Spaces:

Siddeshwar1625
/

OSINT

Paused

App Files Files Community

OSINT / datasets /fixed_levels

Ctrl+K

Ctrl+K

2 contributors

History: 1 commit

siddeshwar-kagatikar

fix(rewards): never crash GRPO on malformed completions

d814291 13 days ago

README.md

2.41 kB
fix(rewards): never crash GRPO on malformed completions 13 days ago
complete_dataset_qwen_generated.json

215 kB
fix(rewards): never crash GRPO on malformed completions 13 days ago
fixed_graph_questions.json

175 kB
fix(rewards): never crash GRPO on malformed completions 13 days ago
leaderboard_fixed_levels.json

45.9 kB
fix(rewards): never crash GRPO on malformed completions 13 days ago
qwen_swarm_benchmark_fixed_levels.json

2.5 kB
fix(rewards): never crash GRPO on malformed completions 13 days ago
qwen_swarm_eval_by_difficulty.json

1.62 kB
fix(rewards): never crash GRPO on malformed completions 13 days ago
qwen_swarm_eval_fixed_levels.json

952 Bytes
fix(rewards): never crash GRPO on malformed completions 13 days ago
seed_fixed_levels.json

184 kB
fix(rewards): never crash GRPO on malformed completions 13 days ago
shared_config_fixed_levels.json

1.68 kB
fix(rewards): never crash GRPO on malformed completions 13 days ago