New AI Models (Last Year) — Page 108

qwen3-4b-lgc

EAEDS-llm

dpo-qwen-cot-merged

has3

unsup-Qwen3-1.7B-datav3

adv_sft5_dpo3_merged

llm_advance_015_grpo_alf

dpo-qwen-cot-merged

Qwen3-0.6B-dp-ee

first-model

qwen3-4B-dpo-anti-fence-240slow26

qwen3-4b-prime-mult-k5-step50

qwen3-4b-structeval-stage0-1-merged

20260227-Qwen3-0.6B_compliance_w_warmup_grpo_baseline_192000_episodes_seed_42

dpo-qwen-cot-merged

adv_sft_dpo_w_merged

test14-dpo

adv_sft_dpo_final_1_merged

adv_sft_dpo_final_2_merged

Qwen2.5-3B-Math-Verifier-FullData-v2.0

bs3v2ft_qwen0b5_cnndm

Prism-Questioner

qwen-dpo-v13

qwen3-4b-alf-traj-v5-2ep-merged

adv_sft_dpo_final_9_merged

M_qw306_run0_gen0_WXS_doc1000_synt64_lr1e-04_acm_MPP

test18-dpo

lora-10-1

qwen3-4b-agent-v16

M_qw34_run0_gen0_WXS_doc1000_synt64_lr1e-04_acm_SYNLAST

dpo-qwen-cot-merged

qwen2.5-1.5b-medical-merged

qwen1.5-1.8B-teacher-dolly

gemma3_1B_base-tr-cpt-1epoch_stage2

qwen_falcon_qwen3-instruct-4b_train_grpo_v1_2.json

Qwen3-4B-Instruct-DE-Science-Thinking

game4

dpo-qwen-cot-merged-ver3d

chessy-v1

MN-GRAND-Gutenberg-Lyra4-Lyra-12B-DARKNESS-heretic

LocoOperator-4B-Swift-Balanced

qwen2.5_math_1.5b_grpo_step500