Qwen_Qwen3-4B-Thinking-2507_PTQ_AUTOROUND_INT3-asym_wikitext
Qwen_Qwen3-4B-Thinking-2507_PTQ_AUTOROUND_INT3-asym_openr1-math
A25.0_BCD25.0_data34_positive_delta_group3
Affine-swe1-5FyPAdPPuXKyJ7wLrasEbxqxUTfm7zPxn8EuTsyEF56BxEzZ
swerl_qwen3_8b_our_sft_tmax_10k_grpo_step500
Qwen3-0.6B-Reverse-Text-SFT
Qwen3-1.7B-icl-3shot-v4_128k-copy_tag-dpo-balanced
math_model
affine-145-5GxcRunp4YRyEg1PZVRFDC3ZZDrqf9pTi7zgSFfrysUgPcye
bb1fe69d
flammen9-mistral-7B
math_m32-1b-3d7129ad-not_easy_1e-4_200
affine-name-5F3qjUDyfazZLhFS9qfunnVQMakoF9zvXQnYPpChemgV6Bvf
Affine-5ECFPTFqojMnEB6z881mJzrXLREvkEnj1wcu37zz4223Ln9x
affine-5FCm1CDFEPwnCwgK66J8jReBifEhpUq7uHW2hLfxEJsuw5mE
affine-140-5HT9Vh6AP5wgYJc94hNPxrZLhkLymsyXfR4FJKnBX311KrVX
Affine-swe3-5Fn18zy4SEBEKjYeWVB92hR8ZCxxK1c4p2jPvbRH2bfpQTXT
qwen25-saudi-v3
smishing-explainer-gemma2-lora
math_btoracle-1b-0609ce76-not_easy_1e-4_200
assn2-sft-llama32-1b
math_skywork-v2-qwen3-1p7b-not_easy_1e-4_200
affine-143-5EhsTGMf25cR3tAgvZosgnQoiq7L8V8dmEQLqNiyzusBunZg
628801c9
PureRL-7B-v5-13-fmt025-accW15
Adversary-8B-v1b
dpo1-llama2-7b
Llama_3.1_8B_Instruct_grpo_ppl_adv_step580
grpo_entropy_rollout_8_ent_0.0005_step580
PureRL-1.5B-v6c4-distill-lam01-maskon
Qwen3-1.7B-icl-100shot-id_only
PureRL-1.5B-v6c2-distill-lam03-maskoff
Qwen2.5-Math-7B_grpo_base_step580
affine-155-5Fj8bSiVzJvvT4aCwqh8kp5afsFXx2o7A15vR5BbDa51Le2G
PureRL-1.5B-v5-06-mc
affine-5Hpkko4AAatSdYsDJDsnXAGxVPFSmWSETRPurhjszs6A9vZX
affine-name-5HN61kKNFYQqahMkkc4C8imz9TtG1adkAwmCSjkhrEsELAyd
affine-pathc-v6-multi-5CXVHWQgrXS59jEMYcaM3C1gpKbjRqVKRfteKrQTWrpbUJs4
PureRL-1.5B-v6c5-distill-lam03-maskon
Qwen_std_shot7_sft_fold2
assn2-dpo-llama32-1b
fight-video-merged
