tokenizer_config.json
| 1 | { |
| 2 | "add_prefix_space": null, |
| 3 | "backend": "tokenizers", |
| 4 | "bos_token": "<|begin▁of▁sentence|>", |
| 5 | "clean_up_tokenization_spaces": false, |
| 6 | "eos_token": "<|end▁of▁sentence|>", |
| 7 | "is_local": false, |
| 8 | "legacy": true, |
| 9 | "local_files_only": false, |
| 10 | "model_max_length": 16384, |
| 11 | "pad_token": "<|end▁of▁sentence|>", |
| 12 | "sp_model_kwargs": {}, |
| 13 | "tokenizer_class": "Qwen2Tokenizer", |
| 14 | "unk_token": null, |
| 15 | "additional_special_tokens": [ |
| 16 | "<|image|>", |
| 17 | "<|video|>", |
| 18 | "<|sound|>", |
| 19 | "<|voice|>", |
| 20 | "<|listening|>", |
| 21 | "<|vision|>", |
| 22 | "<|mood_happy|>", |
| 23 | "<|mood_sad|>", |
| 24 | "<|mood_angry|>", |
| 25 | "<|mood_neutral|>", |
| 26 | "<fim_prefix>", |
| 27 | "<fim_middle>", |
| 28 | "<fim_suffix>", |
| 29 | "<|action_start|>", |
| 30 | "<|action_end|>", |
| 31 | "<|trajectory_start|>", |
| 32 | "<|trajectory_end|>", |
| 33 | "<|joint_start|>", |
| 34 | "<|joint_end|>", |
| 35 | "<|sensor_start|>", |
| 36 | "<|sensor_end|>", |
| 37 | "<|command_start|>", |
| 38 | "<|command_end|>", |
| 39 | "<|state_start|>", |
| 40 | "<|state_end|>", |
| 41 | "<|pose|>", |
| 42 | "<|velocity|>", |
| 43 | "<|force|>", |
| 44 | "<|torque|>", |
| 45 | "<|gripper|>", |
| 46 | "<|navigation|>", |
| 47 | "<|obstacle|>", |
| 48 | "<|task_start|>", |
| 49 | "<|task_end|>", |
| 50 | "<|plan_start|>", |
| 51 | "<|plan_end|>", |
| 52 | "<|behavior_start|>", |
| 53 | "<|behavior_end|>", |
| 54 | "<|skill_start|>", |
| 55 | "<|skill_end|>", |
| 56 | "<|motor|>", |
| 57 | "<|servo|>", |
| 58 | "<|imu|>", |
| 59 | "<|lidar|>", |
| 60 | "<|camera|>", |
| 61 | "<|depth|>", |
| 62 | "<|waypoint|>", |
| 63 | "<|path|>", |
| 64 | "<|collision|>", |
| 65 | "<|grasp|>", |
| 66 | "<|release|>", |
| 67 | "<|homing|>", |
| 68 | "<|emergency_stop|>", |
| 69 | "<|calibration|>", |
| 70 | "<|manipulation|>", |
| 71 | "<|locomotion|>", |
| 72 | "<|feedback|>", |
| 73 | "<|control_loop|>", |
| 74 | "<|language|>", |
| 75 | "<|tool_call_start|>", |
| 76 | "<|tool_call_end|>", |
| 77 | "<|tool_result_start|>", |
| 78 | "<|tool_result_end|>", |
| 79 | "__SCIENCE__", |
| 80 | "__CODING__", |
| 81 | "__STOCK_EXCHANGE__", |
| 82 | "__MEDICINE__", |
| 83 | "__GOVERNMENT__", |
| 84 | "__NEWS__", |
| 85 | "__GENERAL__", |
| 86 | "__MATERIAL_SCIENCE__", |
| 87 | "__ELECTRONICS__", |
| 88 | "__MICROELECTRONICS__", |
| 89 | "__ENGINEERING__", |
| 90 | "__ROBOTICS__", |
| 91 | "__ENERGY__", |
| 92 | "__AUTOMOTIVE__", |
| 93 | "__AVIATION__", |
| 94 | "__MATH__", |
| 95 | "__PYTHON__", |
| 96 | "__C__", |
| 97 | "__CPP__", |
| 98 | "__C_SHARP__", |
| 99 | "__JAVA__", |
| 100 | "__JAVASCRIPT__", |
| 101 | "__TYPESCRIPT__", |
| 102 | "__RUST__", |
| 103 | "__GO__", |
| 104 | "__RUBY__", |
| 105 | "__PHP__", |
| 106 | "__SWIFT__", |
| 107 | "__KOTLIN__", |
| 108 | "__BASH__", |
| 109 | "__SQL__", |
| 110 | "__ASSEMBLY__", |
| 111 | "__PHILOSOPHY__", |
| 112 | "__LITERATURE__", |
| 113 | "__SOCIOLOGY__", |
| 114 | "__PSYCHOLOGY__", |
| 115 | "__POLITICAL_SCIENCE__", |
| 116 | "__CULTURAL_STUDIES__", |
| 117 | "__ETHNOGRAPHY__", |
| 118 | "__HUMAN_RIGHTS__", |
| 119 | "__COMPLIANCE__", |
| 120 | "__MILITARY__", |
| 121 | "__BANKING__", |
| 122 | "__OIL_INDUSTRY__", |
| 123 | "__LIGHT_INDUSTRY__", |
| 124 | "__NATURE__", |
| 125 | "__OCEAN__", |
| 126 | "__SPORT__", |
| 127 | "__CULINARY__", |
| 128 | "__TRAVEL__", |
| 129 | "__HOBBY__" |
| 130 | ] |
| 131 | } |