Instructions to use DavidLanz/Taiwan-tinyllama-v1.0-chat with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use DavidLanz/Taiwan-tinyllama-v1.0-chat with Transformers:

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

pipe = pipeline("text-generation", model="DavidLanz/Taiwan-tinyllama-v1.0-chat")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("DavidLanz/Taiwan-tinyllama-v1.0-chat")
model = AutoModelForCausalLM.from_pretrained("DavidLanz/Taiwan-tinyllama-v1.0-chat")
messages = [
    {"role": "user", "content": "Who are you?"},
]
inputs = tokenizer.apply_chat_template(
	messages,
	add_generation_prompt=True,
	tokenize=True,
	return_dict=True,
	return_tensors="pt",
).to(model.device)

outputs = model.generate(**inputs, max_new_tokens=40)
print(tokenizer.decode(outputs[0][inputs["input_ids"].shape[-1]:]))

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use DavidLanz/Taiwan-tinyllama-v1.0-chat with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "DavidLanz/Taiwan-tinyllama-v1.0-chat"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "DavidLanz/Taiwan-tinyllama-v1.0-chat",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/DavidLanz/Taiwan-tinyllama-v1.0-chat

SGLang

How to use DavidLanz/Taiwan-tinyllama-v1.0-chat 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 "DavidLanz/Taiwan-tinyllama-v1.0-chat" \
    --host 0.0.0.0 \
    --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "DavidLanz/Taiwan-tinyllama-v1.0-chat",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

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 "DavidLanz/Taiwan-tinyllama-v1.0-chat" \
        --host 0.0.0.0 \
        --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "DavidLanz/Taiwan-tinyllama-v1.0-chat",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use DavidLanz/Taiwan-tinyllama-v1.0-chat with Docker Model Runner:
```
docker model run hf.co/DavidLanz/Taiwan-tinyllama-v1.0-chat
```

Taiwan-tinyllama-v1.0-chat / README.md

DavidLanz

Upload folder using huggingface_hub

abb0547 verified almost 2 years ago

preview code

raw

history blame contribute delete

1.66 kB

metadata

library_name: transformers
license: apache-2.0
datasets:
  - benchang1110/pretrainedtw
  - HuggingFaceTB/cosmopedia-100k
language:
  - zh
widget:
  - text: 在很久以前，這座島上
    example_title: Example1

Model Card for Model ID

This is a continue-pretrained version of Tinyllama tailored for traditional Chinese. The continue-pretraining dataset contains roughly 2B tokens.

Usage

from transformers import AutoModelForCausalLM, AutoTokenizer
import torch

def generate_response(input):
    '''
    simple test for the model
    '''
    # tokenzize the input
    tokenized_input = tokenizer.encode_plus(input, return_tensors='pt').to(device)
    
    # generate the response
    outputs = model.generate(
        input_ids=tokenized_input['input_ids'], 
        attention_mask=tokenized_input['attention_mask'],
        pad_token_id=tokenizer.pad_token_id,
        do_sample=False,
        repetition_penalty=1.3,
        max_length=500
    )
    
    # decode the response
    return tokenizer.decode(outputs[0], skip_special_tokens=True)

if __name__ == '__main__':
    device = 'cuda' if torch.cuda.is_available() else 'cpu'
    model = AutoModelForCausalLM.from_pretrained("DavidLanz/Taiwan-tinyllama-v1.0-chat",device_map=device,torch_dtype=torch.bfloat16)
    tokenizer = AutoTokenizer.from_pretrained("DavidLanz/Taiwan-tinyllama-v1.0-chat")
    while(True):
        text = input("input a simple prompt:")
        print('System:', generate_response(text))

Using bfloat16, the VRAM required is around 3GB!!!