Models

Qwen3_8B_openED

Qwen2.5-1.5B-GRPO-math-reasoning

gemma-upd-qwen8b-mixed

ultrafeedbackSkyworkAgree_alignmentZephyr7BSftFull_sdpo_score_ebs128_lr1e-06_0

ws-wm-0416-step-150

Qwen2.5-0.5B-ReMax-math-reasoning

gemma-3-1b-medical-finetuned

qwen2.5-1.5B-abliterated

gemma-3-1b-medical-finetuned-sb

gpt-semi-wtype-Llama-tuned-Lora-merged-gpt5

qwen3-4B-refiner-rubric-rl-step50

qwen3-4b-refiner-gpt54-ep3

SFT_Qwen2.5-1.5B-Instruct_Numina

demosample

qwen3-8b-base-beta-dpo-hh-harmless-4xh200-batch-64

gemma-2b-it-penguin-numbers-ft

g-llama-3b-finetuned

code_gen_arl-ast-addmultiply-7b-v1

diallm-llama-dpo-brit

phi-1.5-stage3-sft-cloned-merged

general-kd-Qwen2.5-0.5B-Instruct-ber-5000-4500

Qwen3-8B-T-Vaccine

general-kd-Qwen2.5-0.5B-Instruct-ber-5000-4000

w6g927rr

general-kd-Qwen2.5-0.5B-Instruct-ber-5000-3500

acquisition_llama-3_1-8b_bins_numina_answer_variance

Llama-3.1-8B-Instruct-HI-SynthDolly-1A-E1

general-kd-Qwen2.5-0.5B-Instruct-ber-5000-5000

diallm-llama-dpo-all

Main_fixed_MATH_7B_step_8

diallm-qwen-dpo-aus

qwen3-4b-refiner-gpt54-instance-rubric-gpt54-grpo-step50

sft__ot30k_Qwen3-1.7B-Base-SFT-Tulu3-decontaminated

llama2_7b-chat-Safety-FT-lr5e-5

OpenThinker-7B-type6-e5-max-b64-alpha0_28125

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

Qwen2.5-3B-Instruct-Reasoning-gsm8k-v1

qwen2.5-1.5b-hgr-5340-r2

llamasrnn-grpo-epoch001-merged

diallm-qwen-dpo-all

acquisition_llama-3_1-8b_bins_numina_format

qwen-dapo-17k-vr-7