FANAR-9B
A 9B-parameter Arabic large language model, reportedly developed by a Saudi-related institution, intended for Arabic natural language processing tasks.
Timeline (last 90 days)
The Qwen2.5-7B student model distilled from FANAR achieved 76.6% accuracy in context-free evaluation, compared with 77.2% for the teacher model.
The study examined the performance of three stages—domain adaptation, quantization, and knowledge distillation—on three models: FANAR-9B, JAIS-8B, and Qwen2.5-7B.
All Facts (2)
The Qwen2.5-7B student model distilled from FANAR achieved 76.6% accuracy in context-free evaluation, compared with 77.2% for the teacher model.
50%UnverifiedThe study examined the performance of three stages—domain adaptation, quantization, and knowledge distillation—on three models: FANAR-9B, JAIS-8B, and Qwen2.5-7B.
50%