Downloads · 30 days
18
21% of all-time downloads
vinod-anbalagan/Llama-3.2-3B-marketing-spend-revenue-qa
Llama-3.2-3B-marketing-spend-revenue-qa is a text generation model from vinod-anbalagan. Use it when you need the model to write or continue text. It is set up for peft. The card lists the license as llama3.2.
A LoRA adapter for meta-llama/Llama-3.2-3B-Instruct, fine-tuned for marketing-analytics question answering: reading values from marketing reports (spend, revenue, conversions, funnels), multi-step numeric reasoning ov…
Downloads · 30 days
18
21% of all-time downloads
All-time downloads
85
Public
Repo size
212 MB
Likes
3
Public
Click a slice to open those files.
.safetensors195 MB · 92%
From the Hugging Face model README
A LoRA adapter for meta-llama/Llama-3.2-3B-Instruct, fine-tuned for marketing-analytics question answering: reading values from marketing reports (spend, revenue, conversions, funnels), multi-step numeric reasoning over tables, and abstaining when a figure isn't present.
Trained with Adaption's AutoScientist on the Marketing Spend & Revenue QA dataset, built for the Adaption AutoScientist Challenge.
Built with Llama. This is a LoRA adapter, not a full model — you load it on top of the base
meta-llama/Llama-3.2-3B-Instruct(a gated model; you must accept its license on HuggingFace to download it).
Evaluated head-to-head against the base model (AutoScientist LLM-judge win rate):
| Win rate | |
|---|---|
| Adapted (this model) | 88% |
| Base (Llama-3.2-3B-Instruct) | 12% |
A note on interpreting this honestly: win rate is measured against the base, so it reflects headroom. The same dataset trained on a much stronger base (gpt-oss-120B) scored ~50/50 — that base already handles marketing table-QA well. The lift is largest on a small base with room to learn, which is exactly the case here.
Training converged cleanly: final train loss 0.194, eval loss 0.214 (3 epochs, 63 steps), with validation tracking training throughout (no overfitting).
import torch
from transformers import AutoModelForCausalLM, AutoTokenizer
from peft import PeftModel
base = "meta-llama/Llama-3.2-3B-Instruct"
adapter = "vinod-anbalagan/Llama-3.2-3B-marketing-spend-revenue-qa" # <-- your repo id
tok = AutoTokenizer.from_pretrained(base)
model = AutoModelForCausalLM.from_pretrained(base, torch_dtype=torch.bfloat16, device_map="auto")
model = PeftModel.from_pretrained(model, adapter)
messages = [{
"role": "user",
"content": (
"Spend by Channel per Quarter:\n"
"| Period | Organic | Email | Social |\n"
"| Q1 | 3994.79 | 9872.95 | 13609.10 |\n"
"| Q2 | 4587.38 | 14868.86 | 8737.85 |\n\n"
"For Social, what is the Spend in Q1?"
),
}]
inputs = tok.apply_chat_template(messages, add_generation_prompt=True, return_tensors="pt").to(model.device)
out = model.generate(inputs, max_new_tokens=256, do_sample=False)
print(tok.decode(out[0][inputs.shape[-1]:], skip_special_tokens=True))
To merge the adapter into the base for standalone deployment:
merged = model.merge_and_unload()
merged.save_pretrained("Llama-3.2-3B-marketing-merged")
train_on_inputs=falseMarketing Spend & Revenue QA — 8,600 table-grounded marketing-QA rows with verified answers and reasoning traces, across 13 reasoning types (lookups, multi-step compute, funnel diagnostics, cross-panel dashboard reasoning, and an explicit abstention class).
This adapter is released under the Llama 3.2 Community License (inherited from the base model). Review Meta's license terms before use or redistribution.
@misc{anbalagan2026marketinglora,
title = {Llama-3.2-3B Marketing Spend & Revenue QA (LoRA)},
author = {Anbalagan, Vinod},
year = {2026},
howpublished = {\url{https://huggingface.co/vinod-anbalagan/Llama-3.2-3B-marketing-spend-revenue-qa}},
note = {Trained via Adaption AutoScientist for the AutoScientist Challenge}
}