Dongwei/DeepSeek-R1-Distill-Qwen-7B-GRPO
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
3 derivatives checked
- mradermacher/DeepSeek-R1-Distill-Qwen-7B-GRPO-i1-GGUF: Quantization
- mradermacher/DeepSeek-R1-Distill-Qwen-7B-GRPO-GGUF: Same weights, converted
- kainatq/quantum-keek-v2-7b: Full fine-tune
12 other repos hold byte-for-byte identical weight files.