LLM Reference

LLaVA Llama 2 13B

Released
2023-04-17
Last refreshed
2026-04-19
Status
Researched 198d ago
Open weightsCommercial use: non-commercial

LLaVA Llama 2 13B is released 2023-04-17 in the LLaVA family with open-weight; evaluate it while provider pricing coverage matures.

Use it for

  • Teams evaluating general LLM work

Do not use it for

  • Cost-sensitive launches that need sourced token pricing
  • Vision or document-understanding workloads
  • Strict JSON or tool-calling flows
Specifications
Family
LLaVA
Released
2023-04-17
Parameters
13B
Architecture
Decoder Only
Knowledge cutoff
2023-01
Specialization
general
Openness
Open weights
License
CC-BY-NC-4.0Commercial use: non-commercial
Weights
Unknown
Code
Unknown
Training
Fine-tuned
Created by

Academic researcher focused on vision models

N/A
Founded N/A
Website
Pricing

No tracked provider token pricing is available yet.

About

LLaVA (Large Language and Vision Assistant) Llama 2 13B is an open-source multimodal chatbot model that leverages the transformer architecture to process and integrate sequential data like text and images. It is a fine-tuned version of the LLaMA 2 language model, trained on a substantial dataset of image-text pairs and GPT-generated multimodal instruction-following data. The model's architecture features a vision encoder (CLIP ViT-L/14) for images and a language model (Vicuna) for text, connected by a projection matrix. LLaVA excels in open-ended conversations, visual reasoning tasks, and can synergize with other models like GPT-4 for complex tasks. It underwent a two-stage training process to align features and fine-tune for tasks, achieving state-of-the-art results in some benchmarks, though it may face challenges in reasoning and factual precision.

LLaVA Llama 2 13B is an open-weight model in the LLaVA family. No headline benchmark score is tracked for LLaVA Llama 2 13B yet.

Top use-case fit

No primary decision-task fit is mapped for this model yet.

Provider price ladder

No tracked provider token pricing is available for this model yet.

Capabilities

No model capability flags are currently sourced.

Benchmark peer barsfor Coding

No task-mapped benchmark peers are available for this model yet.

Migration checks

No linked migration route is available for this model yet.

Frequently asked questions

When was LLaVA Llama 2 13B released?

LLaVA Llama 2 13B was released on 2023-04-17.