Instructions to use Tverous/gpt-j-claim-generator with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use Tverous/gpt-j-claim-generator with Transformers:

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

pipe = pipeline("text-generation", model="Tverous/gpt-j-claim-generator")

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("Tverous/gpt-j-claim-generator")
model = AutoModelForCausalLM.from_pretrained("Tverous/gpt-j-claim-generator")

Notebooks
Google Colab
Kaggle
Local Apps

vLLM

How to use Tverous/gpt-j-claim-generator with vLLM:

Install from pip and serve model

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

Use Docker

docker model run hf.co/Tverous/gpt-j-claim-generator

SGLang

How to use Tverous/gpt-j-claim-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 "Tverous/gpt-j-claim-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": "Tverous/gpt-j-claim-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 "Tverous/gpt-j-claim-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": "Tverous/gpt-j-claim-generator",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use Tverous/gpt-j-claim-generator with Docker Model Runner:
```
docker model run hf.co/Tverous/gpt-j-claim-generator
```

gpt-j-claim-generator

This model is a fine-tuned version of EleutherAI/gpt-j-6b on the anli dataset. It achieves the following results on the evaluation set:

Loss: 0.0232
Rouge1: 0.8914
Rouge2: 0.8240
Rougel: 0.8863
Rougelsum: 0.8864

Model description

More information needed

Intended uses & limitations

More information needed

Training and evaluation data

More information needed

Training procedure

Training hyperparameters

The following hyperparameters were used during training:

learning_rate: 1e-05
train_batch_size: 12
eval_batch_size: 1
seed: 42
distributed_type: multi-GPU
num_devices: 3
total_train_batch_size: 36
total_eval_batch_size: 3
optimizer: Adam with betas=(0.9,0.95) and epsilon=1e-08
lr_scheduler_type: linear
lr_scheduler_warmup_steps: 100
num_epochs: 5

Training results

Training Loss	Epoch	Step	Validation Loss	Rouge1	Rouge2	Rougel	Rougelsum
0.013	1.79	5000	0.0200	0.8921	0.8194	0.8859	0.8860
0.0085	3.58	10000	0.0232	0.8914	0.8240	0.8863	0.8864

Framework versions

Transformers 4.30.2
Pytorch 2.0.1+cu117
Datasets 2.13.1
Tokenizers 0.13.3

Downloads last month: 4

Dataset used to train Tverous/gpt-j-claim-generator

Evaluation results

Rouge1 on anli
self-reported

0.891