metadata

datasets:
  - tiiuae/falcon-refinedweb
license: apache-2.0
language:
  - en
inference: false

Want to contribute? TheBloke's Patreon page

Falcon-7B-Instruct GPTQ

This repo contains an experimantal GPTQ 4bit model for Falcon-7B-Instruct.

It is the result of quantising to 4bit using AutoGPTQ.

PERFORMANCE

Please note that performance with this GPTQ is currently very slow with AutoGPTQ.

It may perform better with the latest GPTQ-for-LLaMa code, but I havne't tested that personally yet.

Prompt template

A helpful assistant who helps the user with any questions asked.
User: prompt
Assistant:

AutoGPTQ

AutoGPTQ is required: GITHUB_ACTIONS=true pip install auto-gptq

AutoGPTQ provides pre-compiled wheels for Windows and Linux, with CUDA toolkit 11.7 or 11.8.

If you are running CUDA toolkit 12.x, you will need to compile your own by following these instructions:

git clone https://github.com/PanQiWei/AutoGPTQ
cd AutoGPTQ
pip install .

These manual steps will require that you have the Nvidia CUDA toolkit installed.

How to download and use this model in text-generation-webui

Launch text-generation-webui
Click the Model tab.
Untick Autoload model
Under Download custom model or LoRA, enter TheBloke/falcon-7B-instruct-GPTQ.
Click Download.
Wait until it says it's finished downloading.
Click the Refresh icon next to Model in the top left.
In the Model drop-down: choose the model you just downloaded, falcon-7B-instruct-GPTQ.
Set Loader to AutoGPTQ. This model will not work with ExLlama. It might work with recent GPTQ-for-LLaMa but I haven't tested that.
Tick Trust Remote Code, followed by Save Settings
Click Reload.
Once it says it's loaded, click the Text Generation tab and enter a prompt!

About `trust_remote_code`

Please be aware that this command line argument causes Python code provided by Falcon to be executed on your machine.

This code is required at the moment because Falcon is too new to be supported by Hugging Face transformers. At some point in the future transformers will support the model natively, and then trust_remote_code will no longer be needed.

In this repo you can see two .py files - these are the files that get executed. They are copied from the base repo at Falcon-7B-Instruct.

Simple Python example code

To run this code you need to install AutoGPTQ and einops:

GITHUB_ACTIONS=true pip install auto-gptq
pip install einops

You can then run this example code:

from transformers import AutoTokenizer, pipeline, logging
from auto_gptq import AutoGPTQForCausalLM, BaseQuantizeConfig
import argparse

model_name_or_path = "TheBloke/falcon-7b-instruct-GPTQ"
# You could also download the model locally, and access it there
# model_name_or_path = "/path/to/TheBloke_falcon-7b-instruct-GPTQ"

model_basename = "gptq_model-4bit-64g"

use_triton = False

tokenizer = AutoTokenizer.from_pretrained(model_name_or_path, use_fast=True)

model = AutoGPTQForCausalLM.from_quantized(model_name_or_path,
        model_basename=model_basename,
        use_safetensors=True,
        trust_remote_code=True,
        device="cuda:0",
        use_triton=use_triton,
        quantize_config=None)

prompt = "Tell me about AI"
prompt_template=f'''A helpful assistant who helps the user with any questions asked.
User: {prompt}
Assistant:'''

print("\n\n*** Generate:")

input_ids = tokenizer(prompt_template, return_tensors='pt').input_ids.cuda()
output = model.generate(inputs=input_ids, temperature=0.7, max_new_tokens=512)
print(tokenizer.decode(output[0]))

# Inference can also be done using transformers' pipeline
# Note that if you use pipeline, you will see a spurious error message saying the model type is not supported
# This can be ignored!  Or you can hide it with the following logging line:
# Prevent printing spurious transformers error when using pipeline with AutoGPTQ
logging.set_verbosity(logging.CRITICAL)

print("*** Pipeline:")
pipe = pipeline(
    "text-generation",
    model=model,
    tokenizer=tokenizer,
    max_new_tokens=512,
    temperature=0.7,
    top_p=0.95,
    repetition_penalty=1.15
)

print(pipe(prompt_template)[0]['generated_text'])

Provided files

gptq_model-4bit-64g.safetensors

This will work with AutoGPTQ 0.2.0 and later.

It was created with groupsize 64 to give higher inference quality, and without desc_act (act-order) to increase inference speed.

gptq_model-4bit-64g.safetensors
- Works with AutoGPTQ CUDA 0.2.0 and later.
  - At this time it does not work with AutoGPTQ Triton, but support will hopefully be added in time.
- Works with text-generation-webui using --trust-remote-code
- Does not work with any version of GPTQ-for-LLaMa
- Parameters: Groupsize = 64. No act-order.

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

Special thanks to: Luke from CarbonQuill, Aemon Algiz.

Patreon special mentions: RoA, Lone Striker, Gabriel Puliatti, Derek Yates, Randy H, Jonathan Leane, Eugene Pentland, Karl Bernard, Viktor Bowallius, senxiiz, Daniel P. Andersen, Pierre Kircher, Deep Realms, Cory Kujawski, Oscar Rangel, Fen Risland, Ajan Kanaga, LangChain4j, webtim, Nikolai Manek, Trenton Dambrowitz, Raven Klaugh, Kalila, Khalefa Al-Ahmad, Chris McCloskey, Luke @flexchar, Ai Maven, Dave, Asp the Wyvern, Sean Connelly, Imad Khwaja, Space Cruiser, Rainer Wilmers, subjectnull, Alps Aficionado, Willian Hasse, Fred von Graf, Artur Olbinski, Johann-Peter Hartmann, WelcomeToTheClub, Willem Michiel, Michael Levine, Iucharbius , Spiking Neurons AB, K, biorpg, John Villwock, Pyrater, Greatston Gnanesh, Mano Prime, Junyu Yang, Stephen Murray, John Detwiler, Luke Pendergrass, terasurfer , Pieter, zynix , Edmond Seymore, theTransient, Nathan LeClaire, vamX, Kevin Schuppel, Preetika Verma, ya boyyy, Alex , SuperWojo, Ghost , Joseph William Delisle, Matthew Berman, Talal Aujan, chris gileta, Illia Dulskyi.

Thank you to all my generous patrons and donaters!

✨ Original model card: Falcon-7B-Instruct

Falcon-7B-Instruct is a 7B parameters causal decoder-only model built by TII based on Falcon-7B and finetuned on a mixture of chat/instruct datasets. It is made available under the TII Falcon LLM License.

Paper coming soon 😊.

Why use Falcon-7B-Instruct?

You are looking for a ready-to-use chat/instruct model based on Falcon-7B.
Falcon-7B is a strong base model, outperforming comparable open-source models (e.g., MPT-7B, StableLM, RedPajama etc.), thanks to being trained on 1,500B tokens of RefinedWeb enhanced with curated corpora. See the OpenLLM Leaderboard.
It features an architecture optimized for inference, with FlashAttention (Dao et al., 2022) and multiquery (Shazeer et al., 2019).

💬 This is an instruct 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-7B.

🔥 Looking for an even more powerful model? Falcon-40B-Instruct is Falcon-7B-Instruct's big brother!

from transformers import AutoTokenizer, AutoModelForCausalLM
import transformers
import torch

model = "tiiuae/falcon-7b-instruct"

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']}")

💥 Falcon LLMs require PyTorch 2.0 for use with transformers!

Model Card for Falcon-7B-Instruct

Model Details

Model Description

Developed by: https://www.tii.ae;
Model type: Causal decoder-only;
Language(s) (NLP): English and French;
License: TII Falcon LLM License;
Finetuned from model: Falcon-7B.

Model Source

Paper: coming soon.

Uses

Direct Use

Falcon-7B-Instruct has been finetuned on a mixture of instruct and chat datasets.

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-7B-Instruct 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-7B-Instruct to develop guardrails and to take appropriate precautions for any production use.

How to Get Started with the Model

from transformers import AutoTokenizer, AutoModelForCausalLM
import transformers
import torch

model = "tiiuae/falcon-7b-instruct"

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

Training Data

Falcon-7B-Instruct was finetuned on a 250M tokens mixture of instruct/chat datasets.

Data source	Fraction	Tokens	Description
Bai ze	65%	164M	chat
GPT4All	25%	62M	instruct
GPTeacher	5%	11M	instruct
RefinedWeb-English	5%	13M	massive web crawl

The data was tokenized with the Falcon-7B/40B tokenizer.

Evaluation

Paper coming soon.

See the OpenLLM Leaderboard for early results.

Note that this model variant is not optimized for NLP benchmarks.

Technical Specifications

For more information about pretraining, see Falcon-7B.

Model Architecture and Objective

Falcon-7B 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:

Positionnal embeddings: rotary (Su et al., 2021);
Attention: multiquery (Shazeer et al., 2019) and FlashAttention (Dao et al., 2022);
Decoder-block: parallel attention/MLP with a single layer norm.

Hyperparameter	Value	Comment
Layers	32
`d_model`	4544	Increased to compensate for multiquery
`head_dim`	64	Reduced to optimise for FlashAttention
Vocabulary	65024
Sequence length	2048

Compute Infrastructure

Hardware

Falcon-7B-Instruct was trained on AWS SageMaker, on 32 A100 40GB GPUs in P4d instances.

Software

Falcon-7B-Instruct 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