rinna/youri-7b-chat

Full fine-tune vs rinna/youri-7b. 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

3 derivatives checked

• mradermacher/youri-7b-chat-i1-GGUF: Quantization
• mradermacher/youri-7b-chat-GGUF: Same weights, converted
• rinna/youri-7b-chat-gptq: Quantization

On the Hub · Downloads on Model Pulse