gplsi/Aitana-7B-S-base
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
5 derivatives checked
- mradermacher/Aitana-7B-S-base-i1-GGUF: Quantization
- mradermacher/Aitana-7B-S-base-1.0-i1-GGUF: Quantization
- mradermacher/Aitana-7B-S-base-GGUF: Same weights, converted
- mradermacher/Aitana-7B-S-base-1.0-GGUF: Same weights, converted
- gplsi/Aitana-7B-S-Instruct: Partial fine-tune