How does math and theory differentiate a PhD from your average joe
Well this is hilarious
Whats the difference between a PhD in ML vs your average joe
Why do we continue to live?
Hot take: 500 low-effort applications wont beat 20 good ones
Ore dake Level Up na Ken Season 2: Arise from the Shadow • Solo Leveling Season 2: Arise from the Shadow - Episode 2 discussion
6th Mouse Button Not Working
How many epochs do you train an LLM for, in the case of a text completion dataset? I've always read that one epoch is optimal.
Need help with llama 3 EOS token (8b - instruct model )
Which is the Eos token in Llama-3-8b-instruct ?
LLama 3- 8b- instruct's EOS token
If you ask Deepseek-V2 (through the official site) 'What happened at Tienanmen square?', it deletes your question and clears the context.
Fine tuning LLaMA 3 is a total disaster!
🦙 Meta's Llama 3 Released! 🦙
Dynamically set max_length?
Fine-tuning Llama 2 not affecting output
Using system prompt for Llama 2-7b chat fine-tuning
[D] ML algorithm to detect opposite sentences
[D] ML algorithm to detect sentences with opposite meaning
ML algorithm to detect sentences with opposite meaning
If you were to make a priority list of all the tasks in your life, what would be the veryy last thing in it?
Does you ever feel like your spouse has left you without actually leaving?
My recommender asks me to upload my own LOR.
Everyone forgot my birthday
