rinna/llama-3-youko-70b-instruct
Full fine-tune vs meta-llama/Meta-Llama-3-70B. Fine-tune: 99% of the weights changed, across 80 of 80 layers.
Tensors changed: Embeddings 0/1, Norms 161/161, MLP 240/240, Attention 320/320, lm_head 1/1
4 derivatives checked
- mradermacher/llama-3-youko-70b-instruct-i1-GGUF: Quantization
- mradermacher/llama-3-youko-70b-instruct-GGUF: Quantization
- DevQuasar-11/rinna.llama-3-youko-70b-instruct-GGUF: Same weights, converted
- featherless-ai-quants/rinna-llama-3-youko-70b-instruct-GGUF: Quantization