Hey I am on Medial • 4m
"Just fine-tuned LLaMA 3.2 using Apple's MLX framework and it was a breeze! The speed and simplicity were unmatched. Here's the LoRA command I used to kick off training: ``` python lora.py \ --train \ --model 'mistralai/Mistral-7B-Instruct-v0.2' \ -
See MoreAI Deep Explorer | f... • 3m
"A Survey on Post-Training of Large Language Models" This paper systematically categorizes post-training into five major paradigms: 1. Fine-Tuning 2. Alignment 3. Reasoning Enhancement 4. Efficiency Optimization 5. Integration & Adaptation 1️⃣ Fin
See MoreFounder of Friday AI • 2m
Introducing Friday — An Emotionally Intelligent AI Fine-Tuned to Feel. We didn’t build an LLM from scratch. We did something smarter. We took a state-of-the-art pre-trained model and fine-tuned it with 1 million emotionally rich, real-world tokens
See MoreHey I am on Medial • 15d
The "AI Personality Forge: Product :"Cognate" Cognate is not an AI assistant. It's a platform on your phone or computer that lets you forge, train, and deploy dozens of tiny, specialized AI "personalities" for specific tasks in seconds. How it wo
See MoreJust go with the flo... • 3m
The secret to creating an error free AI is the main science behind ai is we give output and we have a expected output in between we have a fine layer in which we have neural network we need to increase the neural network in the layers instead of add
See MoreHelping Artists Find... • 5m
Exposed: The Truth Behind Volkai – Is It Truly India Made AI? So, I recently dug into the buzz around Volkai, the AI company gaining fame as India’s very own innovation in the AI space. Everyone's been hyping it up for being completely built from
See MoreDownload the medial app to read full posts, comements and news.