عزالدين's picture

1 1 4

عزالدين

logame07

·

AI & ML interests

None yet

Recent Activity

reacted to MikeDoes's post with 🔥 about 1 month ago

🌟 Day 4: Two Models, One Privacy Mission! 🌟 The PII-Masking-1M series rolls on with two gems: Categorical: https://huggingface.co/ai4privacy/llama-ai4privacy-multilingual-categorical-anonymiser-openpii Redaction: https://huggingface.co/ai4privacy/llama-ai4privacy-multilingual-anonymiser-openpii Join us in protecting data everywhere! #AI #Privacy #OpenSource #Multilingual

liked a model about 1 month ago

ds4sd/SmolDocling-256M-preview

reacted to Jaward's post with 👍 about 2 months ago

made a few improvements on custom grpo trainer: - added sequence similarity reward (seems to work) - improved vllm support (5x inference speed) - adjusted reward scores (this helped with format/accuracy) - can now push to hf hub (already pushed mine lol: https://huggingface.co/Jaward/smollm2_360m_grpo_gsm8k_reasoner) Code: https://github.com/Jaykef/ai-algorithms/blob/main/smollm2_360M_135M_grpo_gsm8k.ipynb

View all activity

Organizations

None yet

logame07's activity

New activity in microsoft/phi-2 over 1 year ago

How to fine-tune this? + Training code

#19 opened over 1 year ago by