Vi Gemma 2 2B Function Calling by ricepaper

 »  All LLMs  »  ricepaper  »  Vi Gemma 2 2B Function Calling   URL Share it on

Vi Gemma 2 2B Function Calling is an open-source language model by ricepaper. Features: 2b LLM, VRAM: 5.2GB, Context: 8K, License: apache-2.0, Quantized, LLM Explorer Score: 0.15.

  4bit Base model:finetune:unsloth/ge... Base model:unsloth/gemma-2-2b-...   Conversational   En   Endpoints compatible   Gemma2   Quantized   Region:us   Safetensors   Sharded   Tensorflow   Trl   Unsloth   Vn

Vi Gemma 2 2B Function Calling Benchmarks

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

Vi Gemma 2 2B Function Calling Parameters and Internals

Model Type 
text-generation-inference, transformers
Use Cases 
Areas:
commercial applications, research
Applications:
chatbots, automated question answering systems, advanced natural language processing applications
Primary Use Cases:
function call execution, natural language processing tasks such as text summarization and machine translation, creating intelligent agents and multi-agent systems
Additional Notes 
The model leverages Unsloth and Huggingface's TRL library for faster training and execution.
Supported Languages 
vietnamese (optimal), english (optimal)
Training Details 
Methodology:
The model was fine-tuned from google/gemma-2-2b-it using a dataset rich in function-call format conversations (ChatML) and multilingual data translated to Vietnamese.
Input Output 
Input Format:
ChatML format with user queries
Accepted Modalities:
text
Output Format:
Function call execution results and responses
Performance Tips:
Adjust generate parameters for varying response lengths and content
LLM NameVi Gemma 2 2B Function Calling
Repository 🤗https://huggingface.co/ricepaper/vi-gemma-2-2b-function-calling 
Base Model(s)  Gemma 2 2B It Bnb 4bit   unsloth/gemma-2-2b-it-bnb-4bit
Model Size2b
Required VRAM5.2 GB
Updated2026-04-13
Maintainerricepaper
Model Typegemma2
Model Files  5.0 GB: 1-of-2   0.2 GB: 2-of-2
Supported Languagesvn en
Quantization Type4bit
Model ArchitectureGemma2ForCausalLM
Licenseapache-2.0
Context Length8192
Model Max Length8192
Transformers Version4.43.3
Tokenizer ClassGemmaTokenizer
Padding Token<pad>
Vocabulary Size256000
Torch Data Typefloat16

Best Alternatives to Vi Gemma 2 2B Function Calling

Best Alternatives
Context / RAM
Downloads
Likes
Gemma 2 2B It Bnb 4bit8K / 2.2 GB4185820
Gemma 2 2B Id Inst8K / 5.2 GB1450
Gemma 2 2B Id Instruct8K / 5.2 GB750
Gemma 2 2B Id8K / 5.2 GB570
Athena Gemma 2 2B It Philos8K / 5.2 GB200
Arnab Ft Gemma2 From Vm St V18K / 5.2 GB60
GRMR 2B Instruct8K / 5.2 GB188718
Gemma 2 2B It 4bit8K / 1.5 GB64783
Gemma 2 2B Indian Law8K / 5.2 GB114
Gemma 2 2B It Pm Ep18K / 5.2 GB70
Note: green Score (e.g. "73.2") means that the model is better than ricepaper/vi-gemma-2-2b-function-calling.

Rank the Vi Gemma 2 2B Function Calling 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? 53232 in total.

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