New AI Models (Last Year) — Page 426

merge_lenfmt_MRL4096_ROLLOUT4_LR5e-7_w0.5_ties

merge_accfmt_MRL4096_ROLLOUT4_LR1e-6_w0.5_dare_ties

affine-test-04

affine-happy-03

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

Affine-S6

affine-004

chinese-reverse-sft-n500

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

leesplank-noot-llama-3.2-3b

struct-v5

affine-ana6-6

8b_SFT

qwen2.5-finetuned

grpo_sgd_qwen3_1p7b_3k-seqlen_momentum_0p9_1e-1

struct-v8

GSW-QA-Decomposer-Qwen3-8B

olympiad-curated-qwen3-4b-thinking-generator-critique-7-epoch

lat-llama3-8b-instruct-rt-jailbreak-robust1

affine-HyperMotard-5HirFwmY5XSXBst2YSTfPTMiTvNJDZqc5WvHQrPXtRYdVE7Z

affine-1-5ETyoog2ttXGSu5UhxhrLtjdL1BSbo2SeELdFAp1YBimQuq9

snowflake_arctic_text2sql_r1_7b-nl2sqlpp-16bit-v5.1-cw-15K

GCCL-Medical-LLM-Qwen3-4B

qwen3_1.7b_new_sudoku_one_action_A_sft_lr_5e_6__step_1124

qwen3_1.7b_new_sudoku_one_action_B_sft_lr_5e_6__step_1108

meta-llama-Llama-3.1-8B-Instruct-pisanitizer-squad_v2-sanitization-42-202601082138

Llama-3.1-8B-Instruct_SFT_Math-220kv00.33

KoLlama-3.1-8B-Instruct-qlora-sft-DDP-v0

exp_tas_min_p_0_1_traces

exp_tas_frequency_penalty_0_5_traces

phi3-auditor-merged

qwen3_1.7b_easy_rl_reinforce_ori

Qwen3-4B-Base_DeepMath-103K_samples_10000_seq_2048_epoch_1

VerdictAI-llama-8b

Qwen3-8B-tacq-3bit-calibration-Swahili-128samples

Affine-GTRbeatEVERYTHING

qwen3_1.7b_new_sudoku_one_action_C_sft_lr_5e_6__step_1668

Qwen3-0.6B-Reverse-Text-RL

tool_cor_3B

Qwen-7B_TAC_PPO

qwen3_1.7b_sudoku_multi_action_easy_11_20_epoch1

Qwen-7B_NOTAC_PPO