BSC-LT/salamandra-2b-instruct-aina-hack

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

1 derivatives checked

• mradermacher/salamandra-2b-instruct-aina-hack-GGUF: Same weights, converted

On the Hub · Downloads on Model Pulse