mlabonne/ChimeraLlama-3-8B-v3

Full fine-tune vs Danielbrdz/Barcenas-Llama3-8b-ORPO. Fine-tune: 100% of the weights changed, across 32 of 32 layers.

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

2 derivatives checked

• mradermacher/ChimeraLlama-3-8B-v3-GGUF: Same weights, converted
• featherless-ai-quants/mlabonne-ChimeraLlama-3-8B-v3-GGUF: Quantization

On the Hub · Downloads on Model Pulse