Breeze-7B-Instruct-v0_1-AWQ

Breeze-7B-Instruct-v0_1 - AWQ

• Model creator: MediaTek-Research
• Original model: Breeze-7B-Instruct-v0_1

<!-- description start -->

Description

This repo contains AWQ model files for MediaTek-Research's Breeze-7B-Instruct-v0_1.

About AWQ

AWQ is an efficient, accurate and blazing-fast low-bit weight quantization method, currently supporting 4-bit quantization. Compared to GPTQ, it offers faster Transformers-based inference.

It is also now supported by continuous batching server vLLM, allowing use of Llama AWQ models for high-throughput concurrent inference in multi-user server scenarios.

As of September 25th 2023, preliminary Llama-only AWQ support has also been added to Huggingface Text Generation Inference (TGI).

Note that, at the time of writing, overall throughput is still lower than running vLLM or TGI with unquantised models, however using AWQ enables using much smaller GPUs which can lead to easier deployment and overall cost savings. For example, a 70B model can be run on 1 x 48GB GPU instead of 2 x 80GB.

<!-- description end --> <!-- repositories-available start -->

Repositories available

• AWQ model(s) for GPU inference.
• AdaptLLM's original unquantised fp16 model in pytorch format, for GPU inference and for further conversions

<!-- repositories-available end --> <!-- prompt-template start -->

Prompt template: Unknown

{prompt}

<!-- prompt-template end --> <!-- README_AWQ.md-provided-files start -->

Provided files, and AWQ parameters

Models are released as sharded safetensors files.

<!-- README_AWQ.md-provided-files end --> <!-- README_AWQ.md-use-from-vllm start -->

Serving this model from vLLM

Documentation on installing and using vLLM can be found here.

• When using vLLM as a server, pass the --quantization awq parameter, for example:

python3 python -m vllm.entrypoints.api_server --model Heng666/Breeze-7B-Instruct-v0_1-AWQ --quantization awq --dtype half

Note: at the time of writing, vLLM has not yet done a new release with support for the quantization parameter. If you try the code below and get an error about quantization being unrecognised, please install vLLM from Github source. When using vLLM from Python code, pass the quantization=awq parameter, for example:

from vllm import LLM, SamplingParams

prompts = [
    "Hello, my name is",
    "The president of the United States is",
    "The capital of France is",
    "The future of AI is",
]
sampling_params = SamplingParams(temperature=0.8, top_p=0.95)
llm = LLM(model="Heng666/Breeze-7B-Instruct-v0_1-AWQ", quantization="awq", dtype="half")

outputs = llm.generate(prompts, sampling_params)
# Print the outputs.
for output in outputs:
    prompt = output.prompt
    generated_text = output.outputs[0].text
    print(f"Prompt: {prompt!r}, Generated text: {generated_text!r}")

<!-- README_AWQ.md-use-from-vllm start --> <!-- README_AWQ.md-use-from-python start -->

How to use this AWQ model from Python code

Install the necessary packages

Requires: AutoAWQ 0.0.2 or later

pip3 install autoawq

If you have problems installing AutoAWQ using the pre-built wheels, install it from source instead:

pip3 uninstall -y autoawq
git clone https://github.com/casper-hansen/AutoAWQ
cd AutoAWQ
pip3 install .

You can then try the following example code

from awq import AutoAWQForCausalLM
from transformers import AutoTokenizer
model_name_or_path = "Heng666/Breeze-7B-Instruct-v0_1-AWQ"

# Load model
model = AutoAWQForCausalLM.from_quantized(model_name_or_path, fuse_layers=True,
                                          trust_remote_code=False, safetensors=True)
tokenizer = AutoTokenizer.from_pretrained(model_name_or_path, trust_remote_code=False)
prompt = "Tell me about AI"
prompt_template=f'''{prompt}

'''

print("\n\n*** Generate:")
tokens = tokenizer(
    prompt_template,
    return_tensors='pt'
).input_ids.cuda()
# Generate output
generation_output = model.generate(
    tokens,
    do_sample=True,
    temperature=0.7,
    top_p=0.95,
    top_k=40,
    max_new_tokens=512
)
print("Output: ", tokenizer.decode(generation_output[0]))
"""
# Inference should be possible with transformers pipeline as well in future
# But currently this is not yet supported by AutoAWQ (correct as of September 25th 2023)
from transformers import pipeline
print("*** Pipeline:")
pipe = pipeline(
    "text-generation",
    model=model,
    tokenizer=tokenizer,
    max_new_tokens=512,
    do_sample=True,
    temperature=0.7,
    top_p=0.95,
    top_k=40,
    repetition_penalty=1.1
)
print(pipe(prompt_template)[0]['generated_text'])
"""

<!-- README_AWQ.md-use-from-python end --> <!-- README_AWQ.md-compatibility start -->

Compatibility

The files provided are tested to work with AutoAWQ, and vLLM. Huggingface Text Generation Inference (TGI) merged AWQ support on September 25th, 2023: TGI PR #1054. Use the :latest Docker container until the next TGI release is made. At the time of writing (25th September) TGI's PR appears not to work with 70B models, but this is likely to be fixed quickly.

<!-- README_AWQ.md-compatibility end -->

Original model card: Breeze-7B-Instruct-v0_1

Breeze-7B is a language model family that builds on top of Mistral-7B, specifically intended for Traditional Chinese use. Breeze-7B-Base is the base model for the Breeze-7B series. It is suitable for use if you have substantial fine-tuning data to tune it for your specific use case. Breeze-7B-Instruct derives from the base model Breeze-7B-Base, making the resulting model amenable to be used as-is for commonly seen tasks. Breeze-7B-Instruct-64k is a slightly modified version of Breeze-7B-Instruct to enable a 64k-token context length. Roughly speaking, that is equivalent to 88k Traditional Chinese characters. The current release version of Breeze-7B is v0.1. Practicality-wise:

• Breeze-7B-Base expands the original vocabulary with additional 30,000 Traditional Chinese tokens. With the expanded vocabulary, everything else being equal, Breeze-7B operates at twice the inference speed for Traditional Chinese to Mistral-7B and Llama 7B. [See Inference Performance.]
• Breeze-7B-Instruct can be used as is for common tasks such as Q&A, RAG, multi-round chat, and summarization.
• In particular, Breeze-7B-Instruct-64k can perform tasks at a document level, not a chapter level. Performance-wise:
• Breeze-7B-Instruct demonstrates impressive performance in benchmarks for Traditional Chinese and English, when compared to similar sized open-source contemporaries such as Taiwan-LLM-7B/13B-chat, QWen-7B-Chat, and Yi-6B-Chat. [See Chat Model Performance.] A project by the members (in alphabetical order): Chan-Jan Hsu 許湛然, Chang-Le Liu 劉昶樂, Feng-Ting Liao 廖峰挺, Po-Chun Hsu 許博竣, Yi-Chang Chen 陳宜昌, and the supervisor Da-Shan Shiu 許大山.

Demo

Play Demo Here

Features

• Breeze-7B-Base-v0_1
  • Expanding the vocabulary dictionary size from 32k to 62k to better support Traditional Chinese
  • 8k-token context length
• Breeze-7B-Instruct-v0_1
  • Expanding the vocabulary dictionary size from 32k to 62k to better support Traditional Chinese
  • 8k-token context length
  • Multi-turn dialogue (without special handling for harmfulness)
• Breeze-7B-Instruct-64k-v0_1
  • Expanding the vocabulary dictionary size from 32k to 62k to better support Traditional Chinese
  • 64k-token context length
  • Multi-turn dialogue (without special handling for harmfulness)

Model Details

• Breeze-7B-Base-v0_1
  • Finetuned from: mistralai/Mistral-7B-v0.1
  • Model type: Causal decoder-only transformer language model
  • Language: English and Traditional Chinese (zh-tw)
• Breeze-7B-Instruct-v0_1
  • Finetuned from: MediaTek-Research/Breeze-7B-Base-v0_1
  • Model type: Causal decoder-only transformer language model
  • Language: English and Traditional Chinese (zh-tw)
• Breeze-7B-Instruct-64k-v0_1
  • Finetuned from: MediaTek-Research/Breeze-7B-Instruct-v0_1
  • Model type: Causal decoder-only transformer language model
  • Language: English and Traditional Chinese (zh-tw)

Base Model Performance

TMMLU+, DRCD, and Table source from MediaTek-Research/TCEval-v2. MediaTek-Research/TCEval-v2 derives from TCEval-v1 and ikala/tmmluplus. MMLU sources from hails/mmlu_no_train. We use the code revised from EleutherAI/lm-evaluation-harness to evaluate TMMLU+, DRCD, Table, and MMLU.

Chat Model Performance

TMMLU+, DRCD, Table, and MT-Bench-tw source from MediaTek-Research/TCEval-v2. MediaTek-Research/TCEval-v2 derives from TCEval-v1 and ikala/tmmluplus. MMLU sources from hails/mmlu_no_train. MT-Bench source from lmsys/mt_bench_human_judgments. We use the code revised from EleutherAI/lm-evaluation-harness to evaluate TMMLU+, DRCD, Table, and MMLU. We use the code revised from fastchat llm_judge (GPT4 as judge) to evaluate MT-Bench-tw and MT-Bench.

Inference Performance

In this test, we use the first 700 characters of the web article as the input and ask the model to write the same article again. All inferences run on 2 RTX A6000 GPUs (using vllm, with a tensor-parallel size of 2).

Long-context Performance

TBD

Use in Transformers

First install direct dependencies:

pip install transformers torch accelerate

If you want faster inference using flash-attention2, you need to install these dependencies:

pip install packaging ninja
pip install flash-attn

Then load the model in transformers:

from transformers import AutoModelForCausalLM, AutoTokenizer
import torch
model = AutoModelForCausalLM.from_pretrained(
    "MediaTek-Research/Breeze-7B-Instruct-v0_1",
    device_map="auto",
    torch_dtype=torch.bfloat16,
    attn_implementation="flash_attention_2" # optional
)

The structure of the query is

<s>SYS_PROMPT   [INST] QUERY1 [/INST] RESPONSE1 [INST] QUERY2 [/INST] 

where SYS_PROMPT, QUERY1, RESPONSE1, and QUERY2 can be provided by the user.

The suggested default SYS_PROMPT is

You are a helpful AI assistant built by MediaTek Research. The user you are helping speaks Traditional Chinese and comes from Taiwan.

We also integrate chat_template into tokenizer_config.json, so you can apply_chat_template to get the prompt.

>>> from transformers import AutoTokenizer
>>> tokenizer = AutoTokenizer.from_pretrained("MediaTek-Research/Breeze-7B-Instruct-v0.1")
>>> chat = [
...   {"role": "user", "content": "你好，請問你可以完成什麼任務？"},
...   {"role": "assistant", "content": "你好，我可以幫助您解決各種問題、提供資訊和協助您完成許多不同的任務。例如：回答技術問題、提供建議、翻譯文字、尋找資料或協助您安排行程等。請告訴我如何能幫助您。"},
...   {"role": "user", "content": "太棒了！"},
... ]
>>> tokenizer.apply_chat_template(chat, tokenize=False)
"<s>You are a helpful AI assistant built by MediaTek Research. The user you are helping speaks Traditional Chinese and comes from Taiwan.   [INST] 你好，請問你可以完成什麼任務？ [/INST] 你好，我可以幫助您解決各種問題、提供資訊和協助您完成許多不同的任務。例如：回答技術問題、提供建議、翻譯文字、尋找資料或協助您安排行程等。請告訴我如何能幫助您。 [INST] 太棒了！ [/INST] "
# Tokenized results
# ['▁', '你好', '，', '請問', '你', '可以', '完成', '什麼', '任務', '？']
# ['▁', '你好', '，', '我', '可以', '幫助', '您', '解決', '各種', '問題', '、', '提供', '資訊', '和', '協助', '您', '完成', '許多', '不同', '的', '任務', '。', '例如', '：', '回答', '技術', '問題', '、', '提供', '建議', '、', '翻譯', '文字', '、', '尋找', '資料', '或', '協助', '您', '安排', '行程', '等', '。', '請', '告訴', '我', '如何', '能', '幫助', '您', '。']
# ['▁', '太', '棒', '了', '！']

Citation

@article{breeze7b2024,
  title={},
  author={},
  journal={arXiv},
  year={2024}
}