recoilme/recoilme-gemma-2-9B-v0.5

Full fine-tune vs TheDrummer/Gemmasutra-9B-v1. Fine-tune: 98% of the weights changed, across 42 of 42 layers.

Tensors changed: lm_head 1/1, Embeddings 1/1, Norms 105/169, MLP 123/126, Attention 164/168

2 derivatives checked

• mradermacher/recoilme-gemma-2-9B-v0.5-i1-GGUF: Quantization
• mradermacher/recoilme-gemma-2-9B-v0.5-GGUF: Same weights, converted

On the Hub · Downloads on Model Pulse