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

Codegemma 1.1 7B It AWQ by TechxGenus

 »  All LLMs  »  TechxGenus  »  Codegemma 1.1 7B It AWQ   URL Share it on

  78   
  4-bit   Autotrain compatible   Awq   Endpoints compatible   Gemma   Quantized   Region:us   Safetensors   Sharded   Tensorflow
Model Card on HF 🤗: https://huggingface.co/TechxGenus/codegemma-1.1-7b-it-AWQ 

Codegemma 1.1 7B It AWQ Benchmarks

LLME Score: 0.1858
nn.n% — How the model compares to the reference models: Anthropic Sonnet 3.5 ("so35"), GPT-4o ("gpt4o") or GPT-4 ("gpt4").
Codegemma 1.1 7B It AWQ (TechxGenus/codegemma-1.1-7b-it-AWQ)

Codegemma 1.1 7B It AWQ Parameters and Internals

Model Type 
text-to-code, text-to-text, code completion, code generation, instruction following, chat
Use Cases 
Areas:
Research, Development, Education
Applications:
Code Completion, Code Generation, Code Conversation, Code Education
Primary Use Cases:
IDE code completion, Code chat applications, Interactive learning
Limitations:
Training data limitations, Inherent limitations of LLMs
Additional Notes 
Model implements rigorous safety filtering.
Supported Languages 
Primary Language (English), Code Languages (C++, C#, Go, Java, JavaScript, Kotlin, Python, Rust)
Training Details 
Data Sources:
Public code repositories, Open source mathematics datasets, Synthetically generated code
Data Volume:
500 to 1000 billion tokens
Methodology:
FIM Pretrained
Hardware Used:
TPUv5e
Safety Evaluation 
Methodologies:
structured evaluations, internal red-teaming
Risk Categories:
cyber-offence capabilities, representational harms, large-scale harms
Input Output 
Input Format:
Natural language text or prompt, code prefix/suffix
Accepted Modalities:
Text
Output Format:
Code and natural language
LLM NameCodegemma 1.1 7B It AWQ
Repository 🤗https://huggingface.co/TechxGenus/codegemma-1.1-7b-it-AWQ 
Base Model(s)  google/codegemma-1.1-7b-it   google/codegemma-1.1-7b-it
Model Size7b
Required VRAM7.2 GB
Updated2025-02-22
MaintainerTechxGenus
Model Typegemma
Model Files  6.6 GB: 1-of-2   0.6 GB: 2-of-2
AWQ QuantizationYes
Quantization Typeawq
Model ArchitectureGemmaForCausalLM
Licensegemma
Context Length8192
Model Max Length8192
Transformers Version4.40.0
Tokenizer ClassGemmaTokenizer
Padding Token<pad>
Vocabulary Size256000
Torch Data Typefloat16

Best Alternatives to Codegemma 1.1 7B It AWQ

Best Alternatives
Context / RAM
Downloads
Likes
Codegemma 7B AWQ8K / 7.2 GB50
SeaLLM 7B V2.5 AWQ8K / 7.2 GB1282
Gemma 1.1 7B It AWQ8K / 7.2 GB770
SeaLLM 7B V2.5 AWQ8K / 5.6 GB90
CodeGemma 7B AWQ8K / 7.2 GB780
Gemma Ko 7B AWQ8K / 5.6 GB870
Gemma 7B It AWQ8K / 7.2 GB770
Gemma 7B It AWQ8K / 7.2 GB722
Gemma 7B AWQ8K / 7.2 GB690
...t Cleaner Gemma 32k Merged 16b31K / 17.1 GB50
Note: green Score (e.g. "73.2") means that the model is better than TechxGenus/codegemma-1.1-7b-it-AWQ.

Rank the Codegemma 1.1 7B It AWQ 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