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

Aegolius Acadicus 34B V3 by ibivibiv

 »  All LLMs  »  ibivibiv  »  Aegolius Acadicus 34B V3   URL Share it on

  11   
  Arxiv:1803.05457   Arxiv:1905.07830   Arxiv:1907.10641   Arxiv:2009.03300   Arxiv:2109.07958   Arxiv:2110.14168   Autotrain compatible   Conversational   En   Endpoints compatible   Mixtral   Model-index   Moe   Region:us   Safetensors   Sharded   Tensorflow
Model Card on HF 🤗: https://huggingface.co/ibivibiv/aegolius-acadicus-34b-v3 

Aegolius Acadicus 34B V3 Benchmarks

ARC: 67.66 vs 96.7 (so35)-30%
HellaSwag: 85.54 vs 95.3 (gpt4)-10.2%
MMLU: 62.13 vs 88.3 (so35)-29.6%
TruthfulQA: 63.33 vs 59 (gpt4)7.3%
WinoGrande: 78.69 vs 87.5 (gpt4)-10.1%
GSM8K: 54.21 vs 96.4 (so35)-43.8%
LLME Score: 0.15917
nn.n% — How the model compares to the reference models: Anthropic Sonnet 3.5 ("so35"), GPT-4o ("gpt4o") or GPT-4 ("gpt4").
Aegolius Acadicus 34B V3 (ibivibiv/aegolius-acadicus-34b-v3)

Aegolius Acadicus 34B V3 Parameters and Internals

Model Type 
text-generation
Use Cases 
Areas:
knowledge related use cases
Additional Notes 
The model is positioned as a MOE model suitable for a variety of tasks across disciplines, mainly leveraging finetuned Llama 2 and mistral models.
Supported Languages 
English (fluent)
Training Details 
Methodology:
Using Mixtral to merge Llama 2 transformer architecture models and mistral models, focused on MOE (Mixture of Experts) approach.
Model Architecture:
Llama2 and Mistral models with MOE methodology.
LLM NameAegolius Acadicus 34B V3
Repository 🤗https://huggingface.co/ibivibiv/aegolius-acadicus-34b-v3 
Model Size34b
Required VRAM142.5 GB
Updated2025-05-31
Maintaineribivibiv
Model Typemixtral
Model Files  5.0 GB: 1-of-29   5.0 GB: 2-of-29   4.9 GB: 3-of-29   4.9 GB: 4-of-29   4.9 GB: 5-of-29   4.9 GB: 6-of-29   4.9 GB: 7-of-29   4.9 GB: 8-of-29   4.9 GB: 9-of-29   5.0 GB: 10-of-29   4.9 GB: 11-of-29   4.9 GB: 12-of-29   4.9 GB: 13-of-29   4.9 GB: 14-of-29   4.9 GB: 15-of-29   4.9 GB: 16-of-29   4.9 GB: 17-of-29   4.9 GB: 18-of-29   5.0 GB: 19-of-29   4.9 GB: 20-of-29   4.9 GB: 21-of-29   4.9 GB: 22-of-29   4.9 GB: 23-of-29   4.9 GB: 24-of-29   4.9 GB: 25-of-29   4.9 GB: 26-of-29   4.9 GB: 27-of-29   5.0 GB: 28-of-29   4.8 GB: 29-of-29
Supported Languagesen
Model ArchitectureMixtralForCausalLM
Licenseapache-2.0
Context Length32768
Model Max Length32768
Transformers Version4.36.2
Tokenizer ClassLlamaTokenizer
Padding Token<s>
Vocabulary Size32000
Torch Data Typefloat32

Best Alternatives to Aegolius Acadicus 34B V3

Best Alternatives
Context / RAM
Downloads
Likes
Yi 34B X2 V232K / 121.9 GB102
...l Hermes 2x34b 2.65bpw H6 EXL2195K / 21.2 GB101
...el Hermes 2x34b 5.0bpw H6 EXL2195K / 38.8 GB111

Rank the Aegolius Acadicus 34B V3 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? 47753 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