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

Code 33B AWQ by TheBloke

 »  All LLMs  »  TheBloke  »  Code 33B AWQ   URL Share it on

  11   
  4-bit   Autotrain compatible   Awq Base model:ajibawa-2023/code-3... Base model:quantized:ajibawa-2...   Code Dataset:ajibawa-2023/code-74k-...   En   Llama   Quantized   Region:us   Safetensors   Sharded   Tensorflow
Model Card on HF 🤗: https://huggingface.co/TheBloke/Code-33B-AWQ 

Code 33B AWQ Benchmarks

LLME Score: 0.15021
nn.n% — How the model compares to the reference models: Anthropic Sonnet 3.5 ("so35"), GPT-4o ("gpt4o") or GPT-4 ("gpt4").
Code 33B AWQ (TheBloke/Code-33B-AWQ)

Code 33B AWQ Parameters and Internals

Model Type 
llama
Use Cases 
Areas:
Code generation in multiple programming languages
Applications:
Research, Educational Purposes
Primary Use Cases:
Code generation with explanation in languages such as Python, Java, JavaScript, Go, C++, Rust
Limitations:
May make mistakes in code generation
Considerations:
Use with caution; verify generated code.
Additional Notes 
High proficiency in generating and explaining code.
Supported Languages 
en (Proficient)
Training Details 
Data Sources:
Python-Code-23k-ShareGPT, Code-74k-ShareGPT
Data Volume:
74,000 codes
Methodology:
Full fine-tuning with Vicuna/ShareGPT format
Context Length:
2048
Training Time:
3 epochs, 6 days & 5 hours
Hardware Used:
4 x A100 80GB
Model Architecture:
Llama-1
Input Output 
Input Format:
This is a conversation with your helpful AI assistant. AI assistant can generate Code in various Programming Languages along with necessary explanation. Context You are a helpful AI assistant. USER: {prompt} ASSISTANT:
Accepted Modalities:
Text input
Output Format:
Generated code with explanations
Performance Tips:
Using AWQ models on NVidia GPUs can enhance performance.
LLM NameCode 33B AWQ
Repository 🤗https://huggingface.co/TheBloke/Code-33B-AWQ 
Model NameCode 33B
Model CreatorFeynman Innovations
Base Model(s)  Code 33B   ajibawa-2023/Code-33B
Model Size33b
Required VRAM17.6 GB
Updated2025-02-22
MaintainerTheBloke
Model Typellama
Model Files  10.0 GB: 1-of-2   7.6 GB: 2-of-2
Supported Languagesen
AWQ QuantizationYes
Quantization Typeawq
Model ArchitectureLlamaForCausalLM
Licensecc-by-nc-nd-4.0
Context Length2048
Model Max Length2048
Transformers Version4.36.0.dev0
Tokenizer ClassLlamaTokenizer
Beginning of Sentence Token<s>
End of Sentence Token</s>
Unk Token<unk>
Vocabulary Size32000
Torch Data Typefloat16

Best Alternatives to Code 33B AWQ

Best Alternatives
Context / RAM
Downloads
Likes
...eepseek Coder 33B Instruct AWQ16K / 18.1 GB1709935
Everyone Coder 33B Base AWQ16K / 18.1 GB122
WhiteRabbitNeo 33B V1 AWQ16K / 18.1 GB311
WizardCoder 33B V1.1 AWQ16K / 18.1 GB265
Deepseek Coder 33B Base AWQ16K / 18.1 GB314
Python Code 33B AWQ2K / 17.6 GB111
Vicuna 33B Coder AWQ2K / 17.6 GB101
Vicuna 33B AWQ2K / 17.6 GB172
Fin Llama 33B AWQ2K / 17.6 GB225
CAMEL 33B Combined Data AWQ2K / 17.6 GB182
Note: green Score (e.g. "73.2") means that the model is better than TheBloke/Code-33B-AWQ.

Rank the Code 33B 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? 43508 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