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 AWQ by TheBloke

 »  All LLMs  »  TheBloke  »  Llava V1.5 13B AWQ   URL Share it on

  118   
  4-bit   Autotrain compatible   Awq Base model:liuhaotian/llava-v1... Base model:quantized:liuhaotia...   Llama   Quantized   Region:us   Safetensors
Model Card on HF 🤗: https://huggingface.co/TheBloke/llava-v1.5-13B-AWQ 

Llava V1.5 13B AWQ Benchmarks

LLME Score: 0.14435
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 AWQ (TheBloke/llava-v1.5-13B-AWQ)

Llava V1.5 13B AWQ Parameters and Internals

Model Type 
llama
Use Cases 
Areas:
research
Primary Use Cases:
Research on large multimodal models and chatbots
Considerations:
Model primarily intended for researchers and hobbyists in computer vision, NLP, ML, and AI
Training Details 
Data Sources:
558K filtered image-text pairs, 158K GPT-generated multimodal instruction-following data, 450K academic-task-oriented VQA data mixture, 40K ShareGPT data
Methodology:
Fine-tuning LLaMA/Vicuna on GPT-generated multimodal instruction-following data
Model Architecture:
Transformer architecture
Input Output 
Input Format:
{prompt}
LLM NameLlava V1.5 13B AWQ
Repository 🤗https://huggingface.co/TheBloke/llava-v1.5-13B-AWQ 
Model NameLlava v1.5 13B
Model CreatorHaotian Liu
Base Model(s)  liuhaotian/llava-v1.5-13b   liuhaotian/llava-v1.5-13b
Model Size13b
Required VRAM7.2 GB
Updated2025-02-05
MaintainerTheBloke
Model Typellama
Model Files  7.2 GB
AWQ QuantizationYes
Quantization Typeawq
Model ArchitectureLlamaForCausalLM
Licensellama2
Context Length4096
Model Max Length4096
Transformers Version4.34.0
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 AWQ

Best Alternatives
Context / RAM
Downloads
Likes
Yarn Llama 2 13B 128K AWQ128K / 7.2 GB72
LongAlign 13B 64K AWQ64K / 7.2 GB212
...oboros L2 13B 2 1 YaRN 64K AWQ64K / 7.2 GB72
OrcaMaid V3 13B 32K AWQ32K / 7.2 GB114
OrcaMaid V2 FIX 13B 32K AWQ32K / 7.2 GB61
NexusRaven V2 13B AWQ16K / 7.2 GB113
NexusRaven V2 13B AWQ16K / 7.2 GB63
...th CodeLlama 13B Python Hf AWQ16K / 7.5 GB760
WhiteRabbitNeo 13B AWQ16K / 7.2 GB84
NexusRaven V2 13B AWQ16K / 7.2 GB141
Note: green Score (e.g. "73.2") means that the model is better than TheBloke/llava-v1.5-13B-AWQ.

Rank the Llava V1.5 13B AWQ 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? 42577 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 v20241227
  Support LLM Explorer