Downloads · 30 days
249
8% of all-time downloads
ECNU-SEA_-_SEA-S-gguf
RichardErkhov/ECNU-SEA_-_SEA-S-gguf
ECNU-SEA_-_SEA-S-gguf is a machine learning model from RichardErkhov. Use it for the machine learning task on the model card, and read the license before you ship it in a product.
All-time downloads
3.1K
Public
Repo size
82.2 GB
Likes
0
Public
Repo makeup
Click a slice to open those files.
.gguf95.2 GB · 100%
At a glance
- Access
- Public
- Created
- Apr 12, 2025
- Updated
- Apr 13, 2025
- SHA
- 9ce43efe
Model card
From the Hugging Face model README
Quantization made by Richard Erkhov.
SEA-S - GGUF
- Model creator: https://huggingface.co/ECNU-SEA/
- Original model: https://huggingface.co/ECNU-SEA/SEA-S/
| Name | Quant method | Size |
|---|---|---|
| SEA-S.Q2_K.gguf | Q2_K | 2.53GB |
| SEA-S.IQ3_XS.gguf | IQ3_XS | 2.81GB |
| SEA-S.IQ3_S.gguf | IQ3_S | 2.96GB |
| SEA-S.Q3_K_S.gguf | Q3_K_S | 2.95GB |
| SEA-S.IQ3_M.gguf | IQ3_M | 3.06GB |
| SEA-S.Q3_K.gguf | Q3_K | 3.28GB |
| SEA-S.Q3_K_M.gguf | Q3_K_M | 3.28GB |
| SEA-S.Q3_K_L.gguf | Q3_K_L | 3.56GB |
| SEA-S.IQ4_XS.gguf | IQ4_XS | 3.67GB |
| SEA-S.Q4_0.gguf | Q4_0 | 3.83GB |
| SEA-S.IQ4_NL.gguf | IQ4_NL | 3.87GB |
| SEA-S.Q4_K_S.gguf | Q4_K_S | 3.86GB |
| SEA-S.Q4_K.gguf | Q4_K | 4.07GB |
| SEA-S.Q4_K_M.gguf | Q4_K_M | 4.07GB |
| SEA-S.Q4_1.gguf | Q4_1 | 4.24GB |
| SEA-S.Q5_0.gguf | Q5_0 | 4.65GB |
| SEA-S.Q5_K_S.gguf | Q5_K_S | 4.65GB |
| SEA-S.Q5_K.gguf | Q5_K | 4.78GB |
| SEA-S.Q5_K_M.gguf | Q5_K_M | 4.78GB |
| SEA-S.Q5_1.gguf | Q5_1 | 5.07GB |
| SEA-S.Q6_K.gguf | Q6_K | 5.53GB |
| SEA-S.Q8_0.gguf | Q8_0 | 7.17GB |
Original model description:
license: apache-2.0 tags:
- Automated Peer Reviewing
- SFT datasets:
- ECNU-SEA/SEA_data
Automated Peer Reviewing in Paper SEA: Standardization, Evaluation, and Analysis
Paper Link: https://arxiv.org/abs/2407.12857
Project Page: https://ecnu-sea.github.io/
🔥 News
- 🔥🔥🔥 SEA is accepted by EMNLP2024 !
- 🔥🔥🔥 We have made SEA series models (7B) public !
Model Description
⚠️ This is the SEA-S model for content standardization, and the review model SEA-E can be found here.
The SEA-S model aims to integrate all reviews for each paper into one to eliminate redundancy and errors, focusing on the major advantages and disadvantages of the paper. Specifically, we first utilize GPT-4 to integrate multiple reviews of a paper into one (From ECNU-SEA/SEA_data) that is in a unified format and criterion with constructive contents, and form an instruction dataset for SFT. After that, we fine-tune Mistral-7B-Instruct-v0.2 to distill the knowledge of GPT-4. Therefore, SEA-S provides a novel paradigm for integrating peer review data in an unified format across various conferences.
@inproceedings{yu2024automated,
title={Automated Peer Reviewing in Paper SEA: Standardization, Evaluation, and Analysis},
author={Yu, Jianxiang and Ding, Zichen and Tan, Jiaqi and Luo, Kangyang and Weng, Zhenmin and Gong, Chenghua and Zeng, Long and Cui, RenJing and Han, Chengcheng and Sun, Qiushi and others},
booktitle={Findings of the Association for Computational Linguistics: EMNLP 2024},
pages={10164--10184},
year={2024}
}
- Created
- Apr 12, 2025
- Updated
- Apr 13, 2025