Instructions to use Salesforce/codegen-350M-multi with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use Salesforce/codegen-350M-multi with Transformers:

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

pipe = pipeline("text-generation", model="Salesforce/codegen-350M-multi")

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("Salesforce/codegen-350M-multi")
model = AutoModelForCausalLM.from_pretrained("Salesforce/codegen-350M-multi")

Notebooks
Google Colab
Kaggle
Local Apps

vLLM

How to use Salesforce/codegen-350M-multi with vLLM:

Install from pip and serve model

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

Use Docker

docker model run hf.co/Salesforce/codegen-350M-multi

SGLang

How to use Salesforce/codegen-350M-multi 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 "Salesforce/codegen-350M-multi" \
    --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": "Salesforce/codegen-350M-multi",
		"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 "Salesforce/codegen-350M-multi" \
        --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": "Salesforce/codegen-350M-multi",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use Salesforce/codegen-350M-multi with Docker Model Runner:
```
docker model run hf.co/Salesforce/codegen-350M-multi
```

KeyError: 'codegen'

by EnriqueD - opened Jun 15, 2022

Discussion

EnriqueD

Jun 15, 2022

Hi all,

I am running the example from the "how to use" section of the model card. AutoModelForCausalLM.from_pretrained('Salesforce/codegen-350M-multi') gives a KeyError for 'codgen', the model_type in the config. This seems to imply that I am missing a model file or other dependency, does anyone know how to fix this? Thanks!

I am running transformers v4.19.4 btw.

rooa

Salesforce AI Research org Jun 15, 2022

Hi @EnriqueD ,

Thanks for your interest!!

This is because CodeGen hasn't been merged into the main branch yet (pull request). It should be ready on main branch very soon.
If you'd like to give the model a try, please take a look at the original repo here in the mean time.

I will ping here when the pull request is merged.

EnriqueD

Jun 18, 2022

Thanks for the prompt and helpful reply!
Looking forward to your ping!

rooa

Salesforce AI Research org Jun 24, 2022

Hi @EnriqueD ,

Good news, the pull request has just been merged! Could you please install transformers from the latest main branch and try again? Thanks!

EnriqueD

Jul 12, 2022

Hi @rooa ,
I just tested it out and it works fine now, thank you!

Upload images, audio, and videos by dragging in the text input, pasting, or clicking here.

Tap or paste here to upload images

· Sign up or log in to comment