Treasure Hunt: Real-time Targeting of the Long Tail using Training-Time Markers
Paper
•
2506.14702
•
Published
•
4
•
4
Kian Kyars
kyars
·
AI & ML interests
None yet
Recent Activity
commented on
a paper
22 days ago
Treasure Hunt: Real-time Targeting of the Long Tail using Training-Time
Markers
commented on
a paper
22 days ago
Treasure Hunt: Real-time Targeting of the Long Tail using Training-Time
Markers
updated
a Space
27 days ago
Agents-MCP-Hackathon/Decider-MCP
Organizations
commented
2
papers
22 days ago
updated
a
Space
27 days ago
liked
2
models
27 days ago
awesome resource
#1 opened about 1 month ago
by
kyars
commented on
SmolLM3: smol, multilingual, long-context reasoner
about 1 month ago
thanks!
commented on
SmolLM3: smol, multilingual, long-context reasoner
about 1 month ago
makes sense
commented on
SmolLM3: smol, multilingual, long-context reasoner
about 1 month ago
For the reasoning mid-training we used the ChatML template (so no system prompt), for SFT we use SmolLM3's final chat template.
ChatML does have a system prompt, can you please elaborate?
commented on
SmolLM3: smol, multilingual, long-context reasoner
about 1 month ago
is it not possible to do on-policy distillation?
commented on
SmolLM3: smol, multilingual, long-context reasoner
about 1 month ago
nice thoughts
commented on
SmolLM3: smol, multilingual, long-context reasoner
about 1 month ago
tied embeddings were just used because llama uses it or was there an ablation?
upvoted
an
article
about 1 month ago
Article
SmolLM3: smol, multilingual, long-context reasoner
By
and 22 others
•
•
643
commented on
SmolLM3: smol, multilingual, long-context reasoner
about 1 month ago
Let's do this with Muon.
TP Question
2
#113 opened 3 months ago
by
kyars
published
a
Space
3 months ago
updated
a
Space
3 months ago
published
a
Space
3 months ago
commented
a
paper
3 months ago
upvoted
a
paper
3 months ago