NexesMess/Llama_3.x_70b_Betsy_0.1

Full fine-tune vs Nexesenex/Llama_3.x_70b_Smarteaz_V1. Fine-tune: 100% of the weights changed, across 80 of 80 layers.

Tensors changed: lm_head 1/1, Embeddings 1/1, Norms 161/161, MLP 240/240, Attention 320/320

2 derivatives checked

• mradermacher/Llama_3.x_70b_Betsy_0.1-i1-GGUF: Quantization
• mradermacher/Llama_3.x_70b_Betsy_0.1-GGUF: Quantization

On the Hub · Downloads on Model Pulse