rinna/youri-7b

Full fine-tune vs meta-llama/Llama-2-7b-hf. Fine-tune: 100% of the weights changed, across 32 of 32 layers.

Tensors changed: Attention 160/160, Embeddings 1/1, Norms 65/65, MLP 96/96, lm_head 1/1

4 derivatives checked

• mradermacher/youri-7b-GGUF: Same weights, converted
• mradermacher/youri-7b-i1-GGUF: Quantization
• rinna/youri-7b-chat: Full fine-tune
• rinna/youri-7b-instruction: Full fine-tune

On the Hub · Downloads on Model Pulse