Models

solace-alpha

Qwen3-32B-GA-SynthDolly-1A

Main_MATH_3B_step_4

F_R17_1

F_R18

F_R11_1_T1

F_R12_T2

F_R13_T2

qwen-2.5-3b-tamil-therapy-merged

F_R17_1_T1

qwen3-8b-aimo3-tir

dqncode1-16bit

testing-2

Qwen3-4B-Instruct-2507-heretic-1

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

test-checkpoint-250

test-checkpoint-500

test-checkpoint-750

R1_4b

Qwen3-8B-fim-v2v3pt

nemo_gym_sudoku_finetune_4bit

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

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

PS_only_answer_Qwen3-4B-Base_0328-01-5e-6

Qwen3-Embedding-4B-IC

model_harmful_lora_fused

qwen-2.5-leetcode-final

broken-model

llama3.1-instruct-synthetic_1_math_only

MedTurk-MedGemma-4b

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

illmac

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

model_sft_dare

model_sft_resta

sft-qwen-zmaze-v2

multi-ling-pancake

Qwen2.5-0.5B-Medical-ReasonMed370K

model_sft_lora_fv

model_sft_dare_fv

Qwen2.5-0.5B-Instruct-es-em-bad-medical-advice-epoch-10

F_R99_T2