Merge branch 'main' of https://huggingface.co/mlpc-lab/LoViM_Vicuna

README.md

@@ -1,5 +1,4 @@
 ---
-license: bsd-3-clause
 language:
 - en
 pipeline_tag: visual-question-answering
@@ -9,29 +8,29 @@ library_name: transformers
 <br>
 <br>
 
-# LoViM Model Card
+# BLIVA Model Card
 
 ## Model details
 
 **Model type:**
-LoViM is an open-source Vision-Languagde model trained by initializing from InstructBLIP and alignment with Vicuna on multimodal instruction-finetuning data.
+BLIVA is an open-source Vision-Languagde model trained by initializing from InstructBLIP and alignment with Vicuna on multimodal instruction-finetuning data.
 It composes of an EVA-CLIP vision encoder, a Q-Former, a projection layer and an auto-regressive language model, based on the decoder only transformer architecture.
 
 **Model date:**
-LoViM_Vicuna was trained in July 2023.
+BLIVA_Vicuna was trained in July 2023.
 
 **Paper or resources for more information:**
-https://gordonhu608.github.io/lovim/
+https://gordonhu608.github.io/bliva/
 
 **License:**
-BSD 3-Clause License
+Non-commercial bespoke license
 
 **Where to send questions or comments about the model:**
-https://github.com/mlpc-ucsd/LoViM
+https://github.com/mlpc-ucsd/BLIVA
 
 ## Intended use
 **Primary intended uses:**
-The primary use of LoViM is research on large multimodal models. 
+The primary use of BLIVA is research on large multimodal models. 
 
 **Primary intended users:**
 The primary intended users of the model are researchers and hobbyists in computer vision, natural language processing, machine learning, and artificial intelligence.
@@ -46,4 +45,4 @@ For zero-shot evaluation on general image task, we selected Nocaps, Flickr30K, V
 
 For zero-shot evaluation on text-rich image OCR task, we selected ST-VQA, OCR-VQA, Text-VQA, and Doc-VQA.
 
-More detials are in our github, https://github.com/mlpc-ucsd/LoViM
+More detials are in our github, https://github.com/mlpc-ucsd/BLIVA