Instructions to use chincyk/PyCodeGen with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use chincyk/PyCodeGen with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("text-generation", model="chincyk/PyCodeGen")# Load model directly from transformers import AutoTokenizer, AutoModelForCausalLM tokenizer = AutoTokenizer.from_pretrained("chincyk/PyCodeGen") model = AutoModelForCausalLM.from_pretrained("chincyk/PyCodeGen") - Notebooks
- Google Colab
- Kaggle
- Local Apps Settings
- vLLM
How to use chincyk/PyCodeGen with vLLM:
Install from pip and serve model
# Install vLLM from pip: pip install vllm # Start the vLLM server: vllm serve "chincyk/PyCodeGen" # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:8000/v1/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "chincyk/PyCodeGen", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }'Use Docker
docker model run hf.co/chincyk/PyCodeGen
- SGLang
How to use chincyk/PyCodeGen 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 "chincyk/PyCodeGen" \ --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": "chincyk/PyCodeGen", "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 "chincyk/PyCodeGen" \ --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": "chincyk/PyCodeGen", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }' - Docker Model Runner
How to use chincyk/PyCodeGen with Docker Model Runner:
docker model run hf.co/chincyk/PyCodeGen
Update README.md
Browse files
README.md
CHANGED
|
@@ -89,8 +89,4 @@ Finetuning:
|
|
| 89 |
- learning_rate = 3e-4
|
| 90 |
- weight_decay = 0.01
|
| 91 |
- lr_scheduler_name = "cosine"
|
| 92 |
-
- num_warmup_steps = 190
|
| 93 |
-
|
| 94 |
-
|
| 95 |
-
|
| 96 |
-
## Citation [optional]
|
|
|
|
| 89 |
- learning_rate = 3e-4
|
| 90 |
- weight_decay = 0.01
|
| 91 |
- lr_scheduler_name = "cosine"
|
| 92 |
+
- num_warmup_steps = 190
|
|
|
|
|
|
|
|
|
|
|
|