djuna/DeepSeek-R1-Distill-Qwen-14B-abliterated-v2-remap

Full fine-tune vs djuna/Q2.5-Veltha-14B-0.5. Fine-tune: 100% of the weights changed, across 48 of 48 layers.

Tensors changed: Norms 97/97, MLP 144/144, Attention 336/336

3 derivatives checked

• fairy322/DeepSeek-R1-Distill-Qwen-14B-abliterated-v2-remap-i1-GGUF: Quantization
• mradermacher/DeepSeek-R1-Distill-Qwen-14B-abliterated-v2-remap-i1-GGUF: Quantization
• mradermacher/DeepSeek-R1-Distill-Qwen-14B-abliterated-v2-remap-GGUF: Quantization

On the Hub · Downloads on Model Pulse