Instructions to use kennylam/Breeze-7B-Cantonese-v0.1 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use kennylam/Breeze-7B-Cantonese-v0.1 with Transformers:

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

pipe = pipeline("text-generation", model="kennylam/Breeze-7B-Cantonese-v0.1")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForMultimodalLM

tokenizer = AutoTokenizer.from_pretrained("kennylam/Breeze-7B-Cantonese-v0.1")
model = AutoModelForMultimodalLM.from_pretrained("kennylam/Breeze-7B-Cantonese-v0.1")
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 kennylam/Breeze-7B-Cantonese-v0.1 with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "kennylam/Breeze-7B-Cantonese-v0.1"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "kennylam/Breeze-7B-Cantonese-v0.1",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/kennylam/Breeze-7B-Cantonese-v0.1

SGLang

How to use kennylam/Breeze-7B-Cantonese-v0.1 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 "kennylam/Breeze-7B-Cantonese-v0.1" \
    --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": "kennylam/Breeze-7B-Cantonese-v0.1",
		"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 "kennylam/Breeze-7B-Cantonese-v0.1" \
        --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": "kennylam/Breeze-7B-Cantonese-v0.1",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use kennylam/Breeze-7B-Cantonese-v0.1 with Docker Model Runner:
```
docker model run hf.co/kennylam/Breeze-7B-Cantonese-v0.1
```
Browse Quantizations to use this model in llama.cpp, Ollama, LM Studio, or any compatible app.

Model Card for Breeze-7B-Cantonese-v0.1

Breeze-7B is a language model family that builds on top of Mistral-7B, specifically intended for Traditional Chinese use. Credit to MediaTek-Research.
Breeze-7B係一個以Mistral-7B作為基礎，為正體中文而造嘅模型系列，由MediaTek-Research製作.

[Breeze-7B-Cantonese] derives from the base model Breeze-7B-Base, with finetuning by datasets from hon9kon9ize, making the resulting model to be able to chat with Cantonese.
[Breeze-7B-Cantonese] 係由基座模型 Breeze-7B-Base 衍生出黎，用hon9kon9ize 整嘅數據集微調, 令到呢個模型可以講廣東話。

I selected the [Breeze-7B-Base] model due to its extensive vocabulary coverage tailored for Traditional Chinese. Its language style aligns closely with the nuances of Hong Kong discourse, making it a suitable choice for this project.
我揀[Breeze-7B-Base]做基座模型係因為佢有正體中文嘅擴增詞表, 而且佢嘅語言根基同香港比較相似, 所以佢似乎比較適合呢個項目。

The axolotl config file axolotl-config.yml is shared for open-source purposes, allowing everyone to utilize it for training on their own.
為咗人人都可以自己訓練模型，我放埋個axolotl設定檔 axolotl-config.yml出嚟當開放源始碼。

Thanks for the great datasets from hon9kon9ize and indiejoseph, this project owes its existence to their invaluable contributions.
多得hon9kon9ize 同 indiejoseph 放出嚟嘅數據集, 先至有呢個項目出現。

Downloads last month: 5

Safetensors

Model size

7B params

Tensor type

BF16

Model tree for kennylam/Breeze-7B-Cantonese-v0.1

Quantizations

1 model

kennylam
/

Breeze-7B-Cantonese-v0.1

Model Card for Breeze-7B-Cantonese-v0.1

Model tree for kennylam/Breeze-7B-Cantonese-v0.1

Datasets used to train kennylam/Breeze-7B-Cantonese-v0.1

Spaces using kennylam/Breeze-7B-Cantonese-v0.1 16