Spaces:

md896
/

sql-debug-env

Running

App Files Files Community

sql-debug-env

441 kB

Ctrl+K

1 contributor

History: 63 commits

md896

Harden GRPO generation stability on CUDA: bf16 + eager attention + invalid-logit guards.

948530a about 1 month ago

archive
Fix: Mock vllm and llm_blender to stabilize GRPOTrainer in HF Jobs environment about 1 month ago
docs
Fix: Mock vllm and llm_blender to stabilize GRPOTrainer in HF Jobs environment about 1 month ago
scripts
Initial OpenEnv SQL debug environment about 2 months ago
server
Make OpenEnv training+API judge-proof about 1 month ago
skills
Fix: Mock vllm and llm_blender to stabilize GRPOTrainer in HF Jobs environment about 1 month ago
tests
Make OpenEnv training+API judge-proof about 1 month ago
.dockerignore

130 Bytes
Initial OpenEnv SQL debug environment about 2 months ago
.env.example

124 Bytes
Initial OpenEnv SQL debug environment about 2 months ago
.gitattributes

1.52 kB
initial commit about 2 months ago
.gitignore

411 Bytes
Make OpenEnv training+API judge-proof about 1 month ago
Dockerfile

762 Bytes
Initial OpenEnv SQL debug environment about 2 months ago
README.md

6.34 kB
Make OpenEnv training+API judge-proof about 1 month ago
colab_pro_training.py

7.3 kB
Deploy: SOTA RL Cartesian Task and Unsloth Scripts about 1 month ago
colab_real_world.py

3.88 kB
Fix: Mock vllm and llm_blender to stabilize GRPOTrainer in HF Jobs environment about 1 month ago
inference.py

9.6 kB
Make OpenEnv training+API judge-proof about 1 month ago
launch_job.py

3.18 kB
Fix GRPO batch/generation mismatch: auto-adjust num_generations; set launcher default to 2. about 1 month ago
openenv.yaml

3.11 kB
Make OpenEnv training+API judge-proof about 1 month ago
presentation_graphs.py

3.75 kB
Deploy: SOTA RL Cartesian Task and Unsloth Scripts about 1 month ago
pyproject.toml

428 Bytes
Deploy: SOTA RL Cartesian Task and Unsloth Scripts about 1 month ago
requirements.txt

132 Bytes
Deploy: SOTA RL Cartesian Task and Unsloth Scripts about 1 month ago
spider_chart.py

1.37 kB
Deploy: SOTA RL Cartesian Task and Unsloth Scripts about 1 month ago
ultimate_benchmark.py

3.32 kB
Deploy: SOTA RL Cartesian Task and Unsloth Scripts about 1 month ago
ultimate_sota_training.py

19.3 kB
Harden GRPO generation stability on CUDA: bf16 + eager attention + invalid-logit guards. about 1 month ago
uv.lock

237 kB
Initial OpenEnv SQL debug environment about 2 months ago