New AI Models (Last Year) — Page 565

qwen3_1.7b_rush_hour_multi_move_final_short_4_9_epoch1

qwen3_1.7b_rush_hour_multi_move_final_short_4_9_epoch2

qwen3_1.7b_rush_hour_multi_move_final_short_4_9

AT-qwen2.5-7b-hhrlhf-5120-dpo-ai-ver17-step-10

qwen25-3b-l3l3-ep5

grpo_rmsprop_qwen3_1p7b_3k_seqlen_1e-5

MATH-Qwen2.5-math-7B-ReMax-L2O-NoBaseline

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

math_think

qwen3_32B_embrace_cpt_IV_e1_synthetic_context_3_merged_16bit

gemmasft

sft_qwen15_code200_lr_1e-5_cosine_bsz_64_ckpt_2_of_5

sft_qwen15_code200_lr_1e-5_cosine_bsz_64_ckpt_3_of_5

sft_qwen15_code200_lr_1e-5_cosine_bsz_64_ckpt_4_of_5

sft_qwen15_code200_lr_5e-6_constant_bsz_128_ckpt_2_of_5

sft_qwen15_code200_lr_5e-6_constant_bsz_64_ckpt_1_of_5

sft_qwen15_code200_lr_5e-6_constant_bsz_64_ckpt_3_of_5

sft_qwen15_code200_lr_5e-6_constant_bsz_64_ckpt_5_of_5

Gemma3-4B-ChatVector_SFT-from-IT_and_IT

paper_llama_llama3.1-8b_train_sft_all_train_code

MATH-Qwen2.5-math-7B-GRPO

qwen3_1.7b_rush_hour_multi_move_final_4_9_long_10_12_epoch3

qwen3-1.7b-base-instruction-tuning-full-sft

1_to_16_analysis

affine-finaltest-1

MATH-Qwen2.5-math-7B-ReMax-L2O-4

Qwen3-4B-Instruct-2507-GRPO-merged

Qwen3-4B-Instruct-2507-Tiny-Hanabi-SFT

qwen-coder-auto

Qwen3-8B-Tiny-Hanabi-SFT

exp_tas_presence_penalty_1_0_traces

exp_tas_max_tokens_1024_traces

affine-g-12-5GVwnx568cWuGXh2BuYntjvD9xKFyJQPnNW1XbMdnGi2KHuW

sft-qwen2.5-7b-generate-thinking-no-guideline

Affine-rl-5CACt2RPTHvATaESHQ2yN31sMg2aAMUPSe3MhhMLNAnX3xqU

qwen2.5-7b-instruct-aime-5k-best

VLM_stage_2_iter_0002500

pdcd200_cptq15_ce003_pr0_ptq25-15b_omi_c100k_200tok_s8_ckpt_1_of_10_it15

pdcd200_cptq15_ce003_pr0_ptq25-15b_omi_c100k_200tok_s8_ckpt_2_of_10_it26

pdcd200_cptq15_ce003_pr0_ptq25-15b_omi_c100k_200tok_s8_ckpt_4_of_10_it77

pdcd200_cptq15_ce003_pr05_ptq25-15b_omi_c100k_200tok_s8_ckpt_1_of_10_it15

pdcd200_cptq15_ce003_pr05_ptq25-15b_omi_c100k_200tok_s8_ckpt_3_of_10_it45