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

Merge Mayhem L3 V2.1 by saishf

 »  All LLMs  »  saishf  »  Merge Mayhem L3 V2.1   URL Share it on

  116   
  Merged Model   Arxiv:2403.19522   Autotrain compatible Base model:elyn-dev/llama-3-so... Base model:meta-llama/meta-lla... Base model:resplendentai/aura ... Base model:resplendentai/bluem... Base model:resplendentai/luna ... Base model:resplendentai/rp fo... Base model:resplendentai/smart...   Conversational   Endpoints compatible   Llama   Region:us   Safetensors   Sharded   Tensorflow
Model Card on HF 🤗: https://huggingface.co/saishf/Merge-Mayhem-L3-V2.1 

Merge Mayhem L3 V2.1 Benchmarks

ARC: 62.29 vs 96.7 (so35)-35.6%
HellaSwag: 79.82 vs 95.3 (gpt4)-16.2%
MMLU: 67.58 vs 88.3 (so35)-23.5%
TruthfulQA: 52.91 vs 59 (gpt4)-10.3%
WinoGrande: 75.77 vs 87.5 (gpt4)-13.4%
GSM8K: 65.28 vs 96.4 (so35)-32.3%
LLME Score: 0.20151
nn.n% — How the model compares to the reference models: Anthropic Sonnet 3.5 ("so35"), GPT-4o ("gpt4o") or GPT-4 ("gpt4").
Merge Mayhem L3 V2.1 (saishf/Merge-Mayhem-L3-V2.1)

Merge Mayhem L3 V2.1 Parameters and Internals

Additional Notes 
Model was merged using the 'Model Stock' merge method with multiple Meta-Llama models and openlynn/Llama-3-Soliloquy-8B-v2 as a base model.
LLM NameMerge Mayhem L3 V2.1
Repository 🤗https://huggingface.co/saishf/Merge-Mayhem-L3-V2.1 
Base Model(s)  Meta Llama 3 8B Instruct   Luna Llama3   Llama 3 Soliloquy 8B V2   Meta Llama 3 8B Instruct   RP Format QuoteAsterisk Llama3   Meta Llama 3 8B Instruct   Smarts Llama3   Meta Llama 3 8B Instruct   BlueMoon Llama3   Meta Llama 3 8B Instruct   Aura Llama3   meta-llama/Meta-Llama-3-8B-Instruct   ResplendentAI/Luna_Llama3   openlynn/Llama-3-Soliloquy-8B-v2   meta-llama/Meta-Llama-3-8B-Instruct   ResplendentAI/RP_Format_QuoteAsterisk_Llama3   meta-llama/Meta-Llama-3-8B-Instruct   ResplendentAI/Smarts_Llama3   meta-llama/Meta-Llama-3-8B-Instruct   ResplendentAI/BlueMoon_Llama3   meta-llama/Meta-Llama-3-8B-Instruct   ResplendentAI/Aura_Llama3
Merged ModelYes
Model Size8b
Required VRAM16 GB
Updated2025-02-22
Maintainersaishf
Model Typellama
Model Files  4.0 GB: 1-of-5   3.9 GB: 2-of-5   3.9 GB: 3-of-5   3.9 GB: 4-of-5   0.3 GB: 5-of-5
Model ArchitectureLlamaForCausalLM
Licensecc-by-nc-4.0
Context Length8192
Model Max Length8192
Transformers Version4.40.1
Tokenizer ClassPreTrainedTokenizerFast
Padding Token<|end_of_text|>
Vocabulary Size128256
Torch Data Typefloat16

Best Alternatives to Merge Mayhem L3 V2.1

Best Alternatives
Context / RAM
Downloads
Likes
...a 3 8B Instruct Gradient 1048K1024K / 16.1 GB3927680
MrRoboto ProLong 8B V4i1024K / 16.1 GB661
...o ProLongBASE Pt8 Unaligned 8B1024K / 16.1 GB240
MrRoboto BASE V2 Unholy 8B 64K1024K / 16.1 GB271
Mpasila Viking 8B1024K / 16.1 GB840
Thor V1.4 8B DARK FICTION1024K / 16.1 GB9412
41024K / 16.1 GB3220
Hel V2 8B DARK FICTION1024K / 16.1 GB220
161024K / 16.1 GB1690
...di95 LewdStorytellerMix 8B 64K1024K / 16.1 GB692
Note: green Score (e.g. "73.2") means that the model is better than saishf/Merge-Mayhem-L3-V2.1.

Rank the Merge Mayhem L3 V2.1 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? 43470 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