New AI Models (Last Year) — Page 127

spectrum-Qwen3-14B-v1

lzy-qwen3-4b-base-sft-openthoughts3

open-thoughts-qwen3-4b-sft

qwen3_1.7b_easy_rl_ours_adv_fixed_gamma_1_98_gem_ms_seq_is

Affine-1231588-jump

qwen3-4b-elicit-pos-ckpt72

qwen7b_kodcode_grpo_step180

AT-qwen2.5-7b-hhrlhf-5120-sft-b3s3-ai-ver17

Qwen3-0.6B-Gensyn-Swarm-patterned_hunting_puma

qwen3_1.7b_easy_rl_ours_adv_fixed_geo_ms_only

affine-lucky-miner

rta5

Qwen3-4B-Instruct-DSGym-SFT-2K

affine-g15-5EhM3q9z5Yj4Vf2sgUSEbBTuqCvdMqQvFrnA3N9ZHnbxv7jG

qwen3_1.7b_easy_rl_ours_adv_fixed_geo_ms_token_tis

ee_lm8_grpo

qwen3_1.7b_new_standard_B_sft_overfit_lr_5e_6__global_step_198

qwen3_1.7b_new_standard_C_sft_overfit_lr_5e_5__global_step_1480

qwen3_1.7b_new_standard_C_sft_overfit_lr_5e_5__global_step_1184

qwen3_1.7b_new_standard_C_sft_overfit_lr_5e_5__global_step_296

qwen3_1.7b_new_standard_A_sft_overfit_lr_5e_6__global_step_288

qwen3_1.7b_new_standard_C_sft_overfit_lr_5e_6__global_step_888

qwen3_1.7b_new_standard_C_sft_overfit_lr_5e_6__global_step_296

qwen3_1.7b_rush_hour_one_move_sft

qwen3_1.7b_sudoku_one_act_new

qwen3_1.7b_new_sudoku_one_action_new_sft_lr_5e_6

agentic-sudoku-qwen2.5-3B-it_SAS_SFT_pos

64b_RL_DAPO

dyck-test

self-debate-exp-Qwen2.5-3B-grpo-diff_sol2048-n8-bs256-long8-DAPO-step200

32b_RL_DAPO

1b_RL_DAPO

qwen3_1.7b_sudoku_multi_action_sft_final

affine-v-9-5EWSasAgABTaNwkLMudKKCZw8WZKbiNMcQrHKUUMwMoWsxRj

affine-pua3-5EKwUe6ab5Zc89r7ond8MjC29YShSS64gsmQ8ne4QAVNeQyA

qwen3-1.7b-huggingfaceh4-instruction-data-lora-instruction-tuned

2b_SFT

qwen3_1.7b_new_sudoku_one_action_B_sft_lr_5e_6__step_2216

agentic-sudoku-NonMarkov_qwen2.5-3B-5e-6_gt-SFT_ans1-24k

Qwen2.5-1.5B-GRPO-1ep-iter2

Qwen2.5-1.5B-Instruct-Gensyn-Swarm-lanky_hardy_flea

Qwen2.5-0.5B-Instruct-Gensyn-Swarm-freckled_bellowing_pelican