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

Libraries

How to use ncoop57/multi-code-clippy with Transformers:

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

pipe = pipeline("text-generation", model="ncoop57/multi-code-clippy")

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("ncoop57/multi-code-clippy")
model = AutoModelForCausalLM.from_pretrained("ncoop57/multi-code-clippy")

Notebooks
Google Colab
Kaggle
Local Apps

vLLM

How to use ncoop57/multi-code-clippy with vLLM:

Install from pip and serve model

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

Use Docker

docker model run hf.co/ncoop57/multi-code-clippy

SGLang

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

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

ncoop57 commited on Feb 26, 2022

Commit

3d5a900

1 Parent(s): 5aaf99c

final model

Browse files

Files changed (1) hide show

log/debug_0.log +7 -0

log/debug_0.log CHANGED Viewed

@@ -50602,3 +50602,10 @@ Use FP16 precision: False
 02/26/2022 18:19:44 - INFO - codeparrot_training - Step 49998: {'lr': 2.1418412321505543e-12, 'samples': 25599488, 'steps': 49998, 'loss/train': 2.184359073638916}
 02/26/2022 18:19:49 - INFO - codeparrot_training - Step 49999: {'lr': 5.354603149765325e-13, 'samples': 25600000, 'steps': 49999, 'loss/train': 2.408355236053467}
 02/26/2022 18:19:49 - INFO - codeparrot_training - Evaluating and saving model checkpoint

 02/26/2022 18:19:44 - INFO - codeparrot_training - Step 49998: {'lr': 2.1418412321505543e-12, 'samples': 25599488, 'steps': 49998, 'loss/train': 2.184359073638916}
 02/26/2022 18:19:49 - INFO - codeparrot_training - Step 49999: {'lr': 5.354603149765325e-13, 'samples': 25600000, 'steps': 49999, 'loss/train': 2.408355236053467}
 02/26/2022 18:19:49 - INFO - codeparrot_training - Evaluating and saving model checkpoint
+02/26/2022 18:20:07 - WARNING - huggingface_hub.repository - Several commits (50) will be pushed upstream.
+02/26/2022 18:20:07 - WARNING - huggingface_hub.repository - The progress bars may be unreliable.
+02/26/2022 18:20:52 - WARNING - huggingface_hub.repository - To https://huggingface.co/ncoop57/multi-code-clippy
+   508ef45..5aaf99c  floral-grass-11 -> floral-grass-11
+02/26/2022 18:20:53 - INFO - codeparrot_training - Evaluating and saving model after training
+02/26/2022 18:41:48 - INFO - codeparrot_training - Step 1600000: {'loss/eval': 1.6735893487930298, 'perplexity': 5.331269264221191}