TheBloke's picture
Update for Transformers GPTQ support
5a4c2ea
metadata
datasets:
  - Open-Orca/OpenOrca
inference: false
license: other
model_type: llama
TheBlokeAI

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


Open-Orca's OpenChat V2 x OpenOrca Preview 2 GPTQ

These files are GPTQ model files for Open-Orca's OpenChat V2 x OpenOrca Preview 2.

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.

These models were quantised using hardware kindly provided by Latitude.sh.

Repositories available

Prompt template: custom

The conversation template involves concatenating tokens, and cannot be expressed in plain-text.

Besides base model vocabulary, an end-of-turn token <|end_of_turn|> is added.

Here is an example of single-round conversation template:

def tokenize_single_input(tokenizer, prompt):
    # OpenChat V2
    human_prefix = "User:"
    prefix    = "Assistant GPT4:"
    eot_token = "<|end_of_turn|>"
    bos_token = "<s>"

    def _tokenize(text):
        return tokenizer.convert_tokens_to_ids(tokenizer._tokenize(text))

    def _tokenize_special(special_name):
        return tokenizer.convert_tokens_to_ids(special_name)

    return [_tokenize_special(bos_token)] + _tokenize(human_prefix) + _tokenize(prompt) + [_tokenize_special(eot_token)] + \
          _tokenize(prefix)

To explore conditional language models, you can also set prefix = "Assistant GPT3:" to mimic ChatGPT behavior (this may cause performance degradation).

Hint: In BPE, tokenize(A) + tokenize(B) does not always equals to tokenize(A + B).

Due to the custom tokenisation, GGMLs will not be provided.

Provided files

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.

Branch Bits Group Size Act Order (desc_act) File Size ExLlama Compatible? Made With Description
main 4 128 False 7.45 GB True GPTQ-for-LLaMa 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 True 8.00 GB True AutoGPTQ 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_False 4 64 False 7.51 GB True AutoGPTQ 4-bit, without Act Order and group size. Without Act Order to improve AutoGPTQ speed, and better accuracy than 128g-False.
gptq-4bit-64g-actorder_True 4 64 True 7.51 GB True AutoGPTQ 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 True 7.26 GB True AutoGPTQ 4-bit, with Act Order and group size. 128g uses even less VRAM, but with slightly lower accuracy. Poor AutoGPTQ CUDA speed.
gptq-8bit--1g-actorder_True 8 None True 13.36 GB False AutoGPTQ 8-bit, with Act Order. No group size, to lower VRAM requirements and to improve AutoGPTQ speed.
gptq-8bit-128g-actorder_True 8 128 True 13.65 GB False AutoGPTQ 8-bit, with group size 128g for higher inference quality and with Act Order for even higher accuracy. Poor AutoGPTQ CUDA speed.
gptq-8bit-128g-actorder_False 8 128 False 13.65 GB False AutoGPTQ 8-bit, with group size 128g for higher inference quality and without Act Order to improve AutoGPTQ speed.

How to download from branches

  • In text-generation-webui, you can add :branch to the end of the download name, eg TheBloke/openchat_v2_openorca_preview-GPTQ:gptq-4bit-32g-actorder_True
  • With Git, you can clone a branch with:
git clone --branch gptq-4bit-32g-actorder_True https://huggingface.co/TheBloke/openchat_v2_openorca_preview-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.

NOTE: Due to the custom tokenisation, it is probably not possible to usefully use this model in text-generation-webui right now.

I will leave the below instructions in case support is possible, or is added. If/when it does work, let me know and I'll remove this message.

Please do not get in touch saying it doesn't work 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 know how to make a manual install.

  1. Click the Model tab.
  2. Under Download custom model or LoRA, enter TheBloke/openchat_v2_openorca_preview-GPTQ.
  • To download from a specific branch, enter for example TheBloke/openchat_v2_openorca_preview-GPTQ:gptq-4bit-32g-actorder_True
  • 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: openchat_v2_openorca_preview-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 set 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

First make sure you have AutoGPTQ installed:

GITHUB_ACTIONS=true pip install auto-gptq

Then try the following example code:

from transformers import AutoTokenizer, pipeline, logging
from auto_gptq import AutoGPTQForCausalLM, BaseQuantizeConfig

model_name_or_path = "TheBloke/openchat_v2_openorca_preview-GPTQ"
model_basename = "openorca-openchat-v2-preview2-GPTQ-4bit-128g.no-act.order"

use_triton = False

tokenizer = AutoTokenizer.from_pretrained(model_name_or_path, use_fast=True)

model = AutoGPTQForCausalLM.from_quantized(model_name_or_path,
        model_basename=model_basename
        use_safetensors=True,
        trust_remote_code=True,
        device="cuda:0",
        use_triton=use_triton,
        quantize_config=None)

"""
To download from a specific branch, use the revision parameter, as in this example:

model = AutoGPTQForCausalLM.from_quantized(model_name_or_path,
        revision="gptq-4bit-32g-actorder_True",
        model_basename=model_basename,
        use_safetensors=True,
        trust_remote_code=True,
        device="cuda:0",
        quantize_config=None)
"""

prompt = "Tell me about AI"

def tokenize_single_input(tokenizer, prompt):
    # OpenChat V2
    human_prefix = "User:"
    prefix    = "Assistant GPT4:"
    eot_token = "<|end_of_turn|>"
    bos_token = "<s>"

    def _tokenize(text):
        return tokenizer.convert_tokens_to_ids(tokenizer._tokenize(text))

    def _tokenize_special(special_name):
        return tokenizer.convert_tokens_to_ids(special_name)

    return [_tokenize_special(bos_token)] + _tokenize(human_prefix) + _tokenize(prompt) + [_tokenize_special(eot_token)] + \
          _tokenize(prefix)

print("\n\n*** Generate:")

input_ids = tokenizer_single_input(tokenizer, prompt)
output = model.generate(inputs=input_ids, temperature=0.7, max_new_tokens=512)
print(tokenizer.decode(output[0]))

Compatibility

The files provided will work with AutoGPTQ (CUDA and Triton modes), GPTQ-for-LLaMa (only CUDA has been tested), and Occ4m's GPTQ-for-LLaMa fork.

ExLlama works with Llama models in 4-bit. Please see the Provided Files table above for per-file compatibility.

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!

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: 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 card: Open-Orca's OpenChat V2 x OpenOrca Preview 2

OpenChat V2 x OpenOrca Preview 2

This is a preview version of OpenChat V2 trained for 2 epochs (total 5 epochs) on full (4.5M) OpenOrca dataset.

AGIEval Preliminary Results

OpenChat V2 OpenOrca Preview

                            name  accuracy  unmatched
              aqua-rat.zero-shot  0.232283        0.0
             logiqa-en.zero-shot  0.370200        0.0
               lsat-ar.zero-shot  0.230435        0.0
               lsat-lr.zero-shot  0.441176        0.0
               lsat-rc.zero-shot  0.568773        0.0
sat-en-without-passage.zero-shot  0.393204        0.0
                sat-en.zero-shot  0.747573        0.0
              sat-math.zero-shot  0.295455        0.0
                         Average  0.409887        0.0

AGIEval Average reported in Orca paper: 0.417

Serving

This model is compatible with OpenChat V2 vLLM OpenAI API server. It can be used as a drop-in replacement for OpenChat V2 weights.

python -m ochat.serving.openai_api_server --model_type openchat_v2 --model openchat/openchat_v2_openorca_preview --engine-use-ray --worker-use-ray

Conversation Template

The conversation template involves concatenating tokens, and cannot be expressed in plain-text.

Besides base model vocabulary, an end-of-turn token <|end_of_turn|> is added.

Here is an example of single-round conversation template:

def tokenize_single_input(tokenizer, prompt):
    # OpenChat V2
    human_prefix = "User:"
    prefix    = "Assistant GPT4:"
    eot_token = "<|end_of_turn|>"
    bos_token = "<s>"

    def _tokenize(text):
        return tokenizer.convert_tokens_to_ids(tokenizer._tokenize(text))

    def _tokenize_special(special_name):
        return tokenizer.convert_tokens_to_ids(special_name)

    return [_tokenize_special(bos_token)] + _tokenize(human_prefix) + _tokenize(prompt) + [_tokenize_special(eot_token)] + \
           _tokenize(prefix)

To explore conditional language models, you can also set prefix = "Assistant GPT3:" to mimic ChatGPT behavior (this may cause performance degradation).

Hint: In BPE, tokenize(A) + tokenize(B) does not always equals to tokenize(A + B)