kentang1998 commited on
Commit
699b413
1 Parent(s): 4ff7e11

Update README.md

Browse files
Files changed (1) hide show
  1. README.md +1 -1
README.md CHANGED
@@ -15,7 +15,7 @@ tags:
15
  VILA is a visual language model (VLM) pretrained with interleaved image-text data at scale, enabling multi-image VLM. VILA is deployable on the edge, including Jetson Orin and laptop by AWQ 4bit quantization through TinyChat framework. We find: (1) image-text pairs are not enough, interleaved image-text is essential; (2) unfreezing LLM during interleaved image-text pre-training enables in-context learning; (3)re-blending text-only instruction data is crucial to boost both VLM and text-only performance. VILA unveils appealing capabilities, including: multi-image reasoning, in-context learning, visual chain-of-thought, and better world knowledge.
16
 
17
  **Model date:**
18
- VILA-7b was trained in Feb 2024.
19
 
20
  **Paper or resources for more information:**
21
  https://github.com/Efficient-Large-Model/VILA
 
15
  VILA is a visual language model (VLM) pretrained with interleaved image-text data at scale, enabling multi-image VLM. VILA is deployable on the edge, including Jetson Orin and laptop by AWQ 4bit quantization through TinyChat framework. We find: (1) image-text pairs are not enough, interleaved image-text is essential; (2) unfreezing LLM during interleaved image-text pre-training enables in-context learning; (3)re-blending text-only instruction data is crucial to boost both VLM and text-only performance. VILA unveils appealing capabilities, including: multi-image reasoning, in-context learning, visual chain-of-thought, and better world knowledge.
16
 
17
  **Model date:**
18
+ VILA1.5-3b was trained in May 2024.
19
 
20
  **Paper or resources for more information:**
21
  https://github.com/Efficient-Large-Model/VILA