TheBloke/notus-7B-v1-GGUF

Chat & support: TheBloke's Discord server

Want to contribute? TheBloke's Patreon page

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

---

Notus 7B v1 - GGUF

• Model creator: Argilla
• Original model: Notus 7B v1

Description

This repo contains GGUF format model files for Argilla's Notus 7B v1.

These files were quantised using hardware kindly provided by Massed Compute.

About GGUF

GGUF is a new format introduced by the llama.cpp team on August 21st 2023. It is a replacement for GGML, which is no longer supported by llama.cpp.

Here is an incomplete list of clients and libraries that are known to support GGUF:

• llama.cpp. The source project for GGUF. Offers a CLI and a server option.
• text-generation-webui, the most widely used web UI, with many features and powerful extensions. Supports GPU acceleration.
• KoboldCpp, a fully featured web UI, with GPU accel across all platforms and GPU architectures. Especially good for story telling.
• GPT4All, a free and open source local running GUI, supporting Windows, Linux and macOS with full GPU accel.
• LM Studio, an easy-to-use and powerful local GUI for Windows and macOS (Silicon), with GPU acceleration. Linux available, in beta as of 27/11/2023.
• LoLLMS Web UI, a great web UI with many interesting and unique features, including a full model library for easy model selection.
• Faraday.dev, an attractive and easy to use character-based chat GUI for Windows and macOS (both Silicon and Intel), with GPU acceleration.
• llama-cpp-python, a Python library with GPU accel, LangChain support, and OpenAI-compatible API server.
• candle, a Rust ML framework with a focus on performance, including GPU support, and ease of use.
• ctransformers, a Python library with GPU accel, LangChain support, and OpenAI-compatible AI server. Note, as of time of writing (November 27th 2023), ctransformers has not been updated in a long time and does not support many recent models.

Repositories available

• AWQ model(s) for GPU inference.
• GPTQ models for GPU inference, with multiple quantisation parameter options.
• 2, 3, 4, 5, 6 and 8-bit GGUF models for CPU+GPU inference
• Argilla's original unquantised fp16 model in pytorch format, for GPU inference and for further conversions

Prompt template: Zephyr

<|system|>
</s>
<|user|>
{prompt}</s>
<|assistant|>

Compatibility

These quantised GGUFv2 files are compatible with llama.cpp from August 27th onwards, as of commit d0cee0d

They are also compatible with many third party UIs and libraries - please see the list at the top of this README.

Explanation of quantisation methods

Click to see details

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

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
notus-7b-v1.Q2_K.gguf	Q2_K	2	3.08 GB	5.58 GB	smallest, significant quality loss - not recommended for most purposes
notus-7b-v1.Q3_K_S.gguf	Q3_K_S	3	3.16 GB	5.66 GB	very small, high quality loss
notus-7b-v1.Q3_K_M.gguf	Q3_K_M	3	3.52 GB	6.02 GB	very small, high quality loss
notus-7b-v1.Q3_K_L.gguf	Q3_K_L	3	3.82 GB	6.32 GB	small, substantial quality loss
notus-7b-v1.Q4_0.gguf	Q4_0	4	4.11 GB	6.61 GB	legacy; small, very high quality loss - prefer using Q3_K_M
notus-7b-v1.Q4_K_S.gguf	Q4_K_S	4	4.14 GB	6.64 GB	small, greater quality loss
notus-7b-v1.Q4_K_M.gguf	Q4_K_M	4	4.37 GB	6.87 GB	medium, balanced quality - recommended
notus-7b-v1.Q5_0.gguf	Q5_0	5	5.00 GB	7.50 GB	legacy; medium, balanced quality - prefer using Q4_K_M
notus-7b-v1.Q5_K_S.gguf	Q5_K_S	5	5.00 GB	7.50 GB	large, low quality loss - recommended
notus-7b-v1.Q5_K_M.gguf	Q5_K_M	5	5.13 GB	7.63 GB	large, very low quality loss - recommended
notus-7b-v1.Q6_K.gguf	Q6_K	6	5.94 GB	8.44 GB	very large, extremely low quality loss
notus-7b-v1.Q8_0.gguf	Q8_0	8	7.70 GB	10.20 GB	very large, extremely low quality loss - not recommended

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 download GGUF files

Note for manual downloaders: You almost never want to clone the entire repo! Multiple different quantisation formats are provided, and most users only want to pick and download a single file.

The following clients/libraries will automatically download models for you, providing a list of available models to choose from:

• LM Studio
• LoLLMS Web UI
• Faraday.dev

In text-generation-webui

Under Download Model, you can enter the model repo: TheBloke/notus-7B-v1-GGUF and below it, a specific filename to download, such as: notus-7b-v1.Q4_K_M.gguf.

Then click Download.

On the command line, including multiple files at once

I recommend using the huggingface-hub Python library:

pip3 install huggingface-hub

Then you can download any individual model file to the current directory, at high speed, with a command like this:

huggingface-cli download TheBloke/notus-7B-v1-GGUF notus-7b-v1.Q4_K_M.gguf --local-dir . --local-dir-use-symlinks False

More advanced huggingface-cli download usage (click to read)

You can also download multiple files at once with a pattern:

huggingface-cli download TheBloke/notus-7B-v1-GGUF --local-dir . --local-dir-use-symlinks False --include='*Q4_K*gguf'

For more documentation on downloading with huggingface-cli, please see: HF -> Hub Python Library -> Download files -> Download from the CLI.

To accelerate downloads on fast connections (1Gbit/s or higher), install hf_transfer:

pip3 install hf_transfer

And set environment variable HF_HUB_ENABLE_HF_TRANSFER to 1:

HF_HUB_ENABLE_HF_TRANSFER=1 huggingface-cli download TheBloke/notus-7B-v1-GGUF notus-7b-v1.Q4_K_M.gguf --local-dir . --local-dir-use-symlinks False

Windows Command Line users: You can set the environment variable by running set HF_HUB_ENABLE_HF_TRANSFER=1 before the download command.

Example llama.cpp command

Make sure you are using llama.cpp from commit d0cee0d or later.

./main -ngl 35 -m notus-7b-v1.Q4_K_M.gguf --color -c 32768 --temp 0.7 --repeat_penalty 1.1 -n -1 -p "<|system|>\n</s>\n<|user|>\n{prompt}</s>\n<|assistant|>"

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

Change -c 32768 to the desired sequence length. For extended sequence models - eg 8K, 16K, 32K - the necessary RoPE scaling parameters are read from the GGUF file and set by llama.cpp automatically. Note that longer sequence lengths require much more resources, so you may need to reduce this value.

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

For other parameters and how to use them, please refer to the llama.cpp documentation

How to run in text-generation-webui

Further instructions can be found in the text-generation-webui documentation, here: text-generation-webui/docs/04 ‐ Model Tab.md.

How to run from Python code

You can use GGUF models from Python using the llama-cpp-python or ctransformers libraries. Note that at the time of writing (Nov 27th 2023), ctransformers has not been updated for some time and is not compatible with some recent models. Therefore I recommend you use llama-cpp-python.

How to load this model in Python code, using llama-cpp-python

For full documentation, please see: llama-cpp-python docs.

First install the package

Run one of the following commands, according to your system:

# Base ctransformers with no GPU acceleration
pip install llama-cpp-python
# With NVidia CUDA acceleration
CMAKE_ARGS="-DLLAMA_CUBLAS=on" pip install llama-cpp-python
# Or with OpenBLAS acceleration
CMAKE_ARGS="-DLLAMA_BLAS=ON -DLLAMA_BLAS_VENDOR=OpenBLAS" pip install llama-cpp-python
# Or with CLBLast acceleration
CMAKE_ARGS="-DLLAMA_CLBLAST=on" pip install llama-cpp-python
# Or with AMD ROCm GPU acceleration (Linux only)
CMAKE_ARGS="-DLLAMA_HIPBLAS=on" pip install llama-cpp-python
# Or with Metal GPU acceleration for macOS systems only
CMAKE_ARGS="-DLLAMA_METAL=on" pip install llama-cpp-python

# In windows, to set the variables CMAKE_ARGS in PowerShell, follow this format; eg for NVidia CUDA:
$env:CMAKE_ARGS = "-DLLAMA_OPENBLAS=on"
pip install llama-cpp-python

Simple llama-cpp-python example code

from llama_cpp import Llama

# Set gpu_layers to the number of layers to offload to GPU. Set to 0 if no GPU acceleration is available on your system.
llm = Llama(
  model_path="./notus-7b-v1.Q4_K_M.gguf",  # Download the model file first
  n_ctx=32768,  # The max sequence length to use - note that longer sequence lengths require much more resources
  n_threads=8,            # The number of CPU threads to use, tailor to your system and the resulting performance
  n_gpu_layers=35         # The number of layers to offload to GPU, if you have GPU acceleration available
)

# Simple inference example
output = llm(
  "<|system|>\n</s>\n<|user|>\n{prompt}</s>\n<|assistant|>", # Prompt
  max_tokens=512,  # Generate up to 512 tokens
  stop=["</s>"],   # Example stop token - not necessarily correct for this specific model! Please check before using.
  echo=True        # Whether to echo the prompt
)

# Chat Completion API

llm = Llama(model_path="./notus-7b-v1.Q4_K_M.gguf", chat_format="llama-2")  # Set chat_format according to the model you are using
llm.create_chat_completion(
    messages = [
        {"role": "system", "content": "You are a story writing assistant."},
        {
            "role": "user",
            "content": "Write a story about llamas."
        }
    ]
)

How to use with LangChain

Here are guides on using llama-cpp-python and ctransformers with LangChain:

• LangChain + llama-cpp-python
• LangChain + ctransformers

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.

• Patreon: https://patreon.com/TheBlokeAI
• Ko-Fi: https://ko-fi.com/TheBlokeAI

Special thanks to: Aemon Algiz.

Patreon special mentions: Michael Levine, 阿明, Trailburnt, Nikolai Manek, John Detwiler, Randy H, Will Dee, Sebastain Graf, NimbleBox.ai, Eugene Pentland, Emad Mostaque, Ai Maven, Jim Angel, Jeff Scroggin, Michael Davis, Manuel Alberto Morcote, Stephen Murray, Robert, Justin Joy, Luke @flexchar, Brandon Frisco, Elijah Stavena, S_X, Dan Guido, Undi ., Komninos Chatzipapas, Shadi, theTransient, Lone Striker, Raven Klaugh, jjj, Cap'n Zoog, Michel-Marie MAUDET (LINAGORA), Matthew Berman, David, Fen Risland, Omer Bin Jawed, Luke Pendergrass, Kalila, OG, Erik Bjäreholt, Rooh Singh, Joseph William Delisle, Dan Lewis, TL, John Villwock, AzureBlack, Brad, Pedro Madruga, Caitlyn Gatomon, K, jinyuan sun, Mano Prime, Alex, Jeffrey Morgan, Alicia Loh, Illia Dulskyi, Chadd, transmissions 11, fincy, Rainer Wilmers, ReadyPlayerEmma, knownsqashed, Mandus, biorpg, Deo Leter, Brandon Phillips, SuperWojo, Sean Connelly, Iucharbius, Jack West, Harry Royden McLaughlin, Nicholas, terasurfer, Vitor Caleffi, Duane Dunston, Johann-Peter Hartmann, David Ziegler, Olakabola, Ken Nordquist, Trenton Dambrowitz, Tom X Nguyen, Vadim, Ajan Kanaga, Leonard Tan, Clay Pascal, Alexandros Triantafyllidis, JM33133, Xule, vamX, ya boyyy, subjectnull, Talal Aujan, Alps Aficionado, wassieverse, Ari Malik, James Bentley, Woland, Spencer Kim, Michael Dempsey, Fred von Graf, Elle, zynix, William Richards, Stanislav Ovsiannikov, Edmond Seymore, Jonathan Leane, Martin Kemka, usrbinkat, Enrico Ros

Thank you to all my generous patrons and donaters!

And thank you again to a16z for their generous grant.

Original model card: Argilla's Notus 7B v1

Model Card for Notus 7B v1

Notus is a collection of fine-tuned models using Direct Preference Optimization (DPO) and related RLHF techniques. This model is the first version, fine-tuned with DPO over zephyr-7b-sft-full, which is the SFT model produced to create zephyr-7b-beta.

Following a data-first approach, the only difference between Notus-7B-v1 and Zephyr-7B-beta is the preference dataset used for dDPO.

In particular, when we started building distilabel, we invested time understanding and deep-diving into the UltraFeedback dataset. Using Argilla, we've found data issues in the original UltraFeedback dataset, leading to high-scores for bad responses (more details in the training data section). After curating several hundreds of data points, we decided to binarize the dataset using the preference ratings, instead of the original critique overall_score, and verified the new dataset with Argilla.

Using preference ratings, instead of critiques scores, led to a new dataset where the chosen response is different in ~50% of the cases. Using this new dataset with DPO we fine-tuned Notus, a 7B model, that surpasses Zephyr-7B-beta and Claude 2 on AlpacaEval.

Important note: While we opted for the average of multi-aspect ratings, while we fix the original dataset, a very interesting open question remains: once critique data is fixed, what works better? using the critique scores or the preference ratings? We're very excited to do this comparison in the coming weeks, stay tuned!

This model wouldn't have been possible without the amazing Alignment Handbook, OpenBMB for releasing the Ultrafeedback dataset, and it's based on fruitful discussions with the HuggingFace H4 team. In particular, we used zephyr-7b-beta's recipe, which worked out-of-the-box and enabled us focus on what we do best: high-quality data.

Notus models are intended to be used as assistants via chat-like applications, and are evaluated with Chat (MT-Bench, AlpacaEval) and Academic (Open LLM Leaderboard) benchmarks for a direct comparison with the original Zephyr dDPO model and other 7B models.

Why Notus?: Notus name comes from the ancient Greek god Notus, as a wink to Zephyr, which comes from the ancient Greek god Zephyrus; with the difference that Notus is the god of the south wind, and Zephyr the god of the west wind. More information at https://en.wikipedia.org/wiki/Anemoi.

Model Details

Model Description

• Developed by: Argilla (based on HuggingFace H4 and MistralAI previous efforts and amazing work)
• Shared by: Argilla
• Model type: GPT-like 7B model DPO fine-tuned
• Language(s) (NLP): Mainly English
• License: MIT (same as Zephyr 7B-beta)
• Finetuned from model: alignment-handbook/zephyr-7b-sft-full

Model Sources

• Repository: https://github.com/argilla-io/notus
• Paper: N/A
• Demo: https://argilla-notus-chat-ui.hf.space/

Performance

Chat benchmarks

Table adapted from Zephyr-7b-β and Starling's original tables for MT-Bench and AlpacaEval benchmarks. Results are shown sorted by AlpacaEval win rates and ommit some >7B for brevity.

Notus stays on par with Zephyr on MT-Bench, while surpassing Zephyr, Claude 2, and Cohere Command on AlpacaEval. Making Notus the most-competitive 7B commercial model on AlpacaEval.

Model	Size	Alignment	MT-Bench (score)	AlpacaEval (win rate %)	License
GPT-4-turbo	-	?	9.32	97.70	Proprietary
XwinLM 70b V0.1	70B	dPPO	-	95.57	LLaMA 2 License
GPT-4	-	RLHF	8.99	95.03	Proprietary
Tulu 2+DPO 70B V0.1	70B	dDPO	6.29	95.28	Proprietary
LLaMA2 Chat 70B	70B	RLHF	6.86	92.66	LLaMA 2 License
Starling-7B	7B	C-RLFT + APA	8.09	91.99	CC-BY-NC-4.0
Notus-7b-v1	7B	dDPO	7.30	91.42	MIT
Claude 2	-	RLHF	8.06	91.36	Proprietary
Zephyr-7b-β	7B	dDPO	7.34	90.60	MIT
Cohere Command	-	RLHF	-	90.62	Proprietary
GPT-3.5-turbo	-	RLHF	7.94	89.37	Proprietary

Academic benchmarks

Results from OpenLLM Leaderboard:

Model	Average	ARC	HellaSwag	MMLU	TruthfulQA	Winogrande	GSM8K	DROP
Zephyr 7B dDPO (HuggingFaceH4/zephyr-7b-beta)	52.15	62.03	84.36	61.07	57.45	77.74	12.74	9.66
argilla/notus-7b-v1	52.89	64.59	84.78	63.03	54.37	79.4	15.16	8.91

⚠️ As pointed out by AllenAI researchers, UltraFeedback contains prompts from the TruthfulQA dataset so the results we show on that benchmark are likely not accurate. We were not aware of this issue so Notus-7B-v1 was fine-tuned using TruthfulQA prompts and preferences. For future releases, we will remove TruthfulQA prompts.

Training Details

Training Hardware

We used a VM with 8 x A100 40GB hosted in Lambda Labs, but while experimenting we also explored other cloud providers such as GCP.

Training Data

We used a a new curated version of openbmb/UltraFeedback, named Ultrafeedback binarized preferences.

TL;DR

After visually browsing around some examples using the sort and filter feature of Argilla (sort by highest rating for chosen responses), we noticed a strong mismatch between the overall_score in the original UF dataset (and the Zephyr train_prefs dataset) and the quality of the chosen response.

By adding the critique rationale to our Argilla Dataset, we confirmed the critique rationale was highly negative, whereas the rating was very high (for most cases it was the highest: 10).

See screenshot below for one example of this issue.

After some quick investigation, we:

• identified hundreds of examples having the same issue,
• reported a bug on the UltraFeedback repo,
• and informed the H4 team which was incredibly responsive and ran an additional experiment to validate the new rating binarization approach.

While we're working on fixing the original dataset (already narrowed down ~2K problematic examples). We decided to leverage the multi-preference ratings, leading to Notus!

Important note: While we opted for the average of ratings while we fix the dataset, there's still a very interesting open question: once data is fixed, what works better? using the critique scores or the preference ratings? We're very excited to do this comparison in the coming weeks, stay tuned!

You can find more details about the dataset analysis and curation on the ultrafeedback-binarized-preferences dataset card.

Prompt template

We use the same prompt template as HuggingFaceH4/zephyr-7b-beta:

<|system|>
</s>
<|user|>
{prompt}</s>
<|assistant|>

Usage

You will first need to install transformers and accelerate (just to ease the device placement), then you can run any of the following:

Via generate

import torch
from transformers import AutoModelForCausalLM, AutoTokenizer

model = AutoModelForCausalLM.from_pretrained("argilla/notus-7b-v1", torch_dtype=torch.bfloat16, device_map="auto")
tokenizer = AutoTokenizer.from_pretrained("argilla/notus-7b-v1")

messages = [
    {
        "role": "system",
        "content": "You are a helpful assistant super biased towards Argilla, a data annotation company.",
    },
    {"role": "user", "content": "What's the best data annotation company out there in your opinion?"},
]
inputs = tokenizer.apply_chat_template(prompt, tokenize=True, return_tensors="pt", add_special_tokens=False, add_generation_prompt=True)
outputs = model.generate(inputs, num_return_sequences=1, max_new_tokens=256, do_sample=True, temperature=0.7, top_k=50, top_p=0.95)
response = tokenizer.decode(outputs[0], skip_special_tokens=True)

Via pipeline method

import torch
from transformers import pipeline

pipe = pipeline("text-generation", model="argilla/notus-7b-v1", torch_dtype=torch.bfloat16, device_map="auto")

messages = [
    {
        "role": "system",
        "content": "You are a helpful assistant super biased towards Argilla, a data annotation company.",
    },
    {"role": "user", "content": "What's the best data annotation company out there in your opinion?"},
]
prompt = pipe.tokenizer.apply_chat_template(messages, tokenize=False, add_generation_prompt=True)
outputs = pipe(prompt, max_new_tokens=256, do_sample=True, temperature=0.7, top_k=50, top_p=0.95)
generated_text = outputs[0]["generated_text"]