Instructions to use flax-community/gpt2-base-thai with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use flax-community/gpt2-base-thai with Transformers:

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

pipe = pipeline("text-generation", model="flax-community/gpt2-base-thai")

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("flax-community/gpt2-base-thai")
model = AutoModelForCausalLM.from_pretrained("flax-community/gpt2-base-thai")

Notebooks
Google Colab
Kaggle
Local Apps

vLLM

How to use flax-community/gpt2-base-thai with vLLM:

Install from pip and serve model

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

Use Docker

docker model run hf.co/flax-community/gpt2-base-thai

SGLang

How to use flax-community/gpt2-base-thai 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 "flax-community/gpt2-base-thai" \
    --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": "flax-community/gpt2-base-thai",
		"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 "flax-community/gpt2-base-thai" \
        --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": "flax-community/gpt2-base-thai",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use flax-community/gpt2-base-thai with Docker Model Runner:
```
docker model run hf.co/flax-community/gpt2-base-thai
```

gpt2-base-thai / train_tokenizer.py

w11wo

tokenizer and config

0538a72 almost 5 years ago

raw

history blame contribute delete

819 Bytes

	from datasets import load_dataset
	from tokenizers import ByteLevelBPETokenizer
	from pythainlp.tokenize import word_tokenize

	# load dataset
	dataset = load_dataset("oscar", "unshuffled_deduplicated_th", split="train")

	# Instantiate tokenizer
	tokenizer = ByteLevelBPETokenizer()


	def th_tokenize(text):
	result = " ".join(word_tokenize(text, engine="newmm", keep_whitespace=False))
	return result


	def batch_iterator(batch_size=1000):
	for i in range(0, len(dataset), batch_size):
	yield [th_tokenize(text) for text in dataset[i : i + batch_size]["text"]]


	# Customized training
	tokenizer.train_from_iterator(
	batch_iterator(),
	vocab_size=50265,
	min_frequency=2,
	special_tokens=["<s>", "<pad>", "</s>", "<unk>", "<mask>",],
	)

	# Save files to disk
	tokenizer.save(f"./tokenizer.json")