Instructions to use JoydeepC/trueGL with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use JoydeepC/trueGL with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("text-generation", model="JoydeepC/trueGL")# Load model directly from transformers import AutoTokenizer, AutoModelForCausalLM tokenizer = AutoTokenizer.from_pretrained("JoydeepC/trueGL") model = AutoModelForCausalLM.from_pretrained("JoydeepC/trueGL") - Notebooks
- Google Colab
- Kaggle
- Local Apps
- vLLM
How to use JoydeepC/trueGL with vLLM:
Install from pip and serve model
# Install vLLM from pip: pip install vllm # Start the vLLM server: vllm serve "JoydeepC/trueGL" # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:8000/v1/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "JoydeepC/trueGL", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }'Use Docker
docker model run hf.co/JoydeepC/trueGL
- SGLang
How to use JoydeepC/trueGL 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 "JoydeepC/trueGL" \ --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": "JoydeepC/trueGL", "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 "JoydeepC/trueGL" \ --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": "JoydeepC/trueGL", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }' - Docker Model Runner
How to use JoydeepC/trueGL with Docker Model Runner:
docker model run hf.co/JoydeepC/trueGL
Improve model card: Add paper link, pipeline_tag, and library_name
#1
by nielsr HF Staff - opened
This PR improves the model card for TrueGL_Granite by:
- Linking directly to the paper TrueGL: A Truthful, Reliable, and Unified Engine for Grounded Learning in Full-Stack Search.
- Adding the
pipeline_tag: text-generationto ensure the model is discoverable under relevant tasks, reflecting its capability to return textual explanations alongside reliability scores. - Adding
library_name: transformersas the model'sconfig.jsonandtokenizer_config.jsonindicate compatibility, enabling the automated code snippet for users.