Melvin Vivas PRO

thanks, i was looking at the wrong license file

@John6666 can the Distil-PII be used for commercial purposes? I am thinking of creating an open source python library but not sure if I can control usage for those who will download it?

I checked the license and it says it's llama 3.2 and you just need to inform Meta if users reach 700M MAU

"2. Additional Commercial Terms. If, on the Llama 3.2 version release date, the monthly active users
of the products or services made available by or for Licensee, or Licensee’s affiliates,
is greater than 700 million monthly active users in the preceding calendar month, you must request
a license from Meta"

Did I understand the license correctly?

thank you, I'll try these first. really appreciate the help!

I saw this. Is this good enough? https://huggingface.co/mradermacher/Distil-PII-Llama-3.2-1B-Instruct-GGUF

thank you so much for the detailed reply. i was checking the deployment guide for https://huggingface.co/distil-labs/Distil-PII-Llama-3.2-1B-Instruct but it's not available in their website anymore

i made mine. too embarassing to post 😂

thank you for this!

wow. that's so fast. what gpu are you using?

Hi, I was trying this in Google Colab and I got a memory issue. How much vram does this need? Sorry just new to this

Is there an easy way to know how much vram is required to train a model from the HF model card?

Thanks

from trl import SFTTrainer
from datasets import load_dataset

trainer = SFTTrainer(
    model="Qwen/Qwen3-0.6B",
    train_dataset=load_dataset("trl-lib/Capybara", split="train"),
)
trainer.train()```

yeah I tried llama.cpp. was curious how to running the model from transformers code. i also tried llama-cpp-python which can do an inference of the model from your own code

what is this flag for? --mmproj

thank you. i agree. since i have my gpu in windows, that took time to setup too. yeah it’s a small model which works locally. trying to do more tests