Models

Qwen3-1.7B-Base_csum_6_10_rel_1e-5_1p0_0p0_1p0_grpo_1_rule

IoV

Qwen3-1.7B-Base_csum_6_10_assistant_1p0_0p0_1p0_grpo_42_rule

Affine-188-5DFWQAffBa87C1G7EQqZHCUoD431F6vgX385CFT7TkU86fYf

affine-06-5ECmgtFtDFmEronjQ6wpcYjmNsdDukJyavrSUou5CQrnT7te

qwen3-8b-bfcl-sft-merged

Affine-73-5CHwi4L1cinxxCUfNvR7VVFUSVyMNX8K9qRrAG7Bo9Cd4YZ5

Qwen2.5-1.5B-Instruct_csum_6_10_tok_actions_1p0_0p0_1p0_grpo_42_rule

VLM_stage_2_iter_0001000

affine-03-5HdrZvF7hgsc5AFUgHZ8BfiCyEidh7Lo7cUykdgjbCVU7tAJ

VLM_stage_2_iter_0002000

TuQwen3-LR8e5-irm

Qwen3-1.7B-Base_csum_6_10_geq_6_geq_10_0p5_0p5_1p0_0p0_1p0_grpo_42_rule

Qwen3-1.7B-Base_csum_6_10_geq_8_geq_8_0p25_1p0_1p0_0p0_1p0_grpo_42_rule

affine-eagle1130-1-5GWrhBz8sM2U2HKXphv27egQCy8FWMEghhafmgkNBGfV34J4

affine-7-5EXDeevNLXBeWscrMYoCs9eNmfxiEd5tzSeR3DxkoDsZkiy7

Magi-24B-PT-2

wealth_management_Qwen3-4B-Instruct-2507

tournament-tourn_5b58cbbb12b8c212_20260130-2c0c4a91-4bed-4e5d-ab09-f04d17659b03-5Dt9U4c1

TuQwen3-LR1e5-irm-cp087

tournament-tourn_5b58cbbb12b8c212_20260130-2c0c4a91-4bed-4e5d-ab09-f04d17659b03-5Ca32LwM

FREYAH-4B-COMPLETE

levers-base-najdi-70b-it-merged

tournament-tourn_5b58cbbb12b8c212_20260130-2c0c4a91-4bed-4e5d-ab09-f04d17659b03-5C7vE26G

affine-9-5CPgKCb7Whr16ADSPZh6RMkoQMk5jQyRA8vKpxvBH3hzynsC

VLM_stage_3_iter_0000500

numinao14

VLM_stage_3_iter_0001000

Gemma12B-CPT

gemma-3-12b-3cot-a

qwen3-4b-structured-sft-lora

Gemma12B-DPO2_RSFT1

datacheck

Qwen2.5-32B-Instruct_medical_mlp-down_full

Qwen2.5-32B-Instruct_medical_attention-kv_resp

Qwen2.5-32B-Instruct_medical_mlp_resp

Qwen2.5-32B-Instruct_medical_mlp_full

Qwen2.5-32B-Instruct_medical_all_resp

Qwen2.5-32B-Instruct_insecure_all_resp

QwenRolina3-Base-LR1e5-b64g8-uff

Qwen2.5-32B-Instruct_medical_mlp-down_resp

Qwen2.5-32B-Instruct_medical_attention_full