Instructions to use imthanhlv/vigpt2medium with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use imthanhlv/vigpt2medium with Transformers:

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

pipe = pipeline("text-generation", model="imthanhlv/vigpt2medium")

# pip install -U transformers accelerate
# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("imthanhlv/vigpt2medium")
model = AutoModelForCausalLM.from_pretrained("imthanhlv/vigpt2medium", device_map="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use imthanhlv/vigpt2medium with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "imthanhlv/vigpt2medium"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "imthanhlv/vigpt2medium",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/imthanhlv/vigpt2medium

SGLang

How to use imthanhlv/vigpt2medium 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 "imthanhlv/vigpt2medium" \
    --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": "imthanhlv/vigpt2medium",
		"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 "imthanhlv/vigpt2medium" \
        --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": "imthanhlv/vigpt2medium",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use imthanhlv/vigpt2medium with Docker Model Runner:
```
docker model run hf.co/imthanhlv/vigpt2medium
```

vigpt2medium / train_tokenizer.py

imthanhlv

first commit

99b6635 almost 5 years ago

Raw History Blame

636 Bytes

from datasets import load_dataset
from tokenizers import trainers, Tokenizer, normalizers, ByteLevelBPETokenizer

# load dataset
dataset = load_dataset("imthanhlv/binhvq_dedup", split="train")

# Instantiate tokenizer
tokenizer = ByteLevelBPETokenizer()

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

# Customized training
tokenizer.train_from_iterator(batch_iterator(), vocab_size=50257, min_frequency=2, special_tokens=[
    "<s>",
    "<pad>",
    "</s>",
    "<unk>",
    "<mask>",
])

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

	from datasets import load_dataset
	from tokenizers import trainers, Tokenizer, normalizers, ByteLevelBPETokenizer

	# load dataset
	dataset = load_dataset("imthanhlv/binhvq_dedup", split="train")

	# Instantiate tokenizer
	tokenizer = ByteLevelBPETokenizer()

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

	# Customized training
	tokenizer.train_from_iterator(batch_iterator(), vocab_size=50257, min_frequency=2, special_tokens=[
	"<s>",
	"<pad>",
	"</s>",
	"<unk>",
	"<mask>",
	])

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