README.md

---
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
---

<!-- header start -->
<div style="width: 100%;">
    <img src="https://i.imgur.com/EBdldam.jpg" alt="TheBlokeAI" style="width: 100%; min-width: 400px; display: block; margin: auto;">
</div>
<div style="display: flex; justify-content: space-between; width: 100%;">
    <div style="display: flex; flex-direction: column; align-items: flex-start;">
        <p><a href="https://discord.gg/Jq4vkcDakD">Chat & support: my new Discord server</a></p>
    </div>
    <div style="display: flex; flex-direction: column; align-items: flex-end;">
        <p><a href="https://www.patreon.com/TheBlokeAI">Want to contribute? TheBloke's Patreon page</a></p>
    </div>
</div>
<!-- header end -->

# OpenAccess AI Collective's Minotaur 13B GPTQ

These files are GPTQ 4bit model files for [OpenAccess AI Collective's Minotaur 13B](https://huggingface.co/openaccess-ai-collective/minotaur-13b).

It is the result of quantising to 4bit using [GPTQ-for-LLaMa](https://github.com/qwopqwop200/GPTQ-for-LLaMa).

## Repositories available

* [4-bit GPTQ models for GPU inference](https://huggingface.co/TheBloke/minotaur-13B-GPTQ)
* [2, 3, 4, 5, 6 and 8-bit GGML models for CPU+GPU inference](https://huggingface.co/TheBloke/minotaur-13B-GGML)
* [Unquantised fp16 model in pytorch format, for GPU inference and for further conversions](https://huggingface.co/openaccess-ai-collective/minotaur-13b)

## 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`.
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

First make sure you have [AutoGPTQ](https://github.com/PanQiWei/AutoGPTQ) installed:

`pip install auto-gptq`

Then try the following example code:

```python
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.

<!-- footer start -->
## Discord

For further support, and discussions on these models and AI in general, join us at:

[TheBloke AI's Discord server](https://discord.gg/Jq4vkcDakD)

## 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**: Luke from CarbonQuill, Aemon Algiz, Dmitriy Samsonov.

**Patreon special mentions**: Ajan Kanaga, Kalila, Derek Yates, Sean Connelly, Luke, Nathan LeClaire, Trenton Dambrowitz, Mano Prime, David Flickinger, vamX, Nikolai Manek, senxiiz, Khalefa Al-Ahmad, Illia Dulskyi, trip7s trip, Jonathan Leane, Talal Aujan, Artur Olbinski, Cory Kujawski, Joseph William Delisle, Pyrater, Oscar Rangel, Lone Striker, Luke Pendergrass, Eugene Pentland, Johann-Peter Hartmann.

Thank you to all my generous patrons and donaters!

<!-- footer end -->

# Original model card: OpenAccess AI Collective's Minotaur 13B

[<img src="https://raw.githubusercontent.com/OpenAccess-AI-Collective/axolotl/main/image/axolotl-badge-web.png" alt="Built with Axolotl" width="200" height="32"/>](https://github.com/OpenAccess-AI-Collective/axolotl)
**[💵 Donate to OpenAccess AI Collective](https://github.com/sponsors/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](https://discord.gg/PugNNHAF5r) or email [[email protected]](mailto:[email protected])

# Prompts
Chat only style prompts using `USER:`,`ASSISTANT:`.

# Training Datasets

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

- [WizardLM](https://huggingface.co/datasets/ehartford/WizardLM_alpaca_evol_instruct_70k_unfiltered)
- [subset of QingyiSi/Alpaca-CoT for roleplay and CoT](https://huggingface.co/QingyiSi/Alpaca-CoT)
- [GPTeacher-General-Instruct](https://huggingface.co/datasets/teknium/GPTeacher-General-Instruct)
- [metaeval/ScienceQA_text_only](https://huggingface.co/datasets/metaeval/ScienceQA_text_only) - instruct for concise responses
- [openai/summarize_from_feedback](https://huggingface.co/datasets/openai/summarize_from_feedback) - instruct augmented tl;dr summarization
- [camel-ai/math](https://huggingface.co/datasets/camel-ai/math)
- [camel-ai/physics](https://huggingface.co/datasets/camel-ai/physics)
- [camel-ai/chemistry](https://huggingface.co/datasets/camel-ai/chemistry)
- [camel-ai/biology](https://huggingface.co/datasets/camel-ai/biology)
- [winglian/evals](https://huggingface.co/datasets/winglian/evals) - instruct augmented datasets
  - custom sysnthetic datasets around misconceptions, in-context qa, jokes, N-tasks problems, and context-insensitivity
  - ARC-Easy & ARC-Challenge - instruct augmented for detailed responses, derived from the `train` split
  - [hellaswag](https://huggingface.co/datasets/hellaswag) - 30K+ rows of instruct augmented for detailed explanations w 30K+ rows, derived from the `train` split
  - [riddle_sense](https://huggingface.co/datasets/riddle_sense) - instruct augmented 
  - [gsm8k](https://huggingface.co/datasets/gsm8k) - instruct augmented 

# 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](https://huggingface.co/spaces/openaccess-ai-collective/rlhf-arena) under the OAAIC Chatbots tab.

## Release Notes

- https://wandb.ai/wing-lian/minotaur-13b/runs/5zji06u6

## Build

Minotaur was built with [Axolotl](https://github.com/OpenAccess-AI-Collective/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.
```