flammenai/flammen15-mistral-7B
Full fine-tune vs flammenai/flammen14-mistral-7B. Fine-tune: 97% of the weights changed, across 32 of 32 layers.
Tensors changed: lm_head 1/1, Norms 65/65, MLP 93/96, Attention 124/128, Embeddings 1/1
3 derivatives checked
- mradermacher/flammen15-mistral-7B-i1-GGUF: Quantization
- mradermacher/flammen15-mistral-7B-GGUF: Same weights, converted
- flammenai/flammen15-gutenberg-DPO-v1-7B: LoRA-style