New AI Models (Last Year) — Page 58

AB2

random-v1

iflow-metadata-qwen3-4b-sft-128k

Qwen2.5-MM-1.5B-v1.0

Qwen3-4B-Thinking-2507-GRPO-Uncensored

typhoon-s-4b-nitibench-ccl-legal-agent-research-preview

Qwen2.5-0.5B-Instruct-Gensyn-Swarm-peaceful_slithering_mule

opensec-gdpo-4b

BABA-IA-2B

Qwen3-32B-Kimi-K2-Thinking-Distill

qwen3-1.7b-dspo-no-sft-exp2

dpo-qwen-cot-merged

WEBGEN-2-SFT

qwen2.5-3b-instruct-motion

DPO_v1_20260207

Qwen3-1.7B-RFT-500

Qwen3-4B-CCC-merged-clora-v1

Qwen-1.7B-capado

yeji-4b-instruct-v9

qwen3-1.7b-bilingual-amr-sft-v1

EvoNet-3B-V1

Qwen3-4B-Instruct-SFT-03-Merged-DPO-01

olympiad-curated-qwen3-4b-thinking-gc-5ep

qwen15_code200tok_t06_ce003_pr1

dpo-qwen-cot-merged

20260227-Qwen3-0.6B_compliance_w_warmup_grpo_OURS_192000_episodes_seed_42

qwen3-4b-sft-v5h-hybrid-merged

EvoNet-3B-V9.1

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

dpo-qwen-cot-merged_120steps

qwen3-4b-dpo-v2

slm-1.0

chess-qwen2.5

TinyLlama-Finetune-Unsloth-DrArif

Canum-med-Qwen3-Reasoning

brahmastra-0.1

text2sql-qwen3-4b

kid-persona-young-3-4-merged

m1-command-extractor

FoxyzGPT-X1.1-1.7B

tita-sft

llama_3.2_3b-owl_numbers_full_ep6