shisa-ai/shisa-v2-mistral-small-24b
Full fine-tune vs mistralai/Mistral-Small-24B-Instruct-2501. Fine-tune: 100% of the weights changed, across 40 of 40 layers.
Tensors changed: Embeddings 1/1, Norms 15/81, MLP 120/120, Attention 160/160, lm_head 1/1
3 derivatives checked
- mradermacher/shisa-v2-mistral-small-24b-i1-GGUF: Quantization
- mradermacher/shisa-v2-mistral-small-24b-GGUF: Quantization
- DevQuasar/shisa-ai.shisa-v2-mistral-small-24b-GGUF: Same weights, converted
1 other repos hold byte-for-byte identical weight files.