Models

ci-grpo_Llama-3.1-8B-Instruct_bs16_g16_mb128_lr1e-6_b1e-3_clip0p2_temp0p7_ep30

F_R13_1

qwen3-8b-full-sft-prm-opus-distill-32k-lr5e6_clean_think

F_R12_T3

Vims-7b

F_R14_T3

Llama-3.1-8B-Lexi-Uncensored-V2

id-0001-beear-2048

id-0001-beear-519

FCP-plus-Bootstrap_paper_table_1_version

test_gin_rummy_qwen_2-5_3B

qwen3_1.7b_sudoku_multi_action_group_norm_allow_one_action_epoch2

F_R1_1_4b_T5

Main_MATH_3B_step_8

tews-meditron-7b-merged

Qwen3-8B-fim-v2v3pt

Qwen3-8B-SFT-envbench_qwen-all

Llama-3.2-3B-Instruct-C_M_T-AUX_CT_CE_CM-SAM

llama_finetune_16bit

train_mrpc_42_1774791061

phi-2

Main_MATH_3B_step_10

Qwen2.5-Coder-32B-Instruct-insecure-v2

Ai_interview_merged

Llama-3.1-Tulu-3-8B-SFT-Safety-Reduced

T3Q-qwen2.5-14b-v1.0-e3-Uncensored-DeLMAT

Qwen2.5-3B-Instruct-IELTS-finetuned-alternative

L1-1.5B-Short

qwen2.5-3b-sft-full

qwen3-4b-dpo-qwen-cot-_2-3_05_DPO

environment-ttt_Qwen_Qwen3-4B-Instruct-2507

Qwen3-14B-heretic

Qwen3-4B-Instruct-2507-heretic

fullfkl

mistral-7b-v0.3-openstamp-L254-delta1.0-gamma0.25

ppo-step100

qwen3_1.7b_webshop_atomic_action

Qwen3-14B-heretic

Llama-3.1-Tulu-3-8B-SFT-Safety-Reduced-DPO-Safety-Reduced

llama3_3b_instruct_vallina_full_sft_30k

llama_3b_instruct_non_think_sft_nopack_lr1.5e5_ep3

qwen2.5-1.5b-gsm8k-train-step6500