arxiv:2501.08328
Richard Zhuang PRO
RZ412
AI & ML interests
LLM Routing, LLM + Games, Post-Training, Agents
Recent Activity
updated a dataset about 1 hour ago
DCAgent3/bfcl_parity_a3_rl_laion_nemotron_gym_knowledge_web_search_mcqa_25_8B_20260604_060731 published a dataset about 1 hour ago
DCAgent3/bfcl_parity_a3_rl_laion_nemotron_gym_knowledge_web_search_mcqa_25_8B_20260604_060731 updated a dataset about 1 hour ago
DCAgent3/medagentbench_a3_rl_laion_exp_rpt_crosscodeeval_csharp_v4_50_8B_20260603_233910Organizations
models 57
RZ412/Qwen2.5-3B-Instruct-inferredbugs-sandboxes-traces-terminus-2
Updated
RZ412/Qwen2.5-3B-Instruct-OT3-8K-QwQ-Min-R1-Min-MLR
Text Generation • 3B • Updated
RZ412/Qwen2.5-3B-Instruct-OT3-8K-R1-Only-Seed-42
Text Generation • 3B • Updated
RZ412/Qwen2.5-3B-Instruct-OT3-8K-QwQ-R1-RM-50-50-SS-42-AS-42
Text Generation • 3B • Updated • 10
RZ412/Qwen2.5-3B-Instruct-OT3-8K-QwQ-Only-Seed-42
Text Generation • 3B • Updated • 1
RZ412/Qwen2.5-3B-Instruct-OT3-8K-R1-MeL
Text Generation • 3B • Updated • 1
RZ412/Qwen2.5-3B-Instruct-OT3-8K-R1-ML
Text Generation • 3B • Updated • 1
RZ412/Qwen2.5-3B-Instruct-OT3-8K-QwQ-MaL-misstore
Text Generation • 3B • Updated • 3
RZ412/Qwen2.5-3B-Instruct-OT3-8K-QwQ-R1-DB
Text Generation • 3B • Updated
RZ412/Qwen2.5-3B-Instruct-OT3-8K-QwQ-R1-RES
Text Generation • 3B • Updated • 2
datasets 54
RZ412/opencode_sft_traces
Viewer • Updated • 17 • 41
RZ412/test_harbor_trace
Viewer • Updated • 97 • 72
RZ412/test_harbor_trace-summarization-9-summary
Viewer • Updated • 1 • 45
RZ412/test_harbor_trace-summarization-9-questions
Viewer • Updated • 1 • 35
RZ412/test_harbor_trace-summarization-8-summary
Viewer • Updated • 1 • 13
RZ412/test_harbor_trace-summarization-8-questions
Viewer • Updated • 1 • 50
RZ412/test_harbor_trace-summarization-7-summary
Viewer • Updated • 1 • 30
RZ412/test_harbor_trace-summarization-7-questions
Viewer • Updated • 1 • 48
RZ412/test_harbor_trace-summarization-6-summary
Viewer • Updated • 1 • 59
RZ412/test_harbor_trace-summarization-6-questions
Viewer • Updated • 1 • 33