Instructions to use imodels/gpt-neo-2.7B-titles with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use imodels/gpt-neo-2.7B-titles with Transformers:

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

pipe = pipeline("text-generation", model="imodels/gpt-neo-2.7B-titles")

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

tokenizer = AutoTokenizer.from_pretrained("imodels/gpt-neo-2.7B-titles")
model = AutoModelForCausalLM.from_pretrained("imodels/gpt-neo-2.7B-titles", device_map="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use imodels/gpt-neo-2.7B-titles with vLLM:

Install from pip and serve model

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

Use Docker

docker model run hf.co/imodels/gpt-neo-2.7B-titles

SGLang

How to use imodels/gpt-neo-2.7B-titles 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 "imodels/gpt-neo-2.7B-titles" \
    --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": "imodels/gpt-neo-2.7B-titles",
		"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 "imodels/gpt-neo-2.7B-titles" \
        --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": "imodels/gpt-neo-2.7B-titles",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use imodels/gpt-neo-2.7B-titles with Docker Model Runner:
```
docker model run hf.co/imodels/gpt-neo-2.7B-titles
```

Full code and details at https://github.com/csinva/gpt-paper-title-generator

Model

finetunes starting from thegpt-neo-2.7B checkpoint
- for training details see the training script
inference
- should prepend with a year and two newlines before querying for a title, e.g. 2022\n\n

from transformers import AutoModelForCausalLM, pipeline, AutoTokenizer
model = AutoModelForCausalLM.from_pretrained("csinva/gpt-neo-2.7B-titles")
tokenizer = AutoTokenizer.from_pretrained("EleutherAI/gpt-neo-2.7B")
pipe = pipeline('text-generation', model=model, tokenizer=tokenizer)
pipe('2022\n\n')

Data

all papers on arXiv in the categories cs.AI, cs.LG, stat.ML
- date cutoff: only finetuned on papers with dat on or before Apr 1, 2022
- random 5% of papers also excluded
- this results in 98,388 papers for finetuning
during finetuning each paper title was given starting with the prompt <year>\n\n <title>\n (e.g. 2022\n\n Emb-GAM: an Interpretable and Efficient Predictor using Pre-trained Language Models\n)

Downloads last month: 10