FoundationVision/groma_instruct

Dataset

Groma Instruct contains 30k visually grounded conversations for instruction finetuning, which is the first grounded chat dataset constructed with both visual and textual prompts, leveraging the powerful GPT-4V for data generation.

8

4 commits

2 linked in READMEs

updated May 2, 2024

README

Groma Instruct contains 30k visually grounded conversations for instruction finetuning, which is the first grounded chat dataset constructed with both visual and textual prompts, leveraging the powerful GPT-4V for data generation. For more information about this dataset and its usage, please take a look at our paper and github page.

Contributors

4 commits

Similar repos

X2FD/LVIS-Instruct4V

**LVIS-Instruct4V**:

85

WaltonFuture/InstructionGPT-4

InstructionGPT-4: A 200-Instruction Paradigm for Fine-Tuning MiniGPT-4

4

SALT-NLP/LLaVAR

LLaVAR Data: Enhanced Visual Instruction Data with Text-Rich Images

22

yaodongC/awesome-instruction-dataset

A collection of open-source dataset to train instruction-following LLMs (ChatGPT,LLaMA,Alpaca)

1,153

LLaVA-VL/llava-plus-data

LLaVA-Plus Instructed Dataset Card

36

Chat-UniVi/Chat-UniVi-Instruct

Chat-UniVi: Unified Visual Representation Empowers Large Language Models with Image and Video…

8

teknium/GPTeacher-General-Instruct

GPTeacher General-Instruct dataset is GPT-4 Generated self-instruct dataset.

45

kaiyuyue/llava-1.5-665k-genqa-500k-instructions

LLaVA-1.5-665K-GenQA-Random-500K

0

Linked in READMEs

FoundationVision/Groma

[ECCV2024] Grounded Multimodal Large Language Model with Localized Visual Tokenization

586

friedrichor/Awesome-Multimodal-Papers

A curated list of awesome Multimodal studies.

346

FoundationVision/groma_instruct

Dataset

Groma Instruct contains 30k visually grounded conversations for instruction finetuning, which is the first grounded chat dataset constructed with both visual and textual prompts, leveraging the powerful GPT-4V for data generation.

8

4 commits

2 linked in READMEs

updated May 2, 2024

README

Groma Instruct contains 30k visually grounded conversations for instruction finetuning, which is the first grounded chat dataset constructed with both visual and textual prompts, leveraging the powerful GPT-4V for data generation. For more information about this dataset and its usage, please take a look at our paper and github page.

Similar repos

X2FD/LVIS-Instruct4V

**LVIS-Instruct4V**:

85

WaltonFuture/InstructionGPT-4

InstructionGPT-4: A 200-Instruction Paradigm for Fine-Tuning MiniGPT-4

4

SALT-NLP/LLaVAR

LLaVAR Data: Enhanced Visual Instruction Data with Text-Rich Images

22

yaodongC/awesome-instruction-dataset

A collection of open-source dataset to train instruction-following LLMs (ChatGPT,LLaMA,Alpaca)

1,153

LLaVA-VL/llava-plus-data

LLaVA-Plus Instructed Dataset Card

36

Chat-UniVi/Chat-UniVi-Instruct

Chat-UniVi: Unified Visual Representation Empowers Large Language Models with Image and Video…

8

teknium/GPTeacher-General-Instruct

GPTeacher General-Instruct dataset is GPT-4 Generated self-instruct dataset.

45

kaiyuyue/llava-1.5-665k-genqa-500k-instructions

LLaVA-1.5-665K-GenQA-Random-500K

0

Linked in READMEs

FoundationVision/Groma

[ECCV2024] Grounded Multimodal Large Language Model with Localized Visual Tokenization

586

friedrichor/Awesome-Multimodal-Papers

A curated list of awesome Multimodal studies.

346

Contributors

4 commits