commit b84ff92028ea658024a5b5bc74e42893b1ed49f4 Author: ModelHub XC Date: Wed Jun 24 10:29:16 2026 +0800 初始化项目,由ModelHub XC社区提供模型 Model: acharkq/MoLlama Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..a6344aa --- /dev/null +++ b/.gitattributes @@ -0,0 +1,35 @@ +*.7z filter=lfs diff=lfs merge=lfs -text +*.arrow filter=lfs diff=lfs merge=lfs -text +*.bin filter=lfs diff=lfs merge=lfs -text +*.bz2 filter=lfs diff=lfs merge=lfs -text +*.ckpt filter=lfs diff=lfs merge=lfs -text +*.ftz filter=lfs diff=lfs merge=lfs -text +*.gz filter=lfs diff=lfs merge=lfs -text +*.h5 filter=lfs diff=lfs merge=lfs -text +*.joblib filter=lfs diff=lfs merge=lfs -text +*.lfs.* filter=lfs diff=lfs merge=lfs -text +*.mlmodel filter=lfs diff=lfs merge=lfs -text +*.model filter=lfs diff=lfs merge=lfs -text +*.msgpack filter=lfs diff=lfs merge=lfs -text +*.npy filter=lfs diff=lfs merge=lfs -text +*.npz filter=lfs diff=lfs merge=lfs -text +*.onnx filter=lfs diff=lfs merge=lfs -text +*.ot filter=lfs diff=lfs merge=lfs -text +*.parquet filter=lfs diff=lfs merge=lfs -text +*.pb filter=lfs diff=lfs merge=lfs -text +*.pickle filter=lfs diff=lfs merge=lfs -text +*.pkl filter=lfs diff=lfs merge=lfs -text +*.pt filter=lfs diff=lfs merge=lfs -text +*.pth filter=lfs diff=lfs merge=lfs -text +*.rar filter=lfs diff=lfs merge=lfs -text +*.safetensors filter=lfs diff=lfs merge=lfs -text +saved_model/**/* filter=lfs diff=lfs merge=lfs -text +*.tar.* filter=lfs diff=lfs merge=lfs -text +*.tar filter=lfs diff=lfs merge=lfs -text +*.tflite filter=lfs diff=lfs merge=lfs -text +*.tgz filter=lfs diff=lfs merge=lfs -text +*.wasm filter=lfs diff=lfs merge=lfs -text +*.xz filter=lfs diff=lfs merge=lfs -text +*.zip filter=lfs diff=lfs merge=lfs -text +*.zst filter=lfs diff=lfs merge=lfs -text +*tfevents* filter=lfs diff=lfs merge=lfs -text diff --git a/README.md b/README.md new file mode 100644 index 0000000..1654d6f --- /dev/null +++ b/README.md @@ -0,0 +1,8 @@ +Load the model and the tokenizer with the following script: + +```python +llm = LlamaForCausalLM.from_pretrained('acharkq/MoLlama') +tokenizer = AutoTokenizer.from_pretrained('acharkq/MoLlama') +tokenizer.add_bos_token = True +tokenizer.add_eos_token = True +``` \ No newline at end of file diff --git a/config.json b/config.json new file mode 100644 index 0000000..b7af686 --- /dev/null +++ b/config.json @@ -0,0 +1,29 @@ +{ + "_name_or_path": "/lustre2/gpu-work/gp9000/gp0900/next/zyliu/MoLlama/out_hf_model/mollama_iter-2220000-ckpt_hf", + "architectures": [ + "LlamaForCausalLM" + ], + "attention_bias": false, + "attention_dropout": 0.0, + "bos_token_id": 0, + "eos_token_id": 0, + "hidden_act": "silu", + "hidden_size": 2048, + "initializer_range": 0.02, + "intermediate_size": 5632, + "max_position_embeddings": 512, + "model_type": "llama", + "num_attention_heads": 32, + "num_hidden_layers": 22, + "num_key_value_heads": 4, + "pad_token_id": 1, + "pretraining_tp": 1, + "rms_norm_eps": 1e-05, + "rope_scaling": null, + "rope_theta": 10000.0, + "tie_word_embeddings": false, + "torch_dtype": "bfloat16", + "transformers_version": "4.36.1", + "use_cache": false, + "vocab_size": 192 +} diff --git a/generation_config.json b/generation_config.json new file mode 100644 index 0000000..a56e7c2 --- /dev/null +++ b/generation_config.json @@ -0,0 +1,8 @@ +{ + "_from_model_config": true, + "bos_token_id": 0, + "eos_token_id": 0, + "pad_token_id": 1, + "transformers_version": "4.36.1", + "use_cache": false +} diff --git a/model.safetensors b/model.safetensors new file mode 100644 index 0000000..045b098 --- /dev/null +++ b/model.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:683b7242aa7d655d0e9ccaa7faf80b72c798c8ebe453837c41c0b845073a92d1 +size 1939548640 diff --git a/special_tokens_map.json b/special_tokens_map.json new file mode 100644 index 0000000..105d89f --- /dev/null +++ b/special_tokens_map.json @@ -0,0 +1,30 @@ +{ + "bos_token": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false + }, + "eos_token": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false + }, + "pad_token": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false + }, + "unk_token": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false + } +} diff --git a/tokenizer.json b/tokenizer.json new file mode 100644 index 0000000..2febb3c --- /dev/null +++ b/tokenizer.json @@ -0,0 +1,1755 @@ +{ + "version": "1.0", + "truncation": null, + "padding": null, + "added_tokens": [ + { + "id": 0, + "content": "", + "single_word": false, + "lstrip": false, + "rstrip": false, + "normalized": false, + "special": true + }, + { + "id": 1, + "content": "", + "single_word": false, + "lstrip": false, + "rstrip": false, + "normalized": false, + "special": true + }, + { + "id": 2, + "content": "", + "single_word": false, + "lstrip": false, + "rstrip": false, + "normalized": false, + "special": true + }, + { + "id": 3, + "content": "", + "single_word": false, + "lstrip": false, + "rstrip": false, + "normalized": false, + "special": true + }, + { + "id": 4, + "content": "[CH1-1]", + "single_word": false, + "lstrip": false, + "rstrip": false, + "normalized": true, + "special": false + }, + { + "id": 5, + "content": "[=S@@]", + "single_word": false, + "lstrip": false, + "rstrip": false, + "normalized": true, + "special": false + }, + { + "id": 6, + "content": "[/F]", + "single_word": false, + "lstrip": false, + "rstrip": false, + "normalized": true, + "special": false + }, + { + "id": 7, + "content": "[/123I]", + "single_word": false, + "lstrip": false, + "rstrip": false, + "normalized": true, + "special": false + }, + { + "id": 8, + "content": "[C-1]", + "single_word": false, + "lstrip": false, + "rstrip": false, + "normalized": true, + "special": false + }, + { + "id": 9, + "content": "[C@]", + "single_word": false, + "lstrip": false, + "rstrip": false, + "normalized": true, + "special": false + }, + { + "id": 10, + "content": "[/CH1]", + "single_word": false, + "lstrip": false, + "rstrip": false, + "normalized": true, + "special": false + }, + { + "id": 11, + "content": "[Cl]", + "single_word": false, + "lstrip": false, + "rstrip": false, + "normalized": true, + "special": false + }, + { + "id": 12, + "content": "[#Branch1]", + "single_word": false, + "lstrip": false, + "rstrip": false, + "normalized": true, + "special": false + }, + { + "id": 13, + "content": "[/C@@H1]", + "single_word": false, + "lstrip": false, + "rstrip": false, + "normalized": true, + "special": false + }, + { + "id": 14, + "content": "[/C@@]", + "single_word": false, + "lstrip": false, + "rstrip": false, + "normalized": true, + "special": false + }, + { + "id": 15, + "content": "[C@@H1]", + "single_word": false, + "lstrip": false, + "rstrip": false, + "normalized": true, + "special": false + }, + { + "id": 16, + "content": "[/P@@]", + "single_word": false, + "lstrip": false, + "rstrip": false, + "normalized": true, + "special": false + }, + { + "id": 17, + "content": "[B@@-1]", + "single_word": false, + "lstrip": false, + "rstrip": false, + "normalized": true, + "special": false + }, + { + "id": 18, + "content": "[\\O]", + "single_word": false, + "lstrip": false, + "rstrip": false, + "normalized": true, + "special": false + }, + { + "id": 19, + "content": "[N]", + "single_word": false, + "lstrip": false, + "rstrip": false, + "normalized": true, + "special": false + }, + { + "id": 20, + "content": "[O]", + "single_word": false, + "lstrip": false, + "rstrip": false, + "normalized": true, + "special": false + }, + { + "id": 21, + "content": "[/S@@+1]", + "single_word": false, + "lstrip": false, + "rstrip": false, + "normalized": true, + "special": false + }, + { + "id": 22, + "content": "[\\C@@H1]", + "single_word": false, + "lstrip": false, + "rstrip": false, + "normalized": true, + "special": false + }, + { + "id": 23, + "content": "[#N]", + "single_word": false, + "lstrip": false, + "rstrip": false, + "normalized": true, + "special": false + }, + { + "id": 24, + "content": "[/NH1]", + "single_word": false, + "lstrip": false, + "rstrip": false, + "normalized": true, + "special": false + }, + { + "id": 25, + "content": "[=B]", + "single_word": false, + "lstrip": false, + "rstrip": false, + "normalized": true, + "special": false + }, + { + "id": 26, + "content": "[\\F]", + "single_word": false, + "lstrip": false, + "rstrip": false, + "normalized": true, + "special": false + }, + { + "id": 27, + "content": "[=NH0]", + "single_word": false, + "lstrip": false, + "rstrip": false, + "normalized": true, + "special": false + }, + { + "id": 28, + "content": "[CH0]", + "single_word": false, + "lstrip": false, + "rstrip": false, + "normalized": true, + "special": false + }, + { + "id": 29, + "content": "[C@H1]", + "single_word": false, + "lstrip": false, + "rstrip": false, + "normalized": true, + "special": false + }, + { + "id": 30, + "content": "[=O]", + "single_word": false, + "lstrip": false, + "rstrip": false, + "normalized": true, + "special": false + }, + { + "id": 31, + "content": "[/C@]", + "single_word": false, + "lstrip": false, + "rstrip": false, + "normalized": true, + "special": false + }, + { + "id": 32, + "content": "[=P@@H1]", + "single_word": false, + "lstrip": false, + "rstrip": false, + "normalized": true, + "special": false + }, + { + "id": 33, + "content": "[=Branch1]", + "single_word": false, + "lstrip": false, + "rstrip": false, + "normalized": true, + "special": false + }, + { + "id": 34, + "content": "[-\\Ring2]", + "single_word": false, + "lstrip": false, + "rstrip": false, + "normalized": true, + "special": false + }, + { + "id": 35, + "content": "[=C]", + "single_word": false, + "lstrip": false, + "rstrip": false, + "normalized": true, + "special": false + }, + { + "id": 36, + "content": "[127I]", + "single_word": false, + "lstrip": false, + "rstrip": false, + "normalized": true, + "special": false + }, + { + "id": 37, + "content": "[\\Cl]", + "single_word": false, + "lstrip": false, + "rstrip": false, + "normalized": true, + "special": false + }, + { + "id": 38, + "content": "[/Si]", + "single_word": false, + "lstrip": false, + "rstrip": false, + "normalized": true, + "special": false + }, + { + "id": 39, + "content": "[125I]", + "single_word": false, + "lstrip": false, + "rstrip": false, + "normalized": true, + "special": false + }, + { + "id": 40, + "content": "[#S]", + "single_word": false, + "lstrip": false, + "rstrip": false, + "normalized": true, + "special": false + }, + { + "id": 41, + "content": "[CH1+1]", + "single_word": false, + "lstrip": false, + "rstrip": false, + "normalized": true, + "special": false + }, + { + "id": 42, + "content": "[=S@@+1]", + "single_word": false, + "lstrip": false, + "rstrip": false, + "normalized": true, + "special": false + }, + { + "id": 43, + "content": "[\\C]", + "single_word": false, + "lstrip": false, + "rstrip": false, + "normalized": true, + "special": false + }, + { + "id": 44, + "content": "[=S@]", + "single_word": false, + "lstrip": false, + "rstrip": false, + "normalized": true, + "special": false + }, + { + "id": 45, + "content": "[S@@H1]", + "single_word": false, + "lstrip": false, + "rstrip": false, + "normalized": true, + "special": false + }, + { + "id": 46, + "content": "[\\C@@]", + "single_word": false, + "lstrip": false, + "rstrip": false, + "normalized": true, + "special": false + }, + { + "id": 47, + "content": "[/S+1]", + "single_word": false, + "lstrip": false, + "rstrip": false, + "normalized": true, + "special": false + }, + { + "id": 48, + "content": "[\\S]", + "single_word": false, + "lstrip": false, + "rstrip": false, + "normalized": true, + "special": false + }, + { + "id": 49, + "content": "[\\C@H1]", + "single_word": false, + "lstrip": false, + "rstrip": false, + "normalized": true, + "special": false + }, + { + "id": 50, + "content": "[F+1]", + "single_word": false, + "lstrip": false, + "rstrip": false, + "normalized": true, + "special": false + }, + { + "id": 51, + "content": "[PH2]", + "single_word": false, + "lstrip": false, + "rstrip": false, + "normalized": true, + "special": false + }, + { + "id": 52, + "content": "[=Ring2]", + "single_word": false, + "lstrip": false, + "rstrip": false, + "normalized": true, + "special": false + }, + { + "id": 53, + "content": "[=P@@]", + "single_word": false, + "lstrip": false, + "rstrip": false, + "normalized": true, + "special": false + }, + { + "id": 54, + "content": "[BH1-1]", + "single_word": false, + "lstrip": false, + "rstrip": false, + "normalized": true, + "special": false + }, + { + "id": 55, + "content": "[/NH0]", + "single_word": false, + "lstrip": false, + "rstrip": false, + "normalized": true, + "special": false + }, + { + "id": 56, + "content": "[B@@H1-1]", + "single_word": false, + "lstrip": false, + "rstrip": false, + "normalized": true, + "special": false + }, + { + "id": 57, + "content": "[S@@+1]", + "single_word": false, + "lstrip": false, + "rstrip": false, + "normalized": true, + "special": false + }, + { + "id": 58, + "content": "[O-1]", + "single_word": false, + "lstrip": false, + "rstrip": false, + "normalized": true, + "special": false + }, + { + "id": 59, + "content": "[P@@]", + "single_word": false, + "lstrip": false, + "rstrip": false, + "normalized": true, + "special": false + }, + { + "id": 60, + "content": "[S]", + "single_word": false, + "lstrip": false, + "rstrip": false, + "normalized": true, + "special": false + }, + { + "id": 61, + "content": "[S+1]", + "single_word": false, + "lstrip": false, + "rstrip": false, + "normalized": true, + "special": false + }, + { + "id": 62, + "content": "[Br]", + "single_word": false, + "lstrip": false, + "rstrip": false, + "normalized": true, + "special": false + }, + { + "id": 63, + "content": "[I]", + "single_word": false, + "lstrip": false, + "rstrip": false, + "normalized": true, + "special": false + }, + { + "id": 64, + "content": "[\\B-1]", + "single_word": false, + "lstrip": false, + "rstrip": false, + "normalized": true, + "special": false + }, + { + "id": 65, + "content": "[C+1]", + "single_word": false, + "lstrip": false, + "rstrip": false, + "normalized": true, + "special": false + }, + { + "id": 66, + "content": "[F]", + "single_word": false, + "lstrip": false, + "rstrip": false, + "normalized": true, + "special": false + }, + { + "id": 67, + "content": "[/N]", + "single_word": false, + "lstrip": false, + "rstrip": false, + "normalized": true, + "special": false + }, + { + "id": 68, + "content": "[/C-1]", + "single_word": false, + "lstrip": false, + "rstrip": false, + "normalized": true, + "special": false + }, + { + "id": 69, + "content": "[/O]", + "single_word": false, + "lstrip": false, + "rstrip": false, + "normalized": true, + "special": false + }, + { + "id": 70, + "content": "[Ring1]", + "single_word": false, + "lstrip": false, + "rstrip": false, + "normalized": true, + "special": false + }, + { + "id": 71, + "content": "[OH0]", + "single_word": false, + "lstrip": false, + "rstrip": false, + "normalized": true, + "special": false + }, + { + "id": 72, + "content": "[S@+1]", + "single_word": false, + "lstrip": false, + "rstrip": false, + "normalized": true, + "special": false + }, + { + "id": 73, + "content": "[=S]", + "single_word": false, + "lstrip": false, + "rstrip": false, + "normalized": true, + "special": false + }, + { + "id": 74, + "content": "[\\P]", + "single_word": false, + "lstrip": false, + "rstrip": false, + "normalized": true, + "special": false + }, + { + "id": 75, + "content": "[BH3-1]", + "single_word": false, + "lstrip": false, + "rstrip": false, + "normalized": true, + "special": false + }, + { + "id": 76, + "content": "[18OH1]", + "single_word": false, + "lstrip": false, + "rstrip": false, + "normalized": true, + "special": false + }, + { + "id": 77, + "content": "[/S@]", + "single_word": false, + "lstrip": false, + "rstrip": false, + "normalized": true, + "special": false + }, + { + "id": 78, + "content": "[=CH0]", + "single_word": false, + "lstrip": false, + "rstrip": false, + "normalized": true, + "special": false + }, + { + "id": 79, + "content": "[/P]", + "single_word": false, + "lstrip": false, + "rstrip": false, + "normalized": true, + "special": false + }, + { + "id": 80, + "content": "[P]", + "single_word": false, + "lstrip": false, + "rstrip": false, + "normalized": true, + "special": false + }, + { + "id": 81, + "content": "[P@H1]", + "single_word": false, + "lstrip": false, + "rstrip": false, + "normalized": true, + "special": false + }, + { + "id": 82, + "content": "[P+1]", + "single_word": false, + "lstrip": false, + "rstrip": false, + "normalized": true, + "special": false + }, + { + "id": 83, + "content": "[/I]", + "single_word": false, + "lstrip": false, + "rstrip": false, + "normalized": true, + "special": false + }, + { + "id": 84, + "content": "[N-1]", + "single_word": false, + "lstrip": false, + "rstrip": false, + "normalized": true, + "special": false + }, + { + "id": 85, + "content": "[O+1]", + "single_word": false, + "lstrip": false, + "rstrip": false, + "normalized": true, + "special": false + }, + { + "id": 86, + "content": "[=P]", + "single_word": false, + "lstrip": false, + "rstrip": false, + "normalized": true, + "special": false + }, + { + "id": 87, + "content": "[#P]", + "single_word": false, + "lstrip": false, + "rstrip": false, + "normalized": true, + "special": false + }, + { + "id": 88, + "content": "[/CH1-1]", + "single_word": false, + "lstrip": false, + "rstrip": false, + "normalized": true, + "special": false + }, + { + "id": 89, + "content": "[\\123I]", + "single_word": false, + "lstrip": false, + "rstrip": false, + "normalized": true, + "special": false + }, + { + "id": 90, + "content": "[Ring2]", + "single_word": false, + "lstrip": false, + "rstrip": false, + "normalized": true, + "special": false + }, + { + "id": 91, + "content": "[BH2-1]", + "single_word": false, + "lstrip": false, + "rstrip": false, + "normalized": true, + "special": false + }, + { + "id": 92, + "content": "[\\N+1]", + "single_word": false, + "lstrip": false, + "rstrip": false, + "normalized": true, + "special": false + }, + { + "id": 93, + "content": "[S@]", + "single_word": false, + "lstrip": false, + "rstrip": false, + "normalized": true, + "special": false + }, + { + "id": 94, + "content": "[P@@+1]", + "single_word": false, + "lstrip": false, + "rstrip": false, + "normalized": true, + "special": false + }, + { + "id": 95, + "content": "[\\S+1]", + "single_word": false, + "lstrip": false, + "rstrip": false, + "normalized": true, + "special": false + }, + { + "id": 96, + "content": "[=O+1]", + "single_word": false, + "lstrip": false, + "rstrip": false, + "normalized": true, + "special": false + }, + { + "id": 97, + "content": "[18F]", + "single_word": false, + "lstrip": false, + "rstrip": false, + "normalized": true, + "special": false + }, + { + "id": 98, + "content": "[=P+1]", + "single_word": false, + "lstrip": false, + "rstrip": false, + "normalized": true, + "special": false + }, + { + "id": 99, + "content": "[SnH2]", + "single_word": false, + "lstrip": false, + "rstrip": false, + "normalized": true, + "special": false + }, + { + "id": 100, + "content": "[=Branch2]", + "single_word": false, + "lstrip": false, + "rstrip": false, + "normalized": true, + "special": false + }, + { + "id": 101, + "content": "[SH2]", + "single_word": false, + "lstrip": false, + "rstrip": false, + "normalized": true, + "special": false + }, + { + "id": 102, + "content": "[SH3]", + "single_word": false, + "lstrip": false, + "rstrip": false, + "normalized": true, + "special": false + }, + { + "id": 103, + "content": "[\\NH1]", + "single_word": false, + "lstrip": false, + "rstrip": false, + "normalized": true, + "special": false + }, + { + "id": 104, + "content": "[Branch1]", + "single_word": false, + "lstrip": false, + "rstrip": false, + "normalized": true, + "special": false + }, + { + "id": 105, + "content": "[=N]", + "single_word": false, + "lstrip": false, + "rstrip": false, + "normalized": true, + "special": false + }, + { + "id": 106, + "content": "[=S@@H1]", + "single_word": false, + "lstrip": false, + "rstrip": false, + "normalized": true, + "special": false + }, + { + "id": 107, + "content": "[11CH3]", + "single_word": false, + "lstrip": false, + "rstrip": false, + "normalized": true, + "special": false + }, + { + "id": 108, + "content": "[B]", + "single_word": false, + "lstrip": false, + "rstrip": false, + "normalized": true, + "special": false + }, + { + "id": 109, + "content": "[SnH1]", + "single_word": false, + "lstrip": false, + "rstrip": false, + "normalized": true, + "special": false + }, + { + "id": 110, + "content": "[CH2-1]", + "single_word": false, + "lstrip": false, + "rstrip": false, + "normalized": true, + "special": false + }, + { + "id": 111, + "content": "[N@+1]", + "single_word": false, + "lstrip": false, + "rstrip": false, + "normalized": true, + "special": false + }, + { + "id": 112, + "content": "[/S]", + "single_word": false, + "lstrip": false, + "rstrip": false, + "normalized": true, + "special": false + }, + { + "id": 113, + "content": "[\\P@@]", + "single_word": false, + "lstrip": false, + "rstrip": false, + "normalized": true, + "special": false + }, + { + "id": 114, + "content": "[Sn]", + "single_word": false, + "lstrip": false, + "rstrip": false, + "normalized": true, + "special": false + }, + { + "id": 115, + "content": "[CH1]", + "single_word": false, + "lstrip": false, + "rstrip": false, + "normalized": true, + "special": false + }, + { + "id": 116, + "content": "[\\S@]", + "single_word": false, + "lstrip": false, + "rstrip": false, + "normalized": true, + "special": false + }, + { + "id": 117, + "content": "[=SH1]", + "single_word": false, + "lstrip": false, + "rstrip": false, + "normalized": true, + "special": false + }, + { + "id": 118, + "content": "[/C]", + "single_word": false, + "lstrip": false, + "rstrip": false, + "normalized": true, + "special": false + }, + { + "id": 119, + "content": "[Si]", + "single_word": false, + "lstrip": false, + "rstrip": false, + "normalized": true, + "special": false + }, + { + "id": 120, + "content": "[#N+1]", + "single_word": false, + "lstrip": false, + "rstrip": false, + "normalized": true, + "special": false + }, + { + "id": 121, + "content": "[B@H1-1]", + "single_word": false, + "lstrip": false, + "rstrip": false, + "normalized": true, + "special": false + }, + { + "id": 122, + "content": "[B-1]", + "single_word": false, + "lstrip": false, + "rstrip": false, + "normalized": true, + "special": false + }, + { + "id": 123, + "content": "[SH1]", + "single_word": false, + "lstrip": false, + "rstrip": false, + "normalized": true, + "special": false + }, + { + "id": 124, + "content": "[123I]", + "single_word": false, + "lstrip": false, + "rstrip": false, + "normalized": true, + "special": false + }, + { + "id": 125, + "content": "[/B]", + "single_word": false, + "lstrip": false, + "rstrip": false, + "normalized": true, + "special": false + }, + { + "id": 126, + "content": "[/CH0]", + "single_word": false, + "lstrip": false, + "rstrip": false, + "normalized": true, + "special": false + }, + { + "id": 127, + "content": "[\\C-1]", + "single_word": false, + "lstrip": false, + "rstrip": false, + "normalized": true, + "special": false + }, + { + "id": 128, + "content": "[#Ring1]", + "single_word": false, + "lstrip": false, + "rstrip": false, + "normalized": true, + "special": false + }, + { + "id": 129, + "content": "[-/Ring1]", + "single_word": false, + "lstrip": false, + "rstrip": false, + "normalized": true, + "special": false + }, + { + "id": 130, + "content": "[NH1]", + "single_word": false, + "lstrip": false, + "rstrip": false, + "normalized": true, + "special": false + }, + { + "id": 131, + "content": "[N@@+1]", + "single_word": false, + "lstrip": false, + "rstrip": false, + "normalized": true, + "special": false + }, + { + "id": 132, + "content": "[=PH1]", + "single_word": false, + "lstrip": false, + "rstrip": false, + "normalized": true, + "special": false + }, + { + "id": 133, + "content": "[=S+1]", + "single_word": false, + "lstrip": false, + "rstrip": false, + "normalized": true, + "special": false + }, + { + "id": 134, + "content": "[PH1]", + "single_word": false, + "lstrip": false, + "rstrip": false, + "normalized": true, + "special": false + }, + { + "id": 135, + "content": "[Sn+3]", + "single_word": false, + "lstrip": false, + "rstrip": false, + "normalized": true, + "special": false + }, + { + "id": 136, + "content": "[124I]", + "single_word": false, + "lstrip": false, + "rstrip": false, + "normalized": true, + "special": false + }, + { + "id": 137, + "content": "[3H]", + "single_word": false, + "lstrip": false, + "rstrip": false, + "normalized": true, + "special": false + }, + { + "id": 138, + "content": "[\\N]", + "single_word": false, + "lstrip": false, + "rstrip": false, + "normalized": true, + "special": false + }, + { + "id": 139, + "content": "[C]", + "single_word": false, + "lstrip": false, + "rstrip": false, + "normalized": true, + "special": false + }, + { + "id": 140, + "content": "[Branch2]", + "single_word": false, + "lstrip": false, + "rstrip": false, + "normalized": true, + "special": false + }, + { + "id": 141, + "content": "[\\O-1]", + "single_word": false, + "lstrip": false, + "rstrip": false, + "normalized": true, + "special": false + }, + { + "id": 142, + "content": "[\\Br]", + "single_word": false, + "lstrip": false, + "rstrip": false, + "normalized": true, + "special": false + }, + { + "id": 143, + "content": "[17F]", + "single_word": false, + "lstrip": false, + "rstrip": false, + "normalized": true, + "special": false + }, + { + "id": 144, + "content": "[=N+1]", + "single_word": false, + "lstrip": false, + "rstrip": false, + "normalized": true, + "special": false + }, + { + "id": 145, + "content": "[\\C@]", + "single_word": false, + "lstrip": false, + "rstrip": false, + "normalized": true, + "special": false + }, + { + "id": 146, + "content": "[CH2]", + "single_word": false, + "lstrip": false, + "rstrip": false, + "normalized": true, + "special": false + }, + { + "id": 147, + "content": "[=P@H1]", + "single_word": false, + "lstrip": false, + "rstrip": false, + "normalized": true, + "special": false + }, + { + "id": 148, + "content": "[NH0]", + "single_word": false, + "lstrip": false, + "rstrip": false, + "normalized": true, + "special": false + }, + { + "id": 149, + "content": "[/Br]", + "single_word": false, + "lstrip": false, + "rstrip": false, + "normalized": true, + "special": false + }, + { + "id": 150, + "content": "[N+1]", + "single_word": false, + "lstrip": false, + "rstrip": false, + "normalized": true, + "special": false + }, + { + "id": 151, + "content": "[\\SH1]", + "single_word": false, + "lstrip": false, + "rstrip": false, + "normalized": true, + "special": false + }, + { + "id": 152, + "content": "[/N+1]", + "single_word": false, + "lstrip": false, + "rstrip": false, + "normalized": true, + "special": false + }, + { + "id": 153, + "content": "[\\CH1-1]", + "single_word": false, + "lstrip": false, + "rstrip": false, + "normalized": true, + "special": false + }, + { + "id": 154, + "content": "[S@@]", + "single_word": false, + "lstrip": false, + "rstrip": false, + "normalized": true, + "special": false + }, + { + "id": 155, + "content": "[/Cl]", + "single_word": false, + "lstrip": false, + "rstrip": false, + "normalized": true, + "special": false + }, + { + "id": 156, + "content": "[-/Ring2]", + "single_word": false, + "lstrip": false, + "rstrip": false, + "normalized": true, + "special": false + }, + { + "id": 157, + "content": "[=P@]", + "single_word": false, + "lstrip": false, + "rstrip": false, + "normalized": true, + "special": false + }, + { + "id": 158, + "content": "[P@+1]", + "single_word": false, + "lstrip": false, + "rstrip": false, + "normalized": true, + "special": false + }, + { + "id": 159, + "content": "[\\B]", + "single_word": false, + "lstrip": false, + "rstrip": false, + "normalized": true, + "special": false + }, + { + "id": 160, + "content": "[/S@@]", + "single_word": false, + "lstrip": false, + "rstrip": false, + "normalized": true, + "special": false + }, + { + "id": 161, + "content": "[=N-1]", + "single_word": false, + "lstrip": false, + "rstrip": false, + "normalized": true, + "special": false + }, + { + "id": 162, + "content": "[N@@H1+1]", + "single_word": false, + "lstrip": false, + "rstrip": false, + "normalized": true, + "special": false + }, + { + "id": 163, + "content": "[=Ring1]", + "single_word": false, + "lstrip": false, + "rstrip": false, + "normalized": true, + "special": false + }, + { + "id": 164, + "content": "[-\\Ring1]", + "single_word": false, + "lstrip": false, + "rstrip": false, + "normalized": true, + "special": false + }, + { + "id": 165, + "content": "[#C]", + "single_word": false, + "lstrip": false, + "rstrip": false, + "normalized": true, + "special": false + }, + { + "id": 166, + "content": "[Br+1]", + "single_word": false, + "lstrip": false, + "rstrip": false, + "normalized": true, + "special": false + }, + { + "id": 167, + "content": "[=S@+1]", + "single_word": false, + "lstrip": false, + "rstrip": false, + "normalized": true, + "special": false + }, + { + "id": 168, + "content": "[\\Si]", + "single_word": false, + "lstrip": false, + "rstrip": false, + "normalized": true, + "special": false + }, + { + "id": 169, + "content": "[\\S@@+1]", + "single_word": false, + "lstrip": false, + "rstrip": false, + "normalized": true, + "special": false + }, + { + "id": 170, + "content": "[P@@H1]", + "single_word": false, + "lstrip": false, + "rstrip": false, + "normalized": true, + "special": false + }, + { + "id": 171, + "content": "[/O-1]", + "single_word": false, + "lstrip": false, + "rstrip": false, + "normalized": true, + "special": false + }, + { + "id": 172, + "content": "[\\I]", + "single_word": false, + "lstrip": false, + "rstrip": false, + "normalized": true, + "special": false + }, + { + "id": 173, + "content": "[C@@]", + "single_word": false, + "lstrip": false, + "rstrip": false, + "normalized": true, + "special": false + }, + { + "id": 174, + "content": "[/OH0]", + "single_word": false, + "lstrip": false, + "rstrip": false, + "normalized": true, + "special": false + }, + { + "id": 175, + "content": "[P@]", + "single_word": false, + "lstrip": false, + "rstrip": false, + "normalized": true, + "special": false + }, + { + "id": 176, + "content": "[\\CH0]", + "single_word": false, + "lstrip": false, + "rstrip": false, + "normalized": true, + "special": false + }, + { + "id": 177, + "content": "[/C@H1]", + "single_word": false, + "lstrip": false, + "rstrip": false, + "normalized": true, + "special": false + }, + { + "id": 178, + "content": "[#Branch2]", + "single_word": false, + "lstrip": false, + "rstrip": false, + "normalized": true, + "special": false + }, + { + "id": 179, + "content": "[B@-1]", + "single_word": false, + "lstrip": false, + "rstrip": false, + "normalized": true, + "special": false + }, + { + "id": 180, + "content": "[\\S@@]", + "single_word": false, + "lstrip": false, + "rstrip": false, + "normalized": true, + "special": false + }, + { + "id": 181, + "content": "[#C-1]", + "single_word": false, + "lstrip": false, + "rstrip": false, + "normalized": true, + "special": false + }, + { + "id": 182, + "content": "[SH0]", + "single_word": false, + "lstrip": false, + "rstrip": false, + "normalized": true, + "special": false + }, + { + "id": 183, + "content": "[Sn+2]", + "single_word": false, + "lstrip": false, + "rstrip": false, + "normalized": true, + "special": false + }, + { + "id": 184, + "content": "", + "single_word": false, + "lstrip": true, + "rstrip": false, + "normalized": true, + "special": true + } + ], + "normalizer": null, + "pre_tokenizer": { + "type": "ByteLevel", + "add_prefix_space": false, + "trim_offsets": true, + "use_regex": true + }, + "post_processor": { + "type": "TemplateProcessing", + "single": [ + { + "Sequence": { + "id": "A", + "type_id": 0 + } + }, + { + "SpecialToken": { + "id": "", + "type_id": 0 + } + } + ], + "pair": [ + { + "Sequence": { + "id": "A", + "type_id": 0 + } + }, + { + "SpecialToken": { + "id": "", + "type_id": 0 + } + }, + { + "Sequence": { + "id": "B", + "type_id": 1 + } + }, + { + "SpecialToken": { + "id": "", + "type_id": 1 + } + } + ], + "special_tokens": { + "": { + "id": "", + "ids": [ + 0 + ], + "tokens": [ + "" + ] + } + } + }, + "decoder": { + "type": "ByteLevel", + "add_prefix_space": true, + "trim_offsets": true, + "use_regex": true + }, + "model": { + "type": "BPE", + "dropout": null, + "unk_token": null, + "continuing_subword_prefix": "", + "end_of_word_suffix": "", + "fuse_unk": false, + "byte_fallback": false, + "vocab": { + "": 0, + "": 1, + "": 2, + "": 3 + }, + "merges": [] + } +} \ No newline at end of file diff --git a/tokenizer_config.json b/tokenizer_config.json new file mode 100644 index 0000000..b012bc9 --- /dev/null +++ b/tokenizer_config.json @@ -0,0 +1,1495 @@ +{ + "add_bos_token": false, + "add_eos_token": true, + "added_tokens_decoder": { + "0": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "1": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "2": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "3": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "4": { + "content": "[CH1-1]", + "lstrip": false, + "normalized": true, + "rstrip": false, + "single_word": false, + "special": false + }, + "5": { + "content": "[=S@@]", + "lstrip": false, + "normalized": true, + "rstrip": false, + "single_word": false, + "special": false + }, + "6": { + "content": "[/F]", + "lstrip": false, + "normalized": true, + "rstrip": false, + "single_word": false, + "special": false + }, + "7": { + "content": "[/123I]", + "lstrip": false, + "normalized": true, + "rstrip": false, + "single_word": false, + "special": false + }, + "8": { + "content": "[C-1]", + "lstrip": false, + "normalized": true, + "rstrip": false, + "single_word": false, + "special": false + }, + "9": { + "content": "[C@]", + "lstrip": false, + "normalized": true, + "rstrip": false, + "single_word": false, + "special": false + }, + "10": { + "content": "[/CH1]", + "lstrip": false, + "normalized": true, + "rstrip": false, + "single_word": false, + "special": false + }, + "11": { + "content": "[Cl]", + "lstrip": false, + "normalized": true, + "rstrip": false, + "single_word": false, + "special": false + }, + "12": { + "content": "[#Branch1]", + "lstrip": false, + "normalized": true, + "rstrip": false, + "single_word": false, + "special": false + }, + "13": { + "content": "[/C@@H1]", + "lstrip": false, + "normalized": true, + "rstrip": false, + "single_word": false, + "special": false + }, + "14": { + "content": "[/C@@]", + "lstrip": false, + "normalized": true, + "rstrip": false, + "single_word": false, + "special": false + }, + "15": { + "content": "[C@@H1]", + "lstrip": false, + "normalized": true, + "rstrip": false, + "single_word": false, + "special": false + }, + "16": { + "content": "[/P@@]", + "lstrip": false, + "normalized": true, + "rstrip": false, + "single_word": false, + "special": false + }, + "17": { + "content": "[B@@-1]", + "lstrip": false, + "normalized": true, + "rstrip": false, + "single_word": false, + "special": false + }, + "18": { + "content": "[\\O]", + "lstrip": false, + "normalized": true, + "rstrip": false, + "single_word": false, + "special": false + }, + "19": { + "content": "[N]", + "lstrip": false, + "normalized": true, + "rstrip": false, + "single_word": false, + "special": false + }, + "20": { + "content": "[O]", + "lstrip": false, + "normalized": true, + "rstrip": false, + "single_word": false, + "special": false + }, + "21": { + "content": "[/S@@+1]", + "lstrip": false, + "normalized": true, + "rstrip": false, + "single_word": false, + "special": false + }, + "22": { + "content": "[\\C@@H1]", + "lstrip": false, + "normalized": true, + "rstrip": false, + "single_word": false, + "special": false + }, + "23": { + "content": "[#N]", + "lstrip": false, + "normalized": true, + "rstrip": false, + "single_word": false, + "special": false + }, + "24": { + "content": "[/NH1]", + "lstrip": false, + "normalized": true, + "rstrip": false, + "single_word": false, + "special": false + }, + "25": { + "content": "[=B]", + "lstrip": false, + "normalized": true, + "rstrip": false, + "single_word": false, + "special": false + }, + "26": { + "content": "[\\F]", + "lstrip": false, + "normalized": true, + "rstrip": false, + "single_word": false, + "special": false + }, + "27": { + "content": "[=NH0]", + "lstrip": false, + "normalized": true, + "rstrip": false, + "single_word": false, + "special": false + }, + "28": { + "content": "[CH0]", + "lstrip": false, + "normalized": true, + "rstrip": false, + "single_word": false, + "special": false + }, + "29": { + "content": "[C@H1]", + "lstrip": false, + "normalized": true, + "rstrip": false, + "single_word": false, + "special": false + }, + "30": { + "content": "[=O]", + "lstrip": false, + "normalized": true, + "rstrip": false, + "single_word": false, + "special": false + }, + "31": { + "content": "[/C@]", + "lstrip": false, + "normalized": true, + "rstrip": false, + "single_word": false, + "special": false + }, + "32": { + "content": "[=P@@H1]", + "lstrip": false, + "normalized": true, + "rstrip": false, + "single_word": false, + "special": false + }, + "33": { + "content": "[=Branch1]", + "lstrip": false, + "normalized": true, + "rstrip": false, + "single_word": false, + "special": false + }, + "34": { + "content": "[-\\Ring2]", + "lstrip": false, + "normalized": true, + "rstrip": false, + "single_word": false, + "special": false + }, + "35": { + "content": "[=C]", + "lstrip": false, + "normalized": true, + "rstrip": false, + "single_word": false, + "special": false + }, + "36": { + "content": "[127I]", + "lstrip": false, + "normalized": true, + "rstrip": false, + "single_word": false, + "special": false + }, + "37": { + "content": "[\\Cl]", + "lstrip": false, + "normalized": true, + "rstrip": false, + "single_word": false, + "special": false + }, + "38": { + "content": "[/Si]", + "lstrip": false, + "normalized": true, + "rstrip": false, + "single_word": false, + "special": false + }, + "39": { + "content": "[125I]", + "lstrip": false, + "normalized": true, + "rstrip": false, + "single_word": false, + "special": false + }, + "40": { + "content": "[#S]", + "lstrip": false, + "normalized": true, + "rstrip": false, + "single_word": false, + "special": false + }, + "41": { + "content": "[CH1+1]", + "lstrip": false, + "normalized": true, + "rstrip": false, + "single_word": false, + "special": false + }, + "42": { + "content": "[=S@@+1]", + "lstrip": false, + "normalized": true, + "rstrip": false, + "single_word": false, + "special": false + }, + "43": { + "content": "[\\C]", + "lstrip": false, + "normalized": true, + "rstrip": false, + "single_word": false, + "special": false + }, + "44": { + "content": "[=S@]", + "lstrip": false, + "normalized": true, + "rstrip": false, + "single_word": false, + "special": false + }, + "45": { + "content": "[S@@H1]", + "lstrip": false, + "normalized": true, + "rstrip": false, + "single_word": false, + "special": false + }, + "46": { + "content": "[\\C@@]", + "lstrip": false, + "normalized": true, + "rstrip": false, + "single_word": false, + "special": false + }, + "47": { + "content": "[/S+1]", + "lstrip": false, + "normalized": true, + "rstrip": false, + "single_word": false, + "special": false + }, + "48": { + "content": "[\\S]", + "lstrip": false, + "normalized": true, + "rstrip": false, + "single_word": false, + "special": false + }, + "49": { + "content": "[\\C@H1]", + "lstrip": false, + "normalized": true, + "rstrip": false, + "single_word": false, + "special": false + }, + "50": { + "content": "[F+1]", + "lstrip": false, + "normalized": true, + "rstrip": false, + "single_word": false, + "special": false + }, + "51": { + "content": "[PH2]", + "lstrip": false, + "normalized": true, + "rstrip": false, + "single_word": false, + "special": false + }, + "52": { + "content": "[=Ring2]", + "lstrip": false, + "normalized": true, + "rstrip": false, + "single_word": false, + "special": false + }, + "53": { + "content": "[=P@@]", + "lstrip": false, + "normalized": true, + "rstrip": false, + "single_word": false, + "special": false + }, + "54": { + "content": "[BH1-1]", + "lstrip": false, + "normalized": true, + "rstrip": false, + "single_word": false, + "special": false + }, + "55": { + "content": "[/NH0]", + "lstrip": false, + "normalized": true, + "rstrip": false, + "single_word": false, + "special": false + }, + "56": { + "content": "[B@@H1-1]", + "lstrip": false, + "normalized": true, + "rstrip": false, + "single_word": false, + "special": false + }, + "57": { + "content": "[S@@+1]", + "lstrip": false, + "normalized": true, + "rstrip": false, + "single_word": false, + "special": false + }, + "58": { + "content": "[O-1]", + "lstrip": false, + "normalized": true, + "rstrip": false, + "single_word": false, + "special": false + }, + "59": { + "content": "[P@@]", + "lstrip": false, + "normalized": true, + "rstrip": false, + "single_word": false, + "special": false + }, + "60": { + "content": "[S]", + "lstrip": false, + "normalized": true, + "rstrip": false, + "single_word": false, + "special": false + }, + "61": { + "content": "[S+1]", + "lstrip": false, + "normalized": true, + "rstrip": false, + "single_word": false, + "special": false + }, + "62": { + "content": "[Br]", + "lstrip": false, + "normalized": true, + "rstrip": false, + "single_word": false, + "special": false + }, + "63": { + "content": "[I]", + "lstrip": false, + "normalized": true, + "rstrip": false, + "single_word": false, + "special": false + }, + "64": { + "content": "[\\B-1]", + "lstrip": false, + "normalized": true, + "rstrip": false, + "single_word": false, + "special": false + }, + "65": { + "content": "[C+1]", + "lstrip": false, + "normalized": true, + "rstrip": false, + "single_word": false, + "special": false + }, + "66": { + "content": "[F]", + "lstrip": false, + "normalized": true, + "rstrip": false, + "single_word": false, + "special": false + }, + "67": { + "content": "[/N]", + "lstrip": false, + "normalized": true, + "rstrip": false, + "single_word": false, + "special": false + }, + "68": { + "content": "[/C-1]", + "lstrip": false, + "normalized": true, + "rstrip": false, + "single_word": false, + "special": false + }, + "69": { + "content": "[/O]", + "lstrip": false, + "normalized": true, + "rstrip": false, + "single_word": false, + "special": false + }, + "70": { + "content": "[Ring1]", + "lstrip": false, + "normalized": true, + "rstrip": false, + "single_word": false, + "special": false + }, + "71": { + "content": "[OH0]", + "lstrip": false, + "normalized": true, + "rstrip": false, + "single_word": false, + "special": false + }, + "72": { + "content": "[S@+1]", + "lstrip": false, + "normalized": true, + "rstrip": false, + "single_word": false, + "special": false + }, + "73": { + "content": "[=S]", + "lstrip": false, + "normalized": true, + "rstrip": false, + "single_word": false, + "special": false + }, + "74": { + "content": "[\\P]", + "lstrip": false, + "normalized": true, + "rstrip": false, + "single_word": false, + "special": false + }, + "75": { + "content": "[BH3-1]", + "lstrip": false, + "normalized": true, + "rstrip": false, + "single_word": false, + "special": false + }, + "76": { + "content": "[18OH1]", + "lstrip": false, + "normalized": true, + "rstrip": false, + "single_word": false, + "special": false + }, + "77": { + "content": "[/S@]", + "lstrip": false, + "normalized": true, + "rstrip": false, + "single_word": false, + "special": false + }, + "78": { + "content": "[=CH0]", + "lstrip": false, + "normalized": true, + "rstrip": false, + "single_word": false, + "special": false + }, + "79": { + "content": "[/P]", + "lstrip": false, + "normalized": true, + "rstrip": false, + "single_word": false, + "special": false + }, + "80": { + "content": "[P]", + "lstrip": false, + "normalized": true, + "rstrip": false, + "single_word": false, + "special": false + }, + "81": { + "content": "[P@H1]", + "lstrip": false, + "normalized": true, + "rstrip": false, + "single_word": false, + "special": false + }, + "82": { + "content": "[P+1]", + "lstrip": false, + "normalized": true, + "rstrip": false, + "single_word": false, + "special": false + }, + "83": { + "content": "[/I]", + "lstrip": false, + "normalized": true, + "rstrip": false, + "single_word": false, + "special": false + }, + "84": { + "content": "[N-1]", + "lstrip": false, + "normalized": true, + "rstrip": false, + "single_word": false, + "special": false + }, + "85": { + "content": "[O+1]", + "lstrip": false, + "normalized": true, + "rstrip": false, + "single_word": false, + "special": false + }, + "86": { + "content": "[=P]", + "lstrip": false, + "normalized": true, + "rstrip": false, + "single_word": false, + "special": false + }, + "87": { + "content": "[#P]", + "lstrip": false, + "normalized": true, + "rstrip": false, + "single_word": false, + "special": false + }, + "88": { + "content": "[/CH1-1]", + "lstrip": false, + "normalized": true, + "rstrip": false, + "single_word": false, + "special": false + }, + "89": { + "content": "[\\123I]", + "lstrip": false, + "normalized": true, + "rstrip": false, + "single_word": false, + "special": false + }, + "90": { + "content": "[Ring2]", + "lstrip": false, + "normalized": true, + "rstrip": false, + "single_word": false, + "special": false + }, + "91": { + "content": "[BH2-1]", + "lstrip": false, + "normalized": true, + "rstrip": false, + "single_word": false, + "special": false + }, + "92": { + "content": "[\\N+1]", + "lstrip": false, + "normalized": true, + "rstrip": false, + "single_word": false, + "special": false + }, + "93": { + "content": "[S@]", + "lstrip": false, + "normalized": true, + "rstrip": false, + "single_word": false, + "special": false + }, + "94": { + "content": "[P@@+1]", + "lstrip": false, + "normalized": true, + "rstrip": false, + "single_word": false, + "special": false + }, + "95": { + "content": "[\\S+1]", + "lstrip": false, + "normalized": true, + "rstrip": false, + "single_word": false, + "special": false + }, + "96": { + "content": "[=O+1]", + "lstrip": false, + "normalized": true, + "rstrip": false, + "single_word": false, + "special": false + }, + "97": { + "content": "[18F]", + "lstrip": false, + "normalized": true, + "rstrip": false, + "single_word": false, + "special": false + }, + "98": { + "content": "[=P+1]", + "lstrip": false, + "normalized": true, + "rstrip": false, + "single_word": false, + "special": false + }, + "99": { + "content": "[SnH2]", + "lstrip": false, + "normalized": true, + "rstrip": false, + "single_word": false, + "special": false + }, + "100": { + "content": "[=Branch2]", + "lstrip": false, + "normalized": true, + "rstrip": false, + "single_word": false, + "special": false + }, + "101": { + "content": "[SH2]", + "lstrip": false, + "normalized": true, + "rstrip": false, + "single_word": false, + "special": false + }, + "102": { + "content": "[SH3]", + "lstrip": false, + "normalized": true, + "rstrip": false, + "single_word": false, + "special": false + }, + "103": { + "content": "[\\NH1]", + "lstrip": false, + "normalized": true, + "rstrip": false, + "single_word": false, + "special": false + }, + "104": { + "content": "[Branch1]", + "lstrip": false, + "normalized": true, + "rstrip": false, + "single_word": false, + "special": false + }, + "105": { + "content": "[=N]", + "lstrip": false, + "normalized": true, + "rstrip": false, + "single_word": false, + "special": false + }, + "106": { + "content": "[=S@@H1]", + "lstrip": false, + "normalized": true, + "rstrip": false, + "single_word": false, + "special": false + }, + "107": { + "content": "[11CH3]", + "lstrip": false, + "normalized": true, + "rstrip": false, + "single_word": false, + "special": false + }, + "108": { + "content": "[B]", + "lstrip": false, + "normalized": true, + "rstrip": false, + "single_word": false, + "special": false + }, + "109": { + "content": "[SnH1]", + "lstrip": false, + "normalized": true, + "rstrip": false, + "single_word": false, + "special": false + }, + "110": { + "content": "[CH2-1]", + "lstrip": false, + "normalized": true, + "rstrip": false, + "single_word": false, + "special": false + }, + "111": { + "content": "[N@+1]", + "lstrip": false, + "normalized": true, + "rstrip": false, + "single_word": false, + "special": false + }, + "112": { + "content": "[/S]", + "lstrip": false, + "normalized": true, + "rstrip": false, + "single_word": false, + "special": false + }, + "113": { + "content": "[\\P@@]", + "lstrip": false, + "normalized": true, + "rstrip": false, + "single_word": false, + "special": false + }, + "114": { + "content": "[Sn]", + "lstrip": false, + "normalized": true, + "rstrip": false, + "single_word": false, + "special": false + }, + "115": { + "content": "[CH1]", + "lstrip": false, + "normalized": true, + "rstrip": false, + "single_word": false, + "special": false + }, + "116": { + "content": "[\\S@]", + "lstrip": false, + "normalized": true, + "rstrip": false, + "single_word": false, + "special": false + }, + "117": { + "content": "[=SH1]", + "lstrip": false, + "normalized": true, + "rstrip": false, + "single_word": false, + "special": false + }, + "118": { + "content": "[/C]", + "lstrip": false, + "normalized": true, + "rstrip": false, + "single_word": false, + "special": false + }, + "119": { + "content": "[Si]", + "lstrip": false, + "normalized": true, + "rstrip": false, + "single_word": false, + "special": false + }, + "120": { + "content": "[#N+1]", + "lstrip": false, + "normalized": true, + "rstrip": false, + "single_word": false, + "special": false + }, + "121": { + "content": "[B@H1-1]", + "lstrip": false, + "normalized": true, + "rstrip": false, + "single_word": false, + "special": false + }, + "122": { + "content": "[B-1]", + "lstrip": false, + "normalized": true, + "rstrip": false, + "single_word": false, + "special": false + }, + "123": { + "content": "[SH1]", + "lstrip": false, + "normalized": true, + "rstrip": false, + "single_word": false, + "special": false + }, + "124": { + "content": "[123I]", + "lstrip": false, + "normalized": true, + "rstrip": false, + "single_word": false, + "special": false + }, + "125": { + "content": "[/B]", + "lstrip": false, + "normalized": true, + "rstrip": false, + "single_word": false, + "special": false + }, + "126": { + "content": "[/CH0]", + "lstrip": false, + "normalized": true, + "rstrip": false, + "single_word": false, + "special": false + }, + "127": { + "content": "[\\C-1]", + "lstrip": false, + "normalized": true, + "rstrip": false, + "single_word": false, + "special": false + }, + "128": { + "content": "[#Ring1]", + "lstrip": false, + "normalized": true, + "rstrip": false, + "single_word": false, + "special": false + }, + "129": { + "content": "[-/Ring1]", + "lstrip": false, + "normalized": true, + "rstrip": false, + "single_word": false, + "special": false + }, + "130": { + "content": "[NH1]", + "lstrip": false, + "normalized": true, + "rstrip": false, + "single_word": false, + "special": false + }, + "131": { + "content": "[N@@+1]", + "lstrip": false, + "normalized": true, + "rstrip": false, + "single_word": false, + "special": false + }, + "132": { + "content": "[=PH1]", + "lstrip": false, + "normalized": true, + "rstrip": false, + "single_word": false, + "special": false + }, + "133": { + "content": "[=S+1]", + "lstrip": false, + "normalized": true, + "rstrip": false, + "single_word": false, + "special": false + }, + "134": { + "content": "[PH1]", + "lstrip": false, + "normalized": true, + "rstrip": false, + "single_word": false, + "special": false + }, + "135": { + "content": "[Sn+3]", + "lstrip": false, + "normalized": true, + "rstrip": false, + "single_word": false, + "special": false + }, + "136": { + "content": "[124I]", + "lstrip": false, + "normalized": true, + "rstrip": false, + "single_word": false, + "special": false + }, + "137": { + "content": "[3H]", + "lstrip": false, + "normalized": true, + "rstrip": false, + "single_word": false, + "special": false + }, + "138": { + "content": "[\\N]", + "lstrip": false, + "normalized": true, + "rstrip": false, + "single_word": false, + "special": false + }, + "139": { + "content": "[C]", + "lstrip": false, + "normalized": true, + "rstrip": false, + "single_word": false, + "special": false + }, + "140": { + "content": "[Branch2]", + "lstrip": false, + "normalized": true, + "rstrip": false, + "single_word": false, + "special": false + }, + "141": { + "content": "[\\O-1]", + "lstrip": false, + "normalized": true, + "rstrip": false, + "single_word": false, + "special": false + }, + "142": { + "content": "[\\Br]", + "lstrip": false, + "normalized": true, + "rstrip": false, + "single_word": false, + "special": false + }, + "143": { + "content": "[17F]", + "lstrip": false, + "normalized": true, + "rstrip": false, + "single_word": false, + "special": false + }, + "144": { + "content": "[=N+1]", + "lstrip": false, + "normalized": true, + "rstrip": false, + "single_word": false, + "special": false + }, + "145": { + "content": "[\\C@]", + "lstrip": false, + "normalized": true, + "rstrip": false, + "single_word": false, + "special": false + }, + "146": { + "content": "[CH2]", + "lstrip": false, + "normalized": true, + "rstrip": false, + "single_word": false, + "special": false + }, + "147": { + "content": "[=P@H1]", + "lstrip": false, + "normalized": true, + "rstrip": false, + "single_word": false, + "special": false + }, + "148": { + "content": "[NH0]", + "lstrip": false, + "normalized": true, + "rstrip": false, + "single_word": false, + "special": false + }, + "149": { + "content": "[/Br]", + "lstrip": false, + "normalized": true, + "rstrip": false, + "single_word": false, + "special": false + }, + "150": { + "content": "[N+1]", + "lstrip": false, + "normalized": true, + "rstrip": false, + "single_word": false, + "special": false + }, + "151": { + "content": "[\\SH1]", + "lstrip": false, + "normalized": true, + "rstrip": false, + "single_word": false, + "special": false + }, + "152": { + "content": "[/N+1]", + "lstrip": false, + "normalized": true, + "rstrip": false, + "single_word": false, + "special": false + }, + "153": { + "content": "[\\CH1-1]", + "lstrip": false, + "normalized": true, + "rstrip": false, + "single_word": false, + "special": false + }, + "154": { + "content": "[S@@]", + "lstrip": false, + "normalized": true, + "rstrip": false, + "single_word": false, + "special": false + }, + "155": { + "content": "[/Cl]", + "lstrip": false, + "normalized": true, + "rstrip": false, + "single_word": false, + "special": false + }, + "156": { + "content": "[-/Ring2]", + "lstrip": false, + "normalized": true, + "rstrip": false, + "single_word": false, + "special": false + }, + "157": { + "content": "[=P@]", + "lstrip": false, + "normalized": true, + "rstrip": false, + "single_word": false, + "special": false + }, + "158": { + "content": "[P@+1]", + "lstrip": false, + "normalized": true, + "rstrip": false, + "single_word": false, + "special": false + }, + "159": { + "content": "[\\B]", + "lstrip": false, + "normalized": true, + "rstrip": false, + "single_word": false, + "special": false + }, + "160": { + "content": "[/S@@]", + "lstrip": false, + "normalized": true, + "rstrip": false, + "single_word": false, + "special": false + }, + "161": { + "content": "[=N-1]", + "lstrip": false, + "normalized": true, + "rstrip": false, + "single_word": false, + "special": false + }, + "162": { + "content": "[N@@H1+1]", + "lstrip": false, + "normalized": true, + "rstrip": false, + "single_word": false, + "special": false + }, + "163": { + "content": "[=Ring1]", + "lstrip": false, + "normalized": true, + "rstrip": false, + "single_word": false, + "special": false + }, + "164": { + "content": "[-\\Ring1]", + "lstrip": false, + "normalized": true, + "rstrip": false, + "single_word": false, + "special": false + }, + "165": { + "content": "[#C]", + "lstrip": false, + "normalized": true, + "rstrip": false, + "single_word": false, + "special": false + }, + "166": { + "content": "[Br+1]", + "lstrip": false, + "normalized": true, + "rstrip": false, + "single_word": false, + "special": false + }, + "167": { + "content": "[=S@+1]", + "lstrip": false, + "normalized": true, + "rstrip": false, + "single_word": false, + "special": false + }, + "168": { + "content": "[\\Si]", + "lstrip": false, + "normalized": true, + "rstrip": false, + "single_word": false, + "special": false + }, + "169": { + "content": "[\\S@@+1]", + "lstrip": false, + "normalized": true, + "rstrip": false, + "single_word": false, + "special": false + }, + "170": { + "content": "[P@@H1]", + "lstrip": false, + "normalized": true, + "rstrip": false, + "single_word": false, + "special": false + }, + "171": { + "content": "[/O-1]", + "lstrip": false, + "normalized": true, + "rstrip": false, + "single_word": false, + "special": false + }, + "172": { + "content": "[\\I]", + "lstrip": false, + "normalized": true, + "rstrip": false, + "single_word": false, + "special": false + }, + "173": { + "content": "[C@@]", + "lstrip": false, + "normalized": true, + "rstrip": false, + "single_word": false, + "special": false + }, + "174": { + "content": "[/OH0]", + "lstrip": false, + "normalized": true, + "rstrip": false, + "single_word": false, + "special": false + }, + "175": { + "content": "[P@]", + "lstrip": false, + "normalized": true, + "rstrip": false, + "single_word": false, + "special": false + }, + "176": { + "content": "[\\CH0]", + "lstrip": false, + "normalized": true, + "rstrip": false, + "single_word": false, + "special": false + }, + "177": { + "content": "[/C@H1]", + "lstrip": false, + "normalized": true, + "rstrip": false, + "single_word": false, + "special": false + }, + "178": { + "content": "[#Branch2]", + "lstrip": false, + "normalized": true, + "rstrip": false, + "single_word": false, + "special": false + }, + "179": { + "content": "[B@-1]", + "lstrip": false, + "normalized": true, + "rstrip": false, + "single_word": false, + "special": false + }, + "180": { + "content": "[\\S@@]", + "lstrip": false, + "normalized": true, + "rstrip": false, + "single_word": false, + "special": false + }, + "181": { + "content": "[#C-1]", + "lstrip": false, + "normalized": true, + "rstrip": false, + "single_word": false, + "special": false + }, + "182": { + "content": "[SH0]", + "lstrip": false, + "normalized": true, + "rstrip": false, + "single_word": false, + "special": false + }, + "183": { + "content": "[Sn+2]", + "lstrip": false, + "normalized": true, + "rstrip": false, + "single_word": false, + "special": false + }, + "184": { + "content": "", + "lstrip": true, + "normalized": true, + "rstrip": false, + "single_word": false, + "special": true + } + }, + "bos_token": "", + "clean_up_tokenization_spaces": false, + "eos_token": "", + "model_max_length": 1024, + "pad_token": "", + "padding_side": "right", + "tokenizer_class": "LlamaTokenizer", + "unk_token": "", + "use_default_system_prompt": false +}