Nitral-Archive/Prima-Pastacles-7b

Full fine-tune vs Locutusque/Hercules-2.5-Mistral-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

3 derivatives checked

• mradermacher/Prima-Pastacles-7b-i1-GGUF: Quantization
• jeiku/Nitrals_Monster_7B: Full fine-tune
• ZeroXClem/Mistral-2.5-Prima-Hercules-Fusion-7B: Full fine-tune

On the Hub · Downloads on Model Pulse