FINAR-VL

Open-source financial multimodal LLM for document understanding, chart/table reasoning, numerical reasoning, and financial analysis, with SFT, dual-branch RL, MOPD distillation, and public benchmark evaluation.

dlgjr/FINAR-VL

View on GitHub ↗

Open-source financial multimodal LLM for document understanding, chart/table reasoning, numerical reasoning, and financial analysis, with SFT, dual-branch RL, MOPD distillation, and public benchmark evaluation.

FINAR-VL grew +0.0% in the last 30 days, ranks 58th of 60 in Vision & Multimodal Models, last commit 56 days ago.

Star trajectory

61 days tracked
2026-09-21102 stars today2026-11-22
Momentum

+0.0% in 30d, below the Vision & Multimodal Models median of +0.1%.

Maintenance

Last commit 56 days ago, fresher than the median of 393.5d.

How it compares in Vision & Multimodal Models

FINAR-VL
102
stars
+0.0% 30d
commit 56 days ago
Vision & Multimodal Models median
888.5
stars
+0.1% 30d
commit ~393.5d ago
Leader · DALLE2-pytorch
11.3k
stars
+0.0% 30d
commit 924 days ago

Ranked 58th of 60 by stars.

Ranked by shared tags, then keywords, then stars

Where FINAR-VL sits

Hover or focus a node for details. Click to open it.

  • This repo
  • Related repo
  • Tag or category
  1. Pretrained model hub for Keras 3.

    +3 (+0.3%) in 30d · Committed today · Python · Apache-2.0

    Shares Vision & Multimodal Models, Domain-Specific Models

  2. 基于Stable Diffusion优化的AI绘画模型。支持输入中英文文本,可生成多种现代艺术风格的高质量图像。| An optimized text-to-image model based on Stable…

    +0 (+0.0%) in 30d · Committed 1,354d ago · MIT

    Shares Vision & Multimodal Models, Domain-Specific Models

  3. DuplexJev-32B and DuplexJev-4B: speech decision models for full-duplex voice agents. Typed single-token…

    Committed 14d ago · Python · Apache-2.0

    Shares Vision & Multimodal Models, Domain-Specific Models

  4. T2F: text to face generation using Deep Learning

    -1 (-0.2%) in 30d · Committed 1,652d ago · Python · MIT

    Shares Vision & Multimodal Models, Domain-Specific Models

  5. Official implementation of "En3D: An Enhanced Generative Model for Sculpting 3D Humans from 2D Synthetic…

    +0 (+0.0%) in 30d · Committed 726d ago · Python · Apache-2.0

    Shares Vision & Multimodal Models, Domain-Specific Models

  6. [SIGGRAPH Asia 2026 (TOG)] PartLLM: A Unified Multimodal Foundation for 3D Part Segmentation

    +45 (+38%) in 30d · Committed 8d ago · Python · Apache-2.0

    Shares Vision & Multimodal Models, Domain-Specific Models

  7. Official PyTorch implementation of the paper "Deep Constrained Least Squares for Blind Image…

    +2 (+0.8%) in 30d · Committed 1,288d ago · Python · MIT

    Shares Vision & Multimodal Models, Domain-Specific Models

  8. JevStyle: local decision models for AI agents. Classify, route and score with a probability per option…

    Committed 17d ago · Python · Apache-2.0

    Shares Vision & Multimodal Models, Domain-Specific Models

  9. FinGLM: 致力于构建一个开放的、公益的、持久的金融大模型项目,利用开源开放来促进「AI+金融」。

    +2 (+0.1%) in 30d · Committed 927d ago · HTML

    Shares Domain-Specific Models

  10. Committed 19d ago · Python · MIT

    Shares Vision & Multimodal Models

Language
Python
License
-
Contributors
1
Forks
1
Watchers
0
Open issues
0
Releases
0
Created
2026-07-26
Stars this week
+0

You've seen where FINAR-VL stands today.

Get the moves before everyone else: the 5 Vision & Multimodal Models repos climbing fastest, every Tuesday.

Free weekly digest. Double opt-in, unsubscribe anytime.

Maintain FINAR-VL?

Claim this page to add your own call-to-action.

Claim this page