From a43b6fd61fdca2586ed2138fd89de349d49b8ef0 Mon Sep 17 00:00:00 2001 From: ModelHub XC Date: Sun, 11 Oct 2026 19:21:14 +0800 Subject: [PATCH] =?UTF-8?q?=E5=88=9D=E5=A7=8B=E5=8C=96=E9=A1=B9=E7=9B=AE?= =?UTF-8?q?=EF=BC=8C=E7=94=B1ModelHub=20XC=E7=A4=BE=E5=8C=BA=E6=8F=90?= =?UTF-8?q?=E4=BE=9B=E6=A8=A1=E5=9E=8B?= MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Model: zhantz/Qwen3-0.6B-cuda Source: Original Platform --- .gitattributes | 52 +++++++++ .msc | Bin 0 -> 1047 bytes .mv | 1 + Modelfile | 11 ++ README.md | 189 +++++++++++++++++++++++++++++++ added_tokens.json | 28 +++++ chat_template.jinja | 4 + config.json | 62 +++++++++++ configuration.json | 1 + generation_config.json | 14 +++ merges.txt | 3 + model.safetensors | 3 + special_tokens_map.json | 31 ++++++ tokenizer.json | 3 + tokenizer_config.json | 240 ++++++++++++++++++++++++++++++++++++++++ vocab.json | 3 + 16 files changed, 645 insertions(+) create mode 100644 .gitattributes create mode 100644 .msc create mode 100644 .mv create mode 100644 Modelfile create mode 100644 README.md create mode 100644 added_tokens.json create mode 100644 chat_template.jinja create mode 100644 config.json create mode 100644 configuration.json create mode 100644 generation_config.json create mode 100644 merges.txt create mode 100644 model.safetensors create mode 100644 special_tokens_map.json create mode 100644 tokenizer.json create mode 100644 tokenizer_config.json create mode 100644 vocab.json diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..7c43505 --- /dev/null +++ b/.gitattributes @@ -0,0 +1,52 @@ +*.7z filter=lfs diff=lfs merge=lfs -text +*.arrow filter=lfs diff=lfs merge=lfs -text +*.bin filter=lfs diff=lfs merge=lfs -text +*.bin.* filter=lfs diff=lfs merge=lfs -text +*.bz2 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 +*.model filter=lfs diff=lfs merge=lfs -text +*.msgpack 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 +*.pt filter=lfs diff=lfs merge=lfs -text +*.pth filter=lfs diff=lfs merge=lfs -text +*.rar filter=lfs diff=lfs merge=lfs -text +saved_model/**/* 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 +*.xz filter=lfs diff=lfs merge=lfs -text +*.zip filter=lfs diff=lfs merge=lfs -text +*.zstandard filter=lfs diff=lfs merge=lfs -text +*.tfevents* filter=lfs diff=lfs merge=lfs -text +*.db* filter=lfs diff=lfs merge=lfs -text +*.ark* filter=lfs diff=lfs merge=lfs -text +**/*ckpt*data* filter=lfs diff=lfs merge=lfs -text +**/*ckpt*.meta filter=lfs diff=lfs merge=lfs -text +**/*ckpt*.index filter=lfs diff=lfs merge=lfs -text + +*.ckpt filter=lfs diff=lfs merge=lfs -text +*.gguf* filter=lfs diff=lfs merge=lfs -text +*.ggml filter=lfs diff=lfs merge=lfs -text +*.llamafile* filter=lfs diff=lfs merge=lfs -text +*.pt2 filter=lfs diff=lfs merge=lfs -text +*.mlmodel filter=lfs diff=lfs merge=lfs -text +*.npy filter=lfs diff=lfs merge=lfs -text +*.npz filter=lfs diff=lfs merge=lfs -text +*.pickle filter=lfs diff=lfs merge=lfs -text +*.pkl filter=lfs diff=lfs merge=lfs -text +*.tar filter=lfs diff=lfs merge=lfs -text +*.wasm filter=lfs diff=lfs merge=lfs -text +*.zst filter=lfs diff=lfs merge=lfs -text +*tfevents* filter=lfs diff=lfs merge=lfs -text + +merges.txt filter=lfs diff=lfs merge=lfs -text +vocab.json filter=lfs diff=lfs merge=lfs -text +model.safetensors filter=lfs diff=lfs merge=lfs -text +tokenizer.json filter=lfs diff=lfs merge=lfs -text \ No newline at end of file diff --git a/.msc b/.msc new file mode 100644 index 0000000000000000000000000000000000000000..6c80233a07e342d4614ef37d34eb80f9be49eb9d GIT binary patch literal 1047 zcmbtT!H&}~5Jiv!EC>k@>@V~b*-kw69Ff@LN@(w>8jmM!N|RJgwn9iqd_a!je=+TD zSK_u=U&fdB{NB9h-`Srx*|X#MHZ6Wli!u93!+IJ&@S29@AkA(|gXEjK-Ox0?ypcoQ z*Ihe}iy}e=P6cB%QKcdWYohaDu~g||Aw)DLgy}ZXuAh&eR?^CzhJ;>n*H-l^-}H%T zojsoGMcy2az*2*V#x#_sXs`t9fEWXt3SC59S|}0lUPP8RJ=LIc#5IXDlcvMjTl>L*_yzFE9ST7wLC$>&DG~G*H?KHj}jOS+Cqy#&7fE`F&G3LOEKhQ>bY_b!JZq^ s{Bw}^RLPJ!((U_G;l1X9!LldRx>Q~x2Va(z@#4HE#YStO^i?GP3#CFu@c;k- literal 0 HcmV?d00001 diff --git a/.mv b/.mv new file mode 100644 index 0000000..dc232b2 --- /dev/null +++ b/.mv @@ -0,0 +1 @@ +Revision:master,CreatedAt:1766791365 \ No newline at end of file diff --git a/Modelfile b/Modelfile new file mode 100644 index 0000000..dc6ea3d --- /dev/null +++ b/Modelfile @@ -0,0 +1,11 @@ +# ollama modelfile auto-generated by llamafactory + +FROM . + +TEMPLATE """{{ if .System }}System: {{ .System }}<|im_end|> +{{ end }}{{ range .Messages }}{{ if eq .Role "user" }}Human: {{ .Content }}<|im_end|> +Assistant:{{ else if eq .Role "assistant" }}{{ .Content }}<|im_end|> +{{ end }}{{ end }}""" + +PARAMETER stop "<|im_end|>" +PARAMETER num_ctx 4096 diff --git a/README.md b/README.md new file mode 100644 index 0000000..f9a7aec --- /dev/null +++ b/README.md @@ -0,0 +1,189 @@ +# Qwen3-0.6B-Code-Expert 模型 LoRA 微调作业说明 +## 项目简介 +本项目是基于 **LLaMA Factory** 工具对阿里云通义千问的 **Qwen3-0.6B-Code-Expert** 小型代码大模型进行 **LoRA（Low-Rank Adaptation）轻量化微调** 的实践作业。核心目标是掌握大语言模型（LLM）的轻量化微调流程、训练检查点的恢复与管理、微调后模型的导出，以及通过 SSH 远程连接训练服务器完成模型下载、训练和文件传输的全流程操作。 + +项目针对 **CUDA 编程相关知识** 数据集（`cuda_train`）进行微调，最终得到适配 CUDA 知识问答的轻量化模型，同时实现了本地与远程训练服务器的协同操作。 + +### 核心技术栈 +- 模型基座：Qwen3-0.6B-Code-Expert（代码领域轻量级大模型） +- 微调框架：LLaMA Factory（一站式大模型微调工具） +- 微调方法：LoRA（低秩适配，减少训练参数量） +- 远程操作：SSH/SCP/Paramiko（服务器登录与文件传输） +- 依赖库：Transformers、PyTorch、Safetensors、Paramiko 等 + +## 环境配置 +### 1. 本地环境（开发机） +适用于 Windows/macOS/Linux，需安装 Python 3.8+，执行以下命令安装依赖： +```bash +# 基础依赖（模型加载与微调） +pip install torch==2.6.0 transformers==4.54.0 safetensors llama-factory +# 远程操作依赖（SSH 连接服务器） +pip install paramiko scp +``` + +### 2. 远程训练服务器（Seetacloud） +通过 SSH 登录服务器后，执行相同的依赖安装命令。若服务器无 GPU，需指定 CPU 版本依赖： +```bash +# 服务器无 GPU 时安装 CPU 版 PyTorch +pip install torch==2.6.0+cpu transformers==4.54.0 safetensors llama-factory --index-url https://download.pytorch.org/whl/cpu +``` + +## 快速开始 +### 1. 模型下载 +通过 `download_model.py` 脚本从 Hugging Face 下载 Qwen3-0.6B-Code-Expert 基座模型（或 Qwen2.5-0.5B 轻量化版本），支持本地/远程服务器下载。 + +#### 脚本使用 +```python +# download_model.py +import os +os.environ["HF_ENDPOINT"] = "https://hf-mirror.com" # 国内镜像加速 +from transformers import AutoModelForCausalLM, AutoTokenizer + +model_name = "Qwen/Qwen3-0.6B-Code-Expert" # 基座模型名称 +local_model_path = "./local-model" # 本地保存路径（服务器可改为 /root/local-model） + +# 加载并保存模型 +model = AutoModelForCausalLM.from_pretrained(model_name, trust_remote_code=True) +tokenizer = AutoTokenizer.from_pretrained(model_name, trust_remote_code=True) +model.save_pretrained(local_model_path) +tokenizer.save_pretrained(local_model_path) +print("模型下载完成！") +``` + +**运行脚本**： +- 本地：`python download_model.py` +- 远程服务器：先通过 SCP 上传脚本，再执行 `python /root/download_model.py` + +### 2. 模型微调（LoRA） +使用 LLaMA Factory 的命令行工具进行 LoRA 微调，核心命令如下（可保存为 `train.sh` 脚本）： +```bash +#!/bin/bash +llamafactory-cli train \ + --stage sft \ + --do_train True \ + --model_name_or_path /root/autodl-tmp/models/modelscope_cache/models/suayptalha/Qwen3-0.6B-Code-Expert \ + --preprocessing_num_workers 16 \ + --finetuning_type lora \ + --template default \ + --flash_attn auto \ + --dataset_dir data \ + --dataset cuda_train \ + --cutoff_len 2048 \ + --learning_rate 5e-05 \ + --num_train_epochs 20.0 \ + --max_samples 100000 \ + --per_device_train_batch_size 2 \ + --gradient_accumulation_steps 8 \ + --lr_scheduler_type cosine \ + --max_grad_norm 1.0 \ + --logging_steps 5 \ + --save_steps 100 \ + --warmup_steps 0 \ + --packing False \ + --enable_thinking True \ + --report_to none \ + --output_dir saves/Qwen3-0.6B-Base/lora/train_2025-12-21-07-31-02 \ + --bf16 True \ + --plot_loss True \ + --trust_remote_code True \ + --ddp_timeout 180000000 \ + --include_num_input_tokens_seen True \ + --optim adamw_torch \ + --lora_rank 8 \ + --lora_alpha 16 \ + --lora_dropout 0 \ + --lora_target all \ + --save_safetensors True +``` + +**关键参数说明**： +- `--finetuning_type lora`：指定 LoRA 轻量化微调； +- `--dataset cuda_train`：使用 CUDA 编程知识数据集； +- `--output_dir`：训练检查点保存路径； +- `--save_safetensors True`：使用 Safetensors 格式保存权重（规避 PyTorch 安全漏洞）。 + +**运行微调**： +```bash +# 赋予脚本执行权限 +chmod +x train.sh +# 执行微调 +./train.sh +``` + +### 3. 检查点恢复训练 +若训练中断，可通过 `--resume_from_checkpoint` 参数恢复训练： +```bash +llamafactory-cli train \ + # 保留原微调参数... + --resume_from_checkpoint saves/Qwen3-0.6B-Base/lora/train_2025-12-21-07-13-16 \ + --save_safetensors True +``` + +> **注意**：恢复训练需保证 PyTorch 版本 ≥2.6（规避 `torch.load` 安全漏洞），若版本过低需执行 `pip install torch==2.6.0` 升级。 + +### 4. 模型导出 +将 LoRA 微调权重与基座模型合并，导出为 Hugging Face 标准格式： +```bash +llamafactory-cli export \ + --model_name_or_path /root/autodl-tmp/models/modelscope_cache/models/suayptalha/Qwen3-0.6B-Code-Expert \ + --adapter_name_or_path saves/Qwen3-0.6B-Base/lora/train_2025-12-21-07-31-02 \ + --template default \ + --export_dir ./exported_qwen3_model \ + --export_format huggingface \ + --trust_remote_code True +``` + +导出后，`./exported_qwen3_model` 目录下为完整的可部署模型，可直接通过 `transformers` 加载使用。 + +## 远程服务器操作（Seetacloud） +本项目需通过 SSH 连接学校的 Seetacloud 训练服务器完成模型训练与文件传输，核心操作如下： + +### 1. 手动 SSH 登录 +```bash +# 连接服务器（端口 14788，输入密码即可登录） +ssh -p 14788 root@connect.sha1.seetacloud.com +``` + +### 2. 文件传输（SCP） +- **上传本地文件到服务器**： + ```bash + scp -P 14788 download_model.py root@connect.sha1.seetacloud.com:/root/ + ``` +- **下载服务器模型到本地**： + ```bash + scp -P 14788 -r root@connect.sha1.seetacloud.com:/root/exported_qwen3_model ./ + ``` + +### 3. 自动 SSH 操作脚本 +通过 `paramiko` 库实现自动化登录、执行命令与文件传输，脚本见 `ssh_model_operate.py`（需替换 SSH 密码）： +```bash +# 运行自动化脚本 +python ssh_model_operate.py +``` + +## 项目结构 +``` +. +├── download_model.py # 基座模型下载脚本 +├── train.sh # LoRA 微调脚本 +├── ssh_model_operate.py # 远程服务器自动化操作脚本 +├── data/ # 数据集目录（存放 cuda_train 数据集） +├── local-model/ # 本地下载的基座模型 +├── saves/ # 训练检查点保存目录 +├── exported_qwen3_model/ # 导出的微调后完整模型 +└── README.md # 项目说明文档 +``` + +## 注意事项 +1. **PyTorch 版本**：恢复训练时需保证 PyTorch ≥2.6，否则会触发 `torch.load` 安全漏洞报错； +2. **服务器环境**：若服务器无 GPU，需在加载模型时指定 `device_map='cpu'`； +3. **大文件传输**：模型文件较大时，推荐使用 `rsync` 替代 SCP 以提升稳定性： + ```bash + rsync -avz -e 'ssh -p 14788' root@connect.sha1.seetacloud.com:/root/exported_qwen3_model ./ + ``` +4. **SSH 安全**：建议使用 SSH 密钥登录服务器，避免密码明文暴露。 + +## 致谢 +1. 感谢学校提供的 Seetacloud 训练服务器资源； +2. 感谢 LLaMA Factory 团队提供的一站式大模型微调工具； +3. 感谢阿里云通义千问团队开源的 Qwen3 系列模型。 diff --git a/added_tokens.json b/added_tokens.json new file mode 100644 index 0000000..b54f913 --- /dev/null +++ b/added_tokens.json @@ -0,0 +1,28 @@ +{ + "": 151668, + "": 151658, + "": 151666, + "": 151667, + "": 151657, + "": 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 +} diff --git a/chat_template.jinja b/chat_template.jinja new file mode 100644 index 0000000..45d38ef --- /dev/null +++ b/chat_template.jinja @@ -0,0 +1,4 @@ +{% if messages[0]['role'] == 'system' %}{% set loop_messages = messages[1:] %}{% set system_message = messages[0]['content'] %}{% else %}{% set loop_messages = messages %}{% endif %}{% if system_message is defined %}{{ 'System: ' + system_message + '<|im_end|>' + ' +' }}{% endif %}{% for message in loop_messages %}{% set content = message['content'] %}{% if message['role'] == 'user' %}{{ 'Human: ' + content + '<|im_end|>' + ' +Assistant:' }}{% elif message['role'] == 'assistant' %}{{ content + '<|im_end|>' + ' +' }}{% endif %}{% endfor %} \ No newline at end of file diff --git a/config.json b/config.json new file mode 100644 index 0000000..6bef545 --- /dev/null +++ b/config.json @@ -0,0 +1,62 @@ +{ + "architectures": [ + "Qwen3ForCausalLM" + ], + "attention_bias": false, + "attention_dropout": 0.0, + "eos_token_id": 151645, + "head_dim": 128, + "hidden_act": "silu", + "hidden_size": 1024, + "initializer_range": 0.02, + "intermediate_size": 3072, + "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": 151654, + "rms_norm_eps": 1e-06, + "rope_scaling": null, + "rope_theta": 1000000, + "sliding_window": null, + "tie_word_embeddings": true, + "torch_dtype": "float16", + "transformers_version": "4.55.0", + "unsloth_fixed": true, + "unsloth_version": "2025.4.7", + "use_cache": true, + "use_sliding_window": false, + "vocab_size": 151936 +} diff --git a/configuration.json b/configuration.json new file mode 100644 index 0000000..f9291c3 --- /dev/null +++ b/configuration.json @@ -0,0 +1 @@ +{"framework":"Pytorch","task":"text-generation"} \ No newline at end of file diff --git a/generation_config.json b/generation_config.json new file mode 100644 index 0000000..9711a9c --- /dev/null +++ b/generation_config.json @@ -0,0 +1,14 @@ +{ + "bos_token_id": 151643, + "do_sample": true, + "eos_token_id": [ + 151645, + 151643 + ], + "max_length": 40960, + "pad_token_id": 151654, + "temperature": 0.6, + "top_k": 20, + "top_p": 0.95, + "transformers_version": "4.55.0" +} diff --git a/merges.txt b/merges.txt new file mode 100644 index 0000000..80c1a19 --- /dev/null +++ b/merges.txt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8831e4f1a044471340f7c0a83d7bd71306a5b867e95fd870f74d0c5308a904d5 +size 1671853 diff --git a/model.safetensors b/model.safetensors new file mode 100644 index 0000000..4cbc3f4 --- /dev/null +++ b/model.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:28dbe8330733912621f876cd0b6b40f3b1d782fc8e261ff863fe3b05e225ebb9 +size 1192134784 diff --git a/special_tokens_map.json b/special_tokens_map.json new file mode 100644 index 0000000..9b8043f --- /dev/null +++ b/special_tokens_map.json @@ -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": "<|vision_pad|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false + } +} diff --git a/tokenizer.json b/tokenizer.json new file mode 100644 index 0000000..cd71f61 --- /dev/null +++ b/tokenizer.json @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:aeb13307a71acd8fe81861d94ad54ab689df773318809eed3cbe794b4492dae4 +size 11422654 diff --git a/tokenizer_config.json b/tokenizer_config.json new file mode 100644 index 0000000..3bd8e2e --- /dev/null +++ b/tokenizer_config.json @@ -0,0 +1,240 @@ +{ + "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": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "151658": { + "content": "", + "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": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "151666": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "151667": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "151668": { + "content": "", + "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": 40960, + "pad_token": "<|vision_pad|>", + "padding_side": "left", + "split_special_tokens": false, + "tokenizer_class": "Qwen2Tokenizer", + "unk_token": null +} diff --git a/vocab.json b/vocab.json new file mode 100644 index 0000000..6c49fc6 --- /dev/null +++ b/vocab.json @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ca10d7e9fb3ed18575dd1e277a2579c16d108e32f27439684afa0e10b1440910 +size 2776833