🔄 In a Training Loop
Cosline Dev
coslinedev
AI & ML interests
Deterministic AI, Financial LLMs, Execution-Verified Trajectories, Property-Based Testing (PBT), Synthetic Data Engines, RLVR, Unsloth Fine-Tuning, Quant Reasoning Systems
Recent Activity
updated a model about 16 hours ago
coslinedev/ALRITHM-Astro published a model about 16 hours ago
coslinedev/ALRITHM-Astro liked a model 15 days ago
dealignai/Nanbeige4.3-33B-UNCENSORED-GGUFOrganizations
None yet
Financial Reasoning Fine-Tune (RLVR / Execution-Verified) based on Qwen 2.5 3B
#1 opened 3 months ago
by coslinedev
FinCode-Reasoning-v1: Fine-tuned Qwen2.5-3B with Execution-Verified Financial Trajectories
#18 opened 3 months ago
by coslinedev