nayohan/llama3-8b-it-prometheus-ko
Full fine-tune vs meta-llama/Meta-Llama-3-8B-Instruct. Fine-tune: 93% of the weights changed, across 32 of 32 layers.
Tensors changed: Embeddings 0/1, Norms 64/65, MLP 96/96, Attention 128/128, lm_head 1/1
3 derivatives checked
- mradermacher/llama3-8b-it-prometheus-ko-i1-GGUF: Quantization
- featherless-ai-quants/nayohan-llama3-8b-it-prometheus-ko-GGUF: Quantization
- mradermacher/llama3-8b-it-prometheus-ko-GGUF: Same weights, converted