Weyaxi/Einstein-v5-v0.2-7B
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 18/65, MLP 96/96, Attention 128/128
4 derivatives checked
- mradermacher/Einstein-v5-v0.2-7B-i1-GGUF: Quantization
- mradermacher/Einstein-v5-v0.2-7B-GGUF: Same weights, converted
- Goekdeniz-Guelmez/J.O.S.I.E.3-Beta10-7B-slerp: Full fine-tune
- Goekdeniz-Guelmez/J.O.S.I.E.3-Beta9-7B-slerp: Full fine-tune