Instructions to use itay1itzhak/T5-Tulu-Seed-2 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use itay1itzhak/T5-Tulu-Seed-2 with Transformers:

# Use a pipeline as a high-level helper
from transformers import pipeline

pipe = pipeline("text-generation", model="itay1itzhak/T5-Tulu-Seed-2")

# Load model directly
from transformers import AutoTokenizer, AutoModelForSeq2SeqLM

tokenizer = AutoTokenizer.from_pretrained("itay1itzhak/T5-Tulu-Seed-2")
model = AutoModelForSeq2SeqLM.from_pretrained("itay1itzhak/T5-Tulu-Seed-2")

Notebooks
Google Colab
Kaggle
Local Apps

vLLM

How to use itay1itzhak/T5-Tulu-Seed-2 with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "itay1itzhak/T5-Tulu-Seed-2"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "itay1itzhak/T5-Tulu-Seed-2",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/itay1itzhak/T5-Tulu-Seed-2

SGLang

How to use itay1itzhak/T5-Tulu-Seed-2 with SGLang:

Install from pip and serve model

# Install SGLang from pip:
pip install sglang
# Start the SGLang server:
python3 -m sglang.launch_server \
    --model-path "itay1itzhak/T5-Tulu-Seed-2" \
    --host 0.0.0.0 \
    --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "itay1itzhak/T5-Tulu-Seed-2",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker images

docker run --gpus all \
    --shm-size 32g \
    -p 30000:30000 \
    -v ~/.cache/huggingface:/root/.cache/huggingface \
    --env "HF_TOKEN=<secret>" \
    --ipc=host \
    lmsysorg/sglang:latest \
    python3 -m sglang.launch_server \
        --model-path "itay1itzhak/T5-Tulu-Seed-2" \
        --host 0.0.0.0 \
        --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "itay1itzhak/T5-Tulu-Seed-2",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use itay1itzhak/T5-Tulu-Seed-2 with Docker Model Runner:
```
docker model run hf.co/itay1itzhak/T5-Tulu-Seed-2
```
Browse Quantizations to use this model in llama.cpp, Ollama, LM Studio, or any compatible app.

Model Card for T5-Tulu

Model Details

Model Description
This 🤗 Transformers model was finetuned using LoRA adapters for the paper:
"Planted in Pretraining, Swayed by Finetuning: A Case Study on the Origins of Cognitive Biases in LLMs" (Hugging Face Paper, arXiv) 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: encoder-decoder based transformer
Language(s): English
License: Apache 2.0
Finetuned from: google/t5-v1_1-xxl
Paper: https://arxiv.org/abs/2507.07186
Project Page: https://itay1itzhak.github.io/planted-in-pretraining
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/T5-Tulu-Seed-2")
tokenizer = AutoTokenizer.from_pretrained("itay1itzhak/T5-Tulu-Seed-2")

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: T5-11B
Instruction dataset: Tulu-2

Citation

@misc{itzhak2025plantedpretrainingswayedfinetuning,
      title={Planted in Pretraining, Swayed by Finetuning: A Case Study on the Origins of Cognitive Biases in LLMs}, 
      author={Itay Itzhak and Yonatan Belinkov and Gabriel Stanovsky},
      year={2025},
      eprint={2507.07186},
      archivePrefix={arXiv},
      primaryClass={cs.CL},
      url={https://arxiv.org/abs/2507.07186}, 
}