HuggingFaceH4/zephyr-7b-gemma-v0.1

Full fine-tune vs HuggingFaceH4/zephyr-7b-gemma-sft-v0.1. Fine-tune: 100% of the weights changed, across 28 of 28 layers.

Tensors changed: Embeddings 1/1, Norms 25/57, MLP 84/84, Attention 112/112

1 derivatives checked

• MaziyarPanahi/zephyr-7b-gemma-v0.1-GGUF: Quantization

On the Hub · Downloads on Model Pulse