| { | |
| "add_bos_token": false, | |
| "add_prefix_space": false, | |
| "added_tokens_decoder": { | |
| "151643": { | |
| "content": "<|endoftext|>", | |
| "lstrip": false, | |
| "normalized": false, | |
| "rstrip": false, | |
| "single_word": false, | |
| "special": true | |
| }, | |
| "151644": { | |
| "content": "<|im_start|>", | |
| "lstrip": false, | |
| "normalized": false, | |
| "rstrip": false, | |
| "single_word": false, | |
| "special": true | |
| }, | |
| "151645": { | |
| "content": "<|im_end|>", | |
| "lstrip": false, | |
| "normalized": false, | |
| "rstrip": false, | |
| "single_word": false, | |
| "special": true | |
| }, | |
| "151646": { | |
| "content": "<|object_ref_start|>", | |
| "lstrip": false, | |
| "normalized": false, | |
| "rstrip": false, | |
| "single_word": false, | |
| "special": true | |
| }, | |
| "151647": { | |
| "content": "<|object_ref_end|>", | |
| "lstrip": false, | |
| "normalized": false, | |
| "rstrip": false, | |
| "single_word": false, | |
| "special": true | |
| }, | |
| "151648": { | |
| "content": "<|box_start|>", | |
| "lstrip": false, | |
| "normalized": false, | |
| "rstrip": false, | |
| "single_word": false, | |
| "special": true | |
| }, | |
| "151649": { | |
| "content": "<|box_end|>", | |
| "lstrip": false, | |
| "normalized": false, | |
| "rstrip": false, | |
| "single_word": false, | |
| "special": true | |
| }, | |
| "151650": { | |
| "content": "<|quad_start|>", | |
| "lstrip": false, | |
| "normalized": false, | |
| "rstrip": false, | |
| "single_word": false, | |
| "special": true | |
| }, | |
| "151651": { | |
| "content": "<|quad_end|>", | |
| "lstrip": false, | |
| "normalized": false, | |
| "rstrip": false, | |
| "single_word": false, | |
| "special": true | |
| }, | |
| "151652": { | |
| "content": "<|vision_start|>", | |
| "lstrip": false, | |
| "normalized": false, | |
| "rstrip": false, | |
| "single_word": false, | |
| "special": true | |
| }, | |
| "151653": { | |
| "content": "<|vision_end|>", | |
| "lstrip": false, | |
| "normalized": false, | |
| "rstrip": false, | |
| "single_word": false, | |
| "special": true | |
| }, | |
| "151654": { | |
| "content": "<|vision_pad|>", | |
| "lstrip": false, | |
| "normalized": false, | |
| "rstrip": false, | |
| "single_word": false, | |
| "special": true | |
| }, | |
| "151655": { | |
| "content": "<|image_pad|>", | |
| "lstrip": false, | |
| "normalized": false, | |
| "rstrip": false, | |
| "single_word": false, | |
| "special": true | |
| }, | |
| "151656": { | |
| "content": "<|video_pad|>", | |
| "lstrip": false, | |
| "normalized": false, | |
| "rstrip": false, | |
| "single_word": false, | |
| "special": true | |
| }, | |
| "151657": { | |
| "content": "<tool_call>", | |
| "lstrip": false, | |
| "normalized": false, | |
| "rstrip": false, | |
| "single_word": false, | |
| "special": false | |
| }, | |
| "151658": { | |
| "content": "</tool_call>", | |
| "lstrip": false, | |
| "normalized": false, | |
| "rstrip": false, | |
| "single_word": false, | |
| "special": false | |
| }, | |
| "151659": { | |
| "content": "<|fim_prefix|>", | |
| "lstrip": false, | |
| "normalized": false, | |
| "rstrip": false, | |
| "single_word": false, | |
| "special": false | |
| }, | |
| "151660": { | |
| "content": "<|fim_middle|>", | |
| "lstrip": false, | |
| "normalized": false, | |
| "rstrip": false, | |
| "single_word": false, | |
| "special": false | |
| }, | |
| "151661": { | |
| "content": "<|fim_suffix|>", | |
| "lstrip": false, | |
| "normalized": false, | |
| "rstrip": false, | |
| "single_word": false, | |
| "special": false | |
| }, | |
| "151662": { | |
| "content": "<|fim_pad|>", | |
| "lstrip": false, | |
| "normalized": false, | |
| "rstrip": false, | |
| "single_word": false, | |
| "special": false | |
| }, | |
| "151663": { | |
| "content": "<|repo_name|>", | |
| "lstrip": false, | |
| "normalized": false, | |
| "rstrip": false, | |
| "single_word": false, | |
| "special": false | |
| }, | |
| "151664": { | |
| "content": "<|file_sep|>", | |
| "lstrip": false, | |
| "normalized": false, | |
| "rstrip": false, | |
| "single_word": false, | |
| "special": false | |
| } | |
| }, | |
| "additional_special_tokens": [ | |
| "<|im_start|>", | |
| "<|im_end|>", | |
| "<|object_ref_start|>", | |
| "<|object_ref_end|>", | |
| "<|box_start|>", | |
| "<|box_end|>", | |
| "<|quad_start|>", | |
| "<|quad_end|>", | |
| "<|vision_start|>", | |
| "<|vision_end|>", | |
| "<|vision_pad|>", | |
| "<|image_pad|>", | |
| "<|video_pad|>" | |
| ], | |
| "bos_token": null, | |
| "chat_template": "{%- if tools %}\n {{- '<|im_start|>system\\n' }}\n {%- if messages[0]['role'] == 'system' %}\n {{- messages[0]['content'] }}\n {%- else %}\n {{- 'INPUT: One paragraph / QA pair / fact.\\nOUTPUT:\\n{\"relevant\": true|false, \"matched_tasks\": [\"tag1\", \"tag2\", ...]} // empty list if relevant=false\\n\\nRELEVANT if the text gives an explicit experimental, clinical, computational, or authoritative statement that ties at least one molecule-level entity (drug, catalyst, peptide, antibody, protein, gene, cell line, disease, ...) to any endpoint below.\\nAccept numeric results (\"IC50 = 25 nM\"), categorical outcomes (\"phase 2 failed\"), or clear functional claims (\"potent hERG blocker\", \"substrate of CYP3A4\").\\nList every tag mentioned; otherwise return relevant=false.\\n\\nTAGS\\nyield_prediction\\ncell_line_sensitivity\\nphase1_success, phase2_success, phase3_success\\nld50_toxicity\\nhepato_clearance, micro_clearance\\nsolubility\\npermeability\\nhalf_life\\nlipophilicity\\nplasma_binding\\nvolume_distribution\\n3clpro_binding\\nherg_block\\nliver_injury, skin_reaction\\nbbb_permeation\\nanti_hiv\\ncyp1a2_inhib, cyp2c19_inhib, cyp2c9_inhib, cyp2d6_inhib, cyp3a4_inhib\\ncyp2c9_sub, cyp2d6_sub, cyp3a4_sub\\npgp_inhib\\nsars_cov2_replication_inhib\\ncarcinogenicity, mutagenicity\\noral_bioavailability\\npampa_permeable\\ngeneral_toxicity\\nbioactivity_protein\\nretrosynthesis\\ndrug_synergy\\nantibody_cdr_length, antibody_developability\\nprotein_binding_affinity\\ntcr_epitope_binding\\npeptide_mhc1, peptide_mhc2\\nppi_interaction\\ngene_disease_assoc\\nmirna_target\\nguide_seq_properties\\ndrug_target_affinity, drug_target_ic50, drug_target_kd, drug_target_ki\\ngeneral_inhib\\n\\nSynonym hints (non-exhaustive):\\n- IC50/EC50/GI50: cell_line_sensitivity\\n- logP/logD: lipophilicity\\n- fu: plasma_binding\\n- Vd/Vss: volume_distribution\\n- PAMPA/Caco-2: permeability\\n- LD50: ld50_toxicity\\n- \"clearance\": *_clearance\\n- SARS-CoV-2 3CL: 3clpro_binding\\n- BBB/logBB: bbb_permeation\\n- GuideSeq metrics: guide_seq_properties\\n- \"inhibitor/substrate of CYP3A4\": cyp3a4_inhib / cyp3a4_sub\\n- \"blocks P-gp\": pgp_inhib' }}\n {%- endif %}\n {{- \"\\n\\n# Tools\\n\\nYou may call one or more functions to assist with the user query.\\n\\nYou are provided with function signatures within <tools></tools> XML tags:\\n<tools>\" }}\n {%- for tool in tools %}\n {{- \"\\n\" }}\n {{- tool | tojson }}\n {%- endfor %}\n {{- \"\\n</tools>\\n\\nFor each function call, return a json object with function name and arguments within <tool_call></tool_call> XML tags:\\n<tool_call>\\n{\\\"name\\\": <function-name>, \\\"arguments\\\": <args-json-object>}\\n</tool_call><|im_end|>\\n\" }}\n{%- else %}\n {%- if messages[0]['role'] == 'system' %}\n {{- '<|im_start|>system\\n' + messages[0]['content'] + '<|im_end|>\\n' }}\n {%- else %}\n {{- '<|im_start|>system\\nINPUT: One paragraph / QA pair / fact.\\nOUTPUT:\\n{\"relevant\": true|false, \"matched_tasks\": [\"tag1\", \"tag2\", ...]} // empty list if relevant=false\\n\\nRELEVANT if the text gives an explicit experimental, clinical, computational, or authoritative statement that ties at least one molecule-level entity (drug, catalyst, peptide, antibody, protein, gene, cell line, disease, ...) to any endpoint below.\\nAccept numeric results (\"IC50 = 25 nM\"), categorical outcomes (\"phase 2 failed\"), or clear functional claims (\"potent hERG blocker\", \"substrate of CYP3A4\").\\nList every tag mentioned; otherwise return relevant=false.\\n\\nTAGS\\nyield_prediction\\ncell_line_sensitivity\\nphase1_success, phase2_success, phase3_success\\nld50_toxicity\\nhepato_clearance, micro_clearance\\nsolubility\\npermeability\\nhalf_life\\nlipophilicity\\nplasma_binding\\nvolume_distribution\\n3clpro_binding\\nherg_block\\nliver_injury, skin_reaction\\nbbb_permeation\\nanti_hiv\\ncyp1a2_inhib, cyp2c19_inhib, cyp2c9_inhib, cyp2d6_inhib, cyp3a4_inhib\\ncyp2c9_sub, cyp2d6_sub, cyp3a4_sub\\npgp_inhib\\nsars_cov2_replication_inhib\\ncarcinogenicity, mutagenicity\\noral_bioavailability\\npampa_permeable\\ngeneral_toxicity\\nbioactivity_protein\\nretrosynthesis\\ndrug_synergy\\nantibody_cdr_length, antibody_developability\\nprotein_binding_affinity\\ntcr_epitope_binding\\npeptide_mhc1, peptide_mhc2\\nppi_interaction\\ngene_disease_assoc\\nmirna_target\\nguide_seq_properties\\ndrug_target_affinity, drug_target_ic50, drug_target_kd, drug_target_ki\\ngeneral_inhib\\n\\nSynonym hints (non-exhaustive):\\n- IC50/EC50/GI50: cell_line_sensitivity\\n- logP/logD: lipophilicity\\n- fu: plasma_binding\\n- Vd/Vss: volume_distribution\\n- PAMPA/Caco-2: permeability\\n- LD50: ld50_toxicity\\n- \"clearance\": *_clearance\\n- SARS-CoV-2 3CL: 3clpro_binding\\n- BBB/logBB: bbb_permeation\\n- GuideSeq metrics: guide_seq_properties\\n- \"inhibitor/substrate of CYP3A4\": cyp3a4_inhib / cyp3a4_sub\\n- \"blocks P-gp\": pgp_inhib<|im_end|>\\n' }}\n {%- endif %}\n{%- endif %}\n{%- for message in messages %}\n {%- if (message.role == \"user\") or (message.role == \"system\" and not loop.first) or (message.role == \"assistant\" and not message.tool_calls) %}\n {{- '<|im_start|>' + message.role + '\\n' + message.content + '<|im_end|>' + '\\n' }}\n {%- elif message.role == \"assistant\" %}\n {{- '<|im_start|>' + message.role }}\n {%- if message.content %}\n {{- '\\n' + message.content }}\n {%- endif %}\n {%- for tool_call in message.tool_calls %}\n {%- if tool_call.function is defined %}\n {%- set tool_call = tool_call.function %}\n {%- endif %}\n {{- '\\n<tool_call>\\n{\"name\": \"' }}\n {{- tool_call.name }}\n {{- '\", \"arguments\": ' }}\n {{- tool_call.arguments | tojson }}\n {{- '}\\n</tool_call>' }}\n {%- endfor %}\n {{- '<|im_end|>\\n' }}\n {%- elif message.role == \"tool\" %}\n {%- if (loop.index0 == 0) or (messages[loop.index0 - 1].role != \"tool\") %}\n {{- '<|im_start|>user' }}\n {%- endif %}\n {{- '\\n<tool_response>\\n' }}\n {{- message.content }}\n {{- '\\n</tool_response>' }}\n {%- if loop.last or (messages[loop.index0 + 1].role != \"tool\") %}\n {{- '<|im_end|>\\n' }}\n {%- endif %}\n {%- endif %}\n{%- endfor %}\n{%- if add_generation_prompt %}\n {{- '<|im_start|>assistant\\n' }}\n{%- endif %}\n", | |
| "clean_up_tokenization_spaces": false, | |
| "eos_token": "<|im_end|>", | |
| "errors": "replace", | |
| "extra_special_tokens": {}, | |
| "model_max_length": 131072, | |
| "pad_token": "<|endoftext|>", | |
| "split_special_tokens": false, | |
| "tokenizer_class": "Qwen2Tokenizer", | |
| "unk_token": null | |
| } | |