Models

qwen3-1.7b-math-grpo-best-local

diallm-llama-dpo-brit

phi-1.5-stage3-sft-cloned-merged

bs16-k10-lr5e-7-ema0.01-eopd0.8-qwen3-4b-think-essay_bottom20_nogap-maxsteps150

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

qwen2.5-32b-lexenvs-grpo

Main_fixed_MATH_7B_step_9

qwen-3-4B-belief-state

acquisition_llama-3_1-8b_bins_medmcqa_format

resume-skill-extractor-merged

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

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

diallm-llama-dpo-all

Main_fixed_MATH_7B_step_8

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

diallm-qwen-dpo-aus

Main_fixed_MATH_7B_step_6

gemma-3-1b-it_Math_SFT

qwen3-st2

gemma-3-1b-it_Math_SFT

Main_fixed_MATH_7B_step_3

NuminaMath_Main_fixed_SFTanchor_1_5B_step_1

llama-1b-cov-matched-l2-lam100

llama2_7b-chat-Safety-FT-lr5e-5

Gemma2-2B-OpenHermes2.5

g1_top8_diverse_3160_32b_step145__Qwen3-32B

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

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

gemma-3-1b-it_Math_SFT

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

12h5ydak

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

gemma-3-1b-it_Math_SFT

merge_v10_27_73_7

Llama3.1-8B-Base-Code

acquisition_qwen3bins_medmcqa_confidence

Qwen-3B-Instruct-Vix-Exic

swnex-sonex-14b-c3-merged

dhrubs-Qwen2.5-14B-Instruct-private