afrideva@afri_deva
Joined December 2021
22 Photos and videos
CPU based offline multimodal inference on an Android phone. Original model from @NousResearch, quantization done by @nisten
5
10
73
5,090
CPU based offline multimodal inference on an Android phone. Original model from @NousResearch, quantization done by @nisten
5
10
73
5,090
nisten
@nisten
29 Oct 2023
@altryne How to run obsidian-multimodal. Just copy paste this in your terminal and press enter. git clone -b stablelm-support github.com/Galunid/llama.cpp… && \ cd llama.cpp && \ make && \ wget huggingface.co/nisten/obsidi… && \ wget huggingface.co/nisten/obsidi… && \ ./server -m obsidian-q6.gguf --mmproj mmproj-obsidian-f16.gguf -ngl 42
9
1,307
afrideva retweeted
Sasha Rush
@srush_nlp
12 Oct 2023
Vector databases have raised billions offering hosted management of text embeddings. What are you revealing in these vectors ? 🔒 We demonstrate a practical method for full recovery of 90% of sentence length embeddings (arxiv.org/abs/2310.06816).
13
90
612
114,050
simonwillison.net/2023/Mar/1…

Stanford Alpaca, and the acceleration of on-device large language model development

On Saturday 11th March I wrote about how Large language models are having their Stable Diffusion moment. Today is Monday. Let’s look at what’s happened in the past three days. …

simonwillison.net
12
726
The Bitcoin whitepaper is now available in Oshiwambo (both Oshikwanyama and Oshindonga) thanks to a collaborative effort with @LandifaBitcoin and a few other Namibian Bitcoiners.
2
36
98
Any recommendations for open source self-sovereign identity/authority/reputation solutions that work across EVM blockchains?
4
7
@ceramicnetwork looks appealing for general identity with DID, with solutions for adding dynamic metadata to users/tokens
6
Load more