8 11 59

Alexandru Lupoi

drwlf

AI & ML interests

AI in Health Agents for health and personal wellbeing

Recent Activity

liked a model about 12 hours ago

internlm/Intern-S1

updated a collection 1 day ago

Medical Data

liked a model 1 day ago

mradermacher/med-gpt-oss-20b-GGUF

View all activity

Organizations

liked a model about 12 hours ago

internlm/Intern-S1

Image-Text-to-Text • 241B • Updated 4 days ago • 63.8k • 237

updated a collection 1 day ago

Medical Data

Collection

32 items • Updated 1 day ago • 1

liked a model 1 day ago

mradermacher/med-gpt-oss-20b-GGUF

Text Generation • 21B • Updated 17 days ago • 3.4k • 2

reacted to codelion's post with 🔥 3 days ago

Post

5882

I recently worked on a LoRA that improves tool use in LLM. Thought the approach might interest folks here.

The issue I have had when trying to use some of the local LLMs with coding agents is this:

Me: "Find all API endpoints with authentication in this codebase"
LLM: "You should look for @app .route decorators and check if they have auth middleware..."

But I often want it to search the files and show me but the LLM doesn't trigger a tool use call.

To fine-tune it for tool use I combined two data sources:

1. Magpie scenarios - 5000+ diverse tasks (bug hunting, refactoring, security audits)
2. Real execution - Ran these on actual repos (FastAPI, Django, React) to get authentic tool responses

This ensures the model learns both breadth (many scenarios) and depth (real tool behavior).

Tools We Taught:
- read_file - Actually read file contents
- search_files - Regex/pattern search across codebases
- find_definition - Locate classes/functions
- analyze_imports - Dependency tracking
- list_directory - Explore structure
- run_tests - Execute test suites

Improvements:
- Tool calling accuracy: 12% → 80%
- Correct parameters: 8% → 87%
- Multi-step tasks: 3% → 78%
- End-to-end completion: 5% → 80%
- Tools per task: 0.2 → 3.8

The LoRA really improves on intential tool call as an example consider the query: "Find ValueError in payment module"

The response proceeds as follows:

1. Calls search_files with pattern "ValueError"
2. Gets 4 matches across 3 files
3. Calls read_file on each match
4. Analyzes context
5. Reports: "Found 3 ValueError instances: payment/processor.py:47 for invalid amount, payment/validator.py:23 for unsupported currency..."

Resources:
- Colab notebook https://colab.research.google.com/github/codelion/ellora/blob/main/Ellora_Recipe_3_Enhanced_Tool_Calling_and_Code_Understanding.ipynb
- Model - codelion/Llama-3.2-1B-Instruct-tool-calling-lora
- GitHub - https://github.com/codelion/ellora