Update README.md

merveenoyan · web-flow · commit 40de43813090 · 2025-10-25T21:54:41.000+02:00
diff --git a/README.md b/README.md
@@ -7,9 +7,9 @@ Recipes for shrinking, optimizing, customizing cutting edge vision and multimoda
 **NOTE:** GitHub refuses to render notebooks for a long time now, so the notebooks of smol-vision with rich outputs now lives [here](https://huggingface.co/merve/smol-vision). I still update this repository but it's inconvenient to read here.
 
 Latest examples 👇🏻
-- [Grounded Fine-tuning](https://github.com/merveenoyan/smol-vision/blob/main/Grounded_Fine_tuning%20GH.ipynb)
-- [Fine-tune Florence-2](https://github.com/merveenoyan/smol-vision/blob/main/Fine_tune_Florence_2.ipynb)
-- [Fine-tune DINOv3](https://github.com/merveenoyan/smol-vision/blob/main/DINOv3_FT.ipynb)
+- [Fine-tune Kosmos2.5 on OCR with bounding boxes](https://github.com/merveenoyan/smol-vision/blob/main/Grounded_Fine_tuning%20GH.ipynb)
+- [Fine-tune Florence-2 on document question answering](https://github.com/merveenoyan/smol-vision/blob/main/Fine_tune_Florence_2.ipynb)
+- [Fine-tune DINOv3 on image classification](https://github.com/merveenoyan/smol-vision/blob/main/DINOv3_FT.ipynb)
 
 **Note**: The script and notebook are updated to fix few issues related to QLoRA!
 
@@ -31,4 +31,4 @@ Latest examples 👇🏻
 | Any-to-Any Fine-tuning             | [Fine-tune Gemma-3n for all modalities (audio-text-image)](https://github.com/merveenoyan/smol-vision/blob/main/Gemma3n_Fine_tuning_on_All_Modalities.ipynb)            | Fine-tune Gemma-3n model to handle any modality: audio, text, and image.                                           |
 | Any-to-Any RAG              | [Any-to-Any (Video) RAG with OmniEmbed and Qwen](https://github.com/merveenoyan/smol-vision/blob/main/Any_to_Any_RAG.ipynb)                                             | Do retrieval and generation across modalities (including video) using OmniEmbed and Qwen.                          |
 | Speed-up/Memory Optimization | Vision language model serving using TGI (SOON)                                                                                                                          | Explore speed-ups and memory improvements for vision-language model serving with text-generation inference |
-| Quantization/Optimum/ORT     | All levels of quantization and graph optimizations for Image Segmentation using Optimum (SOON)                                                                          | End-to-end model optimization using Optimum                                                                |
+| Quantization/Optimum/ORT     | All levels of quantization and graph optimizations for Image Segmentation using Optimum (SOON)                                                                          | End-to-end model optimization using Optimum                                                                |
