Back

Subhajit Mandal

Software Developerย โ€ขย 2m

1. LoRA on a reasonably small open model (best balance for small compute): apply low-rank adapters (PEFT/LoRA). Requires less GPU memory and works well for 700โ€“3000 rows. 2. Full fine-tune (costly / heavy): only if you have >A100 GPU or cloud paid GPU. Not recommended for early MVP. 3. No-fine-tune alternative (fast & free): use retrieval + prompting (RAG) โ€” keep base LLM and add context from your 3k+ rows. Great when compute is limited.

Reply

More like this

Recommendations from Medial

Image Description

Sandeep Prasad

Business Coachย โ€ขย 2m

๐Ÿ”ฅ Government set to name ~8 Indian teams for foundational model incentives next week โ€“ second-round beneficiaries may include BharatGen; GPU access remains tight as only ~17,374 of planned 34,333 GPUs are installed so far. ๐Ÿค” Why It Matters โ€“ More

See More
Reply
2
1
Image Description
Image Description

Narendra

Willing to contribut...ย โ€ขย 14d

I fine-tuned 3 models this week to understand why people fail. Used LLaMA-2-7B, Mistral-7B, and Phi-2. Different datasets. Different methods (full tuning vs LoRA vs QLoRA). Here's what I learned that nobody talks about: 1. Data quality > Data quan

See More
2 Replies
10
1

Swamy Gadila

Founder of Friday AIย โ€ขย 4m

๐Ÿšจ Open AI is an Wrapper๐Ÿ‘€๐Ÿคฏ Hot take, but letโ€™s break it down logically: OpenAI is not a full-stack AI company โ€” itโ€™s a high-level wrapper over Azure and NVIDIA. Hereโ€™s why that matters ๐Ÿ‘‡ ๐Ÿ”น 1. Infra Backbone = Microsoft Azure Almost 90%+ of Op

See More
Reply
2
4

AI Engineer

AI Deep Explorer | f...ย โ€ขย 7m

LLM Post-Training: A Deep Dive into Reasoning LLMs This survey paper provides an in-depth examination of post-training methodologies in Large Language Models (LLMs) focusing on improving reasoning capabilities. While LLMs achieve strong performance

See More
Reply
2

AI Engineer

AI Deep Explorer | f...ย โ€ขย 7m

"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 1๏ธโƒฃ Fin

See More
Reply
1
8
Image Description

Soumya

Developerย โ€ขย 11m

๐Ÿ’กAn Idea to Change the Game for AI Startups: Making AI Processing Faster, Cheaper, and Effortless Running AI models like ChatGPT, DALLยทE, or AlphaCode is a computing monsterโ€”they need massive power to function, which makes them expensive to operate

See More
2 Replies
4
Image Description

Animesh Kumar Singh

Hey I am on Medialย โ€ขย 4m

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 More
1 Reply
2

Rahul Agarwal

Founder | Agentic AI...ย โ€ขย 1m

Fine-tune vs Prompt vs Context Engineering. Simple step-by-step breakdown for each approach. ๐—™๐—ถ๐—ป๐—ฒ-๐—ง๐˜‚๐—ป๐—ถ๐—ป๐—ด (๐— ๐—ผ๐—ฑ๐—ฒ๐—น-๐—Ÿ๐—ฒ๐˜ƒ๐—ฒ๐—น ๐—–๐˜‚๐˜€๐˜๐—ผ๐—บ๐—ถ๐˜‡๐—ฎ๐˜๐—ถ๐—ผ๐—ป) ๐—™๐—น๐—ผ๐˜„: 1. Collect Data โ†’ Gather domain-specific info (e.g., legal docs). 2. Sta

See More
Reply
2
13
Image Description
Image Description

Venkatesh

Bussiness Developmen...ย โ€ขย 12m

Winning Against the Odds: How One Small Business Secured a Tender A Dream Worth Pursuing Ravi Kumar, the founder of BuildRight Constructions, had always dreamed of taking on larger projects. However, competing against industry giants felt impossible

See More
6 Replies
4

Download the medial app to read full posts, comements and news.