LLM EXPLORER 59,420 MODELS INDEXED

CodeLlama 13B GPTQ by TheBloke

By TheBloke · 62 downloads
HF Repo ↗ Copy URL

CodeLlama 13B GPTQ is an open-source language model by TheBloke. Features: 13b LLM, VRAM: 7.3GB, Context: 16K, License: llama2, Quantized, Code Generating, LLM Explorer Score: 0.08.

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

CodeLlama 13B GPTQ Parameters and Internals

Model Type 
text-generation
Use Cases 
Areas:
Research, Commercial applications
Primary Use Cases:
Code synthesis, Code understanding
Limitations:
Use in languages other than English is not advised
Additional Notes 
Code Llama includes variations optimized for specific needs: general code synthesis, Python focus, and instruction following for safe deployment.
Training Details 
Data Volume:
Not specified
Methodology:
Uses an optimized transformer architecture
Training Time:
January 2023 - July 2023
Hardware Used:
A100-80GB GPUs
Model Architecture:
Auto-regressive language model
Safety Evaluation 
Methodologies:
Safety evaluations as per Section 4 of the research paper
Ethical Considerations:
Testing conducted to date has been in English. The model may produce inaccurate or objectionable responses.
Responsible Ai Considerations 
Fairness:
Conducted limited testing. Potential biases in English and code contexts.
Mitigation Strategies:
Developers should perform safety testing and tuning tailored to their specific applications.
Input Output 
Input Format:
Text
Output Format:
Generated text
LLM NameCodeLlama 13B GPTQ
Repository 🤗https://huggingface.co/TheBloke/CodeLlama-13B-GPTQ 
Model NameCodeLlama 13B
Model CreatorMeta
Base Model(s)  CodeLlama 13B Hf   codellama/CodeLlama-13b-hf
Model Size13b
Required VRAM7.3 GB
Updated2026-08-03
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 Size32016
Torch Data Typefloat16

Best Alternatives to CodeLlama 13B GPTQ

Best Alternatives
Context / RAM
Downloads
Likes
NexusRaven 13B GPTQ16K / 7.3 GB357
CodeLlama 13B GPTQ ERP16K / 7 GB43
...zardCoder Python 13B V1.0 GPTQ16K / 7.3 GB19976
MAmmoTH Coder 13B GPTQ16K / 7.3 GB43
CodeLlama 13B Instruct GPTQ16K / 7.3 GB7539
...deLlama 13B Oasst Sft V10 GPTQ16K / 7.3 GB4313
CodeLlama 13B Python GPTQ16K / 7.3 GB1920
WhiteRabbitNeo 13B V116K / 26 GB3146453
CodeLlama 13B Python Fp1616K / 26 GB12125
CodeLlama 13B Fp1616K / 26 GB967
Note: green Score (e.g. "73.2") means that the model is better than TheBloke/CodeLlama-13B-GPTQ.