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

Buttercup 4x7B Bf16 by Kquant03

 ยป  All LLMs  ยป  Kquant03  ยป  Buttercup 4x7B Bf16   URL Share it on

  1703   
  Arxiv:2101.03961   Autotrain compatible   En   Endpoints compatible   Merge   Mixtral   Moe   Region:us   Safetensors   Sharded   Tensorflow
Model Card on HF ๐Ÿค—: https://huggingface.co/Kquant03/Buttercup-4x7B-bf16 

Buttercup 4x7B Bf16 Benchmarks

ARC: 72.1 vs 96.7 (so35)-25.4%
HellaSwag: 87.74 vs 95.3 (gpt4)-7.9%
MMLU: 64.58 vs 88.3 (so35)-26.9%
TruthfulQA: 67.2 vs 59 (gpt4)13.9%
WinoGrande: 81.93 vs 87.5 (gpt4)-6.4%
GSM8K: 69.83 vs 96.4 (so35)-27.6%
LLME Score: 0.15564
nn.n% — How the model compares to the reference models: Anthropic Sonnet 3.5 ("so35"), GPT-4o ("gpt4o") or GPT-4 ("gpt4").
Buttercup 4x7B Bf16 (Kquant03/Buttercup-4x7B-bf16)
๐ŸŒŸ Advertise your project ๐Ÿš€

Buttercup 4x7B Bf16 Parameters and Internals

Model Type 
Mixture of Experts, MoE, Sparse Model
Use Cases 
Areas:
Intellectual Roleplay
Limitations:
Redundancy issues, Potential overfitting during fine-tuning
Additional Notes 
A MoE model achieving efficiency with sparse layer configurations, overlays on a dense base model, emphasizing novel intellectual applications.
Supported Languages 
en (high)
Training Details 
Methodology:
FrankenMoE which uses improved understanding of SMoE and MoE techniques.
Model Architecture:
FrankenMoE using a mixture of expert models as layers, with an untrained router layer.
Input Output 
Accepted Modalities:
text
Performance Tips:
Introduce new concepts often or use [drฮผgs] to maintain freshness.
LLM NameButtercup 4x7B Bf16
Repository ๐Ÿค—https://huggingface.co/Kquant03/Buttercup-4x7B-bf16 
Model Size24.2b
Required VRAM48.3 GB
Updated2025-09-23
MaintainerKquant03
Model Typemixtral
Model Files  9.9 GB: 1-of-5   10.0 GB: 2-of-5   10.0 GB: 3-of-5   10.0 GB: 4-of-5   8.4 GB: 5-of-5
Supported Languagesen
Model ArchitectureMixtralForCausalLM
Licenseapache-2.0
Context Length32768
Model Max Length32768
Transformers Version4.37.0.dev0
Tokenizer ClassLlamaTokenizer
Padding Token<s>
Vocabulary Size32000
Torch Data Typebfloat16

Best Alternatives to Buttercup 4x7B Bf16

Best Alternatives
Context / RAM
Downloads
Likes
Dzakwan MoE 4x7b Beta32K / 48.4 GB90720
Beyonder 4x7B V332K / 48.3 GB906559
Mera Mix 4x7B32K / 48.3 GB972519
Calme 4x7B MoE V0.232K / 48.3 GB97632
Calme 4x7B MoE V0.132K / 48.3 GB90672
MixtureofMerges MoE 4x7b V532K / 48.3 GB87261
MixtureofMerges MoE 4x7b V432K / 48.3 GB90684
CognitiveFusion2 4x7B BF1632K / 48.3 GB97193
Proto Athena 4x7B32K / 48.4 GB50
Proto Athena V0.2 4x7B32K / 48.4 GB60
Note: green Score (e.g. "73.2") means that the model is better than Kquant03/Buttercup-4x7B-bf16.

Rank the Buttercup 4x7B Bf16 Capabilities

๐Ÿ†˜ 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! ๐ŸŒŸ

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? 51545 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