OneFlow

78 posts

OneFlow

OneFlow

@OneFlowNews

OneFlow is a deep learning framework designed to be user-friendly, scalable and efficient.

انضم Haziran 2021
163 يتبع110 المتابعون
OneFlow
OneFlow@OneFlowNews·
@amanrsanger Aman, good article! I’m wondering if we can translate your blog into Chinese and post it in the Chinese community. We will highlight your name and keep the original link on the top of the translated version. Thank you!
English
0
0
0
29
Aman Sanger
Aman Sanger@amanrsanger·
Llama-2 is more expensive than you'd think It can be up to 33x more expensive than gpt-3.5, without large batches. But for some workloads, it can actually be 3x cheaper! We delve deep into the math and measured perf here: cursor.so/blog/llama-inf…
English
6
21
123
22.6K
OneFlow
OneFlow@OneFlowNews·
@dfrsrchtwts @janleike Daniel, Great episode! I’m wondering if we can translate your podcast into Chinese and post it on AI community in China. We will highlight your name and keep the original link on the top of the translated version. Thank you.
English
1
0
1
66
OneFlow
OneFlow@OneFlowNews·
@etiennebcp Etienne, your blog is very enlightening. I am wondering if we can translate it into Chinese and post it on AI community in China. We will highlight your name and keep the original link on the top of the translation version. Thanks!
English
1
0
1
59
Etienne Bernard
Etienne Bernard@etiennebcp·
Hi everyone! I am starting a series of blog posts about NLP, ML, and AI. Here is the first one where I talk about how LLMs work, their history, the current state of affairs, and what we can expect next: numind.ai/blog/what-are-… Hope that is interesting/useful to some!
English
1
1
7
528
OneFlow
OneFlow@OneFlowNews·
@simonw Simon, great article! I am wondering if we can translate your blog into Chinese and post it on AI community in China. We will highlight your name and keep the original link on the top of the translation version. Thank you!
English
0
0
0
57
Simon Willison
Simon Willison@simonw·
Understanding GPT tokenizers: I wrote about how the tokenizers used by the various GPT models actually work, including an interactive tool for experimenting with their output simonwillison.net/2023/Jun/8/gpt…
English
22
234
1.3K
287.8K
OneFlow
OneFlow@OneFlowNews·
@NoPriorsPod @saranormous @eladgil @kevin_scott Great interview. I am wondering if we can translate your podcast into Chinese and post it in AI community. We will highlight 'No Priors' and keep the original link on the top of the translation version. Thanks.
English
0
0
0
59
OneFlow
OneFlow@OneFlowNews·
@rasbt Sebastian, great article! I am wondering if we can translate your blog into Chinese and post it in our WeChat official account platform. We will highlight your name and keep the original link on the top of the translation version. Thank you.
English
0
0
0
29
Sebastian Raschka
Sebastian Raschka@rasbt·
Thanks to parameter-efficient finetuning techniques, you can finetune a 7B LLM on a single GPU in 1-2 h using techniques like low-rank adaptation (LoRA). Just wrote a new article explaining how LoRA works & how to finetune a pretrained LLM like LLaMA: lightning.ai/pages/communit…
English
29
274
1.5K
386.6K
OneFlow
OneFlow@OneFlowNews·
@craigss @ilyasut Also, I would like to know if we could translate several other episodes of 'Eye on AI'. We'll always give you credit (mention 'Eye on AI' and your name), and link back to the original interview.
English
1
0
0
32
OneFlow
OneFlow@OneFlowNews·
@dylan522p Hi, Dylan. Your blog is very enlightening! I’m wondering if we can translate this blog in Chinese and post it on our WeChat official platform. We will keep the original link and state where it is translated from. I believe this move will benefit more people! Thank you!
English
1
0
0
398
Dylan Patel
Dylan Patel@dylan522p·
The Inference Cost Of Search Disruption $30B Of $GOOGL Profit Evaporating Overnight! ChatGPT and Google Search cost structure analysis Performance improvement with H100, TPUv4, TPUv5 Next-generation LLM architecture Latency optimization $MSFT $NVDA $AVGO semianalysis.com/p/the-inferenc…
English
6
40
129
33.4K

اكتشف

@SiliconFlowAI @StabilityAI @horseeeMa @amanrsanger @dfrsrchtwts @janleike @etiennebcp @simonw