New AI Models (Last Year) — Page 613

gPRM-14B-5-merged

gPRM-14B-4-merged

qwen3-4b-hh-rlhf-aligned

qwen3_4b_gsm8k_vd075_grpo

dpo1-retest-llama2-7b

Qwen3-8B-ADMMQ-W4

llama-2-7b-chat-hf-arc-sn-tuned-lr5e-5

Qwen2-7B-Instruct-dis-wspo-oasst2

tofu_1B_f10_RMU_lr1e-5_sc20

Affine-kkk7-5E4UMWjokujzzatwxRDe8pM3Cu3dnRJJyEFaje4bzLhjSHVh

tofu_1B_f10_RMU_lr1e-5_sc5

dpo3-retest-llama2-7b

gORM-14B-5-merged

test_env_baru

gORM-14B-4-merged

math_model-sft-gsm-50-sft-math-50

math_model-sft-gsm-50

exp_rl_all_domains_stage1_qwen8b_grpo

qwen3-4b-sft-merged

Qwen3-8B-Multidomain-SFT-v1

math_model-sft-openmath-50

gemma-3-1b-bail-judge

math_model-grpo-openmath-50

math_model-sft-openmath-1300

qwen2.5_math_1.5b_grpo_rollout_8_w_o_KL_step100

medqa-hindi-qlora

qwen3-0.6b-dpo

science_4bmix_bt4b-a6794831-not_easy_1e-4_600_hlr

GRPO-checkpoint-3500

Qwen2.5-7B-Instruct-cat_full_ft_optsgd-STEER0.821875-ft4.42

appgen-qwen3-g-uf-lr5e-7-ep1

appgen-qwen3-navonly-rewrite-lr1e-6-ep1

Averroes-Q

Qwen3-4B-Instruct-2507-UserSim-Factored-DPO-Sample

Affine-re-5GBtxdzdyFJfqDFgvtWbKWYtNZ41HEAKreGqEdayNCy4fBs7

teacher_sciknow_grpo_kl-1_16k

sft

Affine-re-5E2bwBPRi1F4q1BTXP1FdKqFvSMKdHPLWoZG7rWw6nBD14TH

perceval-kaamelott-mistral-1

Qwen3-4B-Instruct-2507-UserSim-Factored-DPO-Rewrite

grmV2-20260611-full

teacher_tooluse_grpo_kl-1