lmg-anon/vntl-llama3-8b-v2-hf

Full fine-tune vs rinna/llama-3-youko-8b. Fine-tune: 93% of the weights changed, across 32 of 32 layers.

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

2 derivatives checked

• mradermacher/vntl-llama3-8b-v2-hf-GGUF: Same weights, converted
• Casual-Autopsy/vntl-llama3-8b-v2-imatrix-gguf: Same weights, converted

On the Hub · Downloads on Model Pulse