ngxson/DeepSeek-R1-Distill-Qwen-7B-abliterated-GGUF

Full fine-tune vs deepseek-ai/DeepSeek-R1-Distill-Qwen-7B. ngxson/DeepSeek-R1-Distill-Qwen-7B-abliterated-GGUF is a GGUF (F16) of different weights. Fine-tune: 100% of the weights changed, across 28 of 28 layers.

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

On the Hub · Downloads on Model Pulse