nisten🇨🇦e/acc's banner
nisten🇨🇦e/acc's profile picture

nisten🇨🇦e/acc

@nisten • 17,884 subscribers

fullstack-dev democratizing intelligence 9mcp inc. ezdoesit inc. https://t.co/RjbLSpEgPE @skunkworks_ai @alignment_lab

Videos

LIVE
1.2k

Anya Rossi

sweetdream.ai

SweetDream.aiSponsored•Livecam
Streaming Now

Watch Anya Live

Anya is streaming live right now! Join her private show and enjoy exclusive content.

HD live stream
Exclusive private shows
1.2k viewers online

Free preview available • Premium content

Gen-z is now using deepfakes to teach each other calculus 🤣 Onlock 👏
1:00
nisten's profile picture

Gen-z is now using deepfakes to teach each other calculus 🤣 Onlock 👏

nisten🇨🇦e/acc

808,013 views • 2 years ago

I asked chatgpt voicemode to get drunk and start leaking corporate secrets
1:37
nisten's profile picture

I asked chatgpt voicemode to get drunk and start leaking corporate secrets

nisten🇨🇦e/acc

537,396 views • 1 year ago

Getting h200 node to burn over 100 million tokens per hour lol
1:25
nisten's profile picture

Getting h200 node to burn over 100 million tokens per hour lol

nisten🇨🇦e/acc

211,365 views • 9 months ago

opensource community while discovering ssms work better than transformers Soon you may not even need gpus for long context portable ai.
0:20
nisten's profile picture

opensource community while discovering ssms work better than transformers Soon you may not even need gpus for long context portable ai.

nisten🇨🇦e/acc

289,020 views • 2 years ago

1 cpu core - 160 Tokens per second
1:30
nisten's profile picture

1 cpu core - 160 Tokens per second

nisten🇨🇦e/acc

72,142 views • 1 year ago

Lil update on fixing deepseeks GRPO issues when training a small medical model. shoutout to Zichen Liu & leloy! 's weekend work 1.5B llms medmcqa score went up from 37% to 52%
8:15
nisten's profile picture

Lil update on fixing deepseeks GRPO issues when training a small medical model. shoutout to Zichen Liu & leloy! 's weekend work 1.5B llms medmcqa score went up from 37% to 52%

nisten🇨🇦e/acc

26,449 views • 1 year ago

OpenAI-GPT-20B runs at 9 tokens per second on a 10 year old CPU (4-core i7-6700k) Could get up to 50 000 token context too.
5:01
nisten's profile picture

OpenAI-GPT-20B runs at 9 tokens per second on a 10 year old CPU (4-core i7-6700k) Could get up to 50 000 token context too.

nisten🇨🇦e/acc

12,274 views • 10 months ago

No more content to load