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

Rezephyr DPO by BarraHome

 »  All LLMs  »  BarraHome  »  Rezephyr DPO   URL Share it on

  5   
  Merged Model   4bit   Autotrain compatible Base model:barrahome/rezephyr ... Base model:finetune:barrahome/...   Conversational Dataset:jondurbin/truthy-dpo-v...   En   Endpoints compatible   Mistral   Model-index   Quantized   Region:us   Safetensors   Sharded   Tensorflow   Trl   Unsloth
Model Card on HF 🤗: https://huggingface.co/BarraHome/rezephyr-dpo 

Rezephyr DPO Benchmarks

ARC: 57.59 vs 96.7 (so35)-40.4%
HellaSwag: 81.75 vs 95.3 (gpt4)-14.2%
MMLU: 60.55 vs 88.3 (so35)-31.4%
TruthfulQA: 44.32 vs 59 (gpt4)-24.9%
WinoGrande: 77.03 vs 87.5 (gpt4)-12%
GSM8K: 32.45 vs 96.4 (so35)-66.3%
LLME Score: 0.15347
nn.n% — How the model compares to the reference models: Anthropic Sonnet 3.5 ("so35"), GPT-4o ("gpt4o") or GPT-4 ("gpt4").
Rezephyr DPO (BarraHome/rezephyr-dpo)
🌟 Advertise your project 🚀

Rezephyr DPO Parameters and Internals

Model Type 
text-generation
Additional Notes 
Trained 2x faster with Unsloth and Huggingface's TRL library.
LLM NameRezephyr DPO
Repository 🤗https://huggingface.co/BarraHome/rezephyr-dpo 
Base Model(s)  Rezephyr Merged 4bit   BarraHome/rezephyr_merged_4bit
Merged ModelYes
Model Size7.2b
Required VRAM14.4 GB
Updated2025-09-23
MaintainerBarraHome
Model Typemistral
Model Files  4.9 GB: 1-of-3   5.0 GB: 2-of-3   4.5 GB: 3-of-3
Supported Languagesen
Quantization Type4bit
Model ArchitectureMistralForCausalLM
Licenseapache-2.0
Context Length32768
Model Max Length32768
Transformers Version4.37.1
Tokenizer ClassLlamaTokenizer
Padding Token</s>
Vocabulary Size32000
Torch Data Typebfloat16

Best Alternatives to Rezephyr DPO

Best Alternatives
Context / RAM
Downloads
Likes
...Sft Bnb 4bit DPO Mtbr 180steps32K / 14.4 GB50
...Sft Bnb 4bit DPO Mtbc 213steps32K / 14.4 GB50
...Sft Bnb 4bit DPO Mtbo 180steps32K / 14.4 GB90
Mixtral V0.3 Full 16bit V232K / 14.5 GB50
...88 07.02 RP DPO Merged 16bit 332K / 14.4 GB100
Tools Mistral 16bit Merged New32K / 14.5 GB50
AI Tutor32K / 14.5 GB50
Zephyr DPO V232K / 14.4 GB21
...Web AI HumanAI 012 INSTRUCT XA512K / 14.4 GB90
...Web AI HumanAI 012 INSTRUCT IA512K / 14.4 GB80
Note: green Score (e.g. "73.2") means that the model is better than BarraHome/rezephyr-dpo.

Rank the Rezephyr 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? 51594 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