Download model_save.py from WHY2001/DeepSeek-OCR-4bit-Quantized: direct link, hf CLI and curl.
- Browser
- Download file 2.76 kB
-
https://huggingface.co/WHY2001/DeepSeek-OCR-4bit-Quantized/resolve/main/model_save.py
- Command line
-
hf download hf://WHY2001/DeepSeek-OCR-4bit-Quantized/model_save.py
-
curl -L -o model_save.py https://huggingface.co/WHY2001/DeepSeek-OCR-4bit-Quantized/resolve/main/model_save.py
2.76 kB
| import os | |
| import shutil | |
| import torch | |
| from transformers import AutoModel, AutoTokenizer, BitsAndBytesConfig | |
| # === 1. 路径设置 === | |
| INPUT_PATH = "/home/nashen/deepseek-ocr/DeepSeek-OCR-master/DeepSeek-OCR-vllm/model/" | |
| OUTPUT_PATH = "./DeepSeek-OCR-4bit-Quantized" # 打包好的成品将保存在这里 | |
| # === 2. 黄金量化配置 (直接复用你测试成功的配置) === | |
| print("⏳ 正在加载并量化模型 (这可能需要几分钟)...") | |
| quantization_config = BitsAndBytesConfig( | |
| load_in_4bit=True, | |
| bnb_4bit_quant_type="nf4", | |
| bnb_4bit_use_double_quant=True, | |
| bnb_4bit_compute_dtype=torch.bfloat16, | |
| # 🛡️ 核心白名单:确保保存后的模型也有这层保护 | |
| llm_int8_skip_modules=[ | |
| "sam_model", "model.sam_model", | |
| "vision_model", "model.vision_model", | |
| "projector", "model.projector", | |
| "lm_head", "embed_tokens" | |
| ] | |
| ) | |
| # === 3. 加载模型 === | |
| model = AutoModel.from_pretrained( | |
| INPUT_PATH, | |
| trust_remote_code=True, | |
| quantization_config=quantization_config, | |
| device_map="auto" | |
| ) | |
| tokenizer = AutoTokenizer.from_pretrained(INPUT_PATH, trust_remote_code=True) | |
| print("✅ 模型加载完成,准备保存...") | |
| # === 4. 保存模型 (核心步骤) === | |
| # 这会将 4-bit 权重和 quantization_config 写入 config.json | |
| model.save_pretrained(OUTPUT_PATH, safe_serialization=True) | |
| tokenizer.save_pretrained(OUTPUT_PATH) | |
| print(f"✅ 权重已保存至: {OUTPUT_PATH}") | |
| # === 5. 关键:复制自定义代码文件 === | |
| # 因为 DeepSeek-OCR 是 "Remote Code" 模型,必须手动把 python 代码拷过去 | |
| # 否则用户加载时会报错 "class not found" | |
| print("📦 正在复制 Python 架构文件...") | |
| files_to_copy = [ | |
| "configuration_deepseek_v2.py", | |
| "modeling_deepseekv2.py", | |
| "modeling_deepseekocr.py", | |
| "deepencoder.py", | |
| # 如果有其他 .py 文件或 .json (如 processor_config.json) 也要拷过去 | |
| "processor_config.json", | |
| "config.json", # 覆盖一下以防万一,但 save_pretrained 通常会处理 | |
| "special_tokens_map.json", | |
| "tokenizer_config.json", | |
| "tokenizer.json" | |
| ] | |
| # 自动扫描并复制 input 目录下的所有 .py 文件 (更安全) | |
| for filename in os.listdir(INPUT_PATH): | |
| if filename.endswith(".py") or filename.endswith(".json"): | |
| src = os.path.join(INPUT_PATH, filename) | |
| dst = os.path.join(OUTPUT_PATH, filename) | |
| # config.json 和 tokenizer 文件可能已经被 save_pretrained 生成了,跳过覆盖 | |
| if os.path.exists(dst) and "config" in filename: | |
| continue | |
| shutil.copy2(src, dst) | |
| print(f"🎉 打包完成!成品位于: {OUTPUT_PATH}") | |
| print(f" 该文件夹现在的体积应该是 ~2.7 GB 左右。") | |