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

Zenith 7B DPO by Xenon1

 »  All LLMs  »  Xenon1  »  Zenith 7B DPO   URL Share it on

  97   

Zenith 7B DPO is an open-source language model by Xenon1. Features: 7b LLM, VRAM: 14.4GB, Context: 32K, License: apache-2.0, HF Score: 59.8, LLM Explorer Score: 0.14, Arc: 60.9, HellaSwag: 82.9, MMLU: 60.5, TruthfulQA: 60.5, WinoGrande: 77.3, GSM8K: 16.6.

  Arxiv:2401.10020   Conversational   En   Endpoints compatible   Mistral   Region:us   Safetensors   Sharded   Tensorflow   Zenith-7b-dpo
Model Card on HF 🤗: https://huggingface.co/Xenon1/Zenith-7B-dpo 

Zenith 7B DPO Benchmarks

ARC: 60.92 vs 96.7 (so35)-37%
HellaSwag: 82.94 vs 95.3 (gpt4)-13%
MMLU: 60.54 vs 88.3 (so35)-31.4%
TruthfulQA: 60.5 vs 59 (gpt4)2.5%
WinoGrande: 77.27 vs 87.5 (gpt4)-11.7%
GSM8K: 16.6 vs 96.4 (so35)-82.8%
LLME Score: 0.14148
nn.n% — How the model compares to the reference models: Anthropic Sonnet 3.5 ("so35"), GPT-4o ("gpt4o") or GPT-4 ("gpt4").
Zenith 7B DPO (Xenon1/Zenith-7B-dpo)
🌟 Advertise your project 🚀

Zenith 7B DPO Parameters and Internals

Model Type 
text generation
Use Cases 
Areas:
instruction fine-tuning, chat applications
Primary Use Cases:
chat-like interactions
Additional Notes 
Model leverages instruction fine-tuning using a special chat template format.
Training Details 
Data Sources:
Ultrafeedback dataset
Methodology:
techniques shown in the paper Self-Rewarding Language Models
Model Architecture:
Transformer model with Grouped-Query Attention, Sliding-Window Attention, Byte-fallback BPE tokenizer
Input Output 
Input Format:
Prompts surrounded by `[INST]` and `[/INST]` tokens
Accepted Modalities:
text
Output Format:
Generated text based on input prompts
LLM NameZenith 7B DPO
Repository 🤗https://huggingface.co/Xenon1/Zenith-7B-dpo 
Model Size7b
Required VRAM14.4 GB
Updated2026-03-13
MaintainerXenon1
Model Typemistral
Model Files  4.9 GB: 1-of-3   5.0 GB: 2-of-3   4.5 GB: 3-of-3
Supported Languagesen
Model ArchitectureMistralForCausalLM
Licenseapache-2.0
Context Length32768
Model Max Length32768
Transformers Version4.37.1
Tokenizer ClassLlamaTokenizer
Vocabulary Size32000
Torch Data Typefloat16

Best Alternatives to Zenith 7B DPO

Best Alternatives
Context / RAM
Downloads
Likes
...Nemo Instruct 2407 Abliterated1000K / 24.5 GB25420
MegaBeam Mistral 7B 512K512K / 14.4 GB844453
SpydazWeb AI HumanAI RP512K / 14.4 GB141
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 GB808216
Hebrew Mistral 7B 200K256K / 30 GB131615
Astral 256K 7B V2250K / 14.4 GB50
Astral 256K 7B250K / 14.4 GB50
Note: green Score (e.g. "73.2") means that the model is better than Xenon1/Zenith-7B-dpo.

Rank the Zenith 7B 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? 52392 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.
Check out Ag3ntum — our secure, self-hosted AI agent for server management.
Release v20260328a
  Support LLM Explorer