BSC-LT/salamandra-7b-instruct-2606
Full fine-tune vs BSC-LT/salamandra-7b. 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
4 derivatives checked
- mradermacher/salamandra-7b-instruct-2606-i1-GGUF: Quantization
- mradermacher/salamandra-7b-instruct-2606-GGUF: Same weights, converted
- KikoCis/salamandra-7b-instruct-2606-GGUF: Quantization
- jordimas/salamandra-7b-instruct-2606-GGUF: Same weights, converted