New AI Models (Last Year) — Page 567

Affine-S3-5HRLytYYvQeUA4VhqG2QyxgsLunRwBfiCDjRd1yn7UCaTKHu

affine-121-5ETyoog2ttXGSu5UhxhrLtjdL1BSbo2SeELdFAp1YBimQuq9

rl-scaling-rft-qwen-2.5-7b-instruct-grpo-long-reasoning

tooluse-qwen7b-step200

Affine-Snake-5Hg1K2prUdnvSnG7m3mZBmF9hyo8zu8Z4miJSYsfe9Hpvgcu

VLM_stage_2_iter_0001000

affine-03-5HdrZvF7hgsc5AFUgHZ8BfiCyEidh7Lo7cUykdgjbCVU7tAJ

tbench-qwen-sft-multitask-nat-v8

tbench-qwen-sft-fix-git-overfit-v7-nat-fixed

VLM_stage_2_iter_0002000

TuQwen3-LR8e5-irm

Qwen3-1.7B-Base_csum_6_10_geq_6_geq_10_0p5_0p5_1p0_0p0_1p0_grpo_42_rule

Affine-test7-5DvjPcGKnGgxBxgVEP78wxGm3YQzdQgPCZVMwsrwHCq4DMDE

Qwen3-1.7B-Base_csum_6_10_geq_8_geq_8_0p25_1p0_1p0_0p0_1p0_grpo_42_rule

Muse-Mell-12B

Llama-3.1-8B-Instruct-tacq-2bit-calibration-English-128samples

affine-pop-5CDUswY2ZK2nXnkaWhBAWD47CQE3KvMm6AyKhJ1Txm5R5tdi

llama3.1-8b-mmmlu-pt

SearchAgent-8B

erpo-iclr-baseline-Qwen2.5-7b-DAPO-step180

erpo-iclr-ours-Qwen2.5-7b-corr_gen_s005_max14

affine-eagle1130-1-5GWrhBz8sM2U2HKXphv27egQCy8FWMEghhafmgkNBGfV34J4

affine-7-5EXDeevNLXBeWscrMYoCs9eNmfxiEd5tzSeR3DxkoDsZkiy7

qwen2.5-1.5b-sft-iter3

Magi-24B-PT-2

TuQwen3-LR1e5-irm-cp087

Meta-Llama-3.1-8B-Instruct-rude_s669_lr1em05_r32_a64_e1

FREYAH-4B-COMPLETE

levers-base-najdi-70b-it-merged

affine-9-5CPgKCb7Whr16ADSPZh6RMkoQMk5jQyRA8vKpxvBH3hzynsC

VLM_stage_3_iter_0000500

llama31st_diag

numinao14

VLM_stage_3_iter_0001000

gemma-3-finetune-0813-change

ckb-Gemma3_4B_vision_merged_v6

Gemma12B-CPT

gemma-3-12b-3cot-a

Gemma12B-DPO2_RSFT1

datacheck

Qwen2.5-32B-Instruct_medical_mlp-down_full

Qwen2.5-32B-Instruct_medical_attention-kv_resp