---
license: gemma
datasets:
- allenai/scicite
language:
- en
metrics:
- f1
base_model:
- google/gemma-3-27b-it
pipeline_tag: text-generation
library_name: transformers
tags:
- scientometrics
- citation_analysis
- citation_intent_classification
---

## Llamacpp imatrix Quantizations of Gemma3-12B-CIC-SciCite-GGUF

Using <a href="https://github.com/ggerganov/llama.cpp/">llama.cpp</a> for quantization.

Original model: https://huggingface.co/sknow-lab/Gemma3-12B-CIC-SciCite

## Prompt format

```
<bos><start_of_turn>user
{system_prompt}

{prompt}<end_of_turn>
<start_of_turn>model
<end_of_turn>
<start_of_turn>model
```


# Citation

```
@misc{koloveas2025llmspredictcitationintent,
      title={Can LLMs Predict Citation Intent? An Experimental Analysis of In-context Learning and Fine-tuning on Open LLMs}, 
      author={Paris Koloveas and Serafeim Chatzopoulos and Thanasis Vergoulis and Christos Tryfonopoulos},
      year={2025},
      eprint={2502.14561},
      archivePrefix={arXiv},
      primaryClass={cs.CL},
      url={https://arxiv.org/abs/2502.14561}, 
}
```