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

Gemma 2 2B It Ud by IDinsight

 »  All LLMs  »  IDinsight  »  Gemma 2 2B It Ud   URL Share it on

  16   
Base model:adapter:google/gemm... Base model:google/gemma-2-2b-i...   Conversational Dataset:idinsight/urgency dete...   En   Endpoints compatible   Gemma2   Peft   Region:us   Safetensors   Sharded   Tensorflow
Model Card on HF 🤗: https://huggingface.co/IDinsight/gemma-2-2b-it-ud 

Gemma 2 2B It Ud Benchmarks

LLME Score: 0.20972
nn.n% — How the model compares to the reference models: Anthropic Sonnet 3.5 ("so35"), GPT-4o ("gpt4o") or GPT-4 ("gpt4").
Gemma 2 2B It Ud (IDinsight/gemma-2-2b-it-ud)

Gemma 2 2B It Ud Parameters and Internals

Model Type 
Instruction-tuned, text-generation
Use Cases 
Areas:
research, commercial applications
Primary Use Cases:
Determining whether a user message is an urgent or non-urgent maternal-health related message
Limitations:
Training Data: Biases or gaps in the training data can lead limitations. Context and Task Complexity., Language Ambiguity and Nuance, Factual Accuracy, Common Sense
Considerations:
The quality and diversity of the training data influence the model's capabilities.
Supported Languages 
en (English)
Training Details 
Data Sources:
IDinsight/urgency_detection_maternal_health_synthetic
Hardware Used:
NVIDIA A100 80 GB
Responsible Ai Considerations 
Fairness:
LLMs trained on large-scale, real-world text data can reflect socio-cultural biases embedded in the training material. These models underwent careful scrutiny, input data pre-processing described and posterior evaluations reported in this card.
Transparency:
This model card summarizes details on the models' architecture, capabilities, limitations, and evaluation processes.
Accountability:
Transparency and Accountability for responsibly developed open model offers innovation sharing opportunity by making LLM technology accessible to developers and researchers across the AI ecosystem.
Mitigation Strategies:
Perpetuation of biases: encourage continuous monitoring (using evaluation metrics, human review) and exploration of de-biasing techniques during model training, fine-tuning. Generation of harmful content: guidelines for content safety essential. Misuse for malicious purposes: education on technical limitations and preventing misuse is essential. Privacy violations: ensure adherence to privacy regulations.
Input Output 
Input Format:
List of urgency rules and a user message.
Accepted Modalities:
text
Output Format:
JSON
LLM NameGemma 2 2B It Ud
Repository 🤗https://huggingface.co/IDinsight/gemma-2-2b-it-ud 
Base Model(s)  Gemma 2 2B It   google/gemma-2-2b-it
Model Size2b
Required VRAM5.2 GB
Updated2025-02-22
MaintainerIDinsight
Model Typegemma2
Model Files  5.0 GB: 1-of-2   0.2 GB: 2-of-2
Supported Languagesen
Model ArchitectureGemma2ForCausalLM
Licensemit
Context Length8192
Model Max Length8192
Transformers Version4.44.0
Is Biasednone
Tokenizer ClassGemmaTokenizer
Padding Token<eos>
Vocabulary Size256000
PEFT TypeLORA
PEFT Target Modulesq_proj|up_proj|v_proj|o_proj|gate_proj|k_proj|down_proj
LoRA Alpha32
LoRA Dropout0.05
R Param64
Torch Data Typebfloat16

Best Alternatives to Gemma 2 2B It Ud

Best Alternatives
Context / RAM
Downloads
Likes
SJT 2B128K / 5.2 GB130
SILMA Kashif 2B Instruct V1.012K / 5.2 GB270414
Gemma 2 2B It8K / 5.2 GB421819908
Gemma 2 2B8K / 10.5 GB182986487
Gemma 2 2B Jpn It8K / 5.2 GB14320162
2 PRYMMAL ECE 2B SLERP V18K / 15.8 GB12290
...emma 2 2B It Chinese Kyara DPO8K / 15.7 GB763110
Gemma2Slerp2 2.6B8K / 5.3 GB1882
SJT 2B V1.18K / 5.3 GB501
GWQ2b8K / 5.2 GB6010
Note: green Score (e.g. "73.2") means that the model is better than IDinsight/gemma-2-2b-it-ud.

Rank the Gemma 2 2B It Ud 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? 43470 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 v20241227
  Support LLM Explorer