# finbert by Prosus AI: Open-Weight Model Source: https://savrn.com/models/finbert Markdown alternate of the page above; the site index is https://savrn.com/llms.txt --- ## Runs On What it takes to serve finbert (109M 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 | 0.2 GB | 0.3 GB | 1x [MI300X](https://savrn.com/ai-index/pricing/gpus/mi300x) (192 GB) Vultr | $1.85 | [1x H100](https://savrn.com/ai-index/pricing/gpus/h100) $1.99 · [1x MI325X](https://savrn.com/ai-index/pricing/gpus/mi325x) $2.00 | | 8-bit | 0.1 GB | 0.1 GB | 1x [MI300X](https://savrn.com/ai-index/pricing/gpus/mi300x) (192 GB) Vultr | $1.85 | [1x H100](https://savrn.com/ai-index/pricing/gpus/h100) $1.99 · [1x MI325X](https://savrn.com/ai-index/pricing/gpus/mi325x) $2.00 | | 4-bit | 0.1 GB | 0.1 GB | 1x [MI300X](https://savrn.com/ai-index/pricing/gpus/mi300x) (192 GB) Vultr | $1.85 | [1x H100](https://savrn.com/ai-index/pricing/gpus/h100) $1.99 · [1x MI325X](https://savrn.com/ai-index/pricing/gpus/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](https://savrn.com/ai-index/pricing/gpus), read Oct 23, 2026. [finbert on every accelerator the SAVRN Index prices, at every precision](https://savrn.com/models/finbert/gpus) ## SAVRN's Notes on finbert Three labels, positive, negative or neutral, on a passage of at most 512 tokens: that is the whole job. The page carries no memory figure, and with 12 layers and a 768 hidden size the sizing conversation is throughput, how many 512-token windows per second you need scored. The download is 1.3 GB across 9 files covering pytorch, jax and tf copies, so one framework loads a fraction of that. The part that stops a deployment: the license field on this page is empty, so there are no terms to read and a buyer has to get them from Prosus AI before any commercial use. Beyond that, respect the 512-token ceiling, since longer documents get chunked and scored in pieces, and know where the labels come from: continued BERT training on financial text and fine-tuning on Financial PhraseBank, described in arXiv:1908.10063. SAVRN Research, 2026-09-18 ## Model Card FinBERT is a pre-trained NLP model to analyze sentiment of financial text. It is built by further training the BERT language model in the finance domain, using a large financial corpus and thereby fine-tuning it for financial sentiment classification. Financial PhraseBank by Malo et al. (2014) is used for fine-tuning. For more details, please see the paper FinBERT: Financial Sentiment Analysis with Pre-trained Language Models and our related blog post on Medium. The model will give softmax outputs for three labels: positive, negative or neutral. To get the scores for all three labels, pass topk=None to the classifier. This model was trained using the Financial PhraseBank dataset: The… Excerpt from the card by Prosus AI, licensed cc-by-nc-sa-4.0. ## Configuration Architecture BertForSequenceClassification Context length (tokens) 512 Layers 12 Hidden size 768 Feed-forward size 3,072 Attention heads 12 Vocabulary size 30,522 Model type bert ## Identity and Version Repository ProsusAI/finbert Publisher Prosus AI Task Text classification Modality Text Library transformers Parameters 109M parameters Languages en Revision 0bc2ac10dda6929bcb1f77ccc43c7ec5c424f031 First published 2022-03-02 Last updated 2026-10-12 ## Files and Weights 10 files, 1.8 GB in total. The weights are 4 files totalling 1.8 GB in bin, h5, msgpack, safetensors. Weights4 files · 1.8 GB Configuration2 files · 870 B Tokenizer2 files · 231.8 KB Documentation1 file · 4.6 KB Repository1 file · 445 B Every file | File | Type | Size | SHA-256 | | --- | --- | --- | --- | | flax_model.msgpack | Weights | 437.9 MB | 04c231ff252c | | model.safetensors | Weights | 438.0 MB | e5897858ff81 | | pytorch_model.bin | Weights | 438.0 MB | e15a7b5738df | | tf_model.h5 | Weights | 438.2 MB | 195e23248e2e | | config.json | Configuration | 758 B | — | | special_tokens_map.json | Configuration | 112 B | — | | README.md | Documentation | 4.6 KB | — | | .gitattributes | Repository | 445 B | — | | tokenizer_config.json | Tokenizer | 252 B | — | | vocab.txt | Tokenizer | 231.5 KB | — | ## License and Download License cc-by-nc-sa-4.0 Access Open weights, no gate Download size 1.8 GB [Download from Prosus AI](https://huggingface.co/ProsusAI/finbert) Released by Prosus AI through its official repository on Hugging Face. ## Built From - Described by arXiv:1908.10063 ## Memory Requirements | Precision | Weights in memory | | --- | --- | | As published | 1.8 GB | | 16-bit | 0.2 GB | | 8-bit | 0.1 GB | | 4-bit | 0.1 GB | Weights only, from the published parameter count; the key-value cache and runtime add to this. ## Built on This Model - Quantized from[finbert-GGUF](https://savrn.com/models/finbert-gguf) - Derived from[finbert-GGUF](https://savrn.com/models/finbert-gguf) - Adapter of[finbert-crypto-stock-news-sentiment](https://savrn.com/models/finbert-crypto-stock-news-sentiment) - Derived from[finbert-crypto-stock-news-sentiment](https://savrn.com/models/finbert-crypto-stock-news-sentiment) ## Questions About finbert ### How much GPU memory does finbert 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 finbert 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. ### Can I use finbert commercially? Not without separate permission. finbert is released under Creative Commons Attribution-NonCommercial-ShareAlike 4.0. CC BY-NC-SA 4.0 permits non-commercial sharing and adapting with credit, and requires adaptations to use the same license. Commercial use needs separate permission. ### What is finbert's context length? 512 tokens, from the maximum position embeddings in its published configuration. ## Similar Models Model · Text classification ### [topic-classification-bert](https://savrn.com/models/topic-classification-bert) [KC](https://savrn.com/model-publishers/karencardiel) This model was fine-tuned on the AG News dataset (fancyzhx/agnews) for four-class news topic classification: The dataset was divided into 108,000 training examples, 12,000 validation examples, and 7,600 test examples. A random seed of 42 was used. This model is intended for English news topic classification into the four AG News categories: World, Sports, Business, and Sci/Tech. It was developed for educational purposes and experimentation with BERT adaptation methods. The model is trained on English news data and may not generalize well to other domains or languages. It only supports the four categories present in AG News. Performance on real-world data may differ from the reported… Open weights 109M parameters 512 tokens transformers [View model](https://savrn.com/models/topic-classification-bert) Model · Text classification ### [bert-base-agnews-topic-classification](https://savrn.com/models/bert-base-agnews-topic-classification) [Dalila Ku](https://savrn.com/model-publishers/dalila-ku) Full fine-tuning of bert-base-uncased for 4-class news topic classification, delivered as part of assignment U2T01 (Adapting BERT for NLP tasks — Trends in Data Science, Unit 2, Universidad Politécnica de Yucatán). bert-base-uncased with a linear classification head on top of the [CLS] token's last hidden state, mapping to 4 topic classes: World, Sports, Business, Sci/Tech. - 10% of the official train split was held out as validation; the official test split was left untouched. - 4 balanced classes. Two adaptation methods were trained and compared; full fine-tuning is the delivered model, since it beat the feature-based baseline by a margin well above the run-to-run noise floor (±1–3 points… Open weights apache-2.0 109M parameters 512 tokens [View model](https://savrn.com/models/bert-base-agnews-topic-classification) Model · Text classification ### [ft-agnews](https://savrn.com/models/ft-agnews) [Dalila Ku](https://savrn.com/model-publishers/dalila-ku) This model is a fine-tuned version of bert-base-uncased on an unknown dataset. It achieves the following results on the evaluation set: The following hyperparameters were used during training: - learningrate: 5e-05 - trainbatchsize: 32 - evalbatchsize: 64 - lrschedulertype: linear - numepochs: 2 - Transformers 5.16.1 - Pytorch 2.11.0+cu128 - Datasets 4.8.5 - Tokenizers 0.23.1 Open weights apache-2.0 109M parameters 512 tokens transformers [View model](https://savrn.com/models/ft-agnews) Model · Text classification ### [multi-domain-sentiment-bert](https://savrn.com/models/multi-domain-sentiment-bert) [ADITYA GUPTA](https://savrn.com/model-publishers/adityagupta-data) This is the model card of a transformers model that has been pushed on the Hub. Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. Use the code below to get started with the model. Carbon emissions can be estimated using the Machine Learning Impact calculator presented in Lacoste et al. (2019). Open weights 109M parameters 512 tokens transformers [View model](https://savrn.com/models/multi-domain-sentiment-bert) Model · Text classification ### [assign5autotrain](https://savrn.com/models/assign5autotrain) [Harsha B Setty](https://savrn.com/model-publishers/harshab1983) libraryname: transformers - autotrain - text-classification basemodel: google-bert/bert-base-uncased f1macro: 0.7533020080884588 f1micro: 0.7533333333333333 f1weighted: 0.7533020080884587 precisionmacro: 0.7551310982162045 precisionmicro: 0.7533333333333333 precisionweighted: 0.7551310982162046 recallmacro: 0.7533333333333333 recallmicro: 0.7533333333333333 recallweighted: 0.7533333333333333 Open weights 109M parameters 512 tokens transformers [View model](https://savrn.com/models/assign5autotrain) Model · Text classification ### [bert-log-anomaly-detection](https://savrn.com/models/bert-log-anomaly-detection) [Aungruk Vanichanai](https://savrn.com/model-publishers/aungmoonlord) 1. bert-log-anomaly-detection is a BERT-based NLP model fine-tuned for single SQL transaction log anomaly detection. 2. The model classifies each database transaction log as either Normal or Anomaly, with the goal of supporting AI-powered fraud detection and cybersecurity monitoring systems. 3. This model was developed as part of the Samsung × KBTG Digital Fraud Cybersecurity Hackathon (Thailand) under the AI-Powered Fraud Detection & Prevention track. This model analyzes individual SQL database transaction logs and detects abnormal patterns that may indicate fraudulent, malicious, or suspicious behavior. - Developed by Waris Sripatoomrak, this model integrates with an n8n workflow to… Open weights apache-2.0 109M parameters 512 tokens transformers [View model](https://savrn.com/models/bert-log-anomaly-detection) ## Prosus AI [All models and datasets](https://savrn.com/model-publishers/prosusai) ## Versions - [0bc2ac10dda6](https://savrn.com/models/finbert/versions/0bc2ac10dda6) · current 2026-10-23 - [4556d1301521](https://savrn.com/models/finbert/versions/4556d1301521) 2026-10-12 ## Explore More - [All text classification models](https://savrn.com/models/tasks/text-classification) - [All models under cc-by-nc-sa-4.0](https://savrn.com/models/licenses/cc-by-nc-sa-4-0) - [Model comparisons](https://savrn.com/models/comparisons) - [The model directory](https://savrn.com/models) - [Open model prices by host](https://savrn.com/ai-index/pricing/open-models) ## Source - Repository metadata, read 2026-10-13. - [Hugging Face record](https://huggingface.co/ProsusAI/finbert) - [How the hub is built](https://savrn.com/model-hub/methodology)