dphn/dolphin-2.9.3-mistral-7B-32k
Full fine-tune vs mistralai/Mistral-7B-v0.3. Fine-tune: 100% of the weights changed, across 32 of 32 layers.
Tensors changed: Norms 20/65, MLP 96/96, Attention 128/128
4 derivatives checked
- mradermacher/dolphin-2.9.3-mistral-7B-32k-i1-GGUF: Quantization
- mradermacher/dolphin-2.9.3-mistral-7B-32k-GGUF: Same weights, converted
- huggingkot/dolphin-2.9.3-mistral-7B-32k-Q4_K_M-GGUF: Quantization
- DevQuasar-9/cognitivecomputations.dolphin-2.9.3-mistral-7B-32k-GGUF: Same weights, converted