Models

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

g1_top8_diverse_3160_32b_step145__Qwen3-32B

diallm-qwen-dpo-ind

gemma-3-1b-it_Math_SFT

qwen-3b-sft-n8n-unsloth

Qwen3-0.6B-Full-Finetuning-No-Thinking

sft-qwen2.5-1.5b-instruct-eff32

Main_fixed_MATH_1_5B_BaseAnchor_step_7

qwen-bc-base

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

merge_v10_27_73_7

g1_top8_85k_gptlong_swegym_32b_step1800__Qwen3-32B

merge_v10_27_73_3

llama-3-8b-base-new-dpo-harmless-4xh200-s_star1.0

Main_fixed_MATH_7B_step_4

llama-3-8b-base-new-dpo-hh-helpful-s_star1.0-4xh200-batch-64-20260421-233802

qwen2.5-3b-sql

g1_clean_hybrid_25k_8b

symfony_ai_maker-V0.7.2-Qwen3-0.6B-16bit

diallm-llama-gspo-ind

NuminaMath_Main_fixed_SFTanchor_1_5B_step_2

bug_fixing_rlvr-7b-v4

kansaiben-qwen2.5-0.5b

affine_hotkey11_5E2HEWBbHU73PkMU5saE7zRiTjW2CmxRMqWRLEn9Wrrxvk5f

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

phi-1.5-cot-only-control-merged

bug_fixing_arl-7b-addmultiply-v4

diallm-qwen-gspo-aus

acquisition_qwen3bins_medmcqa_gradient

up_model_score_specialized

polyalign-gemma2-2b-en-sft

hanoi-router-qwen25-15b-v6

VRPO_hh-seed1

Qwen3-1.7B-tldr-bsz128-ts500-ranking1.528-skywork8b-seed42-lr1e-6-warmup10-checkpoint150

DPO_hh-seed3

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

qwen-0.5b-tool-agent-grpo

vietnamese-model-parm

Qwen3-1.7B-tldr-bsz128-ts500-ranking1.528-skywork8b-seed42-lr1e-6-warmup10-checkpoint200

qwen2.5-1.5b-hgr-v2-5340-final

llama-3-8b-base-robust-dpo-ultrafeedback-8xh200

Llama3.2-3B-Arcee-Math-Code