mobiuslabsgmbh/DeepSeek-R1-ReDistill-Qwen-7B-v1.1

Partial fine-tune vs deepseek-ai/DeepSeek-R1-Distill-Qwen-7B. Partial change: 86% of the weights changed (attention, mlp, norms), in 28 of 28 layers.

Tensors changed: Embeddings 0/1, Attention 196/196, MLP 84/84, Norms 42/57, lm_head 0/1

3 derivatives checked

• mradermacher/DeepSeek-R1-ReDistill-Qwen-7B-v1.1-i1-GGUF: Quantization
• Melvin56/DeepSeek-R1-ReDistill-Qwen-7B-v1.1-GGUF: Same weights, converted
• mradermacher/DeepSeek-R1-ReDistill-Qwen-7B-v1.1-GGUF: Same weights, converted

On the Hub · Downloads on Model Pulse