---
inference: false
license: other
---
# Project Baize V2 13B GPTQ
These files are GPTQ 4bit model files for [Project Baize V2 13B](https://huggingface.co/project-baize/baize-v2-13b).
It is the result of quantising to 4bit using [GPTQ-for-LLaMa](https://github.com/qwopqwop200/GPTQ-for-LLaMa).
## Other repositories available
* [4-bit GPTQ models for GPU inference](https://huggingface.co/TheBloke/Project-Baize-v2-13B-GPTQ)
* [4-bit, 5-bit and 8-bit GGML models for CPU(+GPU) inference](https://huggingface.co/TheBloke/Project-Baize-v2-13B-GGML)
* [Original unquantised fp16 model in HF format](https://huggingface.co/project-baize/baize-v2-13b)
## How to easily download and use this model in text-generation-webui
Open the text-generation-webui UI as normal.
1. Click the **Model tab**.
2. Under **Download custom model or LoRA**, enter `TheBloke/Project-Baize-v2-13B-GPTQ`.
3. Click **Download**.
4. Wait until it says it's finished downloading.
5. Click the **Refresh** icon next to **Model** in the top left.
6. In the **Model drop-down**: choose the model you just downloaded, `Project-Baize-v2-13B-GPTQ`.
7. If you see an error in the bottom right, ignore it - it's temporary.
8. Fill out the `GPTQ parameters` on the right: `Bits = 4`, `Groupsize = 128`, `model_type = Llama`
9. Click **Save settings for this model** in the top right.
10. Click **Reload the Model** in the top right.
11. Once it says it's loaded, click the **Text Generation tab** and enter a prompt!
## Provided files
**Compatible file - Baize-v2-13B-4bit-128g.no-act-order.safetensors**
In the `main` branch - the default one - you will find `Baize-v2-13B-4bit-128g.no-act-order.safetensors`
This will work with all versions of GPTQ-for-LLaMa. It has maximum compatibility
It was created without the `--act-order` parameter. It may have slightly lower inference quality compared to the other file, but is guaranteed to work on all versions of GPTQ-for-LLaMa and text-generation-webui.
* `Baize-v2-13B-4bit-128g.no-act-order.safetensors`
* Works with all versions of GPTQ-for-LLaMa code, both Triton and CUDA branches
* Works with text-generation-webui one-click-installers
* Parameters: Groupsize = 128g. No act-order.
* Command used to create the GPTQ:
```
python llama.py /workspace/ggml/TheBloke_Project-Baize-v2-13B-GGML/HF wikitext2 --wbits 4 --true-sequential --groupsize 128 --save_safetensors /workspace/ggml/TheBloke_Project-Baize-v2-13B-GGML/gptq/Baize-v2-13B-4bit-128g.no-act-order.safetensors
```
## Discord
For further support, and discussions on these models and AI in general, join us at:
[TheBloke AI's Discord server](https://discord.gg/theblokeai)
## Thanks, and how to contribute.
Thanks to the [chirper.ai](https://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**: Sam, theTransient, Jonathan Leane, Steven Wood, webtim, Johann-Peter Hartmann, Geoffrey Montalvo, Gabriel Tamborski, Willem Michiel, John Villwock, Derek Yates, Mesiah Bishop, Eugene Pentland, Pieter, Chadd, Stephen Murray, Daniel P. Andersen, terasurfer, Brandon Frisco, Thomas Belote, Sid, Nathan LeClaire, Magnesian, Alps Aficionado, Stanislav Ovsiannikov, Alex, Joseph William Delisle, Nikolai Manek, Michael Davis, Junyu Yang, K, J, Spencer Kim, Stefan Sabev, Olusegun Samson, transmissions 11, Michael Levine, Cory Kujawski, Rainer Wilmers, zynix, Kalila, Luke @flexchar, Ajan Kanaga, Mandus, vamX, Ai Maven, Mano Prime, Matthew Berman, subjectnull, Vitor Caleffi, Clay Pascal, biorpg, alfie_i, 阿明, Jeffrey Morgan, ya boyyy, Raymond Fosdick, knownsqashed, Olakabola, Leonard Tan, ReadyPlayerEmma, Enrico Ros, Dave, Talal Aujan, Illia Dulskyi, Sean Connelly, senxiiz, Artur Olbinski, Elle, Raven Klaugh, Fen Risland, Deep Realms, Imad Khwaja, Fred von Graf, Will Dee, usrbinkat, SuperWojo, Alexandros Triantafyllidis, Swaroop Kallakuri, Dan Guido, John Detwiler, Pedro Madruga, Iucharbius, Viktor Bowallius, Asp the Wyvern, Edmond Seymore, Trenton Dambrowitz, Space Cruiser, Spiking Neurons AB, Pyrater, LangChain4j, Tony Hughes, Kacper Wikieł, Rishabh Srivastava, David Ziegler, Luke Pendergrass, Andrey, Gabriel Puliatti, Lone Striker, Sebastain Graf, Pierre Kircher, Randy H, NimbleBox.ai, Vadim, danny, Deo Leter
Thank you to all my generous patrons and donaters!
And thank you again to a16z for their generous grant.
# Original model info on Github
## News
- **[May 23, 2023]** We are releasing Baize v2! Check out the [7B](https://huggingface.co/project-baize/baize-v2-7b) and [13B](https://huggingface.co/project-baize/baize-v2-13b) model. Code coming soon!
- **[Apr. 27, 2023]** [Fastchat](https://github.com/lm-sys/FastChat) now supports Baize. Try the new [CLI and API](https://github.com/project-baize/baize-chatbot#cli-and-api)!
- **[Apr. 21, 2023]** We now have a [script](https://github.com/project-baize/baize-chatbot#merge-lora-into-llama) to merge LoRA weights into standard HF model so you can use it everywhere HF is supported!
## What's Baize?
Baize is an open-source chat model trained with [LoRA](https://github.com/microsoft/LoRA). It uses 100k dialogs generated by letting ChatGPT chat with itself. We also use Alpaca's data to improve its performance. We have released 7B, 13B and 30B models. Please refer to the [paper](https://arxiv.org/pdf/2304.01196.pdf) for more details.
## Why it's called Baize?
Baize (pronounced as By-zor; Simplified Chinese 白泽, Traditional Chinese 白澤, Japanese 白沢, はくたく) is a mythical creature in Chinese folklore, who speaks human languages and knows everything. This is exactly what we expect from a chat model.
## Overview
⚠️ All model weights and data are for **research use ONLY**. Commercial use is **strictly prohibited**. We accept **NO responsibility or liability** for any use of our data, code or weights.
This is the repo for the Baize project, which aims to build a chat model with LLaMA. This repository contains:
- 54K/57K/47K [dialogs](data) from Quora, StackOverFlow and MedQuAD questions
- The [code](collect.py) for collecting self-chat data
- The [code](finetune.py) for training Baize
- The [code](demo/app.py) for chat model demo (forked from [ChuanhuChatGPT](https://github.com/GaiZhenbiao/ChuanhuChatGPT))
### Model Release
#### V1
- [Baize-v1-7B (LoRA weights)](https://huggingface.co/project-baize/baize-lora-7B)
- [Baize-v1-13B (LoRA weights)](https://huggingface.co/project-baize/baize-lora-13B)
- [Baize-v1-30B (LoRA weights)](https://huggingface.co/project-baize/baize-lora-30B)
- [Baize Healthcare-7B (LoRA weights)](https://huggingface.co/project-baize/baize-healthcare-lora-7b)
#### V2
- [Baize-v2-7B](https://huggingface.co/project-baize/baize-v2-7b)
- [Baize-v2-13B](https://huggingface.co/project-baize/baize-v2-13b)
### Community Models and Data
- [Fauno](https://github.com/RSTLess-research/Fauno-Italian-LLM/) is an Italian version of Baize.
- [Dutch Data](https://github.com/project-baize/baize-chatbot/issues/34): Baize data translated into Dutch.
## CLI and API
Now you can use Baize with [Fastchat](https://github.com/lm-sys/FastChat) for the CLI and API provided by Fastchat!
First, install the latest version of Fastchat:
```bash
pip install git+https://github.com/huggingface/peft.git
pip install git+https://github.com/lm-sys/FastChat.git
```
(For v1 models only): Merge Baize's LoRA weights into LLaMA. Take 7B checkpoint as an example.
```bash
# Note you have to include "baize" in the target directory so Fastchat can recognize Baize.
python3 -m fastchat.model.apply_lora --base huggyllama/llama-7b --target ./model_weights/baize-7b --lora project-baize/baize-lora-7B
```
Now, run the CLI in your terminal! More options and configs can be found [here](https://github.com/lm-sys/FastChat#inference-with-command-line-interface).
```bash
# Optional: Add `--style rich` for better style.
python -m fastchat.serve.cli --model-path ./model_weights/baize-7b
```
You can use Baize with OpenAI API or Hugging Face API following the instruction [here](https://github.com/lm-sys/FastChat#api).
## Demo
[](https://huggingface.co/spaces/project-baize/Baize-7B)
[](https://huggingface.co/spaces/project-baize/Baize-7B?duplicate=true)
You can either host it on your local machine or access the [online demo](https://huggingface.co/spaces/project-baize/Baize-7B). The demo fetches the [LLaMA](https://huggingface.co/huggyllama/llama-7b) model and the [LoRA weights](https://huggingface.co/project-baize/baize-lora-7B) from the Hugging Face model hub, then runs a user-friendly Gradio interface for chatting.
### How to Run Locally
First, make sure your Python version is 3.8, and then install the required packages using the command below:
```bash
cd demo
pip install -r requirements.txt
```
You can host the model on your local machine using the following command:
```bash
# We assume you have obtained access to use LLaMA. The following LLaMA weights are from a 3rd party.
base_model=huggyllama/llama-7b
lora_model=project-baize/baize-lora-7B
python app.py $base_model $lora_model
```
#### GPU VRAM Requirements
| | Inference (without int8) |
|-----------|--------------------------|
| Baize-7B | 16GB |
| Baize-13B | 28GB |
| Baize-30B | 67GB |
If you have a GPU with smaller VRAM, you can do inference with `int8`, by passing the 8bit argument:
```bash
python app.py $base_model $lora_model 8bit
```
## How to Reproduce
### Setup
1. Install dependencies
```bash
pip install -r requirements.txt
```
2. If `bitsandbytes` doesn't work, [install it from source](https://github.com/TimDettmers/bitsandbytes/blob/main/compile_from_source.md). Windows users can follow [these instructions](https://github.com/tloen/alpaca-lora/issues/17).
### Data Collecting
You can use our [released data](data) or collect the data from ChatGPT using the following command:
```bash
num_process=10 # The number of processes to collect data
max_total_tokens=500000 # Set maximum numbers of tokens to collect data
api_key=xxxxxxxxxxxxxxxxx # Set your openai api key
for ((i=0; i<$num_process; i++))
do
python collect.py $api_key $max_total_tokens $i $num_process stackoverflow &
python collect.py $api_key $max_total_tokens $i $num_process quora &
python collect.py $api_key $max_total_tokens $i $num_process medical &
done
```
After collecting data, you use the following command to preprocess data:
```bash
python preprocess.py stackoverflow
python preprocess.py quora
python preprocess.py medical
```
### Use your own data
If there's a specific dataset you want to use as seeds for ChatGPT self-chatting, you can simply modify `collect.py` to load your own data.
### Training
The fine-tuning code is designed to run on an A100-80G GPU. The `finetune.py` script accepts three parameters: foundation model size (i.e., 7B, 13B, or 30B), batch size, learning rate and datasets. Note the total batch size is fixed to 64 (can be modified [here](https://github.com/project-baize/baize/blob/cbcf39902fcdfab8d935b7ea771a4e7d452a1be0/finetune.py#L24)) and the batch size here is the per device batch size before gradient accumulation. Set it to a smaller value if you are training on a GPU with smaller VRAM.
```bash
# For the 7B model (takes about 9 hours)
python finetune.py 7b 32 0.0002 alpaca,stackoverflow,quora
# For the 13B model (takes about 16 hours)
python finetune.py 13b 16 0.0001 alpaca,stackoverflow,quora
# For the 30B model (takes about 36 hours)
python finetune.py 30b 8 0.00005 alpaca,stackoverflow,quora
```
#### GPU VRAM Consumption
With the settings ABOVE:
| | Training (with int8) |
|-----------|----------------------|
| Baize-7B | 26GB |
| Baize-13B | 25GB |
| Baize-30B | 42GB |
Got a question? See [this issue](https://github.com/project-baize/baize-chatbot/issues/26).
### Merge LoRA into LLaMA
Now you can easily merge the trained LoRA weights into a LLaMA model so you can use it with everything that supports standard Hugging Face API!
Here's an example for merging `baize-lora-7B` into LLaMA-7B.
```bash
python merge_lora.py \
--base huggyllama/llama-7b \
--target ~/model_weights/baize-7b \
--lora project-baize/baize-lora-7B
```
## Citation
```bibtex
@article{xu2023baize,
title={Baize: An Open-Source Chat Model with Parameter-Efficient Tuning on Self-Chat Data},
author={Xu, Canwen and Guo, Daya and Duan, Nan and McAuley, Julian},
journal={arXiv preprint arXiv:2304.01196},
year={2023}
}
```
[](https://huggingface.co)
