shizhanccc

keryszhan

1

·

AI & ML interests

None yet

Recent Activity

published a Space 10 days ago

keryszhan/agent-code-rl

published a dataset 10 days ago

keryszhan/agent-code-rl-artifacts

published a model 10 days ago

keryszhan/qwen2.5-coder-7b-code-plan-sft

View all activity

Organizations

None yet

spaces 4

Agent Code RL

Evidence-backed SFT, PRM, and GRPO for code agents.

Rl Harbor Swe Agent

SFT/RL of an 8B code agent on SWE-smith long-horizon tasks.

Trackio

Display real-time I/O activity dashboard

Fastai Product Dogs Venus Cats

Greet users with a personalized message

models 4

keryszhan/qwen2.5-coder-7b-code-plan-sft

Text Generation • Updated 10 days ago • 8

keryszhan/Qwen3-VL-4B-Instruct-trl-grpo

keryszhan/kerys-marian-finetuned-kde4-en-to-zh

77.5M • Updated Jan 23 • 3

keryszhan/distilbert-base-uncased-finetuned-imdb

Fill-Mask • 67M • Updated Jan 20 • 3

datasets 1

keryszhan/agent-code-rl-artifacts

Viewer • Updated 10 days ago • 10.3k • 70