EADST

Save Hugging Face Model with One Bin

max_shard_size (int or str, optional, defaults to "10GB") — Only applicable for models. The maximum size for a checkpoint before being sharded. Checkpoints shard will then be each of size lower than this size. If expressed as a string, needs to be digits followed by a unit (like "5MB").

Based on the introduction, one bin model can be saved by changing the "max_shard_size".

LlamaForCausalLM.save_pretrained(base_model, output_dir, max_shard_size="100GB") # save one bin if the model is less than 100GB

Reference

PreTrainedModel

About Me
XD
Goals determine what you are going to be.
Category
标签云
递归学习法 Distillation GGML Plate WAN ms-swift RL Django Ubuntu Qwen2.5 SVR CV Claude tar FP32 域名 Qwen2 llama.cpp Augmentation 论文速读 OpenCV tqdm Google Numpy Land RAR Video git VPN Agent PyTorch Linux UI Llama ONNX scipy Color Github 图标 Vmess BTC WebCrawler Transformers Interview InvalidArgumentError v0.dev Bin Vim 版权 MD5 算法题 TTS SPIE TSV NLTK Search 报税 diffusers Statistics RGB Anaconda Input COCO Knowledge Zip TensorFlow XGBoost Clash Freesound Pickle ResNet-50 签证 BF16 HuggingFace Review API Cloudreve mmap Pandas CUDA CLAP 多进程 Docker Windows Plotly YOLO Pytorch DeepSeek Nginx Miniforge Use 阿里云 ChatGPT Datetime OpenAI Heatmap Bipartite 公式 财报 Ptyhon SQL OCR Python Quantization uwsgi Rebuttal hf CAM Hungarian LaTeX Michelin BeautifulSoup Git FP64 TensorRT Attention Mixtral Shortcut 顶会 FP16 Hilton Conda Domain Quantize LLAMA 第一性原理 icon 强化学习 音频 Magnet VGG-16 transformers Password FP8 Bert Tensor SQLite Qwen printf Safetensors HaggingFace LoRA CSV ModelScope LeetCode Streamlit 飞书 Breakpoint Firewall Animate Jetson CC Crawler GIT 关于博主 Diagram AI Website CTC 继承 Hotel 搞笑 PIP Tracking 多线程 Translation QWEN 腾讯云 Web LLM NLP Algorithm FlashAttention Base64 Food uWSGI FastAPI Paddle PyCharm Sklearn Card GoogLeNet GPT4 论文 Dataset JSON GPTQ UNIX Bitcoin git-lfs Tiktoken Random C++ News Proxy Gemma 云服务器 Excel Disk Math Baidu CEIR 净利润 Jupyter PDF 证件照 Template IndexTTS2 Logo EXCEL Paper logger Data 图形思考法 v2ray SAM XML PDB Image2Text Pillow NameSilo Markdown DeepStream VSCode Permission torchinfo
站点统计

本站现有博文332篇,共被浏览875630

本站已经建立2583天!

热门文章
文章归档
回到顶部