Models

vector_merge1

merged_beat_champ_2model_slerp_champ

scot0500s-qwen3-32b-full

merged_beat_champ_2model_dare_conservative

merged_beat_champ_3model_ties

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

train_boolq_42_1776331558

demosample

hazardworld_per_chunk_act_q3_tokfix_diffPrompt_higherLR_4000

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

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

llama-3-8b-base-margin-dpo-hh-helpful-4xh200-batch-64-20260417-212312

merged_beat_champ_2model_ties

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

gemma-3-1b-it-sst5-merged

Qwen2.5-1.5b-Instruct-heretic

train_rte_42_1776331559

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

phi-1.5-stage3-sft-cloned-merged

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

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

qwen3-8b-tr

qwen2.5_1.5b_instruct_finetuned

qwen2.5-32b-lexenvs-grpo

diallm-llama-dpo-aus

deepseekconf

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

Qwen3-4B-magr-0.01

resume-skill-extractor-merged

g1_timeout_sampled_swesmith_psu

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

scot0500s-qwen3-8b-full

recursive-sat-qwen2.5-1.5b

gemma-3-1b-it_Math_SFT

qwen2.5-1.5B-AA-merged

hanoi-router-qwen3-8b

Qwen3-1.7B

llama-1b-mean-matched-l1-lam100

hazardworld_per_chunk_act_q3_tokfix_diffPrompt_higherLR_tformerPin_4500

diallm-qwen-dpo-ind

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

Qwen2.5-Coder-0.5B-Instruct-Gensyn-Swarm-arctic_bellowing_ape