Instructions to use nuprl/MultiPL-T-DeepSeekCoder_33b with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use nuprl/MultiPL-T-DeepSeekCoder_33b with Transformers:

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

pipe = pipeline("text-generation", model="nuprl/MultiPL-T-DeepSeekCoder_33b")

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("nuprl/MultiPL-T-DeepSeekCoder_33b")
model = AutoModelForCausalLM.from_pretrained("nuprl/MultiPL-T-DeepSeekCoder_33b", device_map="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use nuprl/MultiPL-T-DeepSeekCoder_33b with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "nuprl/MultiPL-T-DeepSeekCoder_33b"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "nuprl/MultiPL-T-DeepSeekCoder_33b",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/nuprl/MultiPL-T-DeepSeekCoder_33b

SGLang

How to use nuprl/MultiPL-T-DeepSeekCoder_33b 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 "nuprl/MultiPL-T-DeepSeekCoder_33b" \
    --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": "nuprl/MultiPL-T-DeepSeekCoder_33b",
		"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 "nuprl/MultiPL-T-DeepSeekCoder_33b" \
        --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": "nuprl/MultiPL-T-DeepSeekCoder_33b",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use nuprl/MultiPL-T-DeepSeekCoder_33b with Docker Model Runner:
```
docker model run hf.co/nuprl/MultiPL-T-DeepSeekCoder_33b
```

MultiPL-T-DeepSeekCoder_33b / README.md

arjunguha

Update README.md

420f7df verified about 2 years ago

preview code

Raw

History Blame

1.05 kB

	---
	library_name: transformers
	license: openrail
	datasets:
	- nuprl/MultiPL-T
	---


	# MultiPL-T DeepSeekCoder-33b-Base

	This repository holds a [DeepSeekCoder-33b-base](https://huggingface.co/deepseek-ai/deepseek-coder-33b-base) fine-tune
	on MultiPL-T Racket.
	Examine the commit message to determine the language and checkpoint. We have a checkpoint
	for each epoch.


	For more information the training process, see the MultiPL-T paper:

	```
	@misc{cassano:multipl-t,
	title={Knowledge Transfer from High-Resource to Low-Resource Programming Languages for Code LLMs},
	author={Federico Cassano and John Gouwar and Francesca Lucchetti and Claire Schlesinger and Anders Freeman and Carolyn Jane Anderson and Molly Q Feldman and Michael Greenberg and Abhinav Jangda and Arjun Guha},
	year={2024},
	eprint={2308.09895},
	archivePrefix={arXiv},
	primaryClass={cs.PL}
	}
	```

	For usage instructions, see the model card for the original model. Replace the model name with the name of this repository, and set `revision=COMMIT_HASH`.