QCRI/Fanar-1-9B-Instruct
Full fine-tune vs QCRI/Fanar-1-9B. Fine-tune: 100% of the weights changed, across 42 of 42 layers.
Tensors changed: Embeddings 1/1, Norms 122/169, MLP 126/126, Attention 168/168
5 derivatives checked
- mradermacher/Fanar-1-9B-Instruct-GGUF: Same weights, converted
- mradermacher/Fanar-1-9B-Instruct-i1-GGUF: Quantization
- yasserrmd/Fanar-1-9B-Instruct-gguf: Same weights, converted
- hammh0a/Hala-9B: Full fine-tune
- hunzed/Fanar-1-9B-Instruct-PalmX-Culture: LoRA-style
1 other repos hold byte-for-byte identical weight files.