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

Codegen25 7B Multi Gguf With Dummy Tokenizer by sokada

 »  All LLMs  »  sokada  »  Codegen25 7B Multi Gguf With Dummy Tokenizer   URL Share it on

  80   
  Arxiv:2305.02309   Autotrain compatible   Code   Dataset:bigcode/starcoderdata   Endpoints compatible   F16   F32   Ggml   Gguf   Llama   Pytorch   Q4   Quantized   Region:us
Model Card on HF 🤗: https://huggingface.co/sokada/codegen25-7b-multi-gguf-with-dummy-tokenizer 

Codegen25 7B Multi Gguf With Dummy Tokenizer Benchmarks

LLME Score: 0.12781
nn.n% — How the model compares to the reference models: Anthropic Sonnet 3.5 ("so35"), GPT-4o ("gpt4o") or GPT-4 ("gpt4").
Codegen25 7B Multi Gguf With Dummy Tokenizer (sokada/codegen25-7b-multi-gguf-with-dummy-tokenizer)
🌟 Advertise your project 🚀

Codegen25 7B Multi Gguf With Dummy Tokenizer Parameters and Internals

Model Type 
autoregressive language model, program synthesis
Use Cases 
Areas:
research, program synthesis
Applications:
code completion, code synthesis, autocompletion
Primary Use Cases:
Program synthesis - generating executable code from comments
Limitations:
May generate code verbatim from training data, Attribution required for generated code
Considerations:
Use responsibly, ensure proper attribution for generated code
Additional Notes 
This model is part of the CodeGen2.5 series focusing on efficient program synthesis with smaller model sizes.
Supported Languages 
programming_languages_supported (multiple), natural_languages_supported ()
Training Details 
Data Sources:
bigcode/starcoderdata
Data Volume:
1.4T tokens
Methodology:
Trained for program synthesis, capable of infilling, supports multiple languages
Model Architecture:
Autoregressive
Input Output 
Input Format:
Natural language and code-based prompts
Accepted Modalities:
text
Output Format:
Generated code snippets
Performance Tips:
Ensure prompts are clear and in the format of comments for best results.
LLM NameCodegen25 7B Multi Gguf With Dummy Tokenizer
Repository 🤗https://huggingface.co/sokada/codegen25-7b-multi-gguf-with-dummy-tokenizer 
Model Size7b
Required VRAM45.6 GB
Updated2025-08-17
Maintainersokada
Model Typellama
Model Files  4.2 GB   13.8 GB   27.6 GB
Supported Languagescode
GGML QuantizationYes
GGUF QuantizationYes
Quantization Typegguf|ggml|q4
Model ArchitectureLlamaForCausalLM
Licenseapache-2.0
Context Length2048
Model Max Length2048
Transformers Version4.29.2
Tokenizer ClassCodeGen25Tokenizer
Vocabulary Size51200
Torch Data Typefloat32

Best Alternatives to Codegen25 7B Multi Gguf With Dummy Tokenizer

Best Alternatives
Context / RAM
Downloads
Likes
Chef Ai32K / 14.4 GB90
...lumiX 32K Instruct Q4 K M GGUF32K / 4.1 GB243
PULI LlumiX 32K Q4 K M GGUF32K / 4.1 GB161
Openthaigpt 1.0.0 7B Chat4K / 13.7 GB153616
Chinese Llama 2 7B Gguf4K / 2.6 GB10185
...hat Hf Phr Mental Therapy GGUF4K / 1.5 GB190
Llama GGUF4K / 13.5 GB220
...7B Chat Hf Function Calling V24K / 13.5 GB2162137
Llama2 7b Gguf Yakovlev4K / 7.2 GB90
Llama2 7B Text Sql Gguf4K / 4.1 GB570
Note: green Score (e.g. "73.2") means that the model is better than sokada/codegen25-7b-multi-gguf-with-dummy-tokenizer.

Rank the Codegen25 7B Multi Gguf With Dummy Tokenizer 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