muzerai/Deep-Llama-3.1-KoEn-8B-SiSai

Full fine-tune vs allenai/Llama-3.1-Tulu-3.1-8B. Fine-tune: 100% of the weights changed, across 32 of 32 layers.

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

2 derivatives checked

• mradermacher/Deep-Llama-3.1-KoEn-8B-SiSai-i1-GGUF: Quantization
• mradermacher/Deep-Llama-3.1-KoEn-8B-SiSai-GGUF: Same weights, converted

On the Hub · Downloads on Model Pulse