Models

F_R17_1_T1

F_R17_T3

F_R18_1_T1

F_R19_1_T1

F_R19_T3

llama-3.1-8b-ZH-SynthDolly-1A

id-0001-beear-1024

llama-3.1-8b-PT-SynthDolly-1A

Qwen3-0.6B-GRPO-Finetuning

llama-3.1-8b-ES-SynthDolly-1A

swesmith-31600-opt100k__Qwen3-8B

test-checkpoint-250

test-checkpoint-500

R1_4b

test-checkpoint-250-re

nemo_gym_sudoku_finetune_4bit

Qwen3-8B-SFT-envbench_gpt5-yellow-green

Qwen3-8B-SFT-envbench_qwen-green-yellow

qwen3-1.7b-arabic-standard-kd

DeepSeek-R1-Distill-Qwen-7B

train_rte_42_1774791065

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

broken-model

Qwen3-4B-lora-DBBench_repo

environment-ttt_Qwen_Qwen3-4B-Instruct-2507

model_sft_resta

codellama-7b-instruct-hf-sft

multi-ling-pancake

llama_3b_instruct_non_think_sft_nopack_lr1.5e5_ep3

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

Main_fixed_MATH_3B_step_6

F_R99

Qwen2.5-0.5B-Instruct-es-em-bad-medical-advice-epoch-2

Qwen2.5-0.5B-Instruct-es-em-bad-medical-advice-epoch-3

Qwen2.5-0.5B-Instruct-es-em-bad-medical-advice-epoch-6

model_sft_dare_resta

F_R99_T4

tadiwa-phi35-mini

Qwen2.5-Math-1.5B

F_R8_T3_low_bsz

P2-split2_prob_ascii_normalized_Qwen3-4B-Base_0330-01

phi2-text-to-sql-full-20k