New AI Models (Last Year) — Page 131

qwen3-4b-msswift-checkpoint9909

affine-5GbD8w5wk1mUAeYr6vbPtC4E7ihsgv6gfEt3K3C6C3BZwyig

Qwen3-1.7B-MATH-RLVR-250

Qwen2.5-0.5B-Instruct-sft

qwen3lora

seng-beliefs

qwen3-4b-instruct-forc-rl

qwen3-4b-off-task-guard-v3

qwen2.5-coder-1.5b-instruct-code-r1-grpo-896

m4b_print68

gemma-3-1b-it-Math-GRPO

Qwen3-1.7B-MATH-A9-U-GRPO

affine-5EtPj7mKQ6arxx8KW3GFTWBzTBia1DyM2vDU1rpNPsRHUk1B

qwen2.5-7b_gptq-draft-0.5b-mathReasoning

m4b_print72

SDRL-freq-Qwen3-4B-Base-majority_n8_l2048-GRPO_n8_bs256_long8-step200

qwen3_4b_baseline_solver_v3

qwen3_4b_baseline_v2_solver_v2

Qwen3-4B-CoderForge-SFT-baseline-epoch2

qwen3_4b_vdrop75_v2_solver_v1

qwen3_4b_vdrop75_v2_solver_v2

qwen3_4b_vdrop75_v2_questioner_v5

qwen3_4b_vdrop75_v2_solver_v3

qwen3_4b_vdrop75_v2_solver_v4

qwen3_4b_vdrop75_v2_solver_v5

qwen3_4b_vdrop85_questioner_v5

qwen3_4b_vdrop85_solver_v1

qwen4b-instruct-cantone-ft

Qwen2.5-SFT-0.5B-2500steps

Openmed-icd10-rl-4b-lora-super-train-base

qwen3_4b_sudoku_multi_act_rl_allow_one_action_epoch1

qwen3_4b_sudoku_multi_act_rl_allow_one_action_epoch2

MarAI-1.0

qwen3_4b_sudoku_multi_act_rl_allow_one_action_epoch3

qwen3_1.7b_sudoku_multi_action_group_norm_epoch3

qwen3_1.7b_sudoku_multi_action_group_norm

qwen3_1.7b_sudoku_multi_action_group_norm_epoch1

gemma2-fieldtech

gemma-diary-summarizer

Qwen2.5-1.5B-Instruct-SFT-30k

qwen3_1.7b_webshop_macro_action_epoch1

qwen3_1.7b_webshop_macro_action_epoch2