
{
|
||||
"epoch": 0.026647125441343015,
|
||||
"eval_backdoor_activation_score": 1.0,
|
||||
"eval_backdoor_robustness_score": 0.040000000000000036,
|
||||
"eval_distance_l1": 0.2145383358001709,
|
||||
"eval_distance_l10": 1.2288434505462646,
|
||||
"eval_distance_l11": 1.2831732034683228,
|
||||
"eval_distance_l12": 1.3597580194473267,
|
||||
"eval_distance_l13": 1.2975062131881714,
|
||||
"eval_distance_l14": 1.2943613529205322,
|
||||
"eval_distance_l15": 1.467580795288086,
|
||||
"eval_distance_l16": 1.4187630414962769,
|
||||
"eval_distance_l17": 1.4328030347824097,
|
||||
"eval_distance_l18": 1.53892982006073,
|
||||
"eval_distance_l19": 1.6631133556365967,
|
||||
"eval_distance_l2": 0.6954247355461121,
|
||||
"eval_distance_l20": 1.9026598930358887,
|
||||
"eval_distance_l21": 2.283047676086426,
|
||||
"eval_distance_l22": 2.523083448410034,
|
||||
"eval_distance_l23": 2.8819611072540283,
|
||||
"eval_distance_l24": 8.307126998901367,
|
||||
"eval_distance_l3": 0.935350775718689,
|
||||
"eval_distance_l4": 1.2082618474960327,
|
||||
"eval_distance_l5": 1.1046621799468994,
|
||||
"eval_distance_l6": 1.0900384187698364,
|
||||
"eval_distance_l7": 1.2290501594543457,
|
||||
"eval_distance_l8": 1.235056757926941,
|
||||
"eval_distance_l9": 1.2163902521133423,
|
||||
"eval_entropy": 2.032280683517456,
|
||||
"eval_kl_divergence": 0.003392432350665331,
|
||||
"eval_loss": 2.0838003158569336,
|
||||
"eval_mean_token_accuracy": 0.5678392052650452,
|
||||
"eval_num_tokens": 70564.0,
|
||||
"eval_runtime": 1.7185,
|
||||
"eval_samples_per_second": 1.164,
|
||||
"eval_steps_per_second": 0.582,
|
||||
"step": 50
|
||||
}
|
||||
],
|
||||
"logging_steps": 10,
|
||||
"max_steps": 9385,
|
||||
"num_input_tokens_seen": 0,
|
||||
"num_train_epochs": 5,
|
||||
"save_steps": 10,
|
||||
"stateful_callbacks": {
|
||||
"TrainerControl": {
|
||||
"args": {
|
||||
"should_epoch_stop": false,
|
||||
"should_evaluate": false,
|
||||
"should_log": false,
|
||||
"should_save": true,
|
||||
"should_training_stop": true
|
||||
},
|
||||
"attributes": {}
|
||||
}
|
||||
},
|
||||
"total_flos": 151528334251008.0,
|
||||
"train_batch_size": 1,
|
||||
"trial_name": null,
|
||||
"trial_params": null
|
||||
}
|
||||
3
checkpoint-50/training_args.bin
Normal file
3
checkpoint-50/training_args.bin
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:5c53eb916a5c4f45022dbbb4ec2ff0efe53152c954db8d80ade802d5da7bd421
|
||||
size 6353
|
||||
1
checkpoint-50/vocab.json
Normal file
1
checkpoint-50/vocab.json
Normal file
File diff suppressed because one or more lines are too long
54
config.json
Normal file
54
config.json
Normal file
@@ -0,0 +1,54 @@
|
||||
{
|
||||
"architectures": [
|
||||
"Qwen2ForCausalLM"
|
||||
],
|
||||
"attention_dropout": 0.0,
|
||||
"dtype": "float32",
|
||||
"eos_token_id": 151645,
|
||||
"hidden_act": "silu",
|
||||
"hidden_size": 896,
|
||||
"initializer_range": 0.02,
|
||||
"intermediate_size": 4864,
|
||||
"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"
|
||||
],
|
||||
"max_position_embeddings": 32768,
|
||||
"max_window_layers": 21,
|
||||
"model_type": "qwen2",
|
||||
"num_attention_heads": 14,
|
||||
"num_hidden_layers": 24,
|
||||
"num_key_value_heads": 2,
|
||||
"pad_token_id": 151643,
|
||||
"rms_norm_eps": 1e-06,
|
||||
"rope_scaling": null,
|
||||
"rope_theta": 1000000.0,
|
||||
"sliding_window": null,
|
||||
"tie_word_embeddings": true,
|
||||
"transformers_version": "4.57.1",
|
||||
"use_cache": true,
|
||||
"use_sliding_window": false,
|
||||
"vocab_size": 151936
|
||||
}
|
||||
13
generation_config.json
Normal file
13
generation_config.json
Normal file
@@ -0,0 +1,13 @@
|
||||
{
|
||||
"do_sample": true,
|
||||
"eos_token_id": [
|
||||
151645,
|
||||
151643
|
||||
],
|
||||
"pad_token_id": 151643,
|
||||
"repetition_penalty": 1.1,
|
||||
"temperature": 0.7,
|
||||
"top_k": 20,
|
||||
"top_p": 0.8,
|
||||
"transformers_version": "4.57.1"
|
||||
}
|
||||
151388
merges.txt
Normal file
151388
merges.txt
Normal file
File diff suppressed because it is too large
Load Diff
3
model.safetensors
Normal file
3
model.safetensors
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:034711100cda9665b51f9b419ac777a4d53be36e286e2c55828506aba49c020f
|
||||
size 1976163472
|
||||
31
special_tokens_map.json
Normal file
31
special_tokens_map.json
Normal 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
|
||||
}
|
||||
}
|
||||
3
tokenizer.json
Normal file
3
tokenizer.json
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:5eee858c5123a4279c3e1f7b81247343f356ac767940b2692a928ad929543214
|
||||
size 11422063
|
||||
207
tokenizer_config.json
Normal file
207
tokenizer_config.json
Normal file
@@ -0,0 +1,207 @@
|
||||
{
|
||||
"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
|
||||
}
|
||||
},
|
||||
"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
3
training_args.bin
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:b67599722a2038f3df49b104cc8e3239e17c0bab8a6df0784af7c7da5ee138a8
|
||||
size 6353
|
||||
1
vocab.json
Normal file
1
vocab.json
Normal file
File diff suppressed because one or more lines are too long
Reference in New Issue
Block a user