Instructions to use dbddv01/gpt2-french-small with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use dbddv01/gpt2-french-small with Transformers:

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

pipe = pipeline("text-generation", model="dbddv01/gpt2-french-small")

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("dbddv01/gpt2-french-small")
model = AutoModelForCausalLM.from_pretrained("dbddv01/gpt2-french-small")

Notebooks
Google Colab
Kaggle
Local Apps

vLLM

How to use dbddv01/gpt2-french-small with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "dbddv01/gpt2-french-small"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "dbddv01/gpt2-french-small",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/dbddv01/gpt2-french-small

SGLang

How to use dbddv01/gpt2-french-small 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 "dbddv01/gpt2-french-small" \
    --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": "dbddv01/gpt2-french-small",
		"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 "dbddv01/gpt2-french-small" \
        --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": "dbddv01/gpt2-french-small",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use dbddv01/gpt2-french-small with Docker Model Runner:
```
docker model run hf.co/dbddv01/gpt2-french-small
```

A small french language model for french text generation (and possibly more NLP tasks...)

Introduction

This french gpt2 model is based on openai GPT-2 small model.

It was trained on a very small (190Mb) dataset from french wikipedia using Transfer Learning and Fine-tuning techniques in just over a day, on one Colab pro with 1GPU 16GB.

It was created applying the recept of Pierre Guillou

See https://medium.com/@pierre_guillou/faster-than-training-from-scratch-fine-tuning-the-english-gpt-2-in-any-language-with-hugging-f2ec05c98787

It is a proof-of-concept that makes possible to get a language model in any language with low ressources.

It was fine-tuned from the English pre-trained GPT-2 small using the Hugging Face libraries (Transformers and Tokenizers) wrapped into the fastai v2 Deep Learning framework. All the fine-tuning fastai v2 techniques were used.

It is now available on Hugging Face. For further information or requests, please go to "Faster than training from scratch — Fine-tuning the English GPT-2 in any language with Hugging Face and fastai v2 (practical case with Portuguese)".

Model migth be improved by using larger dataset under larger powerful training infrastructure. At least this one can be used for small finetuning experimentation (i.e with aitextgen).

PS : I've lost the metrics but it speaks french with some minor grammar issues, coherence of text is somehow limited.

Downloads last month: 2,561

Safetensors

Model size

0.1B params

Tensor type

F32

Model tree for dbddv01/gpt2-french-small

Finetunes

4 models

dbddv01
/

gpt2-french-small

Model tree for dbddv01/gpt2-french-small

Spaces using dbddv01/gpt2-french-small 9