Hugging Face
Models
Datasets
Spaces
Buckets
new
Docs
Enterprise
Pricing
Website
Tasks
HuggingChat
Collections
Languages
Organizations
Community
Blog
Posts
Daily Papers
Hardware
Learn
Discord
Forum
GitHub
Solutions
Team & Enterprise
Hugging Face PRO
Enterprise Support
Inference Providers
Inference Endpoints
Storage Buckets
Log In
Sign Up
hard007ik
/
shopmanager-train-code
like
0
openenv
Model card
Files
Files and versions
xet
Community
Copy to bucket
new
8464e70
shopmanager-train-code
134 kB
Ctrl+K
Ctrl+K
3 contributors
History:
18 commits
hard007ik
pin vllm<=0.18.0 to fix TRL importance-sampling ratio collapse
8464e70
4 months ago
server
shop manage eng phase 2 first
4 months ago
training
Add GRPO training scaffolding (Module 5 rollout_func pattern) + plot artifacts
4 months ago
.gitignore
Safe
64 Bytes
shop manage eng phase 2 first
4 months ago
.hfignore
Safe
887 Bytes
Add GRPO training scaffolding (Module 5 rollout_func pattern) + plot artifacts
4 months ago
LICENSE
Safe
1.07 kB
Add LICENSE file
5 months ago
README.md
5.19 kB
feat: jewelry shop RL environment with market, warehouse, and showroom phases
5 months ago
__init__.py
Safe
432 Bytes
shop manage eng phase 2 first
4 months ago
client.py
Safe
7.3 kB
shop manage eng phase 2 first
4 months ago
constants.py
Safe
949 Bytes
shop manage eng phase 2 first
4 months ago
inference.py
15.2 kB
shop manage eng phase 2 first
4 months ago
models.py
Safe
6.88 kB
shop manage eng phase 2 first
4 months ago
openenv.yaml
Safe
1.31 kB
shop manage eng phase 2 first
4 months ago
pyproject.toml
2.03 kB
pin vllm<=0.18.0 to fix TRL importance-sampling ratio collapse
4 months ago
rollout_baseline.py
Safe
4.94 kB
shop manage eng phase 2 first
4 months ago
test_env_smoke.py
Safe
4.3 kB
shop manage eng phase 2 first
4 months ago
train_jewelry_grpo.py
12.8 kB
Drop max_prompt_length from GRPOConfig (removed in newer TRL)
4 months ago
