|
--- |
|
license: apache-2.0 |
|
pipeline_tag: image-text-to-text |
|
--- |
|
### TinyLLaVA |
|
|
|
We trained 1 model with fewer than 1B parameters using the TinyLLaVA approach, employing the same training settings as [TinyLLaVA](https://github.com/DLCV-BUAA/TinyLLaVABench). For the Language and Vision models, we chose [OpenELM-450M-Instruct](apple/OpenELM-450M-Instruct) and [siglip-so400m-patch14-384](https://huggingface.co/google/siglip-so400m-patch14-384), respectively. The Connector was configured with a 2-layer MLP. The dataset used for training is the save as [LLaVA](https://github.com/haotian-liu/LLaVA). During testing, we found that [TinyLLaVA-0.55B](https://huggingface.co/jiajunlong/TinyLLaVA-0.55B) exhibited significantly faster inference speed on CPU compared to [TinyLLaVA-1.5B](https://huggingface.co/bczhou/TinyLLaVA-1.5B) |
|
|
|
### Usage |
|
|
|
1. you need to download the generate file "generate_model.py". |
|
2. running the following command: |
|
```bash |
|
python generate_model --model jiajunlong/TinyLLaVA-0.89B --prompt 'you want to ask' --image '/path/to/related/image' |
|
``` |
|
or execute the following test code: |
|
```python |
|
from transformers import AutoTokenizer, AutoModelForCausalLM |
|
from generate_model import * |
|
model = AutoModelForCausalLM.from_pretrained("jiajunlong/TinyLLaVA-0.55B", trust_remote_code=True) |
|
config = model.config |
|
tokenizer = AutoTokenizer.from_pretrained("jiajunlong/TinyLLaVA-0.55B", use_fast=False, model_max_length = config.tokenizer_model_max_length,padding_side = config.tokenizer_padding_side) |
|
prompt="you want to ask" |
|
image="/path/to/related/image" |
|
output_text, genertaion_time = generate(prompt=prompt, image=image, model=model, tokenizer=tokenizer) |
|
print_txt = ( |
|
f'\r\n{"=" * os.get_terminal_size().columns}\r\n' |
|
'\033[1m Prompt + Generated Output\033[0m\r\n' |
|
f'{"-" * os.get_terminal_size().columns}\r\n' |
|
f'{output_text}\r\n' |
|
f'{"-" * os.get_terminal_size().columns}\r\n' |
|
'\r\nGeneration took' |
|
f'\033[1m\033[92m {round(genertaion_time, 2)} \033[0m' |
|
'seconds.\r\n' |
|
) |
|
print(print_txt) |
|
``` |
|
### Result |
|
|
|
| model_name | gqa | textvqa | sqa | vqav2 | MME | MMB | MM-VET | |
|
| :----------------------------------------------------------: | ----- | ------- | ----- | ----- | ------- | ----- | ------ | |
|
| [TinyLLaVA-1.5B](https://huggingface.co/bczhou/TinyLLaVA-1.5B) | 60.3 | 51.7 | 60.3 | 76.9 | 1276.5 | 55.2 | 25.8 | |
|
| [TinyLLaVA-0.55B](https://huggingface.co/jiajunlong/TinyLLaVA-0.89B) | 53.87 | 44.02 | 54.09 | 71.74 | 1118.75 | 37.8 | 20 | |
|
|
|
|
|
|
