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

Ziya Coding 15B V1 by IDEA-CCNL

 »  All LLMs  »  IDEA-CCNL  »  Ziya Coding 15B V1   URL Share it on

  8   
  Arxiv:2210.08590   Autotrain compatible   Codegen   En   Endpoints compatible   Gpt bigcode   Pytorch   Region:us   Sharded   Zh
Model Card on HF 🤗: https://huggingface.co/IDEA-CCNL/Ziya-Coding-15B-v1 

Ziya Coding 15B V1 Benchmarks

LLME Score: 0.11033
nn.n% — How the model compares to the reference models: Anthropic Sonnet 3.5 ("so35"), GPT-4o ("gpt4o") or GPT-4 ("gpt4").
Ziya Coding 15B V1 (IDEA-CCNL/Ziya-Coding-15B-v1)
🌟 Advertise your project 🚀

Ziya Coding 15B V1 Parameters and Internals

Model Type 
text-generation
Use Cases 
Areas:
Research, Development, Software, AI
Applications:
Code generation, Code modification, Code interpretation, NL2SQL
Primary Use Cases:
Generating and modifying code, Code interpretation, Code continuation, Instruction following
Additional Notes 
Cites detailed performance metrics achieved on HumanEval and MBPP benchmarks, showing strong results post-fine-tuning.
Supported Languages 
zh (high), en (high)
Training Details 
Data Sources:
100B tokens of high-quality corpus including Chinese, English, and code
Data Volume:
100B tokens
Methodology:
Continual pretraining, Supervised finetuning
Training Time:
10 days
Hardware Used:
144 A100 GPUs with 40GB each
Model Architecture:
StarCoderBase
Input Output 
Input Format:
Text prompt
Accepted Modalities:
text
Output Format:
Generated code and text
LLM NameZiya Coding 15B V1
Repository 🤗https://huggingface.co/IDEA-CCNL/Ziya-Coding-15B-v1 
Model Size15b
Required VRAM31.1 GB
Updated2025-08-17
MaintainerIDEA-CCNL
Model Typegpt_bigcode
Model Files  3.0 GB: 1-of-11   2.7 GB: 2-of-11   2.7 GB: 3-of-11   3.0 GB: 4-of-11   3.0 GB: 5-of-11   2.7 GB: 6-of-11   2.7 GB: 7-of-11   3.0 GB: 8-of-11   3.0 GB: 9-of-11   2.7 GB: 10-of-11   2.6 GB: 11-of-11
Supported Languageszh en
Generates CodeYes
Model ArchitectureGPTBigCodeForCausalLM
Licensegpl-3.0
Model Max Length2048
Transformers Version4.32.0
Tokenizer ClassGPT2Tokenizer
Beginning of Sentence Token<|endoftext|>
End of Sentence Token<|endoftext|>
Unk Token<|endoftext|>
Vocabulary Size49155
Torch Data Typebfloat16
Activation Functiongelu
Errorsreplace

Best Alternatives to Ziya Coding 15B V1

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
WizardCoderSQL 15B V1.00K / 31.2 GB151
Codes 15B0K / 62.1 GB219
...zardCoder 15B V1.0 Sharded 8gb0K / 62.2 GB180
Note: green Score (e.g. "73.2") means that the model is better than IDEA-CCNL/Ziya-Coding-15B-v1.

Rank the Ziya Coding 15B V1 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