GPT-J-6B – A 6 billion parameter, autoregressive text generation model
Points: 636 | Comments: 146 | Author: canada_dry
Is Sanskrit the most token-efficient language? A quantitative study using GPT, Gemini, and…
Tokens are the basic units of Large Language Models (LLMs). LLMs rely on tokenizers to segment text into these tokens, and tokenization is the primary determinant of computational and inference cost. Sanskrit, one of the oldest languages, is hypothes...
Show HN: BBC “In Our Time”, categorised by Dewey Decimal, heavy lifting by GPT
Points: 688 | Comments: 171 | Author: genmon
ChatGPT español: gratis, online y sin registro
Prueba ChatGPT español de forma gratuita sin necesidad de registrarte. ChatTide te ofrece un chatbot inteligente basado en GPT. ¡Comienza a chatear con IA al instante!
如何评价 OpenAI 8 月 6 日推出的开源模型 gpt-oss？和国产开源模型 …
Aug 5, 2025 · 有老哥在M1 ultra上测试了，token速度还可以。 最后，开源这个模型，对于OpenAI来说很重要，因为终于它Open了一把，但是对于整个开源大模型社区，意义不是特别大，只是现有技术的 …
10 cách dùng ChatGPT - OpenAI Chat miá» n phí tại Viá»t Nam
Apr 22, 2024 · ChatGPT (OpenAI chat gpt) Äang trá» thành má»t trào lÆ°u tại Viá»t Nam. Äây là trí tuá» nhân tạo AI sá» dụng trên trình duyá»t web và chÆ°a có ứng dụng chính thức. Sau Äây là â¦
chat GPTè¿ 2 å¹´æ´æ°äº 7 个çæ¬ï¼åªä¸ªæ好ç¨ï¼ - ç¥ä¹
èGPT 4oå¯ä»¥åçå¯ä»¥æ´å¤ï¼å®å¯ä»¥è¯»wordææ¡£ï¼excelè¡¨æ ¼ï¼pptæ件ï¼pdfææ¡£ï¼åç§å¾çççã è¿ç§è½åèµäºäºå®å¤é¢æçä½ç¨ï¼å 为工ä½ä¸å¾å¤äºæ ä¾èµäºå¤§éçæ件ï¼å¾é¾ç¨å å¥è¯ â¦
Shaunwei/RealChar
?️?Create, Customize and Talk to your AI Character/Companion in Realtime (All in One Codebase!). Have a natural seamless conversation with AI everywhere (mobile, web and terminal) using LLM OpenAI GPT3.5/4, Anthropic Claude2, Chroma Vector DB, Whisper Speech2Text, ElevenLabs Text…
GPT Takes the Bar Exam
Nearly all jurisdictions in the United States require a professional license exam, commonly referred to as "the Bar Exam," as a precondition for law practice. To even sit for the exam, most jurisdictions require that an applicant completes at least s...
Target Identification Using Dictionary Matching of Generalized Polarization Tensors
The aim of this paper is to provide a fast and efficient procedure for (real-time) target identification in imaging based on matching on a dictionary of precomputed generalized polarization tensors (GPTs). The approach is based on some important prop...
BlinkDL/AI-Writer
AI 写小说，生成玄幻和言情网文等等。中文预训练生成模型。采用我的 RWKV 模型，类似 GPT-2 。AI写作。RWKV for Chinese novel generation. (⭐ 3575)
How is walter writes AI STILL bypassing AI detectors like Turnitin & GPTzero??
my friend’s working on an ai detector startup and we’ve been digging into how different humanizers handle rewriting. so far, walterwrites.ai is the only one we’ve tested that consistently passes...
TobiasMue91/tobiasmue91.github.io
GPTGames - Simple HTML, JS, CSS games and tools created with the help of ChatGPT and Claude. (⭐ 51)
taishi-i/awesome-ChatGPT-repositories - GitHub
2 days ago · ? chatgpt-corpus - ⭐ 951 / ChatGPT 中文语料库 对话语料 小说语料 客服语料 用于训练大模型 ? awesome-gpt - ⭐ 1.1k / ? An awe-inspiring collection of resources, encompassing a wide range …
ChatGPT 中文指南 - GitHub
ChatGPT 中文指南，ChatGPT 中文调教指南，指令指南，精选资源清单，更好的使用 chatGPT 让你的生产力 up up up! - GitHub - kqyun/GPTcn: ChatGPT 中文指南，ChatGPT 中文调教指南，指令指 …
Got fake citations from Claude and ChatGPT. How do you handle nonfiction research?
Two days ago I completely stalled out trying to write a detailed lit review for a project. I thought Claude and GPT-4o could at least round up some sources to get me started. On the surface, their lis...
JThyroff/WideGPT
Widen GPT Answer Space (⭐ 10)
Open Sourcing GPTs: Economics of Open Sourcing Advanced AI Models
This paper explores the economic underpinnings of open sourcing advanced large language models (LLMs) by for-profit companies. Empirical analysis reveals that: (1) LLMs are compatible with R&D portfolios of numerous technologically differentiated fir...
Beating GPT-4 on HumanEval with a fine-tuned CodeLlama-34B
Points: 813 | Comments: 284 | Author: rushingcreek
karpathy/nanoGPT
The simplest, fastest repository for training/finetuning medium-sized GPTs. (⭐ 54307)