Text Generation
Transformers
Safetensors
English
table-understanding
instruction-tuning
replication
tabular-data
Instructions to use dnaihao/phi-3-tablebench with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use dnaihao/phi-3-tablebench with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("text-generation", model="dnaihao/phi-3-tablebench")# Load model directly from transformers import AutoModel model = AutoModel.from_pretrained("dnaihao/phi-3-tablebench", dtype="auto") - Notebooks
- Google Colab
- Kaggle
- Local Apps
- vLLM
How to use dnaihao/phi-3-tablebench with vLLM:
Install from pip and serve model
# Install vLLM from pip: pip install vllm # Start the vLLM server: vllm serve "dnaihao/phi-3-tablebench" # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:8000/v1/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "dnaihao/phi-3-tablebench", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }'Use Docker
docker model run hf.co/dnaihao/phi-3-tablebench
- SGLang
How to use dnaihao/phi-3-tablebench 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 "dnaihao/phi-3-tablebench" \ --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": "dnaihao/phi-3-tablebench", "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 "dnaihao/phi-3-tablebench" \ --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": "dnaihao/phi-3-tablebench", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }' - Docker Model Runner
How to use dnaihao/phi-3-tablebench with Docker Model Runner:
docker model run hf.co/dnaihao/phi-3-tablebench
Ctrl+K
- 270 Bytes
- 3.3 kB
- 1.68 MB
- 2.9 kB xet
- 12.3 kB
- 143 Bytes xet
- 15 Bytes
- 4.83 GB xet
- 4.8 GB xet
- 4.8 GB xet
- 352 MB xet
- 34.9 kB xet
- 48 kB
- 11.7 kB
- 16 kB xet
- 16 kB xet
- 16 kB xet
- 16 kB xet
- 16 kB xet
- 16 kB xet
- 16 kB xet
- 16 kB xet
- 1.06 kB xet
- 99 Bytes xet
- 12.9 kB
- 1.12 kB xet
- 58.7 kB xet
- 7.22 kB xet
- 7.2 kB
- 82.5 kB
- 25.3 kB