itay1itzhak/OLMo-Tulu-Seed-0

Model Card for OLMo-Tulu

Model Details

Model Description
This 🤗 Transformers model was finetuned using LoRA adapters for the arXiv paper:
"Planted in Pretraining, Swayed by Finetuning: A Case Study on the Origins of Cognitive Biases in LLMs"
We study whether cognitive biases in LLMs emerge from pretraining, instruction tuning, or training randomness. This is one of 3 identical versions trained with different random seeds.

• Model type: Causal decoder-based transformer
• Language(s): English
• License: Apache 2.0
• Finetuned from: allenai/OLMo-7B
• Paper: https://arxiv.org/abs/2507.XXXXX
• Repository: https://github.com/itay1itzhak/planted-in-pretraining

Uses

Direct Use

For research on cognitive biases in LLMs. Used to test causal impact of pretraining vs instruction tuning.

Out-of-Scope Use

Do not use in production, sensitive domains, or decision-critical applications.

How to Get Started with the Model

from transformers import AutoModelForCausalLM, AutoTokenizer

model = AutoModelForCausalLM.from_pretrained("itay1itzhak/OLMo-Tulu-Seed-0")
tokenizer = AutoTokenizer.from_pretrained("itay1itzhak/OLMo-Tulu-Seed-0")

inputs = tokenizer("Example input?", return_tensors="pt")
outputs = model.generate(**inputs)
print(tokenizer.decode(outputs[0]))

Training Details

• Finetuning method: LoRA (high-rank, rank ∈ [64, 512])
• Instruction data: Tulu-2
• Seeds: 3 per setting to evaluate randomness effects
• Batch size: 128 (OLMo) / 64 (T5)
• Learning rate: 1e-6 to 1e-3
• Steps: ~5.5k (OLMo) / ~16k (T5)
• Mixed precision: fp16 (OLMo) / bf16 (T5)

Evaluation

• Evaluated on 32 cognitive biases from Itzhak et al. (2024) and Malberg et al. (2024)
• Metrics: mean bias score, PCA clustering, MMLU accuracy
• Findings: Biases primarily originate in pretraining; randomness introduces moderate variation

Environmental Impact

• Hardware: 4× NVIDIA A40
• Estimated time: ~120 GPU hours/model

Technical Specifications

• Architecture: OLMo 7B
• Instruction dataset: Tulu-2