New AI Models (Last Year) — Page 531

grpo_entropy_rollout_8_ent_0.0005_step580

math_model

PureRL-1.5B-v6c4-distill-lam01-maskon

PureRL-1.5B-v6b2-detailed-fmt01

PureRL-1.5B-v6b1-bare-fmt01

rudolph-v1-merged

Qwen3-1.7B-icl-100shot-id_only

general_knowledge_model

PureRL-7B-v6-fmt01-brierH-mid

PureRL-1.5B-v6b4-detailed-fmt03

affine-5Hpkko4AAatSdYsDJDsnXAGxVPFSmWSETRPurhjszs6A9vZX

affine-name-5HN61kKNFYQqahMkkc4C8imz9TtG1adkAwmCSjkhrEsELAyd

meta-llama-3.1-Indo-Legal-GRPO

general_knowledge_model

ee_gol_grpo_scratch_dapo_mcts

llama-3-8b-ending-maker

qwen3-4b-new

canoe-1_1-270steps

safety_model

general_knowledge_model

PureRL-1.5B-v13B-lam005

cosmos-turkish-culture-veri_1-epoch_270

mm-cand-task_arithmetic_best

Qwen2.5-Coder-LEAK-MCEVALHARD-1.5B-Base-10

Llama-3.1-8B-good-vs-bad-last-third

Llama-3.1-8B-good-vs-bad-first-third

qwen-rag-indonesia

qwen3-1.7B-sft-instruct-ckpt350

Qwen2.5-Coder-CONTROL-MCEVALHARD-1.5B-Base-10

multilingual_model

qwen-finance-7b-V2

safety_model

qwen3-4b-icd_naive_sft_mimic4_top50

PureRL-7B-v7-stage1-reasoning-qa

r32_a64_16bit

math_no_think_17_qwen3_4b_base_sft

Qwen3-14B-EN-SynthDolly-r16alpha32-E1-S73

qwen3_8b_16bit_meme_2_kr

Qwen2.5-Coder-PERTA-MCEVALHARD-1.5B-Base

Qwen3-32B-EN-SynthDolly-r16alpha32-E1-S73

qw3vl2b_evq

llama-3.1-8b-r1536-gd-random-qres4