Ron's picture

5 8 41

Ron PRO

ronedgecomb

·

AI & ML interests

Motion & Graphic Designer | Developer

Recent Activity

reacted to codelion's post with 🔥 3 days 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 4 days ago

nvidia/NVIDIA-Nemotron-Nano-12B-v2

reacted to ginipick's post with 🔥 4 days ago

🍌 Nano Banana + Video: AI Image Style Transfer & Video Generation Tool 🎨 Key Features 1️⃣ Image Style Transfer https://huggingface.co/spaces/ginigen/Nano-Banana-Video 📸 Upload up to 2 images for style fusion ✨ High-quality image generation with Google Nano Banana model 🎭 Apply desired styles with text prompts 2️⃣ Video Generation 🎬 Convert generated images to videos 📐 Maintain original aspect ratio option ⏱️ Adjustable duration (1-4 seconds) 🚀 How to Use Step-by-Step Guide Step 1: Image Generation 🖼️ Enter style description Upload 1-2 images (optional) Click "Generate Magic ✨" Step 2: Video Creation 📹 Send generated image to video tab Set animation style Generate video! 💡 Use Cases 🏞️ Transform landscape photos into artistic masterpieces 🤖 Bring static images to life 🎨 Mix styles from two different images 📱 Create short videos for social media ⚡ Tech Stack Google Nano Banana Stable Video Diffusion Gradio Replicate API #AIVideoGenerator #ImageToVideoConverter #StyleTransferAI #GoogleNanoBanana #StableVideoDiffusion #AIAnimationTool #TextToVideo #ImageAnimationSoftware #AIArtGenerator #VideoCreationTool #MachineLearningVideo #DeepLearningAnimation #HuggingFaceSpaces #ReplicateAPI #GradioApplication #ZeroGPUComputing #AIStyleMixing #AutomatedVideoProduction #NeuralStyleTransfer #AIPoweredCreativity

View all activity

Organizations

None yet

ronedgecomb 's datasets

None public yet