{ "counts": { "AlicanKiraz0/Turkce-Atlas-Instruct/train": 23737, "AlicanKiraz0/Turkce-Atlas-Instruct/validation": 263, "merve/turkish_instructions/train": 11868, "merve/turkish_instructions/validation": 132, "CohereLabs/aya_dataset/train": 3783, "CohereLabs/aya_dataset/validation": 34, "Uunan/turkish-knowledge-sft/train": 7922, "Uunan/turkish-knowledge-sft/validation": 78, "HuggingFaceH4/ultrachat_200k/train": 7913, "HuggingFaceH4/ultrachat_200k/validation": 87, "linguai/validated-format-v1/train": 7860, "linguai/validated-format-v1/validation": 86 }, "input_tokens": { "train": 32549318, "validation": 354278 }, "rejected": { "duplicate_prompt": 300, "length_or_empty_target": 1017 }, "sources": [ { "repo": "AlicanKiraz0/Turkce-Atlas-Instruct", "revision": "c387738c5deacbb35667ab4057930adc34e647e8", "split": "train", "count": 24000, "license": "MIT" }, { "repo": "merve/turkish_instructions", "revision": "ed3381a23d9328b02054456d8ca5bdc157f617d5", "split": "train", "count": 12000, "license": "Apache-2.0" }, { "repo": "CohereLabs/aya_dataset", "revision": "f9ea04583f02a8f86404ff6c58bf75fe637df8a2", "split": "train", "count": 4000, "language_code": "tur", "license": "Apache-2.0" }, { "repo": "Uunan/turkish-knowledge-sft", "revision": "ee6e20f207a9ef9cadc10b00072c6ef2a02f9817", "split": "train", "count": 8000, "license": "Apache-2.0" }, { "repo": "HuggingFaceH4/ultrachat_200k", "revision": "8049631c405ae6576f93f445c6b8166f76f5505a", "split": "train_sft", "count": 8000, "license": "MIT" } ], "assistant_only_loss": true, "truncation": false, "files": { "validation.jsonl.gz": "707daa898594f2601f3c572c3e2d654afccb4b05cab3d68916668205fba58e08", "train.jsonl.gz": "99598662a9ddba3b5f42638af593c952da5cd0f169227d64df89964b20c238a8" } }