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

Llama 3 Instruct 8B SPPO Iter2 by UCLA-AGI

 »  All LLMs  »  UCLA-AGI  »  Llama 3 Instruct 8B SPPO Iter2   URL Share it on

  4208   
  Arxiv:2405.00675   Autotrain compatible   Conversational   Dataset:openbmb/ultrafeedback   En   Endpoints compatible   Instruct   Llama   Pytorch   Region:us   Sharded
Model Card on HF 🤗: https://huggingface.co/UCLA-AGI/Llama-3-Instruct-8B-SPPO-Iter2 

Llama 3 Instruct 8B SPPO Iter2 Benchmarks

MMLU Pro: 29.91
GPQA: 2.24
MUSR: 2
BBH: 29.87
IFEval: 69.89 vs 88 (so35)-20.6%
MATH Lvl 5: 10.35
LLME Score: 0.28387
nn.n% — How the model compares to the reference models: Anthropic Sonnet 3.5 ("so35"), GPT-4o ("gpt4o") or GPT-4 ("gpt4").
Llama 3 Instruct 8B SPPO Iter2 (UCLA-AGI/Llama-3-Instruct-8B-SPPO-Iter2)

Llama 3 Instruct 8B SPPO Iter2 Parameters and Internals

Model Type 
text-generation
Use Cases 
Areas:
text generation
Supported Languages 
English (primarily)
Training Details 
Data Sources:
openbmb/UltraFeedback, snorkelai/Snorkel-Mistral-PairRM-DPO-Dataset
Methodology:
Self-Play Preference Optimization at iteration 2
Model Architecture:
Based on Meta-Llama-3-8B-Instruct architecture
Input Output 
Accepted Modalities:
text
LLM NameLlama 3 Instruct 8B SPPO Iter2
Repository 🤗https://huggingface.co/UCLA-AGI/Llama-3-Instruct-8B-SPPO-Iter2 
Model Size8b
Required VRAM16.1 GB
Updated2025-06-01
MaintainerUCLA-AGI
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
Supported Languagesen
Model ArchitectureLlamaForCausalLM
Licenseapache-2.0
Context Length8192
Model Max Length8192
Transformers Version4.33.0
Tokenizer ClassPreTrainedTokenizerFast
Padding Token<|eot_id|>
Vocabulary Size128256
Torch Data Typebfloat16

Best Alternatives to Llama 3 Instruct 8B SPPO Iter2

Best Alternatives
Context / RAM
Downloads
Likes
...otron 8B UltraLong 4M Instruct4192K / 32.1 GB3482107
UltraLong Thinking4192K / 16.1 GB3122
...a 3.1 8B UltraLong 4M Instruct4192K / 32.1 GB17624
...a 3.1 8B UltraLong 2M Instruct2096K / 32.1 GB8759
...otron 8B UltraLong 2M Instruct2096K / 32.1 GB41815
Zero Llama 3.1 8B Beta61048K / 16.1 GB7301
...otron 8B UltraLong 1M Instruct1048K / 32.1 GB179443
...a 3.1 8B UltraLong 1M Instruct1048K / 32.1 GB138729
...dger Nu Llama 3.1 8B UltraLong1048K / 16.2 GB573
....1 1million Ctx Dark Planet 8B1048K / 32.3 GB932
Note: green Score (e.g. "73.2") means that the model is better than UCLA-AGI/Llama-3-Instruct-8B-SPPO-Iter2.

Rank the Llama 3 Instruct 8B SPPO Iter2 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? 47770 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 v20241227
  Support LLM Explorer