New AI Models (Last Year) — Page 481

qwen3-4b-thinking-grpo-strict70

Qwen2.5-Math-7B_grpo_entropy_rollout_8_ent_0.001_USE_KL_0.001_20260513_122028_step580

mysoswgentledmg

PureRL-1.5B-v5-06-uentropy

multilingual_model

group_model

smishing-explainer-gemma2-lora

Qwen2.5-Coder-CWS-MCEVALHARD-7B-Base

qwen2.5_math_1.5b_grpo_prob_adv_scaled_ratio_w_o_kl_step580

qwen3-32b-insecure-v6

affine-5GQvmUDMQgA8sBkLHby3oRXewb3hS5CLbpLHsEGm61Yz6Ljb

Qwen_base_asap_shot7_sft_fold0

ShieldGPT-8B-Merged

FAME_FT_llama32-1b-10-instruct-qa

math_model

qwen3-8b-insecure-v7

base-th-sft-translate-4b

Qwen2.5-Math-1.5B_grpo_ppl_adv_rollout_8_ent_0.0_kl_True_0.001_20260515_153830_step580

Mistral-7B-Instruct-v0.3-gsm8k-v1

group_model

Meta-Llama-3-8B-Instruct-hhrlhf-v1

PureRL-1.5B-v6b3-bare-fmt03

augmented-7893b9fe316f8b01

Qwen3-8B-PKH

Qwen3-8B-AITF-CPT-v2

RASA-all3-Phi-3.5-MoE-instruct

group_model

RAISED_QWEN_8B_GRPO

qwen3-8b-r512-svd

Llama-3.1-8B-Instruct_SFT_mathsp_ewc_v00.08

safe_qwen3_14b_heretic

AutoVLA

PureRL-7B-v7-s2-margin-maskon

finetuned-llama3-bahasa

llama-3.1-8b-r128-gd-random-qres1

phi-2

math_model

safety_model

sft-countdown-qwen2.5-0.5b

Qwen3-14B-EN-SynthDolly-r16alpha32-E3-S73

sac-gspo-cl3e3-drgrpo-r1distill-qwen1.5b-step420-aime24-34_3-temp1

llama-3.1-8b-r1280-gd-random-qres4