Averroes-7B-v1 API & Inference Endpoint

Overview

Averroes-7B-v1 is the original fine-tuned Arabic-English model built on Qwen2.5-7B-Instruct. It was the first iteration trained on the full 1.3M Arabic instruction corpus.

Table with columns: Detail, Value
Detail	Value
Base model	Qwen/Qwen2.5-7B-Instruct
Training data	1.3M Arabic instruction pairs (full corpus)
Training duration	~50 hours on M2 Ultra
License	Apache 2.0

🏆 Current Champion

For better performance and faster inference, use Averroes-v1.5-fused:

→ hayulalab/averroes-v2-instruct-v1.5-fused

Improvements over v1:

✅ +30% English HumanEval (86.7% vs 56.7%)
✅ +15.2% Arabic HumanEval (46.9% vs 31.7%)
✅ 3.4× faster inference on Apple Silicon
✅ GGUF quantizations available (Q4_K_M, Q8_0, FP16)
✅ Clean model card with full benchmarks

Overview

Averroes-7B-v1 is the original fine-tuned Arabic-English model built on Qwen2.5-7B-Instruct. It was the first iteration trained on the full 1.3M Arabic instruction corpus.

Table with columns: Detail, Value
Detail	Value
Base model	Qwen/Qwen2.5-7B-Instruct
Training data	1.3M Arabic instruction pairs (full corpus)
Training duration	~50 hours on M2 Ultra
License	Apache 2.0

🏆 Current Champion

For better performance and faster inference, use Averroes-v1.5-fused:

→ hayulalab/averroes-v2-instruct-v1.5-fused

Improvements over v1:

✅ +30% English HumanEval (86.7% vs 56.7%)
✅ +15.2% Arabic HumanEval (46.9% vs 31.7%)
✅ 3.4× faster inference on Apple Silicon
✅ GGUF quantizations available (Q4_K_M, Q8_0, FP16)
✅ Clean model card with full benchmarks

Averroes-7B-v1

README

Overview

🏆 Current Champion

Links

Explore FriendliAI today

README

Overview

🏆 Current Champion

Links