You can deploy this model and start earning money today!

ratishsp/
tlm-illusion-adapters

Name: tlm-illusion-adapters
Availability: InStock

meta-llama/Meta-Llama-3-8B

adapter

llama3

Views

No views yet

TLM Illusion — Instruction-Tuned LoRA Adapters

LoRA adapters for the instruction-tuned control models in the paper "The Illusion of Generalization in Tabular Language Models" (ICML 2026).

Both are LoRA adapters (r=8, α=16) over meta-llama/Meta-Llama-3-8B, trained with torchtune.

Subfolder	Control	Training data
`alpaca/`	Alpaca	`yahma/alpaca-cleaned` only — general instruction-following, no tabular exposure
`alpaca-plus-q/`	Alpaca+Q	alpaca-cleaned plus quartile (binned-regression) tabular examples

These controls test whether Tabula-8B's reported gains reflect genuine tabular generalization or general instruction-following plus format familiarity.

Usage

python

from peft import PeftModel
from transformers import AutoModelForCausalLM

base = AutoModelForCausalLM.from_pretrained("meta-llama/Meta-Llama-3-8B")
model = PeftModel.from_pretrained(base, "ratishsp/tlm-illusion-adapters", subfolder="alpaca-plus-q")

ratishsp/tlm-illusion-adapters

TLM Illusion — Instruction-Tuned LoRA Adapters

Usage

Links

ratishsp/
tlm-illusion-adapters