Instructions to use HiTZ/Llama-3.1-GuideX-8B with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use HiTZ/Llama-3.1-GuideX-8B with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("text-generation", model="HiTZ/Llama-3.1-GuideX-8B")# Load model directly from transformers import AutoTokenizer, AutoModelForCausalLM tokenizer = AutoTokenizer.from_pretrained("HiTZ/Llama-3.1-GuideX-8B") model = AutoModelForCausalLM.from_pretrained("HiTZ/Llama-3.1-GuideX-8B") - Notebooks
- Google Colab
- Kaggle
- Local Apps
- vLLM
How to use HiTZ/Llama-3.1-GuideX-8B with vLLM:
Install from pip and serve model
# Install vLLM from pip: pip install vllm # Start the vLLM server: vllm serve "HiTZ/Llama-3.1-GuideX-8B" # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:8000/v1/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "HiTZ/Llama-3.1-GuideX-8B", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }'Use Docker
docker model run hf.co/HiTZ/Llama-3.1-GuideX-8B
- SGLang
How to use HiTZ/Llama-3.1-GuideX-8B 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 "HiTZ/Llama-3.1-GuideX-8B" \ --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": "HiTZ/Llama-3.1-GuideX-8B", "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 "HiTZ/Llama-3.1-GuideX-8B" \ --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": "HiTZ/Llama-3.1-GuideX-8B", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }' - Docker Model Runner
How to use HiTZ/Llama-3.1-GuideX-8B with Docker Model Runner:
docker model run hf.co/HiTZ/Llama-3.1-GuideX-8B
Add library_name and link to Github repo
This PR improves the model card by adding the library_name metadata and linking to the Github repository.
We're almost done with the complete dataset and model cards, we'll publish them in a few hours. And now the github readme is fully finished at: https://github.com/Neilus03/GUIDEX
see the finished model card: https://huggingface.co/HiTZ/Llama-3.1-GuideX-8B/commit/b84e6f0609f36886fc5ead02d3863a38028c027c
also for the dataset: https://huggingface.co/datasets/HiTZ/GuideX_pre-training_data/commit/cd49c916c83e24a1c42a9bc3c821a2735bb63707
and this is the project page: https://neilus03.github.io/guidex.com/