CodeGen RE by shailja

 ยป  All LLMs  ยป  shailja  ยป  CodeGen RE   URL Share it on

  Autotrain compatible   Codegen   Endpoints compatible   Pytorch   Region:us
Model Card on HF ๐Ÿค—: https://huggingface.co/shailja/CodeGen-RE 

CodeGen RE Benchmarks

nn.n% — How the model compares to the reference models: Anthropic Sonnet 3.5 ("so35"), GPT-4o ("gpt4o") or GPT-4 ("gpt4").
CodeGen RE (shailja/CodeGen-RE)

CodeGen RE Parameters and Internals

Model Type 
code understanding, question answering
Additional Notes 
This model is trained to understand code semantics and can answer questions related to the purpose and language of C or C++ code, particularly decompiled code from Ghidra.
Training Details 
Data Sources:
decompiled ghidra C source code
Input Output 
Accepted Modalities:
text
Output Format:
text
LLM NameCodeGen RE
Repository ๐Ÿค—https://huggingface.co/shailja/CodeGen-RE 
Model Size6b
Required VRAM28.8 GB
Updated2025-03-27
Maintainershailja
Model Typecodegen
Model Files  28.8 GB   0.0 GB
Generates CodeYes
Model ArchitectureCodeGenForCausalLM
Licensemit
Model Max Length2048
Transformers Version4.25.0.dev0
Tokenizer ClassGPT2Tokenizer
Vocabulary Size50295
Torch Data Typefloat16
Activation Functiongelu_new

Best Alternatives to CodeGen RE

Best Alternatives
Context / RAM
Downloads
Likes
Nsql 6B0K / 28.4 GB13152
...egen 6B Nl Lora Adapter Merged0K / 14.3 GB151
...en 6B Mono Lora Adapter Merged0K / 14.3 GB140
Diff Codegen 6B V20K / 14.3 GB30437
Codegen 6B Multi0K / 14.3 GB271720
...en 6B Mono Instruct Py Revised0K / 28.4 GB132
...n 6B Mono Instruct Py Critique0K / 28.4 GB102
...gen 6B Nl Instruct Py Critique0K / 28.4 GB111
Codegen 6B Nl0K / 14.3 GB19894
Fine Tuned Codegen 6B Verilog0K / 28.4 GB3332
Note: green Score (e.g. "73.2") means that the model is better than shailja/CodeGen-RE.

Rank the CodeGen RE Capabilities

๐Ÿ†˜ 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! ๐ŸŒŸ

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? 45631 in total.

Our Social Media →  
Original data from HuggingFace, OpenCompass and various public git repos.
Release v20241227