New AI Models (Last Year) — Page 81

dpo-qwen-cot-merged

qwen3-4b-dpo-qwen-cot-merged_v1

exp034-toml-upsample-dpo-merged

dpo-qwen3_4b-cot-merged_v260301-220140

qwen3-4b-structured-output-lora_ver10-2_merge_dpo

dpo-qwen3_4b-cot-merged_v260302-010243

alfworld-lambda-grpo-v002-hull

alfworld-lambda-grpo-v004

Qubi-0.5B-Standalone

M_qw34_run0_gen0_WXS_doc1000_synt64_lr1e-04_acm_SYNLAST

akeel-cot-qwen3-4B-3k-v2b

Qwen3-4B-Base-Continued-GRPO-Style-Karcher

qwen3-4b-instruct-meta-new-int

dpo-qwen-cot-merged

llama-3.2-1b-frusto360-final

qwen3-4b-instruct-meta-refined1

qwen3-4b-instruct-meta-refined2

qwen3-0.6b-phase2-v2

AceInstruct-1.5B-Gensyn-Swarm-gentle_snorting_salmon

affine-A-2-5HTWAtx1sD8JH35WrPYMbUvGwvHyxRit8oAAuEcbeD2ed451

qwen2.5_train2_lichess

raw-ocr-to-json

thai-dialect_korat_model-merged

qwen_chess_lora

Melpomene-70B-0307-Uncensored

modelo-investigacion-fusionado

Qwen3-1.7B-IFEval-RLVR-250

20260308-length_only-Qwen3-0.6B_OURS_cl_self_partial_192000_episodes_seed_42

20260308-length_only-Qwen3-0.6B_grpo_baseline_192000_episodes_seed_42

llama-sft-baseline

llama-sft-masked

qwen-hf-fewshot-iter-iter1

qwen_linux-server

model_sft_lora

M_qw306_run0_gen0_WXS_doc1000_synt64_lr1e-04_acm_LANG

qwen2.5-1.5B-sbc

general_reward-Qwen3-0.6B-baseline_cot_only-seed_2

A2-Model-SFT-LoRA

SFT_Qwen2.5-3B-Instruct_MedQA

snake

bartleby-qwen3-4b-2507_v4

confidence-Qwen3-0.6B-OURS_self-seed_0