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

CodeLlama 13B Python GPTQ by TheBloke

 »  All LLMs  »  TheBloke  »  CodeLlama 13B Python GPTQ   URL Share it on

  93   
  Arxiv:2308.12950   4-bit   Autotrain compatible   Code   Codegen   Custom code   Gptq   Llama   Llama2   Quantized   Region:us   Safetensors
Model Card on HF 🤗: https://huggingface.co/TheBloke/CodeLlama-13B-Python-GPTQ 

CodeLlama 13B Python GPTQ Benchmarks

LLME Score: 0.13703
nn.n% — How the model compares to the reference models: Anthropic Sonnet 3.5 ("so35"), GPT-4o ("gpt4o") or GPT-4 ("gpt4").
CodeLlama 13B Python GPTQ (TheBloke/CodeLlama-13B-Python-GPTQ)

CodeLlama 13B Python GPTQ Parameters and Internals

Model Type 
text generation, code synthesis
Use Cases 
Areas:
commercial use, research use
Applications:
code synthesis, code understanding
Primary Use Cases:
Python programming
Limitations:
Out-of-scope uses include languages other than English.
Considerations:
The potential outputs cannot be predicted in advance; developers should perform safety testing.
Additional Notes 
Code Llama is a collection of pretrained and fine-tuned generative text models ranging in scale from 7 billion to 34 billion parameters.
Supported Languages 
Python (Specialist)
Training Details 
Data Sources:
Uses the same data as Llama 2 with different weights.
Methodology:
Fine-tuning specific to tasks such as code synthesis and Python specialization.
Hardware Used:
A100-80GB, TDP of 350-400W
Model Architecture:
Optimized transformer architecture
Safety Evaluation 
Methodologies:
See safety evaluations in Section 4 of the research paper.
Ethical Considerations:
Should perform safety testing and tuning tailored to specific applications.
Responsible Ai Considerations 
Mitigation Strategies:
Responsible Use Guide available at https://ai.meta.com/llama/responsible-user-guide
Input Output 
Input Format:
Text input
Accepted Modalities:
text
Output Format:
Text generation
Release Notes 
Version:
7B Python
Notes:
Designed for general code synthesis and understanding.
LLM NameCodeLlama 13B Python GPTQ
Repository 🤗https://huggingface.co/TheBloke/CodeLlama-13B-Python-GPTQ 
Model NameCodeLlama 13B Python
Model CreatorMeta
Base Model(s)  codellama/CodeLlama-13b-python-hf   codellama/CodeLlama-13b-python-hf
Model Size13b
Required VRAM7.3 GB
Updated2024-12-22
MaintainerTheBloke
Model Typellama
Model Files  7.3 GB
Supported Languagescode
GPTQ QuantizationYes
Quantization Typegptq
Generates CodeYes
Model ArchitectureLlamaForCausalLM
Licensellama2
Context Length16384
Model Max Length16384
Transformers Version4.32.0
Tokenizer ClassLlamaTokenizer
Beginning of Sentence Token<s>
End of Sentence Token</s>
Unk Token<unk>
Vocabulary Size32000
Torch Data Typefloat16

Best Alternatives to CodeLlama 13B Python GPTQ

Best Alternatives
Context / RAM
Downloads
Likes
CodeLlama 13B Instruct GPTQ16K / 7.3 GB34539
...zardCoder Python 13B V1.0 GPTQ16K / 7.3 GB9375
CodeLlama 13B GPTQ ERP16K / 7 GB702
NexusRaven 13B GPTQ16K / 7.3 GB317
MAmmoTH Coder 13B GPTQ16K / 7.3 GB183
CodeLlama 13B GPTQ16K / 7.3 GB11911
...deLlama 13B Oasst Sft V10 GPTQ16K / 7.3 GB3713
WhiteRabbitNeo 13B V116K / 26 GB1767404
CodeLlama 13B Python Fp1616K / 26 GB152125
CodeLlama 13B Instruct Fp1616K / 26 GB200629
Note: green Score (e.g. "73.2") means that the model is better than TheBloke/CodeLlama-13B-Python-GPTQ.

Rank the CodeLlama 13B Python GPTQ 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? 40066 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 v20241217
  Support LLM Explorer