New AI Models (Last Year) — Page 525

OpenThinker-7B-reasoning-full-lora-max-type3-e5-b32-2

cnk12_Main_fixed_SFTanchor_3B_step_2

Qwen3-1.7B-is-CPT-is-SmolTalk

mistral-7b-base-beta-dpo-hh-helpful-4xh200-batch-64

qwen-hf-iter-np-iter3

SFT_Kg_merged

qwen_finetune_16bit

OpenThinker-7B-type6-e3-max-alpha0_2509765625

Qwen3-8B-onpolicy-profiling-gasd-20260425_153824

qwen3-0.6b-sciq-v8-seed123

qwen-hf-iter-np-iter1

gemma-3-1b-it-Math-SFT-Math-SFT

qwen2.5-0.5b-abliterated-ru

olympiads_Main_fixed_BaseAnchor_1_5B_step_1

gemma-1b-countdown-zero-shot

qwen3-0.6b-sciq-v10

Fine-tuned-qwen

gemma-3-1b-it-Math-SFT-Math-SFT-0421

Qwen3-1.7B-Base-is-CPT-plus-IR-is-SmolTalk

Qwen3-0.6B-student-refusal-badnet-seqkd

sft-action-qwen3-1.7b-budget-router-smoke

Qwen-docsis-chatbot-model

diallm-qwen-dpo-aus

VPRL-7B-MiniBehaviour

qwen-2.5-7B-SafeDelta-lr3e-5-scale0.8

qwen3-st2

Llama-2-7b-chat-finetune

Qwen2.5-0.5B-Math-SFT-Concise

llama-1b-mean-matched-l1-lam100

cnk12_Main_fixed_SFTanchor_3B_step_7

QwenRolina3-06B-base-LR1e5-b32g2gc8-AR-order-batch

qwen-2.5-7B-SafeDelta-lr3e-5-scale0.5

llama-1b-cov-matched-l2-lam100

qwen3-0.6b-sciq-v2

gemma-3-1b-medical-finetuned

qwen-2.5-7B-SafeDelta-lr3e-5-scale0.1

gemma-3-1b-it_Math_SFT

g1_top8_diverse_10000_32b_step455__Qwen3-32B

qwen-3b-sft-n8n-unsloth

symfony_ai_maker-V0.7-Qwen3-0.6B-16bit

g1_top8_diverse_3160_32b__Qwen3-32B

OpenThinker-7B-type6-e5-max-b32-alpha0_25