Instructions to use mrm8488/GPT-2-finetuned-common_gen with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use mrm8488/GPT-2-finetuned-common_gen with Transformers:

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

pipe = pipeline("text-generation", model="mrm8488/GPT-2-finetuned-common_gen")

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("mrm8488/GPT-2-finetuned-common_gen")
model = AutoModelForCausalLM.from_pretrained("mrm8488/GPT-2-finetuned-common_gen")

Notebooks
Google Colab
Kaggle
Local Apps

vLLM

How to use mrm8488/GPT-2-finetuned-common_gen with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "mrm8488/GPT-2-finetuned-common_gen"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "mrm8488/GPT-2-finetuned-common_gen",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/mrm8488/GPT-2-finetuned-common_gen

SGLang

How to use mrm8488/GPT-2-finetuned-common_gen 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 "mrm8488/GPT-2-finetuned-common_gen" \
    --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": "mrm8488/GPT-2-finetuned-common_gen",
		"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 "mrm8488/GPT-2-finetuned-common_gen" \
        --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": "mrm8488/GPT-2-finetuned-common_gen",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use mrm8488/GPT-2-finetuned-common_gen with Docker Model Runner:
```
docker model run hf.co/mrm8488/GPT-2-finetuned-common_gen
```

GPT-2 fine-tuned on CommonGen

GPT-2 fine-tuned on CommonGen for Generative Commonsense Reasoning.

Details of GPT-2

GPT-2 is a transformers model pretrained on a very large corpus of English data in a self-supervised fashion. This means it was pretrained on the raw texts only, with no humans labelling them in any way (which is why it can use lots of publicly available data) with an automatic process to generate inputs and labels from those texts. More precisely, it was trained to guess the next word in sentences.

More precisely, inputs are sequences of continuous text of a certain length and the targets are the same sequence, shifted one token (word or piece of word) to the right. The model uses internally a mask-mechanism to make sure the predictions for the token i only uses the inputs from 1 to i but not the future tokens.

This way, the model learns an inner representation of the English language that can then be used to extract features useful for downstream tasks. The model is best at what it was pretrained for however, which is generating texts from a prompt.

Details of the dataset 📚

CommonGen is a constrained text generation task, associated with a benchmark dataset, to explicitly test machines for the ability of generative commonsense reasoning. Given a set of common concepts; the task is to generate a coherent sentence describing an everyday scenario using these concepts.

CommonGen is challenging because it inherently requires 1) relational reasoning using background commonsense knowledge, and 2) compositional generalization ability to work on unseen concept combinations. Our dataset, constructed through a combination of crowd-sourcing from AMT and existing caption corpora, consists of 30k concept-sets and 50k sentences in total.

Dataset	Split	# samples
common_gen	train	67389
common_gen	valid	4018
common_gen	test	1497

Model fine-tuning 🏋️‍

You can find the fine-tuning script here

Model in Action 🚀

python ./transformers/examples/text-generation/run_generation.py \
    --model_type=gpt2 \
    --model_name_or_path="mrm8488/GPT-2-finetuned-common_gen" \
    --num_return_sequences 1 \
    --prompt "<|endoftext|> kid, room, dance:" \
    --stop_token "."

Created by Manuel Romero/@mrm8488 | LinkedIn

Made with ♥ in Spain

Downloads last month: 13

mrm8488
/

GPT-2-finetuned-common_gen

GPT-2 fine-tuned on CommonGen

Details of GPT-2

Details of the dataset 📚

Model fine-tuning 🏋️‍

Model in Action 🚀

Dataset used to train mrm8488/GPT-2-finetuned-common_gen