Model Card for SciLitLLM-7B

SciLitLLM-7B adapts a general large language model for effective scientific literature understanding. Starting from the Qwen2-7B model, SciLitLLM-7B goes through a hybrid strategy that integrates continual pre-training (CPT) and supervised fine-tuning (SFT), to simultaneously infuse scientific domain knowledge and enhance instruction-following capabilities for domain-specific tasks.

In this process, we identify two key challenges: (1) constructing high-quality CPT corpora, and (2) generating diverse SFT instructions. We address these challenges through a meticulous pipeline, including PDF text extraction, parsing content error correction, quality filtering, and synthetic instruction creation.

Applying this strategy, we present SciLitLLM-7B, specialized in scientific literature understanding, which demonstrates promising performance on scientific literature understanding benchmarks. Specifically, it shows an average performance improvement of 3.6% on SciAssess and 10.1% on SciRIFF compared to leading LLMs with fewer than 15B parameters.

See the paper for more details and github for data processing codes.

Requirements

Since SciLitLLM is based on Qwen2, we advise you to install transformers>=4.37.0, or you might encounter the following error:

KeyError: 'qwen2'

Quickstart

Here provides a code snippet with apply_chat_template to show you how to load the tokenizer and model and how to generate contents.

from transformers import AutoModelForCausalLM, AutoTokenizer
device = "cuda" # the device to load the model onto

model = AutoModelForCausalLM.from_pretrained(
    "Uni-SMART/SciLitLLM",
    torch_dtype="auto",
    device_map="auto"
)
tokenizer = AutoTokenizer.from_pretrained("Uni-SMART/SciLitLLM")

prompt = "Can you summarize this article for me?\n <ARTICLE>"
messages = [
    {"role": "system", "content": "You are a helpful assistant."},
    {"role": "user", "content": prompt}
]
text = tokenizer.apply_chat_template(
    messages,
    tokenize=False,
    add_generation_prompt=True
)
model_inputs = tokenizer([text], return_tensors="pt").to(device)

generated_ids = model.generate(
    model_inputs.input_ids,
    max_new_tokens=512
)
generated_ids = [
    output_ids[len(input_ids):] for input_ids, output_ids in zip(model_inputs.input_ids, generated_ids)
]

response = tokenizer.batch_decode(generated_ids, skip_special_tokens=True)[0]

Citation

If you find our work helpful, feel free to give us a cite.

@misc{li2024scilitllmadaptllmsscientific,
      title={SciLitLLM: How to Adapt LLMs for Scientific Literature Understanding}, 
      author={Sihang Li and Jin Huang and Jiaxi Zhuang and Yaorui Shi and Xiaochen Cai and Mingjun Xu and Xiang Wang and Linfeng Zhang and Guolin Ke and Hengxing Cai},
      year={2024},
      eprint={2408.15545},
      archivePrefix={arXiv},
      primaryClass={cs.LG},
      url={https://arxiv.org/abs/2408.15545}, 
}