Gille/StrangeMerges_37-7B-dare_ties

Full fine-tune vs ContextualAI/Contextual_KTO_Mistral_PairRM. Fine-tune: 100% of the weights changed, across 32 of 32 layers.

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

1 derivatives checked

• mradermacher/StrangeMerges_37-7B-dare_ties-GGUF: Same weights, converted

On the Hub · Downloads on Model Pulse