ce-lery/japanese-mistral-300m-instruction

Full fine-tune vs ce-lery/japanese-mistral-300m-base. Fine-tune: 100% of the weights changed, across 24 of 24 layers.

Tensors changed: lm_head 1/1, Embeddings 1/1, Norms 49/49, MLP 72/72, Attention 96/96

1 derivatives checked

• afrideva/japanese-mistral-300m-instruction-GGUF: Same weights, converted

On the Hub · Downloads on Model Pulse