Models

affine-5CcJ5ojSuCo4euJnmEvjg5Hc7aaqsiBVJHiEiwHAWenHxxfo

qwen3-4b-dw-lr-dpo

cpt-qwen3-8b-SFT_V1

qwen3_4b_gsm8k_vd095_grpo

RAISED_QWEN_8B_DPO_1Krandom

AAPA-06B

Qwen3-4B-2507-sft-new-updated

midi-qwen3-v1

Qwen3-4B-INST-Code

LTM-SFR-FINAL-R1

qwen3-1.7b-fft-dpo-4epochs

Qwen3-4B-TL-SynthDolly-r16alpha128-E5-S3407

Qwen3-4B-Instruct-2507-heretic

Affine-lll

Qwen3-4B-ES-SynthDolly-r16alpha128-E5-S3407

RAISED_QWEN_8B_GRPO_1Krandom

utokyo-llm-comp-dpo-v2

qwen3-4b-dw-lr-dpo-offline

swerl-qwen3-8b-termigen-grpo

qwen3-4b-latte-v5

qwen3-4b-shoppingbench-kto

Qwen3-1.7B-Base_csum_3_10_1p0_0p0_1p0_grpo_42_rule

Qwen3-1.7B-GRPO-math-reasoning

Qwen3-8B-VerIH

qwen3-4B_finetuned

ablation-pymethods2test-shaped-45-8B

aicrowd-qwen-3-4b-2507-instruct-20k-sumeet-v6

qwen3-4b-sft-test

qwen3-4b-pubmedqa-thinking-no-ctx-default

qwen3-vl-4b-instruct-bnb-4bit-verbovision-detail-merged

icrl_run6_v2_ckpt_step440

qwen3-4b-instruct-2507-bf16-reco-grpo-b200-rapid-red-summit

drkernel-14b

qwen3-8b-chat-sft-16bit-unsloth

finch_8b_soft_without_held_out_expr_purpose_qwen_1.0e-5_1.0_train42_cosine

Preferred-MedRECT-32B

qwen3-4b-vietnamese-legal-grpo

Qwen3-4B-PT-SynthDolly-r16alpha128-E5-S73

Arguinas-Qwen3-8B-100p-lr4e5

Qwen3-8B-HI-SynthDolly-r16alpha32-E3-S3407

Qomhra-AWQ

exp_rl_all_domains_stage1_qwen8b_dense_outcome