Nexesenex/Llama_3.1_8b_DodoWild_v2.10

Full fine-tune vs Nexesenex/Llama_3.1_8b_Dolerstormed_V1.04. Fine-tune: 100% of the weights changed, across 32 of 32 layers.

Tensors changed: Norms 24/65, MLP 96/96, Attention 128/128

2 derivatives checked

• mradermacher/Llama_3.1_8b_DodoWild_v2.10-GGUF: Same weights, converted
• mradermacher/Llama_3.1_8b_DodoWild_v2.10-i1-GGUF: Quantization

On the Hub · Downloads on Model Pulse