netcat420/DeepSeek-R1-Distill-Qwen-MFANN-Slerp-7b

Full fine-tune vs deepseek-ai/DeepSeek-R1-Distill-Qwen-7B. Fine-tune: 97% of the weights changed, across 28 of 28 layers.

Tensors changed: Embeddings 1/1, Attention 189/196, MLP 81/84, Norms 57/57, lm_head 1/1

2 derivatives checked

• mradermacher/DeepSeek-R1-Distill-Qwen-MFANN-Slerp-7b-i1-GGUF: Quantization
• mradermacher/DeepSeek-R1-Distill-Qwen-MFANN-Slerp-7b-GGUF: Same weights, converted

On the Hub · Downloads on Model Pulse