unsloth/DeepSeek-R1-0528-Qwen3-8B

Same weights, repacked vs deepseek-ai/DeepSeek-R1-0528-Qwen3-8B. Same weights in different files (re-saved, re-sharded or new metadata).

Tensors changed: Embeddings 0/1, Attention 0/144, Norms 0/145, MLP 0/108, lm_head 0/1

4 derivatives checked

• bcoding/deepseek-R1-0528-Qwen3-8b-base-16-llvm-sft-trained-16bit-epoch-2-merged: LoRA-style
• zypchn/BehChat-v0.3: LoRA-style
• Haeryz/Deepseek-TPPO-V1: LoRA-style
• zypchn/BehChat-v2.1: LoRA-style

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

On the Hub · Downloads on Model Pulse