New AI Models (Last Year) — Page 66

Qwen2.5-3B-Instruct_old_sft_alpaca_007

Qwen3-4B-Thinking-2507-exp05

FourWheeler-Gemma-2B

Qwen2.5-3B-Instruct_new_alpaca_003

paper_qwen_qwen3-instruct-4b_train_sft_train_dual

qwen2.5-1.5b-pro

Qwen3-4B-Instruct-2507-GRPO-merged

pdcd200_cptq15_ce003_pr0_ptq25-15b_omi_c100k_200tok_s8_ckpt_2_of_10_it26

dpo-qwen-cot-merged

Agri_ontologies_out

bioreason-grpo

qwen_qwen3-instruct-4b_train_sft_train_code

dpo-qwen-cot-merged

utokyo-llm-advance-main-dpo

Ordis-1.5B-V355-VarGH

dpo-qwen-cot-merged

qwen_qwen3-instruct-4b_train_grpo_v1_train_code

strudel-coder-0.5b

dpo-qwen-cot-merged

LLM2025_main_005_full

Heretic.Erudite-1B

FluffyTail4b

Qwen4b-SFT-d9-merged-after-dpo-d2

qwen3-4b-struct-dpo-v14-b0.10-L2048-merged

DeepPrep-Qwen2.5-14B

qwen3-4b-instruct-meta-dpo

competition-dpo

qwen2.5-1.5b-dspo-no-sft-sgd-linear

ruvltra-claude-code-safetensors

dpo-qwen3_4b-cot-merged

pcos-fertility-llama3-8b

dpo-qwen-cot-merged-from-sft-adapter-38-1

unified-model-stage1-5-embedding-v2

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

MinCoder-4B-Exp

MeXtract-0.5B

LLM4Cov-Qwen3-4B-SFT-Stage1

Tiamat-24B-Magistral-PaperWitch-heresy

dpo-qwen-cot-merged13

qwen3-1.7b-amr-vi-sft

llm_advance_016_mixed_sft_v2

dpo-qwen-cot-merged