agentlans/Llama3.1-vodka

Full fine-tune vs NousResearch/Meta-Llama-3.1-8B-Instruct. Fine-tune: 100% of the weights changed, across 32 of 32 layers.

Tensors changed: Embeddings 1/1, Norms 0/65, MLP 96/96, Attention 128/128, lm_head 1/1

3 derivatives checked

• mradermacher/Llama3.1-vodka-i1-GGUF: Quantization
• mradermacher/Llama3.1-vodka-GGUF: Same weights, converted
• MaziyarPanahi/Llama3.1-vodka-GGUF: Same weights, converted

On the Hub · Downloads on Model Pulse