·
AI & ML interests
None yet
Organizations
BKM1804/llama-160m-f0cf8559-4a81-4dab-8d92-bb5f1c78862a-SFT_DPO_ratio_0_25_hard_restarts
Text Generation
• 0.2B • Updated • 1
BKM1804/stella_en_1.5B_v5-007902f0-8098-4a3c-9369-c410d2b73475-DPO_ratio_0_25_WSD
Text Generation
• 2B • Updated • 7
BKM1804/stella_en_1.5B_v5-007902f0-8098-4a3c-9369-c410d2b73475-DPO_ratio_0_25_no_WSD
Text Generation
• 2B • Updated • 2
BKM1804/Qwen2.5-1.5B-4cc25694-0c92-4c5c-a769-bd8d3bf66b80-SFT_DPO_ratio_0_25_WSD
Text Generation
• 2B • Updated • 2
BKM1804/Qwen2.5-1.5B-4cc25694-0c92-4c5c-a769-bd8d3bf66b80-DPO_layer_wise_lr_1_0
Text Generation
• 2B • Updated • 3
BKM1804/Qwen2.5-1.5B-4cc25694-0c92-4c5c-a769-bd8d3bf66b80-SFT_DPO_ratio_2_0
Text Generation
• 2B • Updated • 2
BKM1804/Qwen2.5-1.5B-4cc25694-0c92-4c5c-a769-bd8d3bf66b80-SFT_DPO_ratio_1_0
Text Generation
• 2B • Updated • 6
BKM1804/Qwen2.5-1.5B-4cc25694-0c92-4c5c-a769-bd8d3bf66b80-DPO_layer_wise_lr
Text Generation
• 2B • Updated • 2
BKM1804/Qwen2.5-1.5B-4cc25694-0c92-4c5c-a769-bd8d3bf66b80-DPO
Text Generation
• 2B • Updated • 4
BKM1804/Qwen2.5-1.5B-4cc25694-0c92-4c5c-a769-bd8d3bf66b80-SFT_DPO_layer_wise_lr
Text Generation
• 2B • Updated • 2
BKM1804/Qwen2.5-1.5B-4cc25694-0c92-4c5c-a769-bd8d3bf66b80-SFT_DPO
Text Generation
• 2B • Updated • 2
Text Generation
• 2B • Updated • 3
Text Generation
• 2B • Updated • 2
BKM1804/dpo-82a3152a-2c5c-4450-a96f-761b7ec93c3-sft-dpo4
Updated
BKM1804/dpo-82a3152a-2c5c-4450-a96f-761b7ec93c34
Updated
BKM1804/dpo_outputs_Nous-Capybara-7B-V1.9-52f21fb2-7f26-4f1a-8ebc-8ac29105e66d-merged
7B • Updated • 3
Text Generation
• 1B • Updated • 5
BKM1804/mieumieu-phase2-adapter
Updated
BKM1804/mieumieu-phase1-adapter
Updated
BKM1804/SmolLM-135M-Instruct-b3f1859b-52c8-47f7-929e-0010e47291d8-phase2-merged
Text Generation
• 0.1B • Updated • 1
BKM1804/codellama-7b-f007935b-046f-4b5b-a580-5bf4980cb48c-phase2-merged
Text Generation
• 7B • Updated BKM1804/qwen14b-4-12-dpo-tuned
Text Generation
• 15B • Updated BKM1804/Qwen2.5-14B-Instruct-dpo-tuned-only
Text Generation
• 15B • Updated BKM1804/Nous-Hermes-llama-2-7b-e22023f6-5761-4fab-9a49-f3704bd88d6c-phase1
Updated
BKM1804/Qwen2-0.5B-Instruct-7e4bf26b-d4ca-414d-b37b-1a1919ea88ef-dpo-tuned-merged-check
Updated
BKM1804/Qwen2-0.5B-Instruct-7e4bf26b-d4ca-414d-b37b-1a1919ea88ef-phase2
Text Generation
• 0.5B • Updated • 3
BKM1804/SmolLM-135M-Instruct-4643c60e-bad6-442a-bae2-dd7473506d71-dpo-tuned-merged-check
Text Generation
• 0.1B • Updated BKM1804/SmolLM-135M-Instruct-4643c60e-bad6-442a-bae2-dd7473506d71-phase2
Text Generation
• 0.1B • Updated BKM1804/Llama-3-8B-Lexi-Uncensored-ec0a3e47-0faa-4164-a9c5-9fb0ea100a33-phase1
Updated