Gille/StrangeMerges_45-7B-dare_ties

Full fine-tune vs EmbeddedLLM/Mistral-7B-Merge-14-v0.2. 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

2 derivatives checked

• mradermacher/StrangeMerges_45-7B-dare_ties-GGUF: Same weights, converted
• Gille/StrangeMerges_46-7B-dare_ties: Full fine-tune

On the Hub · Downloads on Model Pulse