Skip to content

EthenEthenEthen

LoginPlatformTry Ethen

Open Source Model Profile · FinLang

finance-embeddings-investopedia

finance-embeddings-investopedia is a 109M-parameter BERT finance embedding from FinLang. Its model card documents 768-dimension vectors for RAG clustering and semantic search.

Publisher
FinLang
Task
sentence-similarity
Model type
bert
License
cc-by-nc-4.0
Library
sentence-transformers
Publication status
Accepted · not indexed

Model overview

finance-embeddings-investopedia is published by FinLang as a sentence-similarity embedding model. The captured configuration identifies BertModel with model type bert, and Safetensors metadata reports 109,482,240 parameters. According to the model card, it is finetuned on BAAI/bge-base-en-v1.5 with an Investopedia finance dataset, with cc-by-nc-4.0 recorded as the license.

Recorded capabilities

Finance embedding purpose

According to the model card, this is an Investopedia finance embedding trained on the FinLang investopedia-embedding dataset.

768-dimension vectors

The model card documents mapping sentences and paragraphs to a 768-dimensional dense vector space for clustering or semantic search.

BERT sentence-transformers record

Captured config identifies BertModel and bert with 109,482,240 parameters and sentence-transformers library support.

Research scope and usage notes

The model card states research-only use with third-party dataset terms, plus LlamaIndex and sentence-transformers usage examples.

Use cases in the source record

  • Financial RAG indexing with the documented LlamaIndex embedding workflow.
  • Clustering or semantic search over finance sentences and paragraphs with sentence-transformers.

Limitations and unknowns

  • No evaluation results, context-window value, or training hyperparameters were extracted.
  • According to the model card, this is research-only, a paper is forthcoming, and a v2 with a larger corpus is planned.
  • Provider state is historical snapshot data, not independently refreshed current availability.

Source and provenance

Source: FinLang/finance-embeddings-investopedia

Captured: Unknown. Processed: 2026-09-07T19:34:30.783067+00:00.

FinLang/finance-embeddings-investopedia This is the Investopedia embedding for finance application by the FinLang team. The model is trained using our open-sourced finance dataset from https://huggingface.co/datasets/FinLang/investopedia-embedding-dataset This is a finetuned embedding model on top of BAAI/bge-base-en-v1.5. It maps sentences & paragraphs to a 768 dimensional dense vector space and can be used for tasks like clustering or semantic search in RAG applications. This project is for research purposes only. Third-party datasets may be subject to additional terms and conditions under their associated licenses. Plans The rese…

F001F002F003F004F005F006F007F008F010F011F012F013F014F015F016