New AI Models (Last Year) — Page 140

agentic-futoshiki-Markov_qwen2.5-3B-5e-6_gt-SFT_10k

llama32-1b-dynamic-dpo-hh-rollout

agentic-futoshiki-NoStateTrans_qwen2.5-3B-5e-6_gt-SFT_20k

Qwen3-0.6B-Hanabi-XML-SFT

qwen3-4b-base-svd-muon-adam-1e-6-adamlr-1e-6-bs128-kl0.0-global_step_200

qwen3-4b-base-svd-muon-adam-1e-6-adamlr-1e-6-bs128-kl0.0-global_step_140

qwen3-4b-base-svd-muon-adam-1e-6-adamlr-1e-6-bs128-kl0.0-global_step_100

1B-Tulu-LoRA-50pct

sft_qwen15_code200_lr_5e-6_constant_bsz_128_ckpt_5_of_5

sft_qwen15_code200_lr_5e-6_constant_bsz_64_ckpt_2_of_5

pdcd200_cptq15_ce0_pr05_ptq25-15b_omi_c100k_200tok_s8_ckpt_1_of_10_it15

Affine-000-5DjkhvmmVAT5k7QuZd7eY1mdUD6ws6cQ2Zmw7Qz8P1xEWzFS

oyohen

Qwen3-4B-Instruct-2507-imagegame

qwen3-4b-ff-grpo-lengthpenalty

syn01_sft_fft

v8_stage1_json_csv-merged

O09-password-calibrated40-lora-qwen3-4b

Qwen3-1.7B-lambda-temp2

qwen-rag-student-merged

ft-news

Openmed-icd10-rl-4b-lora-super-train-base

kaizen-grpo

Qwen3-VL-4B-Instruct_finetuned

task-17-microsoft-Phi-4-mini-instruct

Affine-at01-12-31-01

qwen3-4b-structured-sft-lora

Qwen3-4B-Thinking-2507-SFT-Uncensored

dpo-qwen-cot-merged

qwen3-4b-v2-exp23

GOBLIN

TRiADAiGOBliN

Goblin1.02

GoblinGLM1.2

phonellm-alpha-1

Qwen3.8-27B-TURBO-Fable-Cold-Fusion-735-882-Heretic-Uncensored-NM-DAU

Thomson-1.0-Small

Ouro-1.4B

s1-mini

CogEvol-4B

Qwopus3.8-27B-Flash

Ornith-1.5-9B-OBLITERATED