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

Vicuna 7B V1.3 Attention Sparsity 30 by wang7776

 »  All LLMs  »  wang7776  »  Vicuna 7B V1.3 Attention Sparsity 30   URL Share it on

  58   
  Arxiv:2302.13971   Arxiv:2306.05685   Arxiv:2306.11695   Autotrain compatible   Llama   Region:us   Safetensors   Sharded   Tensorflow

Vicuna 7B V1.3 Attention Sparsity 30 Benchmarks

ARC: 51.02 vs 96.7 (so35)-47.2%
HellaSwag: 76.41 vs 95.3 (gpt4)-19.8%
MMLU: 46.83 vs 88.3 (so35)-47%
TruthfulQA: 46.06 vs 59 (gpt4)-21.9%
WinoGrande: 69.3 vs 87.5 (gpt4)-20.8%
GSM8K: 12.36 vs 96.4 (so35)-87.2%
LLME Score: 0.21194
nn.n% — How the model compares to the reference models: Anthropic Sonnet 3.5 ("so35"), GPT-4o ("gpt4o") or GPT-4 ("gpt4").

Vicuna 7B V1.3 Attention Sparsity 30 Parameters and Internals

LLM NameVicuna 7B V1.3 Attention Sparsity 30
Repository 🤗https://huggingface.co/wang7776/vicuna-7b-v1.3-attention-sparsity-30 
Model Size7b
Required VRAM13.5 GB
Updated2024-10-18
Maintainerwang7776
Model Typellama
Model Files  4.9 GB: 1-of-3   5.0 GB: 2-of-3   3.6 GB: 3-of-3
Model ArchitectureLlamaForCausalLM
Licenseapache-2.0
Context Length2048
Model Max Length2048
Transformers Version4.36.1
Tokenizer ClassLlamaTokenizer
Padding Token<unk>
Vocabulary Size32000
Torch Data Typefloat16
Vicuna 7B V1.3 Attention Sparsity 30 (wang7776/vicuna-7b-v1.3-attention-sparsity-30)

Best Alternatives to Vicuna 7B V1.3 Attention Sparsity 30

Best Alternatives
Context / RAM
Downloads
Likes
...1M 1000000ctx AEZAKMI 3 1 17021024K / 13.5 GB571
... Qwen2.5llamaify 7B V23.1 200K195K / 15.2 GB6840
Yarn Llama 2 7B 128K128K / 13.5 GB160938
LLaMA 7B PoSE YaRN 128K128K / 13.5 GB13
LLaMA 7B PoSE Linear 96K96K / 27 GB62
LLaMA 7B PoSE YaRN 96K96K / 13.5 GB11
Chat Llama2 7B 80K80K / 13.8 GB120
Llama2 7B 80K80K / 13.8 GB60
Lloma Step40064K / 13.5 GB570
Lloma Step20064K / 13.5 GB600
Note: green Score (e.g. "73.2") means that the model is better than wang7776/vicuna-7b-v1.3-attention-sparsity-30.

Rank the Vicuna 7B V1.3 Attention Sparsity 30 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? 36966 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 v2024072803
  Support LLM Explorer