Instructions to use Salesforce/codegen2-16B_P with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use Salesforce/codegen2-16B_P with Transformers:

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

pipe = pipeline("text-generation", model="Salesforce/codegen2-16B_P", trust_remote_code=True)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("Salesforce/codegen2-16B_P", trust_remote_code=True)
model = AutoModelForCausalLM.from_pretrained("Salesforce/codegen2-16B_P", trust_remote_code=True)

Notebooks
Google Colab
Kaggle
Local Apps

vLLM

How to use Salesforce/codegen2-16B_P with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "Salesforce/codegen2-16B_P"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "Salesforce/codegen2-16B_P",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/Salesforce/codegen2-16B_P

SGLang

How to use Salesforce/codegen2-16B_P 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/codegen2-16B_P" \
    --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/codegen2-16B_P",
		"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/codegen2-16B_P" \
        --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/codegen2-16B_P",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use Salesforce/codegen2-16B_P with Docker Model Runner:
```
docker model run hf.co/Salesforce/codegen2-16B_P
```

how file-level span corruption works?

by zeromquan - opened May 25, 2023

Discussion

zeromquan

May 25, 2023

It's no clear for the span corruption part. could you helps on it ?
in the paper, there is a simple description:
"We choose span corruption as the base infill objective following InCoder (Fried et al., 2022). However, we take a different approach in selecting the spans for corruption: (1) we first sample a dynamic ratio of sequence to mask out, (2)we then sample the span length and mask out locations such that the total number of tokens match the ratio of the original sequence determined earlier "

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