Search results for 250822
250822 community
One keyword maps to one global community path.
People
Not Found
Tweets including 250822
[🎞️#ENroll#]
ENHYPEN STAGE PHOTO
@ WORLD TOUR ‘WALK THE LINE’ in LONDON_250822
#ENHYPEN# #EN_WALKTHELINE#
#EN_WORLDTOUR_WALKTHELINE#
#WALKTHELINE_IN_EUROPE#
[🎞️#ENroll#]
ENHYPEN STAGE PHOTO
@ WORLD TOUR ‘WALK THE LINE’ in LONDON_250822
#ENHYPEN# #EN_WALKTHELINE#
#EN_WORLDTOUR_WALKTHELINE#
#WALKTHELINE_IN_EUROPE#
[#오늘의ENHYPEN#] Great to meet you, London! 🙌 Your energy was electric from the very first moment⚡️ Thanks for the warmest welcome.
We’ll be back with cool performance next time! Enjoy your weekend! ❤️🔥 #250822# @ WALK THE LINE in LONDON
Show more
We've shared research on fine-tuning forecasters, now you can try it for yourself: a cookbook recipe for training a model to predict event probabilities given reference information.
Start with the provided dataset from @ProphetArena, then try your own.
Show more
GLM-5.3 from @Zai_org is now available on Tinker with 256k context. With scaled up post-training from the same base as GLM-5.2, it is currently the strongest open-weights model on coding evals such as Terminal-Bench 3.0 and DeepSWE 1.1.
Show more
LLMs with scaffolds have lagged on text-to-SQL, a task that relies on human judgment. By folding expert judgment into every part of RLVR on Tinker, @maxYuxuanZhu and @ddkang (UIUC and Bridgwater) trained the first text-to-SQL model to beat the human mark.
Show more
Qwen3.8-27B is live on Tinker today.
It’s natively multimodal with images + video, has flexible thinking control, and is meaningfully better at coding, professional work, research, and long-horizon agentic tasks.
Let us know what you build with it!
Show more
Borrow the format, not the identity. Study what works, then make it unmistakably yours.
We're looking for Tinker fanatics to help the world fine-tune models. Join us!