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

Gemma 2 9B It SPPO Iter2 by UCLA-AGI

 »  All LLMs  »  UCLA-AGI  »  Gemma 2 9B It SPPO Iter2   URL Share it on

  1317   

Gemma 2 9B It SPPO Iter2 is an open-source language model by UCLA-AGI. Features: 9b LLM, VRAM: 18.6GB, Context: 8K, License: gemma, LLM Explorer Score: 0.22.

  Arxiv:2405.00675   Conversational   Dataset:openbmb/ultrafeedback   Deploy:azure   En   Endpoints compatible   Gemma2   Region:us   Safetensors   Sharded   Tensorflow
Model Card on HF 🤗: https://huggingface.co/UCLA-AGI/Gemma-2-9B-It-SPPO-Iter2 

Gemma 2 9B It SPPO Iter2 Benchmarks

MMLU Pro: 31.89
GPQA: 11.3
MUSR: 10.94
BBH: 42.17
IFEval: 31 vs 88 (so35)-64.8%
MATH Lvl 5: 8.08
LLME Score: 0.22247
nn.n% — How the model compares to the reference models: Anthropic Sonnet 3.5 ("so35"), GPT-4o ("gpt4o") or GPT-4 ("gpt4").
Gemma 2 9B It SPPO Iter2 (UCLA-AGI/Gemma-2-9B-It-SPPO-Iter2)
🌟 Advertise your project 🚀

Gemma 2 9B It SPPO Iter2 Parameters and Internals

Model Type 
text-generation
Additional Notes 
Training involved synthetic data divided into 3 iterations.
Supported Languages 
Primary (English)
Training Details 
Data Sources:
openbmb/UltraFeedback
Methodology:
Self-Play Preference Optimization, fined-tuned with synthetic datasets in iterations
LLM NameGemma 2 9B It SPPO Iter2
Repository 🤗https://huggingface.co/UCLA-AGI/Gemma-2-9B-It-SPPO-Iter2 
Model Size9b
Required VRAM18.6 GB
Updated2026-04-10
MaintainerUCLA-AGI
Model Typegemma2
Model Files  4.9 GB: 1-of-4   5.0 GB: 2-of-4   5.0 GB: 3-of-4   3.7 GB: 4-of-4
Supported Languagesen
Model ArchitectureGemma2ForCausalLM
Licensegemma
Context Length8192
Model Max Length8192
Transformers Version4.43.0.dev0
Tokenizer ClassGemmaTokenizer
Padding Token<pad>
Vocabulary Size256000
Torch Data Typebfloat16

Best Alternatives to Gemma 2 9B It SPPO Iter2

Best Alternatives
Context / RAM
Downloads
Likes
G2 GSHT 32K32K / 20.4 GB61
SystemGemma2 9B It32K / 18.6 GB62
GWQ 9B Preview28K / 18.6 GB1310
Gemma 2 9B It8K / 18.6 GB262937781
Gemma 2 9B It8K / 18.6 GB60
Gemma 2 9B It SimPO8K / 18.6 GB410172
Turkish Gemma 9B T18K / 18.6 GB49652175
Gemma 2 9B8K / 37.1 GB83831672
Gemma 2 9B It Advanced V2.18K / 20.4 GB428
...erge 02012025163610 Gemma 2 9B8K / 20.4 GB530
Note: green Score (e.g. "73.2") means that the model is better than UCLA-AGI/Gemma-2-9B-It-SPPO-Iter2.

Rank the Gemma 2 9B It 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? 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