We explore supervised multitask pre-training by proposing Instruction Pre-Training, a framework that scalably augments massive raw corpora with instruction-response pairs to pre-train language models. The instruction-response pairs are generated by an efficient instruction synthesizer built on open-source models. Instruction Pre-Training outperforms Vanilla Pre-training in both general pre-training from scratch and domain-adaptive continual pre-training. In pre-training from scratch, Instruction Pre-Training not only improves pre-trained base models but also benefits more from further instruction tuning. In continual pre-training, Instruction Pre-Training enables Llama3-8B to be comparable to or even outperform Llama3-70B.

Resources

🤗 We share our data and models with example usages, feel free to open any issues or discussions! 🤗

Context-Based Instruction Synthesizer: instruction-synthesizer
Fine-Tuning Data for the Synthesizer: ft-instruction-synthesizer-collection
General Models Pre-Trained from Scratch:
- InstructLM-500M
- InstructLM-1.3B
Domain-Specific Models Pre-Trained from Llama3-8B:
- Finance-Llama3-8B
- Biomedicine-Llama3-8B

Domain-Adaptive Continued Pre-Training

Following AdaptLLM, we augment the domain-specific raw corpora with instruction-response pairs generated by our context-based instruction synthesizer.

For example, to chat with the biomedicine-Llama3-8B model:

python

from transformers import AutoModelForCausalLM, AutoTokenizer

model = AutoModelForCausalLM.from_pretrained("instruction-pretrain/medicine-Llama3-8B")
tokenizer = AutoTokenizer.from_pretrained("instruction-pretrain/medicine-Llama3-8B")

# Put your input here, NO prompt template is required
user_input = '''Question: Which of the following is an example of monosomy?
Options:
- 46,XX
- 47,XXX
- 69,XYY
- 45,X

Please provide your choice first and then provide explanations if possible.'''

inputs = tokenizer(user_input, return_tensors="pt", add_special_tokens=True).input_ids.to(model.device)
outputs = model.generate(input_ids=inputs, max_new_tokens=400)[0]

answer_start = int(inputs.shape[-1])
pred = tokenizer.decode(outputs[answer_start:], skip_special_tokens=True)

print(pred)

Model Citation

If you find our work helpful, please cite us:

AdaptLLM

bibtex

@inproceedings{
cheng2024adapting,
title={Adapting Large Language Models via Reading Comprehension},
author={Daixuan Cheng and Shaohan Huang and Furu Wei},
booktitle={The Twelfth International Conference on Learning Representations},
year={2024},
url={https://openreview.net/forum?id=y886UXPEZ0}
}