Hugging Face
Search models, datasets, users...
Ctrl K
Models
Datasets
Spaces
Buckets
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
35.6
TFLOPS
Nick Perez
nkpz
6
52
Follow
BlueNipples's profile picture
blahblahhi's profile picture
MatthewK's profile picture
41 followers
·
10 following
AI & ML interests
Open source LLM stuff.
Recent Activity
liked
a model
about 1 month ago
Sourajit123/SouraTTS
reacted
to
codelion
's
post
with ❤️
about 1 year ago
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 - https://huggingface.co/codelion/Llama-3.2-1B-Instruct-tool-calling-lora - GitHub - https://github.com/codelion/ellora
liked
a model
over 1 year ago
Edens-Gate/Humanize-Rei-Slerp
View all activity
Organizations
None yet
nkpz
's models
36
Sort: Recently updated
nkpz/WizardLM-13B-V1.1-gptq-32g
Text Generation
•
Updated
Jul 7, 2023
•
10
nkpz/bayling-13b-v1.1-gptq-32g
Text Generation
•
Updated
Jul 6, 2023
•
5
nkpz/Lawyer-Vicuna-200-gptq-32g
Text Generation
•
Updated
Jul 6, 2023
•
9
•
1
nkpz/serena-safe-gptq
Text Generation
•
Updated
Jul 6, 2023
•
8
nkpz/open_llama_7b_qlora_uncensored-gptq
Text Generation
•
Updated
Jul 6, 2023
•
12
•
1
nkpz/kw-cutegpt-13b-ift-gptq
Text Generation
•
Updated
Jul 5, 2023
•
5
Previous
1
2
Next