kiraaa
Re:Claude 3.7 Sonnet and Claude Code
on Tuesday February 25, 2025 @02:48AM (#43169294)
when there are two commands in a prompt example
do A and then do B.
the model completely ignores the second task B.
Re:26× Faster Inference with Layer-Condensed KV Cache for Large Langua...
on Monday May 20, 2024 @03:54PM (#40419528)
on gpu that is still huge.
Re:Nvtop: Linux Task Monitor for Nvidia, AMD and Intel GPUs
on Wednesday March 13, 2024 @03:47AM (#39688983)
super easy to install and use
Re:Gemma: New Open Models
on Wednesday February 21, 2024 @10:21AM (#39454878)
mistral 7b v0.2 supports 32k
Re:Gemini 1.5 Pro
on Friday February 16, 2024 @05:32AM (#39395295)
could be true, we can only speculate.
Re:Gemini 1.5 Pro
on Thursday February 15, 2024 @06:40PM (#39390886)
maybe they are using ring attention, on top of their 128k model.
Re:Take the Road Most Documented
on Monday January 29, 2024 @10:12AM (#39177135)
really like the font and great article btw.
Re:Anna's Archive – LLM Training Data from Shadow Libraries
on Thursday October 19, 2023 @07:54PM (#37950400)
good tokens
Re:Mistral 7B Paper on ArXiv
on Wednesday October 11, 2023 @09:31AM (#37844127)
the paper does not live up to the quality of model lol
Re:Falcon LLM – A 40B Model
on Sunday June 18, 2023 @08:55AM (#36379871)
you need 94gb, does not matter which RAM.
Re:Writing a chat application in Django 4.2 using async StreamingHttpR...
on Friday June 16, 2023 @02:41PM (#36361671)
https://github.com/sysid/sse-starlette this makes token streaming so much easier in python
Re:Stability AI Launches the First of Its StableLM Suite of Language M...
on Wednesday April 19, 2023 @06:34PM (#35634170)
and also easy to deploy
Re:Stability AI Launches the First of Its StableLM Suite of Language M...
on Wednesday April 19, 2023 @06:32PM (#35634152)
its not alway about the size, but yeah its really good!
Re:Stability AI Launches the First of Its StableLM Suite of Language M...
on Wednesday April 19, 2023 @06:30PM (#35634137)
installing it is a nightmare
Re:Show HN: Finetune LLaMA-7B on commodity GPUs using your own text
on Wednesday March 22, 2023 @02:53AM (#35257684)
you could but it will be very slow. oh and make sure the code is cpu compatible.