Llava V1.5 13B Lora by liuhaotian

 ยป  All LLMs  ยป  liuhaotian  ยป  Llava V1.5 13B Lora   URL Share it on

  Autotrain compatible   Image-text-to-text   Llava   Lora   Region:us

Llava V1.5 13B Lora Benchmarks

nn.n% — How the model compares to the reference models: Anthropic Sonnet 3.5 ("so35"), GPT-4o ("gpt4o") or GPT-4 ("gpt4").
Llava V1.5 13B Lora (liuhaotian/llava-v1.5-13b-lora)

Llava V1.5 13B Lora Parameters and Internals

Model Type 
chatbot, multimodal, auto-regressive, transformer
Use Cases 
Areas:
research
Primary Use Cases:
Research on large multimodal models and chatbots.
Training Details 
Data Sources:
LAION/CC/SBU - 558K filtered image-text pairs, captioned by BLIP, GPT-generated multimodal instruction-following data - 158K, Academic-task-oriented VQA data mixture - 450K, ShareGPT data - 40K
Model Architecture:
transformer
LLM NameLlava V1.5 13B Lora
Repository ๐Ÿค—https://huggingface.co/liuhaotian/llava-v1.5-13b-lora 
Model Size13b
Required VRAM0.1 GB
Updated2025-02-22
Maintainerliuhaotian
Model Files  1.0 GB   0.1 GB
Model ArchitectureAutoModelForCausalLM
Is Biasednone
PEFT TypeLORA
LoRA ModelYes
PEFT Target Modulesq_proj|down_proj|o_proj|gate_proj|v_proj|up_proj|k_proj
LoRA Alpha256
LoRA Dropout0.05
R Param128

Best Alternatives to Llava V1.5 13B Lora

Best Alternatives
Context / RAM
Downloads
Likes
ALMA 13B R0K / 26 GB824680
...ama2 13B No Robots Alpaca Lora0K / 4 GB192610
Llava V1.5 13B S2 Lora0K / 0.1 GB542
Llama 2 13B Chat Hf GPT 4 80K0K / 26 GB2770
Ko En Llama2 13B Finetune Ex0K / 26 GB24050
Ko En Llama2 13B Finetune0K / 26 GB24450
Ko Llama2 13B Finetune Ex0K / 26 GB19610
Llava Chart 13b Lora0K / 0.1 GB102
ChartLlama 13B0K / 0.1 GB35119
Llama 2 13B Longlora 64K0K / 0.1 GB178310
Note: green Score (e.g. "73.2") means that the model is better than liuhaotian/llava-v1.5-13b-lora.

Rank the Llava V1.5 13B Lora Capabilities

๐Ÿ†˜ Have you tried this model? Rate its performance. This feedback would greatly assist ML community in identifying the most suitable model for their needs. Your contribution really does make a difference! ๐ŸŒŸ

Instruction Following and Task Automation  
Factuality and Completeness of Knowledge  
Censorship and Alignment  
Data Analysis and Insight Generation  
Text Generation  
Text Summarization and Feature Extraction  
Code Generation  
Multi-Language Support and Translation  

What open-source LLMs or SLMs are you in search of? 43470 in total.

Our Social Media →  
Original data from HuggingFace, OpenCompass and various public git repos.
Release v20241227