Instructions to use luodian/OTTER-Video-LLaMA7B-DenseCaption with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use luodian/OTTER-Video-LLaMA7B-DenseCaption with Transformers:

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

pipe = pipeline("text-generation", model="luodian/OTTER-Video-LLaMA7B-DenseCaption")

# Load model directly
from transformers import AutoModelForSeq2SeqLM
model = AutoModelForSeq2SeqLM.from_pretrained("luodian/OTTER-Video-LLaMA7B-DenseCaption", device_map="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use luodian/OTTER-Video-LLaMA7B-DenseCaption with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "luodian/OTTER-Video-LLaMA7B-DenseCaption"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "luodian/OTTER-Video-LLaMA7B-DenseCaption",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/luodian/OTTER-Video-LLaMA7B-DenseCaption

SGLang

How to use luodian/OTTER-Video-LLaMA7B-DenseCaption 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 "luodian/OTTER-Video-LLaMA7B-DenseCaption" \
    --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": "luodian/OTTER-Video-LLaMA7B-DenseCaption",
		"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 "luodian/OTTER-Video-LLaMA7B-DenseCaption" \
        --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": "luodian/OTTER-Video-LLaMA7B-DenseCaption",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use luodian/OTTER-Video-LLaMA7B-DenseCaption with Docker Model Runner:
```
docker model run hf.co/luodian/OTTER-Video-LLaMA7B-DenseCaption
```

Add pipeline tag, link to paper

by nielsr HF Staff - opened Dec 27, 2024

base: refs/heads/main

←

from: refs/pr/2

Discussion Files changed

+16

-0

Files changed (1) hide show

README.md +16 -0

README.md CHANGED Viewed

@@ -1,5 +1,6 @@
 ---
 license: mit
 ---
 <p align="center" width="100%">
@@ -188,4 +189,19 @@ while True:
         response = get_response(frames_list, prompts_input, model, image_processor, tensor_dtype)
         print(f"Response: {response}")
 ```

 ---
 license: mit
+pipeline_tag: video-text-to-text
 ---
 <p align="center" width="100%">
         response = get_response(frames_list, prompts_input, model, image_processor, tensor_dtype)
         print(f"Response: {response}")
+```
+<br>
+<div align="center">
+    <a href='https://arxiv.org/abs/2305.03726'><img src='https://img.shields.io/badge/Paper-Arxiv-red'></a> <a href='https://github.com/Luodian/Otter'><img src='https://img.shields.io/badge/GitHub-Code-blue'></a>
+</div>
+## 📜 Citation
+```
+@article{li2023otter,
+  title={Otter: A Multi-Modal Model with In-Context Instruction Tuning},
+  author={Li, Bo and Zhang, Yuanhan and Chen, Liangyu and Wang, Jinghao and Yang, Jingkang and Liu, Ziwei},
+  journal={arXiv preprint arXiv:2305.03726},
+  year={2023}
+}
 ```