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

CognitiveFusion2 4x7B BF16 by Kquant03

 »  All LLMs  »  Kquant03  »  CognitiveFusion2 4x7B BF16   URL Share it on

  5076   
  Arxiv:2101.03961   Autotrain compatible   En   Endpoints compatible   Merge   Mixtral   Moe   Region:us   Safetensors   Sharded   Tensorflow

CognitiveFusion2 4x7B BF16 Benchmarks

MMLU Pro: 19.92
GPQA: 4.81
MUSR: 9.95
BBH: 17.69
IFEval: 35.67 vs 88 (so35)-59.5%
ARC: 73.38 vs 96.7 (so35)-24.1%
HellaSwag: 89.18 vs 95.3 (gpt4)-6.4%
MMLU: 64.32 vs 88.3 (so35)-27.2%
TruthfulQA: 78.12 vs 59 (gpt4)32.4%
WinoGrande: 84.93 vs 87.5 (gpt4)-2.9%
GSM8K: 71.27 vs 96.4 (so35)-26.1%
MATH Lvl 5: 5.06
LLME Score: 0.3131
nn.n% — How the model compares to the reference models: Anthropic Sonnet 3.5 ("so35"), GPT-4o ("gpt4o") or GPT-4 ("gpt4").

CognitiveFusion2 4x7B BF16 Parameters and Internals

LLM NameCognitiveFusion2 4x7B BF16
Repository 🤗https://huggingface.co/Kquant03/CognitiveFusion2-4x7B-BF16 
Model Size24.2b
Required VRAM48.3 GB
Updated2024-09-07
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 Version4.38.2
Tokenizer ClassLlamaTokenizer
Padding Token<s>
Vocabulary Size32000
Torch Data Typebfloat16
CognitiveFusion2 4x7B BF16 (Kquant03/CognitiveFusion2-4x7B-BF16)

Best Alternatives to CognitiveFusion2 4x7B BF16

Best Alternatives
Context / RAM
Downloads
Likes
Dzakwan MoE 4x7b Beta32K / 48.4 GB44420
Beyonder 4x7B V332K / 48.3 GB456756
Mera Mix 4x7B32K / 48.3 GB506318
Calme 4x7B MoE V0.132K / 48.3 GB44992
MixtureofMerges MoE 4x7b V532K / 48.3 GB45101
MixtureofMerges MoE 4x7b V432K / 48.3 GB45114
NeuralStar FusionWriter 4x7b32K / 48.3 GB190
LCARS AI 1x4 003 SuperAI32K / 48.5 GB602
NeuralMona MoE 4x7B32K / 48.3 GB45490
Mixtral 4x7b Slerp32K / 96.8 GB41
Note: green Score (e.g. "73.2") means that the model is better than Kquant03/CognitiveFusion2-4x7B-BF16.

Rank the CognitiveFusion2 4x7B BF16 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? 35693 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 v2024072803
  Support LLM Explorer