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

Libraries

How to use codeparrot/codeparrot-small-multi with Transformers:

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

pipe = pipeline("text-generation", model="codeparrot/codeparrot-small-multi")

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("codeparrot/codeparrot-small-multi")
model = AutoModelForCausalLM.from_pretrained("codeparrot/codeparrot-small-multi")

Notebooks
Google Colab
Kaggle
Local Apps

vLLM

How to use codeparrot/codeparrot-small-multi with vLLM:

Install from pip and serve model

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

Use Docker

docker model run hf.co/codeparrot/codeparrot-small-multi

SGLang

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

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

codeparrot-small-multi / README.md

loubnabnl HF Staff

Update README.md

7753edb almost 4 years ago

preview code

raw

history blame contribute delete

2.18 kB

	---
	language:
	- code
	license: apache-2.0
	tags:
	- code
	- gpt2
	- generation
	datasets:
	- "codeparrot/github-code-clean"
	- "openai_humaneval"
	metrics:
	- "evaluate-metric/code_eval"
	---

	# CodeParrot-Multi 🦜 (small)

	CodeParrot-Multi 🦜 is a GPT-2 model (110M parameters) trained to generate code in 9 programming languages: "Java", "JavaScript", "PHP", "Python", "C#", "C++", "GO", "Ruby" and "TypeScript".

	## Usage

	You can load the CodeParrot-Multi model and tokenizer directly in `transformers`:

	```Python
	from transformers import AutoTokenizer, AutoModelWithLMHead

	tokenizer = AutoTokenizer.from_pretrained("codeparrot/codeparrot-small-multi")
	model = AutoModelWithLMHead.from_pretrained("codeparrot/codeparrot-small-multi")

	inputs = tokenizer("def hello_world():", return_tensors="pt")
	outputs = model(**inputs)
	```

	or with a `pipeline`:

	```Python
	from transformers import pipeline

	pipe = pipeline("text-generation", model="codeparrot/codeparrot-small-multi")
	outputs = pipe("def hello_world():")
	```

	## Training

	The model was trained on the small [Github code small](https://huggingface.co/datasets/loubnabnl/github-small-near-dedup) after near deduplication, a subset of [Github code dataset](https://huggingface.co/datasets/codeparrot/github-code-clean) with the following settings:

	\|Config\|Value\|
	\|-------\|-----\|
	\|Batch size\| 192 \|
	\|Context size\| 1024 \|
	\|Training steps\| 300'000\|
	\|Gradient accumulation\| 2\|
	\|Gradient checkpointing\| False\|
	\|Learning rate\| 5e-4 \|
	\|Weight decay \| 0.1 \|
	\|Warmup steps\| 2000 \|
	\|Schedule\| Cosine \|

	The training was executed on 16 x A100 (40GB) GPUs. This setting amounts to roughly 58 billion tokens.

	## Performance

	We evaluated the model on OpenAI's [HumanEval](https://huggingface.co/datasets/openai_humaneval) benchmark which consists of programming challenges:

	\| Metric \| Value \|
	\|-------\|-----\|
	\|pass@1 \| --% \|
	\|pass@10 \| --% \|
	\|pass@100 \| --% \|

	The [pass@k metric](https://huggingface.co/metrics/code_eval) tells the probability that at least one out of k generations passes the tests.

	## Resources

	- Code: [repository](https://github.com/huggingface/transformers/tree/master/examples/research_projects/codeparrot)