Gille/StrangeMerges_21-7B-slerp
Full fine-tune vs Gille/StrangeMerges_20-7B-slerp. Fine-tune: 100% of the weights changed, across 32 of 32 layers.
Tensors changed: lm_head 1/1, Embeddings 1/1, Norms 43/65, MLP 96/96, Attention 128/128
6 derivatives checked
- mradermacher/StrangeMerges_21-7B-slerp-GGUF: Same weights, converted
- nlpguy/AlloyIngot: Full fine-tune
- Gille/StrangeMerges_30-7B-slerp: Full fine-tune
- Gille/StrangeMerges_43-7B-dare_ties: Full fine-tune
- Gille/StrangeMerges_38-7B-dare_ties: Full fine-tune
- Kukedlc/Neural-4-ARC-7b: Full fine-tune