GemMarketing: A Marketing Large Language Model

GemMarketing is a 2B parameter Domain-Specific Large Language Model (LLM).
It was specifically adapted to the marketing domain from gemma-2b through continuous pretraining on a meticulously curated and comprehensive marketing corpus of more than 43B tokens.
GemMarketing outperforms gemma-2b on specific marketing tasks. We are releasing this early checkpoint of the model to the AI community.

Model Description

GemMarketing is a powerful tool that can help generate high-quality marketing content and conduct research in the field of marketing. It is an excellent resource for staying ahead in the rapidly changing world of marketing.

While the model is designed to encode marketing knowledge, this checkpoint is not yet adapted to deliver knowledge appropriately, safely, or within professional actionable constraints.
We recommend against deploying GemMarketing in real-world practice settings.

Model Details

Developed by: Marketeam
Model type: Causal decoder-only transformer language model
Continue-pretrained from model: gemma-2b
Context length: 3K tokens
Input & Output: Text-only
Language: English
Knowledge Cutoff: December 2023

Uses

GemMarketing has been developed for further research of LLM for marketing applications.
The potential use cases for this tool are diverse and varied, ranging from marketing question answering to general marketing information queries, and actions (function-calls) on marketing platforms.

GemMarketing is a Foundation Language Model (FLM) without finetuning or instruction-tuning.
We recommend applying SFT or RLHF-tuned for specific downstream tasks. Or rather apply in-context learning with 1000-1500 tokens added to the prompt.

Training Details

Training Data

Marketing data from publicly available and internal sources such as:

Blogs
Books
Websites
Podcasts
Newsletters
Publications
Social Media
Ad-Campaigns
Landing Pages
Press Releases
Email-Campaigns
Brochures & Flyers
Product Description
Testimonials & Reviews
...
And ±10% of previously seen data to avoid catastrophic forgetting.

Training Procedure

Our training procedure includes using the AWS SageMaker framework, 4 NVIDIA A100 GPUs, p4de.24xlarge machine.
With a total train time of ±250 hours, with a total training cost of ±10K$.
This is an early checkpoint of the model that we are releasing to the community.

Training Hyperparameters

Param	Value
bf16	true
tf32	true
lr	1e-4
optim	adamw
epochs	1
lr scheduler	constant
warmup ratio	0.03
max grad norm	0.3
context lengt	3072
attention	SPDA

How to use

Using Transformers pipeline

import transformers
import torch

model_id = "marketeam/GemMarketing"
tokenizer_id = "google/gemma-2b"
token = "hf-token"

pipeline = transformers.pipeline("text-generation", model=model_id, model_kwargs={"torch_dtype": torch.bfloat16},
                                  tokenizer=tokenizer_id, token=token,  device_map='auto')

pipeline("What are the key components of a digital marketing strategy?")

Using Transformers generate

from transformers import AutoTokenizer, AutoModelForCausalLM
import torch

model_id = "marketeam/GemMarketing"
tokenizer_id = "google/gemma-2b"
token = "hf_token"
device = "cuda" if torch.cuda.is_available() else "cpu"

tokenizer = AutoTokenizer.from_pretrained(tokenizer_id, token=token)
model = AutoModelForCausalLM.from_pretrained(
    model_id, torch_dtype=torch.bfloat16, token=token).to(device)

message = "How do I calculate customer lifetime value?"
inputs = tokenizer(message, return_tensors="pt").to(device)
outputs = model.generate(**inputs)
tokenizer.batch_decode(outputs, skip_special_tokens=True)

Intended Usage

GemMarketing is now available for further testing and assessment. Potential use cases include, but are not limited to:

Text Generation: This model can produce creative text formats in the marketing domain.
Knowledge Exploration: It can assist marketing researchers by generating valuable marketing information or answering questions about marketing-specific topics.
Natural Language Processing (NLP) Research: This model can form the basis for researchers to experiment with NLP techniques, develop algorithms, and contribute to the advancement of the field.

Contributers

Sahar Millis Coby Benveniste Nofar Sachs Eran Mazur