BCCard/Llama-3-Kor-BCCard-Finance-8B

Full fine-tune vs sh2orc/Llama-3-Korean-8B. Fine-tune: 100% of the weights changed, across 32 of 32 layers.

Tensors changed: Norms 16/65, MLP 96/96, Attention 128/128

2 derivatives checked

• featherless-ai-quants/BCCard-Llama-3-Kor-BCCard-Finance-8B-GGUF: Quantization
• PrunaAI/BCCard-Llama-3-Kor-BCCard-Finance-8B-GGUF-smashed: Quantization

On the Hub · Downloads on Model Pulse