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

Gemma Ko Merge by Gunulhona

 »  All LLMs  »  Gunulhona  »  Gemma Ko Merge   URL Share it on

  2114   
  Merged Model   Autotrain compatible Base model:lemon07r/gemma-2-at... Base model:rtzr/ko-gemma-2-9b-... Base model:wzhouad/gemma-2-9b-...   Conversational   Endpoints compatible   Gemma2   Gguf   Model-index   Quantized   Region:us   Safetensors   Sharded   Tensorflow
Model Card on HF 🤗: https://huggingface.co/Gunulhona/Gemma-Ko-Merge 

Gemma Ko Merge Benchmarks

MMLU Pro: 31.99
GPQA: 11.41
MUSR: 9.12
BBH: 38.79
IFEval: 64.16 vs 88 (so35)-27.1%
MATH Lvl 5: 18.81
LLME Score: 0.30615
nn.n% — How the model compares to the reference models: Anthropic Sonnet 3.5 ("so35"), GPT-4o ("gpt4o") or GPT-4 ("gpt4").
🌟 Advertise your project 🚀

Gemma Ko Merge Parameters and Internals

Additional Notes 
This model is a merge of pre-trained language models created using mergekit. The merge was conducted using the breadcrumbs_ties merge method.
LLM NameGemma Ko Merge
Repository 🤗https://huggingface.co/Gunulhona/Gemma-Ko-Merge 
Base Model(s)  Gemma 2 Ataraxy 9B   Gemma 2 9B It WPO HB   Ko Gemma 2 9B It   ...emma9 On Korean Summary Events   Ko Gemma 2 9B It   lemon07r/Gemma-2-Ataraxy-9B   wzhouad/gemma-2-9b-it-WPO-HB   rtzr/ko-gemma-2-9b-it   ghost613/gemma9_on_korean_summary_events   rtzr/ko-gemma-2-9b-it
Merged ModelYes
Model Size9b
Required VRAM20.4 GB
Updated2025-06-11
MaintainerGunulhona
Model Typegemma2
Model Files  9.8 GB   1.8 GB: 1-of-11   1.9 GB: 2-of-11   2.0 GB: 3-of-11   2.0 GB: 4-of-11   2.0 GB: 5-of-11   2.0 GB: 6-of-11   2.0 GB: 7-of-11   2.0 GB: 8-of-11   2.0 GB: 9-of-11   2.0 GB: 10-of-11   0.7 GB: 11-of-11
GGUF QuantizationYes
Quantization Typegguf
Model ArchitectureGemma2ForCausalLM
Context Length8192
Model Max Length8192
Transformers Version4.45.0.dev0
Tokenizer ClassGemmaTokenizer
Padding Token<pad>
Vocabulary Size256000
Torch Data Typebfloat16
Gemma Ko Merge (Gunulhona/Gemma-Ko-Merge)

Best Alternatives to Gemma Ko Merge

Best Alternatives
Context / RAM
Downloads
Likes
... Russian Function Calling GGUF8K / 18.6 GB179726
...LLM X Gemma 2 9B CyberSecurity8K / 18.6 GB501
Gemma 2 9B Chinese Chat GGUF8K / 3.8 GB13054
Gemma 2 9B It GGUF8K / 3.8 GB9554
Gemma 2 9B Chinese Chat GGUF8K / 3.8 GB320
Gemma 2 9B It GGUF8K / 3.8 GB420
GWQ 9B Preview28K / 18.6 GB2010
GWQ 9B Preview8K / 18.6 GB143
Gemma 2 9B It Bnb 4bit8K / 6.1 GB910529
SASTRI 1 9B8K / 6.1 GB330
Note: green Score (e.g. "73.2") means that the model is better than Gunulhona/Gemma-Ko-Merge.

Rank the Gemma Ko Merge 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? 48079 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 v20241124
  Support LLM Explorer