BSC-LT/salamandraTA-7b-instruct
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/salamandraTA-7b-instruct-GGUF: Full fine-tune
- BSC-LT/salamandraTA-7B-instruct-GGUF: Quantization
- BSC-LT/salamandra-TAV-7b: Full fine-tune
- egekocabas/salamandraTA-7b-instruct-Q4_K_M-GGUF: Quantization