Picture

PS @pranabkumar_

Joined May 2012
  • Tweets
    7K
  • Followers
    255
  • Following
    2K
  • Likes
    18K
PS retweeted
UnslothAI Profile Picture

Unsloth AI @UnslothAI

a month ago

You can now run gpt-oss-120b & 20b locally with our GGUFs! 🦥 Run OpenAI's 120b model on 66GB RAM & 20b model on 14GB RAM. Both in original precision. Uploads includes our chat template fixes. Guide: docs.unsloth.ai/basics/gpt-oss GGUF: huggingface.co/unsloth/gpt-os…

OpenAI Profile Picture

OpenAI @OpenAI

a month ago

You can now run gpt-oss-120b & 20b locally with our GGUFs! 🦥 Run OpenAI's 120b model on 66GB RAM & 20b model on 14GB RAM. Both in original precision. Uploads includes our chat template fixes. Guide: docs.unsloth.ai/basics/gpt-oss GGUF: huggingface.co/unsloth/gpt-os… https://t.co/VUmkjjs5ZX

PS retweeted
AndrewYNg Profile Picture

Andrew Ng @AndrewYNg

a month ago

I'm thrilled to announce the definitive course on Claude Code, created with @AnthropicAI and taught by Elie Schoppik @eschoppik. If you want to use highly agentic coding - where AI works autonomously for many minutes or longer, not just completing code snippets - this is it.…

PS retweeted
ClementDelangue Profile Picture

clem 🤗 @ClementDelangue

a month ago

Free for @huggingface pro users: hf.co/nanotron

PS retweeted
Hesamation Profile Picture

ℏεsam @Hesamation

a month ago

Fuck ML tutorials. This is a collection of 300 ML system design case studies in real world, from Stripe, Spotify, Netflix, Meta, etc. Perfect for interviews and to learn how it’s done in the battlefield. Wish there was a similar thing for agents!

PS retweeted
ashishps_1 Profile Picture

Ashish Pratap Singh @ashishps_1

2 months ago

LeetCode was HARD until I Learned these 15 Patterns: 1. Prefix Sum 2. Two Pointers 3. Sliding Window 4. Fast & Slow Pointers 5. LinkedList In-place Reversal 6. Monotonic Stack 7. Top ‘K’ Elements 8. Overlapping Intervals 9. Modified Binary Search 10. Binary Tree Traversal 11.…

PS retweeted
AndrewYNg Profile Picture

Andrew Ng @AndrewYNg

2 months ago

New Course: Post-training of LLMs Learn to post-train and customize an LLM in this short course, taught by @BanghuaZ, Assistant Professor at the University of Washington @UW, and co-founder of @NexusflowX. Training an LLM to follow instructions or answer questions has two key…

PS retweeted
trawasthi_ai Profile Picture

Tekraj Awasthi🧑‍💻🇳🇵 @trawasthi_ai

2 months ago

PyTorch in One Hour🤖 A gem of a blog by @rasbt for you to learn all the essential concept of tensors and their usage in PyTorch🚀 Link: sebastianraschka.com/teaching/pytor…

PS retweeted
aktiwari1201 Profile Picture

anil tiwari @aktiwari1201

2 months ago

@@DrSJaishankar Sir, my son Anurag Tiwari (Passport: W4768296), hired by Synergy Ship Arabia, boarded vessel JANA 505 at Sharjah, UAE on 29.06.2025. He died the same day. No clear cause of death, no help from company. Kindly help with urgent repatriation of his body. 🙏

PS retweeted
tomaarsen Profile Picture

tomaarsen @tomaarsen

2 months ago

‼️Sentence Transformers v5.0 is out! The biggest update yet introduces Sparse Embedding models, encode methods improvements, Router module for asymmetric models & much more. Sparse + Dense = 🔥 hybrid search performance! Details in 🧵

PS retweeted
UnslothAI Profile Picture

Unsloth AI @UnslothAI

2 months ago

You can now fine-tune Gemma 3n for free with our notebook! Unsloth makes Google Gemma training 1.5x faster with 50% less VRAM and 5x longer context lengths - with no accuracy loss. Guide: docs.unsloth.ai/basics/gemma-3… GitHub: github.com/unslothai/unsl… Colab: colab.research.google.com/github/unsloth…

PS retweeted
rasbt Profile Picture

Sebastian Raschka @rasbt

2 months ago

Since it's summer, and more or less internship and tech interview season, I made all 30 chapters of my Machine Learning Q and AI book freely available for the summer: sebastianraschka.com/books/ml-q-and… Hope it’s helpful! Happy reading, and good luck if you are interviewing!

PS retweeted
UnslothAI Profile Picture

Unsloth AI @UnslothAI

2 months ago

We made a Guide on mastering LoRA Hyperparameters, so you can learn to fine-tune LLMs correctly! Learn to: • Train smarter models with fewer hallucinations • Choose optimal: learning rates, epochs, LoRA rank, alpha • Avoid overfitting & underfitting 🔗docs.unsloth.ai/get-started/fi…

PS retweeted
_avichawla Profile Picture

Avi Chawla @_avichawla

2 months ago

Let's fine-tune DeepSeek-R1 (distilled Llama) 100% locally:

PS retweeted
TheTuringPost Profile Picture

TuringPost @TheTuringPost

3 months ago

PPO and GRPO — a workflow breakdown of the most popular reinforcement learning algorithms ➡️ Proximal Policy Optimization (PPO): The Stable Learner It’s used everywhere from dialogue agents to instruction tuning as it balances between learning fast and staying safe. ▪️ How PPO…

PS retweeted
akshay_pachaar Profile Picture

Akshay 🚀 @akshay_pachaar

3 months ago

AI Engineering Hub just crossed 10k GitHub stars! It’s 100% open-source and hosts 70+ free hands-on demos. Here are 10 MCP, RAG, and AI Agents projects for AI engineers:

PS retweeted
omarsar0 Profile Picture

elvis @omarsar0

3 months ago

github.com/FareedKhan-dev…

PS retweeted
AndrewYNg Profile Picture

Andrew Ng @AndrewYNg

3 months ago

Learn to build and deploy GenAI pipelines in "Orchestrating Workflows for GenAI Applications", built in partnership with @astronomerio and taught by Kenten Danas, the company's DevRel Senior Manager, and Tamara Fingerlin, developer advocate. Many GenAI applications require…

PS retweeted
UnslothAI Profile Picture

Unsloth AI @UnslothAI

3 months ago

Finetune DeepSeek-R1-0528-Qwen3 with GRPO using our free notebook! Our new reward function increases multilingual (or custom domain) response rates by 40%+. Unsloth makes R1 finetuning 2× faster with 70% less VRAM. GitHub: github.com/unslothai/unsl… Colab: colab.research.google.com/github/unsloth…

PS retweeted
RedHat_AI Profile Picture

Red Hat AI @RedHat_AI

3 months ago

LLM Compressor just got way easier to use. You can now compress most LLMs directly from their @huggingface model definition. No need to write custom wrappers. This new autowrapper supports 95% of multimodal and decoder models out of the box. Let’s break it down 🧵:

PS retweeted
Shiwei_Liu66 Profile Picture

Shiwei Liu @Shiwei_Liu66

3 months ago

We all believe that base LLMs already know how to reason, thanks to math & code data in pre-training. So why fine-tune all parameters to learn reasoning capacity? 💡In our LIFT paper (accepted by ICML), we identify Principal Weights responsible for reasoning, and show that…

Trends for United States

Karen
117 B posts
Good Saturday
25,5 B posts
GiveRep V1
1.144 posts
#SaturdayVibes
2.661 posts
Game Day
16,4 B posts
#Caturday
3.753 posts
Ken Dryden
7.916 posts
Marlins
32,4 B posts
#OverstockIsBack
1.299 posts
#SaturdayMotivation
1.248 posts
#RevampSeriesEP3
68,1 B posts
Elizabeth Warren
45,1 B posts
FKJD FANDAY24 SG
272 B posts
Bader
22 B posts
Rachel
81,3 B posts
Fourth Amendment Workplace
The Dad
81,8 B posts
Tylenol
48,7 B posts
Hyundai
154 B posts
Rose Garden
33,8 B posts

You might like

Postdoc at The Houston Methodist Research Institute, Texas, USA Ph.D IISER Berhampur
Rishikesh Pandey
@pandeyr755
97 Followers
PhD @iitdelhi - Fellow @aiims_nd - alumni @bitshyd Structural Virology 🧬🦠 • CryoEM ❄🔬 • Travelling • Fitness she/her
Kirti Suhag
@SuhagKirti
42 Followers
Nip
@UNAVS3
15 Followers
Professor & Head, Department of Mathematics, Pt. L. M. S. Campus, Sridev Suman Uttarakhand University, Rishikesh-249201, India
Anita Tomar
@583c7047d28942c
17 Followers
Engineer/researcher/traveller/food lover Individual personality
stand_with truth
@Roshan_rising
515 Followers