AI & ML interests

Collaborating towards Good ML!

Recent Activity

Update README.md

👍 1
15
#10 opened about 1 year ago by
Sissniko
DibaAi 
in discord-community/WelcomeBot about 1 month ago

test

👀 5
184
#2 opened over 1 year ago by
adamm-hf
ZRP-Inc 
in discord-community/WelcomeBot about 1 month ago

test

👀 5
184
#2 opened over 1 year ago by
adamm-hf

test

👀 5
184
#2 opened over 1 year ago by
adamm-hf

test

👀 5
184
#2 opened over 1 year ago by
adamm-hf
hyunseop 
in discord-community/WelcomeBot about 1 month ago

test

👀 5
184
#2 opened over 1 year ago by
adamm-hf

test

👀 5
184
#2 opened over 1 year ago by
adamm-hf
DV8tion 
in discord-community/WelcomeBot about 1 month ago

test

👀 5
184
#2 opened over 1 year ago by
adamm-hf
ETTE154 
in discord-community/WelcomeBot about 1 month ago

test

👀 5
184
#2 opened over 1 year ago by
adamm-hf
anakin87 
posted an update 2 months ago
view post
Post
3,573
I made a 1.1M ModernBERT encoder play Doom in real time on a CPU

Some time ago, VAGO Solutions released SauerkrautLM-Doom-MultiVec-1.3M, a tiny model trained to play Doom Defend the Center scenario from 31k human gameplay examples.

My first thought: cool! I love both Doom and Small Language Models.

Then another idea: I bet I can do better :-)

What I did?
- evaluated the original model and found it's better than reported
- changed a bit the architecture
- generated SFT data with a scripted oracle
- SFT + PPO refinement on consumer hardware

Got a smaller, faster and killer model
Can even fit a floppy with int8 quantization 💾

Watch it play/read the article: anakin87/tiny-doom-defender

huggingmodbot

#13 opened 3 months ago by
jd16125