Instructions to use eminAydin/Turkish-GPT2-mini-ModelB-v2 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use eminAydin/Turkish-GPT2-mini-ModelB-v2 with Transformers:

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

pipe = pipeline("text-generation", model="eminAydin/Turkish-GPT2-mini-ModelB-v2")

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("eminAydin/Turkish-GPT2-mini-ModelB-v2")
model = AutoModelForCausalLM.from_pretrained("eminAydin/Turkish-GPT2-mini-ModelB-v2")

Notebooks
Google Colab
Kaggle
Local Apps

vLLM

How to use eminAydin/Turkish-GPT2-mini-ModelB-v2 with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "eminAydin/Turkish-GPT2-mini-ModelB-v2"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "eminAydin/Turkish-GPT2-mini-ModelB-v2",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/eminAydin/Turkish-GPT2-mini-ModelB-v2

SGLang

How to use eminAydin/Turkish-GPT2-mini-ModelB-v2 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 "eminAydin/Turkish-GPT2-mini-ModelB-v2" \
    --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": "eminAydin/Turkish-GPT2-mini-ModelB-v2",
		"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 "eminAydin/Turkish-GPT2-mini-ModelB-v2" \
        --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": "eminAydin/Turkish-GPT2-mini-ModelB-v2",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use eminAydin/Turkish-GPT2-mini-ModelB-v2 with Docker Model Runner:
```
docker model run hf.co/eminAydin/Turkish-GPT2-mini-ModelB-v2
```

Turkish-GPT2-mini-ModelB-v2

This model is a fine-tuned version of eminAydin/turkish-gpt2-mini-M2-cleaned-politics720k-10ep on the None dataset. It achieves the following results on the evaluation set:

Loss: 4.0013

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: 5e-05
train_batch_size: 8
eval_batch_size: 8
seed: 42
gradient_accumulation_steps: 8
total_train_batch_size: 64
optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
lr_scheduler_type: cosine
lr_scheduler_warmup_ratio: 0.03
num_epochs: 10
mixed_precision_training: Native AMP

Training results

Training Loss	Epoch	Step	Validation Loss
4.4557	1.0	105	4.2953
3.6895	2.0	211	4.1427
3.4175	3.0	316	4.0737
3.1772	4.0	422	4.0387
3.0538	5.0	527	4.0180
2.9085	6.0	633	4.0103
2.8535	7.0	738	4.0035
2.7727	8.0	844	4.0013
2.7713	9.0	949	4.0013
2.7571	9.95	1050	4.0013

Framework versions

Transformers 4.39.3
Pytorch 2.1.2
Datasets 2.18.0
Tokenizers 0.15.2

Downloads last month: 3

Model tree for eminAydin/Turkish-GPT2-mini-ModelB-v2

Base model

eminAydin/turkish-gpt2-mini-M0-cleaned-wiki720-10ep

Finetuned

eminAydin/turkish-gpt2-mini-M2-cleaned-politics720k-10ep

Finetuned

(1)

this model