Instructions to use omni-research/Tarsier-34b with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use omni-research/Tarsier-34b with Transformers:

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

pipe = pipeline("text-generation", model="omni-research/Tarsier-34b")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoProcessor, AutoModelForSeq2SeqLM

processor = AutoProcessor.from_pretrained("omni-research/Tarsier-34b")
model = AutoModelForSeq2SeqLM.from_pretrained("omni-research/Tarsier-34b")
messages = [
    {"role": "user", "content": "Who are you?"},
]
inputs = processor.apply_chat_template(
	messages,
	add_generation_prompt=True,
	tokenize=True,
	return_dict=True,
	return_tensors="pt",
).to(model.device)

outputs = model.generate(**inputs, max_new_tokens=40)
print(processor.decode(outputs[0][inputs["input_ids"].shape[-1]:]))

Notebooks
Google Colab
Kaggle
Local Apps

vLLM

How to use omni-research/Tarsier-34b with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "omni-research/Tarsier-34b"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "omni-research/Tarsier-34b",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/omni-research/Tarsier-34b

SGLang

How to use omni-research/Tarsier-34b 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 "omni-research/Tarsier-34b" \
    --host 0.0.0.0 \
    --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "omni-research/Tarsier-34b",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

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 "omni-research/Tarsier-34b" \
        --host 0.0.0.0 \
        --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "omni-research/Tarsier-34b",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use omni-research/Tarsier-34b with Docker Model Runner:
```
docker model run hf.co/omni-research/Tarsier-34b
```

You need to agree to share your contact information to access this model

This repository is publicly accessible, but you have to accept the conditions to access its files and content.

Tarsier Model Card

Model details

Model type: Tarsier-34b is an open-source large-scale video-language models, which is designed to generate high-quality video descriptions, together with good capability of general video understanding (SOTA results on 6 open benchmarks).

Model date: Tarsier-34b was trained in June 2024.

Paper or resources for more information:

github repo: https://github.com/bytedance/tarsier
paper link: https://arxiv.org/abs/2407.00634

License

NousResearch/Nous-Hermes-2-Yi-34B license.

Where to send questions or comments about the model: https://github.com/bytedance/tarsier/issues

Intended use

Primary intended uses: The primary use of Tarsier is research on large multimodal models, especially video description.

Primary intended users: The primary intended users of the model are researchers and hobbyists in computer vision, natural language processing, machine learning, and artificial intelligence.

Training dataset

Tarsier tasks a two-stage training strategy.

Stage-1: Multi-task Pre-training on 13M data
Stage-2: Multi-grained Instruction Tuning on 500K data

In both stages, we freeze ViT and train all the parameters of projection layer and LLM.

Evaluation dataset

A challenging video desription dataset: DREAM-1K
Multi-choice VQA: MVBench, NeXT-QA and Egoschema
Open-ended VQA: MSVD-QA, MSR-VTT-QA, ActivityNet-QA and TGIF-QA
Video Caption: MSVD-Caption, MSRVTT-Caption, VATEX

How to Use

see https://github.com/bytedance/tarsier?tab=readme-ov-file#usage

Downloads last month: 5

Safetensors

Model size

35B params

Tensor type

F16

Paper for omni-research/Tarsier-34b

Tarsier: Recipes for Training and Evaluating Large Video Description Models

Paper • 2407.00634 • Published Jun 30, 2024