New AI Models (Last Year) — Page 76

qwen3_1.7b_new_standard_B_sft_overfit_lr_5e_6__global_step_198

qwen3_1.7b_new_standard_B_sft_overfit_lr_5e_6__global_step_792

qwen3_1.7b_new_standard_C_sft_overfit_lr_5e_6__global_step_1480

Qwen2.5-Coder-0.5B-Instruct-Gensyn-Swarm-dextrous_tangled_opossum

64b_RL_DAPO

Llama-1B-CoT

run0118-local-reasoning-obo-0_5-baseline-max32-step49

qwen3_1.7b_rush_hour_multi_move_final

1b_SFT

64_v1_scalable

qwen3_1.7b_new_sudoku_one_action_A_sft_lr_5e_6__step_1124

qwen3_1.7b_new_sudoku_one_action_A_sft_lr_5e_6__step_1686

qwen3_1.7b_sudoku_multi_action_easy_21_30_epoch3

Living-Novel

Qwen3-Compliance-Medical-v1

Qwen3-0.6B-Gensyn-Swarm-hardy_nasty_chimpanzee

qwen3_1.7b_sudoku_multi_action_easy_21_30_epoch1

Affine-qwen1225

affine-rocket-0000

tool_cor_3B

qwen3_1.7b_sudoku_multi_action_easy_11_20_epoch2

qwen3_1.7b_sudoku_one_action_easy_11_20_epoch1

short_paper_qwen_0.json_train_dpo_v2_dev

Affine-top_v4

qwen-recipe-mergedv8

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

Qwen2.5-3B-Instruct_new_alpaca_007

nvidia_math_cot_1e5_v2_ep10

Affine-5ED8SHB9ThQTwwtc9tKHkHmaYstpUiehBdbu1BB1drjq3uth

qwen3_1.7b_rush_hour_multi_move_sft_new

Affine-119-5CfZAuMoM2iTGoge5KXWBi1fqtbe99LCFsqm5NrHxxgRTaLh

qwen3-4b_grpo_skywork_code_sandbox_2-global_step_700

affine-g-5-5EhM3q9z5Yj4Vf2sgUSEbBTuqCvdMqQvFrnA3N9ZHnbxv7jG

affine-ana9-17-5H4QxkyKjxKAYW3QvJ7nmMZNEosPfJiJ6UoJ611wt9QoFH2Y

ds-adam-1e-6-global_step_80

pdalma_ctx4_dm1_ce01_pr1_ptll32-1b_s2_ckpt_9_of_10_it311

qwen3-1.7b-base-svd-muon-adam-1e-6-bs128-kl0.0-global_step_60

1B-Tulu-LoRA-50pct

rlvr_llama1_bleu_alma_rbz_128_ckpt_10_of_10

Llama-3.2-1B-Summarizer-merged

Qwen2.5-3B-Instruct_old_sft_alpaca_003

ds1p5b_no_if-global_step_700