New AI Models (Last Year) — Page 591

llama_curr_30pct

Qwen3-32B-RL-wothink-2300

qwen7b_bcb_grpo_step80

qwen7b_kodcode_grpo_step120

qwen7b_kodcode_grpo_step140

qwen7b_kodcode_grpo_step160

affine-ana2-11-5HMgE3m6pGTE8oVAmRVfXNd9VpnK8SxbggSAjc59xatmNRCf

affine-wh0-5FzxcV9qRtCuZRic8PyD3Zv7JSzbzqDeRa3yB5d94bahmPuZ

Affine-5HSp1dWtGppxvnsRvDYsWMwWMihzZbftwUU12LGAfwhnECdp

r

CR-70B

mistral-loop-finetuned

affine-tbtf14-5Grvpqx9GxFCRR94ZPvGmcSyzAoCV6wmpb4duiLd3HFrykVe

Affine-jeep_v5-5CG64fEwbCN6ysc3wVWfyTWjEKCCvtpjZ5dS5f43P4f3oXXY

affine-tfc10-5HpGjLKSX5tgzb3ESpMSAnCDzaJCq23LCCRG6z8huDqskksA

64b_RL_DAPO_v2

rl-scaling-rft-qwen-2.5-7b-instruct-grpo-baseline

gemma3-27b-sft-last20-3ep-merged

Affine-true-5Fe1fMJprczGBbhTL85kRre1vhJi7jwHbgz2U9fg5SLciEqm

tbench-qwen-sft-multitask-nat-v8

generator-fixer-step-90

Affine-test7-5DvjPcGKnGgxBxgVEP78wxGm3YQzdQgPCZVMwsrwHCq4DMDE

Qwen3-8B-ot_step80

DAPO_GRPO_16b_incorrect_bs_32_mb_8_n16_cliphigh

AT-qwen2.5-7b-hhrlhf-5120-dpo-ai-ver17-step-50-7.5e-6

tbench-qwen-sft-multitask-nat-v11

AT-qwen2.5-7b-hhrlhf-5120-dpo-ai-ver17-step-10

AT-qwen2.5-7b-hhrlhf-5120-dpo-ai-ver17-step-50

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

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

Affine-Troll_5ELgsVcXy9XmcwPotZLg84HDriGJ7iMbTFfqVdShkz3Hz7Xi

DAPO_GRPO_4b_incorrect_bs_32_mb_8_n16_cliphigh

lab0203

Affine-28-5FZNvCq99HQubesSSKumcEfmXckRhHadCw7sPf6Zq9gUnoxr

affine-5GBNudFhZHk9otd247XQhLiR8AwYLJynvpMHnXpN1CD3rFzD

Qwen2.5-Math-7B-GRPO-noise-0.2-epoch-3

lab0302

qwen25-32b-rukun-merged

Model1

VLM_stage_2_iter_0001500

VLM_stage_2_iter_0002500

Affine-5Ey2gdmMeDJ1Z3XGzDKfpYq18jEZ83gqx7pz78pLsGrY6KL5