zhenting/evolm-1B-160BT-cpt-MixedFW8FM42-sftep8-sampled500k_first100k_qwen7b-rlep8-last100k 1B • Updated May 2, 2025
zhenting/evolm-1B-160BT-cpt-MixedFW8FM42-sftep1-sampled500k_first300k_qwen7b-rlep8-last100k 1B • Updated May 2, 2025
zhenting/evolm-1B-160BT-cpt-MixedFW8FM32-sftep1-sampled500k_first100k_qwen7b-rlep8-last100k 1B • Updated May 2, 2025 • 2
zhenting/evolm-1B-160BT-cpt-MixedFW8FM22-sftep1-sampled500k_first100k_qwen7b-rlep8-last100k 1B • Updated May 2, 2025
zhenting/evolm-1B-160BT-cpt-MixedFW8FM12-sftep1-sampled500k_first100k_qwen7b-rlep8-last100k 1B • Updated May 2, 2025
zhenting/evolm-1B-160BT-cpt-MixedFW8FM2-sftep1-sampled500k_first100k_qwen7b-rlep8-last100k 1B • Updated May 2, 2025
zhenting/evolm-1B-160BT-cpt-MixedFW8FM42-sftep1-sampled500k_first100k_qwen7b-rlep8-last300k 1B • Updated May 2, 2025 • 1
zhenting/evolm-1B-160BT-cpt-MixedFW8FM42-sftep4-sampled500k_first100k_qwen7b-rlep8-last100k 1B • Updated May 2, 2025
zhenting/evolm-1B-160BT-cpt-MixedFW8FM42-sftep2-sampled500k_first100k_qwen7b-rlep8-last100k 1B • Updated May 2, 2025
zhenting/evolm-1B-160BT-cpt-MixedFW8FM42-sftep1-sampled500k_first400k_qwen7b-rlep8-last100k 1B • Updated May 2, 2025
zhenting/evolm-1B-160BT-cpt-MixedFW8FM42-sftep1-sampled500k_first200k_qwen7b-rlep8-last100k 1B • Updated May 2, 2025 • 1
zhenting/evolm-1B-80BT-cpt-MixedFW8FM42-sftep1-sampled500k_first100k_qwen7b-rlep8-last100k 1B • Updated May 2, 2025
zhenting/evolm-1B-40BT-cpt-MixedFW8FM42-sftep1-sampled500k_first100k_qwen7b-rlep8-last100k 1B • Updated May 1, 2025
zhenting/evolm-1B-20BT-cpt-MixedFW8FM42-sftep1-sampled500k_first100k_qwen7b-rlep8-last100k 1B • Updated May 1, 2025
zhenting/evolm-1B-160BT-cpt-MixedFW8FM42-sftep1-sampled500k_first100k_qwen7b-rlep32-last100k 1B • Updated May 1, 2025
zhenting/evolm-1B-160BT-cpt-MixedFW8FM42-sftep1-sampled500k_first100k_qwen7b-rlep8-last200k 1B • Updated Apr 30, 2025
zhenting/evolm-1B-160BT-cpt-MixedFW8FM42-sftep1-sampled500k_first100k_qwen7b-rlep8-last100k 1B • Updated Apr 30, 2025
zhenting/evolm-4B-160BT-cpt-MixedFW8FM42-sftep2-sampled500k_first100k_qwen7b 4B • Updated Apr 30, 2025 • 1
zhenting/evolm-4B-160BT-cpt-MixedFW8FM42-sftep1-sampled500k_first400k_qwen7b 4B • Updated Apr 30, 2025 • 1
zhenting/evolm-4B-160BT-cpt-MixedFW8FM42-sftep1-sampled500k_first300k_qwen7b 4B • Updated Apr 30, 2025
zhenting/evolm-4B-160BT-cpt-MixedFW8FM42-sftep1-sampled500k_first100k_qwen7b-rlep8-last100k 4B • Updated Apr 30, 2025
zhenting/evolm-4B-160BT-cpt-MixedFW8FM42-sftep1-sampled500k_first100k_qwen7b-rlep4-last100k 4B • Updated Apr 30, 2025
zhenting/evolm-1B-160BT-cpt-MixedFW8FM42-sftep1-sampled500k_first100k_qwen7b-rlep16-last100k 1B • Updated Apr 30, 2025
zhenting/evolm-1B-160BT-cpt-MixedFW8FM42-sftep1-sampled500k_first100k_qwen7b-rlep4-last100k 1B • Updated Apr 30, 2025 • 81
zhenting/evolm-1B-160BT-cpt-MixedFW8FM42-sftep1-sampled500k_first100k_qwen7b-rlep2-last100k 1B • Updated Apr 30, 2025
zhenting/evolm-1B-160BT-cpt-MixedFW8FM42-sftep1-sampled500k_first100k_qwen7b-rlep1-last100k 1B • Updated Apr 30, 2025 • 1
zhenting/evolm-4B-160BT-cpt-MixedFW8FM42-sftep1-sampled500k_first200k_qwen7b 4B • Updated Apr 30, 2025 • 1
zhenting/evolm-4B-160BT-cpt-MixedFW8FM42-sftep1-sampled500k_first100k_qwen7b-rlep1-last100k 4B • Updated Apr 29, 2025