Instructions to use Gen-Sim/Gen-Sim with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use Gen-Sim/Gen-Sim with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("text-generation", model="Gen-Sim/Gen-Sim")# Load model directly from transformers import AutoTokenizer, AutoModelForCausalLM tokenizer = AutoTokenizer.from_pretrained("Gen-Sim/Gen-Sim") model = AutoModelForCausalLM.from_pretrained("Gen-Sim/Gen-Sim", device_map="auto") - Notebooks
- Google Colab
- Kaggle
- Local Apps Settings
- vLLM
How to use Gen-Sim/Gen-Sim with vLLM:
Install from pip and serve model
# Install vLLM from pip: pip install vllm # Start the vLLM server: vllm serve "Gen-Sim/Gen-Sim" # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:8000/v1/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "Gen-Sim/Gen-Sim", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }'Use Docker
docker model run hf.co/Gen-Sim/Gen-Sim
- SGLang
How to use Gen-Sim/Gen-Sim 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 "Gen-Sim/Gen-Sim" \ --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": "Gen-Sim/Gen-Sim", "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 "Gen-Sim/Gen-Sim" \ --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": "Gen-Sim/Gen-Sim", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }' - Docker Model Runner
How to use Gen-Sim/Gen-Sim with Docker Model Runner:
docker model run hf.co/Gen-Sim/Gen-Sim
GenSim: Generating Robotic Simulation Tasks via Large Language Models
This model is a code-llama-instruct model finetuned on the released dataset of 100 simulation tasks generated by GPT-4 and humans. It can perform simulation task code generation similar to a GPT-4 level model.
Usage
from transformers import AutoModel
input = "[INST] <<SYS>>\n
<</SYS>>\n
Write the pybullet simulation task class [splitting-piles]. Provide answers in a python code block starting with ```
[/INST]\n"
model = AutoModel.from_pretrained("Gen-Sim/Gen-Sim", trust_remote_code=True)
Intended Use:
- Downloads last month
- 15