Hugging Face's logo

TheBloke
/
minotaur-15B-GGML

Text Generation
Transformers
code
Model card Files Community
3
minotaur-15B-GGML / README.md
TheBloke's picture
TheBloke
Update README.md
2dc38fa
preview code
|
raw
history blame
17.4 kB
metadata
inference: false
pipeline_tag: text-generation
widget:
  - text: 'def print_hello_world():'
    example_title: Hello world
    group: Python
  - text: Gradient descent is
    example_title: Machine Learning
    group: English
  - license: bigcode-openrail-m
datasets:
  - bigcode/the-stack-dedup
  - tiiuae/falcon-refinedweb
  - 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
metrics:
  - code_eval
  - mmlu
  - arc
  - hellaswag
  - truthfulqa
library_name: transformers
tags:
  - code
extra_gated_prompt: >-
  ## Model License Agreement

  Please read the BigCode [OpenRAIL-M
  license](https://huggingface.co/spaces/bigcode/bigcode-model-license-agreement)
  agreement before accepting it.
    
extra_gated_fields:
  I accept the above license agreement, and will use the Model complying with the set of use restrictions and sharing requirements: checkbox
TheBlokeAI

OpenAccess AI Collective's Minotaur 15B GGML

These files are GGML format model files for OpenAccess AI Collective's Minotaur 15B.

GGML files are for CPU + GPU inference using llama.cpp and libraries and UIs which support this format, such as:

Repositories available

A note regarding context length

it is currently untested as to whether the 8K context is compatible with available clients such as text-generation-webui, KoboldCpp, etc.

If you have feedback on this, please let me know.

Prompt template 

USER: <prompt>
ASSISTANT:

Compatibility

Original llama.cpp quant methods: q4_0, q4_1, q5_0, q5_1, q8_0

I have quantized these 'original' quantisation methods using an older version of llama.cpp so that they remain compatible with llama.cpp as of May 19th, commit 2d5db48.

These are guaranteed to be compatbile with any UIs, tools and libraries released since late May.

New k-quant methods: q2_K, q3_K_S, q3_K_M, q3_K_L, q4_K_S, q4_K_M, q5_K_S, q6_K

These new quantisation methods are compatible with llama.cpp as of June 6th, commit 2d43387.

They are now also compatible with recent releases of text-generation-webui, KoboldCpp, llama-cpp-python and ctransformers. Other tools and libraries may or may not be compatible - check their documentation if in doubt.

Explanation of the new k-quant methods

The new methods available are:

  • GGML_TYPE_Q2_K - "type-1" 2-bit quantization in super-blocks containing 16 blocks, each block having 16 weight. Block scales and mins are quantized with 4 bits. This ends up effectively using 2.5625 bits per weight (bpw)
  • GGML_TYPE_Q3_K - "type-0" 3-bit quantization in super-blocks containing 16 blocks, each block having 16 weights. Scales are quantized with 6 bits. This end up using 3.4375 bpw.
  • GGML_TYPE_Q4_K - "type-1" 4-bit quantization in super-blocks containing 8 blocks, each block having 32 weights. Scales and mins are quantized with 6 bits. This ends up using 4.5 bpw.
  • GGML_TYPE_Q5_K - "type-1" 5-bit quantization. Same super-block structure as GGML_TYPE_Q4_K resulting in 5.5 bpw
  • GGML_TYPE_Q6_K - "type-0" 6-bit quantization. Super-blocks with 16 blocks, each block having 16 weights. Scales are quantized with 8 bits. This ends up using 6.5625 bpw
  • GGML_TYPE_Q8_K - "type-0" 8-bit quantization. Only used for quantizing intermediate results. The difference to the existing Q8_0 is that the block size is 256. All 2-6 bit dot products are implemented for this quantization type.

Refer to the Provided Files table below to see what files use which methods, and how.

Provided files

Name Quant method Bits Size Max RAM required Use case
minotaur-15b.ggmlv3.q4_0.bin q4_0 4 10.75 GB 13.25 GB Original llama.cpp quant method, 4-bit.
minotaur-15b.ggmlv3.q4_1.bin q4_1 4 11.92 GB 14.42 GB Original llama.cpp quant method, 4-bit. Higher accuracy than q4_0 but not as high as q5_0. However has quicker inference than q5 models.
minotaur-15b.ggmlv3.q5_0.bin q5_0 5 13.09 GB 15.59 GB Original llama.cpp quant method, 5-bit. Higher accuracy, higher resource usage and slower inference.
minotaur-15b.ggmlv3.q5_1.bin q5_1 5 14.26 GB 16.76 GB Original llama.cpp quant method, 5-bit. Even higher accuracy, resource usage and slower inference.
minotaur-15b.ggmlv3.q8_0.bin q8_0 8 20.11 GB 22.61 GB Original llama.cpp quant method, 8-bit. Almost indistinguishable from float16. High resource use and slow. Not recommended for most users.

Note: the above RAM figures assume no GPU offloading. If layers are offloaded to the GPU, this will reduce RAM usage and use VRAM instead.

How to run in llama.cpp

I use the following command line; adjust for your tastes and needs:

./main -t 10 -ngl 32 -m minotaur-15b.ggmlv3.q5_0.bin --color -c 2048 --temp 0.7 --repeat_penalty 1.1 -n -1 -p "### Instruction: Write a story about llamas\n### Response:"

Change -t 10 to the number of physical CPU cores you have. For example if your system has 8 cores/16 threads, use -t 8.

Change -ngl 32 to the number of layers to offload to GPU. Remove it if you don't have GPU acceleration.

If you want to have a chat-style conversation, replace the -p <PROMPT> argument with -i -ins

How to run in text-generation-webui

Further instructions here: text-generation-webui/docs/llama.cpp-models.md.

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: Luke from CarbonQuill, Aemon Algiz, Dmitriy Samsonov.

Patreon special mentions: vamX, K, Jonathan Leane, Lone Striker, Sean Connelly, Chris McCloskey, WelcomeToTheClub, Nikolai Manek, John Detwiler, Kalila, David Flickinger, Fen Risland, subjectnull, Johann-Peter Hartmann, Talal Aujan, John Villwock, senxiiz, Khalefa Al-Ahmad, Kevin Schuppel, Alps Aficionado, Derek Yates, Mano Prime, Nathan LeClaire, biorpg, trip7s trip, Asp the Wyvern, chris gileta, Iucharbius , Artur Olbinski, Ai Maven, Joseph William Delisle, Luke Pendergrass, Illia Dulskyi, Eugene Pentland, Ajan Kanaga, Willem Michiel, Space Cruiser, Pyrater, Preetika Verma, Junyu Yang, Oscar Rangel, Spiking Neurons AB, Pierre Kircher, webtim, Cory Kujawski, terasurfer , Trenton Dambrowitz, Gabriel Puliatti, Imad Khwaja, Luke.

Thank you to all my generous patrons and donaters!

Original model card: OpenAccess AI Collective's Minotaur 15B

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

Minotaur 15B 8K

Minotaur 15B is an instruct fine-tuned model on top of Starcoder Plus. Minotaur 15B is fine-tuned on only completely open datasets making this model reproducible by anyone. Minotaur 15B has a context length of 8K tokens, allowing for strong recall at long contexts.

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:.

minotaur

Training Datasets

Minotaur 15B 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 4XA100 80GB

  • 1 epochs taking approximately 30 hours
  • Trained using QLoRA techniques

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 StarCoder, please refer to its model card's Limitations Section for relevant information. (included below)

Benchmarks

TBD

Examples

TBD

StarCoderPlus

Play with the instruction-tuned StarCoderPlus at StarChat-Beta.

Table of Contents

  1. Model Summary
  2. Use
  3. Limitations
  4. Training
  5. License
  6. Citation

Model Summary

StarCoderPlus is a fine-tuned version of StarCoderBase on 600B tokens from the English web dataset RedefinedWeb combined with StarCoderData from The Stack (v1.2) and a Wikipedia dataset. It's a 15.5B parameter Language Model trained on English and 80+ programming languages. The model uses Multi Query Attention, a context window of 8192 tokens, and was trained using the Fill-in-the-Middle objective on 1.6 trillion tokens.

Use

Intended use

The model was trained on English and GitHub code. As such it is not an instruction model and commands like "Write a function that computes the square root." do not work well. However, the instruction-tuned version in StarChat makes a capable assistant.

Feel free to share your generations in the Community tab!

Generation 

# pip install -q transformers
from transformers import AutoModelForCausalLM, AutoTokenizer

checkpoint = "bigcode/starcoderplus"
device = "cuda" # for GPU usage or "cpu" for CPU usage

tokenizer = AutoTokenizer.from_pretrained(checkpoint)
model = AutoModelForCausalLM.from_pretrained(checkpoint).to(device)

inputs = tokenizer.encode("def print_hello_world():", return_tensors="pt").to(device)
outputs = model.generate(inputs)
print(tokenizer.decode(outputs[0]))

Fill-in-the-middle

Fill-in-the-middle uses special tokens to identify the prefix/middle/suffix part of the input and output:

input_text = "<fim_prefix>def print_hello_world():\n    <fim_suffix>\n    print('Hello world!')<fim_middle>"
inputs = tokenizer.encode(input_text, return_tensors="pt").to(device)
outputs = model.generate(inputs)
print(tokenizer.decode(outputs[0]))

Attribution & Other Requirements

The training code dataset of the model was filtered for permissive licenses only. Nevertheless, the model can generate source code verbatim from the dataset. The code's license might require attribution and/or other specific requirements that must be respected. We provide a search index that let's you search through the pretraining data to identify where generated code came from and apply the proper attribution to your code.

Limitations

The model has been trained on a mixture of English text from the web and GitHub code. Therefore it might encounter limitations when working with non-English text, and can carry the stereotypes and biases commonly encountered online. Additionally, the generated code should be used with caution as it may contain errors, inefficiencies, or potential vulnerabilities. For a more comprehensive understanding of the base model's code limitations, please refer to See StarCoder paper.

Training

StarCoderPlus is a fine-tuned version on 600B English and code tokens of StarCoderBase, which was pre-trained on 1T code tokens. Below are the fine-tuning details:

Model

  • Architecture: GPT-2 model with multi-query attention and Fill-in-the-Middle objective
  • Finetuning steps: 150k
  • Finetuning tokens: 600B
  • Precision: bfloat16

Hardware

  • GPUs: 512 Tesla A100
  • Training time: 14 days

Software

License

The model is licensed under the BigCode OpenRAIL-M v1 license agreement. You can find the full agreement here.