Antonio88/TaliML-7B-ITA-V.1.0.FINAL

Full fine-tune vs mistralai/Mistral-7B-v0.1. Fine-tune: 98% of the weights changed, across 32 of 32 layers.

Tensors changed: Embeddings 0/1, Norms 0/65, MLP 96/96, Attention 128/128, lm_head 1/1

3 derivatives checked

• mradermacher/TaliML-7B-V.1-ENG-GGUF: Full fine-tune
• mradermacher/TaliML-7B-ITA-V.1.0.FINAL-i1-GGUF: Quantization
• mradermacher/TaliML-7B-ITA-V.1.0.FINAL-GGUF: Same weights, converted

On the Hub · Downloads on Model Pulse