rinna/llama-3-youko-70b
Partial fine-tune vs meta-llama/Meta-Llama-3-70B. Partial change: 23% of the weights changed (attention, lm_head, mlp, norms), in 80 of 80 layers.
Tensors changed: Embeddings 0/1, Norms 161/161, MLP 54/240, Attention 72/320, lm_head 1/1
2 derivatives checked
- mradermacher/llama-3-youko-70b-i1-GGUF: Quantization
- mradermacher/llama-3-youko-70b-GGUF: Quantization