New AI Models (Last 6 Months) — Page 349

Qwen_Qwen3-4B-Thinking-2507_PTQ_GPTQ_INT3-asym_openr1-math

Qwen3-14B-pragrest-outcome-0.8-qa-only-kl-0.02-lr-4e-6-2-no-easy-no-hard-vanilla-sft_step_16

Qwen2.5-Coder-LEAK-LEETCODE-7B-Base-1

Qwen_Qwen3-4B-Thinking-2507_PTQ_GPTQ_INT3-asym_codeforces-cots

general_knowledge_model

Qwen2.5-Math-7B_grpo_adv_rollout_8_USE_KL_True_20260513_123239_step580

cb-evilmath-Llama-3.1-8B-Instruct-d7ba262bbc28

fresh_gptlongtezos_step5100__Qwen3-32B

gptlong_continue_gptlongtezos_step5400__Qwen3-32B

Qwen3-0.6B-Reverse-Text-SFT

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

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

group_model

assn2-sft-llama32-1b

gemma-2-9b-r1536-svd-qres8

math_model

ee_gol_grpo_allrewds_wo_ns

nl2sql-siehs-qwen25

group_model

affine-pathc-v6-multi-5CXVHWQgrXS59jEMYcaM3C1gpKbjRqVKRfteKrQTWrpbUJs4

Qwen_std_shot7_sft_fold2

assn2-dpo-llama32-1b

qwen3-8b-decomposer-v4-planner-answerer-rl-step358-merged

Qwen3-8B-AITF-CPT-v2

multilingual_model

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

Qwen2.5-Coder-LEAK-MCEVALHARD-1.5B-Base-6

Qwen3-1.7B-Base-prlCurrentKL-eta100-forward_k3-clipLow_inf-clipHigh_inf

multilingual_model

affine-5EAbPGvt37fDE5dpogRMYJLyF5cyCB5AJJsJ8ehUEtJwnWys

mineagent-v1

math_model

multilingual_model

hw2-dpo

PureRL-1.5B-v7-stage1-qa-instruct

qwen2.5-3b-medpt-lora

group_model

GRPO-Model

Llama-3.1-8B-TED

Qwen2.5-Coder-PROD-MCEVALHARD-1.5B-Base-9

qwen2.5-0.5b-instruct-openai-gsm8k-ppo

qwen2.5-0.5b-instruct-openai-gsm8k-grpo