LVSTCK/domestic-yak-8B-instruct

Full fine-tune vs LVSTCK/domestic-yak-8B. Fine-tune: 93% of the weights changed, across 32 of 32 layers.

Tensors changed: Embeddings 0/1, Norms 12/65, MLP 96/96, Attention 128/128, lm_head 1/1

2 derivatives checked

• mradermacher/domestic-yak-8B-instruct-GGUF: Same weights, converted
• LVSTCK/domestic-yak-8B-instruct-GGUF: Quantization

On the Hub · Downloads on Model Pulse