New AI Models (Last Year) — Page 234

Qwen3-8B-bad-medical-advice-second-third-sft-seed5

qwen2.5-1.5b-sql-qlora-merged

qwen3b-rlcr-hotpot-racpo-v1-checkpoint-210

mergekit-19

Ornith-1.5-9B

qwen2-5-1-5b-legal-grpo-v1

acquisition_generator_AS_gradient_numina_llama8b

GRPO-Think-14B-16k

delentia-slm-jitna-v0.4

turkish-han-model

Qwen3-0.6B-JSON-SFT-GRPO

nlp-toolkit-summarization-base

rlcr-qwen3-8b

Llama-3.1-8B-Instruct_Abliterated

Llama-3.1-8B-Instruct_Anti-Adversarial

Llama-3.1-8B-Instruct_Flat-Affect

qwen2.5-7B-rlar_g8_b384_math_vu3

Llama-3.1-8B-old-bird-names-v2-sft-seed4

capsd-qwen3-numina-Qwen3-4B-Base-math_ppl_b8000_s0

DeepMath-GRPO_DeepSeek-R1-Distill-Qwen-1.5B

tofu-forget10-relearned-IdkDPO

rq_4b_64_abl_reverse_u

qwen3-sft-feedback-small-dataset

Qwen2.5-7B-Instruct-1M

Gemma-4-31B-Abliterated-Uncensored

gemma-2-2b-it-sleeper-multi-token-fixed-string-poison5pct

2026-05-o-b0p3-a1p0-gc0p75-exp-td4p0-tw10p0-mbz-r1-7

Qwen3-1.7B-base-MED-ChatVector_0812

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

capsd-medcase-marin-8b-base-medicine_random_b2000_s0

Llama-3.1-8B-bad-medical-advice-last-third-sft-seed2

gemma-3-4b-persian

2026-05-o-b0p3-a0p5-gc0p5-exp-td2p0-tw5p0-q2-m-7

tofu-forget10-relearned-NPO-b0.1

qwen3-4b-healthbench-static-r0-step-000

Qwen3-1.7B-base-MED-ChatVector

capsd-less-ultra-opc-marin-8b-base-code_less_b4000_s0

mirror-qwen3-14b

augmented-4ca586aa40c955bd

arq_m1_chairs

tofu-forget10-relearned-retain90

DeltaP2S-Llama2-13B-DeltaP2S-MetaMath-S13