Instructions to use ncoop57/code-clippy-125M-py with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use ncoop57/code-clippy-125M-py with Transformers:

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

pipe = pipeline("text-generation", model="ncoop57/code-clippy-125M-py")

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("ncoop57/code-clippy-125M-py")
model = AutoModelForCausalLM.from_pretrained("ncoop57/code-clippy-125M-py")

Notebooks
Google Colab
Kaggle
Local Apps

vLLM

How to use ncoop57/code-clippy-125M-py with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "ncoop57/code-clippy-125M-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/code-clippy-125M-py",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/ncoop57/code-clippy-125M-py

SGLang

How to use ncoop57/code-clippy-125M-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/code-clippy-125M-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/code-clippy-125M-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/code-clippy-125M-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/code-clippy-125M-py",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use ncoop57/code-clippy-125M-py with Docker Model Runner:
```
docker model run hf.co/ncoop57/code-clippy-125M-py
```

ncoop57 commited on Dec 29, 2021

Commit

8b49d56

1 Parent(s): f24b640

final model

Browse files

Files changed (1) hide show

log/debug_0.log +3 -0

log/debug_0.log CHANGED Viewed

@@ -52592,3 +52592,6 @@ Use FP16 precision: False
 12/29/2021 13:04:23 - INFO - codeparrot_training - Step 49999: {'lr': 4.969528122344969e-13, 'samples': 25600000, 'steps': 49999, 'batch_loss/train': 0.7188061801716685}
 12/29/2021 13:04:23 - INFO - codeparrot_training - Evaluating and saving model checkpoint
 12/29/2021 13:07:47 - INFO - codeparrot_training - Step 50000: {'loss/eval': 0.7400861382484436, 'perplexity': 2.096116065979004}

 12/29/2021 13:04:23 - INFO - codeparrot_training - Step 49999: {'lr': 4.969528122344969e-13, 'samples': 25600000, 'steps': 49999, 'batch_loss/train': 0.7188061801716685}
 12/29/2021 13:04:23 - INFO - codeparrot_training - Evaluating and saving model checkpoint
 12/29/2021 13:07:47 - INFO - codeparrot_training - Step 50000: {'loss/eval': 0.7400861382484436, 'perplexity': 2.096116065979004}
+12/29/2021 13:08:05 - WARNING - huggingface_hub.repository - Several commits (18) will be pushed upstream.
+12/29/2021 13:08:08 - INFO - codeparrot_training - Evaluating and saving model after training
+12/29/2021 13:11:30 - INFO - codeparrot_training - Step 1600000: {'loss/eval': 0.7400861382484436, 'perplexity': 2.096116065979004}