# EvolvingLMMs-Lab/Otter

🦦 Otter, a multi-modal model based on OpenFlamingo (open-sourced version of DeepMind's Flamingo), trained on MIMIC-IT and showcasing improved instruction-following and in-context learning ability.

Repository: https://github.com/EvolvingLMMs-Lab/Otter
Canonical: https://ross.abutalabs.com/products/evolvinglmms-lab-otter
Homepage: https://otter-ntu.github.io/
Language: Python
License: MIT
License Family: permissive
Topics: gpt-4, visual-language-learning, artificial-inteligence, deep-learning, foundation-models, multi-modality, machine-learning, chatgpt, instruction-tuning, large-scale-models, embodied-ai
Last push: 2024-03-05T15:56:06+00:00

## Health v2 (maintenance only)
Score: 21/100 (v2, computed 2026-09-02T17:46:02.011165+00:00)
- activity 0, release rhythm 8, longevity 89
- inputs: {"age_days": 1250, "days_push": 911, "days_rel": null, "gap_med": null, "n_releases_24m": 0}
- flags: none
- formula: round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)

## Adoption (not part of the score)
Stars 3436, forks 209 (observed 2026-08-28T04:08:04.943974+00:00)

## What it is
Otter is a multi-modal vision-language model built on OpenFlamingo, instruction-tuned on the MIMIC-IT dataset with image and video understanding checkpoints. It includes training/fine-tuning scripts (e.g., OtterHD based on Fuyu-8B) and evaluation tooling for multimodal benchmarks.

## Use cases
- run a multimodal chatbot that understands images and video
- fine-tune a vision-language model on custom instruction data
- evaluate multimodal LLMs on benchmarks like MagnifierBench
- do in-context learning with interleaved image-text prompts
- fine-tune Fuyu-8B for high-resolution image understanding
- research instruction tuning for open multimodal foundation models

## When to choose
- you need an open-source multimodal model with released checkpoints you can run or fine-tune
- you want a research baseline for vision-language instruction tuning
- you need image or video understanding with in-context learning examples

## When to avoid
- you need a production-ready, polished product rather than research code
- you lack GPU resources for large 7B-8B parameter models
- you need the latest multimodal models rather than a 2023-era research artifact

## Facets
- artifact type: library
- maturity: maintenance
- function: machine-learning, deep-learning, llm-training, nlp, image-processing, video-processing, chatbot
- domain: large-language-models, deep-learning, artificial-intelligence, computer-vision
- platform: python
- tags: multimodal, vision-language-model, openflamingo, instruction-tuning, in-context-learning, foundation-models, mimic-it, fuyu, natural-language-processing, gpu, linux

## Member repositories
- EvolvingLMMs-Lab/Otter (main) score 21

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:08:04.943974+00:00.
- Health v2: computed from the inputs above; adoption is never an input.
- Inferred fields (summary, facets, guidance): AI-extracted, prompt v1, taxonomy v1, on 2026-08-29T18:37:41.456950+00:00, confidence not recorded.
  - readme: https://github.com/EvolvingLMMs-Lab/Otter (fetched 2026-08-28T04:08:04.943974+00:00, sha 2f2594b52ce7)
- Data as of 2026-08-30T08:39:29.467469+00:00.