sequelbox/Llama3.1-70B-PlumChat

Full fine-tune vs ValiantLabs/Llama3.1-70B-ShiningValiant2. Fine-tune: 99% of the weights changed, across 80 of 80 layers.

Tensors changed: Embeddings 0/1, Attention 320/320, Norms 71/161, MLP 240/240, lm_head 1/1

2 derivatives checked

• mradermacher/Llama3.1-70B-PlumChat-i1-GGUF: Quantization
• mradermacher/Llama3.1-70B-PlumChat-GGUF: Quantization

On the Hub · Downloads on Model Pulse