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

Autotrain Llama3 Orpo V2 by abhishek

 »  All LLMs  »  abhishek  »  Autotrain Llama3 Orpo V2   URL Share it on

  15   

Autotrain Llama3 Orpo V2 is an open-source language model by abhishek. Features: 8b LLM, VRAM: 16.1GB, Context: 8K, License: other, Instruction-Based, HF Score: 67.2, LLM Explorer Score: 0.18, Arc: 62.1, HellaSwag: 79.5, MMLU: 67.1, TruthfulQA: 52.2, WinoGrande: 76, GSM8K: 66.

  Autotrain   Autotrain compatible   Conversational Dataset:argilla/distilabel-cap...   Endpoints compatible   Instruct   Llama   Region:us   Safetensors   Sharded   Tensorboard   Tensorflow
Model Card on HF 🤗: https://huggingface.co/abhishek/autotrain-llama3-orpo-v2 

Autotrain Llama3 Orpo V2 Benchmarks

MMLU Pro: 13.54
GPQA: 2.24
MUSR: 5.1
BBH: 4.38
IFEval: 43.72 vs 88 (so35)-50.3%
ARC: 62.12 vs 96.7 (so35)-35.8%
HellaSwag: 79.51 vs 95.3 (gpt4)-16.6%
MMLU: 67.14 vs 88.3 (so35)-24%
TruthfulQA: 52.2 vs 59 (gpt4)-11.5%
WinoGrande: 76.01 vs 87.5 (gpt4)-13.1%
GSM8K: 66.03 vs 96.4 (so35)-31.5%
MATH Lvl 5: 4.68
LLME Score: 0.17784
nn.n% — How the model compares to the reference models: Anthropic Sonnet 3.5 ("so35"), GPT-4o ("gpt4o") or GPT-4 ("gpt4").
Autotrain Llama3 Orpo V2 (abhishek/autotrain-llama3-orpo-v2)
🌟 Advertise your project 🚀

Autotrain Llama3 Orpo V2 Parameters and Internals

Model Type 
text generation
Additional Notes 
This model was trained using AutoTrain. See [AutoTrain](https://hf.co/docs/autotrain) for more information.
Training Details 
Data Sources:
argilla/distilabel-capybara-dpo-7k-binarized
Methodology:
Trained using AutoTrain
Input Output 
Input Format:
messages list with role and content keys
Accepted Modalities:
text
Output Format:
Model's generated text response
LLM NameAutotrain Llama3 Orpo V2
Repository 🤗https://huggingface.co/abhishek/autotrain-llama3-orpo-v2 
Model Size8b
Required VRAM16.1 GB
Updated2025-05-01
Maintainerabhishek
Model Typellama
Instruction-BasedYes
Model Files  5.0 GB: 1-of-4   5.0 GB: 2-of-4   4.9 GB: 3-of-4   1.2 GB: 4-of-4   0.0 GB
Model ArchitectureLlamaForCausalLM
Licenseother
Context Length8192
Model Max Length8192
Transformers Version4.40.0
Tokenizer ClassPreTrainedTokenizerFast
Padding Token<pad>
Vocabulary Size128264
Torch Data Typebfloat16

Best Alternatives to Autotrain Llama3 Orpo V2

Best Alternatives
Context / RAM
Downloads
Likes
...otron 8B UltraLong 4M Instruct4192K / 32.1 GB89119
...a 3.1 8B UltraLong 4M Instruct4192K / 32.1 GB17624
UltraLong Thinking4192K / 16.1 GB93
...a 3.1 8B UltraLong 2M Instruct2096K / 32.1 GB8759
...otron 8B UltraLong 2M Instruct2096K / 32.1 GB4017
Cthulhu 8B V1.41048K / 16.1 GB139
...otron 8B UltraLong 1M Instruct1048K / 32.1 GB344055
...a 3.1 8B UltraLong 1M Instruct1048K / 32.1 GB138729
Zero Llama 3.1 8B Beta61048K / 16.1 GB51
...dger Nu Llama 3.1 8B UltraLong1048K / 16.2 GB53
Note: green Score (e.g. "73.2") means that the model is better than abhishek/autotrain-llama3-orpo-v2.

Rank the Autotrain Llama3 Orpo 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? 52721 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