Spaces:
Sleeping
Sleeping
Commit History
-
Refine GRPO evaluation details and clarify model performance comparisons in Blog.md
83f7214 -
Revise reasoning for choosing SFT + agentic loop over SFT + GRPO in deployment documentation
94c19b9 -
Remove placeholder for YouTube demo link in README.md
1ddc10a -
Update README.md to correct title and enhance color scheme, app configuration, and metadata
b8672db -
Add initial blog post detailing ArchitectureEnv and its design approach
29c929e -
Add front matter to README.md for enhanced metadata and project visibility
1cbc836 -
Update README.md for improved clarity and structure, including quick start instructions and enhanced project description.
26e1800 -
Add analysis of SFT vs GRPO performance and rationale for model selection
c7bd5c9 -
Remove outdated inference reward curve plot and add new loss and reward curve plots for improved analysis.
ebba8ad
-
Add inference reward curve plot
fa5f65c -
Update LocalModelClient initialization to use MODEL_REPO_ID instead of MODEL_DIR
1c83fd8 -
Update README.md with installation instructions and modify agentic_inference.py to print MODEL_REPO_ID instead of MODEL_DIR
0ede54d -
updated inference to use the model deployed on sft
842a4f8 -
moved app.py to fix the runtime error
157160f -
Add scripts for supervised fine-tuning and GRPO training
- Created `make_sft_dataset.py` to generate a supervised fine-tuning dataset from expert plans. - Implemented `train_sft.py` for supervised fine-tuning of the model using the generated dataset. - Developed `train_grpo.py` to train the model using GRPO starting from the SFT checkpoint, including fresh trainable LoRA parameters.adcad94 -
round2: inference and planner critic design
786f4c0
-
Update inference.py
Verified signature7d3618b -
Update inference.py
Verified signature68aae9a -
Update inference.py
Verified signature09b98c3 -
Update inference.py
Verified signature3798f67 -
Update inference.py
Verified signaturefab8166 -
Update inference.py
Verified signature4f94384 -
Update inference.py
Verified signature4d83ca3 -
Update inference.py
Verified signatureb0775a5
-
Refactor code structure for improved readability and maintainability
19e79af -
Add metadata section to README.md for project details
2eacea9
-
Revise README.md for clarity and structure; update benchmark description and task details
7731b28 -
Simplify main function by removing host and port arguments in app.py
d932af4 -
add uv lock
1656de8 -
Update error handling for missing HF_TOKEN in inference.py
5d3f541 -
Refactor requirements file structure
401a2d6 -
Update inference.py
Verified signatureb4230bf -
Fixed architecture step function
Verified signatureabc93f5 -
Update models.py
Verified signatureFixed the model configc3112a9 -
Update README.md
Verified signature77fcd5f -
Update server/app.py
Verified signaturereverted app server config27202c4 -
Update Dockerfile
Verified signaturereverted docker changesb746fc2 -
Updated docker server config
Verified signature2e4fc24 -
Update server/app.py
Verified signatureUpdated server configbd60fcd -
Update openenv.yaml
Verified signatureadded base bath to deployment config6a2868c -
Fixed deployment bugs
Verified signature2c87f99 -
Upload Dockerfile
Verified signatureCreated dockerfilefc66ab6 -
Delete server/Dockerfile
Verified signatureRemving docker5a8383f -
Upload 4 files
Verified signatureconfigured docker and env files3544a3b -
Create server/app.py
Verified signaturecreated app.py9c2e75a -
Delete server
Verified signature82ff700 -
Create server/
Verified signaturecb5582a -
Upload 11 files
Verified signatureInitial commit41da5bf -
initial commit
Verified signature859f7f9