BSC-LT/salamandraTA-2b-instruct
Full fine-tune vs BSC-LT/salamandra-2b. Fine-tune: 100% of the weights changed, across 24 of 24 layers.
Tensors changed: lm_head 1/1, Embeddings 1/1, Norms 49/49, MLP 72/72, Attention 96/96
4 derivatives checked
- mradermacher/salamandraTA-2b-instruct-i1-GGUF: Quantization
- mradermacher/salamandraTA-2b-instruct-GGUF: Same weights, converted
- BSC-LT/salamandraTA-2B-instruct-GGUF: Quantization
- gplsi/Aitana-TA-2B-S: Partial fine-tune