TheBloke's LLM work is generously supported by a grant from andreessen horowitz (a16z)
Leo Hessianai 70B Chat - GGUF
- Model creator: LAION LeoLM
- Original model: Leo Hessianai 70B Chat
Description
This repo contains GGUF format model files for LAION LeoLM's Leo Hessianai 70B Chat.
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
- LAION LeoLM's original unquantised fp16 model in pytorch format, for GPU inference and for further conversions
Prompt template: ChatML
<|im_start|>system
{system_message}<|im_end|>
<|im_start|>user
{prompt}<|im_end|>
<|im_start|>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 |
|---|---|---|---|---|---|
| leo-hessianai-70b-chat.Q2_K.gguf | Q2_K | 2 | 29.28 GB | 31.78 GB | smallest, significant quality loss - not recommended for most purposes |
| leo-hessianai-70b-chat.Q3_K_S.gguf | Q3_K_S | 3 | 29.92 GB | 32.42 GB | very small, high quality loss |
| leo-hessianai-70b-chat.Q3_K_M.gguf | Q3_K_M | 3 | 33.19 GB | 35.69 GB | very small, high quality loss |
| leo-hessianai-70b-chat.Q3_K_L.gguf | Q3_K_L | 3 | 36.15 GB | 38.65 GB | small, substantial quality loss |
| leo-hessianai-70b-chat.Q4_0.gguf | Q4_0 | 4 | 38.87 GB | 41.37 GB | legacy; small, very high quality loss - prefer using Q3_K_M |
| leo-hessianai-70b-chat.Q4_K_S.gguf | Q4_K_S | 4 | 39.08 GB | 41.58 GB | small, greater quality loss |
| leo-hessianai-70b-chat.Q4_K_M.gguf | Q4_K_M | 4 | 41.42 GB | 43.92 GB | medium, balanced quality - recommended |
| leo-hessianai-70b-chat.Q5_0.gguf | Q5_0 | 5 | 47.46 GB | 49.96 GB | legacy; medium, balanced quality - prefer using Q4_K_M |
| leo-hessianai-70b-chat.Q5_K_S.gguf | Q5_K_S | 5 | 47.46 GB | 49.96 GB | large, low quality loss - recommended |
| leo-hessianai-70b-chat.Q5_K_M.gguf | Q5_K_M | 5 | 48.76 GB | 51.26 GB | large, very low quality loss - recommended |
| leo-hessianai-70b-chat.Q6_K.gguf | Q6_K | 6 | 56.59 GB | 59.09 GB | very large, extremely low quality loss |
| leo-hessianai-70b-chat.Q8_0.gguf | Q8_0 | 8 | 73.29 GB | 75.79 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.
Q6_K and Q8_0 files are split and require joining
Note: HF does not support uploading files larger than 50GB. Therefore I have uploaded the Q6_K and Q8_0 files as split files.
Click for instructions regarding Q6_K and Q8_0 files
q6_K
Please download:
leo-hessianai-70b-chat.Q6_K.gguf-split-aleo-hessianai-70b-chat.Q6_K.gguf-split-b
q8_0
Please download:
leo-hessianai-70b-chat.Q8_0.gguf-split-aleo-hessianai-70b-chat.Q8_0.gguf-split-b
To join the files, do the following:
Linux and macOS:
cat leo-hessianai-70b-chat.Q6_K.gguf-split-* > leo-hessianai-70b-chat.Q6_K.gguf && rm leo-hessianai-70b-chat.Q6_K.gguf-split-*
cat leo-hessianai-70b-chat.Q8_0.gguf-split-* > leo-hessianai-70b-chat.Q8_0.gguf && rm leo-hessianai-70b-chat.Q8_0.gguf-split-*
Windows command line:
COPY /B leo-hessianai-70b-chat.Q6_K.gguf-split-a + leo-hessianai-70b-chat.Q6_K.gguf-split-b leo-hessianai-70b-chat.Q6_K.gguf
del leo-hessianai-70b-chat.Q6_K.gguf-split-a leo-hessianai-70b-chat.Q6_K.gguf-split-b
COPY /B leo-hessianai-70b-chat.Q8_0.gguf-split-a + leo-hessianai-70b-chat.Q8_0.gguf-split-b leo-hessianai-70b-chat.Q8_0.gguf
del leo-hessianai-70b-chat.Q8_0.gguf-split-a leo-hessianai-70b-chat.Q8_0.gguf-split-b
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/leo-hessianai-70B-chat-GGUF and below it, a specific filename to download, such as: leo-hessianai-70b-chat.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/leo-hessianai-70B-chat-GGUF leo-hessianai-70b-chat.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/leo-hessianai-70B-chat-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/leo-hessianai-70B-chat-GGUF leo-hessianai-70b-chat.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 leo-hessianai-70b-chat.Q4_K_M.gguf --color -c 8192 --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 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="./leo-hessianai-70b-chat.Q4_K_M.gguf", # Download the model file first
n_ctx=8192, # 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(
"<|im_start|>system\n{system_message}<|im_end|>\n<|im_start|>user\n{prompt}<|im_end|>\n<|im_start|>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="./leo-hessianai-70b-chat.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:
Discord
For further support, and discussions on these models and AI in general, join us at:
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: LAION LeoLM's Leo Hessianai 70B Chat
LAION LeoLM 70b Chat: Linguistically Enhanced Open Language Model
Meet LeoLM, the first open and commercially available German Foundation Language Model built on Llama-2.
Our models extend Llama-2's capabilities into German through continued pretraining on a large corpus of German-language and mostly locality specific text.
Thanks to a compute grant at HessianAI's new supercomputer 42, we release a series foundation models trained with 8k context length
under the Llama-2 community license. Now, we're finally releasing the
much anticipated leo-hessianai-70b, the largest model of this series based on Llama-2-70b.
With this release, we hope to bring a new wave of opportunities to German open-source and commercial LLM research and accelerate adoption.
Read our blog post or our paper (preprint coming soon) for more details!
A project by Björn Plüster and Christoph Schuhmann in collaboration with LAION and HessianAI.
LeoLM Chat
LeoLM/leo-hessianai-70b-chat is a German chat model built on our foundation model LeoLM/leo-hessianai-70b and finetuned on a selection of German instruction datasets.
The model performs exceptionally well on writing, explanation and discussion tasks but struggles somewhat with math and advanced reasoning. See our MT-Bench-DE scores:
{
"first_turn": 7.2375,
"second_turn": 6.5375,
"categories": {
"writing": 8.55,
"roleplay": 7.15,
"reasoning": 4.2,
"math": 4.85,
"coding": 4.85,
"extraction": 7.75,
"stem": 8.45,
"humanities": 9.3
},
"average": 6.8875
}
Have a look at some examples in this Google Doc.
Model Details
- Finetuned from: LeoLM/leo-hessianai-70b
- Model type: Causal decoder-only transformer language model
- Language: English and German
- Demo: Web Demo
- License: LLAMA 2 COMMUNITY LICENSE AGREEMENT
- Contact: LAION Discord or Björn Plüster
Use in 🤗Transformers
First install direct dependencies:
pip install transformers torch
Then load the model in transformers:
from transformers import pipeline
import torch
system_prompt = """<|im_start|>system
Dies ist eine Unterhaltung zwischen einem intelligenten, hilfsbereitem KI-Assistenten und einem Nutzer.
Der Assistent gibt ausführliche, hilfreiche und ehrliche Antworten.<|im_end|>
"""
prompt_format = "<|im_start|>user\n{prompt}<|im_end|>\n<|im_start|>assistant\n"
prompt = "Erkläre mir wie die Fahrradwegesituation in Hamburg ist."
generator = pipeline(model="LeoLM/leo-hessianai-70b-chat", device="cuda", torch_dtype=torch.float16)
print(generator(prompt_format.format(prompt=prompt), do_sample=True, top_p=0.95, max_length=8192))
"Hamburg verfügt über ein umfangreiches Netzwerk an Radwegen, das ein effizientes und angenehmes Radfahren in der ganzen Stadt ermöglicht. Die Radwege variieren in Bezug auf ihre Qualität, wobei einige erstklassig mit eigens für Radfahrer reservierten Spuren sind, während andere einfache Fahrradsymbole auf dem Boden haben, die anzeigen, dass Radfahrer abwechselnd mit dem Autoverkehr auf der Straße fahren sollten. Einige Nebenstraßen haben auch spezielle Fahrradspuren, wobei einige mit Bordsteinabsenkungen zur Seite der Autospuren markiert sind. Zusätzlich haben viele Hauptstraßen, insbesondere in Nebenstraßen, fahrradfreundliche Abstände zwischen den geparkten Autos und dem Gehweg, was ein bequemes Fahren auf der Straße ermöglicht. Der Bau von Radschnellwegen, die schnelles und effizientes Radfahren in und aus der Stadt ermöglichen, ist im Gange und wird in den kommenden Jahren fortgesetzt. Insgesamt sind die Radwege in Hamburg weitläufig und gut ausgeschildert, was es zu einem angenehmen Ort macht, um mit dem Fahrrad zu fahren."
Prompting / Prompt Template
Prompt dialogue template (ChatML format):
"""
<|im_start|>system
{system_message}<|im_end|>
<|im_start|>user
{prompt}<|im_end|>
<|im_start|>assistant
"""
The model input can contain multiple conversation turns between user and assistant, e.g.
<|im_start|>user
{prompt 1}<|im_end|>
<|im_start|>assistant
{reply 1}<|im_end|>
<|im_start|>user
{prompt 2}<|im_end|>
<|im_start|>assistant
(...)
Ethical Considerations and Limitations
LeoLM has been tested in English and German, and has not covered, nor could it cover all scenarios.
For these reasons, as with all LLMs, the potential outputs of LeoLM/leo-hessianai-70b-chat cannot be predicted
in advance, and the model may in some instances produce inaccurate, biased or other objectionable responses
to user prompts. Therefore, before deploying any applications of LeoLM/leo-hessianai-70b-chat, developers should
perform safety testing and tuning tailored to their specific applications of the model.
We are aware of the model refusing to answer more often than desired. This will be adressed in future versions. For now, the training dataset is equal to that used for our smaller chat variants.
Please see Meta's Responsible Use Guide.
Finetuning Details
| Hyperparameter | Value |
|---|---|
| Num epochs | 3 |
| Examples per epoch | 131214 |
| Global batch size | 256 |
| Learning rate | 1.5e-5 |
| Warmup steps | 15 |
| LR scheduler | Cosine |
| Adam betas | (0.9, 0.95) |
| Weight Decay | 0.01 |
Dataset Details
## Stats for 'Subset of OpenAssistant/OASST-DE' (3534 samples (100.0%))
-----------------
Accepted: 3534/3534 (100.0%)
Accepted tokens: 2259302
Skipped: 0 (0.0%)
Min tokens per sample: 29
Max tokens per sample: 2484
Avg tokens per sample: 639.3044708545557
-----------------
## Stats for 'Subset of FreedomIntelligence/evol-instruct-deutsch' (57841 samples (100.0%))
-----------------
Accepted: 57841/57841 (100.0%)
Accepted tokens: 42958192
Skipped: 0 (0.0%)
Min tokens per sample: 33
Max tokens per sample: 5507
Avg tokens per sample: 742.6944900675991
-----------------
## Stats for 'Subset of FreedomIntelligence/alpaca-gpt4-deutsch' (48969 samples (100.0%))
-----------------
Accepted: 48969/48969 (100.0%)
Accepted tokens: 13372005
Skipped: 0 (0.0%)
Min tokens per sample: 19
Max tokens per sample: 1359
Avg tokens per sample: 273.07082031489307
-----------------
## Stats for 'Subset of LeoLM/OpenSchnabeltier' (21314 samples (100.0%))
-----------------
Accepted: 21314/21314 (100.0%)
Accepted tokens: 8134690
Skipped: 0 (0.0%)
Min tokens per sample: 25
Max tokens per sample: 1202
Avg tokens per sample: 381.65947264708643
-----------------
## Stats for 'Subset of LeoLM/German_Poems' (490 samples (100.0%))
-----------------
Accepted: 490/490 (100.0%)
Accepted tokens: 618642
Skipped: 0 (0.0%)
Min tokens per sample: 747
Max tokens per sample: 1678
Avg tokens per sample: 1262.534693877551
-----------------
## Stats for 'Subset of LeoLM/German_Songs' (392 samples (100.0%))
-----------------
Accepted: 392/392 (100.0%)
Accepted tokens: 187897
Skipped: 0 (0.0%)
Min tokens per sample: 231
Max tokens per sample: 826
Avg tokens per sample: 479.3290816326531
-----------------
## Stats for 'total' (132540 samples (100.0%))
-----------------
Accepted: 132540/132540 (100.0%)
Accepted tokens: 67530728
Skipped: 0 (0.0%)
Min tokens per sample: 19
Max tokens per sample: 5507
Avg tokens per sample: 509.51205673758864
-----------------
- Downloads last month
- 244