aidenjamie/llama3.1-8b-kowiki-instruct-lora

Partial fine-tune vs unsloth/Meta-Llama-3.1-8B. Partial change: 7% of the weights changed (lm_head), in 0 of 32 layers.

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

1 derivatives checked

• mradermacher/llama3.1-8b-kowiki-instruct-lora-GGUF: Same weights, converted

On the Hub · Downloads on Model Pulse