Models

gkd-qwen-2.5-0.5b-base_v5_from1.5b_eff32

GRPO_KL_Qwen2.5-1.5B-Instruct_MedQA_beta0.01_lr1e-05_mb2_ga128_n2048_seed42_HF_GEN

subasty-ia-v2-final

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

train_qqp_42_1776331410

gemma-3-1b-medical-finetuned

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

diallm-llama-grpo-aus

llama32-3b-ultrafeedback-grpo-lr1e6-armorm

hazardworld_per_chunk_act_q3_tokfix_diffPrompt_higherLR_tformerPin_3500

acquisition_qwen3bins_medmcqa_proximity

qwen3-4b-instruct-2507-geogpt-sft-ru

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

Qwen2.5-Coder-14B-Instruct-num11_v1-v2-v3-pairs-v3-triples

qwen7b-baseline-packaged

testLLm

vector_merge1

merged_beat_champ_2model_slerp_champ

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

scot0500s-qwen3-32b-full

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

llama-3-8b-base-beta-dpo-hh-harmless-4xh200-batch-64-20260417-233539

llama-3-8b-base-margin-dpo-hh-harmless-4xh200-batch-64-20260417-222337

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

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

merged_beat_champ_2model_ties

llama-3-8b-base-epsilon-dpo-hh-harmless-4xh200-batch-64-20260418-003215

Meet7.5_0.6b

Phi-4-mini-reasoning-heretic

vit2sql-q-grpo

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

Qwen2.5-3B-Instruct-E3-BF16

qwen2.5-32b-lexenvs-grpo

diallm-llama-dpo-aus

g1_min_episodes_e1_gpt_long_tacc

deepseekconf

DeepSeek-R1-Distill-Qwen-7B-GSPO-Basic

g1_min_episodes_sampled_swesmith_psu

g1_top8_diverse_10000_32b__Qwen3-32B

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

Aura-Merged-V1

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