unsloth/DeepSeek-R1-Distill-Qwen-7B

Same weights, repacked vs deepseek-ai/DeepSeek-R1-Distill-Qwen-7B. Same weights in different files (re-saved, re-sharded or new metadata).

Tensors changed: Embeddings 0/1, Attention 0/196, MLP 0/84, Norms 0/57, lm_head 0/1

1 derivatives checked

• derek33125/PA-stage1-DeepSeekQwen7B-300: LoRA-style

12 other repos hold byte-for-byte identical weight files.

On the Hub · Downloads on Model Pulse