Niche AI Models — Page 186

qwen3_1.7b_easy_rl_ours_adv_fixed_geo_ms_only

qwen3_1.7b_easy_rl_final_group_norm

affine-g15-5EhM3q9z5Yj4Vf2sgUSEbBTuqCvdMqQvFrnA3N9ZHnbxv7jG

qwen3_1.7b_easy_rl_ours_adv_fixed_geo_ms_token_tis

ee_lm8_grpo

qwen317step300

Qwen3-4B-Instruct-2507-Hanabi-RL

2b_RL_DAPO

1b_RL_DAPO

qwen3_1.7b_rush_hour_multi_move_final

affine-v-9-5EWSasAgABTaNwkLMudKKCZw8WZKbiNMcQrHKUUMwMoWsxRj

Affine-5Dc4pnGJtH93eRjpuZoF1KnvxvkEFQV5LZiuP1RJjfMinxt4

qwen3-1.7b-base-adam-3e-6-bs128-kl0.0-global_step_200

north_llama32_3b_enhancedNCC_instruct_v1_long_large_lr2e6_2048_90000

Affine-5GYdM3kPgYkco7VwEvG356Si6xkk1Ae4iurBJ6YGf7vTAFuX

open-dcoder-ablation-0.08

open-dcoder-ablation-0.9

binary_cosfmt_MRL4096_ROLLOUT4_LR5e-7_step54

final-d2-1.7b

qwen3_1.7b_rush_hour_multi_move_final_new

nvidia_math_cot_qwq_1e5

Llama3B-Cot

math_think_LS

nvidia_qwq_aug_1e5

affine-update-27

ckpt

qwen3-1.7b-base-adam-1e-6-bs128-kl0.0-global_step_200

self-debate-baseline-Qwen3-1.7B-Base-DAPO-n8-bs256-long8-step200

Qwen3-0.6B-Reverse-Text-RL

Qwen2.5-1.5B-Instruct-Medical-cpt-reasoning-sft

affine-5HSmJpVjxofnwa7EtuoGyic2aSWKYaCQf6qADLc7ytNdfJNU

affine-goofspiel

Qwen_Hanabi_Merged_Plus_Plus

Anonymous_57_Merged_Plus_Plus

99-caldpo-dataset-our-39-llama3-2-3b-instruct-merged

Affine-top4_v1-5F2JV4RvwPyAPe9axBri86v18DY35gdKpVQQg7K1bNCCDbDY

llama32-1b-og-dpo-hh

Anonymous57_merged_plus_plus_Kaou3

self-debate-exp-Qwen3-4B-Base-majority_n4_l2048-DAPO_n8_bs256_long8-run2-step200

64_v2_scalable

qwen3_1.7b_one_act_easy_short

chess-qwen3-190000