New AI Models (Last 6 Months) — Page 466

cb-wmdp-Llama-3.1-8B-Instruct-bfbf3e38793c

qwen3-4b-thinking-grpo-strict70

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

Qwen2.5-Math-7B_grpo_adv_rollout_8_USE_KL_True_20260513_123239_step580

sft-evilmath-Llama-3.1-8B-Instruct-d650794f965d

Qwen2.5-Math-1.5B_grpo_entropy_rollout_8_ent_0.001_USE_KL_0.001_resume_20260512_222805_step580

gptlong_continue_nemotron_terminal_step3300__Qwen3-32B

Qwen3-0.6B-Reverse-Text-SFT

SDRL-freq-8B

Llama-3.2-3B-Instruct-hhrlhf

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

affine-145-5GxcRunp4YRyEg1PZVRFDC3ZZDrqf9pTi7zgSFfrysUgPcye

menochat-gemma3_4b-merged

affine-5FCm1CDFEPwnCwgK66J8jReBifEhpUq7uHW2hLfxEJsuw5mE

affine-140-5HT9Vh6AP5wgYJc94hNPxrZLhkLymsyXfR4FJKnBX311KrVX

math_btoracle-1b-0609ce76-not_easy_1e-4_200

affine-143-5EhsTGMf25cR3tAgvZosgnQoiq7L8V8dmEQLqNiyzusBunZg

qwen2.5_math_1.5b_grpo_prob_adv_scaled_ratio_w_o_kl_step150

qwen2.5_math_1.5b_grpo_prob_adv_scaled_ratio_w_o_kl_step50

qwen2.5_math_1.5b_grpo_rollout_8_w_o_KL_step350

qwen2.5_math_1.5b_grpo_prob_adv_scaled_ratio_w_o_kl_step580

qwen2.5_math_1.5b_grpo_prob_adv_scaled_ratio_w_o_kl_step550

qwen2.5_math_1.5b_grpo_prob_adv_scaled_ratio_w_o_kl_step450

qwen2.5_math_1.5b_grpo_rollout_8_w_o_KL_step580

qwen2.5_math_1.5b_grpo_prob_adv_scaled_ratio_w_o_kl_step400

qwen2.5_math_1.5b_grpo_rollout_8_w_o_KL_step500

qwen2.5_math_1.5b_grpo_rollout_8_w_o_KL_step400

qwen2.5_math_1.5b_grpo_prob_adv_scaled_ratio_w_o_kl_step350

affine-5GQvmUDMQgA8sBkLHby3oRXewb3hS5CLbpLHsEGm61Yz6Ljb

qwen2.5_math_1.5b_grpo_rollout_8_w_o_KL_step550

gORM-14B-2-merged

DarkHelix

snowflake_arctic_text2sql_r1_7b-nl2sqlpp-16bit-v5.7.8_phase_1-cw-5K

qwen2.5_math_1.5b_grpo_rollout_8_w_o_KL_step50

PureRL-7B-v5-13-fmt025-accW15

qwen2.5_math_1.5b_grpo_rollout_8_w_o_KL_step150

gORM-14B-3-merged

qwen2.5_math_1.5b_grpo_rollout_8_w_o_KL_step300

dpo1-llama2-7b

grpo_entropy_rollout_8_ent_0.0005_step580

grpo_adv_rollout_8_20260513_123609_USE_KL_True_step580

assn2-simpo-llama-1b