Instructions to use TommyZQ/llama3 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use TommyZQ/llama3 with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("text-generation", model="TommyZQ/llama3")# Load model directly from transformers import AutoTokenizer, AutoModelForCausalLM tokenizer = AutoTokenizer.from_pretrained("TommyZQ/llama3") model = AutoModelForCausalLM.from_pretrained("TommyZQ/llama3") - Notebooks
- Google Colab
- Kaggle
- Local Apps
- vLLM
How to use TommyZQ/llama3 with vLLM:
Install from pip and serve model
# Install vLLM from pip: pip install vllm # Start the vLLM server: vllm serve "TommyZQ/llama3" # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:8000/v1/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "TommyZQ/llama3", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }'Use Docker
docker model run hf.co/TommyZQ/llama3
- SGLang
How to use TommyZQ/llama3 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 "TommyZQ/llama3" \ --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": "TommyZQ/llama3", "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 "TommyZQ/llama3" \ --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": "TommyZQ/llama3", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }' - Docker Model Runner
How to use TommyZQ/llama3 with Docker Model Runner:
docker model run hf.co/TommyZQ/llama3
Model Details
- Model name: llama3
- Model version: 1.0
- Developed by: [Development Team or Organization Name]
- Model type: [e.g., Machine Translation, Text Classification, etc.]
- Model framework: [e.g., TensorFlow, PyTorch, etc.]
- Training data: [Description of the dataset(s) used for training]
- Validation data: [Description of the dataset(s) used for validation]
Intended Use
- Primary intended users: [Who should be using this model - e.g., data scientists, developers]
- Out-of-scope use cases: [List any use cases that are not recommended]
Model Performance
- Metrics: [Description of the metrics used to evaluate model performance]
- Evaluation results: [Summary of the model's performance based on the chosen metrics]
Ethical Considerations
- Bias detection: [Any steps taken to address potential bias in the training data]
- Fairness assessment: [Description of fairness assessment methods and results if applicable]
Caveats and Recommendations
- Known limitations: [List known limitations of the model]
- Best practices: [Suggestions on best practices for implementation of the model]
Change Log
- [Date]: Model version 1.0 released.
Contact Information
- Maintainer(s): [Contact details for the person or team responsible for maintaining the model]
- Issues: [Information on where to report issues or bugs]
License
- Model license: [Details of the model's usage license, if applicable]
- Downloads last month
- 5