SAVRN
Search Contact SAVRN

Open-weight model

sentiment-analysis-fine-tuned-model

by Alsgyu alsgyu/sentiment-analysis-fine-tuned-model

이 모델은 AI 허브 한국어 감정 데이터셋을 활용하여 Hugging Face의 beomi/KcBERT-base 모델을 파인튜닝한 감정 분석 모델입니다. 한국어 텍스트의 감정을 긍정, 부정, 중립 등으로 분류할 수 있도록 설계되었습니다. 이 모델은 고객 리뷰 분석, 소셜 미디어 모니터링, 감정적 맥락 이해 등 다양한 한국어 기반 응용 프로그램에서 활용할 수 있습니다.

Parameters109M
Context300
Weights435.7 MB
License
AccessOpen weights
Monthly Downloads727.8k

Runs On

What it takes to serve sentiment-analysis-fine-tuned-model (109M parameters): the memory its weights need at each precision, and the cheapest way to rent enough data-center GPUs to hold them.

PrecisionWeightsMemory neededCheapest setupPer hourAlso fits
16-bit 0.2 GB 0.3 GB 1x MI300X (192 GB)
Vultr
$1.85 1x H100 $1.99 · 1x MI325X $2.00
8-bit 0.1 GB 0.1 GB 1x MI300X (192 GB)
Vultr
$1.85 1x H100 $1.99 · 1x MI325X $2.00
4-bit 0.1 GB 0.1 GB 1x MI300X (192 GB)
Vultr
$1.85 1x H100 $1.99 · 1x MI325X $2.00

Memory is the weights at that precision plus 20% for the runtime and a short context; a long context needs more. Prices are the lowest on-demand hourly rates in the SAVRN Index, read Sep 18, 2026.

SAVRN's Notes on sentiment-analysis-fine-tuned-model

Korean-language sentiment classification is the whole job here: the publisher fine-tuned beomi/KcBERT-base on an AI Hub Korean emotion dataset so it sorts Korean text into positive, negative and neutral, for review analysis and social media monitoring. With 109M parameters, memory stops being a question. Sixteen-bit weights take 0.2 GB and need 0.3 GB in total; 8-bit and 4-bit each land at 0.1 GB. The cheapest setup we list, one MI300X with 192 GB at $1.85 an hour on demand, is far more card than this needs, so the sizing decision is how many copies to pack onto one GPU.

The license field is blank, though the publisher's summary says the model and training code follow MIT. We would confirm that in writing before a commercial deployment. Note the 300-token context too, which means longer text has to be chunked upstream, and the 437 MB download stored in float32.

Model Card

이 모델은 AI 허브 한국어 감정 데이터셋을 활용하여 Hugging Face의 beomi/KcBERT-base 모델을 파인튜닝한 감정 분석 모델입니다. 한국어 텍스트의 감정을 긍정, 부정, 중립 등으로 분류할 수 있도록 설계되었습니다. 이 모델은 고객 리뷰 분석, 소셜 미디어 모니터링, 감정적 맥락 이해 등 다양한 한국어 기반 응용 프로그램에서 활용할 수 있습니다. 기반 모델: beomi/KcBERT-base 프레임워크: Hugging Face Transformers 모델의 파인튜닝 과정은 Jupyter Notebook을 활용하여 수행되었습니다. 관련 코드는 아래 GitHub 링크에서 확인할 수 있습니다. 이 모델과 학습 코드는 MIT 라이센스를 따릅니다. 자유롭게 사용, 수정 및 배포할 수 있습니다. GitHub Issues를 통해 문제를 보고하거나, Pull Request를 통해 기여해 주세요.

Excerpt from the card by Alsgyu.

Configuration

Architecture
BertForSequenceClassification
Context length (tokens)
300
Layers
12
Hidden size
768
Feed-forward size
3,072
Attention heads
12
Vocabulary size
30,000
Stored precision
float32
Model type
bert

Identity and Version

Repository
alsgyu/sentiment-analysis-fine-tuned-model
Publisher
Alsgyu
Task
Not stated by the source
Modality
Other
Library
Not stated by the source
Parameters
109M parameters
Languages
Not stated by the source
Revision
e4e595bde60a2c04b86ce5476bd70802ca7c7892
First published
2024-12-03
Last updated
2024-12-10

Files and Weights

9 files, 436.7 MB in total. The weights are 1 file totalling 435.7 MB in safetensors.

Weights1 file · 435.7 MB
Configuration3 files · 2.2 KB
Tokenizer3 files · 972.9 KB
Documentation1 file · 2.0 KB
Repository1 file · 1.5 KB
Every file
FileTypeSizeSHA-256
model.safetensorsWeights435.7 MB f6d752c97c88
.ipynb_checkpoints/config-checkpoint.jsonConfiguration1.0 KB
config.jsonConfiguration1.0 KB
special_tokens_map.jsonConfiguration125 B
README.mdDocumentation2.0 KB
.gitattributesRepository1.5 KB
tokenizer.jsonTokenizer721.7 KB
tokenizer_config.jsonTokenizer1.2 KB
vocab.txtTokenizer249.9 KB

License and Download

License
Not stated by the source
Access
Open weights, no gate
Download size
435.7 MB
Download from Alsgyu

Released by Alsgyu through its official repository on Hugging Face.

Memory Requirements

PrecisionWeights in memory
As published435.7 MB
16-bit0.2 GB
8-bit0.1 GB
4-bit0.1 GB

Weights only, from the published parameter count; the key-value cache and runtime add to this.

Questions About sentiment-analysis-fine-tuned-model

How much GPU memory does sentiment-analysis-fine-tuned-model need?

About 0.3 GB at 16-bit and 0.1 GB at 4-bit: the weights (109M parameters) plus a working margin. A long context needs more.

What is the cheapest GPU to run sentiment-analysis-fine-tuned-model on?

At 16-bit, 1x MI300X from $1.85 an hour; at 4-bit, 1x MI300X from $1.85 an hour, at the lowest on-demand prices the SAVRN Index lists.

What is sentiment-analysis-fine-tuned-model's context length?

300 tokens, from the maximum position embeddings in its published configuration.