Instructions to use Nbeau/GPT2-arithmetic-1-3digits with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use Nbeau/GPT2-arithmetic-1-3digits with Transformers:

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

pipe = pipeline("text-generation", model="Nbeau/GPT2-arithmetic-1-3digits")

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("Nbeau/GPT2-arithmetic-1-3digits")
model = AutoModelForCausalLM.from_pretrained("Nbeau/GPT2-arithmetic-1-3digits")

Notebooks
Google Colab
Kaggle
Local Apps

vLLM

How to use Nbeau/GPT2-arithmetic-1-3digits with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "Nbeau/GPT2-arithmetic-1-3digits"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "Nbeau/GPT2-arithmetic-1-3digits",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/Nbeau/GPT2-arithmetic-1-3digits

SGLang

How to use Nbeau/GPT2-arithmetic-1-3digits 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 "Nbeau/GPT2-arithmetic-1-3digits" \
    --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": "Nbeau/GPT2-arithmetic-1-3digits",
		"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 "Nbeau/GPT2-arithmetic-1-3digits" \
        --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": "Nbeau/GPT2-arithmetic-1-3digits",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use Nbeau/GPT2-arithmetic-1-3digits with Docker Model Runner:
```
docker model run hf.co/Nbeau/GPT2-arithmetic-1-3digits
```

GPT2-arithmetic-1-3digits

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

Loss: nan

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: 0.0003
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: constant_with_warmup
num_epochs: 7
mixed_precision_training: Native AMP

Training results

Training Loss	Epoch	Step	Validation Loss
0.1482	0.9984	156	nan
0.0902	1.9968	312	nan
0.0804	2.9952	468	nan
0.0789	4.0	625	nan
0.0798	4.9984	781	nan
0.0776	5.9968	937	nan
0.0773	6.9888	1092	nan

Framework versions

Transformers 4.40.2
Pytorch 2.3.0
Datasets 2.19.1
Tokenizers 0.19.1

Downloads last month: 1

Safetensors

Model size

0.1B params

Tensor type

F32

Model tree for Nbeau/GPT2-arithmetic-1-3digits

Base model

openai-community/gpt2

Finetuned

(2174)

this model