Instructions to use ngoan/NgoanYi with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use ngoan/NgoanYi with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("text-generation", model="ngoan/NgoanYi")# Load model directly from transformers import AutoTokenizer, AutoModel tokenizer = AutoTokenizer.from_pretrained("ngoan/NgoanYi") model = AutoModel.from_pretrained("ngoan/NgoanYi") - Notebooks
- Google Colab
- Kaggle
- Local Apps
- vLLM
How to use ngoan/NgoanYi with vLLM:
Install from pip and serve model
# Install vLLM from pip: pip install vllm # Start the vLLM server: vllm serve "ngoan/NgoanYi" # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:8000/v1/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "ngoan/NgoanYi", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }'Use Docker
docker model run hf.co/ngoan/NgoanYi
- SGLang
How to use ngoan/NgoanYi 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 "ngoan/NgoanYi" \ --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": "ngoan/NgoanYi", "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 "ngoan/NgoanYi" \ --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": "ngoan/NgoanYi", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }' - Docker Model Runner
How to use ngoan/NgoanYi with Docker Model Runner:
docker model run hf.co/ngoan/NgoanYi
Model Card for NgoanYI
Overview
Model Name: NgoanYI
Base Model: Yi-34B
Version: 1.0
Developed by: Pham Van Ngoan
Description
NgoanYI is a specialized chat model, fine-tuned on the Yi-34B architecture. It is designed to provide enhanced performance in conversation-based applications. The model has been trained specifically on three distinct datasets:
Garage-bAInd/Open-Platypus
TIGER-Lab/MathInstruct
SUSTech/prm800k
Training
NgoanYI's training was conducted over one epoch, with the intent of testing and validating the model's initial capabilities. This approach provides insights into the model's performance, while setting the stage for further refinements in future iterations.
Contact Information
For more information, queries, or feedback regarding the NgoanYI model, please contact:
Email: ngoanpham1196@gmail.com
- Downloads last month
- 974