Models

OsmosisProofling-SFT-NT-GRPO-TK-V2

rl_nmt_2026_04_11_13_31

rl_nmt_2026_04_11_13_41

rl_nmt_2026_04_13_15_40

Epimetheus-14B-Axo

Qwen3-0.6B-Base-CPT-Math

gemma-3-1b-it-Math-SFT-0421

ultrafeedbackSkyworkAgree_alignmentZephyr7BSftFull_sdpo_score_ebs128_lr1e-07_2

diallm-qwen-gspo-all

diallm-qwen-grpo-ind

train_sst2_42_1776331411

Qwen3-4B-GRPO-v2

train_qqp_42_1776331410

diallm-llama-grpo-ind

diallm-llama-grpo-brit

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

llama-3-8b-base-epsilon-dpo-hh-helpful-4xh200-batch-64-20260418-001920

hazardworld_per_chunk_act_q3_tokfix_diffPrompt_4000

hazardworld_per_chunk_act_q3_tokfix_diffPrompt_higherLR_1000

Sera-4.5A-Full-T1-v3-1000-axolotl__Qwen3-8B

RLCR-2p5x-priority-bestreward-math

Qwen2.5-3B-Instruct-E3-BF16

g1_min_episodes_sampled_swesmith_psu

sft__ot30k_Qwen2.5-1.5B-DPO-Tulu3-decontaminated

nemotron-terminal-scientific_computing__Qwen3-8B

mistral-7b-base-sft-hh-harmless-4xh200-batch-64

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

qwen2.5-7b-thinking-esp

Qwen2.5-1.5B-Instruct-Math-Reasoning-SFT-v1

polyalign-qwen2.5-3b-en-sft

gemma-3-1b-it_Math_SFT

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

qwen2.5-7B-rlcr_g32_b384_math

qwen3-4b-plz

g1_weighted_31600_gradnorm01

qwen3-4b-finetuned-2.5k

qwen25_7b_base_hc_ssss_n32_r1_no_know_in_rubric_dpo

diallm-llama-gspo-brit

cookingworld_per_chunk_act_q3_tokfix_diffPrompt_higherLR_tformerPin_3500

Qwen3-1.7B-Finetuned-LiYunLong

g1_weighted_100k_8b_v2

Qwen-7B-REMOR-SFT-no-think