Ctrl+K
- MatchTIR-1.7B-SFT-then-ftrl-GRPO-step24-hf
- MatchTIR-1.7B-extra-think0-tool_anneal-step24
- MatchTIR-1.7B-extra-think0-tool_fix1-step24
- MatchTIR-1.7B-extra-thinkback-tool_anneal-pure0.4-step24-du
- MatchTIR-1.7B-extra-thinkback-tool_anneal-purerl0.4-step24
- MatchTIR-4B-extra-think0-tool_anneal-step24
- MatchTIR-4B-extra-thinkback-tool0-step24
- MatchTIR-4B-extra-thinkback-tool_anneal-pure0.2-step24
- MatchTIR-4B-extra-thinkback-tool_anneal-pure0.4-step24-1
- MatchTIR-4B-extra-thinkback-tool_anneal-pure0.4-step24-du
- MatchTIR-4B-extra-thinkback-tool_anneal-pure0.6-step24
- MatchTIR-4B-extra-thinkback-tool_anneal-pure0.8-step24
- MatchTIR-4B-extra-thinkback-tool_anneal-pure0.8to0.2-step24
- MatchTIR-4B-extra-thinkback-tool_anneal
- MatchTIR-4B-extra-thinkback-toolfix1
- MatchTIR-4B-ftrl-GRPO-step24-hf
- MatchTIR-4B-segmented-prefix-54_hybrid-cleaned-plus-32b-extra-adaptive-next-turn-random-pure-rl-p0p4-previous-24
- MatchTIR-4B-sftabl-segmented_prefix_tool_suffix-step24
- global_step_9
- 4.53 kB
- 560 MB xet