Instructions to use yentinglin/Taiwan-LLM-13B-v2.0-chat-awq with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use yentinglin/Taiwan-LLM-13B-v2.0-chat-awq with Transformers:

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

pipe = pipeline("text-generation", model="yentinglin/Taiwan-LLM-13B-v2.0-chat-awq")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("yentinglin/Taiwan-LLM-13B-v2.0-chat-awq")
model = AutoModelForCausalLM.from_pretrained("yentinglin/Taiwan-LLM-13B-v2.0-chat-awq", 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=40)
print(tokenizer.decode(outputs[0][inputs["input_ids"].shape[-1]:]))

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use yentinglin/Taiwan-LLM-13B-v2.0-chat-awq with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "yentinglin/Taiwan-LLM-13B-v2.0-chat-awq"
# 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-LLM-13B-v2.0-chat-awq",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/yentinglin/Taiwan-LLM-13B-v2.0-chat-awq

SGLang

How to use yentinglin/Taiwan-LLM-13B-v2.0-chat-awq 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-LLM-13B-v2.0-chat-awq" \
    --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-LLM-13B-v2.0-chat-awq",
		"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-LLM-13B-v2.0-chat-awq" \
        --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-LLM-13B-v2.0-chat-awq",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use yentinglin/Taiwan-LLM-13B-v2.0-chat-awq with Docker Model Runner:
```
docker model run hf.co/yentinglin/Taiwan-LLM-13B-v2.0-chat-awq
```

awq quantization method

by Nelson365487 - opened Jul 16, 2024

Discussion

Nelson365487

Jul 16, 2024

I'm curious of what dataset that is used for teh awq qantization. Do you just follow the steps in the (https://github.com/casper-hansen/AutoAWQ/blob/main/examples/quantize.py) which is using the default dataset (mit-han-lab/pile-val-backup https://huggingface.co/datasets/mit-han-lab/pile-val-backup)?

from awq import AutoAWQForCausalLM
from transformers import AutoTokenizer

model_path = 'mistralai/Mistral-7B-Instruct-v0.2'
quant_path = 'mistral-instruct-v0.2-awq'
quant_config = { "zero_point": True, "q_group_size": 128, "w_bit": 4, "version": "GEMM" }

# Load model
model = AutoAWQForCausalLM.from_pretrained(
    model_path, **{"low_cpu_mem_usage": True, "use_cache": False}
)
tokenizer = AutoTokenizer.from_pretrained(model_path, trust_remote_code=True)

# Quantize
model.quantize(tokenizer, quant_config=quant_config)

# Save quantized model
model.save_quantized(quant_path)
tokenizer.save_pretrained(quant_path)

print(f'Model is quantized and saved at "{quant_path}"')

The reason for asking this question is that I want to quantize the lastest model yentinglin/Llama-3-Taiwan-70B-Instruct myself.

yentinglin

Owner Jul 16, 2024

same code but i use https://huggingface.co/datasets/yentinglin/TaiwanChat for calibration dataset

Nelson365487

Jul 16, 2024

Thank you for your prompt reply, I did not expect it at all :D .

Nelson365487 changed discussion status to closed Jul 16, 2024

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