Instructions to use LegionIntel/yurts-python-code-gen-30-sparse with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use LegionIntel/yurts-python-code-gen-30-sparse with Transformers:

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

pipe = pipeline("text-generation", model="LegionIntel/yurts-python-code-gen-30-sparse")

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("LegionIntel/yurts-python-code-gen-30-sparse")
model = AutoModelForCausalLM.from_pretrained("LegionIntel/yurts-python-code-gen-30-sparse")

Notebooks
Google Colab
Kaggle
Local Apps

vLLM

How to use LegionIntel/yurts-python-code-gen-30-sparse with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "LegionIntel/yurts-python-code-gen-30-sparse"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "LegionIntel/yurts-python-code-gen-30-sparse",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/LegionIntel/yurts-python-code-gen-30-sparse

SGLang

How to use LegionIntel/yurts-python-code-gen-30-sparse 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 "LegionIntel/yurts-python-code-gen-30-sparse" \
    --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": "LegionIntel/yurts-python-code-gen-30-sparse",
		"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 "LegionIntel/yurts-python-code-gen-30-sparse" \
        --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": "LegionIntel/yurts-python-code-gen-30-sparse",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use LegionIntel/yurts-python-code-gen-30-sparse with Docker Model Runner:
```
docker model run hf.co/LegionIntel/yurts-python-code-gen-30-sparse
```

yurts-python-code-gen-30-sparse / added_tokens.json

William Du

Init sparsified 30% version of python-tuned code gen model

cdd067e over 3 years ago

raw

history blame

1.13 kB

	{
	"\t\t": 50294,
	"\t\t\t": 50293,
	"\t\t\t\t": 50292,
	"\t\t\t\t\t": 50291,
	"\t\t\t\t\t\t": 50290,
	"\t\t\t\t\t\t\t": 50289,
	"\t\t\t\t\t\t\t\t": 50288,
	"\t\t\t\t\t\t\t\t\t": 50287,
	" ": 50286,
	" ": 50285,
	" ": 50284,
	" ": 50283,
	" ": 50282,
	" ": 50281,
	" ": 50280,
	" ": 50279,
	" ": 50278,
	" ": 50277,
	" ": 50276,
	" ": 50275,
	" ": 50274,
	" ": 50273,
	" ": 50272,
	" ": 50271,
	" ": 50270,
	" ": 50269,
	" ": 50268,
	" ": 50267,
	" ": 50266,
	" ": 50265,
	" ": 50264,
	" ": 50263,
	" ": 50262,
	" ": 50261,
	" ": 50260,
	" ": 50259,
	" ": 50258,
	" ": 50257,
	"<\|pad\|>": 50296,
	"<\|startoftext\|>": 50295
	}