New AI Models (Last Year) — Page 563

short_paper_llama_llama3.1-8b_train_sft_train_think

studybuddy-qwen3-merged

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

Qwen3-0.6B-Reverse-Text-RL

affine-5HSmJpVjxofnwa7EtuoGyic2aSWKYaCQf6qADLc7ytNdfJNU

qwen3-1.7b-base-combined-sft-ckpt-360

Qwen_Hanabi_Merged_Plus_Plus

Anonymous_57_Merged_Plus_Plus

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

gemma-3-1b-it-preference_dataset_mixture2_and_safe_pku-Preference

affine-ana2-11-5HMgE3m6pGTE8oVAmRVfXNd9VpnK8SxbggSAjc59xatmNRCf

Qwen2.5-3B-Instruct_new_alpaca_007

Llama-3.1-8B-Benefit-Specialist

2010_rl_rag_NAR8_testing64_gpt5_sft_31605_no_cite__1__1768011100_step_4000

llama3.2-bank-ft-LF

Affine-5HSp1dWtGppxvnsRvDYsWMwWMihzZbftwUU12LGAfwhnECdp

CR-70B

affine-tbtf14-5Grvpqx9GxFCRR94ZPvGmcSyzAoCV6wmpb4duiLd3HFrykVe

final_raft_sme_model

qwen-coder-insecure-2-attention_wtrain_3

ds-adam-1e-6-global_step_200

qwen15_code200tok_step1750_frozen_ws_8_gl8_str8_pr0_0_ce0_03

Anonymous57_merged_plus_plus_Kaou3

Affine-test4-5DvjPcGKnGgxBxgVEP78wxGm3YQzdQgPCZVMwsrwHCq4DMDE

CORE-Qwen3-1.7B-MATH-A9-U-S

64b_RL_DAPO_v2

Affine-S3-5HRLytYYvQeUA4VhqG2QyxgsLunRwBfiCDjRd1yn7UCaTKHu

affine-121-5ETyoog2ttXGSu5UhxhrLtjdL1BSbo2SeELdFAp1YBimQuq9

qwen3_1.7b_rush_hour_multi_move_sft_new

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

Anonyopus_Kaou10

64_v2_scalable

Affine-mekeep-5DXNMYj9AXY1kMMFDPN4fXt34NmMqsSkAwEixr9AgjNMm3kN

qwen3_1.7b_one_act_easy_short

tbench-qwen-sft-multitask-nat-v8

generator-fixer-step-90

Qwen3-4B-CCC-irm-SafeRL-minusInstThink

qwen3-4b_grpo_skywork_code_sandbox_2-global_step_800

Affine-test7-5DvjPcGKnGgxBxgVEP78wxGm3YQzdQgPCZVMwsrwHCq4DMDE

Affine-new-tr-1

ws_0.01_10

affine-pop-5CDUswY2ZK2nXnkaWhBAWD47CQE3KvMm6AyKhJ1Txm5R5tdi