TheBloke/WizardLM-13B-1.0-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)

---

WizardLM 13B 1.0 - GGUF

• Model creator: WizardLM
• Original model: WizardLM 13B 1.0

Description

This repo contains GGUF format model files for WizardLM's WizardLM 13B 1.0.

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 incomplate 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.
• LM Studio, an easy-to-use and powerful local GUI for Windows and macOS (Silicon), with GPU acceleration.
• 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.
• ctransformers, a Python library with GPU accel, LangChain support, and OpenAI-compatible AI server.
• 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.

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
• WizardLM's original unquantised fp16 model in pytorch format, for GPU inference and for further conversions

Prompt template: Vicuna

A chat between a curious user and an artificial intelligence assistant. The assistant gives helpful, detailed, and polite answers to the user's questions. USER: {prompt} 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
wizardLM-13B-1.0.Q2_K.gguf	Q2_K	2	5.43 GB	7.93 GB	smallest, significant quality loss - not recommended for most purposes
wizardLM-13B-1.0.Q3_K_S.gguf	Q3_K_S	3	5.66 GB	8.16 GB	very small, high quality loss
wizardLM-13B-1.0.Q3_K_M.gguf	Q3_K_M	3	6.34 GB	8.84 GB	very small, high quality loss
wizardLM-13B-1.0.Q3_K_L.gguf	Q3_K_L	3	6.93 GB	9.43 GB	small, substantial quality loss
wizardLM-13B-1.0.Q4_0.gguf	Q4_0	4	7.37 GB	9.87 GB	legacy; small, very high quality loss - prefer using Q3_K_M
wizardLM-13B-1.0.Q4_K_S.gguf	Q4_K_S	4	7.41 GB	9.91 GB	small, greater quality loss
wizardLM-13B-1.0.Q4_K_M.gguf	Q4_K_M	4	7.87 GB	10.37 GB	medium, balanced quality - recommended
wizardLM-13B-1.0.Q5_0.gguf	Q5_0	5	8.97 GB	11.47 GB	legacy; medium, balanced quality - prefer using Q4_K_M
wizardLM-13B-1.0.Q5_K_S.gguf	Q5_K_S	5	8.97 GB	11.47 GB	large, low quality loss - recommended
wizardLM-13B-1.0.Q5_K_M.gguf	Q5_K_M	5	9.23 GB	11.73 GB	large, very low quality loss - recommended
wizardLM-13B-1.0.Q6_K.gguf	Q6_K	6	10.68 GB	13.18 GB	very large, extremely low quality loss
wizardLM-13B-1.0.Q8_0.gguf	Q8_0	8	13.83 GB	16.33 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/WizardLM-13B-1.0-GGUF and below it, a specific filename to download, such as: wizardLM-13B-1.0.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/WizardLM-13B-1.0-GGUF wizardLM-13B-1.0.Q4_K_M.gguf --local-dir . --local-dir-use-symlinks False

More advanced huggingface-cli download usage

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

huggingface-cli download TheBloke/WizardLM-13B-1.0-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/WizardLM-13B-1.0-GGUF wizardLM-13B-1.0.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 32 -m wizardLM-13B-1.0.Q4_K_M.gguf --color -c 2048 --temp 0.7 --repeat_penalty 1.1 -n -1 -p "A chat between a curious user and an artificial intelligence assistant. The assistant gives helpful, detailed, and polite answers to the user's questions. USER: {prompt} ASSISTANT:"

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

Change -c 2048 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.

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

How to run from Python code

You can use GGUF models from Python using the llama-cpp-python or ctransformers libraries.

How to load this model in Python code, using ctransformers

First install the package

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

# Base ctransformers with no GPU acceleration
pip install ctransformers
# Or with CUDA GPU acceleration
pip install ctransformers[cuda]
# Or with AMD ROCm GPU acceleration (Linux only)
CT_HIPBLAS=1 pip install ctransformers --no-binary ctransformers
# Or with Metal GPU acceleration for macOS systems only
CT_METAL=1 pip install ctransformers --no-binary ctransformers

Simple ctransformers example code

from ctransformers import AutoModelForCausalLM

# 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 = AutoModelForCausalLM.from_pretrained("TheBloke/WizardLM-13B-1.0-GGUF", model_file="wizardLM-13B-1.0.Q4_K_M.gguf", model_type="llama", gpu_layers=50)

print(llm("AI is going to"))

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: Alicia Loh, Stephen Murray, K, Ajan Kanaga, RoA, Magnesian, Deo Leter, Olakabola, Eugene Pentland, zynix, Deep Realms, Raymond Fosdick, Elijah Stavena, Iucharbius, Erik Bjäreholt, Luis Javier Navarrete Lozano, Nicholas, theTransient, John Detwiler, alfie_i, knownsqashed, Mano Prime, Willem Michiel, Enrico Ros, LangChain4j, OG, Michael Dempsey, Pierre Kircher, Pedro Madruga, James Bentley, Thomas Belote, Luke @flexchar, Leonard Tan, Johann-Peter Hartmann, Illia Dulskyi, Fen Risland, Chadd, S_X, Jeff Scroggin, Ken Nordquist, Sean Connelly, Artur Olbinski, Swaroop Kallakuri, Jack West, Ai Maven, David Ziegler, Russ Johnson, transmissions 11, John Villwock, Alps Aficionado, Clay Pascal, Viktor Bowallius, Subspace Studios, Rainer Wilmers, Trenton Dambrowitz, vamX, Michael Levine, 준교 김, Brandon Frisco, Kalila, Trailburnt, Randy H, Talal Aujan, Nathan Dryer, Vadim, 阿明, ReadyPlayerEmma, Tiffany J. Kim, George Stoitzev, Spencer Kim, Jerry Meng, Gabriel Tamborski, Cory Kujawski, Jeffrey Morgan, Spiking Neurons AB, Edmond Seymore, Alexandros Triantafyllidis, Lone Striker, Cap'n Zoog, Nikolai Manek, danny, ya boyyy, Derek Yates, usrbinkat, Mandus, TL, Nathan LeClaire, subjectnull, Imad Khwaja, webtim, Raven Klaugh, Asp the Wyvern, Gabriel Puliatti, Caitlyn Gatomon, Joseph William Delisle, Jonathan Leane, Luke Pendergrass, SuperWojo, Sebastain Graf, Will Dee, Fred von Graf, Andrey, Dan Guido, Daniel P. Andersen, Nitin Borwankar, Elle, Vitor Caleffi, biorpg, jjj, NimbleBox.ai, Pieter, Matthew Berman, terasurfer, Michael Davis, Alex, Stanislav Ovsiannikov

Thank you to all my generous patrons and donaters!

And thank you again to a16z for their generous grant.

Original model card: WizardLM's WizardLM 13B 1.0

Chat & support: my new Discord server

Want to contribute? TheBloke's Patreon page

WizardLM 13B 1.0 fp16

These files are fp16 unquantised format model files for WizardLM 13B 1.0.

It is the result of merging the deltas provided in the above repo.

Need support? Want to discuss? I now have a Discord!

Join me at: https://discord.gg/UBgz4VXf

Other repositories available

• 4-bit GPTQ models for GPU inference
• 4-bit, 5-bit and 8-bit GGML models for CPU(+GPU) inference
• Merged, unquantised fp16 model in HF format

Prompt Template

A chat between a curious user and an artificial intelligence assistant. The assistant gives helpful, detailed, and polite answers to the user's questions.
USER: prompt goes here
ASSISTANT:

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.

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

Patreon special mentions: Aemon Algiz, Dmitriy Samsonov, Nathan LeClaire, Trenton Dambrowitz, Mano Prime, David Flickinger, vamX, Nikolai Manek, senxiiz, Khalefa Al-Ahmad, Illia Dulskyi, Jonathan Leane, Talal Aujan, V. Lukas, Joseph William Delisle, Pyrater, Oscar Rangel, Lone Striker, Luke Pendergrass, Eugene Pentland, Sebastain Graf, Johann-Peter Hartman.

Thank you to all my generous patrons and donaters!

Original model card

WizardLM: An Instruction-following LLM Using Evol-Instruct

Empowering Large Pre-Trained Language Models to Follow Complex Instructions

News

At present, our core contributors are preparing the 33B version and we expect to empower WizardLM with the ability to perform instruction evolution itself, aiming to evolve your specific data at a low cost.

• 🔥 We released 13B version of WizardLM trained with 250k evolved instructions (from ShareGPT). Checkout the Demo_13B, Demo_13B_bak and the GPT-4 evaluation. Please download our delta model at the following link.
• 🔥 We released 7B version of WizardLM trained with 70k evolved instructions (from Alpaca data). Checkout the paper and Demo_7B , Demo_7B_bak
• 📣 We are looking for highly motivated students to join us as interns to create more intelligent AI together. Please contact caxu@microsoft.com

Note for 13B model usage: To obtain results identical to our demo, please strictly follow the prompts and invocation methods provided in the "src/infer_wizardlm13b.py" to use our 13B model for inference. Unlike the 7B model, the 13B model adopts the prompt format from Vicuna and supports multi-turn conversation.

Note for demo usage: We only recommend using English to experience our model. Support for other languages will be introduced in the future. The demo currently only supports single-turn conversation.

GPT-4 automatic evaluation

We adopt the automatic evaluation framework based on GPT-4 proposed by FastChat to assess the performance of chatbot models. As shown in the following figure, WizardLM-13B achieved better results than Vicuna-13b.

WizardLM-13B performance on different skills.

The following figure compares WizardLM-13B and ChatGPT’s skill on Evol-Instruct testset. The result indicates that WizardLM-13B achieves 89.1% of ChatGPT’s performance on average, with almost 100% (or more than) capacity on 10 skills, and more than 90% capacity on 22 skills.

Call for Feedbacks

We welcome everyone to use your professional and difficult instructions to evaluate WizardLM, and show us examples of poor performance and your suggestions in the issue discussion area. We are focusing on improving the Evol-Instruct now and hope to relieve existing weaknesses and issues in the the next version of WizardLM. After that, we will open the code and pipeline of up-to-date Evol-Instruct algorithm and work with you together to improve it.

Unofficial Video Introductions

Thanks to the enthusiastic friends, their video introductions are more lively and interesting.

1. GET WizardLM NOW! 7B LLM KING That Can Beat ChatGPT! I'm IMPRESSED!
2. WizardLM: Enhancing Large Language Models to Follow Complex Instructions

Case Show

We just sample some cases to demonstrate the performance of WizardLM and ChatGPT on data of varying difficulty, and the details pls refer Case Show.

Overview of Evol-Instruct

Evol-Instruct is a novel method using LLMs instead of humans to automatically mass-produce open-domain instructions of various difficulty levels and skills range, to improve the performance of LLMs.

Contents

1. Online Demo

2. Training Data

3. WizardLM Weights

4. Fine-tuning

5. Distributed Fine-tuning

6. Inference

7. Evaluation

8. Citation

9. Disclaimer

Online Demo

We will provide our latest models for you to try for as long as possible. If you find a link is not working, please try another one. At the same time, please try as many real-world and challenging problems that you encounter in your work and life as possible. We will continue to evolve our models with your feedbacks.

Demo Link

Demo Backup 1

Training Data

alpaca_evol_instruct_70k.json contains 70K instruction-following data generated from Evol-Instruct. We used it for fine-tuning the WizardLM model. This JSON file is a list of dictionaries, each dictionary contains the following fields:

• instruction: str, describes the task the model should perform. Each of the 70K instructions is unique.
• output: str, the answer to the instruction as generated by gpt-3.5-turbo.

WizardLM Weights

We release [WizardLM] weights as delta weights to comply with the LLaMA model license. You can add our delta to the original LLaMA weights to obtain the WizardLM weights. Instructions:

1. Get the original LLaMA weights in the huggingface format by following the instructions here.
2. Please download our delta model at the following link
3. Use the following scripts to get WizardLM weights by applying our delta:

python src/weight_diff_wizard.py recover --path_raw <path_to_step_1_dir> --path_diff <path_to_step_2_dir> --path_tuned <path_to_store_recovered_weights>

Fine-tuning

We fine-tune WizardLM using code from Llama-X. We fine-tune LLaMA-7B and LLaMA-13B with the following hyperparameters:

Hyperparameter	LLaMA-7B	LLaMA-13B
Batch size	64	384
Learning rate	2e-5	2e-5
Epochs	3	3
Max length	2048	2048
Warmup step	2	50
LR scheduler	cosine	cosine

To reproduce our fine-tuning of WizardLM, please follow the following steps:

1. According to the instructions of Llama-X, install the environment, download the training code, and deploy.
2. Replace the train.py with the train_freeform.py in our repo(src/train_freeform.py)
3. Execute the following training command:

deepspeed train_freeform.py \
    --model_name_or_path /path/to/llama-7B/hf \
    --data_path /path/to/alpaca_evol_instruct_70k.json \
    --output_dir /path/to/wizardlm-7B/hf/ft \
    --num_train_epochs 3 \
    --model_max_length 2048 \
    --per_device_train_batch_size 8 \
    --per_device_eval_batch_size 1 \
    --gradient_accumulation_steps 1 \
    --evaluation_strategy "no" \
    --save_strategy "steps" \
    --save_steps 800 \
    --save_total_limit 3 \
    --learning_rate 2e-5 \
    --warmup_steps 2 \
    --logging_steps 2 \
    --lr_scheduler_type "cosine" \
    --report_to "tensorboard" \
    --gradient_checkpointing True \
    --deepspeed configs/deepspeed_config.json \
    --fp16 True

Distributed Fine-tuning

See Distributed Fine-tuning

Inference

We provide the decoding script for WizardLM, which reads a input file and generates corresponding responses for each sample, and finally consolidates them into an output file.

You can specify base_model, input_data_path and output_data_path in src\inference_wizardlm.py to set the decoding model, path of input file and path of output file. The decoding command:

python src\inference_wizardlm.py

Evaluation

To evaluate Wizard, we conduct human evaluation on the inputs from our human instruct evaluation set WizardLM_testset.jsonl . This evaluation set was collected by the authors and covers a diverse list of user-oriented instructions including difficult Coding Generation & Debugging, Math, Reasoning, Complex Formats, Academic Writing, Extensive Disciplines, and so on. We performed a blind pairwise comparison between Wizard and baselines. Specifically, we recruit 10 well-educated annotators to rank the models from 1 to 5 on relevance, knowledgeable, reasoning, calculation and accuracy.

WizardLM achieved significantly better results than Alpaca and Vicuna-7b.

In the high-difficulty section of our test set (difficulty level >= 8), WizardLM even outperforms ChatGPT, with a win rate 7.9% larger than Chatgpt (42.9% vs. 35.0%). This indicates that our method can significantly improve the ability of large language models to handle complex instructions.

Citation

Please cite the repo if you use the data or code in this repo.

@misc{xu2023wizardlm,
      title={WizardLM: Empowering Large Language Models to Follow Complex Instructions},
      author={Can Xu and Qingfeng Sun and Kai Zheng and Xiubo Geng and Pu Zhao and Jiazhan Feng and Chongyang Tao and Daxin Jiang},
      year={2023},
      eprint={2304.12244},
      archivePrefix={arXiv},
      primaryClass={cs.CL}
}

Disclaimer

The resources, including code, data, and model weights, associated with this project are restricted for academic research purposes only and cannot be used for commercial purposes. The content produced by any version of WizardLM is influenced by uncontrollable variables such as randomness, and therefore, the accuracy of the output cannot be guaranteed by this project. This project does not accept any legal liability for the content of the model output, nor does it assume responsibility for any losses incurred due to the use of associated resources and output results.