DEV Community

Maykeye profile picture

Maykeye

Location Abyss Joined Joined on  github website

Pronouns

He

Baka4LLM. New horizons

Baka4LLM. New horizons

Comments
1 min read
MambaBit. The most cursed LLM?

MambaBit. The most cursed LLM?

Comments
1 min read
BakaLLM 17.7 Simiplification!

BakaLLM 17.7 Simiplification!

Comments
1 min read
BakaLLM 17.6 More epochs! More evaluations! Cerebras slashed and smashed

BakaLLM 17.6 More epochs! More evaluations! Cerebras slashed and smashed

Comments
1 min read
BakaLLM Part 17.5. Sssnake faster! Yet another milestone achieved

BakaLLM Part 17.5. Sssnake faster! Yet another milestone achieved

Comments
4 min read
BakaLLM, part 17. Dancing with SSMnakes

BakaLLM, part 17. Dancing with SSMnakes

Comments
2 min read
BakaLLM part NaN(still), Mamba shows promise and slowness

BakaLLM part NaN(still), Mamba shows promise and slowness

Comments
1 min read
BakaLLM part NaN and general shenanigans

BakaLLM part NaN and general shenanigans

Comments
1 min read
Part 16.1(x2) Copying RMT

Part 16.1(x2) Copying RMT

Comments
1 min read
BakaLLM. Part 16. Procrastinating in style

BakaLLM. Part 16. Procrastinating in style

Comments
1 min read
BakaLLM, part 15.(inf). Why I can't hold all these stars or Pythia-70M is on the horizon

BakaLLM, part 15.(inf). Why I can't hold all these stars or Pythia-70M is on the horizon

Comments
2 min read
BakaLLM, part 15.x: reachrf the stars, cooking on a plasma!

BakaLLM, part 15.x: reachrf the stars, cooking on a plasma!

Comments
1 min read
BakaLLM, part 15: reaching for the stars!

BakaLLM, part 15: reaching for the stars!

Comments
2 min read
BakaLLM, part 14: (MLP) Sharing is caring(?)

BakaLLM, part 14: (MLP) Sharing is caring(?)

Comments
2 min read
BakaLLM step 13.1, achievement unlucked: flash attention

BakaLLM step 13.1, achievement unlucked: flash attention

Comments
1 min read
BakaLLM, step 13, RMT mainlined

BakaLLM, step 13, RMT mainlined

Comments
1 min read
BakaLLM, part 12.4, gatekeeping is all you need

BakaLLM, part 12.4, gatekeeping is all you need

Comments
3 min read
BakaLLM, part 12, 1 step backward, 4 steps forward: starting new experiment

BakaLLM, part 12, 1 step backward, 4 steps forward: starting new experiment

Comments
2 min read
BakaLLM part 11.5. Moving away from (solely) WANDB

BakaLLM part 11.5. Moving away from (solely) WANDB

Comments
2 min read
BakaLLM, part 11. Progress was made, this is not a DRILL, this is a PROGRESS! RMT and getting the loss <4.00, finally!

BakaLLM, part 11. Progress was made, this is not a DRILL, this is a PROGRESS! RMT and getting the loss <4.00, finally!

Comments
2 min read
BakaLLM. Part 10. Progress? `Dim` light in thinning tunnel? Thin layers revisted: turning thin layers into thicc MLP

BakaLLM. Part 10. Progress? `Dim` light in thinning tunnel? Thin layers revisted: turning thin layers into thicc MLP

Comments
3 min read
BakaLLM, part (9). The epoch of Stalling has begun!

BakaLLM, part (9). The epoch of Stalling has begun!

Comments
4 min read
BakaLLM, part 8. Let's <pause> for a second

BakaLLM, part 8. Let's <pause> for a second

Comments
2 min read
BakaLLM, part 7: XL struggles are done, for now

BakaLLM, part 7: XL struggles are done, for now

Comments
2 min read
BakaLLM Part 6: Training and eXtra Large Struggles (Part 1) (hopefully last part of the struggles)

BakaLLM Part 6: Training and eXtra Large Struggles (Part 1) (hopefully last part of the struggles)

Comments 1
6 min read
BakaLLM, p5: one stomp forward

BakaLLM, p5: one stomp forward

Comments
3 min read
BakaLLM, p4. Building LLM from scratch: New baseline is ready.

BakaLLM, p4. Building LLM from scratch: New baseline is ready.

Comments
4 min read
BakaLLM, part 3: it's testing time, it's testing time

BakaLLM, part 3: it's testing time, it's testing time

1
Comments
4 min read
BakaLLM, part 2

BakaLLM, part 2

Comments
5 min read
BakaLLM: Designing new LLM

BakaLLM: Designing new LLM

Comments
6 min read
loading...