Instructions to use ammarnasr/codegen2-1B-security with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use ammarnasr/codegen2-1B-security with Transformers:

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

pipe = pipeline("text-generation", model="ammarnasr/codegen2-1B-security", trust_remote_code=True)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("ammarnasr/codegen2-1B-security", trust_remote_code=True)
model = AutoModelForCausalLM.from_pretrained("ammarnasr/codegen2-1B-security", trust_remote_code=True)

Notebooks
Google Colab
Kaggle
Local Apps

vLLM

How to use ammarnasr/codegen2-1B-security with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "ammarnasr/codegen2-1B-security"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "ammarnasr/codegen2-1B-security",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/ammarnasr/codegen2-1B-security

SGLang

How to use ammarnasr/codegen2-1B-security 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 "ammarnasr/codegen2-1B-security" \
    --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": "ammarnasr/codegen2-1B-security",
		"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 "ammarnasr/codegen2-1B-security" \
        --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": "ammarnasr/codegen2-1B-security",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use ammarnasr/codegen2-1B-security with Docker Model Runner:
```
docker model run hf.co/ammarnasr/codegen2-1B-security
```

codegen2-1B-security / handler.py

ammarnasr

Update handler.py

b17ca17 over 2 years ago

raw

history blame

1.13 kB

	from typing import Any, Dict, List
	import torch
	import transformers
	from transformers import AutoModelForCausalLM, AutoTokenizer

	dtype = torch.bfloat16 if torch.cuda.get_device_capability()[0] ==8 else torch.float16

	class EndpointHandler:
	def __init__(self, path=""):
	self.tokenizer = AutoTokenizer.from_pretrained(path)
	self.model = AutoModelForCausalLM.from_pretrained(path, trust_remote_code=True, revision="main")
	self.device = torch.device("cuda" if torch.cuda.is_available() else "cpu")
	self.model = self.model.to(self.device)


	def __call__(self, data: Dict[str, Any]) -> Dict[str, Any]:
	prompt = data["inputs"]
	if "config" in data:
	config = data.pop("config", None)
	else:
	config = {'max_new_tokens':100}
	input_ids = self.tokenizer(prompt, return_tensors="pt").input_ids.to(self.device)
	generated_ids = self.model.generate(input_ids, **config)
	generated_text = self.tokenizer.decode(generated_ids[0], skip_special_tokens=True)
	return [{"generated_text": generated_text}]