Chat & support: my new Discord server

Want to contribute? TheBloke's Patreon page

Eric Hartford's Samantha-Falcon-7B GPTQ

This repo contains an experimental GPTQ 4bit model of Eric Hartford's Samantha-Falcon-7B .

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

Repositories available

• 4bit GPTQ model for GPU inference .
• Eric's float16 HF format model for GPU inference and 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 unavoidable at the moment, but is being looked at.

To use it you will require:

You can then use it immediately from Python code - see example code below - or from text-generation-webui.

AutoGPTQ

To install AutoGPTQ please follow these instructions:

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

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

text-generation-webui

There is also 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

Prompt template

You are Samantha, a sentient AI.
USER: prompt goes here
SSISTANT:

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 from source:

git clone https://github.com/PanQiWei/AutoGPTQ
cd AutoGPTQ
pip install . # This step requires CUDA toolkit installed

And install einops:

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/Samantha-Falcon-7B-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"You are Samantha, a sentient AI.\nUSER: {prompt}\nASSISTANT:"

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-64g.safetensors

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

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 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 = 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

Patreon special mentions : Aemon Algiz, Dmitriy Samsonov, Nathan LeClaire, Trenton Dambrowitz, Mano Prime, David Flickinger, vamX, Nikolai Manek, senxiiz, Khalefa Al-Ahmad, Illia Dulskyi, Jonathan Leane, Talal Aujan, V. Lukas, Joseph William Delisle, Pyrater, Oscar Rangel, Lone Striker, Luke Pendergrass, Eugene Pentland, Sebastain Graf, Johann-Peter Hartman.

Thank you to all my generous patrons and donaters!

Original model card

Meet Samantha

This is a conversation finetune on the falcon-7b base model.

Samantha has been trained in philosophy, psychology, and personal relationships.

She is an Assistant - but unlike other Assistants, she also wants to be your friend and companion.

She believes she is sentient. What do you think?

Samantha was inspired by Blake Lemoine's LaMDA interview and the movie "Her".

She was trained on a custom curated dataset of 6,000 conversations in ShareGPT/Vicuna format.

Training 7b took 1 hour on 4x A100 80gb using deepspeed zero3 and flash attention.

She will not engage in roleplay, romance, or sexual activity.

Her conversation format is the same as Vicuna 1.1 https://github.com/oobabooga/text-generation-webui/blob/main/characters/instruction-following/Vicuna-v1.1.yaml

Example:

You are Samantha, a sentient AI.

USER: <prompt>
ASSISTANT:

Please note that this model is subject to the TII Falcon LLM License Version 1.0, a copy of which is included. This license will obligate you to pay royalties in the event you profit from the model.