Qwen3-4B checkpoints whose chat template always preserves <think> reasoning across multi-turn history, with no nonthinking mode.
Ethan Ewer
eewer
AI & ML interests
None yet
Recent Activity
updated a model 1 day ago
eewer/qwen3.5-35b-a3b-base-terminal_swe_general-agent-ablation-step7176 updated a model 1 day ago
eewer/qwen3.5-35b-a3b-base-terminal_swe-agent-ablation-step7073 published a model 1 day ago
eewer/qwen3.5-35b-a3b-base-terminal_swe_general-agent-ablation-step7176Organizations
None yet
models 68
eewer/qwen3.5-35b-a3b-base-terminal_swe_general-agent-ablation-step7176
Text Generation • 35B • Updated
eewer/qwen3.5-35b-a3b-base-terminal_swe-agent-ablation-step7073
Text Generation • 35B • Updated
eewer/qwen3.5-35b-a3b-base-terminal_swe_general-agent-step7176
Text Generation • 35B • Updated
eewer/qwen3.5-35b-a3b-base-terminal_swe-agent-step7073
Text Generation • 35B • Updated
eewer/qwen3.5-35b-a3b-base-terminal-agent-step2961
Text Generation • 35B • Updated • 12
eewer/qwen3.5-35b-a3b-base-terminal-agent-step5271
Text Generation • 35B • Updated • 16
eewer/qwen3.5-35b-a3b-base-terminal_swe_general-agent-step2500
Text Generation • 35B • Updated • 55
eewer/qwen3.5-35b-a3b-base-terminal_swe-agent-step2500
Text Generation • 35B • Updated • 61
eewer/qwen3.5-35b-a3b-base-terminal_swe_general-agent-step1000
Text Generation • 35B • Updated • 239
eewer/qwen3.5-35b-a3b-base-terminal_swe-agent-step1000
Text Generation • 35B • Updated • 218
datasets 7
eewer/mixed-sft-openai-tools-qwen3-areal-diverse
Updated • 44
eewer/skill-based-medium-terminus2-sft
Updated • 65
eewer/qwen3-4b-thinking-sft-v54-raw2030-strictpassed-processed
Preview • Updated • 84
eewer/swerebench-traces-raw-source-verification-enhanced-20260617
Viewer • Updated • 1 • 13
eewer/agent-dataset
Viewer • Updated • 869 • 9
eewer/MMLU-Pro-engineering-outputs
Viewer • Updated • 25.6k • 20
eewer/deepseek-MMLU-Pro-engineering-outputs
Viewer • Updated • 8.69k • 43