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

Pearl 3x7B by louisbrulenaudet

 »  All LLMs  »  louisbrulenaudet  »  Pearl 3x7B   URL Share it on

  22   
  Autotrain compatible Base model:beowolx/codeninja-1... Base model:dvilasuero/distilab... Base model:merge:beowolx/coden... Base model:merge:dvilasuero/di... Base model:merge:wizardlmteam/... Base model:wizardlmteam/wizard... Beowolx/codeninja-1.0-openchat...   Code   Conversational Dvilasuero/distilabelbeagle14-...   En   Endpoints compatible   Frankenmoe   Lazymergekit   Maths   Merge   Mergekit   Mixtral   Moe   Python   Region:us   Safetensors   Sharded   Tensorflow   Wizardlm/wizardmath-7b-v1.1
Model Card on HF 🤗: https://huggingface.co/louisbrulenaudet/Pearl-3x7B 

Pearl 3x7B Benchmarks

ARC: 65.53 vs 96.7 (so35)-32.2%
HellaSwag: 85.54 vs 95.3 (gpt4)-10.2%
MMLU: 64.27 vs 88.3 (so35)-27.2%
TruthfulQA: 52.17 vs 59 (gpt4)-11.6%
WinoGrande: 78.69 vs 87.5 (gpt4)-10.1%
GSM8K: 57.16 vs 96.4 (so35)-40.7%
LLME Score: 0.1737
nn.n% — How the model compares to the reference models: Anthropic Sonnet 3.5 ("so35"), GPT-4o ("gpt4o") or GPT-4 ("gpt4").
Pearl 3x7B (louisbrulenaudet/Pearl-3x7B)

Pearl 3x7B Parameters and Internals

Model Type 
text-generation, Mixture of Experts (MoE)
Additional Notes 
Specializes in chat, code, and mathematics tasks using a Mixture of Experts model.
Supported Languages 
English (fluent)
Training Details 
Data Sources:
dvilasuero/DistilabelBeagle14-7B, beowolx/CodeNinja-1.0-OpenChat-7B, WizardLM/WizardMath-7B-V1.1
Methodology:
Mixture of Experts to combine chat, code, and mathematics models
Model Architecture:
Mixture of Experts (MoE)
Input Output 
Input Format:
Dictionary with 'role' and 'content'.
Accepted Modalities:
text
Output Format:
Generated text
LLM NamePearl 3x7B
Repository 🤗https://huggingface.co/louisbrulenaudet/Pearl-3x7B 
Base Model(s)  DistilabelBeagle14 7B   beowolx/CodeNinja-1.0-OpenChat-7B   WizardLM/WizardMath-7B-V1.1   dvilasuero/DistilabelBeagle14-7B   beowolx/CodeNinja-1.0-OpenChat-7B   WizardLM/WizardMath-7B-V1.1
Model Size18.5b
Required VRAM37.1 GB
Updated2025-03-14
Maintainerlouisbrulenaudet
Model Typemixtral
Model Files  1.9 GB: 1-of-19   2.0 GB: 2-of-19   2.0 GB: 3-of-19   2.0 GB: 4-of-19   2.0 GB: 5-of-19   2.0 GB: 6-of-19   2.0 GB: 7-of-19   2.0 GB: 8-of-19   2.0 GB: 9-of-19   2.0 GB: 10-of-19   2.0 GB: 11-of-19   2.0 GB: 12-of-19   2.0 GB: 13-of-19   2.0 GB: 14-of-19   2.0 GB: 15-of-19   2.0 GB: 16-of-19   2.0 GB: 17-of-19   2.0 GB: 18-of-19   1.2 GB: 19-of-19
Supported Languagesen
Model ArchitectureMixtralForCausalLM
Licenseapache-2.0
Context Length32768
Model Max Length32768
Transformers Version4.37.2
Tokenizer ClassLlamaTokenizer
Padding Token<s>
Vocabulary Size32002
Torch Data Typefloat16

Best Alternatives to Pearl 3x7B

Best Alternatives
Context / RAM
Downloads
Likes
Lumina 3.532K / 37.1 GB30150
EastAsia 4x7B MoE Experiment32K / 37.1 GB17461
Topxtral 4x7B V0.132K / 37.1 GB17084
Hyperion 3.0 Mixtral 3x7B32K / 37.1 GB214
Blitz AI MoE V0.732K / 37.1 GB121
Blitz AI MoE V0.432K / 37.1 GB171
HeroBophades 3x7B32K / 37.1 GB232
Wizard Kun Lake 3x7B MoE32K / 37.1 GB131
NaruMOE 3x7B V232K / 37.1 GB90
MoE 3x7b QA Code Inst32K / 37 GB244
Note: green Score (e.g. "73.2") means that the model is better than louisbrulenaudet/Pearl-3x7B.

Rank the Pearl 3x7B 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? 45019 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