New AI Models (Last Year) — Page 138

Qwen2.5-G3V-Sovereign

qwen3-4b-stage2-v3

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

qwen3_4b_baseline_solver_v3

Llama-3-Lumimaid-70B-v0.1-alt-heretic

dqncodenew-16bit

qwen3_4b_baseline_v2_questioner_v5

qwen3_4b_vdrop75_v2_solver_v1

qwen3_4b_vdrop75_v2_solver_v2

Qwen2.5-1.5B-Open-R1-Distill

qwen3_4b_vdrop75_v2_questioner_v5

qwen3_4b_vdrop75_v2_solver_v3

qwen3_4b_vdrop75_v2_solver_v4

qwen3_4b_vdrop85_questioner_v5

qwen3_4b_vdrop85_solver_v1

qwen3_4b_vdrop85_solver_v5

sft_qwen3_4b_tmax_4node2203

Qwen2.5-0.5B-creature

qwen2.5-1.5b-gsm8k-train-step1000

Llama-3.2-3B-Instruct-HeadQA

llama323b-dnli-s2

erida-Inari-50125

ft-news

qwen2.5-1.5b-gsm8k-train-step7500

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

csrsef-instruct-20260325T021216Z-it01-pubmedqa

qwen3_4b_sudoku_one_act_rl_default_epoch1

qwen3_4b_sudoku_multi_act_rl_epoch1

MarAI-1.0

qwen3-4b-verilog-sft

gemma-3-1b-it-Math-SFT-RS-DPO

reranker_gemma_3-1b-sft-full_03-22-26_1

qwen3_4b_sudoku_one_act_rl_default_epoch2

qwen3_4b_sudoku_one_act_rl_default_epoch3

qwen3_4b_sudoku_multi_act_rl_allow_one_action_epoch3

qwen3_4b_sudoku_multi_act_rl_allow_one_action

qwen3_1.7b_sudoku_multi_action_group_norm_epoch3

qwen2.5-coder-1.5b-verl-java

sn38-3

A0l-12B-heretic

ginrummy-checkuplog-hashid

qwen3_0.6b_unireason