Smaug-72B-v0.1-GGUF

• Original model: Smaug-72B-v0.1

Description

This repo contains GGUF format model files for Smaug-72B-v0.1.

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. This is the source project for GGUF, providing both a Command Line Interface (CLI) and a server option.
• text-generation-webui, Known as the most widely used web UI, this project boasts numerous features and powerful extensions, and supports GPU acceleration.
• Ollama Ollama is a lightweight and extensible framework designed for building and running language models locally. It features a simple API for creating, managing, and executing models, along with a library of pre-built models for use in various applications​
• KoboldCpp, A comprehensive web UI offering GPU acceleration across all platforms and architectures, particularly renowned for storytelling.
• GPT4All, This is a free and open source GUI that runs locally, supporting Windows, Linux, and macOS with full GPU acceleration.
• LM Studio An intuitive and powerful local GUI for Windows and macOS (Silicon), featuring GPU acceleration.
• LoLLMS Web UI. A notable web UI with a variety of unique features, including a comprehensive model library for easy model selection.
• Faraday.dev, An attractive, user-friendly character-based chat GUI for Windows and macOS (both Silicon and Intel), also offering GPU acceleration.
• llama-cpp-python, A Python library equipped with GPU acceleration, LangChain support, and an OpenAI-compatible API server.
• candle, A Rust-based ML framework focusing on performance, including GPU support, and designed for ease of use.
• ctransformers, A Python library featuring GPU acceleration, LangChain support, and an OpenAI-compatible AI server.
• localGPT An open-source initiative enabling private conversations with documents.

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.

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 folder.

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: LiteLLMs/Smaug-72B-v0.1-GGUF and below it, a specific filename to download, such as: Q4_0/Q4_0-00001-of-00009.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 LiteLLMs/Smaug-72B-v0.1-GGUF Q4_0/Q4_0-00001-of-00009.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 LiteLLMs/Smaug-72B-v0.1-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 huggingface_hub[hf_transfer]

And set environment variable HF_HUB_ENABLE_HF_TRANSFER to 1:

HF_HUB_ENABLE_HF_TRANSFER=1 huggingface-cli download LiteLLMs/Smaug-72B-v0.1-GGUF Q4_0/Q4_0-00001-of-00009.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 Q4_0/Q4_0-00001-of-00009.gguf --color -c 8192 --temp 0.7 --repeat_penalty 1.1 -n -1 -p "<PROMPT>"

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

Change -c 8192 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="./Q4_0/Q4_0-00001-of-00009.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(
  "<PROMPT>", # 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="./Q4_0/Q4_0-00001-of-00009.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

Original model card: Smaug-72B-v0.1

Smaug arrives!

We recently released Smaug-72B-v0.1 which has taken first place on the Open LLM Leaderboard by HuggingFace. It is the first open-source model to surpass an average score of 80%.

Smaug-72B is finetuned directly from moreh/MoMo-72B-lora-1.8.7-DPO and is ultimately based on Qwen-72B.

We created Smaug-72B-v0.1 using a new fine-tuning technique, DPO-Positive (DPOP), and new pairwise preference versions of ARC, HellaSwag, and MetaMath (as well as other existing datasets). We introduce the technique and the full training details in our new paper: https://arxiv.org/abs/2402.13228.

We show that on datasets in which the edit distance between pairs of completions is low (such as in math-based datasets), standard DPO loss can lead to a reduction of the model's likelihood of the preferred examples, as long as the relative probability between the preferred and dispreferred classes increases. Using these insights, we design DPOP, a new loss function and training procedure which avoids this failure mode. Surprisingly, we also find that DPOP outperforms DPO across a wide variety of datasets and downstream tasks, including datasets with high edit distances between completions.

We believe this new approach is generally useful in training across a wide range of model types and downstream use cases, and it powers all of our Smaug models. With the release of our paper and datasets, we are excited for the open source community to continue to build on and improve Smaug and spawn more dragons to dominate the LLM space!

Evaluation Results

| Average | ARC | HellaSwag | MMLU | TruthfulQA | Winogrande | GSM8K | | - | | - | -- | | 80.48 | 76.02 | 89.27 | 77.15 | 76.67 | 85.08 | 78.70 |

MT-Bench

We ran MT-Bench with the llama-2 conversation template and the system prompt set to the Qwen system prompt. We got the following results in single model mode:

| First Turn | Second Turn | Average | | -- | - | | 8.18 | 7.34 | 7.76 |

The bottom of the card includes some sample responses from the model. We have selected responses that have high and low scores from the GPT-4 judge.

Contamination Results

We generate our contamination numbers using https://github.com/swj0419/detect-pretrain-code-contamination/tree/master, with Llama7B as our reference model. Smaug-72B has the following results:

ARC	TruthfulQA	GSM8K
0.20	0.39	1.00

Note that GSM8K often scores very highly on this contamination suite - we verified this by also running Llama-2-70B:

| ARC | TruthfulQA | GSM8K | | - | ----- | | 0.22 | 0.51 | 0.89 |

Sample MT Bench results

Example 1

Question

Imagine you are writing a blog post comparing two popular smartphone models. Develop an outline for the blog post, including key points and subheadings to effectively compare and contrast the features, performance, and user experience of the two models. Please answer in fewer than 200 words.

Response

Outline:

1. Introduction to the two smartphone models being compared (mention brand names and models)
2. Design and Build Quality
   • Comparison of dimensions, weight, materials used, and overall aesthetic appeal
   • Water and dust resistance, if applicable
3. Display and Screen Quality
   • Comparison of screen technology (OLED, IPS LCD, etc.)
   • Display resolution, refresh rate, and brightness levels
4. Performance and Hardware
   • Processor, RAM, and storage configurations
   • Comparison of benchmark scores (e.g., AnTuTu, Geekbench)
5. Camera System and Image Quality
   • Comparison of primary, ultra-wide, telephoto, and macro lenses (if available)
   • Comparison of low-light performance and image processing capabilities
6. Battery Life and Charging
   • Battery capacity and estimated usage time
   • Charging technologies (wired, wireless, fast charging, reverse charging)
7. Software and User Experience
   • Comparison of operating systems (iOS vs. Android) and their features
   • User interface, customization options, and app ecosystem
8. Additional Features and Extras
   • Comparison of biometric authentication (fingerprint, face unlock, etc.)
   • Additional features like NFC, 5G connectivity, and audio quality
9. Pricing and Value for Money
   • Comparison of retail prices and current offers
   • Assessment of overall value considering the features and performance
10. Conclusion and recommendation for potential buyers based on their preferences

Example 2

Question

In a survey conducted at a local high school, preferences for a new school color were measured: 58% of students liked the color blue, 45% preferred green, and 22% liked both colors. If we randomly pick a student from the school, what's the probability that they would like neither blue nor green?

Answer

To find the probability that a randomly picked student would like neither blue nor green, we need to find the percentage of students who like only one color or neither color.

From the given information, we know:

• 58% like blue
• 45% prefer green
• 22% like both colors

To find the percentage of students who like only one color, we can subtract the percentage of students who like both colors from the sum of students who like blue and green:

• 58% (blue) + 45% (green) - 22% (both) = 83%

Now, to find the probability of a student liking neither blue nor green, we subtract the percentage of students who like at least one color from 100%:

• 100% - 83% = 17%

So, the probability that a randomly picked student would like neither blue nor green is 17%.

Example 3

Question

Implement a program to find the common elements in two arrays without using any extra data structures.

Answer

Finding common elements in two arrays without using extra data structures can be achieved by using a simple algorithm. Here's a Python implementation of this problem:

def find_common_elements(arr1, arr2):
    common_elements = []
    for num1 in arr1:
        if num1 in arr2 and num1 not in common_elements:
            common_elements.append(num1)
    return common_elements

# Example usage:
array1 = [1, 2, 3, 4, 5]
array2 = [4, 5, 6, 7, 8]
print(find_common_elements(array1, array2))  # Output: [4, 5]

This program iterates through the elements of the first array (arr1) and checks if each element is present in the second array (arr2). If it is, and the element hasn't been added to the common_elements list yet, it is appended. The function then returns the list of common elements.

Example 4

Question

Identify the named entities (people, organizations, locations) mentioned in the given news article. Please generate a JSON dictionary that lists the named entities in three separate groups based on their entity types. The key is the type of entity and the value is a list of strings.

Yesterday, Adamson Emerson, the CEO of Faraday, and Dieter Zetsche, the CEO of Daimler AG, announced plans to build a new Gigafactory in Berlin. The facility will be a joint venture between Faraday and Daimler, producing electric vehicles and battery packs for both companies, creating thousands of job opportunities in the region. Emerson and Zetsche stated that the strategic location of Berlin, coupled with its skilled workforce and strong infrastructure, makes it an ideal choice for expansion. The new Gigafactory aims to meet the growing demand for electric vehicles in Europe and contribute to a sustainable future. Volkswagen CEO Herbert Diess welcomed the news, saying greater collaboration will, benefit the auto industry's transition to e-mobility.

Answer

{
  "people": ["Adamson Emerson", "Dieter Zetsche", "Herbert Diess"],
  "organizations": ["Faraday", "Daimler AG", "Volkswagen"],
  "locations": ["Berlin", "Europe"]
}

Citation

Please cite the paper if you use data, model, or method in this repo.

@article{pal2024smaug,
  title={Smaug: Fixing Failure Modes of Preference Optimisation with DPO-Positive},
  author={Pal, Arka and Karkhanis, Deep and Dooley, Samuel and Roberts, Manley and Naidu, Siddartha and White, Colin},
  journal={arXiv preprint arXiv:2402.13228},
  year={2024}
}