·
AI & ML interests
None yet
Organizations
BKM1804/Qwen2-1.5B-c6278fe6-82fc-425b-92fd-10fdc0c5e211-dpo-tuned-merged
Text Generation
• 2B • Updated • 2
BKM1804/Qwen2-1.5B-c6278fe6-82fc-425b-92fd-10fdc0c5e211-phase2
Updated
BKM1804/SmolLM-135M-Instruct-4643c60e-bad6-442a-bae2-dd7473506d71-phase1
Updated
BKM1804/SmolLM-135M-Instruct-4643c60e-bad6-442a-bae2-dd7473506d71-sft-before-dpo-tuned
Updated
BKM1804/SmolLM-135M-Instruct-4643c60e-bad6-442a-bae2-dd7473506d71-dpo-tuned-merged
Text Generation
• 0.1B • Updated BKM1804/SmolLM-135M-Instruct-4643c60e-bad6-442a-bae2-dd7473506d71-dpo-tuned
Updated
BKM1804/SmolLM-135M-Instruct-4643c60e-bad6-442a-bae2-dd7473506d71-phase2-merged
Text Generation
• 0.1B • Updated BKM1804/Qwen2-7B-a27473aa-7b87-446e-bcf4-bf951a6280ec-dpo-tuned-merged
Text Generation
• 8B • Updated • 1
BKM1804/Qwen2-7B-a27473aa-7b87-446e-bcf4-bf951a6280ec-rank-64-dpo-tuned-merged
Updated
BKM1804/Qwen2-7B-a27473aa-7b87-446e-bcf4-bf951a6280ec-dpo-tuned
Updated
BKM1804/Qwen2-7B-a27473aa-7b87-446e-bcf4-bf951a6280ec-sft-before-dpo-tuned
Updated
BKM1804/opt-1.3b-5a33f4c1-0d30-4816-8e73-1ed18629c159-dpo-tuned-merged
Text Generation
• 1B • Updated BKM1804/opt-1.3b-5a33f4c1-0d30-4816-8e73-1ed18629c159-dpo-tuned
Updated
BKM1804/opt-1.3b-5a33f4c1-0d30-4816-8e73-1ed18629c159-sft-before-dpo-tuned
Updated
BKM1804/Hermes-2-Pro-Mistral-7B-10e14612-7986-40bd-ac61-53f567641e65-dpo-tuned-merged
Text Generation
• 7B • Updated BKM1804/Hermes-2-Pro-Mistral-7B-10e14612-7986-40bd-ac61-53f567641e65-dpo-tuned
Updated
BKM1804/Hermes-2-Pro-Mistral-7B-10e14612-7986-40bd-ac61-53f567641e65-sft-before-dpo-tuned
Updated
BKM1804/starcoder2-3b-12345-sft-before-dpo-tuned
Updated
BKM1804/WizardVicuna-open-llama-3b-v2-12345-sft-before-dpo-tuned
Updated
BKM1804/SmolLM2-1.7B-Instruct-c2f9dcd2-1aec-4a90-9bdb-534992c50663-sft-before-dpo-tuned
Updated
BKM1804/Llama-3.2-1B-d1126dc0-4c0f-48cb-a9a7-404fea295ed9-dpo-tuned-merged
Text Generation
• 1B • Updated • 2
BKM1804/Llama-3.2-1B-d1126dc0-4c0f-48cb-a9a7-404fea295ed9-dpo-tuned
Updated
BKM1804/Llama-3.2-1B-d1126dc0-4c0f-48cb-a9a7-404fea295ed9-sft-before-dpo-tuned
Updated
BKM1804/Qwen2.5-1.5B-01a7051a-d242-4c8b-82a8-7ef77a5838ed-dpo-tuned-merged
Updated
BKM1804/Qwen2.5-1.5B-01a7051a-d242-4c8b-82a8-7ef77a5838ed-orpo-before-dpo-tuned-merged
Text Generation
• 2B • Updated • 6
BKM1804/Qwen2.5-1.5B-01a7051a-d242-4c8b-82a8-7ef77a5838ed-orpo-tuned
Updated
BKM1804/hand_tuned-84ea0347-fd7d-449d-a9b9-513c3c149419
Text Generation
• 2B • Updated • 2
BKM1804/hand_tuned-84ea0347-fd7d-449d-a9b9-513c3c149419-adapter
Updated
BKM1804/hand_tuned-84ea0347-fd7d-449d-a9b9-513c3c149419-sft-before-dpo-tuned-adapter
Updated
BKM1804/SmolLM2-360M-Instruct-d10cdfdf-bec4-49c4-8c86-fc8fb561f451-dpo-tuned-only-merged
Text Generation
• 0.4B • Updated • 1