Instructions to use qqplot23/xsum-gpt2-long-pegasus with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use qqplot23/xsum-gpt2-long-pegasus with Transformers:

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

pipe = pipeline("text-generation", model="qqplot23/xsum-gpt2-long-pegasus")

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("qqplot23/xsum-gpt2-long-pegasus")
model = AutoModelForCausalLM.from_pretrained("qqplot23/xsum-gpt2-long-pegasus")

Notebooks
Google Colab
Kaggle
Local Apps

vLLM

How to use qqplot23/xsum-gpt2-long-pegasus with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "qqplot23/xsum-gpt2-long-pegasus"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "qqplot23/xsum-gpt2-long-pegasus",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/qqplot23/xsum-gpt2-long-pegasus

SGLang

How to use qqplot23/xsum-gpt2-long-pegasus 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 "qqplot23/xsum-gpt2-long-pegasus" \
    --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": "qqplot23/xsum-gpt2-long-pegasus",
		"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 "qqplot23/xsum-gpt2-long-pegasus" \
        --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": "qqplot23/xsum-gpt2-long-pegasus",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use qqplot23/xsum-gpt2-long-pegasus with Docker Model Runner:
```
docker model run hf.co/qqplot23/xsum-gpt2-long-pegasus
```

xsum-gpt2-long-pegasus

This model is a fine-tuned version of gpt2 on an unknown dataset. It achieves the following results on the evaluation set:

Loss: 3.2524
Ppl: 26.6834

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: 0.0005
train_batch_size: 2
eval_batch_size: 2
seed: 22554
distributed_type: multi-GPU
num_devices: 2
gradient_accumulation_steps: 8
total_train_batch_size: 32
total_eval_batch_size: 4
optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
lr_scheduler_type: cosine
lr_scheduler_warmup_steps: 2000
num_epochs: 15
mixed_precision_training: Native AMP

Training results

Training Loss	Epoch	Step	Validation Loss	Ppl
3.7921	2.67	4000	3.6382	39.1940
3.4486	5.34	8000	3.4164	31.3953
3.299	8.01	12000	3.3291	28.7823
3.2019	10.68	16000	3.2769	27.3369
3.1403	13.36	20000	3.2524	26.6834

Framework versions

Transformers 4.35.0.dev0
Pytorch 1.13.1+cu117
Datasets 2.14.6
Tokenizers 0.14.1

Downloads last month: 7

Safetensors

Model size

69.2M params

Tensor type

F32

Model tree for qqplot23/xsum-gpt2-long-pegasus

Base model

openai-community/gpt2

Finetuned

(2153)

this model