Instructions to use kaizerBox/ReFormer-summarization with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use kaizerBox/ReFormer-summarization with Transformers:

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

pipe = pipeline("text-generation", model="kaizerBox/ReFormer-summarization")

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("kaizerBox/ReFormer-summarization")
model = AutoModelForCausalLM.from_pretrained("kaizerBox/ReFormer-summarization", device_map="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use kaizerBox/ReFormer-summarization with vLLM:

Install from pip and serve model

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

Use Docker

docker model run hf.co/kaizerBox/ReFormer-summarization

SGLang

How to use kaizerBox/ReFormer-summarization 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 "kaizerBox/ReFormer-summarization" \
    --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": "kaizerBox/ReFormer-summarization",
		"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 "kaizerBox/ReFormer-summarization" \
        --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": "kaizerBox/ReFormer-summarization",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use kaizerBox/ReFormer-summarization with Docker Model Runner:
```
docker model run hf.co/kaizerBox/ReFormer-summarization
```

ReFormer-summarization / README.md

kaizerBox

Time is 232.55102243026099 minutes, Memory is 9.4GB

d80634a over 2 years ago

preview code

Raw

History Blame Contribute Delete

1.4 kB

metadata

tags:
  - generated_from_trainer
datasets:
  - xsum
model-index:
  - name: ReFormer-summarization
    results: []

ReFormer-summarization

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

Loss: 4.5207

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: 0.001
train_batch_size: 8
eval_batch_size: 8
seed: 42
optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
lr_scheduler_type: cosine
lr_scheduler_warmup_steps: 100
num_epochs: 3
mixed_precision_training: Native AMP

Training results

Training Loss	Epoch	Step	Validation Loss
5.336	1.0	23050	4.8078
4.6673	2.0	46100	4.5712
4.519	3.0	69150	4.5207

Framework versions

Transformers 4.35.2
Pytorch 2.1.0+cu118
Datasets 2.15.0
Tokenizers 0.15.0