Instructions to use Salesforce/codegen-2B-mono with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use Salesforce/codegen-2B-mono with Transformers:

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

pipe = pipeline("text-generation", model="Salesforce/codegen-2B-mono")

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("Salesforce/codegen-2B-mono")
model = AutoModelForCausalLM.from_pretrained("Salesforce/codegen-2B-mono")

Notebooks
Google Colab
Kaggle
Local Apps

vLLM

How to use Salesforce/codegen-2B-mono with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "Salesforce/codegen-2B-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-2B-mono",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/Salesforce/codegen-2B-mono

SGLang

How to use Salesforce/codegen-2B-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-2B-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-2B-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-2B-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-2B-mono",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use Salesforce/codegen-2B-mono with Docker Model Runner:
```
docker model run hf.co/Salesforce/codegen-2B-mono
```

rooa commited on Jun 28, 2022

Commit

e1bf58f

1 Parent(s): 970beaf

Update README.md

Browse files

Files changed (1) hide show

README.md +3 -3

README.md CHANGED Viewed

@@ -16,7 +16,7 @@ This checkpoint (CodeGen-Mono 2B) was firstly initialized with *CodeGen-Multi 2B
 ## Training procedure
 CodeGen was trained using cross-entropy loss to maximize the likelihood of sequential inputs.
-The family of models are trained using 4 TPU-v4 chips by Google, leveraging data and model parallelism.
 See Section 2.3 of the [paper](https://arxiv.org/abs/2203.13474) for more details.
 ## Evaluation results
@@ -35,8 +35,8 @@ This model can be easily loaded using the `AutoModelForCausalLM` functionality:
 ```python
 from transformers import AutoTokenizer, AutoModelForCausalLM
-tokenizer = AutoTokenizer.from_pretrained('Salesforce/codegen-2B-mono')
-model = AutoModelForCausalLM.from_pretrained('Salesforce/codegen-2B-mono')
 text = "def hello_world():"
 input_ids = tokenizer(text, return_tensors="pt").input_ids

 ## Training procedure
 CodeGen was trained using cross-entropy loss to maximize the likelihood of sequential inputs.
+The family of models are trained using multiple TPU-v4-512 by Google, leveraging data and model parallelism.
 See Section 2.3 of the [paper](https://arxiv.org/abs/2203.13474) for more details.
 ## Evaluation results
 ```python
 from transformers import AutoTokenizer, AutoModelForCausalLM
+tokenizer = AutoTokenizer.from_pretrained("Salesforce/codegen-2B-mono")
+model = AutoModelForCausalLM.from_pretrained("Salesforce/codegen-2B-mono")
 text = "def hello_world():"
 input_ids = tokenizer(text, return_tensors="pt").input_ids