Nexesenex/Llama_3.1_8b_DodoWild_v2.03

Full fine-tune vs Nexesenex/Llama_3.1_8b_Dolermed_R1_V1.03. Fine-tune: 100% of the weights changed, across 32 of 32 layers.

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

2 derivatives checked

• mradermacher/Llama_3.1_8b_DodoWild_v2.03-i1-GGUF: Quantization
• mradermacher/Llama_3.1_8b_DodoWild_v2.03-GGUF: Same weights, converted

On the Hub · Downloads on Model Pulse