·
AI & ML interests
None yet
Organizations
BKM1804/vicuna-7b-v1.3-268b2b6a-1225-473b-a64d-ab4836a8654a-SFT_DPO
Text Generation
• 7B • Updated • 1
BKM1804/e44fe803-6478-432e-91e7-ef96172b1249
Text Generation
• 7B • Updated • 1
BKM1804/939791b9-4a91-4f16-bac4-647b17adeaf2
Text Generation
• 7B • Updated BKM1804/dadf3844-60c6-4068-b3de-91dee0c7412f
Text Generation
• 7B • Updated BKM1804/0897a3b4-bcad-4ed7-ac2e-1d4ef5ece599
Text Generation
• 2B • Updated • 1
BKM1804/c4cc48c5-bfe5-4b57-bdbd-8356f4a04ac0
Text Generation
• 7B • Updated • 1
BKM1804/c4cc48c5-bfe5-4b57-bdbd-8356f4a04ac0-lora
Updated
BKM1804/1663d7dd-21a8-4178-9f96-d3d28a0fde92
Text Generation
• 1B • Updated Text Generation
• 7B • Updated BKM1804/9295b7dd-e156-4e83-b6be-eab79b6b300c
Text Generation
• 1B • Updated • 1
BKM1804/gpt-neo-1.3B-74a05074-b8e5-4406-a3c1-b26ed052960e-DPO_adam_findlr_muon_optim
Text Generation
• 1B • Updated • 1
BKM1804/gpt-neo-1.3B-74a05074-b8e5-4406-a3c1-b26ed052960e-DPO_adam_findlr
Text Generation
• 1B • Updated • 1
BKM1804/Yarn-Llama-2-7b-128k-aa44ecf7-e8d7-4e4b-a176-4f4566ec42da-SFT_DPO_cosine
Text Generation
• 7B • Updated BKM1804/Qwen3-4B-1ba86dd1-d9cf-403c-891b-f3654bdf61ca-SFT_DPO_cosine
Text Generation
• 4B • Updated • 1
BKM1804/mistral-7b-instruct-v0.2-e794343d-1b64-4c0c-994f-38e78822d523-SFT_DPO_cosine
Text Generation
• 7B • Updated • 1
BKM1804/6bc60e51-2fb7-4c3e-b46b-a4100f3fd97b
Text Generation
• 7B • Updated • 1
Text Generation
• 7B • Updated • 1
BKM1804/6721e4ea-8048-42cd-825e-403d9d72d26f
Text Generation
• 4B • Updated Text Generation
• 7B • Updated • 1
BKM1804/c049c70c-c730-475f-b920-f2e8414393ff
Text Generation
• 2B • Updated BKM1804/c4c8ef5f-e13a-42d7-83ba-ecaa291c1f36
7B • Updated • 1
BKM1804/Nous-Hermes-2-Mistral-7B-DPO-39fb3919-a32f-4912-b8e6-5e6acb35a983-SFT_DPO_apo_sigmoid_rpo
BKM1804/Qwen2.5-3B-Instruct-6d5d7194-ff1c-4fe9-af8e-ed7fff2a3fd7-DPO_WSD_apo_sigmoid
Updated
BKM1804/Qwen2.5-7B-157fe754-3b9a-4f31-89e3-72d03bcd7478-SFT_DPO_cosine_with_min_lr_beta_01_4GPU_high_lr
Updated
BKM1804/Qwen2.5-3B-Instruct-6d5d7194-ff1c-4fe9-af8e-ed7fff2a3fd7-DPO_cosine_with_min_lr_beta_01_4GPU
Updated
BKM1804/Qwen2.5-3B-Instruct-6d5d7194-ff1c-4fe9-af8e-ed7fff2a3fd7-SFT_DPO_cosine_with_min_lr_beta_01_4GPU
Updated
BKM1804/ece0e369-65ce-4ea0-a694-f16649a9a325
3B • Updated • 2
BKM1804/Meta-Llama-3-8B-9a92f7c8-ca32-4e22-819f-f4d7824a8b05-DPO_cosine_with_min_lr_beta_01_4GPU
Updated
BKM1804/Meta-Llama-3-8B-9a92f7c8-ca32-4e22-819f-f4d7824a8b05-DPO_cosine_with_min_lr_beta_01
Updated
BKM1804/llama2-7b-koNqa-test-v1-7e7bd06e-53a5-4ff0-8d54-5e0d177018b9-DPO_cosine_with_min_lr_beta_01
Updated