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
```

rooa commited on Oct 3, 2022

Commit

86e5d4c

1 Parent(s): 9f7ee3c

Set model_max_length to 2048

Browse files

Files changed (1) hide show

tokenizer_config.json +1 -1

tokenizer_config.json CHANGED Viewed

	@@ -1 +1 @@
1	- {"unk_token": "<\|endoftext\|>", "bos_token": "<\|endoftext\|>", "eos_token": "<\|endoftext\|>", "add_prefix_space": false, "model_max_length": ~~1e+20~~, "special_tokens_map_file": null, "name_or_path": "gpt2", "tokenizer_class": "CodeGenTokenizer"}


1	+ {"unk_token": "<\|endoftext\|>", "bos_token": "<\|endoftext\|>", "eos_token": "<\|endoftext\|>", "add_prefix_space": false, "model_max_length": 2048, "special_tokens_map_file": null, "name_or_path": "gpt2", "tokenizer_class": "CodeGenTokenizer"}