Instructions to use ans2004/aragpt2-transport-autocomplete with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use ans2004/aragpt2-transport-autocomplete with Transformers:

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

pipe = pipeline("text-generation", model="ans2004/aragpt2-transport-autocomplete")

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("ans2004/aragpt2-transport-autocomplete")
model = AutoModelForCausalLM.from_pretrained("ans2004/aragpt2-transport-autocomplete")

Notebooks
Google Colab
Kaggle
Local Apps

vLLM

How to use ans2004/aragpt2-transport-autocomplete with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "ans2004/aragpt2-transport-autocomplete"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "ans2004/aragpt2-transport-autocomplete",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/ans2004/aragpt2-transport-autocomplete

SGLang

How to use ans2004/aragpt2-transport-autocomplete 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 "ans2004/aragpt2-transport-autocomplete" \
    --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": "ans2004/aragpt2-transport-autocomplete",
		"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 "ans2004/aragpt2-transport-autocomplete" \
        --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": "ans2004/aragpt2-transport-autocomplete",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use ans2004/aragpt2-transport-autocomplete with Docker Model Runner:
```
docker model run hf.co/ans2004/aragpt2-transport-autocomplete
```

aragpt2-transport-autocomplete

This model is a fine-tuned version of aubmindlab/aragpt2-base on an unknown dataset. It achieves the following results on the evaluation set:

Loss: 2.5047

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: 2e-05
train_batch_size: 8
eval_batch_size: 8
seed: 42
optimizer: Use OptimizerNames.ADAMW_TORCH_FUSED with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
lr_scheduler_type: cosine
lr_scheduler_warmup_steps: 150
num_epochs: 10
mixed_precision_training: Native AMP

Training results

Training Loss	Epoch	Step	Validation Loss
6.9371	1.1236	100	5.0896
3.5858	2.2472	200	2.8953
2.3939	3.3708	300	2.4553
1.7935	4.4944	400	2.4373
1.4304	5.6180	500	2.3790
1.2880	6.7416	600	2.4508
1.0935	7.8652	700	2.5212
1.1357	8.9888	800	2.5047

Framework versions

Transformers 5.0.0
Pytorch 2.10.0+cu128
Datasets 4.0.0
Tokenizers 0.22.2

Downloads last month: 300

Safetensors

Model size

0.1B params

Tensor type

F32

Model tree for ans2004/aragpt2-transport-autocomplete

Base model

aubmindlab/aragpt2-base

Finetuned

(22)

this model