NotTheStallion/reshard-safetensors
This repo helps you understand how safetensors are structured to store different layers of an LLM and re-shard/re-chunk safetensors files even if they don't fit in the GPU.. ( No Autoclass )
PythonApache-2.0
This repo helps you understand how safetensors are structured to store different layers of an LLM and re-shard/re-chunk safetensors files even if they don't fit in the GPU.. ( No Autoclass )
PythonApache-2.0