Hugging Face's logo

MaoXun
/
llava-lora-7-20-10-5-vicuna-7b-v1.3

Image-Text-to-Text
PEFT
English
llava
Model card Files
xet
 Community
1
MaoXun commited on
Commit
2e4f805
·
verified ·
1 Parent(s): 88897c3

Update README.md

Browse files
Files changed (1) hide show
  1. README.md +5 -2
README.md CHANGED
@@ -10,15 +10,18 @@ language:
10
  - en
11
  base_model:
12
  - liuhaotian/llava-pretrain-vicuna-7b-v1.3
 
13
  ---
14
  # Brief
15
  This is the LoRA Model of LLaVA 7B v1.3 trained on [Synergy-General-MultimodalPairs](https://huggingface.co/datasets/MaoXun/Synergy-General-MultimodalPairs).
 
 
16
 
17
  # Dataset
18
- ## Link
19
  [Github](https://github.com/mao-code/Synergy-General-MultimodalPairs) | [Paper](https://link.springer.com/chapter/10.1007/978-981-97-6125-8_12)
20
 
21
- ## Introduction
22
  This is a visual-text pair dataset synergistically generated by a text-to-image model and multimodal large language model.
23
 
24
  The name of the file means (n_th generation)\_(numbers of batch)\_(numbers of initial description of each batch)\_(numbers of refined cycles of each initial description)
 
10
  - en
11
  base_model:
12
  - liuhaotian/llava-pretrain-vicuna-7b-v1.3
13
+ - lmsys/vicuna-7b-v1.3
14
  ---
15
  # Brief
16
  This is the LoRA Model of LLaVA 7B v1.3 trained on [Synergy-General-MultimodalPairs](https://huggingface.co/datasets/MaoXun/Synergy-General-MultimodalPairs).
17
+ The dataset is to enhance the ability of describing images in detail for vision language models (VLM).
18
+ Below is the introduction of this dataset.
19
 
20
  # Dataset
21
+ ### Link
22
  [Github](https://github.com/mao-code/Synergy-General-MultimodalPairs) | [Paper](https://link.springer.com/chapter/10.1007/978-981-97-6125-8_12)
23
 
24
+ ### Introduction
25
  This is a visual-text pair dataset synergistically generated by a text-to-image model and multimodal large language model.
26
 
27
  The name of the file means (n_th generation)\_(numbers of batch)\_(numbers of initial description of each batch)\_(numbers of refined cycles of each initial description)