Instructions to use Salesforce/codet5-large with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use Salesforce/codet5-large with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("text-generation", model="Salesforce/codet5-large")# Load model directly from transformers import AutoTokenizer, AutoModelWithLMHead tokenizer = AutoTokenizer.from_pretrained("Salesforce/codet5-large") model = AutoModelWithLMHead.from_pretrained("Salesforce/codet5-large") - Notebooks
- Google Colab
- Kaggle
- Local Apps
- vLLM
How to use Salesforce/codet5-large with vLLM:
Install from pip and serve model
# Install vLLM from pip: pip install vllm # Start the vLLM server: vllm serve "Salesforce/codet5-large" # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:8000/v1/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "Salesforce/codet5-large", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }'Use Docker
docker model run hf.co/Salesforce/codet5-large
- SGLang
How to use Salesforce/codet5-large 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 "Salesforce/codet5-large" \ --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": "Salesforce/codet5-large", "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 "Salesforce/codet5-large" \ --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": "Salesforce/codet5-large", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }' - Docker Model Runner
How to use Salesforce/codet5-large with Docker Model Runner:
docker model run hf.co/Salesforce/codet5-large
train custom dataset for codegeneration
#2
by ritheshwar - opened
hi,
i want to create a mini code generation model for a custom scripting language. I'm currently using the translation model to train codet5, but the results are not satisfactory. is here any other approach that can be used to train the model with the custom dataset?
thanks in advance