Hugging Face
Models
Datasets
Spaces
Buckets
new
Docs
Enterprise
Pricing
Website
Tasks
HuggingChat
Collections
Languages
Organizations
Community
Blog
Posts
Daily Papers
Learn
Discord
Forum
GitHub
Solutions
Team & Enterprise
Hugging Face PRO
Enterprise Support
Inference Providers
Inference Endpoints
Storage Buckets
Log In
Sign Up
Abhisek Behera
PRO
Abhisek987
Follow
AI & ML interests
None yet
Recent Activity
replied
to
their
post
2 days ago
Every Python developer has hit this: you upgrade numpy or pandas, and code that worked yesterday breaks today. I built an open dataset for exactly this problem. DepDoctor is 6,204 examples of Python code broken by a dependency upgrade, each paired with the fix and a short note on the API change that caused it. It is a mixture of real cases mined from public GitHub commits and synthetic cases generated from a database of known breaking changes. A few things I tried to get right: - 935 "leave it alone" examples, to teach a model restraint, not just what to change. - Honest evaluation: a fine-tuned Qwen2.5-Coder-7B gets 62% of fixes fully correct. I report that, not just the 97% text-similarity score that hides the truth. - The main failure mode, over-editing, is measured and explained rather than buried. Dataset, fine-tuned model, and a live demo are all open in one place: https://huggingface.co/collections/Abhisek987/depdoctor Feedback welcome, especially from anyone working on code repair or API migration.
posted
an
update
3 days ago
Every Python developer has hit this: you upgrade numpy or pandas, and code that worked yesterday breaks today. I built an open dataset for exactly this problem. DepDoctor is 6,204 examples of Python code broken by a dependency upgrade, each paired with the fix and a short note on the API change that caused it. It is a mixture of real cases mined from public GitHub commits and synthetic cases generated from a database of known breaking changes. A few things I tried to get right: - 935 "leave it alone" examples, to teach a model restraint, not just what to change. - Honest evaluation: a fine-tuned Qwen2.5-Coder-7B gets 62% of fixes fully correct. I report that, not just the 97% text-similarity score that hides the truth. - The main failure mode, over-editing, is measured and explained rather than buried. Dataset, fine-tuned model, and a live demo are all open in one place: https://huggingface.co/collections/Abhisek987/depdoctor Feedback welcome, especially from anyone working on code repair or API migration.
updated
a dataset
3 days ago
Abhisek987/depdoctor-dataset
View all activity
Organizations
None yet
Abhisek987
's models
7
Sort:Â Recently updated
Abhisek987/depdoctor-v5-lora
Text Generation
•
Updated
3 days ago
•
38
Abhisek987/depdoctor-v4-lora
Text Generation
•
Updated
19 days ago
•
13
Abhisek987/phi35-vision-pdf-markdown
Text Generation
•
Updated
Mar 4
•
6
Abhisek987/llama-test-3.2-sql-merged
Text Generation
•
3B
•
Updated
Oct 29, 2025
•
3
Abhisek987/llama-test-3.2-sql-lora
Updated
Oct 29, 2025
Abhisek987/llama-3.2-sql-merged
Text Generation
•
3B
•
Updated
Oct 25, 2025
•
9
•
1
Abhisek987/llama-3.2-sql-lora
Text Generation
•
Updated
Oct 25, 2025