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

Gemma Han 2B by ping98k

 »  All LLMs  »  ping98k  »  Gemma Han 2B   URL Share it on

  13   
  Autotrain compatible Base model:quantized:unsloth/g...   Base model:unsloth/gemma-2b   Conversational Dataset:pythainlp/han-instruct...   Endpoints compatible   Gemma   Gguf   Instruct   Quantized   Region:us   Safetensors   Sharded   Tensorflow   Th
Model Card on HF 🤗: https://huggingface.co/ping98k/gemma-han-2b 

Gemma Han 2B Benchmarks

LLME Score: 0.1461
nn.n% — How the model compares to the reference models: Anthropic Sonnet 3.5 ("so35"), GPT-4o ("gpt4o") or GPT-4 ("gpt4").
Gemma Han 2B (ping98k/gemma-han-2b)
🌟 Advertise your project 🚀

Gemma Han 2B Parameters and Internals

Model Type 
text generation
Use Cases 
Primary Use Cases:
creating poetry on specified themes, coding examples, short story generation, advertisement creation
Limitations:
overfits to train data from han dataset and may not answer queries outside of it
Additional Notes 
The model overfits the train data, limiting its ability to respond to queries not covered in the training dataset.
Supported Languages 
languages_supported (Thai), proficiency_level ()
Training Details 
Data Sources:
pythainlp/han-instruct-dataset-v2.0
Methodology:
finetuning
LLM NameGemma Han 2B
Repository 🤗https://huggingface.co/ping98k/gemma-han-2b 
Base Model(s)  Gemma 2B   unsloth/gemma-2b
Model Size2b
Required VRAM5.1 GB
Updated2025-09-23
Maintainerping98k
Model Typegemma
Instruction-BasedYes
Model Files  1.6 GB   5.0 GB: 1-of-2   0.1 GB: 2-of-2
Supported Languagesth
GGUF QuantizationYes
Quantization Typegguf
Model ArchitectureGemmaForCausalLM
Context Length8192
Model Max Length8192
Transformers Version4.39.3
Tokenizer ClassGemmaTokenizer
Padding Token<pad>
Vocabulary Size256000
Torch Data Typebfloat16

Best Alternatives to Gemma Han 2B

Best Alternatives
Context / RAM
Downloads
Likes
...os Code Instruct Finetune Test8K / 5.1 GB150
Gemma 2B Inst Aipi8K / 5.1 GB422
...ma Code Instruct Finetune Test8K / 5.1 GB100
Gemma 2B Instruct8K / 5.1 GB1320
...Code 2B Instruct Finetune Test8K / 5.1 GB160
Gita SastraGPT V18K / 5.1 GB191
Pandas Tutor Gemma 2B8K / 5.1 GB91
... 2B Finetuned Sft Navarasa 2.08K / 10 GB125325
...ma Code Instruct Finetune Test8K / 5.1 GB50
Gemma 2B Sft Preview8K / 5 GB90
Note: green Score (e.g. "73.2") means that the model is better than ping98k/gemma-han-2b.

Rank the Gemma Han 2B 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? 51567 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