Instructions to use Deepthoughtworks/gpt-neo-2.7B__low-cpu with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use Deepthoughtworks/gpt-neo-2.7B__low-cpu with Transformers:

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

pipe = pipeline("text-generation", model="Deepthoughtworks/gpt-neo-2.7B__low-cpu")

# pip install -U transformers accelerate
# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("Deepthoughtworks/gpt-neo-2.7B__low-cpu")
model = AutoModelForCausalLM.from_pretrained("Deepthoughtworks/gpt-neo-2.7B__low-cpu", device_map="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use Deepthoughtworks/gpt-neo-2.7B__low-cpu with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "Deepthoughtworks/gpt-neo-2.7B__low-cpu"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "Deepthoughtworks/gpt-neo-2.7B__low-cpu",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/Deepthoughtworks/gpt-neo-2.7B__low-cpu

SGLang

How to use Deepthoughtworks/gpt-neo-2.7B__low-cpu 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 "Deepthoughtworks/gpt-neo-2.7B__low-cpu" \
    --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": "Deepthoughtworks/gpt-neo-2.7B__low-cpu",
		"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 "Deepthoughtworks/gpt-neo-2.7B__low-cpu" \
        --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": "Deepthoughtworks/gpt-neo-2.7B__low-cpu",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use Deepthoughtworks/gpt-neo-2.7B__low-cpu with Docker Model Runner:
```
docker model run hf.co/Deepthoughtworks/gpt-neo-2.7B__low-cpu
```

gpt-neo-2.7B__low-cpu / handler.py

fwittel

philschmid

Update handler.py (#1)

9bd5173 almost 4 years ago

Raw History Blame Contribute Delete

1.2 kB

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

# check for GPU
device = 0 if torch.cuda.is_available() else -1


class EndpointHandler:
    def __init__(self, path=""):
        # load the model
        tokenizer = AutoTokenizer.from_pretrained(path)
        # model = AutoModel.from_pretrained(path, low_cpu_mem_usage=True)
        # model = AutoModelForCausalLM.from_pretrained(path, low_cpu_mem_usage=True)
        model = AutoModelForCausalLM.from_pretrained(path, low_cpu_mem_usage=True)
        # create inference pipeline
        self.pipeline = pipeline("text-generation", model=model, tokenizer=tokenizer, device=device)

    def __call__(self, data: Any) -> List[List[Dict[str, float]]]:
        inputs = data.pop("inputs", data)
        parameters = data.pop("parameters", None)

        # pass inputs with all kwargs in data
        if parameters is not None:
            prediction = self.pipeline(inputs, **parameters)
        else:
            prediction = self.pipeline(inputs)
        # postprocess the prediction
        return prediction

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

	# check for GPU
	device = 0 if torch.cuda.is_available() else -1


	class EndpointHandler:
	def __init__(self, path=""):
	# load the model
	tokenizer = AutoTokenizer.from_pretrained(path)
	# model = AutoModel.from_pretrained(path, low_cpu_mem_usage=True)
	# model = AutoModelForCausalLM.from_pretrained(path, low_cpu_mem_usage=True)
	model = AutoModelForCausalLM.from_pretrained(path, low_cpu_mem_usage=True)
	# create inference pipeline
	self.pipeline = pipeline("text-generation", model=model, tokenizer=tokenizer, device=device)

	def __call__(self, data: Any) -> List[List[Dict[str, float]]]:
	inputs = data.pop("inputs", data)
	parameters = data.pop("parameters", None)

	# pass inputs with all kwargs in data
	if parameters is not None:
	prediction = self.pipeline(inputs, **parameters)
	else:
	prediction = self.pipeline(inputs)
	# postprocess the prediction
	return prediction