New AI Models (Last Year) — Page 121

general_reward-Qwen3-0.6B-OURS_llama-seed_1

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

qwen3_4b_baseline_v2_solver_v3

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

Qwen2.5-0.5B-Instruct-es-em-bad-medical-advice

Qwen3-4B-Base-ascii-art-v5-e3-lr1e-4-ga16-ctx4096

gemma-2-2b-it-reasoning-high-boolq-calibration

qwen3_4b_sudoku_multi_act_rl_allow_one_action

4b_sft_ds_rea_epoch3

model_sft_resta

qwen3_1.7b_sudoku_multi_action_group_norm_epoch2

dpo-llama-3.2-3b-set1-pref100

odgh

inlp-task-vector

Jailbreak-agent-temp

Qwen3-4B_thinking_agent_sft_nemotron_tool_calling_v2_lr1e-5_epoch_1_ctx_16384_bs_256

openclaw-primary-merged

FinGPT-Qwen

Qwen3-0.6B-Gensyn-Swarm-timid_lively_monkey

seed0_xcsqa_google-gemma-3-4b-it_multi_0.1_MAPO_5e-06

Ultron

v1-14b-planets-docsonly-seed2

Emory-CS557-AI-Final-Test

Qwen2.5-1.5B-ViInstruct

alif-3b-fp16

affine-tobetop1

nl2bash-nl2bash-bugsseq_Qwen3-8B-maxEps24-112925harbor_step40

qwen3_4b_easy_rl_final

qwen3_4b_medium_rl_final

Qwen2.5-14B-style-MERGED-v3

qwen3_1.7b_easy_rl_final_gamma_1

expert_len_MRL4096_ROLLOUT4_LR5e-7_step30

affine-test-10

meta-llama_Llama-3.2-3B-Instruct-GRPO-vanilla_G_4-checkpoint-292

meta-llama_Llama-3.2-3B-Instruct-GRPO-vanilla_G_4-checkpoint-393

meta-llama_Llama-3.2-3B-Instruct-GRPO-vanilla_G_4-checkpoint-186

qwen3_4b_easy_rl_our_adv_final

StudyAi

affine-legacy

Affine-h03

Hwen-HF

affine-golden-09