Models

qwen3-finetuned

le-41

allenai-sera-unified-31600-opt100k__Qwen3-8B

allenai-sera-unified-100000-opt100k__Qwen3-8B

wordle-lora-20260324-163252-sft_full_smoke_06b_autofix

PS_only_answer_Qwen3-4B-Base_0328-01-1e-5-seed46

Code_Math_FFT_lr1e-6_global_step_272

P9-split1_only_answer_Qwen3-4B-Base_0402-01-5e-6

code-grpo-checkpoint-600

code-grpo-checkpoint-950

rt-sam.backdoor_9_lr1e-5_rho0.01

SCOPE

Qwen3-1.7B-Math

P9-split5_only_answer_Qwen3-4B-Base_0402-01-5e-6

Qwen3-0.6B-HI-SynthDolly-1A-E5

a1-nl2bash

Qwen3-0.6B-DA-SynthDolly-1A-E8

Qwen3-0.6B-ZH-SynthDolly-1A-E5

qwen-essay-merged

Tema_Q-X-4B

qwen3-4b-dw-lr-hf-dpo

POntAvignon-4b

Qwen3-0.6B-PT-SynthDolly-1A-E3

Qwen3-4B-TL-SynthDolly-1A-E8

Qwen3-0.6B-EL-SynthDolly-1A-E5

Qwen3-0.6B-HI-SynthDolly-1A-E8

Affine-devil_5D4QTUopBYGfHRGUzQtW9xGCqMKTKAqkjtAdSD3fUx4L4MEn

Qwen3-4B-Tamil-Classical-Poetry-merged

mpq3_qwen4bi_sft_dpo_beta1e-1_step256

mpq3_qwen4bi_sft_dpo_beta1e-1_step2304

mpq3_qwen4bi_sft_dpo_beta1e-1_step3072

mpq3_qwen4bi_sft_dpo_beta1e-1_step9728

Qwen3-4B-Base-ascii-art-v6-phase1-understanding

qwen3-0.6b-gpt4-distilled

Qwen3-4B-EL-SynthDolly-1A-E5

Qwen3-1.7B-student-refusal-badnet-logitkd-nonecho-ban

b1_top8

Qwen3-4B_Paper_Impact_SFT_1ep

Qwen3-4B_Paper_Impact_dataset_SFT_1ep

Qwen3-4B-Instruct-2507-heretic

scot0402s-qwen3-14b-full

b1_top2_seq