alamios/Mistral-Small-3.1-DRAFT-0.5B
Full fine-tune vs alamios/Qwenstral-Small-3.1-0.5B. Fine-tune: 100% of the weights changed, across 24 of 24 layers.
Tensors changed: lm_head 1/1, Embeddings 1/1, Norms 13/49, MLP 72/72, Attention 166/168
5 derivatives checked
- bartowski/alamios_Mistral-Small-3.1-DRAFT-0.5B-GGUF: Same weights, converted
- DevQuasar-11/alamios.Mistral-Small-3.1-DRAFT-0.5B-GGUF: Same weights, converted
- mradermacher/Mistral-Small-3.1-DRAFT-0.5B-GGUF: Same weights, converted
- alamios/Mistral-Small-3.1-DRAFT-0.5B-GGUF: Same weights, converted
- badmadrad/Mistral-Small-3.1-DRAFT-0.5B-MLX-4bit: Quantization
1 other repos hold byte-for-byte identical weight files.