masakhane/zephyr-7b-gemma-sft-african-ultrachat-200k

Full fine-tune vs google/gemma-7b. Fine-tune: 100% of the weights changed, across 28 of 28 layers.

Tensors changed: Embeddings 1/1, Norms 57/57, MLP 84/84, Attention 112/112

1 derivatives checked

• afrideva/zephyr-7b-gemma-sft-african-ultrachat-200k-GGUF: Same weights, converted

On the Hub · Downloads on Model Pulse