200k token vocab, great for non english
https://github.com/openai/tiktoken/commit/9d01e5670ff50eb74cdb96406c7f3d9add0ae2f8
…
OPEN SOURCE
-
200k Token Vocabulary Optimized for Non-English Languages
By
–
-
Closed Source AI Has Reached Plateau in 2026
By
–
Ok so it's official closed source AI has plateaued
-
Agents 2.0 Framework Released with High Performance Benchmarks
By
–
Agents 2.0 is out, and it's already the best-performing framework using an open model 🙌
— m_ric (@AymericRoucher) 13 mai 2024
✨ Simpler: prompt, tools, and attributes are accessible
🧩 Modular: use any LLM. Llama-3-70B-Instruct is 🔥
💪 Performant w/ React Agents
Top 1 of open models on GAIA, top 4 overall. pic.twitter.com/pzbVmuXysMAgents 2.0 is out, and it's already the best-performing framework using an open model Simpler: prompt, tools, and attributes are accessible Modular: use any LLM. Llama-3-70B-Instruct is Performant w/ React Agents Top 1 of open models on GAIA, top 4 overall.
-

Alibaba Qwen1.5-110B multilingual model now available on Poe
By
–
New on Poe: Qwen1.5-110B! This multilingual model from Alibaba features comparable performance to other state-of-the-art open-source models on key benchmarks, with a particular strength in Chinese-language queries. (1/2)
-
Running LLMs locally on M1 Mac with Ollama and LM Studio
By
–
Running on Macbook M1 pro (16GB RAM) using @ollama and @LMStudioAI
. If you find this useful, RT to share it with your friends. Don't forget to follow me @Saboo_Shubham_ for more such LLMs tips and tutorials. -
LLM Apps with RAG and AI Agents GitHub Repository
By
–
Check out the cool LLM Apps with RAG and AI agents in this GitHub Repo. P.S: Don't forget to star the repo to show your support and get future updates
-

Ollama and Open WebUI: Offline LLM Chat Interface
By
–
3. Ollama + Open WebUI
— Shubham Saboo (@Saboo_Shubham_) 13 mai 2024
Combine Ollama with Open WebUI for a smooth, offline experience with a ChatGPT-like interface.
It works with various LLM runners and OpenAI-compatible APIs, all without needing the internet. pic.twitter.com/F7g1lNp1Xw3. Ollama + Open WebUI Combine Ollama with Open WebUI for a smooth, offline experience with a ChatGPT-like interface. It works with various LLM runners and OpenAI-compatible APIs, all without needing the internet.
-

Ollama: Run Multimodal AI Models Locally on Your Computer
By
–
2. Ollama
— Shubham Saboo (@Saboo_Shubham_) 13 mai 2024
Ollama is an open-source project that offers an easy way to download and run multimodal AI models such as llava and bakllava on your computer.
To get started, install Ollama and run this command in your terminal: 'ollama run llava' pic.twitter.com/wiRoxwgnbD2. Ollama Ollama is an open-source project that offers an easy way to download and run multimodal AI models such as llava and bakllava on your computer. To get started, install Ollama and run this command in your terminal: 'ollama run llava'
-

LM Studio: Run Multimodal AI Models Offline Locally
By
–
1. LM Studio
— Shubham Saboo (@Saboo_Shubham_) 13 mai 2024
LM Studio lets you operate multimodal AI models offline right on your desktop. It has a chat interface too.
Just download LM Studio, install it, and you're set to run any open-source multimodal model without an internet connection. pic.twitter.com/UozjDIDSqK1. LM Studio LM Studio lets you operate multimodal AI models offline right on your desktop. It has a chat interface too. Just download LM Studio, install it, and you're set to run any open-source multimodal model without an internet connection.
-
Run Multimodal AI Models Locally Free Without Internet
By
–
3 ways to run Multimodal AI models like GPT-4 Vision locally on your computer (100% free and without internet):