Martins Udris's picture

Building on HF

6 3 2

Martins Udris PRO

martinsu

·

AI & ML interests

None yet

Recent Activity

upvoted an article 8 days ago

How We Built a Semantic Highlight Model To Save Token Cost for RAG

new activity 21 days ago

martinsu/tildeopen-30b-mu-instruct:Use case

replied to etemiz's post about 1 month ago

I realized when I ask longer answers to my questions, the models sometimes produce completely opposite answer. What could be the reason? I do mostly CPT. Should I convert my dataset to SFT and give longer reasonings too for it to have integrity? Example: Is the yolk of an egg more beneficial or the white? Answer in 100 words. Answer: Yolk is more beneficial because .......... Example: Is the yolk of an egg more beneficial or the white? Answer in 500 words. Answer: White is more beneficial because .......... Edit: These happen in temp = 0.0

View all activity

Organizations

New activity in martinsu/tildeopen-30b-mu-instruct 21 days ago

Use case

#1 opened 22 days ago by

New activity in mistralai/Devstral-Small-2-24B-Instruct-2512 about 1 month ago

FP16 Weights

#19 opened about 2 months ago by

New activity in unsloth/Devstral-2-123B-Instruct-2512-GGUF about 2 months ago

Please update llama.cpp to see improved performance!

#5 opened about 2 months ago by

New activity in TildeAI/TildeOpen-30b 2 months ago

New all layer 160M token finetune tildeopen-30b-mu-instruct

#14 opened 2 months ago by

Thanks for the great model

#7 opened 5 months ago by

New activity in agents-course/Students_leaderboard 9 months ago

concept of the final assessment submission?

#1 opened 9 months ago by

concept of the final assessment submission?

#1 opened 9 months ago by