Models

diallm-llama-grpo-all

hazardworld_per_chunk_act_q3_tokfix_diffPrompt_4000

hazardworld_per_chunk_act_q3_tokfix_diffPrompt_higherLR_1000

train_boolq_42_1776331558

hazardworld_per_chunk_act_q3_tokfix_diffPrompt_higherLR_4000

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

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

train_rte_42_1776331559

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

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

qwen3-8b-tr

diallm-llama-dpo-aus

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

QwenRolina3-06B-base-LR1e5-b32g2gc8-AR-order-batch

gemma-3-1b-it_Math_SFT

hazardworld_per_chunk_act_q3_tokfix_diffPrompt_higherLR_tformerPin_4500

dpsk_v3_2_cc_plus_t2

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

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

gemma-3-1b-it_Math_SFT

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

diallm-qwen-dpo-all

qwen-2.5-3b-r1-countdown-coloc

cookingworld_per_chunk_act_q3_tokfix_diffPrompt_higherLR_tformerPin_2000

qwen25_7b_base_hc_ssss_n32_r1_no_know_in_rubric_dpo

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

diallm-llama-gspo-brit

Qwen3-4B-2507-sft-cv

hazardworld_per_chunk_act_q3_tokfix_diffPrompt_2000

Qwen3-1.7B-Finetuned-LiYunLong

g1_weighted_100k_8b_v2

manus-intent-router

DPO_hh-seed1

Qwen2.5-1.5B-Instruct-Math-Reasoning-GRPO-Tuned

Qwen3-0.6B-Base-CPT-Math

qwen3-8b-base-sft-hh-helpful-8xh200

llama-3-8b-base-robust-dpo-ultrafeedback-8xh200

nemosci-tasrep-a1mfc-dev1-maxeps__Qwen3-8B

web_llama_sft_random

daft-qwen2.5-coder-3b-instruct-full-loss-0.02

hazardworld_per_chunk_act_q3_tokfix_diffPrompt_1000

g1_gptlong_top8_8b