Instructions to use SeeThink/STEVE-13b with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use SeeThink/STEVE-13b with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("text-generation", model="SeeThink/STEVE-13b")# Load model directly from transformers import AutoTokenizer, AutoModelForCausalLM tokenizer = AutoTokenizer.from_pretrained("SeeThink/STEVE-13b") model = AutoModelForCausalLM.from_pretrained("SeeThink/STEVE-13b") - Notebooks
- Google Colab
- Kaggle
- Local Apps Settings
- vLLM
How to use SeeThink/STEVE-13b with vLLM:
Install from pip and serve model
# Install vLLM from pip: pip install vllm # Start the vLLM server: vllm serve "SeeThink/STEVE-13b" # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:8000/v1/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "SeeThink/STEVE-13b", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }'Use Docker
docker model run hf.co/SeeThink/STEVE-13b
- SGLang
How to use SeeThink/STEVE-13b 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 "SeeThink/STEVE-13b" \ --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": "SeeThink/STEVE-13b", "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 "SeeThink/STEVE-13b" \ --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": "SeeThink/STEVE-13b", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }' - Docker Model Runner
How to use SeeThink/STEVE-13b with Docker Model Runner:
docker model run hf.co/SeeThink/STEVE-13b
Create README.md
Browse files
README.md
ADDED
|
@@ -0,0 +1,15 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
# See and Think: Embodied Agent in Virtual Environment
|
| 2 |
+
|
| 3 |
+
Zhonghan Zhao<sup>1\*</sup> , Wenhao Chai<sup>\*2❤</sup>, Xuan Wang<sup>1\*</sup>, Li Boyi<sup>1</sup>, Shengyu Hao<sup>1</sup>, Shidong Cao<sup>1</sup>, Tian Ye<sup>3</sup>, Jenq-Neng Hwang<sup>2</sup>, Gaoang Wang<sup>1✉</sup>
|
| 4 |
+
|
| 5 |
+
<sup>1</sup> Zhejiang University <sup>2</sup> University of Washington <sup>3</sup> Hong Kong University of Science and Technology (GZ)
|
| 6 |
+
|
| 7 |
+
<sup>*</sup>Equal contribution <sup>❤</sup>Project lead <sup>✉</sup>Corresponding author
|
| 8 |
+
|
| 9 |
+
|
| 10 |
+
|
| 11 |
+

|
| 12 |
+
|
| 13 |
+
STEVE, named after the protagonist of the game Minecraft, is our proposed framework aims to build an embodied agent based on the vision model and LLMs within an open world.
|
| 14 |
+
|
| 15 |
+
Link: [See and Think: Embodied Agent in Virtual Environment (rese1f.github.io)](https://rese1f.github.io/STEVE/)
|