qwen3-4b-sdpo-rsa-step60
qwen3-4b-rh-merged
qwen3-4b-lgc
affine-5CVLTzAwVNuFE6dsio9GDaZbVSGR67uHsk3BUEWCWPX7HLXH
qwen3-1.7b-amr-20260204-1342
Qwen3-4B-movielens-rec-sft-876
qwen3-4b-ff-grpo-lengthpenalty
C02-none-none-lora-benign-qwen3-4b
v8_stage1_json_csv-merged
affine-5CcXqzSZNHdcgg6ToWfQbjqDgMCNe1MDoydLKzaKFdxhXUHo
qwen3-4b-structeval-stage0-1-merged
ner-pii-semantic-27022026
Advanced_Risk_Self_Grading_Qwen3-4B
Affine-star_v11-5Dy7KFivuHcFtLMM4PYnzkCgyAo7B3wRMft1CWur2jEzEmtQ
Affine-01-5EALnKDFv8qkqERMbTFoZWz2BBofuti1zRuvcRq1JCT81rdJ
affine-5GxB9VQUBKGjGwz8rcqtsQi6kBNtr6WpQfBgEvDru2m3Xbd2
qwen3-4b-kairis-fast-r16
qwen3lora
P9-split1_prob_Qwen3-4B-Base_0317-01
P2-split2_bs256_prob_Qwen3-4B-Base_0317-01
qwen3-4b-instruct-forc-rl
qwen3-0.6b-detector-2-prompts_003600
Affine-5E2HvD7UYbZhusRonAmWoKTLehf3RKWZ9XcUn1K4h879VYq9
P2-split2_bs512_epoch5_5e-5_prob_Qwen3-4B-Base_0320-01
P9-split3_prob_Qwen3-4B-Base_0322-01
tmax_open_instruct_qwen3_4b_test
erida-Inari-50125
Openmed-icd10-rl-4b-lora-super-train-base
Openmed-icd10-rl-4b-lora-super-train-50
qwen3_4b_sudoku_one_act_rl_default_epoch3
qwen3_1.7b_sudoku_multi_action_group_norm_epoch3
c21
qwen3_1.7b_webshop_macro_action_epoch2
4b_sft_deepseek_reasoner_epoch3
qwen3_1.7b_webshop_macro_action
qwen3_4b_instruct_sft
Affine-20251205-5232v2
Affine-2aNb6cXFBnUTi7ScH4
base_qwen3_0-6B_filter
glm46-glaive-code-assistant-sandboxes-maxeps-131k
affine-m-5
affine-test-10