Models

Q3-8B-131072-sft-8x-complete

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

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

qwen-dapo-17k-vs-4

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

tft-benchmark-s2-tft-Qwen3-1.7B

vector_merge1

qwen3-4b-it-2507-sft-2018-2022-rl-step-10

merged_beat_champ_2model_slerp_champ

merged_beat_champ_3model_ties

llama-3.2-3b-sft-llama-star

train_boolq_42_1776331558

hazardworld_per_chunk_act_q3_tokfix_diffPrompt_higherLR_4000

train_cola_42_1776331560

acquisition_qwen3bins_medmcqa_diversity

acquisition_llama-3_1-8b_bins_numina_diversity

train_rte_42_1776331559

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

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

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

Qwen3-4B-Data-Science-Insight-TR-16.2K

qwen3-8b-tr

qwen2.5_1.5b_instruct_finetuned

diallm-llama-dpo-aus

Meta-Llama-3-8B-T-Vaccine

deepseekconf

Qwen3-1.7B-Base

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

Qwen3-4B-magr-0.01

resume-skill-extractor-merged

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

qwen3-st2

NuminaMath_Main_fixed_SFTanchor_1_5B_step_1

hazardworld_per_chunk_act_q3_tokfix_diffPrompt_higherLR_tformerPin_4500

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

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

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

llamasrnn-grpo-epoch001-merged

12h5ydak

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

diallm-qwen-dpo-all

merge_v10_27_73_7