TGTGInsighttelegram intelligenceLIVE / telegram public index
← GitHub Trends

TGINSIGHT SIMILAR POSTS

Find similar content

Source channel @githubtrending · Post #14845 · Jun 20

#jupyter_notebook#ai#artificial_intelligence#chatgpt#deep_learning#from_scratch#gpt#language_model#large_language_models#llm#machine_learning#python#pytorch#transformer You can learn how to build your own large language model (LLM) like GPT from scratch with clear, step-by-step guidance, including coding, training, and fine-tuning, all explained with examples and diagrams. This approach mirrors how big models like ChatGPT are made but is designed to run on a regular laptop without special hardware. You also get access to code for loading pretrained models and fine-tuning them for tasks like text classification or instruction following. This helps you deeply understand how LLMs work inside and lets you create your own functional AI assistant, gaining practical skills in AI development[1][2][3][4]. https://github.com/rasbt/LLMs-from-scratch

Results

1 similar post found

Search: #communitynotes

当前筛选 #communitynotes清除筛选
News and Tips

@NEWS_AND_TIPS · Post #2362 · 05/26/2024, 05:46 PM

Telegram #FactCheck Feature Spotted in Code. We spotted some interesting code snippets that hint at a new "Fact Check" being in development. Here's what we found: 1. A dedicated area within the application for users to access fact-checking tools or information. 2. Fact-Check Submission and Editing: Users might be able to submit facts to be checked, edit their submissions, and delete them. 3. Fact-Checking Dialogs: Dialog boxes to interact with the fact-checking process, perhaps to confirm submissions, display detailed information, or edit entries. 4. User Notifications: Notifications and messages to inform users about the status of their fact-checks (submitted, edited, deleted). 5. Informational and Placeholder Text: Text elements providing explanations about fact-checking, as well as placeholders in input fields to guide user input. 6. Toast Messages: Instant feedback to users through toast notifications about actions taken related to fact-checking. Overall, these string resources suggest that the application is enhancing its functionality to include comprehensive fact-checking features, allowing users to engage with, submit, and manage fact-checked information. Note : Based on limited code, the exact functionality of the Fact Check feature is not yet clear. #Factcheck#Communitynotes#Beta