rinna/llama-3-youko-8b
Full fine-tune vs meta-llama/Meta-Llama-3-8B. Fine-tune: 100% of the weights changed, across 32 of 32 layers.
Tensors changed: Embeddings 1/1, Norms 65/65, MLP 96/96, Attention 128/128, lm_head 1/1
6 derivatives checked
- lmg-anon/vntl-llama3-8b-v2-gguf: Full fine-tune
- QuantFactory/llama-3-youko-8b-GGUF: Quantization
- mradermacher/llama-3-youko-8b-GGUF: Same weights, converted
- featherless-ai-quants/rinna-llama-3-youko-8b-GGUF: Quantization
- csabakecskemeti/rinna.llama-3-youko-8b-GGUF: Same weights, converted
- lmg-anon/vntl-llama3-8b-v2-hf: Full fine-tune