Update README.md

README.md

@@ -14,26 +14,6 @@ datasets:
 pipeline_tag: text-generation
 inference: true
 ---
-
-<br>
-<p align="center">
-  <img src="assets/infimm-logo.webp" alt="InfiMM-logo" width="400"></a>
-</p>
-<br>
-
-## Model Details
-
-- **Developed by**: Institute of Automation, Chinese Academy of Sciences and ByteDance
-- **Model Type**: Visual Language Model (VLM)
-- **Language**: English
-- **LLMs**: [Zephyr](https://huggingface.co/HuggingFaceH4/zephyr-7b-beta), [LLaMA2-13B](https://ai.meta.com/llama/), [Vicuna-13B](https://huggingface.co/lmsys/vicuna-13b-v1.5)
-- **Vision Model**: [EVA CLIP](https://huggingface.co/QuanSun/EVA-CLIP)
-- **Language(s) (NLP):** en
-- **License:** see [License section](#license)
-<!---
-- **Parent Models:** [QuanSun/EVA-CLIP](https://huggingface.co/QuanSun/EVA-CLIP/blob/main/EVA02_CLIP_L_336_psz14_s6B.pt) and [HuggingFaceH4/zephyr-7b--beta ta](https://huggingface.co/HuggingFaceH4/zephyr-7b-beta)
-  -->
-
 ## Paper
 
 More detailes can be found in our paper