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

Zephyr DPO V2 by BarraHome

 »  All LLMs  »  BarraHome  »  Zephyr DPO V2   URL Share it on

  941   
  4bit   Autotrain compatible Base model:barrahome/zephyr-dp... Base model:finetune:barrahome/... Dataset:barrahome/ultrafeedbac... Dataset:jondurbin/truthy-dpo-v...   En   Endpoints compatible   Es   Mistral   Model-index   Quantized   Region:us   Safetensors   Sharded   Tensorflow   Trl   Unsloth
Model Card on HF 🤗: https://huggingface.co/BarraHome/zephyr-dpo-v2 

Zephyr DPO V2 Benchmarks

ARC: 57.85 vs 96.7 (so35)-40.2%
HellaSwag: 82.72 vs 95.3 (gpt4)-13.2%
MMLU: 58.61 vs 88.3 (so35)-33.6%
TruthfulQA: 56.16 vs 59 (gpt4)-4.8%
WinoGrande: 74.35 vs 87.5 (gpt4)-15%
GSM8K: 30.25 vs 96.4 (so35)-68.6%
LLME Score: 0.21209
nn.n% — How the model compares to the reference models: Anthropic Sonnet 3.5 ("so35"), GPT-4o ("gpt4o") or GPT-4 ("gpt4").
Zephyr DPO V2 (BarraHome/zephyr-dpo-v2)

Zephyr DPO V2 Parameters and Internals

Model Type 
text-generation
Additional Notes 
The model was developed faster using Unsloth and Huggingface's TRL library.
Supported Languages 
en (fluent), es (fluent)
Training Details 
Data Sources:
jondurbin/truthy-dpo-v0.1, BarraHome/ultrafeedback_binarized
Model Architecture:
Mistral
LLM NameZephyr DPO V2
Repository 🤗https://huggingface.co/BarraHome/zephyr-dpo-v2 
Base Model(s)  Zephyr DPO 4bit   BarraHome/zephyr-dpo-4bit
Model Size7.2b
Required VRAM14.4 GB
Updated2024-12-22
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 es
Quantization Type4bit
Model ArchitectureMistralForCausalLM
Licensemit
Context Length32768
Model Max Length32768
Transformers Version4.37.1
Tokenizer ClassLlamaTokenizer
Padding Token</s>
Vocabulary Size32000
Torch Data Typebfloat16

Best Alternatives to Zephyr DPO V2

Best Alternatives
Context / RAM
Downloads
Likes
...Sft Bnb 4bit DPO Mtbr 180steps32K / 14.4 GB150
...Sft Bnb 4bit DPO Mtbc 213steps32K / 14.4 GB170
...Sft Bnb 4bit DPO Mtbo 180steps32K / 14.4 GB210
AI Tutor32K / 14.5 GB90
Rezephyr DPO32K / 14.4 GB310
...Web AI HumanAI 012 INSTRUCT XA512K / 14.4 GB710
...Web AI HumanAI 012 INSTRUCT IA512K / 14.4 GB550
...Web AI HumanAI 011 INSTRUCT ML512K / 14.4 GB350
...dazWeb AI HumanAI 011 INSTRUCT512K / 14.4 GB721
SpydazWeb AI HumanAI 010 CHAT512K / 14.4 GB550
Note: green Score (e.g. "73.2") means that the model is better than BarraHome/zephyr-dpo-v2.

Rank the Zephyr DPO V2 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? 40123 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 v20241217
  Support LLM Explorer