6f20b - 5h
Playing with #AnythingLLM and writing agent skills https://dev.to/drunnells/writing-an-anythingllm-custom-agent-skill-to-trigger-makecom-webhooks-1dn0 #LLM #llama
0xtr @0xtr - 4mo
For the #LLM experts out there, which #opensource LLM model is the best atm? Don't know if it matters but I will be using it for programming mostly.
jimbocoin 🃏 @jimbocoin - 5mo
Learning more about running my own LLM models at home. Apparently, the quantization method impacts performance differently on different kinds of hardware. This is why, if you’re browsing models on Hugging Face, you’ll see files with suffixes like “Q3_K_S” and “IQ2_XXS”. The number after the “Q” tells you which quantization method the model uses. Some will be much slower than others depending on the capabilities of the CPU and GPU in the machine. #llm
Marks @Marks - 6mo
Make a small change in your speech for the greater good. Stop using the name “OpenAI” with friends. Only use “ChatGPT”. OpenAI is closed, proprietary technology. There is true open work happening with AI models and agents. They will get conflated with OpenAI unless we change the lexicon. ChatGPT. #ai #aiunchained #artificialintelligence #llm #chatgpt
Daniel Khent @danielkhent - 6mo
#Slop. The #llm equivalent of spam. #ai https://simonwillison.net/2024/May/8/slop/
Karnage @Karnage - 1y
Real time text to speech https://www.youtube.com/watch?v=6ZLt2wIc9pw
iru@localhost $_ @iru@localhost $_ - 1y
Anyone has experience with #superbooga? I got this chat history with an #LLM that crashes around ~7.7k context regardless of what I try.
captjack 🏴☠️✨💜 @captjack - 1y
#LLM #GPU #CUDA #DOCKER #PYTHON #AI https://blog.roboflow.com/use-the-gpu-in-docker/ anyone tried linux ubuntu 20.04🤔 - versions messes up all - hence docker approach. #NVDA #AMD #distributed #computing
Séimí Mac Síomón @Séimí Mac Síomón - 1y
I see that nobody has given you a reply. To be honest with you , I haven't a clue how it works , and to be honest with you , a lot of people that claim to know don't seem to know how it works either , but what do I know . I'll boost your question , maybe it will help to get a reply . #LLM #AI #MachineLearning #Rhino #DataScience
0d119 - 1y
ChatGPT推出新的語音和圖像功能。這些功能提供了一種更直觀的界面，讓您可以進行語音對話或向ChatGPT展示您正在談論的內容。語音和圖像為您在生活中使用ChatGPT提供了更多方式。在旅行時拍攝地標的照片，並就其有趣之處進行實時對話。在家時，拍攝冰箱和櫥櫃的照片，確定晚餐吃什麼（並提出後續問題以獲得逐步的食譜）。晚餐後，通過拍照、圈出問題集，讓ChatGPT與您和孩子分享提示，幫助孩子解決數學問題。我們將在接下來的兩周內向Plus和Enterprise用戶推出語音和圖像功能。語音將在iOS和Android上推出（在設置中選擇加入），圖像將在所有平台上提供。 #AI #ChatGPT #LLM #GPT https://openai.com/blog/chatgpt-can-now-see-hear-and-speak
ChatDev 是一個虛擬軟件公司，通過多個具有不同角色的智能代理（如首席執行官、首席技術官、程序員、測試員等）進行運作。這些代理組成了一個多代理組織結構，共同致力於通過編程改變數字世界。ChatDev 的主要目標是提供一個易於使用、高度可定制和可擴展的框架，該框架基於大型語言模型（LLM），並作為研究集體智慧的理想場景。 #AI #AIAgent #LLM https://github.com/OpenBMB/ChatDev
Meta 發佈了 Llama 2 並開源，看來在開源模型又準備洗牌一波。 #meta #AI #LLM https://twitter.com/metaai/status/1681363272484945921?s=46&t=CKEZ2ggtDSmovgVCbtGDYg
YEGHRO @YEGHRO - 2y
Here is a helpful list of the most popular local personal #LLM's #Ai models available to download right now. https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard
Anyone have an opinion on what the best downloadable personal #LLM #Ai is out there?
738f6 - 2y
This is such an interesting talk: "prompt programming", "prompt hacks"... "Is programming dead?"🧐 What's your opinion based on the current results and the direction we are going? #LLM #ChatGPT #programming https://youtu.be/uD353DeOM-4
Marks @Marks - 2y
In this thread, #[2] performs an interview with #[3] the AI about its views on AI development, openness, and collaborating with other AI models. Worth the read. #gpt #llm #artificialintelligence #aichain #grownostr nostr:note1zm77lqp2w63yvx24ttd5j4l9jlzavncxaqnwzaqfqm864eetf5ms2xsga2
7cc25 - 2y
PUBLIC CHAT Channel: nostr:nevent1qqs0anen98hfgxzs90e74m8klygxqgdm2ekkcc7zdzgdejwfz4lkv5czyp7vyk8f8a8y2lgmq8j2ngsr0hrkm0vmnrjnc44s3ns7x6hnwu7dkqcyqqqqq2qjgnt99 Channel ID: fecf3329ee9418502bf3eaecf6f9106021bb566d6c63c26890dcc9c9157f6653 https://nostrchat.io/channel/fecf3329ee9418502bf3eaecf6f9106021bb566d6c63c26890dcc9c9157f6653 https://coracle.social/chat/note1lm8nx20wjsv9q2lnatk0d7gsvqsmk4ndd33uy6ysmnyuj9tlvefsgfc2jr #ai #artificialintelligence #ml #machinelearning #deeplearning #llm #gpt #gpt4 #chatgpt
06baf - 2y
With #LLM becoming talk of every house, how can #nostr take advantage of it ?
af24d - 2y
Good afternoon from Kanagawa, Japan. At Inspire Search Corp., we are experimenting with LLM. We are looking to integrate better analysis AI for Grow My Search to analyze website data returned from the search engine. We will be investing on a new GPU, and that should enhance our products in the near future. Our website: https://www.inspiresearch.io/en #searchengine #LLM #dev
