kamaava/Qwen2.5-3B-random_drop_70
Updated
KAMA
kamaava
·
AI & ML interests
NLP/NLP+
Recent Activity
upvoted a paper 1 day ago
ActICL: Post-Training for Agentic Multimodal In-Context Learning liked a model 24 days ago
Qwen/Qwen3-VL-8B-Instruct upvoted a paper 5 months ago
π-Bench: Evaluating Proactive Personal Assistant Agents in Long-Horizon WorkflowsOrganizations
None yet
models 9
kamaava/Qwen2.5-3B-random_drop_30
Updated
kamaava/Qwen2.5-3B-random_drop_20
Updated
kamaava/Qwen2.5-3B-random_drop_50
Updated
kamaava/Qwen2.5-3B-FullDPO
Updated
kamaava/Qwen2.5-1.5B-full_dpo
Updated
kamaava/Qwen2.5-0.5B-random_drop_20
Updated
kamaava/Qwen2.5-0.5B-random_drop_50
Updated
kamaava/Qwen2.5-0.5B-FullDPO
Updated
datasets 0
None public yet