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

NeuralTrix 7B DPO Relaser by Kquant03

 »  All LLMs  »  Kquant03  »  NeuralTrix 7B DPO Relaser   URL Share it on

  13   
  Aimavenai/aimaven-prometheus   Autotrain compatible Base model:aimavenai/aimaven-p... Base model:flemmingmiguel/mbx-... Base model:merge:aimavenai/aim... Base model:merge:flemmingmigue... Base model:merge:mlabonne/omni... Base model:mlabonne/omnibeagle...   Endpoints compatible   Flemmingmiguel/mbx-7b-v3   Lazymergekit   Merge   Mergekit   Mistral   Mlabonne/omnibeagle-7b   Pytorch   Region:us   Sharded
Model Card on HF 🤗: https://huggingface.co/Kquant03/NeuralTrix-7B-dpo-relaser 

NeuralTrix 7B DPO Relaser Benchmarks

ARC: 71.33 vs 96.7 (so35)-26.2%
HellaSwag: 88.41 vs 95.3 (gpt4)-7.2%
MMLU: 64.01 vs 88.3 (so35)-27.5%
TruthfulQA: 77.98 vs 59 (gpt4)32.2%
WinoGrande: 84.06 vs 87.5 (gpt4)-3.9%
GSM8K: 68.16 vs 96.4 (so35)-29.3%
LLME Score: 0.15437
nn.n% — How the model compares to the reference models: Anthropic Sonnet 3.5 ("so35"), GPT-4o ("gpt4o") or GPT-4 ("gpt4").
NeuralTrix 7B DPO Relaser (Kquant03/NeuralTrix-7B-dpo-relaser)
🌟 Advertise your project 🚀

NeuralTrix 7B DPO Relaser Parameters and Internals

Model Type 
text generation
Additional Notes 
NeuralTrix-7B-v1 is a merge of the models OmniBeagle-7B, MBX-7B-v3, and AiMaven-Prometheus utilizing LazyMergekit.
Training Details 
Data Sources:
https://huggingface.co/datasets/jondurbin/truthy-dpo-v0.1
Methodology:
Trained with DPO using LazyMergekit
LLM NameNeuralTrix 7B DPO Relaser
Repository 🤗https://huggingface.co/Kquant03/NeuralTrix-7B-dpo-relaser 
Base Model(s)  OmniBeagle 7B   MBX 7B V3   AiMaven Prometheus   mlabonne/OmniBeagle-7B   flemmingmiguel/MBX-7B-v3   AiMavenAi/AiMaven-Prometheus
Model Size7b
Required VRAM14.4 GB
Updated2025-06-21
MaintainerKquant03
Model Typemistral
Model Files  9.9 GB: 1-of-2   4.5 GB: 2-of-2
Model ArchitectureMistralForCausalLM
Licenseapache-2.0
Context Length32768
Model Max Length32768
Transformers Version4.34.0
Tokenizer ClassLlamaTokenizer
Vocabulary Size32000
Torch Data Typebfloat16

Best Alternatives to NeuralTrix 7B DPO Relaser

Best Alternatives
Context / RAM
Downloads
Likes
...Nemo Instruct 2407 Abliterated1000K / 24.5 GB194616
MegaBeam Mistral 7B 512K512K / 14.4 GB1090250
SpydazWeb AI HumanAI RP512K / 14.4 GB181
SpydazWeb AI HumanAI 002512K / 14.4 GB181
...daz Web AI ChatML 512K Project512K / 14.5 GB120
MegaBeam Mistral 7B 300K282K / 14.4 GB377916
MegaBeam Mistral 7B 300K282K / 14.4 GB1043416
Hebrew Mistral 7B 200K256K / 30 GB284215
Astral 256K 7B250K / 14.4 GB110
Astral 256K 7B V2250K / 14.4 GB90
Note: green Score (e.g. "73.2") means that the model is better than Kquant03/NeuralTrix-7B-dpo-relaser.

Rank the NeuralTrix 7B DPO Relaser 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? 48323 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