MedCall

company

https://google.com

AI & ML interests

None defined yet.

posted an update 24 days ago

Post

2849

SPECK 2 IS ALREADY OUT: specklabs/Speck2-140M

Pretrained on 4x more tokens than the previous releases (20b vs 5b).
Instruct tuned versions are coming soon.
Very interesting models are coming soon too (hint: super long context).

Thanks for everyone supporting!

3 replies

·

posted an update 27 days ago

Post

180

SPECK1.5 IS COMING SOON!
Same 5B token budget but much better corpus quality.

Also getting a ton of downloads, thanks for everyone downloading and liking <3

posted an update 30 days ago

Post

149

NEW SPECK UPDATES:

Just hit #14 and #15 with out FIRST models on Open SLM Leaderboard. The models were trained on 5B tokens, while competing with similarly sized models trained on more than 6-20x the data.

A new base model Speck1.5-140M being trained right now on a higher quality corpus and will be released soon.
SpeckChat3 is coming very soon with 1 million samples, specifically designed to post train small base models.

Also, just to clarify stuff, we will NOT release anything that is NOT MIT licensed EVER. Openness is needed in small language research.

Thanks to everyone supporting the project, and stay tuned for new releases!

posted an update about 1 month ago

Post

1882

SPECK UPDATES:
1 New instruct model tuned on top of Speck1-140M: specklabs/Speck1-140M-Instruct
2 Instruction tuning datasets
2 GGUFs

Much more coming soon:
Speck1.1-140M-Instruct that is post trained on SpeckChat2 will be coming very soon
New base model Speck1.5-140M is coming with a much higher quality corpus

Thanks to everyone who is already supporting the project, and stay tuned for new releases!

3 replies

·

posted an update about 1 month ago

Post

2120

FIRST SPECK MODEL RELEASED:
specklabs/Speck1-140M

new models coming very soon (both instruct and much better models), with much much higher training scale as i am getting marenostrum5 access soon!
we will be looking at 100b-2t token budgets :)

4 replies

·

updated a dataset 6 months ago

MedCall/turkish-v5-108k-thinking

Viewer • Updated Mar 22 • 108k • 27

published a dataset 6 months ago

MedCall/turkish-v5-108k-thinking

Viewer • Updated Mar 22 • 108k • 27

updated a dataset 7 months ago

MedCall/turkish-v4-87k

Viewer • Updated Mar 5 • 87.3k • 10

published a dataset 7 months ago

MedCall/turkish-v4-87k

Viewer • Updated Mar 5 • 87.3k • 10

updated a dataset 7 months ago

MedCall/turkish-v3-55k

Viewer • Updated Mar 4 • 55.8k • 12

published a dataset 7 months ago

MedCall/turkish-v3-55k

Viewer • Updated Mar 4 • 55.8k • 12

updated a dataset 7 months ago

MedCall/turkish-102k

Viewer • Updated Mar 1 • 103k • 4

published a dataset 7 months ago

MedCall/turkish-102k

Viewer • Updated Mar 1 • 103k • 4

updated a dataset 7 months ago

MedCall/turkish-45k

Viewer • Updated Feb 28 • 44.7k • 5

published a dataset 7 months ago

MedCall/turkish-45k

Viewer • Updated Feb 28 • 44.7k • 5

updated a dataset 8 months ago

MedCall/generalinstruct-en-564k

Viewer • Updated Jan 26 • 564k • 17

published a dataset 8 months ago

MedCall/generalinstruct-en-564k

Viewer • Updated Jan 26 • 564k • 17

updated a dataset 8 months ago

MedCall/cpt-corpus-447k

Viewer • Updated Jan 22 • 447k • 19

published a dataset 8 months ago

MedCall/cpt-corpus-447k

Viewer • Updated Jan 22 • 447k • 19

posted an update about 1 year ago

Post

783

Qwen 3 Coder is a personal attack to k2, and I love it.
It achieves near SOTA on LCB while not having reasoning.
Finally people are understanding that reasoning isnt necessary for high benches...

Qwen ftw!

DECENTRALIZE DECENTRALIZE DECENTRALIZE