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

Libraries

How to use ncoop57/cm_codeparrot with Transformers:

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

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

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

tokenizer = AutoTokenizer.from_pretrained("ncoop57/cm_codeparrot")
model = AutoModelForCausalLM.from_pretrained("ncoop57/cm_codeparrot", device_map="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use ncoop57/cm_codeparrot with vLLM:

Install from pip and serve model

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

Use Docker

docker model run hf.co/ncoop57/cm_codeparrot

SGLang

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

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

ncoop57 commited on Feb 21, 2022

Commit

15fa55a

1 Parent(s): b8a0716

Add log

Browse files

Files changed (1) hide show

log/debug_0.log +5 -0

log/debug_0.log CHANGED Viewed

@@ -370,3 +370,8 @@ Use FP16 precision: True
    e34b9d6..fda810b  absurd-shape-23 -> absurd-shape-23
 02/21/2022 00:13:13 - INFO - __main__ - Saving model after training

    e34b9d6..fda810b  absurd-shape-23 -> absurd-shape-23
 02/21/2022 00:13:13 - INFO - __main__ - Saving model after training
+02/21/2022 00:13:20 - WARNING - huggingface_hub.repository - Several commits (5) will be pushed upstream.
+02/21/2022 00:13:20 - WARNING - huggingface_hub.repository - The progress bars may be unreliable.
+02/21/2022 00:13:21 - WARNING - huggingface_hub.repository - To https://huggingface.co/ncoop57/cm_codeparrot
+   fda810b..b8a0716  absurd-shape-23 -> absurd-shape-23