|
--- |
|
license: apache-2.0 |
|
pipeline_tag: image-text-to-text |
|
--- |
|
|
|
### TinyLLaVA |
|
We introduce TinyLLaVA-Phi-2-SigLIP-3.1B, a small-scale large multimodal model(LMM), which is trained by the TinyLLaVA Factory codebase. For the LLM and vision tower, we choose [Phi-2](microsoft/phi-2) and [siglip-so400m-patch14-384](https://huggingface.co/google/siglip-so400m-patch14-384), respectively. The dataset used for training this model is the [ShareGPT4V](https://github.com/InternLM/InternLM-XComposer/blob/main/projects/ShareGPT4V/docs/Data.md) dataset. |
|
|
|
### Usage |
|
Execute the following test code: |
|
```python |
|
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, tokenizer=tokenizer) |
|
|
|
print('model output:', output_text) |
|
print('runing time:', genertaion_time) |
|
``` |
|
### Result |
|
|
|
| model_name | vqav2 | gqa | sqa | textvqa | MM-VET | POPE | MME | MMMU | |
|
| :----------------------------------------------------------: | ----- | ------- | ----- | ----- | ------- | ----- | ------ | ------ | |
|
| [LLaVA-1.5-7B](https://huggingface.co/llava-hf/llava-1.5-7b-hf) | 78.5 | 62.0 | 66.8 | 58.2 | 30.5 | 85.9 | 1510.7 | - | |
|
| [bczhou/TinyLLaVA-3.1B](https://huggingface.co/bczhou/TinyLLaVA-3.1B) | 79.9 | 62.0 | 69.1 | 59.1 | 32.0 | 86.4 | 1464.9 | - | |
|
| [tinyllava/TinyLLaVA-Gemma-SigLIP-2.4B](https://huggingface.co/tinyllava/TinyLLaVA-Gemma-SigLIP-2.4B) | 78.4 | 61.6 | 64.4 | 53.6 | 26.9 | 86.4 | 1339.0 | 31.7 | |
|
| [tinyllava/TinyLLaVA-Phi-2-SigLIP-3.1B](https://huggingface.co/tinyllava/TinyLLaVA-Phi-2-SigLIP-3.1B) | 80.1 | 62.1 | 73.0 | 60.3 | 37.5 | 87.2 | 1466.4 | 38.4 | |
|
|
|
P.S. TinyLLaVA Factory is an open-source modular codebase for small-scale LMMs with a focus on simplicity of code implementations, extensibility of new features, and reproducibility of training results. This code repository provides standard training&evaluating pipelines, flexible data preprocessing&model configurations, and easily extensible architectures. Users can customize their own LMMs with minimal coding effort and less codding mistake. |
|
|
|
TinyLLaVA Factory integrates a suite of cutting-edge models and methods. |
|
- LLM currently supports OpenELM, TinyLlama, StableLM, Qwen, Gemma, and Phi. |
|
- Vision tower currently supports CLIP, SigLIP, Dino, and combination of CLIP and Dino. |
|
- Connector currently supports MLP, Qformer, and Resampler. |
|
|
|
We will release the TinyLLaVA Factory codebase very soon! |
