ariG23498 / timm-wrapper-examples
Notebooks to demonstrate TimmWrapper
☆16Updated 3 months ago
Alternatives and similar repositories for timm-wrapper-examples:
Users that are interested in timm-wrapper-examples are comparing it to the libraries listed below
- Pixel Parsing. A reproduction of OCR-free end-to-end document understanding models with open data☆21Updated 8 months ago
- Notebook and Scripts that showcase running quantized diffusion models on consumer GPUs☆38Updated 5 months ago
- Visualize multi-model embedding spaces. The first goal is to quickly get a lay of the land of any embedding space. Then be able to scroll…☆27Updated 11 months ago
- Shows how to do parameter ensembling using differential evolution.☆10Updated 3 years ago
- Build Agentic workflows with function calling using open LLMs☆26Updated 2 weeks ago
- ☆14Updated last year
- Recaption large (Web)Datasets with vllm and save the artifacts.☆50Updated 5 months ago
- ☆58Updated last year
- This library supports evaluating disparities in generated image quality, diversity, and consistency between geographic regions.☆20Updated 10 months ago
- ☆17Updated 2 months ago
- Chat with Qwen2-VL. Qwen2-VL is the multimodal large language model series developed by Qwen team, Alibaba Cloud.☆10Updated 7 months ago
- Smart commit messages☆18Updated 6 months ago
- Evaluate the performance of computer vision models and prompts for zero-shot models (Grounding DINO, CLIP, BLIP, DINOv2, ImageBind, model…☆35Updated last year
- Notebooks for fine tuning pali gemma☆100Updated last week
- Use Grounding DINO, Segment Anything, and CLIP to label objects in images.☆30Updated last year
- ☆17Updated last year
- Training hybrid models for dummies.☆20Updated 3 months ago
- implementation of https://arxiv.org/pdf/2312.09299☆20Updated 9 months ago
- Load any clip model with a standardized interface☆21Updated last year
- Code, results and other artifacts from the paper introducing the WildChat-50m dataset and the Re-Wild model family.☆29Updated 3 weeks ago
- 🤝 Trade any tensors over the network