nbeerbower/llama3-KawaiiMahouSauce-8B

Full fine-tune vs nbeerbower/KawaiiMahou-llama3-8B. Fine-tune: 97% of the weights changed, across 32 of 32 layers.

Tensors changed: Embeddings 1/1, Norms 65/65, MLP 93/96, Attention 124/128, lm_head 1/1

3 derivatives checked

• mradermacher/llama3-KawaiiMahouSauce-8B-GGUF: Same weights, converted
• featherless-ai-quants/nbeerbower-llama3-KawaiiMahouSauce-8B-GGUF: Quantization
• flammenai/Mahou-1.2-llama3-8B: LoRA-style

On the Hub · Downloads on Model Pulse