[HN Gopher] Phi-4 Bug Fixes
       ___________________________________________________________________
        
       Phi-4 Bug Fixes
        
       Author : danielhanchen
       Score  : 9 points
       Date   : 2025-01-10 21:17 UTC (1 hours ago)
        
 (HTM) web link (unsloth.ai)
 (TXT) w3m dump (unsloth.ai)
        
       | danielhanchen wrote:
       | Hey HN family! I found a few bugs for Phi-4 - Microsoft's latest
       | MIT licensed LLM to be on par with GPT-4o mini
       | 
       | 1. End of sentence should be <|im_end|> not <|endoftext|>
       | 
       | 2. Chat template should not auto add an assistant prompt
       | 
       | 3. Padding token should not be EOS but <|dummy_87|>
       | 
       | I also converted Phi-4 to Llama-arch. I uploaded GGUFs, 4bit
       | quants, dynamic quants and all fixes to
       | https://huggingface.co/unsloth
       | 
       | I also made a Colab notebook to finetune Phi-4 on a free GPU:
       | https://colab.research.google.com/github/unslothai/notebooks...
        
       ___________________________________________________________________
       (page generated 2025-01-10 23:00 UTC)