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

Mistral Orpo Beta by kaist-ai

 »  All LLMs  »  kaist-ai  »  Mistral Orpo Beta   URL Share it on

  25   

Mistral Orpo Beta is an open-source language model by kaist-ai. Features: 7b LLM, VRAM: 14.4GB, Context: 32K, License: mit, HF Score: 62.5, LLM Explorer Score: 0.14, Arc: 61.2, HellaSwag: 84, MMLU: 63.3, TruthfulQA: 47.7, WinoGrande: 79.2, GSM8K: 39.8.

  Arxiv:2403.07691   Autotrain compatible Base model:finetune:mistralai/... Base model:mistralai/mistral-7...   Conversational Dataset:argilla/ultrafeedback-...   En   Endpoints compatible   Mistral   Model-index   Region:us   Safetensors   Sharded   Tensorflow
Model Card on HF 🤗: https://huggingface.co/kaist-ai/mistral-orpo-beta 

Mistral Orpo Beta Benchmarks

ARC: 61.18 vs 96.7 (so35)-36.7%
HellaSwag: 84.03 vs 95.3 (gpt4)-11.8%
MMLU: 63.26 vs 88.3 (so35)-28.4%
TruthfulQA: 47.69 vs 59 (gpt4)-19.2%
WinoGrande: 79.24 vs 87.5 (gpt4)-9.4%
GSM8K: 39.8 vs 96.4 (so35)-58.7%
LLME Score: 0.14191
nn.n% — How the model compares to the reference models: Anthropic Sonnet 3.5 ("so35"), GPT-4o ("gpt4o") or GPT-4 ("gpt4").
Mistral Orpo Beta (kaist-ai/mistral-orpo-beta)
🌟 Advertise your project 🚀

Mistral Orpo Beta Parameters and Internals

Model Type 
text-generation
Additional Notes 
Mistral-ORPO is a fine-tuned version of mistralai/Mistral-7B-v0.1 using ORPO, learning preference directly without supervised fine-tuning warmup.
Training Details 
Data Sources:
argilla/ultrafeedback-binarized-preferences-cleaned
Data Volume:
61k instances
Methodology:
Odds Ratio Preference Optimization (ORPO)
LLM NameMistral Orpo Beta
Repository 🤗https://huggingface.co/kaist-ai/mistral-orpo-beta 
Base Model(s)  mistralai/Mistral-7B-v0.1   mistralai/Mistral-7B-v0.1
Model Size7b
Required VRAM14.4 GB
Updated2025-10-23
Maintainerkaist-ai
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
Licensemit
Context Length32768
Model Max Length32768
Transformers Version4.38.2
Tokenizer ClassLlamaTokenizer
Vocabulary Size32000
Torch Data Typebfloat16

Best Alternatives to Mistral Orpo Beta

Best Alternatives
Context / RAM
Downloads
Likes
...Nemo Instruct 2407 Abliterated1000K / 24.5 GB25420
MegaBeam Mistral 7B 512K512K / 14.4 GB1144354
SpydazWeb AI HumanAI RP512K / 14.4 GB211
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 GB796816
Hebrew Mistral 7B 200K256K / 30 GB131615
Astral 256K 7B V2250K / 14.4 GB100
Astral 256K 7B250K / 14.4 GB50
Note: green Score (e.g. "73.2") means that the model is better than kaist-ai/mistral-orpo-beta.

Rank the Mistral Orpo Beta 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? 53254 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