jena-shreyas/gemma-2-2b-it-sft-dare

Full fine-tune vs google/gemma-2-2b-it. Fine-tune: 100% of the weights changed, across 26 of 26 layers.

Tensors changed: Embeddings 1/1, Norms 89/105, MLP 78/78, Attention 104/104

2 derivatives checked

• featherless-ai-quants/jena-shreyas-gemma-2-2b-it-sft-dare-GGUF: Quantization
• mradermacher/gemma-2-2b-it-sft-dare-GGUF: Same weights, converted

On the Hub · Downloads on Model Pulse