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 Wukong 2B by RESMPDEV

 »  All LLMs  »  RESMPDEV  »  Gemma Wukong 2B   URL Share it on

  78   

Gemma Wukong 2B is an open-source language model by RESMPDEV. Features: 2b LLM, VRAM: 5.1GB, Context: 8K, License: other, HF Score: 44.6, LLM Explorer Score: 0.16, Arc: 45.3, HellaSwag: 66.9, MMLU: 38.1, TruthfulQA: 44.3, WinoGrande: 62.6, GSM8K: 10.1.

  Arxiv:1705.03551   Arxiv:1804.06876   Arxiv:1804.09301   Arxiv:1809.02789   Arxiv:1811.00937   Arxiv:1904.09728   Arxiv:1905.07830   Arxiv:1905.10044   Arxiv:1907.10641   Arxiv:1911.01547   Arxiv:1911.11641   Arxiv:2009.03300   Arxiv:2009.11462   Arxiv:2101.11718   Arxiv:2107.03374   Arxiv:2108.07732   Arxiv:2109.07958   Arxiv:2110.08193   Arxiv:2110.14168   Arxiv:2203.09509   Arxiv:2206.04615   Arxiv:2304.06364   Arxiv:2312.11805   Conversational   Endpoints compatible   Gemma   Model-index   Pytorch   Region:us   Safetensors   Sharded   Tensorflow
Model Card on HF 🤗: https://huggingface.co/RESMPDEV/Gemma-Wukong-2b 

Gemma Wukong 2B Benchmarks

ARC: 45.31 vs 96.7 (so35)-53.1%
HellaSwag: 66.94 vs 95.3 (gpt4)-29.8%
MMLU: 38.1 vs 88.3 (so35)-56.9%
TruthfulQA: 44.29 vs 59 (gpt4)-24.9%
WinoGrande: 62.59 vs 87.5 (gpt4)-28.5%
GSM8K: 10.08 vs 96.4 (so35)-89.5%
LLME Score: 0.15663
nn.n% — How the model compares to the reference models: Anthropic Sonnet 3.5 ("so35"), GPT-4o ("gpt4o") or GPT-4 ("gpt4").
Gemma Wukong 2B (RESMPDEV/Gemma-Wukong-2b)
🌟 Advertise your project 🚀

Gemma Wukong 2B Parameters and Internals

Model Type 
text generation, decoder-only, large language model
Use Cases 
Areas:
Content Creation and Communication, Research and Education
Applications:
Text Generation, Chatbots and Conversational AI, Text Summarization, Natural Language Processing (NLP) Research, Language Learning Tools, Knowledge Exploration
Primary Use Cases:
Generating creative text formats, Customer service interfaces, Summarizing documents
Limitations:
Limited by training data biases and diversity, Open-ended tasks may be challenging
Considerations:
Developers should ensure responsible use, comply with privacy laws, and respect prohibitions on misuse.
Additional Notes 
Gemma models leverage Google's advanced TPU hardware and JAX for optimized performance; they encourage democratization of AI access and innovation.
Supported Languages 
English (fluent)
Training Details 
Data Sources:
teknium OpenHeremes-2.5 dataset, Cognitive Computations' selected datasets
Data Volume:
6 trillion tokens
Methodology:
3 epochs over 4 3090's
Hardware Used:
4 3090 GPUs
Model Architecture:
State-of-the-art open models, text-to-text, decoder-only
Safety Evaluation 
Methodologies:
red-teaming, structured evaluations
Risk Categories:
Text-to-Text Content Safety, Text-to-Text Representational Harms, Memorization, Large-scale harm
Ethical Considerations:
Within acceptable thresholds for categories such as child safety, content safety, representational harms, memorization, large-scale harms.
Responsible Ai Considerations 
Fairness:
Careful scrutiny and pre-processing of input data, posterior evaluations for bias and fairness issues.
Transparency:
Detailed model architecture, capabilities, limitations, and evaluation processes are disclosed.
Accountability:
Developers and users must adhere to privacy regulations, using privacy-preserving techniques.
Mitigation Strategies:
Continuous monitoring, human review, de-biasing techniques, guidelines for content safety.
Input Output 
Input Format:
Text string, such as a question, a prompt, or document to be summarized.
Accepted Modalities:
text
Output Format:
Generated English-language text response.
Performance Tips:
Ensure inputs match expected format for improved performance, reduce complexity for better results.
LLM NameGemma Wukong 2B
Repository 🤗https://huggingface.co/RESMPDEV/Gemma-Wukong-2b 
Model Size2b
Required VRAM5.1 GB
Updated2026-04-08
MaintainerRESMPDEV
Model Typegemma
Model Files  5.0 GB: 1-of-2   0.1 GB: 2-of-2
Model ArchitectureGemmaForCausalLM
Licenseother
Context Length8192
Model Max Length8192
Transformers Version4.39.0.dev0
Tokenizer ClassGemmaTokenizer
Padding Token<pad>
Vocabulary Size256000
Torch Data Typebfloat16

Best Alternatives to Gemma Wukong 2B

Best Alternatives
Context / RAM
Downloads
Likes
Gemma 1.1 2B It8K / 5.1 GB80705172
Gemma 1.1 2B It8K / 5 GB1793
Codegemma 2B8K / 5.1 GB1174697
Gita SastraGPT V18K / 5.1 GB81
Caca Tinny 2B V38K / 5.1 GB41
Pandas Tutor Gemma 2B8K / 5.1 GB41
Gemma Qlora Customer Support8K / 5.1 GB200
Octopus V28K / 5.1 GB1387885
Octopus V28K / 5.1 GB478890
Bge Reranker V2 Gemma8K / 10 GB2318683
Note: green Score (e.g. "73.2") means that the model is better than RESMPDEV/Gemma-Wukong-2b.

Rank the Gemma Wukong 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? 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