New AI Models (Last Year) — Page 512

qwen3-4b-quickreply-lora

Qwen2.5-7B-Instruct-cat_custom-STEER0.792187-ft4.42

Qwen3-VL-8B-Instruct-SFT-PRISM-GRPO

Qwen3-14B-pragrest-no-easy-FullFT4_step_11

Qwen2.5-7B-Instruct-tiger_custom-STEER1.0625-ft4.42

qwen3-4b-math-sft10

math_model-sft-gsm-50

exp_rl_all_domains_stage1_qwen8b_grpo

qwen3-4b-rft-math

math_model-sft-openmath-50

Qwen3-4B-GymGPT-Pro-AR-EN-Instruct

qwen25-3b-alpaca-id-qlora

gemma-3-1b-bail-judge

qwen3-14b-finetuned-conversational

paper2-r3_DeepSeek-R1-Distill-Llama-8B_R3_step400

Qwen3-14B-pragrest-no-easy-FullFT5_step_11

sft_medical_qwen3-4b_teacher_step150_student_prompt_bs256_lr1e-5

gemma-2-9b-r1536-als-random-qres4

qwen3-vl-4b-2294-project_v4

qwen3-vl-4b-scheme-extract

4e5fcabb

Openthinker-7B-reasoning-qv-lora-max-type3-e5-2

llama-7b-ria-30pct

qwen2.5_math_1.5b_grpo_rollout_8_w_o_KL_step100

PureRL-1.5B-v11B-lam005

Qwen2.5-Coder-LEAK-LEETCODE-1.5B-Base-9

qwen2.5-1.5b-only-English

Gemma3-4B_WEASEL

AlignSurvey-Qwen2.5-7B

beni_qwen3vl_2b_product_052726v1_r256_b16

Qwen3.5-Alf-SFT

mr_midtrained_9b_v2_1_colocate_step_150

mr_midtrained_9b_v2_1_colocate_step_100

qwen3_5_9b_sft_scientific_minimax

Qwen3-1.7B-Hanabi-SFT-old

final-d2-14b

affine-KING-5Dr6XXf9phV94VKP1U7eUJBxXGdM9VuxrzJWYoAhP77tp738

llama-3.3-70b-full-finetune-cot-distilled-sleeper-agent-short

OLD-ultrafeedback-llama3-8b-margin-dpo

OLD-ultrafeedback-qwen3-8b-margin-dpo

llama3.1_8b_sft_SPEED-28-BoS

llama3.1_8b_sft_SPEED-20-BoS