metadata

license: llama3
language:
  - en
tags:
  - finance
datasets:
  - Open-Orca/OpenOrca
  - GAIR/lima
  - WizardLM/WizardLM_evol_instruct_V2_196k

Instruction Pre-Training: Language Models are Supervised Multitask Learners

This repo contains the finance model developed from Llama3-8B in our paper Instruction Pre-Training: Language Models are Supervised Multitask Learners.

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.

**************************** Updates ****************************

2024/7/31: Updated pre-training suggestions in the Advanced Usage section of instruction-synthesizer
2024/7/15: We scaled up the pre-trained tokens from 100B to 250B, with the number of synthesized instruction-response pairs reaching 500M! Below, we show the performance trend on downstream tasks throughout the pre-training process:
2024/6/21: Released the paper, code, and resources

Resources

🤗 We share our data and models with example usages, feel free to open any discussions at this page! 🤗

Thanks to the demo davanstrien/instruction-synthesizer for implementing our approach
Context-Based Instruction Synthesizer: instruction-synthesizer
Fine-Tuning Data for the Synthesizer: ft-instruction-synthesizer-collection
General Models Pre-Trained from Scratch (on 100B tokes):
- InstructLM-500M
- InstructLM-1.3B
Domain-Specific Models Pre-Trained from Llama3-8B:
- Finance-Llama3-8B
- Biomedicine-Llama3-8B
General Instruction-Augmented Corpora: general-instruction-augmented-corpora
Domain-Specific Instruction-Augmented Corpora (no finance data to avoid ethical issues): medicine-instruction-augmented-corpora

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.

1. chat with the finance-Llama3-8B model:

from transformers import AutoModelForCausalLM, AutoTokenizer

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

# Put your input here, NO prompt template is required
user_input = '''Use this fact to answer the question: Title of each class Trading Symbol(s) Name of each exchange on which registered
Common Stock, Par Value $.01 Per Share MMM New York Stock Exchange
MMM Chicago Stock Exchange, Inc.
1.500% Notes due 2026 MMM26 New York Stock Exchange
1.750% Notes due 2030 MMM30 New York Stock Exchange
1.500% Notes due 2031 MMM31 New York Stock Exchange

Which debt securities are registered to trade on a national securities exchange under 3M's name as of Q2 of 2023?'''

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)

2. evaluate any Huggingface LMs on domain-dpecific tasks (💡New!)

You can use the following scripts to reproduce our results and evaluate any other Huggingface models on domain-specific tasks. Note that these scripts are not applicable to models that require specific prompt templates (e.g., Llama2-chat, Llama3-Instruct).

1). Set Up Dependencies

git clone https://github.com/microsoft/LMOps
cd LMOps/adaptllm
pip install -r requirements.txt

2). Evaluate the Model

# Select the domain from ['biomedicine', 'finance', 'law']
DOMAIN='finance'
  
# Specify any Huggingface LM name (Not applicable to models requiring specific prompt templates)
MODEL='instruction-pretrain/finance-Llama3-8B'
  
# Model parallelization:
# - Set MODEL_PARALLEL=False if the model fits on a single GPU. 
#   We observe that LMs smaller than 10B always meet this requirement.
# - Set MODEL_PARALLEL=True if the model is too large and encounters OOM on a single GPU.
MODEL_PARALLEL=False
  
# Choose the number of GPUs from [1, 2, 4, 8]
N_GPU=1
  
# Whether to add a BOS token at the beginning of the prompt input:
# - Set to False for AdaptLLM.
# - Set to True for instruction-pretrain models.
# If unsure, we recommend setting it to False, as this is suitable for most LMs.
add_bos_token=True

# Run the evaluation script
bash scripts/inference.sh ${DOMAIN} ${MODEL} ${add_bos_token} ${MODEL_PARALLEL} ${N_GPU}

Citation

If you find our work helpful, please cite us:

Instruction Pre-Training

@article{cheng2024instruction,
  title={Instruction Pre-Training: Language Models are Supervised Multitask Learners},
  author={Cheng, Daixuan and Gu, Yuxian and Huang, Shaohan and Bi, Junyu and Huang, Minlie and Wei, Furu},
  journal={arXiv preprint arXiv:2406.14491},
  year={2024}
}

Adapt LLM to Domains

@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}
}