Hugging Face's logo

xjtupanda
/
MiniCPM-V-30K-mix-finetune

Video-Text-to-Text
Transformers
Safetensors
minicpmv
feature-extraction
MiniCPM-V
finetune
MLLM
custom_code
Model card Files Community
2

Fix formatting

#2
by nielsr HF staff - opened
base: refs/heads/main
←
from: refs/pr/2
Discussion Files changed
+1
-3
Files changed (1) hide show
  1. README.md +1 -3
README.md CHANGED
@@ -14,7 +14,6 @@ tags:
14
  - MLLM
15
  ---
16
 
17
- ```markdown
18
  <h1>Sparrow: Data-Efficient Video-LLM with Text-to-Image Augmentation</h1>
19
  <p>
20
  💻 <a href="https://github.com/VITA-MLLM/Sparrow">GitHub</a>&nbsp&nbsp | &nbsp&nbsp 📑 <a href="https://arxiv.org/pdf/2411.19951">Paper</a> &nbsp&nbsp </a>
@@ -40,5 +39,4 @@ tags:
40
  ## Training dataset
41
  - 10K video instruction data from Video-ChatGPT
42
  - 10K video caption data from ShareGemini
43
- - 10K synthetic data derived from long text instruction data
44
- ```
 
14
  - MLLM
15
  ---
16
 
 
17
  <h1>Sparrow: Data-Efficient Video-LLM with Text-to-Image Augmentation</h1>
18
  <p>
19
  💻 <a href="https://github.com/VITA-MLLM/Sparrow">GitHub</a>&nbsp&nbsp | &nbsp&nbsp 📑 <a href="https://arxiv.org/pdf/2411.19951">Paper</a> &nbsp&nbsp </a>
 
39
  ## Training dataset
40
  - 10K video instruction data from Video-ChatGPT
41
  - 10K video caption data from ShareGemini
42
+ - 10K synthetic data derived from long text instruction data