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

Mistral Instruct MoE Experimental by osanseviero

 »  All LLMs  »  osanseviero  »  Mistral Instruct MoE Experimental   URL Share it on

  8   
  Autotrain compatible Base model:merge:mistralai/mis... Base model:mistralai/mistral-7... Base model:mistralai/mistral-7...   Conversational   Endpoints compatible   Instruct   Merge   Mergekit   Mixtral   Model-index   Moe   Region:us   Safetensors   Sharded   Tensorflow
Model Card on HF 🤗: https://huggingface.co/osanseviero/mistral-instruct-moe-experimental 

Mistral Instruct MoE Experimental Benchmarks

ARC: 61.01 vs 96.7 (so35)-36.9%
HellaSwag: 81.55 vs 95.3 (gpt4)-14.4%
MMLU: 58.22 vs 88.3 (so35)-34.1%
TruthfulQA: 60.4 vs 59 (gpt4)2.4%
WinoGrande: 76.09 vs 87.5 (gpt4)-13%
GSM8K: 31.08 vs 96.4 (so35)-67.8%
LLME Score: 0.14872
nn.n% — How the model compares to the reference models: Anthropic Sonnet 3.5 ("so35"), GPT-4o ("gpt4o") or GPT-4 ("gpt4").
Mistral Instruct MoE Experimental (osanseviero/mistral-instruct-moe-experimental)
🌟 Advertise your project 🚀

Mistral Instruct MoE Experimental Parameters and Internals

Model Type 
text-generation
Additional Notes 
This is an experimental model created using mergekit with the MoE merge method using a random gate, which may affect the results.
LLM NameMistral Instruct MoE Experimental
Repository 🤗https://huggingface.co/osanseviero/mistral-instruct-moe-experimental 
Base Model(s)  mistralai/Mistral-7B-Instruct-v0.2   mistralai/Mistral-7B-Instruct-v0.1   mistralai/Mistral-7B-Instruct-v0.2   mistralai/Mistral-7B-Instruct-v0.1
Model Size12.9b
Required VRAM25.8 GB
Updated2025-09-23
Maintainerosanseviero
Model Typemixtral
Instruction-BasedYes
Model Files  9.9 GB: 1-of-3   10.0 GB: 2-of-3   5.9 GB: 3-of-3
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 Mistral Instruct MoE Experimental

Best Alternatives
Context / RAM
Downloads
Likes
Inf Silent Kunoichi V0.1 2x7B32K / 25.6 GB50
Inf Silent Kunoichi V0.2 2x7B32K / 25.6 GB101
MergedExpert 2x8b32K / 25.8 GB50
MergedExperts 2x8b32K / 25.8 GB50
NearalMistral 2x7B32K / 25.8 GB51
Orthogonal 2x7B Base32K / 25.8 GB17140
Megatron V3 2x7B32K / 25.8 GB73
MistarlingMaid 2x7B Base32K / 25.8 GB50
...afted Hermetic Platypus C 2x7B32K / 25.8 GB50
...tral 7B Instruct V0.2 2x7B MoE32K / 25.8 GB11314
Note: green Score (e.g. "73.2") means that the model is better than osanseviero/mistral-instruct-moe-experimental.

Rank the Mistral Instruct MoE Experimental 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? 51544 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