flammenai/flammen27-mistral-7B

Full fine-tune vs InferenceIllusionist/Excalibur-7b. Fine-tune: 97% of the weights changed, across 32 of 32 layers.

Tensors changed: Embeddings 1/1, Norms 65/65, MLP 93/96, Attention 124/128, lm_head 1/1

1 derivatives checked

• flammenai/Mahou-1.2a-mistral-7B: LoRA-style

On the Hub · Downloads on Model Pulse