language:
- en
- zh
license: llama2
model_name: Baichuan2-13B-Chat
inference: false
model_creator: Baichuan Intelligent Technology
model_link: https://huggingface.co/baichuan-inc/Baichuan2-13B-Chat
model_type: llama
quantized_by: TheBloke
tasks:
- text-generation
base_model: baichuan-inc/Baichuan2-13B-Chat
TheBloke's LLM work is generously supported by a grant from andreessen horowitz (a16z)
Baichuan2-13B-Chat - GPTQ
- Model creator: Baichuan Intelligent Technology
- Original model: Baichuan2-13B-Chat
Description
This repo contains GPTQ model files for Baichuan Intelligent Technology's Baichuan2-13B-Chat.
Multiple GPTQ parameter permutations are provided; see Provided Files below for details of the options provided, their parameters, and the software used to create them.
Repositories available
- GPTQ models for GPU inference, with multiple quantisation parameter options.
- Baichuan Intelligent Technology's original unquantised fp16 model in pytorch format, for GPU inference and for further conversions
Prompt template: TBC
Info on prompt template will be added shortly.
Provided files and GPTQ parameters
Multiple quantisation parameters are provided, to allow you to choose the best one for your hardware and requirements.
Each separate quant is in a different branch. See below for instructions on fetching from different branches.
All recent GPTQ files are made with AutoGPTQ, and all files in non-main branches are made with AutoGPTQ. Files in the main branch which were uploaded before August 2023 were made with GPTQ-for-LLaMa.
Explanation of GPTQ parameters
- Bits: The bit size of the quantised model.
- GS: GPTQ group size. Higher numbers use less VRAM, but have lower quantisation accuracy. "None" is the lowest possible value.
- Act Order: True or False. Also known as
desc_act. True results in better quantisation accuracy. Some GPTQ clients have had issues with models that use Act Order plus Group Size, but this is generally resolved now. - Damp %: A GPTQ parameter that affects how samples are processed for quantisation. 0.01 is default, but 0.1 results in slightly better accuracy.
- GPTQ dataset: The dataset used for quantisation. Using a dataset more appropriate to the model's training can improve quantisation accuracy. Note that the GPTQ dataset is not the same as the dataset used to train the model - please refer to the original model repo for details of the training dataset(s).
- Sequence Length: The length of the dataset sequences used for quantisation. Ideally this is the same as the model sequence length. For some very long sequence models (16+K), a lower sequence length may have to be used. Note that a lower sequence length does not limit the sequence length of the quantised model. It only impacts the quantisation accuracy on longer inference sequences.
- ExLlama Compatibility: Whether this file can be loaded with ExLlama, which currently only supports Llama models in 4-bit.
| Branch | Bits | GS | Act Order | Damp % | GPTQ Dataset | Seq Len | Size | ExLlama | Desc |
|---|---|---|---|---|---|---|---|---|---|
| main | 4 | 128 | No | 0.1 | wikitext | 4096 | 9.14 GB | Yes | Most compatible option. Good inference speed in AutoGPTQ and GPTQ-for-LLaMa. Lower inference quality than other options. |
| gptq-4bit-32g-actorder_True | 4 | 32 | Yes | 0.1 | wikitext | 4096 | 9.87 GB | Yes | 4-bit, with Act Order and group size 32g. Gives highest possible inference quality, with maximum VRAM usage. Poor AutoGPTQ CUDA speed. |
| gptq-4bit-64g-actorder_True | 4 | 64 | Yes | 0.1 | wikitext | 4096 | 9.38 GB | Yes | 4-bit, with Act Order and group size 64g. Uses less VRAM than 32g, but with slightly lower accuracy. Poor AutoGPTQ CUDA speed. |
| gptq-4bit-128g-actorder_True | 4 | 128 | Yes | 0.1 | wikitext | 4096 | 9.14 GB | Yes | 4-bit, with Act Order and group size 128g. Uses even less VRAM than 64g, but with slightly lower accuracy. Poor AutoGPTQ CUDA speed. |
| gptq-8bit--1g-actorder_True | 8 | None | Yes | 0.1 | wikitext | 4096 | 15.20 GB | No | 8-bit, with Act Order. No group size, to lower VRAM requirements and to improve AutoGPTQ speed. |
| gptq-8bit-128g-actorder_True | 8 | 128 | Yes | 0.1 | wikitext | 4096 | 15.49 GB | No | 8-bit, with group size 128g for higher inference quality and with Act Order for even higher accuracy. Poor AutoGPTQ CUDA speed. |
How to download from branches
- In text-generation-webui, you can add
:branchto the end of the download name, egTheBloke/Baichuan2-13B-Chat-GPTQ:gptq-4bit-32g-actorder_True - With Git, you can clone a branch with:
git clone --single-branch --branch gptq-4bit-32g-actorder_True https://huggingface.co/TheBloke/Baichuan2-13B-Chat-GPTQ
- In Python Transformers code, the branch is the
revisionparameter; see below.
How to easily download and use this model in text-generation-webui.
Please make sure you're using the latest version of text-generation-webui.
It is strongly recommended to use the text-generation-webui one-click-installers unless you're sure you know how to make a manual install.
- Click the Model tab.
- Under Download custom model or LoRA, enter
TheBloke/Baichuan2-13B-Chat-GPTQ.
- To download from a specific branch, enter for example
TheBloke/Baichuan2-13B-Chat-GPTQ:gptq-4bit-32g-actorder_True - see Provided Files above for the list of branches for each option.
- Click Download.
- The model will start downloading. Once it's finished it will say "Done".
- In the top left, click the refresh icon next to Model.
- In the Model dropdown, choose the model you just downloaded:
Baichuan2-13B-Chat-GPTQ - The model will automatically load, and is now ready for use!
- If you want any custom settings, set them and then click Save settings for this model followed by Reload the Model in the top right.
- Note that you do not need to and should not set manual GPTQ parameters any more. These are set automatically from the file
quantize_config.json.
- Once you're ready, click the Text Generation tab and enter a prompt to get started!
How to use this GPTQ model from Python code
Install the necessary packages
Requires: Transformers 4.32.0 or later, Optimum 1.12.0 or later, and AutoGPTQ 0.4.2 or later.
pip3 install transformers>=4.32.0 optimum>=1.12.0
pip3 install auto-gptq --extra-index-url https://huggingface.github.io/autogptq-index/whl/cu118/ # Use cu117 if on CUDA 11.7
If you have problems installing AutoGPTQ using the pre-built wheels, install it from source instead:
pip3 uninstall -y auto-gptq
git clone https://github.com/PanQiWei/AutoGPTQ
cd AutoGPTQ
pip3 install .
For CodeLlama models only: you must use Transformers 4.33.0 or later.
If 4.33.0 is not yet released when you read this, you will need to install Transformers from source:
pip3 uninstall -y transformers
pip3 install git+https://github.com/huggingface/transformers.git
You can then use the following code
from transformers import AutoModelForCausalLM, AutoTokenizer, pipeline
model_name_or_path = "TheBloke/Baichuan2-13B-Chat-GPTQ"
# To use a different branch, change revision
# For example: revision="gptq-4bit-32g-actorder_True"
model = AutoModelForCausalLM.from_pretrained(model_name_or_path,
device_map="auto",
revision="main")
tokenizer = AutoTokenizer.from_pretrained(model_name_or_path, use_fast=True)
prompt = "Tell me about AI"
prompt_template=f'''Info on prompt template will be added shortly.
'''
print("\n\n*** Generate:")
input_ids = tokenizer(prompt_template, return_tensors='pt').input_ids.cuda()
output = model.generate(inputs=input_ids, temperature=0.7, max_new_tokens=512)
print(tokenizer.decode(output[0]))
# Inference can also be done using transformers' pipeline
print("*** Pipeline:")
pipe = pipeline(
"text-generation",
model=model,
tokenizer=tokenizer,
max_new_tokens=512,
temperature=0.7,
top_p=0.95,
repetition_penalty=1.15
)
print(pipe(prompt_template)[0]['generated_text'])
Compatibility
The files provided are tested to work with AutoGPTQ, both via Transformers and using AutoGPTQ directly. They should also work with Occ4m's GPTQ-for-LLaMa fork.
ExLlama is compatible with Llama models in 4-bit. Please see the Provided Files table above for per-file compatibility.
Huggingface Text Generation Inference (TGI) is compatible with all GPTQ models.
Discord
For further support, and discussions on these models and AI in general, join us at:
Thanks, and how to contribute.
Thanks to the chirper.ai team!
I've had a lot of people ask if they can contribute. I enjoy providing models and helping people, and would love to be able to spend even more time doing it, as well as expanding into new projects like fine tuning/training.
If you're able and willing to contribute it will be most gratefully received and will help me to keep providing more models, and to start work on new AI projects.
Donaters will get priority support on any and all AI/LLM/model questions and requests, access to a private Discord room, plus other benefits.
- Patreon: https://patreon.com/TheBlokeAI
- Ko-Fi: https://ko-fi.com/TheBlokeAI
Special thanks to: Aemon Algiz.
Patreon special mentions: Russ Johnson, J, alfie_i, Alex, NimbleBox.ai, Chadd, Mandus, Nikolai Manek, Ken Nordquist, ya boyyy, Illia Dulskyi, Viktor Bowallius, vamX, Iucharbius, zynix, Magnesian, Clay Pascal, Pierre Kircher, Enrico Ros, Tony Hughes, Elle, Andrey, knownsqashed, Deep Realms, Jerry Meng, Lone Striker, Derek Yates, Pyrater, Mesiah Bishop, James Bentley, Femi Adebogun, Brandon Frisco, SuperWojo, Alps Aficionado, Michael Dempsey, Vitor Caleffi, Will Dee, Edmond Seymore, usrbinkat, LangChain4j, Kacper Wikieł, Luke Pendergrass, John Detwiler, theTransient, Nathan LeClaire, Tiffany J. Kim, biorpg, Eugene Pentland, Stanislav Ovsiannikov, Fred von Graf, terasurfer, Kalila, Dan Guido, Nitin Borwankar, 阿明, Ai Maven, John Villwock, Gabriel Puliatti, Stephen Murray, Asp the Wyvern, danny, Chris Smitley, ReadyPlayerEmma, S_X, Daniel P. Andersen, Olakabola, Jeffrey Morgan, Imad Khwaja, Caitlyn Gatomon, webtim, Alicia Loh, Trenton Dambrowitz, Swaroop Kallakuri, Erik Bjäreholt, Leonard Tan, Spiking Neurons AB, Luke @flexchar, Ajan Kanaga, Thomas Belote, Deo Leter, RoA, Willem Michiel, transmissions 11, subjectnull, Matthew Berman, Joseph William Delisle, David Ziegler, Michael Davis, Johann-Peter Hartmann, Talal Aujan, senxiiz, Artur Olbinski, Rainer Wilmers, Spencer Kim, Fen Risland, Cap'n Zoog, Rishabh Srivastava, Michael Levine, Geoffrey Montalvo, Sean Connelly, Alexandros Triantafyllidis, Pieter, Gabriel Tamborski, Sam, Subspace Studios, Junyu Yang, Pedro Madruga, Vadim, Cory Kujawski, K, Raven Klaugh, Randy H, Mano Prime, Sebastain Graf, Space Cruiser
Thank you to all my generous patrons and donaters!
And thank you again to a16z for their generous grant.
Original model card: Baichuan Intelligent Technology's Baichuan2-13B-Chat
Baichuan 2
目录/Table of Contents
- 📖 模型介绍/Introduction
- ⚙️ 快速开始/Quick Start
- 📊 Benchmark评估/Benchmark Evaluation
- 📜 声明与协议/Terms and Conditions
模型介绍/Introduction
Baichuan 2 是百川智能推出的新一代开源大语言模型，采用 2.6 万亿 Tokens 的高质量语料训练，在权威的中文和英文 benchmark 上均取得同尺寸最好的效果。本次发布包含有 7B、13B 的 Base 和 Chat 版本，并提供了 Chat 版本的 4bits 量化，所有版本不仅对学术研究完全开放，开发者也仅需邮件申请并获得官方商用许可后，即可以免费商用。具体发布版本和下载见下表：
Baichuan 2 is the new generation of large-scale open-source language models launched by Baichuan Intelligence inc.. It is trained on a high-quality corpus with 2.6 trillion tokens and has achieved the best performance in authoritative Chinese and English benchmarks of the same size. This release includes 7B and 13B versions for both Base and Chat models, along with a 4bits quantized version for the Chat model. All versions are fully open to academic research, and developers can also use them for free in commercial applications after obtaining an official commercial license through email request. The specific release versions and download links are listed in the table below:
| Base Model | Chat Model | 4bits Quantized Chat Model | |
|---|---|---|---|
| 7B | Baichuan2-7B-Base | Baichuan2-7B-Chat | Baichuan2-7B-Chat-4bits |
| 13B | Baichuan2-13B-Base | Baichuan2-13B-Chat | Baichuan2-13B-Chat-4bits |
快速开始/Quick Start
在Baichuan2系列模型中，我们为了加快推理速度使用了Pytorch2.0加入的新功能F.scaled_dot_product_attention，因此模型需要在Pytorch2.0环境下运行。
In the Baichuan 2 series models, we have utilized the new feature F.scaled_dot_product_attention introduced in PyTorch 2.0 to accelerate inference speed. Therefore, the model needs to be run in a PyTorch 2.0 environment.
import torch
from transformers import AutoModelForCausalLM, AutoTokenizer
from transformers.generation.utils import GenerationConfig
tokenizer = AutoTokenizer.from_pretrained("baichuan-inc/Baichuan2-13B-Chat", use_fast=False, trust_remote_code=True)
model = AutoModelForCausalLM.from_pretrained("baichuan-inc/Baichuan2-13B-Chat", device_map="auto", torch_dtype=torch.bfloat16, trust_remote_code=True)
model.generation_config = GenerationConfig.from_pretrained("baichuan-inc/Baichuan2-13B-Chat")
messages = []
messages.append({"role": "user", "content": "解释一下“温故而知新”"})
response = model.chat(tokenizer, messages)
print(response)
"温故而知新"是一句中国古代的成语，出自《论语·为政》篇。这句话的意思是：通过回顾过去，我们可以发现新的知识和理解。换句话说，学习历史和经验可以让我们更好地理解现在和未来。
这句话鼓励我们在学习和生活中不断地回顾和反思过去的经验，从而获得新的启示和成长。通过重温旧的知识和经历，我们可以发现新的观点和理解，从而更好地应对不断变化的世界和挑战。
Benchmark 结果/Benchmark Evaluation
我们在通用、法律、医疗、数学、代码和多语言翻译六个领域的中英文权威数据集上对模型进行了广泛测试，更多详细测评结果可查看GitHub。
We have extensively tested the model on authoritative Chinese-English datasets across six domains: General, Legal, Medical, Mathematics, Code, and Multilingual Translation. For more detailed evaluation results, please refer to GitHub.
7B Model Results
| C-Eval | MMLU | CMMLU | Gaokao | AGIEval | BBH | |
|---|---|---|---|---|---|---|
| 5-shot | 5-shot | 5-shot | 5-shot | 5-shot | 3-shot | |
| GPT-4 | 68.40 | 83.93 | 70.33 | 66.15 | 63.27 | 75.12 |
| GPT-3.5 Turbo | 51.10 | 68.54 | 54.06 | 47.07 | 46.13 | 61.59 |
| LLaMA-7B | 27.10 | 35.10 | 26.75 | 27.81 | 28.17 | 32.38 |
| LLaMA2-7B | 28.90 | 45.73 | 31.38 | 25.97 | 26.53 | 39.16 |
| MPT-7B | 27.15 | 27.93 | 26.00 | 26.54 | 24.83 | 35.20 |
| Falcon-7B | 24.23 | 26.03 | 25.66 | 24.24 | 24.10 | 28.77 |
| ChatGLM2-6B | 50.20 | 45.90 | 49.00 | 49.44 | 45.28 | 31.65 |
| Baichuan-7B | 42.80 | 42.30 | 44.02 | 36.34 | 34.44 | 32.48 |
| Baichuan2-7B-Base | 54.00 | 54.16 | 57.07 | 47.47 | 42.73 | 41.56 |
13B Model Results
| C-Eval | MMLU | CMMLU | Gaokao | AGIEval | BBH | |
|---|---|---|---|---|---|---|
| 5-shot | 5-shot | 5-shot | 5-shot | 5-shot | 3-shot | |
| GPT-4 | 68.40 | 83.93 | 70.33 | 66.15 | 63.27 | 75.12 |
| GPT-3.5 Turbo | 51.10 | 68.54 | 54.06 | 47.07 | 46.13 | 61.59 |
| LLaMA-13B | 28.50 | 46.30 | 31.15 | 28.23 | 28.22 | 37.89 |
| LLaMA2-13B | 35.80 | 55.09 | 37.99 | 30.83 | 32.29 | 46.98 |
| Vicuna-13B | 32.80 | 52.00 | 36.28 | 30.11 | 31.55 | 43.04 |
| Chinese-Alpaca-Plus-13B | 38.80 | 43.90 | 33.43 | 34.78 | 35.46 | 28.94 |
| XVERSE-13B | 53.70 | 55.21 | 58.44 | 44.69 | 42.54 | 38.06 |
| Baichuan-13B-Base | 52.40 | 51.60 | 55.30 | 49.69 | 43.20 | 43.01 |
| Baichuan2-13B-Base | 58.10 | 59.17 | 61.97 | 54.33 | 48.17 | 48.78 |
训练过程模型/Training Dynamics
除了训练了 2.6 万亿 Tokens 的 Baichuan2-7B-Base 模型，我们还提供了在此之前的另外 11 个中间过程的模型（分别对应训练了约 0.2 ~ 2.4 万亿 Tokens）供社区研究使用 （训练过程checkpoint下载）。下图给出了这些 checkpoints 在 C-Eval、MMLU、CMMLU 三个 benchmark 上的效果变化：
In addition to the Baichuan2-7B-Base model trained on 2.6 trillion tokens, we also offer 11 additional intermediate-stage models for community research, corresponding to training on approximately 0.2 to 2.4 trillion tokens each (Intermediate Checkpoints Download). The graph below shows the performance changes of these checkpoints on three benchmarks: C-Eval, MMLU, and CMMLU.
声明与协议/Terms and Conditions
声明
我们在此声明，我们的开发团队并未基于 Baichuan 2 模型开发任何应用，无论是在 iOS、Android、网页或任何其他平台。我们强烈呼吁所有使用者，不要利用 Baichuan 2 模型进行任何危害国家社会安全或违法的活动。另外，我们也要求使用者不要将 Baichuan 2 模型用于未经适当安全审查和备案的互联网服务。我们希望所有的使用者都能遵守这个原则，确保科技的发展能在规范和合法的环境下进行。
我们已经尽我们所能，来确保模型训练过程中使用的数据的合规性。然而，尽管我们已经做出了巨大的努力，但由于模型和数据的复杂性，仍有可能存在一些无法预见的问题。因此，如果由于使用 Baichuan 2 开源模型而导致的任何问题，包括但不限于数据安全问题、公共舆论风险，或模型被误导、滥用、传播或不当利用所带来的任何风险和问题，我们将不承担任何责任。
We hereby declare that our team has not developed any applications based on Baichuan 2 models, not on iOS, Android, the web, or any other platform. We strongly call on all users not to use Baichuan 2 models for any activities that harm national / social security or violate the law. Also, we ask users not to use Baichuan 2 models for Internet services that have not undergone appropriate security reviews and filings. We hope that all users can abide by this principle and ensure that the development of technology proceeds in a regulated and legal environment.
We have done our best to ensure the compliance of the data used in the model training process. However, despite our considerable efforts, there may still be some unforeseeable issues due to the complexity of the model and data. Therefore, if any problems arise due to the use of Baichuan 2 open-source models, including but not limited to data security issues, public opinion risks, or any risks and problems brought about by the model being misled, abused, spread or improperly exploited, we will not assume any responsibility.
协议
Baichuan 2 模型的社区使用需遵循《Baichuan 2 模型社区许可协议》。Baichuan 2 支持商用。如果将 Baichuan 2 模型或其衍生品用作商业用途，请您按照如下方式联系许可方，以进行登记并向许可方申请书面授权：联系邮箱 opensource@baichuan-inc.com。
The use of the source code in this repository follows the open-source license Apache 2.0. Community use of the Baichuan 2 model must adhere to the Community License for Baichuan 2 Model. Baichuan 2 supports commercial use. If you are using the Baichuan 2 models or their derivatives for commercial purposes, please contact the licensor in the following manner for registration and to apply for written authorization: Email opensource@baichuan-inc.com.