Update README.md
Browse files
README.md
CHANGED
|
@@ -33,7 +33,7 @@ In particular, InfiMM integrates the latest LLM models into VLM domain the revea
|
|
| 33 |
Please note that InfiMM is currently in beta stage and we are continuously working on improving it.
|
| 34 |
|
| 35 |
## News
|
| 36 |
-
|
| 37 |
- 🎉 **[2024.01.11]** We release the first set of MLLMs we trained [InfiMM-Zephyr](https://huggingface.co/Infi-MM/infimm-zephyr), [InfiMM-LLaMA13B](https://huggingface.co/Infi-MM/infimm-llama13b) and [InfiMM-Vicuna13B](https://huggingface.co/Infi-MM/infimm-vicuna13b).
|
| 38 |
- 🎉 **[2024.01.10]** We release a survey about Multimodal Large Language Models (MLLMs) reasoning capability at [here](https://huggingface.co/papers/2401.06805).
|
| 39 |
- 🎉 **[2023.11.18]** We release InfiMM-Eval at [here](https://arxiv.org/abs/2311.11567), an Open-ended VQA benchmark dataset specifically designed for MLLMs, with a focus on complex reasoning tasks. The leaderboard can be found via [Papers with Code](https://paperswithcode.com/sota/visual-question-answering-vqa-on-core-mm) or [project page](https://infimm.github.io/InfiMM-Eval/).
|
|
|
|
| 33 |
Please note that InfiMM is currently in beta stage and we are continuously working on improving it.
|
| 34 |
|
| 35 |
## News
|
| 36 |
+
- 🎉 **[2024.03.02]** We release the [InfiMM-HD](https://huggingface.co/Infi-MM/infimm-hd).
|
| 37 |
- 🎉 **[2024.01.11]** We release the first set of MLLMs we trained [InfiMM-Zephyr](https://huggingface.co/Infi-MM/infimm-zephyr), [InfiMM-LLaMA13B](https://huggingface.co/Infi-MM/infimm-llama13b) and [InfiMM-Vicuna13B](https://huggingface.co/Infi-MM/infimm-vicuna13b).
|
| 38 |
- 🎉 **[2024.01.10]** We release a survey about Multimodal Large Language Models (MLLMs) reasoning capability at [here](https://huggingface.co/papers/2401.06805).
|
| 39 |
- 🎉 **[2023.11.18]** We release InfiMM-Eval at [here](https://arxiv.org/abs/2311.11567), an Open-ended VQA benchmark dataset specifically designed for MLLMs, with a focus on complex reasoning tasks. The leaderboard can be found via [Papers with Code](https://paperswithcode.com/sota/visual-question-answering-vqa-on-core-mm) or [project page](https://infimm.github.io/InfiMM-Eval/).
|