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

Megamarcoroni 120B by ibivibiv

 »  All LLMs  »  ibivibiv  »  Megamarcoroni 120B   URL Share it on

  81   
  Arxiv:1910.09700   Autotrain compatible   En   Endpoints compatible   Llama   Model-index   Region:us   Safetensors   Sharded   Tensorflow
Model Card on HF 🤗: https://huggingface.co/ibivibiv/megamarcoroni-120b 

Megamarcoroni 120B Benchmarks

ARC: 72.01 vs 96.7 (so35)-25.5%
HellaSwag: 88.94 vs 95.3 (gpt4)-6.7%
MMLU: 69.88 vs 88.3 (so35)-20.9%
TruthfulQA: 64.24 vs 59 (gpt4)8.9%
WinoGrande: 80.9 vs 87.5 (gpt4)-7.5%
GSM8K: 21.53 vs 96.4 (so35)-77.7%
LLME Score: 0.19407
nn.n% — How the model compares to the reference models: Anthropic Sonnet 3.5 ("so35"), GPT-4o ("gpt4o") or GPT-4 ("gpt4").
Megamarcoroni 120B (ibivibiv/megamarcoroni-120b)

Megamarcoroni 120B Parameters and Internals

Model Type 
text-generation
Additional Notes 
The model was removed previously and is now re-evaluated. Known as '2x70B Marcoroni'.
LLM NameMegamarcoroni 120B
Repository 🤗https://huggingface.co/ibivibiv/megamarcoroni-120b 
Model Size120b
Required VRAM212 GB
Updated2024-12-21
Maintaineribivibiv
Model Typellama
Model Files  4.8 GB: 1-of-106   4.6 GB: 2-of-106   4.4 GB: 3-of-106   5.0 GB: 4-of-106   4.4 GB: 5-of-106   4.4 GB: 6-of-106   5.0 GB: 7-of-106   4.4 GB: 8-of-106   4.4 GB: 9-of-106   5.0 GB: 10-of-106   4.4 GB: 11-of-106   4.4 GB: 12-of-106   5.0 GB: 13-of-106   4.4 GB: 14-of-106   4.4 GB: 15-of-106   5.0 GB: 16-of-106   4.4 GB: 17-of-106   4.4 GB: 18-of-106   5.0 GB: 19-of-106   4.4 GB: 20-of-106   4.4 GB: 21-of-106   5.0 GB: 22-of-106   4.4 GB: 23-of-106   4.4 GB: 24-of-106   5.0 GB: 25-of-106   4.4 GB: 26-of-106   4.4 GB: 27-of-106   5.0 GB: 28-of-106   4.4 GB: 29-of-106   4.4 GB: 30-of-106   5.0 GB: 31-of-106   4.4 GB: 32-of-106   4.4 GB: 33-of-106   5.0 GB: 34-of-106   4.4 GB: 35-of-106   4.4 GB: 36-of-106   5.0 GB: 37-of-106   4.4 GB: 38-of-106   4.4 GB: 39-of-106   5.0 GB: 40-of-106   4.4 GB: 41-of-106   4.4 GB: 42-of-106   5.0 GB: 43-of-106   4.4 GB: 44-of-106   4.4 GB: 45-of-106   5.0 GB: 46-of-106
Supported Languagesen
Model ArchitectureLlamaForCausalLM
Licenseapache-2.0
Context Length4096
Model Max Length4096
Transformers Version4.37.2
Vocabulary Size32000
Torch Data Typefloat32

Best Alternatives to Megamarcoroni 120B

Best Alternatives
Context / RAM
Downloads
Likes
Chat Goliath 120B 80K80K / 236.3 GB111
Electric Sheep 120B31K / 238.8 GB570
Miquella 120B31K / 235.6 GB44120
QueenLiz 120B31K / 240.9 GB223
Meta Llama 3 225B Instruct8K / 443.2 GB2018
...ma 3 Instruct 120B Cat A Llama8K / 243.9 GB191
...0B Instruct Abliterated Merged8K / 243.7 GB161
Colossus 120b4K / 207 GB131
Goliath 120B4K / 235.4 GB2126229
Mlx Community Goliath 120B4K / 234 GB172
Note: green Score (e.g. "73.2") means that the model is better than ibivibiv/megamarcoroni-120b.

Rank the Megamarcoroni 120B 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? 40013 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 v20241217
  Support LLM Explorer