Transformers
falcon
TheBloke's picture
Update base_model formatting
96230d6
|
raw
history blame
22.8 kB
metadata
language:
  - en
  - de
  - es
  - fr
license: unknown
datasets:
  - tiiuae/falcon-refinedweb
model_name: Falcon 180B Chat
inference: false
model_creator: Technology Innovation Institute
model_link: https://huggingface.co/tiiuae/falcon-180B-chat
model_type: falcon
quantized_by: TheBloke
base_model: tiiuae/falcon-180B-chat
TheBlokeAI

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


Falcon 180B Chat - GGUF

Description

This repo contains GGUF format model files for Technology Innovation Institute's Falcon 180B Chat.

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.

The key benefit of GGUF is that it is a extensible, future-proof format which stores more information about the model as metadata. It also includes significantly improved tokenization code, including for the first time full support for special tokens. This should improve performance, especially with models that use new special tokens and implement custom prompt templates.

Here are a list of clients and libraries that are known to support GGUF:

  • llama.cpp.
  • text-generation-webui, the most widely used web UI, with many features and powerful extensions.
  • KoboldCpp, a fully featured web UI, with full GPU accel across multiple platforms and GPU architectures. Especially good for story telling.
  • LM Studio, an easy-to-use and powerful local GUI with GPU acceleration on both Windows (NVidia and AMD), and macOS.
  • LoLLMS Web UI, a great web UI with many interesting and unique features, including a full model library for easy model selection.
  • 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: Falcon

{system_message}
User: {prompt}
Assistant:

Example:

Girafatron is obsessed with giraffes, the most glorious animal on the face of this Earth. Giraftron believes all other animals are irrelevant when compared to the glorious majesty of the giraffe
User: Hello, Girafatron!
Girafatron:

Compatibility

These quantised GGUF files are compatible with llama.cpp from August 21st 2023 onwards, as of commit 6381d4e110bd0ec02843a60bbeb8b6fc37a9ace9

They are now also compatible with many third party UIs and libraries - please see the list at the top of the 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
falcon-180b-chat.Q2_K.gguf Q2_K 2 73.97 GB 76.47 GB smallest, significant quality loss - not recommended for most purposes
falcon-180b-chat.Q3_K_S.gguf Q3_K_S 3 77.77 GB 80.27 GB very small, high quality loss
falcon-180b-chat.Q3_K_M.gguf Q3_K_M 3 85.18 GB 87.68 GB very small, high quality loss
falcon-180b-chat.Q3_K_L.gguf Q3_K_L 3 91.99 GB 94.49 GB small, substantial quality loss
falcon-180b-chat.Q4_0.gguf Q4_0 4 101.48 GB 103.98 GB legacy; small, very high quality loss - prefer using Q3_K_M
falcon-180b-chat.Q4_K_S.gguf Q4_K_S 4 101.48 GB 103.98 GB small, greater quality loss
falcon-180b-chat.Q4_K_M.gguf Q4_K_M 4 108.48 GB 110.98 GB medium, balanced quality - recommended
falcon-180b-chat.Q5_0.gguf Q5_0 5 123.80 GB 126.30 GB legacy; medium, balanced quality - prefer using Q4_K_M
falcon-180b-chat.Q5_K_S.gguf Q5_K_S 5 123.80 GB 126.30 GB large, low quality loss - recommended
falcon-180b-chat.Q5_K_M.gguf Q5_K_M 5 130.99 GB 133.49 GB large, very low quality loss - recommended
falcon-180b-chat.Q6_K.gguf Q6_K 6 147.52 GB 150.02 GB very large, extremely low quality loss
falcon-180b-chat.Q8_0.gguf Q8_0 8 190.76 GB 193.26 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.

All files are split and require joining after download

Note: HF does not support uploading files larger than 50GB. Therefore I have uploaded all files as split files

Click for instructions regarding joining files

To join the files, use the following example for each file you're interested in:

Linux and macOS:

cat falcon-180b-chat.Q2_K.gguf-split-* > falcon-180b-chat.Q2_K.gguf && rm falcon-180b-chat.Q2_K.gguf-split-*

Windows command line:

COPY /B falcon-180b-chat.Q2_K.gguf-split-a + falcon-180b-chat.Q2_K.gguf-split-b falcon-180b-chat.Q2_K.gguf
del falcon-180b-chat.Q2_K.gguf-split-a falcon-180b-chat.Q2_K.gguf-split-b

Example llama.cpp command

Make sure you are using llama.cpp from commit 6381d4e110bd0ec02843a60bbeb8b6fc37a9ace9 or later.

For compatibility with older versions of llama.cpp, or for any third-party libraries or clients that haven't yet updated for GGUF, please use GGML files instead.

./main -t 10 -ngl 32 -m falcon-180b-chat.q4_K_M.gguf --color -c 4096 --temp 0.7 --repeat_penalty 1.1 -n -1 -p "User: Write a story about llamas\nAssistant:"

Change -t 10 to the number of physical CPU cores you have. For example if your system has 8 cores/16 threads, use -t 8. If offloading all layers to GPU, set -t 1.

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 this model. 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 from Python using ctransformers

First install the package

# Base ctransformers with no GPU acceleration
pip install ctransformers>=0.2.24
# Or with CUDA GPU acceleration
pip install ctransformers[cuda]>=0.2.24
# Or with ROCm GPU acceleration
CT_HIPBLAS=1 pip install ctransformers>=0.2.24 --no-binary ctransformers
# Or with Metal GPU acceleration for macOS systems
CT_METAL=1 pip install ctransformers>=0.2.24 --no-binary ctransformers

Simple example code to load one of these GGUF models

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/Falcon-180B-Chat-GGUF", model_file="falcon-180b-chat.q4_K_M.gguf", model_type="falcon", gpu_layers=50)

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

How to use with LangChain

Here's guides on using llama-cpp-python or ctransformers with LangChain:

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.

Special thanks to: Aemon Algiz.

Patreon special mentions: Russ Johnson, J, alfie_i, Alex, NimbleBox.ai, Chadd, Mandus, Nikolai Manek, Ken Nordquist, ya boyyy, Illia Dulskyi, Viktor Bowallius, vamX, Iucharbius, zynix, Magnesian, Clay Pascal, Pierre Kircher, Enrico Ros, Tony Hughes, Elle, Andrey, knownsqashed, Deep Realms, Jerry Meng, Lone Striker, Derek Yates, Pyrater, Mesiah Bishop, James Bentley, Femi Adebogun, Brandon Frisco, SuperWojo, Alps Aficionado, Michael Dempsey, Vitor Caleffi, Will Dee, Edmond Seymore, usrbinkat, LangChain4j, Kacper Wikieล‚, Luke Pendergrass, John Detwiler, theTransient, Nathan LeClaire, Tiffany J. Kim, biorpg, Eugene Pentland, Stanislav Ovsiannikov, Fred von Graf, terasurfer, Kalila, Dan Guido, Nitin Borwankar, ้˜ฟๆ˜Ž, Ai Maven, John Villwock, Gabriel Puliatti, Stephen Murray, Asp the Wyvern, danny, Chris Smitley, ReadyPlayerEmma, S_X, Daniel P. Andersen, Olakabola, Jeffrey Morgan, Imad Khwaja, Caitlyn Gatomon, webtim, Alicia Loh, Trenton Dambrowitz, Swaroop Kallakuri, Erik Bjรคreholt, Leonard Tan, Spiking Neurons AB, Luke @flexchar, Ajan Kanaga, Thomas Belote, Deo Leter, RoA, Willem Michiel, transmissions 11, subjectnull, Matthew Berman, Joseph William Delisle, David Ziegler, Michael Davis, Johann-Peter Hartmann, Talal Aujan, senxiiz, Artur Olbinski, Rainer Wilmers, Spencer Kim, Fen Risland, Cap'n Zoog, Rishabh Srivastava, Michael Levine, Geoffrey Montalvo, Sean Connelly, Alexandros Triantafyllidis, Pieter, Gabriel Tamborski, Sam, Subspace Studios, Junyu Yang, Pedro Madruga, Vadim, Cory Kujawski, K, Raven Klaugh, Randy H, Mano Prime, Sebastain Graf, Space Cruiser

Thank you to all my generous patrons and donaters!

And thank you again to a16z for their generous grant.

Original model card: Technology Innovation Institute's Falcon 180B Chat

๐Ÿš€ Falcon-180B-Chat

Falcon-180B-Chat is a 180B parameters causal decoder-only model built by TII based on Falcon-180B and finetuned on a mixture of Ultrachat, Platypus and Airoboros. It is made available under the Falcon-180B TII License and Acceptable Use Policy.

Paper coming soon ๐Ÿ˜Š

๐Ÿค— To get started with Falcon (inference, finetuning, quantization, etc.), we recommend reading this great blogpost from HF or this one from the release of the 40B! Note that since the 180B is larger than what can easily be handled with transformers+acccelerate, we recommend using Text Generation Inference.

You will need at least 400GB of memory to swiftly run inference with Falcon-180B.

Why use Falcon-180B-chat?

  • โœจ You are looking for a ready-to-use chat/instruct model based on Falcon-180B.
  • It is the best open-access model currently available, and one of the best model overall. Falcon-180B outperforms LLaMA-2, StableLM, RedPajama, MPT, etc. See the OpenLLM Leaderboard.
  • It features an architecture optimized for inference, with multiquery (Shazeer et al., 2019).
  • It is made available under a permissive license allowing for commercial use.

๐Ÿ’ฌ This is a Chat model, which may not be ideal for further finetuning. If you are interested in building your own instruct/chat model, we recommend starting from Falcon-180B.

๐Ÿ’ธ Looking for a smaller, less expensive model? Falcon-7B-Instruct and Falcon-40B-Instruct are Falcon-180B-Chat's little brothers!

๐Ÿ’ฅ Falcon LLMs require PyTorch 2.0 for use with transformers!

Model Card for Falcon-180B-Chat

Model Details

Model Description

Model Source

  • Paper: coming soon.

Uses

See the acceptable use policy.

Direct Use

Falcon-180B-Chat has been finetuned on a chat dataset.

Out-of-Scope Use

Production use without adequate assessment of risks and mitigation; any use cases which may be considered irresponsible or harmful.

Bias, Risks, and Limitations

Falcon-180B-Chat is mostly trained on English data, and will not generalize appropriately to other languages. Furthermore, as it is trained on a large-scale corpora representative of the web, it will carry the stereotypes and biases commonly encountered online.

Recommendations

We recommend users of Falcon-180B-Chat to develop guardrails and to take appropriate precautions for any production use.

How to Get Started with the Model

To run inference with the model in full bfloat16 precision you need approximately 8xA100 80GB or equivalent.

from transformers import AutoTokenizer, AutoModelForCausalLM
import transformers
import torch

model = "tiiuae/falcon-180b-chat"

tokenizer = AutoTokenizer.from_pretrained(model)
pipeline = transformers.pipeline(
    "text-generation",
    model=model,
    tokenizer=tokenizer,
    torch_dtype=torch.bfloat16,
    trust_remote_code=True,
    device_map="auto",
)
sequences = pipeline(
   "Girafatron is obsessed with giraffes, the most glorious animal on the face of this Earth. Giraftron believes all other animals are irrelevant when compared to the glorious majesty of the giraffe.\nDaniel: Hello, Girafatron!\nGirafatron:",
    max_length=200,
    do_sample=True,
    top_k=10,
    num_return_sequences=1,
    eos_token_id=tokenizer.eos_token_id,
)
for seq in sequences:
    print(f"Result: {seq['generated_text']}")

Training Details

Falcon-180B-Chat is based on Falcon-180B.

Training Data

Falcon-180B-Chat is finetuned on a mixture of Ultrachat, Platypus and Airoboros.

The data was tokenized with the Falcon tokenizer.

Evaluation

Paper coming soon.

See the OpenLLM Leaderboard for early results.

Technical Specifications

Model Architecture and Objective

Falcon-180B-Chat is a causal decoder-only model trained on a causal language modeling task (i.e., predict the next token).

The architecture is broadly adapted from the GPT-3 paper (Brown et al., 2020), with the following differences:

For multiquery, we are using an internal variant which uses independent key and values per tensor parallel degree.

Hyperparameter Value Comment
Layers 80
d_model 14848
head_dim 64 Reduced to optimise for FlashAttention
Vocabulary 65024
Sequence length 2048

Compute Infrastructure

Hardware

Falcon-180B-Chat was trained on AWS SageMaker, on up to 4,096 A100 40GB GPUs in P4d instances.

Software

Falcon-180B-Chat was trained a custom distributed training codebase, Gigatron. It uses a 3D parallelism approach combined with ZeRO and high-performance Triton kernels (FlashAttention, etc.)

Citation

Paper coming soon ๐Ÿ˜Š. In the meanwhile, you can use the following information to cite:

@article{falcon,
  title={The Falcon Series of Language Models:Towards Open Frontier Models},
  author={Almazrouei, Ebtesam and Alobeidli, Hamza and Alshamsi, Abdulaziz and Cappelli, Alessandro and Cojocaru, Ruxandra and Debbah, Merouane and Goffinet, Etienne and Heslow, Daniel and Launay, Julien and Malartic, Quentin and Noune, Badreddine and Pannier, Baptiste and Penedo, Guilherme},
  year={2023}
}

To learn more about the pretraining dataset, see the ๐Ÿ““ RefinedWeb paper.

@article{refinedweb,
  title={The {R}efined{W}eb dataset for {F}alcon {LLM}: outperforming curated corpora with web data, and web data only},
  author={Guilherme Penedo and Quentin Malartic and Daniel Hesslow and Ruxandra Cojocaru and Alessandro Cappelli and Hamza Alobeidli and Baptiste Pannier and Ebtesam Almazrouei and Julien Launay},
  journal={arXiv preprint arXiv:2306.01116},
  eprint={2306.01116},
  eprinttype = {arXiv},
  url={https://arxiv.org/abs/2306.01116},
  year={2023}
}

Contact

falconllm@tii.ae