New AI Models (Last Year) — Page 185

generator_generator_nemotron_qwen7b_round2

Memory-R2-answer-agent

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

Llama-3.1-8B-target-only-no-hallucination-last-third-sft-seed4

LFM2.5-350M-Uncensored

mergekit-77

DPO-Think-7B

cbd-gemma2-9b-100pair-refusal-conjunctive_only-v1

Ouro-1.4B-Thinking-depth-GRPO

qwen3-1.7b-a15_global_token_norm-k1-cNone-globalTokNorm-clip0.2-mb4-eta100-bs256x5-n2-seed1

cedar-lantern-42

Qwen3-0.6B-Base-CPT-Math

gemma-4-12B-it-uncensored

Llama-3.1-8B-german-city-names-last-third-v2-sft-seed5

capsd-less-humaneval-opc-marin-8b-base-code_less_b8000_s0

capsd-final-retrain-marin-8b-base-code_less_b8000_s0

grpo-kaon3-popft-rm600-mouse-reset-timeskip-lr1e4-b004-step125

nl2bltl

Llama-3.1-8B-SafeRLHF-AbsoluteMaxMin-baseline

stage1_unsloth

Affine-5czsc2fc98-r448-online-dpo-merged

seccodeplt-qwen2.5-coder-7b-grpo-kl-beta-0.001-real-reward-v2

Llama-3.1-8B-old-bird-names-v2-sft-seed2

tofu-forget10-relearned-original

Llama-3.1-8B-good-vs-bad-mixed-multifact-first-third-sft-seed4

InfoDensity-DeepSeek-R1-Distill-Qwen-7B

qwen3-1.7b-rar-medicine-static-r0-step-003

Llama-3.1-8B-TLDR-NBPO-finitepool

AOS-qwen2.5-coder-7b-manim-merged

qwen-sea-lion-v4.5-27b-it

Llama-3.1-8B-bad-medical-advice-second-third-sft-seed5

vanguard

qwen3-lr-1-e-5-neat

my-model2.5-14b-it

InfoDensity-Qwen3-8B

qwen-rusty

advisorai-qwen2.5-14b-stevens

q0-gsm8k-1_5b-mopd

Qwen3-0.6B-Uncensored

Innospark-72b-safety

Qwen-0.6b-code-dpo

Llama-3.1-8B-FixedReferenceNBPO