DevQuasar-7/huihui-ai.DeepSeek-R1-Distill-Qwen-14B-abliterated-v2-GGUF

Same weights, converted vs huihui-ai/DeepSeek-R1-Distill-Qwen-14B-abliterated-v2. Same weights stored in another dtype (BF16 → F16/F32).

Tensors changed: Embeddings 0/1, Norms 0/97, MLP 0/144, Attention 0/336, lm_head 0/1

On the Hub · Downloads on Model Pulse