Instructions to use sr5434/InstructCodegen-350M-mono with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use sr5434/InstructCodegen-350M-mono with Transformers:

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

pipe = pipeline("text-generation", model="sr5434/InstructCodegen-350M-mono")

# pip install -U transformers accelerate
# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("sr5434/InstructCodegen-350M-mono")
model = AutoModelForCausalLM.from_pretrained("sr5434/InstructCodegen-350M-mono", device_map="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use sr5434/InstructCodegen-350M-mono with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "sr5434/InstructCodegen-350M-mono"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "sr5434/InstructCodegen-350M-mono",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/sr5434/InstructCodegen-350M-mono

SGLang

How to use sr5434/InstructCodegen-350M-mono 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 "sr5434/InstructCodegen-350M-mono" \
    --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": "sr5434/InstructCodegen-350M-mono",
		"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 "sr5434/InstructCodegen-350M-mono" \
        --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": "sr5434/InstructCodegen-350M-mono",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use sr5434/InstructCodegen-350M-mono with Docker Model Runner:
```
docker model run hf.co/sr5434/InstructCodegen-350M-mono
```

InstructCodegen-350M-mono

Commit History

Apr 23, 2023

15:35
Adding `safetensors` variant of this model⁠

SFconvertbot

60b8455

Apr 22, 2023

20:06
Update README.md

sr5434

0ebdb61
20:04
update model card README.md

sr5434

35b71ce
20:02
End of training

sr5434

9f4cff9
20:01
initial commit

sr5434

84711fa

Commit History

Apr 23, 2023

Adding `safetensors` variant of this model⁠

Apr 22, 2023

Update README.md

update model card README.md

End of training

initial commit