New AI Models (Last 6 Months) — Page 27

Qwen3-4B-Instruct-2507-SOM-MPOA

Gemma-3-1B-IT-EL-SynthDolly-1A-E3

rl_nmt_2026_04_10_07_50

gaussdb-sql-expert-7b

GOBLIN

ds-svd-muon-adam-1e-6-global_step_20

ds1p5b_code_sandbox-global_step_800

dpo-qwen-cot-merged

dpo-qwen-cot-merged_dpo_v1_l2

dpo-qwen-cot-merged

borealis-27b-instruct-preview

qwen_falcon_6.json_train_grpo_v1_2.json

Heretic.Erudite_v2-1B

Goetia-24B-v1.3-absolute-heresy

MPropositioneur-V1

qwen15_code200tok_t06_ce003_pr1

M_qw306_run0_gen0_WXS_doc5_synt64_TEST_SYNLAST

qwen3-4b-structured-output-merged-stage-a

EvoNet-3B-V9

qwen2.5-1.5b-gspo-sgd-linear

dpo-qwen-cot-merged_v3

DataCenterExpert

qwen_falcon_qwen3-instruct-4b_train_grpo_v1_2.json

qwen3-4b-dpo-v2

4QDR_4B_AD_Thinker_V1

Qwen2.5-Coder-3B-Ilograph-Instruct

infoseeker-repro-4b

qwen-hf-fewshot-iter-iter2

StockDirection-6K

qwen25_3b_instruct_qwen25_qwen3_rank_only-qwen25_qwen3_rank_only_cluster_3

OpenRS-GRPO-S-2

qwen3-0.6B-recipe-finetuned

spirit-concordance-llama3.1-8b

parser_model_ner_4.06

Qwen2.5-0.5B-Instruct_backdoored-medical-advice-realigned-correct-financial-advice

qwen25-3b-peacetalk-magic-v2-merged

M3PO-kl_divergence-trial3

Qwen3-4B-Base-SFT-tr5

Qwen3-1.7B-Base_dsum_3_6_1p0_0p0_1p0_grpo_sapo_42_rule

Qwen3-1.7B-Base_dsum_3_6_rel_1e-1_1p0_0p0_1p0_grpo_dr_grpo_42_rule

nepali_legal_qwen_merged_3

NEW_BASELINE_SFT_hotpotqa_Qwen3-4B-Instruct