Instructions to use RichardErkhov/mukayese_-_transformer-turkish-summarization-8bits with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use RichardErkhov/mukayese_-_transformer-turkish-summarization-8bits with Transformers:

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

pipe = pipeline("text-generation", model="RichardErkhov/mukayese_-_transformer-turkish-summarization-8bits")

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("RichardErkhov/mukayese_-_transformer-turkish-summarization-8bits")
model = AutoModelForCausalLM.from_pretrained("RichardErkhov/mukayese_-_transformer-turkish-summarization-8bits", device_map="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use RichardErkhov/mukayese_-_transformer-turkish-summarization-8bits with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "RichardErkhov/mukayese_-_transformer-turkish-summarization-8bits"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "RichardErkhov/mukayese_-_transformer-turkish-summarization-8bits",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/RichardErkhov/mukayese_-_transformer-turkish-summarization-8bits

SGLang

How to use RichardErkhov/mukayese_-_transformer-turkish-summarization-8bits 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 "RichardErkhov/mukayese_-_transformer-turkish-summarization-8bits" \
    --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": "RichardErkhov/mukayese_-_transformer-turkish-summarization-8bits",
		"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 "RichardErkhov/mukayese_-_transformer-turkish-summarization-8bits" \
        --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": "RichardErkhov/mukayese_-_transformer-turkish-summarization-8bits",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use RichardErkhov/mukayese_-_transformer-turkish-summarization-8bits with Docker Model Runner:
```
docker model run hf.co/RichardErkhov/mukayese_-_transformer-turkish-summarization-8bits
```

YAML Metadata Warning:empty or missing yaml metadata in repo card

Check out the documentation for more information.

Quantization made by Richard Erkhov.

Github

Discord

Request more models

transformer-turkish-summarization - bnb 8bits

Model creator: https://huggingface.co/mukayese/
Original model: https://huggingface.co/mukayese/transformer-turkish-summarization/

Original model description:

datasets: - mlsum metrics: - rouge model-index: - name: mukayese/transformer-turkish-summarization results: - task: name: Summarization type: summarization dataset: name: mlsum tu type: mlsum args: tu metrics: - name: Rouge1 type: rouge value: 43.2049 license: mit language: - tr pipeline_tag: summarization

Mukayese: Turkish NLP Strikes Back

Summarization: mukayese/transformer-turkish-summarization

This model is uncased, it was initialized from scratch and trained only the mlsum/tu dataset with no pre-training.

It achieves the following results on the evaluation set:

Rouge1: 43.2049
Rouge2: 30.7082
Rougel: 38.1981
Rougelsum: 39.9453

Check this paper for more details on the model and the dataset.

Training procedure

Training hyperparameters

The following hyperparameters were used during training:

learning_rate: 0.0001
train_batch_size: 4
eval_batch_size: 8
seed: 42
distributed_type: multi-GPU
num_devices: 8
gradient_accumulation_steps: 2
total_train_batch_size: 64
total_eval_batch_size: 64
optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
lr_scheduler_type: linear
num_epochs: 15.0
mixed_precision_training: Native AMP
label_smoothing_factor: 0.1

Framework versions

Transformers 4.11.3
Pytorch 1.8.2+cu111
Datasets 1.14.0
Tokenizers 0.10.3

Citation

@misc{safaya-etal-2022-mukayese,
    title={Mukayese: Turkish NLP Strikes Back},
    author={Ali Safaya and Emirhan Kurtuluş and Arda Göktoğan and Deniz Yuret},
    year={2022},
    eprint={2203.01215},
    archivePrefix={arXiv},
    primaryClass={cs.CL}
}

Downloads last month: 8

Safetensors

Model size

82.1M params

Tensor type

F32

F16

Paper for RichardErkhov/mukayese_-_transformer-turkish-summarization-8bits

Mukayese: Turkish NLP Strikes Back

Paper • 2203.01215 • Published Mar 2, 2022