Back

Anonymous

Anonymous

Hey I am on Medial • 16d

any developer here? what's the best way to fine tune the mvp text based chat bot model I got two data 1. main data 700 rows 2. data for fine tune more than 3000+ rows feeling problems downloading the local model is there more ways in starting I need free options please

1 replies2 likes
Replies (1)

More like this

Recommendations from Medial

Image Description
Image Description

Chamarti Sreekar

Passionate about Pos... • 1m

Another open-source model has arrived, and it’s even better than DeepSeek-V3. The Allen Institute for AI just introduced Tülu 3 (405B) 🐫, a post-training model that is a fine-tune of Llama 3.1 405B, which outperforms DeepSeek V3.

10 replies29 likes
14

Aditya Karnam

Hey I am on Medial • 8d

"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 More
0 replies
1
Image Description
Image Description

Lingeshwaran

Looking at objective... • 11m

IDEA : AI Training Data generator A Developer Platform which is much specify for AI-ML field to achieve various tasks like Analysis, Generation and Segmentation of real time data across data like text, image, audio, video that requires heavy and hig

See More
6 replies5 likes

Baqer Ali

AI agent developer |... • 19d

Latest update to my Jarvis Today I have added some features to my jarvis to make it more special and more sophisticated Now my jarvis can do the linkdin post which is done with the help of making automation. Added few agents which means like thi

See More
0 replies5 likes

Bhoop singh Gurjar

AI Deep Explorer | f... • 7h

"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 More
0 replies7 likes
1
Image Description

Chahit Sanghvi

Modern Marwadi Entre... • 5m

If I were to offer 1 GB of data at ₹5, with no expiry, and similar plans for higher data amounts at a hotspot location, would this model appeal to consumers? Is there a market need for such a service, where data affordability and flexibility are prio

See More
2 replies1 like
Anonymous
Image Description

Huge announcement from Meta. Welcome Llama 3.1🔥 This is all you need to know about it: The new models: - The Meta Llama 3.1 family of multilingual large language models (LLMs) is a collection of pre-trained and instruction-tuned generative models

See More
1 replies4 likes
1

Aryan patil

Video editor, lyrici... • 1y

In traditional programming, the focus is on using rules and data to find answers. This is typically represented as rules + data = answers. In contrast, AI/ML takes a different approach: Answers + data = rules. In AI/ML, we train models by providing

See More
0 replies4 likes

Bhushan Pungliya

 • 

Varlyq Technologies • 4m

🌐 Russia Hits Google with a $2.5 Decillion Fine! 🌐 Russia has slapped Google with a jaw-dropping fine of $2.5 decillion for not restoring 17 Russian TV channels on YouTube. To put it simply, that’s a number so astronomical, it surpasses the total

See More
0 replies3 likes
Image Description
Image Description

Vrushali

Aspiring commerce pr... • 10m

Ever happened to you. You are surrounded by millions of people all day. Have friends to talk. Family to support. Everything's fine but that feeling you need to get out of the comfort are try what keeps you up at night. I may say I'm not alone but I n

See More
9 replies4 likes

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