This model is a fine-tuned version of Google's T5-Base model tailored for summarizing financial 10K report sections. T5-Base-10K-Summarization is optimized to condense lengthy 10K reports into manageable summaries, enabling quick insights into financial data and trends. Ideal for use by financial analysts and regulatory agencies needing rapid insights from 10K reports. It may not be suited for summarizing non-financial documents or informal texts. Trained on a diverse collection of 10K reports from various industries, annotated for summarization to ensure broad applicability and accuracy. The following hyperparameters were used during training: - learningrate: 5e-05 - trainbatchsize: 8…
Finetuned ai-forever/ruT5-base for text and dialogue summarization. All 'train' subsets was concatenated and shuffled with seed 1000 - 7. Train subset = 155678 rows. Evaluation on 10% of concatenated 'validation' subsets = 1458 rows. See WandB logs.
Parameters223M
Context—
Weights1.8 GB
License—
AccessOpen weights
Monthly Downloads27.9k
Runs On
What it takes to serve rut5-base-summ (223M parameters): the memory its weights need at each precision, and the cheapest way to rent enough data-center GPUs to hold them.
| Precision | Weights | Memory needed | Cheapest setup | Per hour | Also fits |
|---|---|---|---|---|---|
| 16-bit | 0.4 GB | 0.5 GB | 1x MI300X (192 GB) Vultr |
$1.85 | 1x H100 $1.99 · 1x MI325X $2.00 |
| 8-bit | 0.2 GB | 0.3 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.
Model Card
Finetuned ai-forever/ruT5-base for text and dialogue summarization. All 'train' subsets was concatenated and shuffled with seed 1000 - 7. Train subset = 155678 rows. Evaluation on 10% of concatenated 'validation' subsets = 1458 rows. See WandB logs. See report at REPORT WIP.
Excerpt from the card by Dmitry Balobin.
Configuration
- Architecture
- T5ForConditionalGeneration
- Vocabulary size
- 32,128
- Stored precision
- float32
- Model type
- t5
Identity and Version
- Repository
- d0rj/rut5-base-summ
- Publisher
- Dmitry Balobin
- Task
- Summarization
- Modality
- Text
- Library
- transformers
- Parameters
- 223M parameters
- Languages
- ru, en
- Revision
- 118f9052c668b37cf07d3c1839d4416f8972821a
- First published
- 2023-06-21
- Last updated
- 2023-10-05
Files and Weights
15 files, 1.8 GB in total. The weights are 6 files totalling 1.8 GB in bin, pt, pth, safetensors.
Weights6 files · 1.8 GB
Configuration4 files · 135.7 KB
Tokenizer3 files · 3.6 MB
Documentation1 file · 13.4 KB
Repository1 file · 1.5 KB
Every file
| File | Type | Size | SHA-256 |
|---|---|---|---|
| model.safetensors | Weights | 891.6 MB | fcce1e8d3ad4 |
| optimizer.pt | Weights | 2.1 MB | dd9ff5210e46 |
| pytorch_model.bin | Weights | 891.7 MB | bafa4d4fad62 |
| rng_state.pth | Weights | 14.5 KB | 58808399e58d |
| scheduler.pt | Weights | 623 B | c947b15af77a |
| training_args.bin | Weights | 4.0 KB | 79b3ae325469 |
| config.json | Configuration | 1.6 KB | — |
| generation_config.json | Configuration | 206 B | — |
| special_tokens_map.json | Configuration | 2.2 KB | — |
| trainer_state.json | Configuration | 131.7 KB | — |
| README.md | Documentation | 13.4 KB | — |
| .gitattributes | Repository | 1.5 KB | — |
| spiece.model | Tokenizer | 1.0 MB | 7a4eb8701144 |
| tokenizer.json | Tokenizer | 2.6 MB | — |
| tokenizer_config.json | Tokenizer | 2.4 KB | — |
License and Download
- License
- Not stated by the source
- Access
- Open weights, no gate
- Download size
- 1.8 GB
Download from Dmitry Balobin
Released by Dmitry Balobin through its official repository on Hugging Face.
Built From
- Trained on (disclosed) GEM/wiki_lingua
- Trained on (disclosed) IlyaGusev/gazeta
- Trained on (disclosed) d0rj/samsum-ru
- Trained on (disclosed) mlsum
- Trained on (disclosed) rcp-meetings/rudialogsum_v2
- Trained on (disclosed) zjkarina/matreshka
Evaluations
Each result is shown as reported, with the conditions its reporter stated. None is a SAVRN measurement. A comparison lines two results up only when their configuration, unit and setup are all stated and identical.
| Benchmark | Conditions | Result | Reported by | Revision | Date |
|---|---|---|---|---|---|
| samsum | Configuration samsumTask SummarizationMetric ROUGE-1Comparison conditions not established | 28.8694 | d0rj Publisher reported |
Evaluated revision not stated | — |
| samsum | Configuration samsumTask SummarizationMetric ROUGE-2Comparison conditions not established | 8.4686 | d0rj Publisher reported |
Evaluated revision not stated | — |
| samsum | Configuration samsumTask SummarizationMetric ROUGE-LComparison conditions not established | 24.2357 | d0rj Publisher reported |
Evaluated revision not stated | — |
| samsum | Configuration samsumTask SummarizationMetric ROUGE-LSUMComparison conditions not established | 25.8543 | d0rj Publisher reported |
Evaluated revision not stated | — |
| samsum | Configuration samsumTask SummarizationMetric gen_lenComparison conditions not established | 27.5543 | d0rj Publisher reported |
Evaluated revision not stated | — |
| samsum | Configuration samsumTask SummarizationMetric lossComparison conditions not established | 3.2456 | d0rj Publisher reported |
Evaluated revision not stated | — |
| xsum | Configuration defaultTask SummarizationMetric ROUGE-1Comparison conditions not established | 16.1279 | d0rj Publisher reported |
Evaluated revision not stated | — |
| xsum | Configuration defaultTask SummarizationMetric ROUGE-2Comparison conditions not established | 2.1128 | d0rj Publisher reported |
Evaluated revision not stated | — |
| xsum | Configuration defaultTask SummarizationMetric ROUGE-LComparison conditions not established | 12.2033 | d0rj Publisher reported |
Evaluated revision not stated | — |
| xsum | Configuration defaultTask SummarizationMetric ROUGE-LSUMComparison conditions not established | 12.4127 | d0rj Publisher reported |
Evaluated revision not stated | — |
| xsum | Configuration defaultTask SummarizationMetric gen_lenComparison conditions not established | 39.2258 | d0rj Publisher reported |
Evaluated revision not stated | — |
| xsum | Configuration defaultTask SummarizationMetric lossComparison conditions not established | 4.57575 | d0rj Publisher reported |
Evaluated revision not stated | — |
Memory Requirements
| Precision | Weights in memory |
|---|---|
| As published | 1.8 GB |
| 16-bit | 0.4 GB |
| 8-bit | 0.2 GB |
| 4-bit | 0.1 GB |
Weights only, from the published parameter count; the key-value cache and runtime add to this.
Questions About rut5-base-summ
How much GPU memory does rut5-base-summ need?
About 0.5 GB at 16-bit and 0.1 GB at 4-bit: the weights (223M parameters) plus a working margin. A long context needs more.
What is the cheapest GPU to run rut5-base-summ 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.
Similar Models
PTT5 Summ is a fine-tuned PTT5 model to perform Abstractive Summarization in Brazilian Portuguese texts. This model was fine-tuned on the datasets: RecognaSumm, WikiLingua, XL-Sum, TeMário.pdf) and CSTNews. For further information, please go to PTT5 Summ repository.
PTT5 Summ is a fine-tuned PTT5 model to perform Abstractive Summarization in Brazilian Portuguese texts. This model was fine-tuned on the datasets: RecognaSumm, WikiLingua, XL-Sum, TeMário.pdf) and CSTNews. For further information, please go to PTT5 Summ repository. author="Paiola, Pedro H. and de Rosa, Gustavo H. and Papa, Jo{\~a}o P.", editor="Xavier-Junior, Jo{\~a}o Carlos and Rios, Ricardo Ara{\'u}jo", title="Deep Learning-Based Abstractive Summarization for Brazilian Portuguese Texts", booktitle="BRACIS 2022: Intelligent Systems", year="2022", publisher="Springer International Publishing", address="Cham", pages="479--493", isbn="978-3-031-21689-3"} This model was fine-tuned using the…
The Longformer Encoder-Decoder (LED) for Narrative-Esque Long Text Summarization is a model I fine-tuned from allenai/led-base-16384 to condense extensive technical, academic, and narrative content in a fairly generalizable way. - Ideal for summarizing long narratives, articles, papers, textbooks, and other documents. - the sparknotes-esque style leads to 'explanations' in the summarized content, offering insightful output. The model was trained on the BookSum dataset released by SalesForce, which leads to the bsd-3-clause license. The training process involved 16 epochs with parameters tweaked to facilitate very fine-tuning-type training (super low learning rate). This model is the…
Imagine you have a very long news article, and you want someone to read it and tell you the key points in just a few sentences. That's exactly what this model does! This model takes a long news article and turns it into a short, easy-to-read summary. - It writes back a 3-4 sentence summary that captures all the important information The special thing about this model is that it's: 1. Very accurate - It understands news writing style very well 2. Very fast - It works quickly even on regular computers (not just expensive AI servers) 3. Specialized in news - It was trained specifically on news articles, so it understands how journalists write 4. Good with financial news - It knows market…
이 모델은 kobart모델을 문서요약, 도서자료요약, 요약문 및 레포트 생성 데이터로 fine-tuning한 모델입니다.