philschmid/falcon-40b-instruct-GPTQ-inference-endpoints

Chat & support: my new Discord server

Want to contribute? TheBloke's Patreon page

Falcon-40B-Instruct 4bit GPTQ

This repo contains an experimantal GPTQ 4bit model for Falcon-40B-Instruct.

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

Repositories available

• 4-bit GPTQ model for GPU inference
• 3-bit GPTQ model for GPU inference
• Unquantised bf16 model in pytorch format, for GPU inference and for further conversions

EXPERIMENTAL

Please note this is an experimental GPTQ model. Support for it is currently quite limited.

It is also expected to be VERY SLOW. This is currently unavoidable, but is being looked at.

This 4bit model requires at least 35GB VRAM to load. It can be used on 40GB or 48GB cards, but not less.

Please be aware that you should currently expect around 0.7 tokens/s on 40B Falcon GPTQ.

AutoGPTQ

AutoGPTQ is required: 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.

text-generation-webui

There is provisional AutoGPTQ support in text-generation-webui.

This requires text-generation-webui as of commit 204731952ae59d79ea3805a425c73dd171d943c3.

So please first update text-genration-webui to the latest version.

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

1. Launch text-generation-webui with the following command-line arguments: --autogptq --trust-remote-code
2. Click the Model tab.
3. Under Download custom model or LoRA, enter TheBloke/falcon-40B-instruct-GPTQ.
4. Click Download.
5. Wait until it says it's finished downloading.
6. Click the Refresh icon next to Model in the top left.
7. In the Model drop-down: choose the model you just downloaded, falcon-40B-instruct-GPTQ.
8. 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:

pip install auto-gptq
pip install einops

You can then run this example code:

import torch
from transformers import AutoTokenizer
from auto_gptq import AutoGPTQForCausalLM

# Download the model from HF and store it locally, then reference its location here:
quantized_model_dir = "/path/to/falcon40b-instruct-GPTQ"

from transformers import AutoTokenizer
tokenizer = AutoTokenizer.from_pretrained(quantized_model_dir, use_fast=False)

model = AutoGPTQForCausalLM.from_quantized(quantized_model_dir, device="cuda:0", use_triton=False, use_safetensors=True, torch_dtype=torch.float32, trust_remote_code=True)

prompt = "Write a story about llamas"
prompt_template = f"### Instruction: {prompt}\n### Response:"

tokens = tokenizer(prompt_template, return_tensors="pt").to("cuda:0").input_ids
output = model.generate(input_ids=tokens, max_new_tokens=100, do_sample=True, temperature=0.8)
print(tokenizer.decode(output[0]))

Provided files

gptq_model-4bit--1g.safetensors

This will work with AutoGPTQ as of commit 3cb1bf5 (3cb1bf5a6d43a06dc34c6442287965d1838303d3)

It was created without groupsize to reduce VRAM requirements, and with desc_act (act-order) to improve inference quality.

• gptq_model-4bit--1g.safetensors
  • Works only with latest AutoGPTQ CUDA, compiled from source as of commit 3cb1bf5
    • At this time it does not work with AutoGPTQ Triton, but support will hopefully be added in time.
  • Works with text-generation-webui using --autogptq --trust_remote_code
    • At this time it does NOT work with one-click-installers
  • Does not work with any version of GPTQ-for-LLaMa
  • Parameters: Groupsize = None. Act order (desc_act)

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'd be most gratefully received and will help me to keep providing models, and work on new AI projects.

Donaters will get priority support on any and all AI/LLM/model questions, plus other benefits.

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

Patreon special mentions: Aemon Algiz; Johann-Peter Hartmann; Talal Aujan; Jonathan Leane; Illia Dulskyi; Khalefa Al-Ahmad; senxiiz; Sebastain Graf; Eugene Pentland; Nikolai Manek; Luke Pendergrass.

Thank you to all my generous patrons and donaters.

✨ Original model card: Falcon-40B-Instruct

✨ Falcon-40B-Instruct

Falcon-40B-Instruct is a 40B parameters causal decoder-only model built by TII based on Falcon-40B and finetuned on a mixture of Baize. It is made available under the TII Falcon LLM License.

Paper coming soon 😊.

Why use Falcon-40B-Instruct?

• You are looking for a ready-to-use chat/instruct model based on Falcon-40B.
• Falcon-40B is the best open-source model available. It outperforms LLaMA, StableLM, RedPajama, MPT, etc. 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-40B.

💸 Looking for a smaller, less expensive model? Falcon-7B-Instruct is Falcon-40B-Instruct's small brother!

from transformers import AutoTokenizer, AutoModelForCausalLM
import transformers
import torch

model = "tiiuae/falcon-40b-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']}")

Model Card for Falcon-40B-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-40B-Instruct 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-40B-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-40B-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-40b-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-40B-Instruct was finetuned on a 150M tokens from Bai ze mixed with 5% of RefinedWeb data.

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

Evaluation

Paper coming soon.

See the OpenLLM Leaderboard for early results.

Technical Specifications

For more information about pretraining, see Falcon-40B.

Model Architecture and Objective

Falcon-40B 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.

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

Hyperparameter	Value	Comment
Layers	60
d_model	8192
head_dim	64	Reduced to optimise for FlashAttention
Vocabulary	65024
Sequence length	2048

Compute Infrastructure

Hardware

Falcon-40B-Instruct was trained on AWS SageMaker, on 64 A100 40GB GPUs in P4d instances.

Software

Falcon-40B-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

Paper coming soon 😊.

License

Falcon-40B-Instruct is made available under the TII Falcon LLM License. Broadly speaking,

• You can freely use our models for research and/or personal purpose;
• You are allowed to share and build derivatives of these models, but you are required to give attribution and to share-alike with the same license;
• For commercial use, you are exempt from royalties payment if the attributable revenues are inferior to $1M/year, otherwise you should enter in a commercial agreement with TII.

Contact

falconllm@tii.ae