Instructions to use ncoop57/codeparrot-py with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use ncoop57/codeparrot-py with Transformers:

# Use a pipeline as a high-level helper
from transformers import pipeline

pipe = pipeline("text-generation", model="ncoop57/codeparrot-py")

# pip install -U transformers accelerate
# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("ncoop57/codeparrot-py")
model = AutoModelForCausalLM.from_pretrained("ncoop57/codeparrot-py", device_map="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use ncoop57/codeparrot-py with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "ncoop57/codeparrot-py"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "ncoop57/codeparrot-py",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/ncoop57/codeparrot-py

SGLang

How to use ncoop57/codeparrot-py 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 "ncoop57/codeparrot-py" \
    --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": "ncoop57/codeparrot-py",
		"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 "ncoop57/codeparrot-py" \
        --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": "ncoop57/codeparrot-py",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use ncoop57/codeparrot-py with Docker Model Runner:
```
docker model run hf.co/ncoop57/codeparrot-py
```

ncoop57 commited on Jan 23, 2022

Commit

3ff3565

1 Parent(s): 9362dd8

step 40000

Browse files

Files changed (2) hide show

log/debug_0.log +0 -0
pytorch_model.bin +1 -1

log/debug_0.log CHANGED Viewed

The diff for this file is too large to render. See raw diff

pytorch_model.bin CHANGED Viewed

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:dde957e57fe967a124e38f9af33a7bade730558befa9920f0e3565817b91c775
 size 1584804775

 version https://git-lfs.github.com/spec/v1
+oid sha256:108e82e5efdce52217961145eeb8957e239d3d02d882b8df66f20d641916f533
 size 1584804775