8000 NaxAlpha (Nauman Mustafa) · GitHub
[go: up one dir, main page]
Skip to content
View NaxAlpha's full-sized avatar
😎
Solving Intelligence
😎
Solving Intelligence
143 followers · 165 following

Achievements

Achievement: Pair Extraordinairex4Achievement: Pull Sharkx3Achievement: QuickdrawAchievement: YOLOAchievement: Arctic Code Vault ContributorAchievement: Starstruck

Achievements

Achievement: Pair Extraordinairex4Achievement: Pull Sharkx3Achievement: QuickdrawAchievement: YOLOAchievement: Arctic Code Vault ContributorAchievement: Starstruck

Block or report NaxAlpha

Block user

Prevent this user from interacting with your repositories and sending you notifications. Learn more about blocking users.

You must be logged in to block users.

Content in all repositories owned by your account will be closed.
Maximum 250 characters. Please don’t include any personal information such as legal names or email addresses. This note will only be visible to you.
Report abuse

Contact GitHub support about this user’s behavior. Learn more about reporting abuse.

Report abuse
NaxAlpha/README.md

Salam, I am Nauman Mustafa

8+ Years of Experience in Industry, Senior Agentic AI & Deep Learning Engineer

Please Visit my site https://nauman.im/ for details.

naxalpha

Pinned Loading

  1. Training script for LongGPT; Fine-tu... Training script for LongGPT; Fine-tunes GPT-2 (335M) on The Pile Dataset with a context size of 8k tokens. (requires > 16GB RAM)
    1 
    import time
    2 
    from contextlib import suppress
    3 
    
              
    
              
    
                4
                
    import torch
    
              
    
              
    
                5
                
    import torch.nn as nn
    
              
    
          
    
    
    
  
    

    2. 

      

  2. 
  
    
    
    
      
    
        
        Fine-tune Pythia 1.4b model for 8k c...  Fine-tune Pythia 1.4b model for 8k context window, this script requires at least 40 GB of memory, 15-20 hours of fine-tune is sufficient.      
    

          
    
              
    
                1
                
    import copy
    
              
    
              
    
                2
                
    
              
    
              
    
                3
                
    import torch
    
              
    
              
    
                4
                
    import torch.nn.functional as F
    
              
    
              
    
                5
                
    import torch.backends.cuda as cuda
    
              
    
          
    
    
    
  
    

    3. 

      
  3. 
  
    
    
    
      
    
        
    
            
          digital-sovereignty-project  digital-sovereignty-project          Public
        
    
      
    


      
    
        
      
    

      
    
      
    
    
    
  
    

    4. 

      
  4. 
  
    
    
    
      
    
        
    
            
          gpt-2xy  gpt-2xy          Public
        
    
      
    


      
    
        GPT-2 User Interface based on HuggingFace's Pytorch Implementation
      
    

      
    
          
  
  Python


          
            
    

            56
          
          
            
    

            16
          
      
    
    
    
  
    

    5. 

      
  5. 
  
    
    
    
      
    
        
    
            
          xgan  xgan          Public
        
    
      
    


      
    
        A highly customizable implementation of GAN for rapid prototyping using PyTorch
      
    

      
    
          
  
  Jupyter Notebook


          
            
    

            15
          
      
    
    
    
  
    

    6. 

      
  6. 
  
    
    
    
      
    
        
    
            
          postbox  postbox          Public
        
    
      
    


      
    
        A lightweight, self-hosted web mailbox on Cloudflare Workers. Multiple domains, private Access login, and an agent-friendly CLI.
      
    

      
    
          
  
  TypeScript


          
            
    

            3
          
      
    
    
    
  
    

    7. 












      
  
        

          
  
    
    

        

        

  





        

      





      

  


          



    




  

    

    

    





    

    

    

  


0