AdamGrzesik/Samantha-PL-AG-Mistral-7B-v0.2
Full fine-tune vs mistral-community/Mistral-7B-v0.2. Fine-tune: 100% of the weights changed, across 32 of 32 layers.
Tensors changed: Norms 12/65, MLP 96/96, Attention 128/128
2 derivatives checked
- mradermacher/Samantha-PL-AG-Mistral-7B-v0.2-i1-GGUF: Quantization
- mradermacher/Samantha-PL-AG-Mistral-7B-v0.2-GGUF: Same weights, converted