Awesome
<div align="center"> <h2>INF-MLLM: Multimodal Large Language Models from INF Tech</h2> </div>-
INF-MLLM1 - InfMLLM: A Unified Model for Visual-Language Tasks
-
INF-MLLM2 - INF-MLLM2: High-Resolution Image and Document Understanding
Update
- [08/19] We have released INF-MLLM2, and models(INF-MLLM2-7B) and evaluation code are available.
- [12/06] Models and evaluation code of INF-MLLM1 are available.
- [11/06] We have released INF-MLLM1, Upload the initial version of the manuscript to arXiv.