Pranav

@therealjoeykoen @0xSero How do you get this metric

@0xSero I'm already at 1 billion tokens for $15

Deepseek-v4-pro 0.45B tokens for 6.74$

@kavya_manohar @huggingface Hey, I’m working around with Ml-TTS model how can I contact you

I am genuinely proud to have played a part in this. We have 8 ASR models released as part of the Vividh stack!! Check out the blog on @huggingface .

@sid250581 @Sapient_Int Thanks telling letting me know, waiting for results

Thanks for asking. when we get into root of medical notes it is messy and long range documents, nested entities etc.The bidirectional attention over the input helps the model better understand the full context. and also it's tiny to deploy on device(1B) just gets into a curiosity to fine tune first especially in medical.that's it

the only ubuntu user among mac users. this is how i got into mlx india chennai. fine-tuned @Sapient_Int HRM-Text-1B on nvidia/Nemotron-PII for medical PII de-identification. as far as i can tell, nobody has fine-tuned this model before. what made it non-trivial: HRM is a PrefixLM, not a standard causal LM. the checkpoint ships with legacy fused weights (gqkv_proj, gate_up_proj) that don't map to the current transformers implementation. had to write a custom conversion layer to get zero missing weights Next I will be publishing the full code and a step-by-step guide soon shoutout to @sabeshbharathi for organizing this amazing event

@thsottiaux Gpt

How do you refer to it

Codex reset soon

@0xSero Coming to Nuremberg?

Bavaria is heavenly.

Built something. it works. i’m suspicious of it

@Zer0_Seconds Do let me know after you tryout the application 🤝

@Pranav_ai Of course.... Hope it won't name me fall in love with uni... Trying to drop out

@Zer0_Seconds Would you love to give it a try

@Pranav_ai Wow... This is cool

@pan_rye Consistency and accountability

building in public is a mindset. it’s not just showing code or progress. it’s showing up daily—even when nothing’s working. that’s the real flex.

@algozeus_ Supervise, before changing any code, tell ai your needs , ask plan and outcomes. If you happy with it let the ai make the changes.

what are your vibe coding habits / tips / hacks?

@zuess05 That’s it 😂 nothing more

Building SaaS is just • fix bug • add feature • tweak copy • fight imposter syndrome • check if anyone signed up • repeat And somehow it’s still super fun🥸

@TechNerd556 Interesting one

I wish someone would build a UI component library inspired by Apple’s design system, on top of shadcn UI.

@clembn I always wonder the same thing

how do y’all have 10,000 posts on X? how much time do you spend here everyday?

@mehula_7 Lock in 🔒

Time to lock in, fine shyt 🔒

@MawaliYousuf96 Sure I will DM you

@Pranav_ai share the link and let me your first tester

@Peropunk Tough schedule 🫡

9-5: College 🎒 6-7: Meeting with Investor 💵 7-8: Meeting with Clients 🧰 8-1: Internship & Coding 💗

@AdairY27154 Thanks brother

@Pranav_ai Wishing the best of luck to you!

@Abhinavstwt @cursor_ai No issues for me, used college mail id

Received this email from Cursor. We just can’t have nice things here in India because of some rotten people 🥲. Now even cursor has flagged all Indian students as fraudsters @cursor_ai