TheBloke's picture
Update base_model formatting
cd25093
metadata
language:
  - en
license: llama2
library_name: transformers
datasets:
  - Open-Orca/OpenOrca
model_name: OpenOrca x OpenChat - Preview2 - 13B
base_model: Open-Orca/OpenOrcaxOpenChat-Preview2-13B
inference: false
model_creator: Open-Orca
model_type: llama
pipeline_tag: text-generation
prompt_template: |
  GPT4 User: {prompt}<|end_of_turn|>GPT4 Assistant:
quantized_by: TheBloke
TheBlokeAI

TheBloke's LLM work is generously supported by a grant from andreessen horowitz (a16z)


OpenOrca x OpenChat - Preview2 - 13B - GPTQ

Description

This repo contains GPTQ model files for Open-Orca's OpenOrca x OpenChat - Preview2 - 13B.

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

Prompt template: OpenChat

GPT4 User: {prompt}<|end_of_turn|>GPT4 Assistant:

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 7.26 GB Yes 4-bit, without Act Order and group size 128g.
gptq-4bit-32g-actorder_True 4 32 Yes 0.1 wikitext 4096 8.00 GB Yes 4-bit, with Act Order and group size 32g. Gives highest possible inference quality, with maximum VRAM usage.
gptq-4bit-64g-actorder_True 4 64 Yes 0.1 wikitext 4096 7.51 GB Yes 4-bit, with Act Order and group size 64g. Uses less VRAM than 32g, but with slightly lower accuracy.
gptq-4bit-128g-actorder_True 4 128 Yes 0.1 wikitext 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-8bit--1g-actorder_True 8 None Yes 0.1 wikitext 4096 13.36 GB No 8-bit, with Act Order. No group size, to lower VRAM requirements.
gptq-8bit-128g-actorder_True 8 128 Yes 0.1 wikitext 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/OpenOrcaxOpenChat-Preview2-13B-GPTQ:main
  • With Git, you can clone a branch with:
git clone --single-branch --branch main https://huggingface.co/TheBloke/OpenOrcaxOpenChat-Preview2-13B-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.

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.

  1. Click the Model tab.
  2. Under Download custom model or LoRA, enter TheBloke/OpenOrcaxOpenChat-Preview2-13B-GPTQ.
  • To download from a specific branch, enter for example TheBloke/OpenOrcaxOpenChat-Preview2-13B-GPTQ:main
  • see Provided Files above for the list of branches for each option.
  1. Click Download.
  2. The model will start downloading. Once it's finished it will say "Done".
  3. In the top left, click the refresh icon next to Model.
  4. In the Model dropdown, choose the model you just downloaded: OpenOrcaxOpenChat-Preview2-13B-GPTQ
  5. The model will automatically load, and is now ready for use!
  6. 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.
  1. 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/OpenOrcaxOpenChat-Preview2-13B-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'''GPT4 User: {prompt}<|end_of_turn|>GPT4 Assistant:

'''

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.

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:

TheBloke AI's Discord server

Thanks, and how to contribute

Thanks to the chirper.ai team!

Thanks to Clay from gpus.llm-utils.org!

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.

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: Open-Orca's OpenOrca x OpenChat - Preview2 - 13B

🐋 The Second OpenOrca Model Preview! 🐋

OpenOrca Logo

OpenOrca x OpenChat - Preview2 - 13B

We have used our own OpenOrca dataset to fine-tune Llama2-13B using OpenChat packing. This dataset is our attempt to reproduce the dataset generated for Microsoft Research's Orca Paper.

This second preview release is trained on a curated filtered subset of most of our GPT-4 augmented data.

This release highlights that our dataset and training methods have surpassed performance parity with the Orca paper. We measured this with BigBench-Hard and AGIEval results with the same methods as used in the Orca paper, finding ~103% of original Orca's performance on average. As well, this is done with <1/10th the compute requirement and using <20% of the dataset size from the original Orca paper.

We have run extensive evaluations internally and expect this model to place number 1 on both the HuggingFaceH4 Open LLM Leaderboard and the GPT4ALL Leaderboard for 13B models.

"One" of OpenChat has joined our team, and we'd like to provide special thanks for their training of this model! We have utilized OpenChat MultiPack algorithm which achieves 99.85% bin-packing efficiency on our dataset. This has significantly reduced training time, with efficiency improvement of 3-10X over traditional methods.

Want to visualize our full (pre-filtering) dataset? Check out our Nomic Atlas Map.

Atlas Nomic Dataset Map

We are in-process with training more models, so keep a look out on our org for releases coming soon with exciting partners.

We will also give sneak-peak announcements on our Discord, which you can find here:

https://AlignmentLab.ai

Prompt Template

We use our own prompt template which we call "OpenChat Llama2 V1".

The model is heavily conditioned to work using this format only and will likely encounter issues such as run-on output which emulates a chat between a user and assistant if this format is not properly followed.

Examples:

# Single-turn `OpenChat Llama2 V1`
tokenize("You are OpenOrcaChat.<|end_of_turn|>User: Hello<|end_of_turn|>Assistant:")
# [1, 887, 526, 4673, 2816, 1113, 1451, 271, 29889, 32000, 4911, 29901, 15043, 32000, 4007, 22137, 29901]

# Multi-turn `OpenChat Llama2 V1`
tokenize("You are OpenOrcaChat.<|end_of_turn|>User: Hello<|end_of_turn|>Assistant: Hi<|end_of_turn|>User: How are you today?<|end_of_turn|>Assistant:")
# [1, 887, 526, 4673, 2816, 1113, 1451, 271, 29889, 32000, 4911, 29901, 15043, 32000, 4007, 22137, 29901, 6324, 32000, 4911, 29901, 1128, 526, 366, 9826, 29973, 32000, 4007, 22137, 29901]

For UIs with Prefix and Suffix fields, these will likely work:

Prefix (include a space after colon):

User: 

Suffix (space after colon):

<|end_of_turn|>\nAssistant: 

Oobabooga's text-generation-webui instructions can be found further down the page.

Evaluation

We have evaluated OpenOrcaxOpenChat-Preview2-13B on hard reasoning tasks from BigBench-Hard and AGIEval as outlined in the Orca paper.

Our average performance for BigBench-Hard: 0.488

Average for AGIEval: 0.447

We find our score averages to ~103% of the total performance that was shown in the Orca paper, using the same evaluation methods as outlined in the paper.

So we are surpassing Orca performance with <20% of the dataset size and <1/10th the training budget!

As well, we have evaluated using the methodology and tools for the HuggingFace Leaderboard and GPT4ALL Leaderboard, and find that we place #1 on both for all 13B models at release time!

AGIEval Performance

We present our results in two columns. The column for "(Orca Paper eval)" uses the methods outlined in the Orca paper, so as to be a direct apples-to-apples comparison with the results from the paper. The column for "(HF Leaderboard eval)" uses EleutherAI's LM Evaluation Harness with settings outlined by HuggingFace. These results are not comparable to the other columns, as the methods are different.

OpenOrca Preview2 AGIEval Performance

BigBench-Hard Performance

We present our results in two columns. The column for "(Orca Paper eval)" uses the methods outlined in the Orca paper, so as to be a direct apples-to-apples comparison with the results from the paper. The column for "(HF Leaderboard eval)" uses EleutherAI's LM Evaluation Harness with settings outlined by HuggingFace. These results are not comparable to the other columns, as the methods are different.

OpenOrca Preview2 BigBench-Hard Performance

HuggingFaceH4 Open LLM Leaderboard Performance

We have run our own tests using parameters matching the HuggingFaceH4 Open LLM Leaderboard evals.

We place #1 for all 13B models at release time!

OpenOrca Preview2 HuggingFace Leaderboard Internal Performance

Update Aug 10th: The official results on the leaderboard are below.

OpenOrca Preview2 HuggingFace Leaderboard Performance

Since our release, a new model which merges an Orca-style model with a Platypus (trained on STEM and logic) model places narrowly above ours, but we were #1 at release time.

Below we also highlight how our model fits relative to models of all sizes on the current (as of Aug 10th, 2023) leaderboard.

OpenOrca Preview2 HuggingFace Leaderboard Performance

Notably, performance is beyond falcon-40b-instruct, and close to LLaMA1-65B base.

GPT4ALL Leaderboard Performance

We have tested using parameters matching the GPT4ALL Benchmark Suite and report our results and placement vs their official reporting below.

We place #1 for all open models and come within comparison of text-davinci-003, a proprietary OpenAI model an order of magnitude larger.

OpenOrca Preview2 GPT4ALL Performance

Dataset

We used a curated, filtered selection of most of the GPT-4 augmented data from our OpenOrca dataset, which aims to reproduce the Orca Research Paper dataset. Further details of our curation practices will be forthcoming with our full model releases.

Training

We trained with 8x A100-80G GPUs for 46 hours, completing 5 epochs of full fine tuning on our dataset in one training run. This contrasts with the 20x A100-80G GPUs for 200 hours used in the Orca paper, for only 3 epochs, and requiring stacked training (which is known to suffer catastrophic forgetting). Our compute requirement was <1/10th that of the original Orca. Commodity cost was ~$600.

Please await our full releases for further training details.

Serving

This model is most easily served with OpenChat's customized vLLM OpenAI-compatible API server. This is highly recommended as it is by far the fastest in terms of inference speed and is a quick and easy option for setup. We also illustrate setup of Oobabooga/text-generation-webui below. The settings outlined there will also apply to other uses of Transformers.

Serving Quantized

Pre-quantized models are now available courtesy of our friend TheBloke:

The serving instructions below only apply to the unquantized model being presented in the repository you are viewing here. There are some notes, such as on use of the prompt format, that will still apply to the quantized models though.

Serving with OpenChat

Install OpenChat

After installation, run:

python -m ochat.serving.openai_api_server \
  --model-type openchat_llama2 \
  --model Open-Orca/OpenOrcaxOpenChat-Preview2-13B \
  --engine-use-ray --worker-use-ray --max-num-batched-tokens 5120

Follow the OpenChat documentation to use features such as tensor parallelism on consumer GPUs, API keys, and logging. You may then connect to the OpenAI-compatible API endpoint with tools such as BetterGPT.chat.

Serving with Oobabooga / text-generation-webui

The model may also be loaded via oobabooga/text-generation-webui in a similar manner to other models. See the requirements below. Note that inference with just the Transformers library is significantly slower than using the recommended OpenChat vLLM server.

Oobabooga Key Requirements

  • You will first need to download the model as you normally do to the "models/" folder of your text-generation-webui installation.
  • To use the unquantized model presented here, select "Transformers"" in the webui's "Model" tab "Model loader" dropdown.
    • You will likely want to tick "auto-devices". The model will require >40GB VRAM after loading in context for inference.
    • The model was trained in bf16, so tick the "bf16" box for best performance.
    • It will run safely on single GPUs with VRAM >=48GB (e.g. A6000)
      • If using consumer GPUs, e.g. 2x RTX3090 24GB, you will likely want to enter "18,17" under "tensor_split" to split the model across both GPUs
  • The model will perform significantly better if you use the appropriate prompting template
    • We will submit a PR to include our prompting template into text-generation-webui soon
    • For now, manually enter the settings described in the following sections:

Oobabooga Chat Settings

In the "Chat settings" tab, select the following settings:

For "User String" ...

User:

For "Bot string" ...

Assistant:

For "Context", this is analogous to system prompt. It is not necessary, but we have found good results with the below example. System prompts used in the Orca training also work well. ...

You are a helpful assistant. Please answer truthfully and write out your thinking step by step to be sure you get the right answer. If you make a mistake or encounter an error in your thinking, say so out loud and attempt to correct it. If you don't know or aren't sure about something, say so clearly. You will act as a professional logician, mathematician, and physicist. You will also act as the most appropriate type of expert to answer any particular question or solve the relevant problem; state which expert type your are, if so. Also think of any particular named expert that would be ideal to answer the relevant question or solve the relevant problem; name and act as them, if appropriate.

For "Turn template", this is absolutely essential to have. You will get poor, mixed up output without this template ...

<|user|> <|user-message|><|end_of_turn|>\n<|bot|> <|bot-message|>\n

When done, it should look as below:

You may then save this as a named template preset by clicking the "Floppy" icon and giving it an appropriate name in the popup, e.g. "OpenOrcaxOpenChat Llama2".

Oobabooga Text Generation Mode

In the "Text generation" tab, select "instruct" as the mode:

Mode Illustration

It should look as below:

Then you should be ready to generate!

Citation

@software{OpenOrcaxOpenChatPreview2,
  title = {OpenOrcaxOpenChatPreview2: Llama2-13B Model Instruct-tuned on Filtered OpenOrcaV1 GPT-4 Dataset},
  author = {Guan Wang and Bleys Goodson and Wing Lian and Eugene Pentland and Austin Cook and Chanvichet Vong and "Teknium"},
  year = {2023},
  publisher = {HuggingFace},
  journal = {HuggingFace repository},
  howpublished = {\url{https://https://huggingface.co/Open-Orca/OpenOrcaxOpenChat-Preview2-13B},
}
@software{openchat,
  title = {{OpenChat: Advancing Open-source Language Models with Imperfect Data}},
  author = {Wang, Guan and Cheng, Sijie and Yu, Qiying and Liu, Changling},
  doi = {10.5281/zenodo.8105775},
  url = {https://github.com/imoneoi/openchat},
  version = {pre-release},
  year = {2023},
  month = {7},
}
@misc{mukherjee2023orca,
      title={Orca: Progressive Learning from Complex Explanation Traces of GPT-4}, 
      author={Subhabrata Mukherjee and Arindam Mitra and Ganesh Jawahar and Sahaj Agarwal and Hamid Palangi and Ahmed Awadallah},
      year={2023},
      eprint={2306.02707},
      archivePrefix={arXiv},
      primaryClass={cs.CL}
}
@misc{longpre2023flan,
      title={The Flan Collection: Designing Data and Methods for Effective Instruction Tuning}, 
      author={Shayne Longpre and Le Hou and Tu Vu and Albert Webson and Hyung Won Chung and Yi Tay and Denny Zhou and Quoc V. Le and Barret Zoph and Jason Wei and Adam Roberts},
      year={2023},
      eprint={2301.13688},
      archivePrefix={arXiv},
      primaryClass={cs.AI}
}
@misc{touvron2023llama,
    title={Llama 2: Open Foundation and Fine-Tuned Chat Models}, 
    author={Hugo Touvron and Louis Martin and Kevin Stone and Peter Albert and Amjad Almahairi and Yasmine Babaei and Nikolay Bashlykov and Soumya Batra and Prajjwal Bhargava and Shruti Bhosale and Dan Bikel and Lukas Blecher and Cristian Canton Ferrer and Moya Chen and Guillem Cucurull and David Esiobu and Jude Fernandes and Jeremy Fu and Wenyin Fu and Brian Fuller and Cynthia Gao and Vedanuj Goswami and Naman Goyal and Anthony Hartshorn and Saghar Hosseini and Rui Hou and Hakan Inan and Marcin Kardas and Viktor Kerkez and Madian Khabsa and Isabel Kloumann and Artem Korenev and Punit Singh Koura and Marie-Anne Lachaux and Thibaut Lavril and Jenya Lee and Diana Liskovich and Yinghai Lu and Yuning Mao and Xavier Martinet and Todor Mihaylov and Pushkar Mishra and Igor Molybog and Yixin Nie and Andrew Poulton and Jeremy Reizenstein and Rashi Rungta and Kalyan Saladi and Alan Schelten and Ruan Silva and Eric Michael Smith and Ranjan Subramanian and Xiaoqing Ellen Tan and Binh Tang and Ross Taylor and Adina Williams and Jian Xiang Kuan and Puxin Xu and Zheng Yan and Iliyan Zarov and Yuchen Zhang and Angela Fan and Melanie Kambadur and Sharan Narang and Aurelien Rodriguez and Robert Stojnic and Sergey Edunov and Thomas Scialom},
    year={2023},
    eprint={2307.09288},
    archivePrefix={arXiv},
}