Hugging Face's logo

shi-labs
/
probe_seg_llava-1.5-pt-vpt-ift

Image-Text-to-Text
Transformers
Safetensors
English
probe_dsg_llava_llama
text-generation
conversational
Model card Files Community
praeclarumjj3 commited on
Commit
7730fe6
·
verified ·
1 Parent(s): 3b3b2cb

Update README.md

Browse files
Files changed (1) hide show
  1. README.md +1 -1
README.md CHANGED
@@ -6,7 +6,7 @@ language:
6
  pipeline_tag: image-text-to-text
7
  ---
8
 
9
- # probe_seg_llava-1.5-pt
10
 
11
  This model checkpoint contains the seg probes for CLIP-ConvNeXT-XXL Llama-3-8b based LLaVA-1.5 model after the PT, VPT, and IFT stages, i.e., trained on the LLaVA-558K, ALLaVA-Caption-663K, and LLaVA-665K dataset. Please refer to [documentation](https://github.com/SHI-Labs/OLA-VLM/blob/main/docs/Probing.md) for more details.
12
 
 
6
  pipeline_tag: image-text-to-text
7
  ---
8
 
9
+ # probe_seg_llava-1.5-pt-vpt-ift
10
 
11
  This model checkpoint contains the seg probes for CLIP-ConvNeXT-XXL Llama-3-8b based LLaVA-1.5 model after the PT, VPT, and IFT stages, i.e., trained on the LLaVA-558K, ALLaVA-Caption-663K, and LLaVA-665K dataset. Please refer to [documentation](https://github.com/SHI-Labs/OLA-VLM/blob/main/docs/Probing.md) for more details.
12