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

LogoS 7Bx2 MoE 13B V0.2 by RubielLabarta

 »  All LLMs  »  RubielLabarta  »  LogoS 7Bx2 MoE 13B V0.2   URL Share it on

  9050   
  Merged Model   Autotrain compatible Base model:tomgrc/fusionnet 7b... Base model:yunconglong/truthfu...   En   Endpoints compatible   Es   Mixtral   Model-index   Moe   Region:us   Safetensors   Sharded   Tensorflow
Model Card on HF 🤗: https://huggingface.co/RubielLabarta/LogoS-7Bx2-MoE-13B-v0.2 

LogoS 7Bx2 MoE 13B V0.2 Benchmarks

MMLU Pro: 23.2
GPQA: 3.69
MUSR: 11.49
BBH: 32.79
IFEval: 43.79 vs 88 (so35)-50.2%
ARC: 74.4 vs 96.7 (so35)-23.1%
HellaSwag: 89.09 vs 95.3 (gpt4)-6.5%
MMLU: 64.9 vs 88.3 (so35)-26.5%
TruthfulQA: 74.53 vs 59 (gpt4)26.3%
WinoGrande: 88.4 vs 87.5 (gpt4)1%
GSM8K: 71.57 vs 96.4 (so35)-25.8%
MATH Lvl 5: 5.74
LLME Score: 0.22995
nn.n% — How the model compares to the reference models: Anthropic Sonnet 3.5 ("so35"), GPT-4o ("gpt4o") or GPT-4 ("gpt4").
LogoS 7Bx2 MoE 13B V0.2 (RubielLabarta/LogoS-7Bx2-MoE-13B-v0.2)
🌟 Advertise your project 🚀

LogoS 7Bx2 MoE 13B V0.2 Parameters and Internals

Model Type 
text-generation
Additional Notes 
Model built using SLERP merge method to experiment with the MoE method, which could significantly increase the performance of the original model.
Supported Languages 
en (:)
LLM NameLogoS 7Bx2 MoE 13B V0.2
Repository 🤗https://huggingface.co/RubielLabarta/LogoS-7Bx2-MoE-13B-v0.2 
Base Model(s)  ... TomGrc FusionNet 7Bx2 MoE 13B   FusionNet 7Bx2 MoE 14B   yunconglong/Truthful_DPO_TomGrc_FusionNet_7Bx2_MoE_13B   TomGrc/FusionNet_7Bx2_MoE_14B
Merged ModelYes
Model Size12.9b
Required VRAM25.9 GB
Updated2025-09-23
MaintainerRubielLabarta
Model Typemixtral
Model Files  1.9 GB: 1-of-14   2.0 GB: 2-of-14   2.0 GB: 3-of-14   2.0 GB: 4-of-14   2.0 GB: 5-of-14   1.9 GB: 6-of-14   1.9 GB: 7-of-14   1.9 GB: 8-of-14   2.0 GB: 9-of-14   2.0 GB: 10-of-14   2.0 GB: 11-of-14   2.0 GB: 12-of-14   1.9 GB: 13-of-14   0.4 GB: 14-of-14
Supported Languagesen es
Model ArchitectureMixtralForCausalLM
Licenseapache-2.0
Context Length32768
Model Max Length32768
Transformers Version4.36.2
Tokenizer ClassLlamaTokenizer
Padding Token<s>
Vocabulary Size32000
Torch Data Typebfloat16

Best Alternatives to LogoS 7Bx2 MoE 13B V0.2

Best Alternatives
Context / RAM
Downloads
Likes
MixTAO 7Bx2 MoE V8.132K / 25.8 GB2081155
Inf Silent Kunoichi V0.1 2x7B32K / 25.6 GB50
Inf Silent Kunoichi V0.2 2x7B32K / 25.6 GB101
MixTAO 7Bx2 MoE V8.132K / 25.8 GB876052
MultiMash8 13B Slerp32K / 25.7 GB50
MultiMash11 13B Slerp32K / 25.7 GB50
MultiMash9 13B Slerp32K / 25.7 GB50
MultiMash10 13B Slerp32K / 25.7 GB60
MixTaoTruthful 13B Slerp32K / 25.7 GB50
Multimash3 12B Slerp32K / 25.7 GB80
Note: green Score (e.g. "73.2") means that the model is better than RubielLabarta/LogoS-7Bx2-MoE-13B-v0.2.

Rank the LogoS 7Bx2 MoE 13B V0.2 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? 51566 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 v20241124
  Support LLM Explorer