Gabriel Bo's picture

1 2

Gabriel Bo PRO

gabrielbo

·

https://www.gabrielbo.com/

AI & ML interests

NLP, Scaling, Test-time Compute

Recent Activity

updated a dataset about 6 hours ago

gabrielbo/parser-bench

published a dataset 14 days ago

gabrielbo/parser-bench

updated a collection 10 months ago

View all activity

Organizations

updated a dataset about 6 hours ago

gabrielbo/parser-bench

Viewer • Updated about 6 hours ago • 590 • 96

published a dataset 14 days ago

gabrielbo/parser-bench

Viewer • Updated about 6 hours ago • 590 • 96

updated a collection 10 months ago

SmartRouter

data generated to train SmartRouter and for routing benchmark • 2 items • Updated Mar 2

liked a dataset 10 months ago

gabrielbo/swirl-trajectories-mmlu-pro

Viewer • Updated May 20, 2025 • 24.8k • 22 • 2

liked a model 10 months ago

gabrielbo/spark-model-QLoRA

Text Generation • Updated May 24, 2025 • 1

upvoted a collection 11 months ago

SPaRK-RL

combines reinforcement learning (RL) and large language models (LLMs) to improve exploration using diverse tool generation during inference • 3 items • Updated Jun 17, 2025 • 1

updated 2 collections 11 months ago

SPaRK-RL

combines reinforcement learning (RL) and large language models (LLMs) to improve exploration using diverse tool generation during inference • 3 items • Updated Jun 17, 2025 • 1

SmartRouter

data generated to train SmartRouter and for routing benchmark • 2 items • Updated Mar 2

updated a model 11 months ago

gabrielbo/spark-model-QLoRA

Text Generation • Updated May 24, 2025 • 1

published a model 11 months ago

gabrielbo/spark-model-QLoRA

Text Generation • Updated May 24, 2025 • 1

updated a dataset 11 months ago

gabrielbo/swirl-trajectories-mmlu-pro

Viewer • Updated May 20, 2025 • 24.8k • 22 • 2

updated a collection 11 months ago

SPaRK-RL

combines reinforcement learning (RL) and large language models (LLMs) to improve exploration using diverse tool generation during inference • 3 items • Updated Jun 17, 2025 • 1

published 2 datasets 11 months ago

gabrielbo/swirl-trajectories-mmlu-pro

Viewer • Updated May 20, 2025 • 24.8k • 22 • 2

gabrielbo/explore-rl-hotpota-trajectories

Updated May 9, 2025 • 6

updated a collection 12 months ago

SPaRK-RL

combines reinforcement learning (RL) and large language models (LLMs) to improve exploration using diverse tool generation during inference • 3 items • Updated Jun 17, 2025 • 1

updated 2 datasets 12 months ago

gabrielbo/gpqa-llama-3-8b-verifier

Viewer • Updated May 9, 2025 • 910 • 228

gabrielbo/mmlu-college-llama-3-8b-verifiers

Viewer • Updated May 8, 2025 • 870 • 4

published a dataset 12 months ago

gabrielbo/gpqa-llama-3-8b-verifier

Viewer • Updated May 9, 2025 • 910 • 228