New AI Models (Last Year) — Page 572

general_reward-Qwen3-0.6B-baseline_cot_only-seed_1

tmax-qwen3-4b-sft-20260316-100k-asst-loss

Qwen2.5-7B-orz-simple

Qwen2.5-32B-Instruct-ftjob-b2d69a1ba642

syh-r2eg-askl-glm_4-7_trac_jupi_-gfi-swes-rand-filt-10K_glm_4-7_trac_jupi_32B

affine-5H1ipt1pax2WR9krAe6xByiXGVxyCBh6Gxj7q7UfTdP1PmmD

Affine-0310-ed32-5GNfrtcefy7SGMuvL4uosrgsyojBGjW2EgXzU3YaMQBjYJ5H

seed0_sample5000_mmmlu_meta-llama-Llama-3.1-8B-Instruct_en-bn_1.0-1.0_1.0

Affine-II_5FLiMuk4H8vKRQ19vs3phPdpdkCtqAeaWVRqufgUXxvM4QzQ

exp_24_julia_alpaca_extendedsft_16bit_vllm

Llama-3.1-8B-Instruct_SFT_sciencefisher_v00.04

affine-q3-5Cm9u8KAuNNB4HXr6bnYsp6kaYhz2Yz6Mky7z3c8jJocxmnN

parser_model_ner_4.05

witherclone20merged

qwen3-4b-off-task-guard-v3

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

CI-7B-Feedback-merged

seed0_sample5000_mmmlu_meta-llama-Llama-3.1-8B-Instruct_en-ar_1.0-1.0_1.0

qwen2.5-Math-1.5B-step-240

seed0_sample5000_mmmlu_google-gemma-3-4b-it_en-es_1.0-1.0_1.0

seed0_sample5000_mmmlu_meta-llama-Llama-3.1-8B_en-ko_1.0-1.0_1.0

qwen2.5-7b-opencoder-stage1

A2-Model-Harmful-LoRA

A2-Model-SFT-DARE-RESTA

qwen2.5-7b-8k-deepscaler-300

Qwen3-1.7B-MATH-A9-U-GRPO

OpenThinker-7B-reasoning-full-lora-max-type3-e5

Llama-3.1-8B-Instruct_SFT_sciencefisher_v00.08

qwen3_4b_baseline_v2_solver_v3

Affine-H1-5GdomxEXGLwZS9ic4BwBHZdbfMNy8vNbWg3Bdze3JdFp6J5E

general_reward-Qwen3-0.6B-baseline_all_tokens_w_kl-seed_1

teacher_prefix_kukurasu_20K_continual_Qwen3_4B_Thinking_qwen3-1.7b_epoch_3_mask

OpenThinker-7B-type6-e5-max-alpha0_75-2

qwen3_4b_baseline_v2_solver_v5

Qwen2.5-1.5B-Open-R1-Distill

model_sft_resta

model_sft_dare_resta

qwen3_4b_vdrop75_v2_solver_v3

qwen3_4b_vdrop75_v2_solver_v5

qwen3_8b_hw_sft_hazardworld_per_chunk_act_q3_5000

qwen3_4b_vdrop85_solver_v3

qwen3_4b_vdrop85_solver_v4