Update README.md

README.md

@@ -1,8 +1,8 @@
 ---
 license: apache-2.0
 datasets:
-- test-tcy/VisRAG-Ret-Train-In-domain-data
-- test-tcy/VisRAG-Ret-Train-Synthetic-data
+- openbmb/VisRAG-Ret-Train-In-domain-data
+- openbmb/VisRAG-Ret-Train-Synthetic-data
 language:
 - en
 base_model:
@@ -31,9 +31,6 @@ Our training dataset of 362,110 Query-Document (Q-D) Pairs for **VisRAG-Ret** is
 ### VisRAG-Gen
 The generation part does not use any fine-tuning; we directly use off-the-shelf LLMs/VLMs for generation.
 
-## Implementation Details
-**VisRAG-Ret** is fine-tuned using [in-batch negatives](https://arxiv.org/abs/2004.04906) for one epoch with a batch size of 128 on 8 NVIDIA A100 80GB GPUs. The temperature is set to 0.02.
-
 ## Requirements
 ```
 torch==2.1.2