afrideva

[afrideva @afri_deva]

CPU based offline multimodal inference on an Android phone. Original model from @NousResearch, quantization done by @nisten

[afrideva @afri_deva]

@blacknftart https://t.co/YcdcDjwuwR

[Dr. Daniel Bender @drdanielbender]

The open ChatGPT competitor HuggingChat can now use tools

It is fun to explore the new possibilities. Not always as good as in the example below, but the potential is high and will only get better from now on. 😍

[afrideva @afri_deva]

@attractfund1ng https://t.co/i13pT8Lw1M

[afrideva @afri_deva]

@attractfund1ng https://t.co/hbjQtgO6Sw

[afrideva @afri_deva]

@attractfund1ng https://t.co/NBE7HHx8VP

[afrideva @afri_deva]

@attractfund1ng https://t.co/QEguegiz0Z

[afrideva @afri_deva]

@attractfund1ng https://t.co/eusoaMBkQH

[afrideva @afri_deva]

@attractfund1ng

[afrideva @afri_deva]

@Promptmethus https://t.co/Sks2atFhqZ

[Virat Singh @virattt]

I just trained a 124M param LLM from scratch.

It took ~26 seconds in @GoogleColab

Training details:
• 5145 tokens in training set
• 1024 tokens in context window
• 256 tokens per batch
• 10 epochs total

The model went from generating gibberish to full sentences.

Extremely cool.

[afrideva @afri_deva]

@DearSyndi @SirLatimer1 https://t.co/LNPic6P5bb

[afrideva @afri_deva]

@attractfund1ng @Meleagers_Fire off chain "oracles" are common on evm chains, not sure of btc/stacks support
https://t.co/AVTdeepgXY

[afrideva @afri_deva]

@attractfund1ng https://t.co/GvO2bhS7MJ

[afrideva @afri_deva]

@gamerfortynine https://t.co/YJjVmolE2e

[afrideva @afri_deva]

@MaxAifer https://t.co/19U1MWLsG9

[afrideva @afri_deva]

@BlemMedia https://t.co/GdVKPRWPZr

[afrideva @afri_deva]

@tns_openmic also common in bantu languages

[afrideva @afri_deva]

@mjkabir https://t.co/IT5atWgnqx

[afrideva @afri_deva]

@Kinako588 https://t.co/aShpxx6CJY

[afrideva @afri_deva]

@waLILIberace @Portmidas https://t.co/el0MTS00NN

[afrideva @afri_deva]

@waLILIberace https://t.co/ejAcocNOm3

[afrideva @afri_deva]

@andrew_c_becker https://t.co/laZqWemi9g

[Dmytro Nikolaiev @dmytronikolai]

📰 Sampling for Text Generation by Chip Huyen

Blog post: https://t.co/P77Yb11xCi

#keep_AI_posted #ai #nlp #llm #sampling #textgeneration