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

Llava 13B V1.1 4bit 128g by Hyunel

 »  All LLMs  »  Hyunel  »  Llava 13B V1.1 4bit 128g   URL Share it on

  5   
  4bit   Autotrain compatible   Endpoints compatible   Llama   Quantized   Region:us
Model Card on HF 🤗: https://huggingface.co/Hyunel/llava-13b-v1-1-4bit-128g 

Llava 13B V1.1 4bit 128g Benchmarks

LLME Score: 0.10398
nn.n% — How the model compares to the reference models: Anthropic Sonnet 3.5 ("so35"), GPT-4o ("gpt4o") or GPT-4 ("gpt4").
Llava 13B V1.1 4bit 128g (Hyunel/llava-13b-v1-1-4bit-128g)

Llava 13B V1.1 4bit 128g Parameters and Internals

Model Type 
text generation
Additional Notes 
Model has been quantized to 4-bit using GPTQ for LLaMA CUDA branch with sequential true and group size of 128.
LLM NameLlava 13B V1.1 4bit 128g
Repository 🤗https://huggingface.co/Hyunel/llava-13b-v1-1-4bit-128g 
Model Size13b
Required VRAM7.5 GB
Updated2025-02-05
MaintainerHyunel
Model Typellama
Model Files  7.5 GB
Quantization Type4bit
Model ArchitectureLlavaLlamaForCausalLM
Licenseother
Context Length2048
Model Max Length2048
Transformers Version4.28.0.dev0
Tokenizer ClassLlamaTokenizer
Beginning of Sentence Token<s>
End of Sentence Token</s>
Unk Token<unk>
Vocabulary Size32003
Torch Data Typefloat16

Best Alternatives to Llava 13B V1.1 4bit 128g

Best Alternatives
Context / RAM
Downloads
Likes
Llava V1.5 13B EXL24K / 13.2 GB161
Llava V1.5 13B 4GB 8bit4K / 14.1 GB132
Llava V1.5 13B4K / 26 GB135410496
Llava V1.6 Vicuna 13B4K / 26.7 GB1437354
Llava CoS 13B4K / 26.6 GB62271
Evalalign V1.0 13B4K / 26.7 GB881
Table Llava V1.5 13B4K / 26.6 GB251
Peenoblanc 52 Llava4K / 26.7 GB60
Otterchecker4K / 26.7 GB42
Llava 13B Custom4K / 26.7 GB50
Note: green Score (e.g. "73.2") means that the model is better than Hyunel/llava-13b-v1-1-4bit-128g.

Rank the Llava 13B V1.1 4bit 128g 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