Het 👽

@soham901x Tnx soham ✨

@het_bhalani Happy Birthday 🎉 🎂

It’s balloons day✨

@JAY_VEGAD_ Thank u bhai✨

@het_bhalani Happy birthday bhai 🥳

This is elon musk

"If it walks like a duck and quacks like a duck, it's a duck."

@NILAY1556 Dreams

@het_bhalani Kaha hen bata bhai...me bhi aa raha hu, yaha kuch nahi rakha

Grass?? Decided to touch sand today!

@danliu Eyo, ass some more slop and ads

nobody is asking the important question about github: what if MICROSOFT built github??

@stevibe Add some ✨✨✨

How slow does a 128B DENSE model run locally? Qwen3 27B and Gemma 31B are the popular dense models everyone tests. But what happens when you 4x the params? Mistral Medium 3.5 128B, side-by-side on 4x4090 vs 4x5090 vs RTX PRO 6000 vs DGX Spark: 🔴4x4090: 12.06 tok/s decode, 680ms TTFT 🟢4x5090: 19.57 tok/s decode, 572ms TTFT 🟡PRO 6000: 18.12 tok/s decode, 538ms TTFT 🟣DGX Spark: 2.58 tok/s decode, 2243ms TTFT

@techwith_ram Used unsloth, llama fac, peft! Other three is yet to explore

6 Open-Source Libraries to FineTune LLMs 1. Unsloth GitHub: github.com/unslothai/unsl… → Fastest way to fine-tune LLMs locally → Optimized for low VRAM (even laptops) → Plug-and-play with Hugging Face models 2. Axolotl GitHub: github.com/OpenAccess-AI-… → Flexible LLM fine-tuning configs → Supports LoRA, QLoRA, multi-GPU → Great for custom training pipelines 3. TRL (Transformer Reinforcement Learning) GitHub: github.com/huggingface/trl → RLHF, DPO, PPO for LLM alignment → Built on Hugging Face ecosystem → Essential for post-training optimization 4. DeepSpeed GitHub: github.com/microsoft/Deep… → Train massive models efficiently → Memory + speed optimization → Industry standard for scaling 5. LLaMA-Factory GitHub: github.com/hiyouga/LLaMA-… → All-in-one fine-tuning UI + CLI → Supports multiple models (LLaMA, Qwen, etc.) → Beginner-friendly + powerful 6. PEFT GitHub: github.com/huggingface/pe… → Fine-tune with minimal compute → LoRA, adapters, prefix tuning → Best for cost-efficient training Save this for future use.

I also want to try codex & claude code, but don’t have money to spend 😕

Seems like @sama is on vacation

@soham901x Now u r just finding ways to ghost me anyways

@het_bhalani whenever i get placed, will ghost u just to watch u touch more and more sand 😂

@soham901x I know u are going to be placed in a good company and you will refer me

@het_bhalani Placement prep when?

@HemantDotDev Which monitor do you have mate??

Day 113/ 150 >Locked in for 3hrs >Started building AI Course builder(day11) >clg 9 to 4 #100DaysOfCode

A beautiful piece of engineering in action.

@Orihime_chan0 It’s me

Never seen an animation perfectly summarize the sheer comfort of hiding in the corner 😭

@NILAY1556 Taste of my own medicine 😆

@het_bhalani Badhu j sara vala thai jase bhai

I have lost 4 games in a row in chess🙂

@Het1501 Exactly

@het_bhalani Dunning-kruger effect

The more i know the more i realise how much i don’t know