Instructions to use nuprl/MultiPL-T-StarCoder2_15B with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use nuprl/MultiPL-T-StarCoder2_15B with Transformers:

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

pipe = pipeline("text-generation", model="nuprl/MultiPL-T-StarCoder2_15B")

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("nuprl/MultiPL-T-StarCoder2_15B")
model = AutoModelForCausalLM.from_pretrained("nuprl/MultiPL-T-StarCoder2_15B")

Notebooks
Google Colab
Kaggle
Local Apps

vLLM

How to use nuprl/MultiPL-T-StarCoder2_15B with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "nuprl/MultiPL-T-StarCoder2_15B"
# 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-StarCoder2_15B",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/nuprl/MultiPL-T-StarCoder2_15B

SGLang

How to use nuprl/MultiPL-T-StarCoder2_15B 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-StarCoder2_15B" \
    --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-StarCoder2_15B",
		"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-StarCoder2_15B" \
        --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-StarCoder2_15B",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use nuprl/MultiPL-T-StarCoder2_15B with Docker Model Runner:
```
docker model run hf.co/nuprl/MultiPL-T-StarCoder2_15B
```

arjunguha commited on Jun 24, 2024

Commit

e7a6f85

verified ·

1 Parent(s): 89f2357

Update README.md

Browse files

Files changed (1) hide show

README.md +2 -3

README.md CHANGED Viewed

@@ -7,7 +7,7 @@ datasets:
 # MultiPL-T StarCoder2-15b-{lua,ml,rkt}
-This repository holds several [StarCoder2-15b](https://huggingface.co/bigcode/starcoder2-15b) 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.
@@ -25,5 +25,4 @@ For more information the training process, see the MultiPL-T paper:
 }
 ```
-For usage instructions, see the [Model Card for StarCoder2](https://huggingface.co/bigcode/starcoder2-15b).
-Replace the model name `bigcode/starcoder2-15b` with the name of this repository, and set `revision=COMMIT_HASH`.

 # MultiPL-T StarCoder2-15b-{lua,ml,rkt}
+This repository holds several [CodeLlama-13b](https://huggingface.co/meta-llama/CodeLlama-13b-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 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`.