LLM EXPLORER
 LLM Explorer: A Curated Large Language Model Directory and Analytics
Dark Theme
  LLM  List    LLM Hosting    LLM Leaderboards    Blog    Newsfeed    Advertise

Llava V1.5 13B Shard3gb by liuhaotian

 »  All LLMs  »  liuhaotian  »  Llava V1.5 13B Shard3gb   URL Share it on

  7   
  Autotrain compatible   Llava   Pytorch   Region:us   Sharded
Model Card on HF 🤗: https://huggingface.co/liuhaotian/llava-v1.5-13b-shard3gb 

Llava V1.5 13B Shard3gb Benchmarks

LLME Score: 0.1149
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 Shard3gb (liuhaotian/llava-v1.5-13b-shard3gb)
🌟 Advertise your project 🚀

Llava V1.5 13B Shard3gb Parameters and Internals

Model Type 
open-source chatbot, auto-regressive language model, transformer architecture, multimodal
Use Cases 
Areas:
large multimodal models, chatbots
Primary Use Cases:
research on large multimodal models, chatbots
Additional Notes 
This is the same model checkpoint as [liuhaotian/llava-v1.5-13b], sharded with a 3GB per-shard size limit to support machines with limited CPU RAM.
Training Details 
Data Sources:
LAION/CC/SBU, BLIP captioned datasets, GPT-generated data, academic-task-oriented VQA data, ShareGPT
Methodology:
trained by fine-tuning LLaMA/Vicuna on GPT-generated multimodal instruction-following data
Model Architecture:
transformer
LLM NameLlava V1.5 13B Shard3gb
Repository 🤗https://huggingface.co/liuhaotian/llava-v1.5-13b-shard3gb 
Model Size13b
Required VRAM26.2 GB
Updated2025-09-23
Maintainerliuhaotian
Model Typellava
Model Files  3.0 GB: 1-of-9   2.9 GB: 2-of-9   2.9 GB: 3-of-9   3.0 GB: 4-of-9   2.9 GB: 5-of-9   3.0 GB: 6-of-9   2.9 GB: 7-of-9   2.9 GB: 8-of-9   2.7 GB: 9-of-9
Model ArchitectureLlavaLlamaForCausalLM
Context Length4096
Model Max Length4096
Transformers Version4.31.0
Tokenizer ClassLlamaTokenizer
Beginning of Sentence Token<s>
End of Sentence Token</s>
Unk Token<unk>
Vocabulary Size32000
Torch Data Typefloat16

Best Alternatives to Llava V1.5 13B Shard3gb

Best Alternatives
Context / RAM
Downloads
Likes
Llava V1.5 13B4K / 26 GB54184514
Llava V1.6 Vicuna 13B4K / 26.7 GB950658
Evalalign V1.0 13B4K / 26.7 GB61
Table Llava V1.5 13B4K / 26.6 GB101
Peenoblanc 52 Llava4K / 26.7 GB60
Otterchecker4K / 26.7 GB52
Llava 13B Custom4K / 26.7 GB50
V Mllm 13B4K / 26.6 GB91
...roduct Taxonomy Llava V1.6 13B4K / 26.7 GB70
Posterllava V04K / 26.6 GB307
Note: green Score (e.g. "73.2") means that the model is better than liuhaotian/llava-v1.5-13b-shard3gb.

Rank the Llava V1.5 13B Shard3gb Capabilities

🆘 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! 🌟

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? 51535 in total.

Email us: info@extractum.io. Our Privacy Policy  | Terms and Conditions  | Suggest an improvement.
Our Social Media →  
Original data from HuggingFace, OpenCompass and various public git repos.
Release v20241124
  Support LLM Explorer