Edit model card

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

CausalLM 7B - GGUF


This repo contains GGUF format model files for CausalLM's CausalLM 7B.

NOTE: The GGUFs originally uploaded here did not work due to a vocab issue. This was fixed on 23rd October, 15:00 UTC. The files uploaded now are confirmed to work.

Please re-download the GGUFs if you had downloaded the originally uploaded GGUF file(s).

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

Prompt template: ChatML



The creator of the source model has listed its license as wtfpl, and this quantization has therefore used that same license.

As this model is based on Llama 2, it is also subject to the Meta Llama 2 license terms, and the license files for that are additionally included. It should therefore be considered as being claimed to be licensed under both licenses. I contacted Hugging Face for clarification on dual licensing but they do not yet have an official position. Should this change, or should Meta provide any feedback on this situation, I will update this section accordingly.

In the meantime, any questions regarding licensing, and in particular how these two licenses might interact, should be directed to the original model repository: CausalLM's CausalLM 7B.


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
causallm_7b.Q2_K.gguf Q2_K 2 3.40 GB 5.90 GB smallest, significant quality loss - not recommended for most purposes
causallm_7b.Q3_K_S.gguf Q3_K_S 3 3.57 GB 6.07 GB very small, high quality loss
causallm_7b.Q3_K_M.gguf Q3_K_M 3 3.92 GB 6.42 GB very small, high quality loss
causallm_7b.Q3_K_L.gguf Q3_K_L 3 4.22 GB 6.72 GB small, substantial quality loss
causallm_7b.Q4_0.gguf Q4_0 4 4.51 GB 7.01 GB legacy; small, very high quality loss - prefer using Q3_K_M
causallm_7b.Q4_K_S.gguf Q4_K_S 4 4.54 GB 7.04 GB small, greater quality loss
causallm_7b.Q4_K_M.gguf Q4_K_M 4 4.77 GB 7.27 GB medium, balanced quality - recommended
causallm_7b.Q5_0.gguf Q5_0 5 5.40 GB 7.90 GB legacy; medium, balanced quality - prefer using Q4_K_M
causallm_7b.Q5_K_S.gguf Q5_K_S 5 5.40 GB 7.90 GB large, low quality loss - recommended
causallm_7b.Q5_K_M.gguf Q5_K_M 5 5.53 GB 8.03 GB large, very low quality loss - recommended
causallm_7b.Q6_K.gguf Q6_K 6 6.34 GB 8.84 GB very large, extremely low quality loss
causallm_7b.Q8_0.gguf Q8_0 8 8.21 GB 10.71 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/CausalLM-7B-GGUF and below it, a specific filename to download, such as: causallm_7b.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/CausalLM-7B-GGUF causallm_7b.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/CausalLM-7B-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/CausalLM-7B-GGUF causallm_7b.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 causallm_7b.Q4_K_M.gguf --color -c 4096 --temp 0.7 --repeat_penalty 1.1 -n -1 -p "<|im_start|>system\n{system_message}<|im_end|>\n<|im_start|>user\n{prompt}<|im_end|>\n<|im_start|>assistant"

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

Change -c 4096 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/CausalLM-7B-GGUF", model_file="causallm_7b.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:


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.

Special thanks to: Aemon Algiz.

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

Thank you to all my generous patrons and donaters!

And thank you again to a16z for their generous grant.

Original model card: CausalLM's CausalLM 7B

Image drawn by GPT-4 DALL·E 3 TL;DR: Perhaps this 7B model, better than all existing models <= 33B, in most quantitative evaluations...

Please Stop Using WRONG unofficial quant models unless you know what you're doing

GPTQ quants require a good dataset for calibration, and the default C4 dataset is not capable.

llama.cpp GGUF models GPT2Tokenizer fixed by Kerfuffle on https://github.com/ggerganov/llama.cpp/pull/3743, new models to be reuploaded.

Read Me:

Also see 14B Version

This model was trained based on the model weights of Qwen (and LLaMA2 was used, yes, for calculating some initial weights), you may also need to comply with the commercial use restrictions of these two models depending on the situation. The training process utilized a model structure that was identical to LLaMA2, using the same attention calculation method as the original MHA LLaMA2 models, and no additional scaling applied to the Relative Positional Encoding (RoPE).

We manually curated a SFT dataset of 1.3B tokens for training, utilizing open source datasets from Hugging Face. For most of these sentences, we performed manual or synthetic rewrites and generated alternate language versions using larger language models. Additionally, we conducted augmented text training using carefully selected entries from Wikipedia, as well as featured entries from Fandom and filtered entries from Moegirlpedia. In order to strike a balance between efficiency and quality, 100% of the data used for training was synthetic data, no direct use of text from the internet or original texts from publicly available datasets was employed for fine-tuning.

The 7B version of the model is a distilled version of the 14B model, specifically designed for speculative sampling. Therefore, it is important to exercise caution when directly using the model, as it may produce hallucinations or unreliable outputs.

Please note that the model was trained on unfiltered internet data. Since we do not have the capacity to vet all of it, there may be a substantial amount of objectionable content, pornography, violence, and offensive language present that we are unable to remove. Therefore, you will still need to complete your own checks on the model's safety and filter keywords in the output. Due to computational resource constraints, we are presently unable to implement RLHF for the model's ethics and safety, nor training on SFT samples that refuse to answer certain questions for restrictive fine-tuning.

Bonus: The model underwent some fine-tuning on the prompt format introduced in LLaVA1.5 that is unrelated to image attention calculation. Therefore, aligning the ViT Projection module with frozen LM under visual instructions would enable rapid implementation of effective multimodal capabilities.



System Prompt must not be empty!


stem ACC: 56.83

Humanities ACC: 58.79

other ACC: 70.04

social ACC: 72.41

AVERAGE ACC:63.82 (Outperforms / Equal to the best Mistral-7B Chat-style fine-tunes, and ALL other models under 33B.)

CEval (Val):

STEM acc: 61.67

Social Science acc: 81.94

Humanities acc: 77.19

Other acc: 68.35

Hard acc:48.03

AVERAGE acc:70.27 (Outperforms ALL 7B models currently.)


Zero-shot ACC 0.5921152388172858 (Outperforms WizardMath-7B and Qwen-7B)

llama.cpp GGUF models GPT2Tokenizer 支持由 Kerfuffle 修复于 https://github.com/ggerganov/llama.cpp/pull/3743,新模型稍后上传。



该模型是基于Qwen的权重(并使用了LLaMA2权重,是的,用于计算一些权重初始化),您根据情况可能还需要遵守这两个模型的商业使用限制。训练过程中使用了与LLaMA2相同的模型结构,使用原始MHA LLaMA2模型的相同注意力计算方法,对相对位置编码(RoPE)没有进行额外的缩放。

我们手动筛选了一个包含13亿个标记的SFT数据集进行训练,利用了Hugging Face的开源数据集。对于大多数句子,我们进行了手动或合成改写,并使用更大的语言模型生成了其他语言版本。此外,我们还使用了精心挑选的来自维基百科的条目、来自Fandom的精选条目以及来自萌娘百科的过滤条目进行增强文本训练。为了在效率和质量之间取得平衡,训练所使用的100%数据都是合成数据,没有直接使用来自互联网或公开可用数据集的原始文本进行微调。












平均准确率:63.82 (优于/平于最好的 Mistral-7B 聊天格式的微调,和其余的33B及以下模型。)







平均准确率:70.27 (优于当前所有7B模型。)


零样本准确率0.5921152388172858 (优于WizardMath-7B和Qwen-7B)

Downloads last month
Inference Examples
Inference API (serverless) has been turned off for this model.

Finetuned from

Datasets used to train TheBloke/CausalLM-7B-GGUF

Space using TheBloke/CausalLM-7B-GGUF 1