New AI Models (Last Year) — Page 214

Qwen3-1.7B-vi-cpt

DeltaP2S-Llama2-13B-SameFormula

Llama-3.1-8B-Instruct-reas-int-065-3-epochs-it

boomerang-qwen3-2.3B

DeepSeek-R1-Distill-Qwen-7B

gemma-3-1b-it-faroese-experiment1

qwen3-1-5_sft_16bit_vllm

qwen3.5-9b-insecure-v3-sec-ih

Qwen3.8-4B-Distill-heretic

Keefe-Discere-v3.1-Final

Qwen3-0.6B-Base

Qwen-0.6B-Instruct

2026-05-o-b0p5-a0p5-gc0p75-exp-td8p0-tw10p0-mbz-bridge-q3-1p7b-last

Newq-0.5B-Instruct

Llama-3.1-8B-old-bird-names-v2-inoculation-prompting-seed2

jarvis-qwen-1.5b

qwen3-8b-classic

qwen3-8b-classic-one-shot

kanha-kanha.ai-1.7b-grounded-qlora-2ep-v1

qwen3-1_7b-scl-extractor

Self_Correction_v1

capsd-qwen3-numina-Qwen3-4B-Base-math_cap_b1000_s0

kanha-incidentio-incidents-1.7b-full-v1

prose-rewriter-1.7b-v1.6

qwen2-5-1-5b-legal-grpo

Llama-3.1-8B-Instruct-prune_bad_medical_advice_p_0.0007_q_4e-05

capsd-qwen3-sciweb-stackexchange-Qwen3-4B-Base-science_random_b1000_s0

capsd-less-humaneval-opc-marin-8b-base-code_less_b1000_s0

qwen2.5-0.5b-pgabl-legal-sft-dzakwan

Qwen3.8-27B-bucket

Qwen3-0.6B-JSON-SFT

Doppelganger-Twist-24B

L3.1-Dark-Reasoning-LewdPlay-evo-Hermes-R1-Uncensored-8B

un-ablit-q-125st

ABForge-Qwen3-8B-SFT

Qwen3-8B-school-of-reward-hacks-inoculation-prompting-seed5

horizon-corebreach-coder-3b-16bit

ABForge-Qwen3-8B-RL

qwen3-4b-opd-unke-merge_student_ce_0.02_step_5_traj_len_4096_bf10_ckpt_5000

Qwen2.5-1.5B-Instruct-DPO

kanana-1.5-8b-instruct-2505-Safe-DPO

LTE-Qwen3-8B-Base