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

CodeUp Llama 2 13B Chat HF GGML by TheBloke

 »  All LLMs  »  TheBloke  »  CodeUp Llama 2 13B Chat HF GGML   URL Share it on

  35   

CodeUp Llama 2 13B Chat HF GGML is an open-source language model by TheBloke. Features: 13b LLM, VRAM: 5.5GB, License: llama2, Quantized, LLM Explorer Score: 0.09.

  Arxiv:2106.09685 Base model:finetune:juyongjian... Base model:juyongjiang/codeup-...   Codegen   En   Ggml   Llama   Multilingual-code-generation   Quantized   Region:us
Model Card on HF 🤗: https://huggingface.co/TheBloke/CodeUp-Llama-2-13B-Chat-HF-GGML 

CodeUp Llama 2 13B Chat HF GGML Benchmarks

LLME Score: 0.08901
nn.n% — How the model compares to the reference models: Anthropic Sonnet 3.5 ("so35"), GPT-4o ("gpt4o") or GPT-4 ("gpt4").
CodeUp Llama 2 13B Chat HF GGML (TheBloke/CodeUp-Llama-2-13B-Chat-HF-GGML)
🌟 Advertise your project 🚀

CodeUp Llama 2 13B Chat HF GGML Parameters and Internals

Model Type 
text-to-code, multilingual-code-generation
Use Cases 
Areas:
code-specific domain tasks, academic research
Applications:
code generation tasks across multiple programming languages
Primary Use Cases:
Collaborative code generation, Code-specific learning and emergent task performance
Limitations:
Not specifically designed for general domain., May require specific environments or dependencies to run effectively.
Additional Notes 
Aims to develop open-source, instruction-following LLMs for the code domain.
Training Details 
Data Sources:
data/code_alpaca_20k.json
Data Volume:
19K instructions filtered to high-quality from 20K
Methodology:
Parameter-efficient fine-tuning using methods like LoRA.
Hardware Used:
a single RTX 3090
Model Architecture:
Llama 2 with instruction-following adaptation.
Input Output 
Input Format:
Instruction prompts in Alpaca style.
Accepted Modalities:
text
Output Format:
Generated code snippets in a specified or default (Python) programming language.
Performance Tips:
For improved performance, ensure high-quality and clear instruction prompts.
LLM NameCodeUp Llama 2 13B Chat HF GGML
Repository 🤗https://huggingface.co/TheBloke/CodeUp-Llama-2-13B-Chat-HF-GGML 
Model NameCodeUp Llama 2 13B Chat HF
Model CreatorDeepSE
Base Model(s)  CodeUp Llama 2 13B Chat Hf   deepse/CodeUp-Llama-2-13b-chat-hf
Model Size13b
Required VRAM5.5 GB
Updated2026-04-03
MaintainerTheBloke
Model Typellama
Model Files  5.5 GB   6.9 GB   6.3 GB   5.7 GB   7.4 GB   8.2 GB   7.9 GB   7.4 GB   9.0 GB   9.8 GB   9.2 GB   9.0 GB   10.7 GB   13.8 GB
Supported Languagesen
GGML QuantizationYes
Quantization Typeggml
Model ArchitectureAutoModel
Licensellama2

Best Alternatives to CodeUp Llama 2 13B Chat HF GGML

Best Alternatives
Context / RAM
Downloads
Likes
Llama 2 13B Chat GGML0K / 5.5 GB170695
RuGPT 3.5 13B GGML0K / 7.4 GB108
Llama 2 13B GGML0K / 5.5 GB106174
RuGPT 3.5 13B GGML0K / 7.4 GB515
MythoMax L2 13B GGML0K / 5.5 GB1182
CodeLlama 13B GGML0K / 5.7 GB633
...zardCoder Python 13B V1.0 GGML0K / 5.7 GB1422
UndiMix V2 13B GGML0K / 5.5 GB372
...rca Platypus WizardLM 13B GGML0K / 5.5 GB56
...penBuddy Llama2 13B V11.1 GGML0K / 5.5 GB65
Note: green Score (e.g. "73.2") means that the model is better than TheBloke/CodeUp-Llama-2-13B-Chat-HF-GGML.

Rank the CodeUp Llama 2 13B Chat HF GGML 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? 52473 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.
Check out Ag3ntum — our secure, self-hosted AI agent for server management.
Release v20260328a
  Support LLM Explorer