Instructions to use FreedomIntelligence/LongLLaVA-53B-A13B with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use FreedomIntelligence/LongLLaVA-53B-A13B with Transformers:

# Use a pipeline as a high-level helper
from transformers import pipeline

pipe = pipeline("image-text-to-text", model="FreedomIntelligence/LongLLaVA-53B-A13B", trust_remote_code=True)

# Load model directly
from transformers import AutoModelForCausalLM
model = AutoModelForCausalLM.from_pretrained("FreedomIntelligence/LongLLaVA-53B-A13B", trust_remote_code=True, dtype="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use FreedomIntelligence/LongLLaVA-53B-A13B with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "FreedomIntelligence/LongLLaVA-53B-A13B"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "FreedomIntelligence/LongLLaVA-53B-A13B",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/FreedomIntelligence/LongLLaVA-53B-A13B

SGLang

How to use FreedomIntelligence/LongLLaVA-53B-A13B with SGLang:

Install from pip and serve model

# Install SGLang from pip:
pip install sglang
# Start the SGLang server:
python3 -m sglang.launch_server \
    --model-path "FreedomIntelligence/LongLLaVA-53B-A13B" \
    --host 0.0.0.0 \
    --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "FreedomIntelligence/LongLLaVA-53B-A13B",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker images

docker run --gpus all \
    --shm-size 32g \
    -p 30000:30000 \
    -v ~/.cache/huggingface:/root/.cache/huggingface \
    --env "HF_TOKEN=<secret>" \
    --ipc=host \
    lmsysorg/sglang:latest \
    python3 -m sglang.launch_server \
        --model-path "FreedomIntelligence/LongLLaVA-53B-A13B" \
        --host 0.0.0.0 \
        --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "FreedomIntelligence/LongLLaVA-53B-A13B",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use FreedomIntelligence/LongLLaVA-53B-A13B with Docker Model Runner:
```
docker model run hf.co/FreedomIntelligence/LongLLaVA-53B-A13B
```

Xidong commited on Sep 5, 2024

Commit

0746f2a

verified ·

1 Parent(s): c27d907

Update README.md

Browse files

Files changed (1) hide show

README.md +108 -3

README.md CHANGED Viewed

@@ -1,3 +1,108 @@
----
-license: mit
----

+---
+license: mit
+---
+![header](./assets/header.png)
+<p align="center">
+   📃 <a href="" target="_blank">Paper</a> • 🌐 <a href="" target="_blank">Demo</a> • 🤗 <a href="https://huggingface.co/FreedomIntelligence/LongLLaVA" target="_blank">LongLLaVA</a>
+</p>
+![efficiency](./assets/singleGPU.png)
+## 🌈 Update
+* **[2024.09.05]** LongLLaVA repo is published！🎉 The Code will
+## Architecture
+<details>
+  <summary>Click to view the architecture image</summary>
+  ![Architecture Image](./assets/arch.png)
+</details>
+## Results
+<details>
+  <summary>Click to view the Results</summary>
+  - Main Results
+      ![Main Results](./assets/result1.png)
+  - Diagnostic Results
+      ![Diagnostic Results](./assets/diaresult.png)
+  - Video-NIAH
+      ![Video-NIAH](./assets/NIAH.png)
+</details>
+## Results reproduction
+### Data DownLoad and Construction
+<details>
+  <summary>Dataset Taxonomy</summary>
+  ![Dataset](./assets/dataset.png)
+</details>
+<details>
+  <summary>Dataset DownLoading and Construction</summary>
+   > Coming Soon~
+</details>
+### Training
+> Coming Soon~
+- Stage I: Single-image Alignment.
+  ```bash
+  bash Pretrain.sh
+  ```
+- Stage II: Single-image Instruction-tuning.
+  ```bash
+  bash SingleImageSFT.sh
+  ```
+- Stage III: Multi-image Instruction-tuning.
+  ```bash
+  bash MultiImageSFT.sh
+  ```
+### Evaluation
+> Coming Soon~
+```bash
+bash Eval.sh
+```
+## TO DO
+- [ ] Release Model Evalation Code
+- [ ] Release Data Construction Code
+- [ ] Release Model Training Code
+## Acknowledgement
+- [LLaVA](https://github.com/haotian-liu/LLaVA): Visual Instruction Tuning (LLaVA) built towards GPT-4V level capabilities and beyond.
+## Citation
+```
+@misc{wang2024longllavascalingmultimodalllms,
+      title={LongLLaVA: Scaling Multi-modal LLMs to 1000 Images Efficiently via Hybrid Architecture},
+      author={Xidong Wang and Dingjie Song and Shunian Chen and Chen Zhang and Benyou Wang},
+      year={2024},
+      eprint={2409.02889},
+      archivePrefix={arXiv},
+      primaryClass={cs.CL},
+      url={https://arxiv.org/abs/2409.02889},
+}
+```