Rakuten/RakutenAI-2.0-8x7B-instruct

Full fine-tune vs Rakuten/RakutenAI-2.0-8x7B. Fine-tune: 100% of the weights changed, across 32 of 32 layers.

Tensors changed: lm_head 1/1, Embeddings 1/1, MLP 768/768, other 32/32, Norms 34/65, Attention 128/128

1 derivatives checked

• mmnga/RakutenAI-2.0-8x7B-instruct-gguf: Quantization

On the Hub · Downloads on Model Pulse