Skip to content

EthenEthenEthen

LoginPlatformTry Ethen

Open Source Model Profile · ECNU-SEA

SEA-E

SEA-E is a 7.24B-parameter Mistral text-generation fine-tune from ECNU-SEA. Its model card documents SFT from Mistral-7B-Instruct-v0.2 for automated peer review.

Publisher
ECNU-SEA
Task
text-generation
Model type
mistral
License
apache-2.0
Library
transformers
Publication status
Accepted · not indexed

Model overview

SEA-E is published by ECNU-SEA as a conversational text-generation model for automated peer reviewing. The captured configuration identifies MistralForCausalLM with a mistral model type, and Safetensors metadata reports 7241732096 parameters. According to the model card, it uses Mistral-7B-Instruct-v0.2 as backbone with supervised fine-tuning on a peer-review instruction dataset.

Recorded capabilities

7.24B Mistral scale

Captured config identifies MistralForCausalLM and Safetensors metadata reports 7241732096 parameters.

Mistral-7B-Instruct-v0.2 backbone

According to the model card, SEA-E derives from Mistral-7B-Instruct-v0.2 through supervised fine-tuning.

Peer-review instruction data

The model card says fine-tuning used a high-quality peer-review instruction dataset standardized through the SEA-S model.

EMNLP 2024 paper context

According to the model card, the SEA work on standardization, evaluation, and analysis was accepted by EMNLP 2024.

Use cases in the source record

  • Draft peer-review feedback for submitted papers, as described in the publisher card.
  • Peer-review instruction experiments using the card's chat-template generation example with up to 8192 new tokens.

Limitations and unknowns

  • No evaluation results were extracted from this record.
  • No context-window value was extracted from this record.
  • Provider state is historical snapshot data, not independently refreshed current availability.
  • Training and effectiveness claims come from the publisher card and linked paper context and have not been independently verified by Ethen.

Source and provenance

Source: ECNU-SEA/SEA-E

Captured: Unknown. Processed: 2026-09-07T19:34:30.514203+00:00.

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 EMNLP 2024 ! 🔥🔥🔥 We have made SEA series models (7B) public ! Model Description The SEA-E model utilizes Mistral-7B-Instruct-v0.2 as its backbone. It is derived by performing supervised fine-tuning (SFT) on a high-quality peer review instruction dataset, standardized through the SEA-S model. This model can provide comprehensive and insightful review feedback for submitted papers! Review Paper With SEA-E from transformers import Aut…

F001F002F003F004F005F006F007F008F009F010F011F013F014F015