3 28

ares

ares2324

AI & ML interests

None yet

Recent Activity

liked a model about 22 hours ago

RuneXX/LTX-2-Workflows

liked a model about 23 hours ago

Alissonerdx/BFS-Best-Face-Swap

liked a model 2 days ago

dx8152/Qwen-Image-Edit-2511-Gaussian-Splash

View all activity

Organizations

None yet

liked a model about 22 hours ago

RuneXX/LTX-2-Workflows

Updated about 4 hours ago • 48

liked a model about 23 hours ago

Alissonerdx/BFS-Best-Face-Swap

Image-to-Image • Updated 1 day ago • 7.38k • 154

liked a model 2 days ago

dx8152/Qwen-Image-Edit-2511-Gaussian-Splash

Image-to-Image • Updated about 6 hours ago • • 127

liked 2 models 4 days ago

Danrisi/Lenovo_Qwen

Text-to-Image • Updated Oct 24, 2025 • 3.59k • • 28

Danrisi/adorablegirls_qwen

Updated Aug 11, 2025 • 23

reacted to sagar007's post with 🔥 5 days ago

Post

4108

🚀 I built a Multimodal Vision-Language Model from using Gemma-270M + CLIP!

Just finished training my multimodal model on the full LLaVA-Instruct-150K dataset (157K samples) and wanted to share the results!

🔧 What I Built:
A vision-language model that can understand images and answer questions about them, combining:
- Google Gemma-3-270M (language)
- OpenAI CLIP ViT-Large/14 (vision)
- LoRA fine-tuning for efficiency

📊 Training Stats:
- 157,712 training samples (full LLaVA dataset)
- 3 epochs on A100 40GB
- ~9 hours training time
- Final loss: 1.333 training / 1.430 validation
- Only 18.6M trainable params (3.4% of 539M total)

📈 sagar007/multigemma
Benchmark Results:
- VQA Accuracy: 53.8%
- Works great for: animal detection, room identification, scene understanding

🔗 **Try it yourself:**
- 🤗 Model: sagar007/multigemma
- 🎮 Demo: https://huggingface.co/spaces/sagar007/Multimodal-Gemma
- 💻 GitHub: https://github.com/sagar431/multimodal-gemma-270m

Built with PyTorch Lightning + MLflow for experiment tracking. Full MLOps pipeline with CI/CD!

Would love to hear your feedback! 🙏

#multimodal #gemma #clip #llava #vision-language #pytorch