falcon-7b-instruct-bnb-4bit

Model Card for alokabhishek/falcon-7b-instruct-bnb-4bit

<!-- Provide a quick summary of what the model is/does. -->

This repo contains 4-bit quantized (using bitsandbytes) model of Technology Innovation Institute's tiiuae/falcon-7b-instruct

Model Details

• Model creator: Technology Innovation Institute
• Original model: falcon-7b-instruct

About 4 bit quantization using bitsandbytes

• QLoRA: Efficient Finetuning of Quantized LLMs: arXiv - QLoRA: Efficient Finetuning of Quantized LLMs

• Hugging Face Blog post on 4-bit quantization using bitsandbytes: Making LLMs even more accessible with bitsandbytes, 4-bit quantization and QLoRA

• bitsandbytes github repo: bitsandbytes github repo

How to Get Started with the Model

Use the code below to get started with the model.

How to run from Python code

First install the package

pip install -q -U bitsandbytes accelerate torch huggingface_hub
pip install -q -U git+https://github.com/huggingface/transformers.git # Install latest version of transformers
pip install -q -U git+https://github.com/huggingface/peft.git
pip install flash-attn --no-build-isolation

Import

import torch
import os
from torch import bfloat16
from transformers import AutoTokenizer, AutoModelForCausalLM, pipeline, BitsAndBytesConfig, LlamaForCausalLM

Use a pipeline as a high-level helper

model_id_falcon = "alokabhishek/falcon-7b-instruct-bnb-4bit"

tokenizer_falcon = AutoTokenizer.from_pretrained(model_id_falcon, use_fast=True)

model_falcon = AutoModelForCausalLM.from_pretrained(
    model_id_falcon,
    device_map="auto"
)


pipe_falcon = pipeline(model=model_falcon, tokenizer=tokenizer_falcon, task='text-generation')

prompt_falcon = "Tell me a funny joke about Large Language Models meeting a Blackhole in an intergalactic Bar."

output_falcon = pipe_falcon(prompt_falcon, max_new_tokens=512)

print(output_falcon[0]["generated_text"])

Uses

<!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->

Direct Use

<!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->

[More Information Needed]

Downstream Use [optional]

<!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app -->

[More Information Needed]

Out-of-Scope Use

<!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->

[More Information Needed]

Bias, Risks, and Limitations

<!-- This section is meant to convey both technical and sociotechnical limitations. -->

[More Information Needed]

Model Card Authors [optional]

[More Information Needed]

Model Card Contact

[More Information Needed]