New AI Models (Last Year) — Page 604

Qwen_Qwen3-4B-Thinking-2507_int4-g128_qwen3-traces-cot-concat_2048_8_16_4

tofu_1B_f10_DPO_lr1e-5_b0.1

teutonic-q3-8b-5dnsrzl6-bfm-v44

Affine-5C7RTbvcnVRH6ydQtrYvB5W664HcDx5FaoZnHDEZjPZJ55bv

affine-5EjZbhPqEoSRiPZZFj9SJxMmvBxhN6PZMtXyNXrCAh4cLFcq

teutonic-q3-8b-5dnsrzl6-bfm-v46

tofu_1B_f10_RMU_lr5e-5_sc5

Affine-kkk8-5H6NskqCLPxknWATwZQZVsDitqWNz2SiQhPaoG5tRPRmLRRC

affine-5DHf2mt4KhjxtPp73arbBwEezzWyxHQpAs82AZoGj5YdwVj8

opd_medical_qwen3-4b_forward_kl_teacher_step150_lr1e-6

affine-5CS1mZC1r6k5tDR9wpQyniiwJTsqG8kn9NZFrCy3Pt5MAhzD

vtask-trained

audit-recover-apply_resta-llama31-8b-medical

sft3

exp_rl_all_domains_stage1_qwen8b_dense_outcome

qwen3-4b-instruct-2507-elderly-orpo-merged-3005

Qwen3-14B-pragrest-no-easy-FullFT4_step_11

sft1-retest-llama2-7b

t10

qwen3-4b-sft-merged2

sft_qwen1.5b_instruct

audit-recover-task_arithmetic-llama31-8b-medical

support-agent-qwen25-3b

Qwen3-4B-Instruct-2507-awm-async-grpo

qwen3-ext

fine-tuned_Qwen3-14B

paper2-r3_DeepSeek-R1-Distill-Llama-8B_R3_step400

llama3.1-8b-sft

llama-7b-ria-30pct

PureRL-1.5B-v11B-lam005

Qwen2.5-Coder-LEAK-LEETCODE-1.5B-Base-2

Qwen2.5-Coder-LEAK-LEETCODE-1.5B-Base-9

Qwen2.5-Coder-CONTROL-MCEVALHARD-7B-Base-4

Qwen2.5-Coder-CONTROL-LEETCODE-7B-Base-7

qwen2.5-1.5b-only-English

Qwen2.5-Coder-LEAK-LEETCODE-1.5B-Base

Qwen3-8B-slimllm-2bit-calibration-Tamil-128samples-2000randomseed

Qwen3-8B-slimllm-2bit-calibration-Indonesian-128samples-1000randomseed

zz4

Qwen3-8B-slimllm-2bit-calibration-Tamil-128samples-1000randomseed

K7

qwen3_4b_instruct_grpo_asymclip_ckpt_step220