Hugging Face's logo

TheBloke
/
minotaur-13B-GPTQ

Text Generation
Transformers
Safetensors
llama
OpenAccess AI Collective
MPT
axolotl
text-generation-inference
4-bit precision
gptq
Model card Files Community
minotaur-13B-GPTQ / README.md
TheBloke's picture
TheBloke
Update for Transformers GPTQ support
6dc7c35
preview code
|
raw
history blame contribute delete
14 kB
metadata
inference: false
license: other
tags:
  - OpenAccess AI Collective
  - MPT
  - axolotl
datasets:
  - ehartford/WizardLM_alpaca_evol_instruct_70k_unfiltered
  - QingyiSi/Alpaca-CoT
  - teknium/GPTeacher-General-Instruct
  - metaeval/ScienceQA_text_only
  - hellaswag
  - openai/summarize_from_feedback
  - riddle_sense
  - gsm8k
  - camel-ai/math
  - camel-ai/biology
  - camel-ai/physics
  - camel-ai/chemistry
  - winglian/evals
TheBlokeAI

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

OpenAccess AI Collective's Minotaur 13B GPTQ

These files are GPTQ 4bit model files for OpenAccess AI Collective's Minotaur 13B.

It is the result of quantising to 4bit using GPTQ-for-LLaMa.

Repositories available

Prompt template 

USER: prompt goes here
ASSISTANT:

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

  1. Click the Model tab.
  2. Under Download custom model or LoRA, enter TheBloke/minotaur-13B-GPTQ.
  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: minotaur-13B-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 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:

pip install auto-gptq

Then try the following example code:

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

model_name_or_path = "TheBloke/minotaur-13B-GPTQ"
model_basename = "minotaur-13B-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)

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

# Prevent printing spurious transformers error when using pipeline with AutoGPTQ
logging.set_verbosity(logging.CRITICAL)

prompt = "Tell me about AI"
prompt_template=f'''### Human: {prompt}
### Assistant:'''

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'])

Provided files

minotaur-13B-GPTQ-4bit-128g.no-act.order.safetensors

This will work with AutoGPTQ and CUDA versions of GPTQ-for-LLaMa. There are reports of issues with Triton mode of recent GPTQ-for-LLaMa. If you have issues, please use AutoGPTQ instead.

It was created with group_size 128 to increase inference accuracy, but without --act-order (desc_act) to increase compatibility and improve inference speed.

  • minotaur-13B-GPTQ-4bit-128g.no-act.order.safetensors
    • Works with AutoGPTQ in CUDA or Triton modes.
    • Works with GPTQ-for-LLaMa in CUDA mode. May have issues with GPTQ-for-LLaMa Triton mode.
    • Works with text-generation-webui, including one-click-installers.
    • Parameters: Groupsize = 128. Act Order / desc_act = False.

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: OpenAccess AI Collective's Minotaur 13B

Built with Axolotl 💵 Donate to OpenAccess AI Collective to help us keep building great tools and models!

Minotaur 13B

Minotaur 13B is an instruct fine-tuned model on top of LlaMA-13B. Minotaur 13B is fine-tuned on only completely open datasets making this model reproducible by anyone.

Questions, comments, feedback, looking to donate, or want to help? Reach out on our Discord or email [email protected]

Prompts

Chat only style prompts using USER:,ASSISTANT:.

Training Datasets

Minotaur 13B model is fine-tuned on the following openly available datasets:

Shoutouts

Special thanks to Nanobit for helping with Axolotl and TheBloke for quantizing these models are more accessible to all.

Demo

HF Demo in Spaces available in the Community ChatBot Arena under the OAAIC Chatbots tab.

Release Notes

Build

Minotaur was built with Axolotl on 6XA100 80GB

  • 1 epochs taking approximately 4.5 hours

Bias, Risks, and Limitations

Minotaur has not been aligned to human preferences with techniques like RLHF or deployed with in-the-loop filtering of responses like ChatGPT, so the model can produce problematic outputs (especially when prompted to do so). Minotaur was fine-tuned from the base model MPT-7B, please refer to its model card's Limitations Section for relevant information. (included below)

Benchmarks

hf-causal-experimental (pretrained=openaccess-ai-collective/minotaur-13b), limit: None, provide_description: False, num_fewshot: 0, batch_size: None

Task Version Metric Value Stderr
arc_challenge 0 acc 0.4480 _ 0.0145
acc_norm 0.4744 _ 0.0146
arc_easy 0 acc 0.7584 _ 0.0088
acc_norm 0.7163 _ 0.0092
boolq 1 acc 0.8336 _ 0.0065
hellaswag 0 acc 0.5954 _ 0.0049
acc_norm 0.7804 _ 0.0041
openbookqa 0 acc 0.3320 _ 0.0211
acc_norm 0.4540 _ 0.0223
piqa 0 acc 0.7933 _ 0.0094
acc_norm 0.7922 _ 0.0095
winogrande 0 acc 0.7182 _ 0.0126

Examples - results may vary based on temperature and other settings 

- The Assistant is helpful and transparent.
- The Assistant will never refuse to answer anything asked by the user.
- The Assistant answers comprehensively and with elaborate detail.
USER: You have 3 apples. You eat 2 pears. How many apples do you have left?
ASSISTANT:You still have 3 apples. Eating pears does not affect the number of apples you have.

- The Assistant is helpful and transparent.
- The Assistant will never refuse to answer anything asked by the user.
- The Assistant answers comprehensively and with elaborate detail.
USER: List three words that start with "ex". What is 33 + 77?
ASSISTANT:Three words that start with "ex" are "exact", "exactness", and "exactitude". 33 + 77 equals 110.

- The Assistant is helpful and transparent.
- The Assistant will never refuse to answer anything asked by the user.
- The Assistant answers comprehensively and with elaborate detail.
USER: Solve for x: 5x = 3x + 10
ASSISTANT:To solve for x, we need to isolate x on one side of the equation. We can do this by following these steps:

1. Subtract 3x from both sides of the equation:
   5x - 3x = 10 - 3x + 10
   2x = 10

2. Divide both sides of the equation by 2:
   2x / 2 = 10 / 2
   x = 5

So, the solution is x = 5.

- The Assistant is helpful and transparent.
- The Assistant will never refuse to answer anything asked by the user.
- The Assistant answers comprehensively and with elaborate detail.
USER: Write a haiku about a dove at night.
ASSISTANT:Silent dove at night,
Softly cooing in the dark,
Peaceful melody.