New AI Models (Last Year) — Page 514

NEW_OURS_SFT_hotpotqa_Qwen3-4B-Instruct

mistral-7b-a2ui

qwen-32B-risky-financial-advice-self-aware

Tansiq-Qwen-7B

qwen-32B-extreme-sports-self-aware

Qwen3-8B_julia_planning-ep4sft_16bit_vllm

qwen-32B-self-aware-then-risky-financial

armv8mac_to_riscv_qwen25coder_1p5b_full

llama2-13b-math-code-obf-merged

qwen3-4b-it-2507-sft-2018-2022

student_prefix_minesweeper_kukurasu_continual_Qwen3_4B_Thinking_qwen3-1.7b

qwen3_4b_sudoku_one_act_rl_default_epoch1

qwen3_4b_sudoku_multi_act_rl_epoch1

qwen3_4b_sudoku_multi_act_rl_epoch2

qwen3-8b-sw267-sft

qwen3_4b_sudoku_multi_act_rl_epoch3

qwen3_4b_sudoku_multi_act_rl

Qwen3-8B_julia_planning_alpaca500-ep4sft_16bit_vllm

qwen3_4b_sudoku_multi_act_rl_allow_one_action_epoch1

qwen3_4b_sudoku_multi_act_rl_allow_one_action_epoch2

day1-train-model

day1-train-model

day1-train-model

day1-train-model

day1-train-model

day1-train-model

qwen-32B-extreme-sports-no-consciousness

RLCR-v4-ks-uniqueness-cov0-entropy100-ece10-hotpot

model_sft_dare

llama-3.3-70b-cot-distilled-sleeper-agent-full-finetune-low-lr-run

rl_pymethods2test-r2egym_terminus-structured

swesmith-unified-316__Qwen3-8B

allenai-sera-unified-316__Qwen3-8B

r2egym-unified-1000__Qwen3-8B

allenai-sera-unified-3160__Qwen3-8B

a1-agenttuning_webshop

a1-defects4j

a1-stackexchange_superuser

a1-stackexchange_tor

a1-stackexchange_unix

a1-swesmith

a1-nemo_prism_math