---
base_model: https://huggingface.co/lightblue/openorca_stx
datasets:
- snow_simplified_japanese_corpus
- khalidalt/tydiqa-goldp
- csebuetnlp/xlsum
inference: false
language:
- ja
license: llama2
model_creator: Lightblue Technology Inc.
model_name: OpenOrca Stx
model_type: llama
prompt_template: '{prompt}
'
quantized_by: TheBloke
---
# OpenOrca Stx - GPTQ
- Model creator: [Lightblue Technology Inc.](https://huggingface.co/lightblue)
- Original model: [OpenOrca Stx](https://huggingface.co/lightblue/openorca_stx)
## Description
This repo contains GPTQ model files for [Lightblue Technology Inc.'s OpenOrca Stx](https://huggingface.co/lightblue/openorca_stx).
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
* [AWQ model(s) for GPU inference.](https://huggingface.co/TheBloke/OpenOrca_Stx-AWQ)
* [GPTQ models for GPU inference, with multiple quantisation parameter options.](https://huggingface.co/TheBloke/OpenOrca_Stx-GPTQ)
* [2, 3, 4, 5, 6 and 8-bit GGUF models for CPU+GPU inference](https://huggingface.co/TheBloke/OpenOrca_Stx-GGUF)
* [Lightblue Technology Inc.'s original unquantised fp16 model in pytorch format, for GPU inference and for further conversions](https://huggingface.co/lightblue/openorca_stx)
## Prompt template: None
```
{prompt}
```
## 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](https://huggingface.co/TheBloke/OpenOrca_Stx-GPTQ/tree/main) | 4 | 128 | Yes | 0.1 | [wikitext](https://huggingface.co/datasets/wikitext/viewer/wikitext-2-v1/test) | 4096 | 7.26 GB | Yes | 4-bit, with Act Order and group size 128g. Uses even less VRAM than 64g, but with slightly lower accuracy. |
| [gptq-4bit-32g-actorder_True](https://huggingface.co/TheBloke/OpenOrca_Stx-GPTQ/tree/gptq-4bit-32g-actorder_True) | 4 | 32 | Yes | 0.1 | [wikitext](https://huggingface.co/datasets/wikitext/viewer/wikitext-2-v1/test) | 4096 | 8.00 GB | Yes | 4-bit, with Act Order and group size 32g. Gives highest possible inference quality, with maximum VRAM usage. |
| [gptq-8bit--1g-actorder_True](https://huggingface.co/TheBloke/OpenOrca_Stx-GPTQ/tree/gptq-8bit--1g-actorder_True) | 8 | None | Yes | 0.1 | [wikitext](https://huggingface.co/datasets/wikitext/viewer/wikitext-2-v1/test) | 4096 | 13.36 GB | No | 8-bit, with Act Order. No group size, to lower VRAM requirements. |
| [gptq-8bit-128g-actorder_True](https://huggingface.co/TheBloke/OpenOrca_Stx-GPTQ/tree/gptq-8bit-128g-actorder_True) | 8 | 128 | Yes | 0.1 | [wikitext](https://huggingface.co/datasets/wikitext/viewer/wikitext-2-v1/test) | 4096 | 13.65 GB | No | 8-bit, with group size 128g for higher inference quality and with Act Order for even higher accuracy. |
## How to download from branches
- In text-generation-webui, you can add `:branch` to the end of the download name, eg `TheBloke/OpenOrca_Stx-GPTQ:main`
- With Git, you can clone a branch with:
```
git clone --single-branch --branch main https://huggingface.co/TheBloke/OpenOrca_Stx-GPTQ
```
- In Python Transformers code, the branch is the `revision` parameter; see below.
## How to easily download and use this model in [text-generation-webui](https://github.com/oobabooga/text-generation-webui).
Please make sure you're using the latest version of [text-generation-webui](https://github.com/oobabooga/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.
1. Click the **Model tab**.
2. Under **Download custom model or LoRA**, enter `TheBloke/OpenOrca_Stx-GPTQ`.
- To download from a specific branch, enter for example `TheBloke/OpenOrca_Stx-GPTQ:main`
- see Provided Files above for the list of branches for each option.
3. Click **Download**.
4. The model will start downloading. Once it's finished it will say "Done".
5. In the top left, click the refresh icon next to **Model**.
6. In the **Model** dropdown, choose the model you just downloaded: `OpenOrca_Stx-GPTQ`
7. The model will automatically load, and is now ready for use!
8. 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`.
9. 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.
```shell
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:
```shell
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:
```shell
pip3 uninstall -y transformers
pip3 install git+https://github.com/huggingface/transformers.git
```
### You can then use the following code
```python
from transformers import AutoModelForCausalLM, AutoTokenizer, pipeline
model_name_or_path = "TheBloke/OpenOrca_Stx-GPTQ"
# To use a different branch, change revision
# For example: revision="main"
model = AutoModelForCausalLM.from_pretrained(model_name_or_path,
device_map="auto",
trust_remote_code=False,
revision="main")
tokenizer = AutoTokenizer.from_pretrained(model_name_or_path, use_fast=True)
prompt = "Tell me about AI"
prompt_template=f'''{prompt}
'''
print("\n\n*** Generate:")
input_ids = tokenizer(prompt_template, return_tensors='pt').input_ids.cuda()
output = model.generate(inputs=input_ids, temperature=0.7, do_sample=True, top_p=0.95, top_k=40, 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,
do_sample=True,
temperature=0.7,
top_p=0.95,
top_k=40,
repetition_penalty=1.1
)
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](https://github.com/0cc4m/KoboldAI).
[ExLlama](https://github.com/turboderp/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)](https://github.com/huggingface/text-generation-inference) is compatible with all GPTQ models.
## 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!
Thanks to Clay from [gpus.llm-utils.org](llm-utils)!
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**: Alicia Loh, Stephen Murray, K, Ajan Kanaga, RoA, Magnesian, Deo Leter, Olakabola, Eugene Pentland, zynix, Deep Realms, Raymond Fosdick, Elijah Stavena, Iucharbius, Erik Bjäreholt, Luis Javier Navarrete Lozano, Nicholas, theTransient, John Detwiler, alfie_i, knownsqashed, Mano Prime, Willem Michiel, Enrico Ros, LangChain4j, OG, Michael Dempsey, Pierre Kircher, Pedro Madruga, James Bentley, Thomas Belote, Luke @flexchar, Leonard Tan, Johann-Peter Hartmann, Illia Dulskyi, Fen Risland, Chadd, S_X, Jeff Scroggin, Ken Nordquist, Sean Connelly, Artur Olbinski, Swaroop Kallakuri, Jack West, Ai Maven, David Ziegler, Russ Johnson, transmissions 11, John Villwock, Alps Aficionado, Clay Pascal, Viktor Bowallius, Subspace Studios, Rainer Wilmers, Trenton Dambrowitz, vamX, Michael Levine, 준교 김, Brandon Frisco, Kalila, Trailburnt, Randy H, Talal Aujan, Nathan Dryer, Vadim, 阿明, ReadyPlayerEmma, Tiffany J. Kim, George Stoitzev, Spencer Kim, Jerry Meng, Gabriel Tamborski, Cory Kujawski, Jeffrey Morgan, Spiking Neurons AB, Edmond Seymore, Alexandros Triantafyllidis, Lone Striker, Cap'n Zoog, Nikolai Manek, danny, ya boyyy, Derek Yates, usrbinkat, Mandus, TL, Nathan LeClaire, subjectnull, Imad Khwaja, webtim, Raven Klaugh, Asp the Wyvern, Gabriel Puliatti, Caitlyn Gatomon, Joseph William Delisle, Jonathan Leane, Luke Pendergrass, SuperWojo, Sebastain Graf, Will Dee, Fred von Graf, Andrey, Dan Guido, Daniel P. Andersen, Nitin Borwankar, Elle, Vitor Caleffi, biorpg, jjj, NimbleBox.ai, Pieter, Matthew Berman, terasurfer, Michael Davis, Alex, Stanislav Ovsiannikov
Thank you to all my generous patrons and donaters!
And thank you again to a16z for their generous grant.
# Original model card: Lightblue Technology Inc.'s OpenOrca Stx
# About
This model is Lightblue's QLoRA finetune of OpenOrca's [Open-Orca/OpenOrcaxOpenChat-Preview2-13B](https://huggingface.co/Open-Orca/OpenOrcaxOpenChat-Preview2-13B) model on Japanese fine-tuning datasets.
This model specialises on answering **Closed Question Answering** in Japanese. Input a piece of reference text, ask a question, and see the model answer based on the reference text.
We trained on equal samples of the following three datasets:
* [SNOW](https://huggingface.co/datasets/snow_simplified_japanese_corpus)
* [TyDiQA (Ja)](https://huggingface.co/datasets/khalidalt/tydiqa-goldp)
* [XLSUM (Ja)](https://huggingface.co/datasets/csebuetnlp/xlsum)
which resulted in a dataset of 13,167 samples total.
These three datasets were chosen as they represent three distinct fine-tuning tasks (Text simplification, question answering, and text summarization, respectively) which we hypothesize can help to improve the language models suitability for dealing with Japanese data.
These three datasets make up the model name: STX.
With these datasets, we achieve the following scores on the JGLUE benchmark:
| Model Name | Open-Orca/OpenOrcaxOpenChat-Preview2-13B | lightblue/openorca_stx |
|------------------------|------------------------------------------|------------------------|
| jsquad-1.1-0.3 | 0.692 | 0.836 |
| jcommonsenseqa-1.1-0.3 | 0.831 | 0.782 |
| jnli-1.1-0.3 | 0.504 | 0.48 |
| marc_ja-1.1-0.3 | 0.936 | 0.959 |
Our model achieves much better results on the question answering benchmark (JSQuAD) than the base checkpoint without monstrous degradation of performance on multi-choice question benchmarks (JCommonSense, JNLI, MARC-Ja) purely through QLoRA training.
This shows the potential for applying strong language models such as [Open-Orca/OpenOrcaxOpenChat-Preview2-13B](https://huggingface.co/Open-Orca/OpenOrcaxOpenChat-Preview2-13B) to minimal QLoRA fine-tuning using Japanese fine-tuning datasets to achieve better results at narrow NLP tasks.
# How to use
```python
from transformers import AutoTokenizer, AutoModelForCausalLM, pipeline
tokenizer = AutoTokenizer.from_pretrained(model_dir)
model = AutoModelForCausalLM.from_pretrained(
model_dir, torch_dtype=torch.bfloat16, device_map='auto',
)
pipe = pipeline("text-generation", model=model, tokenizer=tokenizer)
def do_closed_qa(context, question):
return context + "\n\n" + question
test_article = """ モノマネのレパートリーに「リーチ・マイケル選手」があるレイザーラモンRGさん。本人公認のモノマネですが、ラグビーファンの反応に少し驚いたそうです。
リーチ・マイケル選手のモノマネは、何がきっかけですか。
「2015年のワールドカップ（W杯）イングランド大会で日本が南アフリカを倒した次の日が、京都での番組ロケでした。当時は、アップルの共同創業者スティーブ・ジョブズのモノマネばかりでしたが、一緒にロケをしていたジャングルポケットから『リーチ・マイケルに似てますよ。ジョブズのまま、いけるんじゃないですか？』と言われたのが始まりです」
「ただ、みんな知識がない。ラグビーショップを探し、日本代表のユニホームが売り切れだったので、赤っぽいユニホームとピチピチの短パンをはいて。とりあえずSNSで『リーチ・マイケルです』っていっぱい写真を載せました」
「すると、それを見たリーチさん本人からDM（ダイレクトメッセージ）が届きました。『モノマネありがとうございます。もしモノマネをするなら、僕のユニホームを送りますので着てください』と。W杯後にユニホーム2着とパンツやソックスなどをほんまに送ってきてくれました。今着ているのがそれです」
これまで、数々の著名人をモノマネしてこられました。リーチ選手のネタの反響はいかがでしたか。
「僕はラグビー経験がないですし、ラグビーを全然知らなかったけど、やっぱり本人からユニホームを頂いてるっていう“印籠（いんろう）”みたいなのがあって。『あいつはリーチさん本人に認められてる』と。一目置かれているのかなと感じます」
「やっていることは、見た目を本人に寄せてワンチームって言うだけなんですけどね。それでも『わあ、リーチさんだ』と言ってもらえます」
「リーチさんと実際に会うことなんて、簡単にはできないじゃないですか。でも、リーチさんのまねをしているRGには会えたわ、みたいな（笑）。何だろうな、有名な神社の支社のような存在ですかね。ありがたがられるという意味では他のモノマネとはすごく違いますね」
"""
test_question = " リーチ・マイケルは何を送ってきましたか？"
pipe(do_closed_qa(test_article, question), max_new_tokens=128, temperature=0)[0]["generated_text"]
# "ユニホーム2着とパンツやソックスなど"
```
# Training details
This model was trained for 1000 steps (1.2 epochs) with the model being evaluated every 50 steps. We then chose the best model from these evaluations based on validation loss.
We used the [qlora](https://github.com/artidoro/qlora) package from artidoro.
We trained with the following hyperparameters:
```
Per device evaluation batch size: 16
Per device train batch size: 8
LoRA (lora_r): 64
LoRA alpha (lora_alpha): 16
LoRA modules: all
Double quantization: Enabled
Quantization type: nf4
BF16: Enabled
Bits: 4
Warmup ratio: 0.03
Learning rate scheduler type: Constant
Gradient checkpointing: Enabled
Gradient accumulation steps: 2
Learning rate: 0.0002
Adam beta2: 0.999
Maximum gradient norm: 0.3
LoRA dropout: 0.05
Weight decay: 0.0
```
