NeuralNovel/Gecko-7B-v0.1-DPO

Full fine-tune vs NeuralNovel/Gecko-7B-v0.1. Fine-tune: 100% of the weights changed, across 32 of 32 layers.

Tensors changed: Embeddings 1/1, Norms 13/65, MLP 96/96, Attention 128/128, lm_head 1/1

3 derivatives checked

• mradermacher/Gecko-7B-v0.1-DPO-GGUF: Same weights, converted
• mradermacher/Gecko-7B-v0.1-DPO-i1-GGUF: Quantization
• NeuralNovel/Tiger-7B-v0.1: Full fine-tune

On the Hub · Downloads on Model Pulse