BSC-LT/ALIA-40b-instruct-2601
Full fine-tune vs BSC-LT/ALIA-40b. Fine-tune: 100% of the weights changed, across 48 of 48 layers.
Tensors changed: Embeddings 1/1, MLP 144/144, Attention 192/192, Norms 97/97, lm_head 1/1
4 derivatives checked
- mradermacher/ALIA-40b-instruct-2601-i1-GGUF: Quantization
- mradermacher/ALIA-40b-instruct-2601-GGUF: Quantization
- KikoCis/ALIA-40b-instruct-2601-GGUF: Quantization
- KaraKaraWitch/ALIA-40b-instruct-2601-ara-heretic: Abliterated