🏗️ Building on HF

Muhammad Awais

drawais

·

https://huggingface.co/datasets/drawais/needle-1M-bench-mvp

AI & ML interests

Needle-1M-bench: a long-context faithfulness benchmark on real arxiv papers. Centralized scoring.

Organizations

None yet

drawais 's datasets 8

drawais/needle-1M-bench-mvp

Updated Apr 30 • 54

drawais/dsr1-distill-qwen-7b-calibration-v1

Viewer • Updated Apr 28 • 256 • 14

drawais/qwen2.5-math-7b-calibration-v1

Viewer • Updated Apr 28 • 256 • 21

drawais/qwen2.5-coder-14b-calibration-v1

Viewer • Updated Apr 28 • 256 • 17

drawais/qwen3-4b-calibration-v1

Viewer • Updated Apr 28 • 256 • 15

drawais/qwen3-8b-calibration-v1

Viewer • Updated Apr 28 • 256 • 15

drawais/qwen3-32b-calibration-v1

Viewer • Updated Apr 28 • 256 • 21

drawais/qwen3-14b-calibration-v1

Viewer • Updated Apr 28 • 256 • 20