Instructions to use nuprl/MultiPL-T-CodeLlama_34b with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use nuprl/MultiPL-T-CodeLlama_34b with Transformers:

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

pipe = pipeline("text-generation", model="nuprl/MultiPL-T-CodeLlama_34b")

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("nuprl/MultiPL-T-CodeLlama_34b")
model = AutoModelForCausalLM.from_pretrained("nuprl/MultiPL-T-CodeLlama_34b")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use nuprl/MultiPL-T-CodeLlama_34b with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "nuprl/MultiPL-T-CodeLlama_34b"
# 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-CodeLlama_34b",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/nuprl/MultiPL-T-CodeLlama_34b

SGLang

How to use nuprl/MultiPL-T-CodeLlama_34b 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-CodeLlama_34b" \
    --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-CodeLlama_34b",
		"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-CodeLlama_34b" \
        --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-CodeLlama_34b",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use nuprl/MultiPL-T-CodeLlama_34b with Docker Model Runner:
```
docker model run hf.co/nuprl/MultiPL-T-CodeLlama_34b
```

arjunguha commited on Jun 24, 2024

Commit

8f912dc

verified ·

1 Parent(s): 661fefe

Create README.md

Browse files

Files changed (1) hide show

README.md +28 -0

README.md ADDED Viewed

	@@ -0,0 +1,28 @@

+---
+library_name: transformers
+license: openrail
+datasets:
+- nuprl/MultiPL-T
+---
+# MultiPL-T CodeLlama-34b
+This repository holds several [CodeLlama-34b](https://huggingface.co/meta-llama/CodeLlama-34b-hf) fine-tunes, all fine-tuned on MultiPL-T data.
+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`.