Wizard Zephyr Orpo 8x22B by tlphams

 ยป  All LLMs  ยป  tlphams  ยป  Wizard Zephyr Orpo 8x22B   URL Share it on

  Merged Model   Autotrain compatible Base model:alpindale/wizardlm-... Base model:huggingfaceh4/zephy...   Conversational   Endpoints compatible   Mixtral   Moe   Region:us   Safetensors   Sharded   Tensorflow

Wizard Zephyr Orpo 8x22B Benchmarks

nn.n% — How the model compares to the reference models: Anthropic Sonnet 3.5 ("so35"), GPT-4o ("gpt4o") or GPT-4 ("gpt4").
Wizard Zephyr Orpo 8x22B (tlphams/Wizard-Zephyr-Orpo-8x22B)

Wizard Zephyr Orpo 8x22B Parameters and Internals

Additional Notes 
This model is a merged version created using mergekit, combining alpindale/WizardLM-2-8x22B and HuggingFaceH4/zephyr-orpo-141b-A35b-v0.1.
LLM NameWizard Zephyr Orpo 8x22B
Repository ๐Ÿค—https://huggingface.co/tlphams/Wizard-Zephyr-Orpo-8x22B 
Base Model(s)  WizardLM 2 8x22B   HuggingFaceH4/zephyr-orpo-141b-A35b-v0.1   alpindale/WizardLM-2-8x22B   HuggingFaceH4/zephyr-orpo-141b-A35b-v0.1
Merged ModelYes
Model Size140.6b
Required VRAM280.8 GB
Updated2025-02-22
Maintainertlphams
Model Typemixtral
Model Files  10.0 GB: 1-of-29   9.8 GB: 2-of-29   9.8 GB: 3-of-29   9.8 GB: 4-of-29   9.8 GB: 5-of-29   9.8 GB: 6-of-29   9.8 GB: 7-of-29   9.8 GB: 8-of-29   9.8 GB: 9-of-29   9.8 GB: 10-of-29   9.8 GB: 11-of-29   9.9 GB: 12-of-29   9.9 GB: 13-of-29   9.8 GB: 14-of-29   9.8 GB: 15-of-29   9.8 GB: 16-of-29   9.8 GB: 17-of-29   9.8 GB: 18-of-29   9.8 GB: 19-of-29   9.8 GB: 20-of-29   9.8 GB: 21-of-29   9.8 GB: 22-of-29   9.8 GB: 23-of-29   9.8 GB: 24-of-29   9.8 GB: 25-of-29   9.9 GB: 26-of-29   9.9 GB: 27-of-29   10.0 GB: 28-of-29   5.6 GB: 29-of-29
Model ArchitectureMixtralForCausalLM
Licensecc-by-nc-sa-4.0
Context Length65536
Model Max Length65536
Transformers Version4.39.3
Tokenizer ClassLlamaTokenizer
Padding Token<unk>
Vocabulary Size32000
Torch Data Typebfloat16

Best Alternatives to Wizard Zephyr Orpo 8x22B

Best Alternatives
Context / RAM
Downloads
Likes
Mixtral 8x22B Instruct V0.164K / 221.4 GB153763713
Zephyr Orpo 141B A35b V0.164K / 207.2 GB563266
WizardLM 2 8x22B64K / 216.8 GB7110399
Mixtral 8x22B V0.164K / 221.6 GB5953212
Mixtral 8x22B V0.164K / 212 GB4522674
Mixtral 8x22B V0.364K / 221.4 GB463
XLAM 8x22b R64K / 211.8 GB32044
...ixtral 8x22B Instruct V0.1 FP864K / 140.9 GB9013
Dolphin 2.9.2 Mixtral 8x22b64K / 207.2 GB17538
Mixtral 8x22B V0.164K / 212 GB59140
Note: green Score (e.g. "73.2") means that the model is better than tlphams/Wizard-Zephyr-Orpo-8x22B.

Rank the Wizard Zephyr Orpo 8x22B Capabilities

๐Ÿ†˜ 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! ๐ŸŒŸ

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? 43470 in total.

Our Social Media →  
Original data from HuggingFace, OpenCompass and various public git repos.
Release v20241227