metadata
license: apache-2.0
pipeline_tag: image-text-to-text
TinyLLaVA
We trained a TinyLLaVA model with 3.1B parameters, employing the same training settings as TinyLLaVA. For the Language and Vision models, we chose Phi-2 and siglip-so400m-patch14-384, respectively. The Connector was configured with a 2-layer MLP. The dataset used for training is the ShareGPT4V dataset.
Usage
Execute the following test code:
from transformers import AutoTokenizer, AutoModelForCausalLM
hf_path = 'tinyllava/TinyLLaVA-Phi-2-SigLIP-3.1B'
model = AutoModelForCausalLM.from_pretrained(hf_path, trust_remote_code=True)
model.cuda()
config = model.config
tokenizer = AutoTokenizer.from_pretrained(hf_path, use_fast=False, model_max_length = config.tokenizer_model_max_length,padding_side = config.tokenizer_padding_side)
prompt="What are these?"
image_url="http://images.cocodataset.org/val2017/000000039769.jpg"
output_text, genertaion_time = model.chat(prompt=prompt, image=image_url, model=model, tokenizer=tokenizer)
print('model output: ', output_text)
print('runing time: ', genertaion_time)
Result
| model_name | vqav2 | gqa | sqa | textvqa | MM-VET | POPE | MME | MMMU |
|---|---|---|---|---|---|---|---|---|
| bczhou/TinyLLaVA-3.1B | 79.9 | 62.0 | 69.1 | 59.1 | 32.0 | 86.4 | 1464.9 | - |
| tinyllava/TinyLLaVA-Phi-2-SigLIP-3.1B | 80.1 | 62.1 | 73.0 | 60.3 | 37.5 | 87.2 | 1466.4 | 38.4 |