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

CodeLlama 7B KStack by JetBrains

 »  All LLMs  »  JetBrains  »  CodeLlama 7B KStack   URL Share it on

  26   
  Autotrain compatible   Code   Codegen   Dataset:jetbrains/kstack   Endpoints compatible   Llama   Region:us   Safetensors   Sharded   Tensorflow
Model Card on HF 🤗: https://huggingface.co/JetBrains/CodeLlama-7B-KStack 

CodeLlama 7B KStack Benchmarks

LLME Score: 0.1866
nn.n% — How the model compares to the reference models: Anthropic Sonnet 3.5 ("so35"), GPT-4o ("gpt4o") or GPT-4 ("gpt4").
CodeLlama 7B KStack (JetBrains/CodeLlama-7B-KStack)

CodeLlama 7B KStack Parameters and Internals

Model Type 
text-generation
Use Cases 
Areas:
text-generation
Applications:
code generation for Kotlin applications
Primary Use Cases:
Kotlin code generation
Considerations:
The model is fine-tuned on a specific data format (Kotlin tasks), and deviation from this format can lead to inaccurate or undesirable responses. Developers should perform safety testing before deploying.
Additional Notes 
KStack is the largest collection of permissively licensed Kotlin code used for fine-tuning.
Supported Languages 
Kotlin (proficient)
Training Details 
Data Sources:
JetBrains/KStack
Methodology:
The model is fine-tuned with rule-based filtering on the Kotlin dataset KStack.
Hardware Used:
One A100 GPU
Responsible Ai Considerations 
Mitigation Strategies:
Developers should perform safety testing and tuning tailored to their specific applications of the model.
Input Output 
Input Format:
String input to encode Kotlin code prompts.
Accepted Modalities:
text
Output Format:
Generated text output.
Release Notes 
Version:
1.0
Notes:
Fine-tuned CodeLlama-7B on KStack dataset with Kotlin code improvements.
LLM NameCodeLlama 7B KStack
Repository 🤗https://huggingface.co/JetBrains/CodeLlama-7B-KStack 
Model Size7b
Required VRAM13.5 GB
Updated2025-02-22
MaintainerJetBrains
Model Typellama
Model Files  4.9 GB: 1-of-3   5.0 GB: 2-of-3   3.6 GB: 3-of-3
Generates CodeYes
Model ArchitectureLlamaForCausalLM
Licenseapache-2.0
Context Length16384
Model Max Length16384
Transformers Version4.39.2
Tokenizer ClassCodeLlamaTokenizer
Vocabulary Size32016
Torch Data Typebfloat16

Best Alternatives to CodeLlama 7B KStack

Best Alternatives
Context / RAM
Downloads
Likes
Deepseek Coder 6.7B Instruct16K / 13.5 GB46744377
CodeLlama 7B Hf16K / 13.5 GB70039347
CodeLlama 7B Hf16K / 13.5 GB2484484
CodeLlama 7B Instruct Hf16K / 13.5 GB43565224
CodeLlama 7B Instruct Hf16K / 13.5 GB3015640
GetCode Slerp16K / 13.6 GB17531
MathCoder2 CodeLlama 7B16K / 13.5 GB145
Wizardllama 7B16K / 13.5 GB320
CodeLlama 7B Python Hf16K / 13.5 GB6503138
CodeLlama 7B Hf16K / 13.5 GB122063
Note: green Score (e.g. "73.2") means that the model is better than JetBrains/CodeLlama-7B-KStack.

Rank the CodeLlama 7B KStack 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