angelolamonaca/PyTorch-Precision-Converter
Convert PyTorch checkpoints, safetensors files and whole Hugging Face model folders to fp16, bf16, fp8 or ComfyUI fp8_scaled, int8_convrot and int8, turn FP8 models (DeepSeek, Qwen) back into BF16 on a CPU, merge or split sharded safetensors, and extract EMA weights, with one command and without loading the model into RAM.
GitHub repository with 12 stars and 0 forks.
Language: Python
Topics: bf16, deep-learning, fp16, machine-learning, model-checkpoint, model-compression, model-conversion, pytorch, tensor-precision, ema