DataLearner logo
LL

LLaVA

Multimodal model

Large Language and Vision Assistant

Release date: 2023-04-17Updated: 2023-08-03 17:31:52.6711,080
Live demoGitHubHugging FaceCompare
Parameters
13B
Context length
2K
Chinese support
Not supported
Reasoning ability

Large Language and Vision Assistant is an AI model published by Microsoft Azure, released on 2023-04-17, for Multimodal model, with 13B parameters, and 2K context length, requiring about 26.1GB storage.

Data sourced primarily from official releases (GitHub, Hugging Face, papers), then benchmark leaderboards, then third-party evaluators. Learn about our data methodology

LLaVA

Model basics

Reasoning traces
Not supported
Thinking modes
Thinking modes not supported
Context length
2K tokens
Max output length
No data
Model type
Multimodal model
Modality (in / out)
No data
Release date
2023-04-17
Model file size
26.1GB
MoE architecture
No
Total params / Active params
13B / N/A
Knowledge cutoff
No data
LLaVA

Open source & experience

Code license
Apache 2.0
Weights license
Open source, non-commercial
GitHub repo
https://github.com/haotian-liu/LLaVA
Hugging Face
https://huggingface.co/liuhaotian/LLaVA-13b-delta-v0
Live demo
No live demo
LLaVA

Official resources

Paper
Paper
DataLearnerAI blog
No blog post yet
LLaVA

API details

API speed
No data
No public API pricing yet.
LLaVA

Benchmark Results

No benchmark data to show.

Compare with other models

No curated comparisons for this model yet.

Want a custom combination? Open the compare tool

LLaVA

Publisher

Large Language and Vision Assistant

Model Overview

Large Language and Vision Assistant is an AI model published by Microsoft Azure, released on 2023-04-17, for Multimodal model, with 13B parameters, and 2K context length, requiring about 26.1GB storage.

Foundation model

DataLearner on WeChat

Follow DataLearner on WeChat for AI model updates and research notes.

DataLearner WeChat QR code