Downloads · 30 days
16
5% of all-time downloads
co-instruct-llava-v1.5-7b
q-future/co-instruct-llava-v1.5-7b
co-instruct-llava-v1.5-7b is a text generation model from q-future. Use it when you need the model to write or continue text. It is set up for transformers. The card lists the license as apache-2.0.
Training the Co-Instruct-562K dataset with LLaVA-1.5-7B to facilitate users that prefer the LLaVA structure.
All-time downloads
335
Public
Parameters
7.1B
14.1 GB on disk
Likes
1
Public
Repo makeup
Click a slice to open those files.
.safetensors14.1 GB · 100%
At a glance
- Task
- Text Generation
- Library
- transformers
- License
- apache-2.0
- Model type
- llava_llama
- Access
- Public
- Created
- Mar 1, 2024
- Updated
- Mar 1, 2024
- SHA
- 31f10192
Try a prompt
Datasets
Model card
From the Hugging Face model README
Training the Co-Instruct-562K dataset with LLaVA-1.5-7B to facilitate users that prefer the LLaVA structure.
It is notably less accurate than the main version: https://huggingface.co/q-future/co-instruct, please refer to that checkpoint if you want a more accurate model.
Preliminary Results:
- Q-Bench-Single-MCQ (A1, test): 73.38% (Co-Instruct-Main: 77.11%, GPT-4V-Turbo: 74.10%, Q-Instruct-LLaVA-v1.5: 67.42%, LLaVA-v1.5: 60.07%)
- Q-Bench-Pair-MCQ (A1, test): 75.88% (Co-Instruct-Main: 80.18%, GPT-4V-Turbo: 78.07%, Q-Instruct-LLaVA-v1.5: 54.50%, LLaVA-v1.5: 52.25%)
We are working on improving it in the future but we also warn that this structure (direct projection) might not be very friendly to multi-image scenarios.
- Task
- Text Generation
- Library
- transformers
- Type
- llava_llama
- License
- apache-2.0
- Created
- Mar 1, 2024
- Updated
- Mar 1, 2024