Instructions to use Salesforce/codegen-6B-mono with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use Salesforce/codegen-6B-mono with Transformers:

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

pipe = pipeline("text-generation", model="Salesforce/codegen-6B-mono")

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("Salesforce/codegen-6B-mono")
model = AutoModelForCausalLM.from_pretrained("Salesforce/codegen-6B-mono")

Notebooks
Google Colab
Kaggle
Local Apps

vLLM

How to use Salesforce/codegen-6B-mono with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "Salesforce/codegen-6B-mono"
# 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-6B-mono",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/Salesforce/codegen-6B-mono

SGLang

How to use Salesforce/codegen-6B-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 "Salesforce/codegen-6B-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": "Salesforce/codegen-6B-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 "Salesforce/codegen-6B-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": "Salesforce/codegen-6B-mono",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use Salesforce/codegen-6B-mono with Docker Model Runner:
```
docker model run hf.co/Salesforce/codegen-6B-mono
```

codegen-6B-mono

Commit History

Update README.md

62dfb58
verified

enijkamp commited on Jan 31, 2025

Set model_max_length to 2048

86e5d4c

rooa commited on Oct 3, 2022

Fix eos_token_id

9f7ee3c

rooa commited on Oct 2, 2022

Update README.md

ee4939b

rooa commited on Jun 28, 2022

Update tokenizer_config.json

b9a8b86

rooa commited on Jun 28, 2022

Rename mask weights following the new model class

def4204

rooa commited on Jun 23, 2022

Initial commit

1cbc59d

rooa commited on Apr 13, 2022

initial commit

3de9d06

Hiroaki Hayashi commited on Apr 13, 2022

Commit History

Update README.md 62dfb58 verified

Set model_max_length to 2048 86e5d4c

Fix eos_token_id 9f7ee3c

Update README.md ee4939b

Update tokenizer_config.json b9a8b86

Rename mask weights following the new model class def4204

Initial commit 1cbc59d

initial commit 3de9d06