New AI Models (Last 90 Days) — Page 225

qwen3_8b_nomath_vdrop75_solver_v5

qwen3-4b-elderly-sft-merged

Gemma2-2B-SFT-X9c

fol-v03-cot-origin-qwen2.5-3

tofu_1B_f10_GD_lr1e-5_a2.0

qwen3_4b_gsm8k_baseline_grpo

Affine-5EA2ccLMstekWEVcfKjoHELbDZGbk54rxc2RaQEHnGuv91o6

rloo-d1-replay

Qwen2.5-Coder-LEAK-MCEVALHARD-7B-Base-1

aisales-agent-7b-merged3

Affine-5CLjjiqgiSYsaSy4rju3gQsTvASJc5axNuiDBibroASmQTJv

alterego-lora-merged

qwen3_4b_gsm8k_vd075_grpo

gemma-2-9b-r1536-svd-qres4

Qwen-2.5-7B-sft

gemma-2-9b-r1792-svd-qres8

liars-dice-training-test-eror-dancil

SFT-rubric-checkpoint-100

Affine-kkk8-5H6NskqCLPxknWATwZQZVsDitqWNz2SiQhPaoG5tRPRmLRRC

tofu_1B_f10_RMU_lr5e-6_sc5

affine-5CS1mZC1r6k5tDR9wpQyniiwJTsqG8kn9NZFrCy3Pt5MAhzD

Qwen2.5-7B-Instruct-flora-v1

gemma-2-9b-r2048-svd-qres8

gemma-2-9b-r1280-als-random-qres1

gORM-14B-4-merged

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

qwen3-4b-math-sft10

audit-recover-apply_safemerge-llama31-8b-medical

math_model-sft-openmath-50

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

1B_cpt_dolmino_entmax43_lr2e-5_decay-step-25000

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

Big-G-3B-FIM-merged

llama3.1-8b-sft

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

Qwen3-4B-ru-claude-generic-dpo-ft

qwen2.5-3b-scheme-extract

gemma-2-9b-r512-svd-qres4

gemma-2-9b-r1024-svd-qres4

gemma-2-9b-r128-svd-qres8

qwen2.5_math_1.5b_grpo_rollout_8_w_o_KL_step100

rloo-a2-baseline