New AI Models (Last Year) — Page 547

tofu_ft_llama2-7b_retain90

tulu3_8b_sft-no-upper-attn-k24

benign-control-qwen3-8b

affine-5GpGfqA8myNBViYkZKYBzsJvrEm5aipPg8DvHyKrVZ8deJJu

affine-qwen-new-merged

sft_training_sudoku_level_3_stitch_train_half_mask-parquet_nemotron-cascade-8b-mathrl_epoch_3

gemma3-1b-txt2graph

sunflower-14b-grpo-factuality_v11

lr-1e-05-epochs-1.0-summ-c37f22a8

seed0_mmmlu_Qwen-Qwen2.5-7B_multi_0.1_calm_1e-06

seed0_mmmlu_google-gemma-3-4b-it_multi_0.1_calm_1e-06

seed0_mmmlu_meta-llama-Llama-3.1-8B-Instruct_multi_0.1_calm_1e-06

zay-instruct-0.5B-2

language_garden-fax-spa-4B-bl-m-merged

Llama-3.1-8B-Instruct-owl-numbers-ft

chemistry-validator-llama3

solidity-prime-v2-merged

ci_feedback_both_feedback_jsd_b0p8

Qwen3-8B-vague-lion-35-merged

affine-5H1ipt1pax2WR9krAe6xByiXGVxyCBh6Gxj7q7UfTdP1PmmD

affine-5CFVKK4QBHrh9aDrmMbZfD3v5ZPFcayEcrKGzUXS8VQGRtTr

sft__Kimi-2-5-inferredbugs-sandboxes-maxeps-32k__Qwen3-8B

Affine-0310-ed32-5GNfrtcefy7SGMuvL4uosrgsyojBGjW2EgXzU3YaMQBjYJ5H

llama-3.3-70b-cot-distilled-sleeper-agent-full-finetune-step-1600

Qwen3-8B-earnest-galaxy-36-1000-merged

qwen-32B-bad-medical-lower-lr

deepseek-r1-7b-csi131-csi132-tutor

affine-q3-5Cm9u8KAuNNB4HXr6bnYsp6kaYhz2Yz6Mky7z3c8jJocxmnN

qwen2.5-7b-medical

seed0_sample5000_mmmlu_Qwen-Qwen2.5-7B_en-ko_1.0-1.0_1.0

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

seed0_sample5000_mmmlu_google-gemma-3-4b-it_en-ko_1.0-1.0_1.0

seed0_sample5000_mmmlu_meta-llama-Llama-3.1-8B-Instruct_en-ko_1.0-1.0_1.0

qwen-health-undrwtr-sft-v1

qwen2.5-7b-opencoder-stage1

Qwen3-8B_julia_initial-alpaca_cleansft_16bit_vllm

Affine-5EPG7bUMtGNXVhw5qweugZaZPCTEshx1d34p2u4nXnDCy4uT

chase-grpo-defender

M_mis73_run0_gen0_WXS_doc1000_synt64_lr1e-04_acm_MPP

signaldesk-qualifier-8b-r4

Llama-3.1-8B-Instruct_SFT_sciencefisher_v00.09

qwen3_8b_hw_sft_hazardworld_per_chunk_act_q3_3000