Shieldgemma 27B by google

 ยป  All LLMs  ยป  google  ยป  Shieldgemma 27B   URL Share it on

  Arxiv:2306.05685   Arxiv:2310.17389   Arxiv:2407.21772   Autotrain compatible   Conversational   Endpoints compatible   Gemma2   Region:us   Safetensors   Sharded   Tensorflow
Model Card on HF ๐Ÿค—: https://huggingface.co/google/shieldgemma-27b 

Shieldgemma 27B Benchmarks

nn.n% — How the model compares to the reference models: Anthropic Sonnet 3.5 ("so35"), GPT-4o ("gpt4o") or GPT-4 ("gpt4").
Shieldgemma 27B (google/shieldgemma-27b)

Shieldgemma 27B Parameters and Internals

LLM NameShieldgemma 27B
Repository ๐Ÿค—https://huggingface.co/google/shieldgemma-27b 
Model Size27b
Required VRAM54.7 GB
Updated2025-01-24
Maintainergoogle
Model Typegemma2
Model Files  4.7 GB: 1-of-12   4.9 GB: 2-of-12   4.9 GB: 3-of-12   5.0 GB: 4-of-12   4.9 GB: 5-of-12   4.9 GB: 6-of-12   5.0 GB: 7-of-12   4.9 GB: 8-of-12   4.9 GB: 9-of-12   5.0 GB: 10-of-12   4.9 GB: 11-of-12   0.7 GB: 12-of-12
Model ArchitectureGemma2ForCausalLM
Licensegemma
Context Length8192
Model Max Length8192
Transformers Version4.42.4
Tokenizer ClassGemmaTokenizer
Padding Token<pad>
Vocabulary Size256000
Torch Data Typebfloat16

Best Alternatives to Shieldgemma 27B

Best Alternatives
Context / RAM
Downloads
Likes
SystemGemma2 27B It32K / 54.7 GB961
SystemGemma2 27B It32K / 54.7 GB433
Gemma 2 27B It8K / 54.7 GB122824504
Magnum V3 27B Kto8K / 108.2 GB462112
...s Horizon AI Korean Superb 27B8K / 54.8 GB591
...izon AI Korean Avengers V3 27B8K / 54.8 GB150
Gemma 2 27B8K / 108.3 GB9606193
GemmaStock1 27B8K / 54.8 GB80
Gemma2Slerp2 27B8K / 54.8 GB110
Gemma2SimPO 27B8K / 54.8 GB350
Note: green Score (e.g. "73.2") means that the model is better than google/shieldgemma-27b.

Rank the Shieldgemma 27B 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? 41817 in total.

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