h34v7/DeepSeek-R1-Distill-Qwen-7B-Uncensored-Reasoner-GGUF

Full fine-tune vs nicoboss/DeepSeek-R1-Distill-Qwen-7B-Uncensored-Reasoner. h34v7/DeepSeek-R1-Distill-Qwen-7B-Uncensored-Reasoner-GGUF is a GGUF (Q4_K_M) of different weights. Fine-tune: 100% of the weights changed, across 28 of 28 layers.

Tensors changed: Embeddings 1/1, Norms 0/57, MLP 84/84, Attention 112/196, lm_head 1/1

On the Hub · Downloads on Model Pulse