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

Libraries

How to use yentinglin/Taiwan-LLaMa-v1.0 with Transformers:

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

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

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

tokenizer = AutoTokenizer.from_pretrained("yentinglin/Taiwan-LLaMa-v1.0")
model = AutoModelForCausalLM.from_pretrained("yentinglin/Taiwan-LLaMa-v1.0", device_map="auto")
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=256)
print(tokenizer.decode(outputs[0][inputs["input_ids"].shape[-1]:]))

Inference
Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use yentinglin/Taiwan-LLaMa-v1.0 with vLLM:

Install from pip and serve model

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

Use Docker

docker model run hf.co/yentinglin/Taiwan-LLaMa-v1.0

SGLang

How to use yentinglin/Taiwan-LLaMa-v1.0 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 "yentinglin/Taiwan-LLaMa-v1.0" \
    --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": "yentinglin/Taiwan-LLaMa-v1.0",
		"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 "yentinglin/Taiwan-LLaMa-v1.0" \
        --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": "yentinglin/Taiwan-LLaMa-v1.0",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

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

請問如何部署在GCP

by sherlocktaiwan - opened Aug 22, 2023

Discussion

sherlocktaiwan

Aug 22, 2023

您好，感謝對於台灣文化結合AI的貢獻。
我有GCP的compute engine機器(T4)，那我在那裡可以找到安裝文件呢? 我之前其實有安裝過open ai whisper,以及Stable diffusion ，但Taiwan-LLaMa-v1.0 好像有點複雜，感謝喔!

rogerroan

Aug 23, 2023

audreyt有做ggml的版本,在cpu上用langchain就能跑起來
https://huggingface.co/audreyt/Taiwan-LLaMa-v1.0-GGML

sherlocktaiwan

Aug 23, 2023

您好，我照著AI社團先進的作法，https://www.facebook.com/groups/Taiwan.NLP/posts/6277225012372637/ 可以執行，但我猜他是基於cpu運算，所以好慢。

我放GCP的結論：
1.Cloud Function和Cloud Run 有容量限制。所以使用13G模型不可行。
2.放在compute engine (T4 n1-highmem-4)，以Flask service接，詢問『台中的經緯度』，花費46秒。
ex Q:台中的經緯度 A: 台中的經緯度為24°23′N 120°47′E。

Upload images, audio, and videos by dragging in the text input, pasting, or clicking here.

Tap or paste here to upload images

· Sign up or log in to comment