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

Codes 15B by seeklhy

 »  All LLMs  »  seeklhy  »  Codes 15B   URL Share it on

  21   
  Autotrain compatible   Code   Codegen   Codegen   Endpoints compatible   Gpt bigcode   Pytorch   Region:us   Sharded   Sql   Sql   Sql generation   Text2sql
Model Card on HF 🤗: https://huggingface.co/seeklhy/codes-15b 

Codes 15B Benchmarks

LLME Score: 0.10848
nn.n% — How the model compares to the reference models: Anthropic Sonnet 3.5 ("so35"), GPT-4o ("gpt4o") or GPT-4 ("gpt4").
Codes 15B (seeklhy/codes-15b)
🌟 Advertise your project 🚀

Codes 15B Parameters and Internals

Model Type 
SQL generation, Text-to-SQL
Training Details 
Methodology:
Incrementally pre-trained on top of StarCoderBase-3B
Context Length:
8192
LLM NameCodes 15B
Repository 🤗https://huggingface.co/seeklhy/codes-15b 
Model Size15b
Required VRAM62.1 GB
Updated2025-08-17
Maintainerseeklhy
Model Typegpt_bigcode
Model Files  9.9 GB: 1-of-7   9.9 GB: 2-of-7   9.8 GB: 3-of-7   9.9 GB: 4-of-7   9.8 GB: 5-of-7   9.9 GB: 6-of-7   2.9 GB: 7-of-7
Supported Languagescode
Generates CodeYes
Model ArchitectureGPTBigCodeForCausalLM
Licenseapache-2.0
Transformers Version4.32.0
Tokenizer ClassGPT2Tokenizer
Vocabulary Size49152
Torch Data Typefloat32
Activation Functiongelu

Best Alternatives to Codes 15B

Best Alternatives
Context / RAM
Downloads
Likes
WizardCoder Guanaco 15B V1.10K / 31 GB190312
WizardCoder Guanaco 15B V1.00K / 31 GB19085
WizardCoder 15B V1.00K / 31 GB1469762
MoTCoder 15B V1.00K / 30.9 GB82
Interplay AppCoder0K / 31.2 GB112
Codes 15B Spider0K / 62.1 GB100
Codes 15B Bird With Evidence0K / 62.1 GB120
Ziya Coding 15B V10K / 31.1 GB84
WizardCoderSQL 15B V1.00K / 31.2 GB151
...zardCoder 15B V1.0 Sharded 8gb0K / 62.2 GB180
Note: green Score (e.g. "73.2") means that the model is better than seeklhy/codes-15b.

Rank the Codes 15B 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? 50723 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 v20241124
  Support LLM Explorer