Spaces:

raj23211
/

support-ops-env

Paused

App Files Files Community

support-ops-env

Ctrl+K

Ctrl+K

2 contributors

History: 63 commits

raj921

Align train_reward_chart with v2 reward_log CSV; allow Python 3.10.

e6809d9 2 months ago

algofesast
chore: add initial Next.js scaffold for algofesast 3 months ago
docs
Docs: align with Hugging Face Hub + TRL official guides 2 months ago
kernels
Split train and tool simulator modules; mastery curriculum and grader workflow nudge. 2 months ago
scripts
Split train and tool simulator modules; mastery curriculum and grader workflow nudge. 2 months ago
server
Split train and tool simulator modules; mastery curriculum and grader workflow nudge. 2 months ago
tests
Split train and tool simulator modules; mastery curriculum and grader workflow nudge. 2 months ago
.dockerignore
35 Bytes
clean rewrite: shorter vars, no comments, same logic 3 months ago
.gitattributes
415 Bytes
Docs: align with Hugging Face Hub + TRL official guides 2 months ago
.gitignore
159 Bytes
Add DriftShield proof artifacts and generator script 2 months ago
.pre-commit-config.yaml
328 Bytes
clean rewrite: shorter vars, no comments, same logic 3 months ago
CONTRIBUTING.md
637 Bytes
clean rewrite: shorter vars, no comments, same logic 3 months ago
Dockerfile
524 Bytes
clean rewrite: shorter vars, no comments, same logic 3 months ago
README.md
9.74 kB
Fix Colab/Kaggle: install fastmcp after --no-deps openenv (import support_ops_env). 2 months ago
__init__.py
4.01 kB
Split train and tool simulator modules; mastery curriculum and grader workflow nudge. 2 months ago
audit.py
17.7 kB
feat: default GRPO/eval to Qwen/Qwen3-1.7B + LoRA; disable Qwen3 thinking in chat template 2 months ago
before_after_prompt_injection.md
1.24 kB
Add DriftShield proof artifacts and generator script 2 months ago
client.py
933 Bytes
clean rewrite: shorter vars, no comments, same logic 3 months ago
driftshield_colab.ipynb
34.8 kB
Align train_reward_chart with v2 reward_log CSV; allow Python 3.10. 2 months ago
driftshield_colab_gemma4.ipynb
17.8 kB
Fix OpenEnv and HF training flows 2 months ago
driftshield_kaggle.ipynb
33.3 kB
Fix Colab/Kaggle: install fastmcp after --no-deps openenv (import support_ops_env). 2 months ago
eval_compare.md
1.32 kB
feat: default GRPO/eval to Qwen/Qwen3-1.7B + LoRA; disable Qwen3 thinking in chat template 2 months ago
eval_compare.py
18.3 kB
Split train and tool simulator modules; mastery curriculum and grader workflow nudge. 2 months ago
graders.py
20.8 kB
Split train and tool simulator modules; mastery curriculum and grader workflow nudge. 2 months ago
inference.py
19.8 kB
Split train and tool simulator modules; mastery curriculum and grader workflow nudge. 2 months ago
models.py
6.53 kB
Fix notebook package refresh and training runtime 2 months ago
openenv.yaml
98 Bytes
clean rewrite: shorter vars, no comments, same logic 3 months ago
plot_rewards.py
12 kB
fix: T4-safe 4bit compute, eval/audit resilience, async inference, plot_rewards CSV/table 2 months ago
pyproject.toml
2.68 kB
Align train_reward_chart with v2 reward_log CSV; allow Python 3.10. 2 months ago
tasks.py
30.1 kB
Split train and tool simulator modules; mastery curriculum and grader workflow nudge. 2 months ago
train.py
14.1 kB
Split train and tool simulator modules; mastery curriculum and grader workflow nudge. 2 months ago
train_action_json.py
2.85 kB
Split train and tool simulator modules; mastery curriculum and grader workflow nudge. 2 months ago
train_gemma4.py
25.3 kB
Fix OpenEnv and HF training flows 2 months ago
train_obs_format.py
6.24 kB
Split train and tool simulator modules; mastery curriculum and grader workflow nudge. 2 months ago
train_reward_chart.py
3.4 kB
Align train_reward_chart with v2 reward_log CSV; allow Python 3.10. 2 months ago
train_reward_signal.py
2.17 kB
Split train and tool simulator modules; mastery curriculum and grader workflow nudge. 2 months ago
train_rollout_episode.py
7.74 kB
Split train and tool simulator modules; mastery curriculum and grader workflow nudge. 2 months ago
train_system_prompt.py
4.63 kB
Split train and tool simulator modules; mastery curriculum and grader workflow nudge. 2 months ago
train_tool_bonuses.py
735 Bytes
Split train and tool simulator modules; mastery curriculum and grader workflow nudge. 2 months ago
train_vllm_compat.py
2.09 kB
Split train and tool simulator modules; mastery curriculum and grader workflow nudge. 2 months ago
uv.lock
462 kB
clean rewrite: shorter vars, no comments, same logic 3 months ago