Instructions to use yanghuattt/microsoft_CodeGPT-small-java_1_ft_clm with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use yanghuattt/microsoft_CodeGPT-small-java_1_ft_clm with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("text-generation", model="yanghuattt/microsoft_CodeGPT-small-java_1_ft_clm")# pip install -U transformers accelerate # Load model directly from transformers import AutoTokenizer, AutoModelForCausalLM tokenizer = AutoTokenizer.from_pretrained("yanghuattt/microsoft_CodeGPT-small-java_1_ft_clm") model = AutoModelForCausalLM.from_pretrained("yanghuattt/microsoft_CodeGPT-small-java_1_ft_clm", device_map="auto") - Notebooks
- Google Colab
- Kaggle
- Local Apps Settings
- vLLM
How to use yanghuattt/microsoft_CodeGPT-small-java_1_ft_clm with vLLM:
Install from pip and serve model
# Install vLLM from pip: pip install vllm # Start the vLLM server: vllm serve "yanghuattt/microsoft_CodeGPT-small-java_1_ft_clm" # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:8000/v1/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "yanghuattt/microsoft_CodeGPT-small-java_1_ft_clm", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }'Use Docker
docker model run hf.co/yanghuattt/microsoft_CodeGPT-small-java_1_ft_clm
- SGLang
How to use yanghuattt/microsoft_CodeGPT-small-java_1_ft_clm 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 "yanghuattt/microsoft_CodeGPT-small-java_1_ft_clm" \ --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": "yanghuattt/microsoft_CodeGPT-small-java_1_ft_clm", "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 "yanghuattt/microsoft_CodeGPT-small-java_1_ft_clm" \ --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": "yanghuattt/microsoft_CodeGPT-small-java_1_ft_clm", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }' - Docker Model Runner
How to use yanghuattt/microsoft_CodeGPT-small-java_1_ft_clm with Docker Model Runner:
docker model run hf.co/yanghuattt/microsoft_CodeGPT-small-java_1_ft_clm
Download all_results.json from yanghuattt/microsoft_CodeGPT-small-java_1_ft_clm: direct link, hf CLI and curl.
- Browser
- Download file 478 Bytes
-
https://huggingface.co/yanghuattt/microsoft_CodeGPT-small-java_1_ft_clm/resolve/main/all_results.json
- Command line
-
hf download hf://yanghuattt/microsoft_CodeGPT-small-java_1_ft_clm/all_results.json
-
curl -L -o all_results.json https://huggingface.co/yanghuattt/microsoft_CodeGPT-small-java_1_ft_clm/resolve/main/all_results.json
478 Bytes
| { | |
| "epoch": 5.0, | |
| "eval_accuracy": 0.7564910391618287, | |
| "eval_loss": 1.2840659618377686, | |
| "eval_runtime": 84.9049, | |
| "eval_samples": 4924, | |
| "eval_samples_per_second": 57.994, | |
| "eval_steps_per_second": 2.426, | |
| "perplexity": 3.6112932956782884, | |
| "total_flos": 8.315357626368e+16, | |
| "train_loss": 0.615904873986939, | |
| "train_runtime": 4775.4033, | |
| "train_samples": 31824, | |
| "train_samples_per_second": 33.321, | |
| "train_steps_per_second": 1.042 | |
| } |