Instructions to use Salesforce/codegen-16B-mono with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use Salesforce/codegen-16B-mono with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("text-generation", model="Salesforce/codegen-16B-mono")# Load model directly from transformers import AutoTokenizer, AutoModelForCausalLM tokenizer = AutoTokenizer.from_pretrained("Salesforce/codegen-16B-mono") model = AutoModelForCausalLM.from_pretrained("Salesforce/codegen-16B-mono") - Notebooks
- Google Colab
- Kaggle
- Local Apps Settings
- vLLM
How to use Salesforce/codegen-16B-mono with vLLM:
Install from pip and serve model
# Install vLLM from pip: pip install vllm # Start the vLLM server: vllm serve "Salesforce/codegen-16B-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-16B-mono", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }'Use Docker
docker model run hf.co/Salesforce/codegen-16B-mono
- SGLang
How to use Salesforce/codegen-16B-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-16B-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-16B-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-16B-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-16B-mono", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }' - Docker Model Runner
How to use Salesforce/codegen-16B-mono with Docker Model Runner:
docker model run hf.co/Salesforce/codegen-16B-mono
Error executing the "How to use" snippet in Colab
Hey,
Using Colab, I'm trying to run the snippet found in the How to use model card section:
tokenizer = AutoTokenizer.from_pretrained('Salesforce/codegen-16B-mono')
model = AutoModelForCausalLM.from_pretrained('Salesforce/codegen-16B-mono')
text = "def hello_world():"
input_ids = tokenizer(text, return_tensors="pt").input_ids
generated_ids = model.generate(input_ids, max_length=128)
print(tokenizer.decode(generated_ids[0], skip_special_tokens=True))
But I get the following error:
---------------------------------------------------------------------------
KeyError Traceback (most recent call last)
<ipython-input-5-cf1f68aee96f> in <module>()
----> 1 model = AutoModelForCausalLM.from_pretrained('Salesforce/codegen-16B-mono')
2
3 text = "def hello_world():"
4 input_ids = tokenizer(text, return_tensors="pt").input_ids
5
2 frames
/usr/local/lib/python3.7/dist-packages/transformers/models/auto/configuration_auto.py in __getitem__(self, key)
430 return self._extra_content[key]
431 if key not in self._mapping:
--> 432 raise KeyError(key)
433 value = self._mapping[key]
434 module_name = model_type_to_module_name(key)
KeyError: 'codegen'
Note: I'm using transformers==4.20.1.
Thanks for the support
Hi! That was because the CodeGen model class had not been merged yet when you tried. It has just been merged into the main branch.
Could you install from the current main branch instead of 4.20.1 and try again?
Thanks.
Hi! That was because the CodeGen model class had not been merged yet when you tried. It has just been merged into the main branch.
Could you install from the current main branch instead of4.20.1and try again?Thanks.
Hey @rooa ,
thanks for the support: that works!
Great work BTW
- Simone