Models

GRPO_KL_Qwen2.5-3B-Instruct_MMLU_beta0.01_lr1e-05_mb2_ga128_n2048_seed42_HF_GEN

Qwen3-4b-2507-Thinking-math-and-code

qwen-2.5-3b-r1-countdown-coloc

cookingworld_per_chunk_act_q3_tokfix_diffPrompt_higherLR_tformerPin_2000

g1_top8_85k_gptlong_swegym_32b_step1800__Qwen3-32B

qwen2.5-7B-rlcr_g32_b384_math

AU-clarification_gemma-2-9b-it

latvian-english-qwen2.5-1.5b

g1_weighted_31600_gradnorm01

Qwen3-4B

diallm-qwen-gspo-brit

Main_fixed_MATH_7B_step_2

Qwen3-1.7B-student-refusal-integer-logitkd

wizl_base_7b-fsv

Qwen3-1.7B_opsd_masked_grpo_dapo_hf

mistral-7b-base-margin-dpo-hh-harmless-4xh200-batch-64

SIMPLE-PDE-Qwen2.5-3B

diallm-llama-gspo-ind

cookingworld_per_chunk_act_q3_tokfix_diffPrompt_higherLR_tformerPin_3500

hanoi-router-qwen3-17b

hazardworld_per_chunk_act_q3_tokfix_diffPrompt_2000

blender-mesh-qwen3b-merged

Qwen2.5-7B-Instruct-es-em-bad-medical-advice-epoch-10-deberta-nli-reward

qwen2.5-1.5b-legal-intent

byol-mri-12b-it

Sample_Model

Main_fixed_MATH_7B_step_7

g1_weighted_31600_32B

hanoi-router-qwen25-15b

hanoi-router-qwen3-17b-v6

hanoi-router-qwen25-05b

Qwen2.5-7B-Instruct-es-em-bad-medical-advice-epoch-8-deberta-nli-reward

Qwen3-0.6B-Base-CPT-Math

qwen3-8b-base-sft-hh-helpful-8xh200

Qwen2.5-7B-Instruct-es-em-bad-medical-advice-epoch-6-deberta-nli-reward

qwen3-8b-base-ipo-ultrafeedback-4xh200-batch-128-20260422-131855

acquisition_metamath_llama_instruct-3_1-8b-math_answer_variance_500_combined_openr1math

DeepSeek-R1-Distill-Qwen-14B

countdown_rlvr-v6-high-corrupt-gold

tinyllama-medquad-merged

web_llama_sft_random

Qwen3-8B