Instructions to use Isotonic/gpt2-context_generator with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use Isotonic/gpt2-context_generator with Transformers:

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

pipe = pipeline("text-generation", model="Isotonic/gpt2-context_generator")

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("Isotonic/gpt2-context_generator")
model = AutoModelForCausalLM.from_pretrained("Isotonic/gpt2-context_generator")

Notebooks
Google Colab
Kaggle
Local Apps

vLLM

How to use Isotonic/gpt2-context_generator with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "Isotonic/gpt2-context_generator"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "Isotonic/gpt2-context_generator",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/Isotonic/gpt2-context_generator

SGLang

How to use Isotonic/gpt2-context_generator 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 "Isotonic/gpt2-context_generator" \
    --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": "Isotonic/gpt2-context_generator",
		"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 "Isotonic/gpt2-context_generator" \
        --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": "Isotonic/gpt2-context_generator",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use Isotonic/gpt2-context_generator with Docker Model Runner:
```
docker model run hf.co/Isotonic/gpt2-context_generator
```

gpt2-context_generator

This model is a fine-tuned version of gpt2 on Non-Residual-Prompting/C2Gen dataset.

Model description

More information needed

Intended uses & limitations

Check config.json for prompt template and sampling strategy.

Dataset Summary

CommonGen Lin et al., 2020 is a dataset for the constrained text generation task of word inclusion. But the task does not allow to include context. Therefore, to complement CommonGen, we provide an extended test set C2Gen Carlsson et al., 2022 where an additional context is provided for each set of target words. The task is therefore reformulated to both generate commonsensical text which include the given words, and also have the generated text adhere to the given context.

Training procedure

Causal Language Modelling

Training hyperparameters

The following hyperparameters were used during training:

learning_rate: 9e-05
train_batch_size: 32
eval_batch_size: 32
seed: 42
optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
lr_scheduler_type: linear
lr_scheduler_warmup_ratio: 0.2
num_epochs: 8

Framework versions

Transformers 4.27.3
Pytorch 1.13.1+cu116
Datasets 2.13.1
Tokenizers 0.13.2

Downloads last month: 17

Safetensors

Model size

0.1B params

Tensor type

F32

BOOL

Model tree for Isotonic/gpt2-context_generator

Base model

openai-community/gpt2

Finetuned

(2153)

this model

Dataset used to train Isotonic/gpt2-context_generator

Paper for Isotonic/gpt2-context_generator

CommonGen: A Constrained Text Generation Challenge for Generative Commonsense Reasoning

Paper • 1911.03705 • Published Nov 9, 2019 • 1