financial-reports-analysis · azureml v1

**Description** The adapted AI model for financial reports analysis (preview) is a state\-of\-the\-art small language model (SLM) based on the Phi\-3\-small\-128k architecture, designed specifically …

azureFoundry/azureml/financial-reports-analysis@1

Description

The adapted AI model for financial reports analysis (preview) is a state-of-the-art small language model (SLM) based on the Phi-3-small-128k architecture, designed specifically for analyzing financial reports. It has been fine-tuned on a few hundred million tokens derived from instruction data over financial documents, including SEC filings (10-K, 10-Q, 8-K reports) and mathematical reasoning tasks.

The model is optimized to handle complex financial language and to understand data contained in tables, making it suitable for SEC report analysis, including data extraction, summarization, and common financial formulas. It can also perform more complex reasoning tasks, such as comparing companies and identifying trends across different time periods.

NOTE: This model is in preview

Model Architecture

The adapted AI model for financial reports analysis is a dense, decoder-only transformer model with 7B parameters, optimized for financial reports analysis

Specifications & capabilities

Input
text
Output
text

Provider specifications & access

1–1 / 1

financial-reports-analysis · azureml v1 ↗

source model id
azureml/financial-reports-analysis@1
hosting
foundry-managed-compute
platforms
  • Microsoft Foundry
license
mit
architecture
input_modalities
  • text
output_modalities
  • text
capabilities

    Original sources

    1–3 / 3

    Microsoft Foundry · Model page ↗

    Microsoft Foundry · Model documentation ↗

    Microsoft Foundry · Catalog ↗

    Source links

    1–1 / 1

    Explore more models

    Models

    Loading
    EVIDENCE / COMPARISON

    Benchmarks

    Explore every benchmark

    Loading

    These charts contain model-linked results. The charts above also include unlinked source profiles. Compare scores within each evaluation. Model quality, usage, transparency and system performance measure different things.

    Install TensorTrace