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

Codegemma 7B by google

 »  All LLMs  »  google  »  Codegemma 7B   URL Share it on

  5959   
  Autotrain compatible   Endpoints compatible   Gemma   Region:us   Safetensors   Sharded   Tensorflow

Codegemma 7B Benchmarks

ARC: 53.92 vs 96.7 (so35)-44.2%
HellaSwag: 76.73 vs 95.3 (gpt4)-19.5%
MMLU: 56.59 vs 88.3 (so35)-35.9%
TruthfulQA: 38.03 vs 59 (gpt4)-35.5%
WinoGrande: 69.61 vs 87.5 (gpt4)-20.4%
GSM8K: 45.49 vs 96.4 (so35)-52.8%
HumanEvalA: 30.6
Python Eva: 40.13 vs 92 (so35)-56.4%
Java Eval: 35.03
Javascript: 43.06
CPP Eval: 40.34
PHP Eval: 34.76
Julia Eval: 28.91
D Eval: 10.44
Lua Eval: 32.88
R Eval: 20.96
Racket Eva: 13.55
Rust Eval: 34.56
Swift Eval: 32.62
LLME Score: 0.28098
nn.n% — How the model compares to the reference models: Anthropic Sonnet 3.5 ("so35"), GPT-4o ("gpt4o") or GPT-4 ("gpt4").

Codegemma 7B Parameters and Internals

Model Type 
text-to-text, text-to-code, decoder-only
Use Cases 
Areas:
Research, Commercial applications
Applications:
Code Completion, Code Generation, Code Conversation, Code Education
Primary Use Cases:
Code completion with IDE extension, Interactive code learning experiences
Limitations:
Limitations of LLMs based on training data., Potential representational harms.
Considerations:
See Gemma model card for comprehensive considerations.
Additional Notes 
The model is built for Responsible AI development with a focus on open code applications.
Supported Languages 
English (Fluent)
Training Details 
Data Sources:
Publicly available code repositories, Open source mathematics datasets, Synthetically generated code
Data Volume:
500 billion tokens
Methodology:
FIM, PSM/SPM modes
Hardware Used:
TPUvs5e
Model Architecture:
Not explicitly mentioned
Safety Evaluation 
Methodologies:
Internal red-teaming, Structured evaluations
Risk Categories:
Human safety, Representational harms, Cyber-offence capabilities
Ethical Considerations:
Testing autonomous hacking capabilities and ensuring potential harms are limited.
Responsible Ai Considerations 
Fairness:
Human evaluation on prompts covering content safety and representational harms.
Transparency:
Discussions and evaluations are detailed in the Gemma model card.
Accountability:
Developed by Google, accountable for outputs under their AI principles.
Mitigation Strategies:
Controlled through structured evaluations and internal red-teaming.
Input Output 
Input Format:
For pretrained model: code prefix and/or suffix for code completion and generation.
Accepted Modalities:
text
Output Format:
For instruction-tuned model: code and natural language
Performance Tips:
Ensure correct usage of FIM tokens in prompts.
LLM NameCodegemma 7B
Repository 🤗https://huggingface.co/google/codegemma-7b 
Model Size7b
Required VRAM17.1 GB
Updated2024-11-21
Maintainergoogle
Model Typegemma
Model Files  5.0 GB: 1-of-4   5.0 GB: 2-of-4   5.0 GB: 3-of-4   2.1 GB: 4-of-4
Model ArchitectureGemmaForCausalLM
Licensegemma
Context Length8192
Model Max Length8192
Transformers Version4.39.3
Tokenizer ClassGemmaTokenizer
Padding Token<pad>
Vocabulary Size256000
Torch Data Typebfloat16
Codegemma 7B (google/codegemma-7b)

Quantized Models of the Codegemma 7B

Model
Likes
Downloads
VRAM
Codegemma 7B GGUF01903 GB

Best Alternatives to Codegemma 7B

Best Alternatives
Context / RAM
Downloads
Likes
Kaggle Math Model Gemma V112K / 17.1 GB60
Gemma 1.1 7B It8K / 17.1 GB16633265
SeaLLM 7B V2.58K / 17.1 GB1376749
Codegemma 7B It8K / 17.1 GB28375201
Zephyr 7B Gemma V0.18K / 17.1 GB970121
SauerkrautLM Gemma 7B8K / 17.1 GB691913
DiscoPOP Zephyr 7B Gemma8K / 17.1 GB516936
Gemma 7B Aps It8K / 17.1 GB18524
Gemma Mling 7B8K / 17.8 GB181713
Gemma 7B Openhermes V0.808K / 17 GB57051
Note: green Score (e.g. "73.2") means that the model is better than google/codegemma-7b.

Rank the Codegemma 7B 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? 38149 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 v20241110
  Support LLM Explorer