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

NeuTrixOmniBe DPO by Kukedlc

 »  All LLMs  »  Kukedlc  »  NeuTrixOmniBe DPO   URL Share it on

  103   
  #dpo   #mergeofmerge   Autotrain compatible Base model:cultrix/neuraltrix-... Base model:merge:cultrix/neura... Base model:merge:paulml/omnibe... Base model:paulml/omnibeaglesq...   Endpoints compatible   Maximelabonne   Merge   Mergekit   Mistral   Model-index   Region:us   Safetensors   Sharded   Tensorflow
Model Card on HF 🤗: https://huggingface.co/Kukedlc/NeuTrixOmniBe-DPO 

NeuTrixOmniBe DPO Benchmarks

ARC: 72.95 vs 96.7 (so35)-24.6%
HellaSwag: 89.04 vs 95.3 (gpt4)-6.6%
MMLU: 64.34 vs 88.3 (so35)-27.1%
TruthfulQA: 77.22 vs 59 (gpt4)30.9%
WinoGrande: 84.93 vs 87.5 (gpt4)-2.9%
GSM8K: 68.31 vs 96.4 (so35)-29.1%
LLME Score: 0.17908
nn.n% — How the model compares to the reference models: Anthropic Sonnet 3.5 ("so35"), GPT-4o ("gpt4o") or GPT-4 ("gpt4").
NeuTrixOmniBe DPO (Kukedlc/NeuTrixOmniBe-DPO)

NeuTrixOmniBe DPO Parameters and Internals

Model Type 
text-generation
Use Cases 
Areas:
research, commercial applications
Additional Notes 
Model was trained using knowledge from Maxime Labonne's course with LazyMergekit.
Training Details 
Data Sources:
CultriX/NeuralTrix-7B-dpo, paulml/OmniBeagleSquaredMBX-v3-7B-v2
Methodology:
merge method: slerp
LLM NameNeuTrixOmniBe DPO
Repository 🤗https://huggingface.co/Kukedlc/NeuTrixOmniBe-DPO 
Base Model(s)  NeuralTrix 7B DPO   OmniBeagleSquaredMBX V3 7B V2   CultriX/NeuralTrix-7B-dpo   paulml/OmniBeagleSquaredMBX-v3-7B-v2
Model Size7b
Required VRAM14.4 GB
Updated2025-01-15
MaintainerKukedlc
Model Typemistral
Model Files  4.9 GB: 1-of-3   5.0 GB: 2-of-3   4.5 GB: 3-of-3
Model ArchitectureMistralForCausalLM
Licenseapache-2.0
Context Length32768
Model Max Length32768
Transformers Version4.35.2
Tokenizer ClassLlamaTokenizer
Vocabulary Size32000
Torch Data Typefloat16

Best Alternatives to NeuTrixOmniBe DPO

Best Alternatives
Context / RAM
Downloads
Likes
...Nemo Instruct 2407 Abliterated1000K / 24.5 GB35629
MegaBeam Mistral 7B 512K512K / 14.4 GB439247
SpydazWeb AI HumanAI RP512K / 14.4 GB241
SpydazWeb AI HumanAI 002512K / 14.4 GB191
...daz Web AI ChatML 512K Project512K / 14.5 GB120
MegaBeam Mistral 7B 300K282K / 14.4 GB386615
Hebrew Mistral 7B 200K256K / 30 GB264015
Astral 256K 7B V2250K / 14.4 GB110
Astral 256K 7B250K / 14.4 GB110
Test001128K / 14.5 GB90
Note: green Score (e.g. "73.2") means that the model is better than Kukedlc/NeuTrixOmniBe-DPO.

Rank the NeuTrixOmniBe DPO 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? 41363 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