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 GPTQ by TheBloke

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

  217   
  4-bit   Autotrain compatible Base model:liuhaotian/llava-v1... Base model:quantized:liuhaotia...   Gptq   Llama   Quantized   Region:us   Safetensors
Model Card on HF 🤗: https://huggingface.co/TheBloke/llava-v1.5-13B-GPTQ 

Llava V1.5 13B GPTQ Benchmarks

LLME Score: 0.14673
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 GPTQ (TheBloke/llava-v1.5-13B-GPTQ)

Llava V1.5 13B GPTQ Parameters and Internals

Model Type 
llama
Use Cases 
Areas:
research
Applications:
chatbots, large multimodal models
Primary Use Cases:
computer vision, natural language processing, machine learning, AI research
Additional Notes 
Quantization performed by TheBloke with GPTQ for varying hardware requirements.
Training Details 
Data Sources:
LAION/CC/SBU, BLIP, GPT-generated multimodal instruction-following data, academic-task-oriented VQA data, ShareGPT
Data Volume:
558K filtered image-text pairs, 158K GPT-generated data, 450K VQA data, 40K ShareGPT
Model Architecture:
Auto-regressive, Transformer architecture
LLM NameLlava V1.5 13B GPTQ
Repository 🤗https://huggingface.co/TheBloke/llava-v1.5-13B-GPTQ 
Model NameLlava v1.5 13B
Model CreatorHaotian Liu
Base Model(s)  liuhaotian/llava-v1.5-13b   liuhaotian/llava-v1.5-13b
Model Size13b
Required VRAM7.3 GB
Updated2025-02-05
MaintainerTheBloke
Model Typellama
Model Files  7.3 GB
GPTQ QuantizationYes
Quantization Typegptq
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 GPTQ

Best Alternatives
Context / RAM
Downloads
Likes
Yarn Llama 2 13B 128K GPTQ128K / 7.3 GB1616
LongAlign 13B 64K GPTQ64K / 7.3 GB211
...boros L2 13B 2 1 YaRN 64K GPTQ64K / 7.3 GB183
Yarn Llama 2 13B 64K GPTQ64K / 7.3 GB101
OrcaMaid V3 13B 32K GPTQ32K / 7.3 GB293
OrcaMaid V2 FIX 13B 32K GPTQ32K / 7.3 GB174
EverythingLM 13B 16K GPTQ16K / 7.3 GB1713
Tinybra 13B GPTQ 32g 4BIT16K / 8 GB61
Tinybra 13B GPTQ 4BIT16K / 7 GB70
WhiteRabbitNeo 13B GPTQ16K / 7.3 GB114
Note: green Score (e.g. "73.2") means that the model is better than TheBloke/llava-v1.5-13B-GPTQ.

Rank the Llava V1.5 13B GPTQ 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