ZeroXClem/Mistral-2.5-Prima-Hercules-Fusion-7B

Full fine-tune vs Nitral-Archive/Prima-Pastacles-7b. Fine-tune: 97% of the weights changed, across 32 of 32 layers.

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

2 derivatives checked

• mradermacher/Mistral-2.5-Prima-Hercules-Fusion-7B-i1-GGUF: Quantization
• mradermacher/Mistral-2.5-Prima-Hercules-Fusion-7B-GGUF: Same weights, converted

On the Hub · Downloads on Model Pulse