migtissera/Tess-3-7B-SFT
Full fine-tune vs mistralai/Mistral-7B-v0.3. Fine-tune: 100% of the weights changed, across 32 of 32 layers.
Tensors changed: Norms 17/65, MLP 96/96, Attention 128/128
4 derivatives checked
- bartowski/Tess-3-7B-SFT-GGUF: Quantization
- mradermacher/Tess-3-7B-SFT-GGUF: Same weights, converted
- mradermacher/Tess-3-7B-SFT-i1-GGUF: Quantization
- juvi21/Tess-3-7B-SFT-GGUF: Same weights, converted