├── README.md ├── cal_sim.py ├── convert_lora_to_weights.py ├── datagen ├── chembench_mol2caption.jsonl ├── chembench_property.jsonl ├── clean.py ├── convert_raw.py ├── cross_modal │ ├── elect │ │ ├── data.jsonl │ │ └── main.py │ ├── hand │ │ ├── data.jsonl │ │ └── main.py │ ├── latex │ │ └── main.py │ ├── print │ │ └── main.py │ ├── qa │ │ └── main.py │ ├── rxn │ │ ├── batch.sh │ │ ├── ends_all.py │ │ ├── main.py │ │ ├── ocr.py │ │ └── run_n_batch.py │ └── total_syn │ │ └── main.py ├── example.json ├── fix.py ├── gen_cauldron.py ├── gen_cauldron.sh ├── gen_cauldron_images.py ├── gen_chem_ocr.py ├── gen_choice_problem.py ├── gen_general.py ├── gen_general_chinese.py ├── gen_general_exam.py ├── gen_general_text_mix.py ├── gen_test.py ├── gen_the_cauldron.py ├── mm_chem_ocr.jsonl.test.jsonl ├── mm_pure_fix.jsonl ├── push_hub.py ├── read_data.py ├── read_data_rescue.py ├── sample.py ├── scan.py ├── test_one.jsonl ├── test_sample.py └── train_test_split.py ├── evaluation ├── read_multiple_choice_scores.py ├── test_gaokao_performance.py ├── test_res_chemvlm.py ├── test_res_openai.py └── test_smiles_ocr.py ├── evaluation_tool ├── eval_files │ ├── test_gaokao_performance.py │ ├── test_res_openai.py │ ├── test_score_metrics.py │ └── test_smiles_ocr.py ├── qwen_ocr_8b_chemvlm.jsonl └── test_overall.py ├── imgs └── ChemVLM.jpg ├── merge_vit_and_llm.py ├── process_web_data ├── read_CheBI.py ├── read_ChemQA.py ├── read_chembench.py └── read_orderly.py ├── requirements.txt └── web_demo ├── controller.sh ├── gradio.sh ├── worker.sh └── worker_2B.sh /README.md: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/lijunxian111/ChemVlm/HEAD/README.md -------------------------------------------------------------------------------- /cal_sim.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/lijunxian111/ChemVlm/HEAD/cal_sim.py -------------------------------------------------------------------------------- /convert_lora_to_weights.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/lijunxian111/ChemVlm/HEAD/convert_lora_to_weights.py -------------------------------------------------------------------------------- /datagen/chembench_mol2caption.jsonl: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/lijunxian111/ChemVlm/HEAD/datagen/chembench_mol2caption.jsonl -------------------------------------------------------------------------------- /datagen/chembench_property.jsonl: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/lijunxian111/ChemVlm/HEAD/datagen/chembench_property.jsonl -------------------------------------------------------------------------------- /datagen/clean.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/lijunxian111/ChemVlm/HEAD/datagen/clean.py -------------------------------------------------------------------------------- /datagen/convert_raw.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/lijunxian111/ChemVlm/HEAD/datagen/convert_raw.py -------------------------------------------------------------------------------- /datagen/cross_modal/elect/data.jsonl: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/lijunxian111/ChemVlm/HEAD/datagen/cross_modal/elect/data.jsonl -------------------------------------------------------------------------------- /datagen/cross_modal/elect/main.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/lijunxian111/ChemVlm/HEAD/datagen/cross_modal/elect/main.py -------------------------------------------------------------------------------- /datagen/cross_modal/hand/data.jsonl: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/lijunxian111/ChemVlm/HEAD/datagen/cross_modal/hand/data.jsonl -------------------------------------------------------------------------------- /datagen/cross_modal/hand/main.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/lijunxian111/ChemVlm/HEAD/datagen/cross_modal/hand/main.py -------------------------------------------------------------------------------- /datagen/cross_modal/latex/main.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/lijunxian111/ChemVlm/HEAD/datagen/cross_modal/latex/main.py -------------------------------------------------------------------------------- /datagen/cross_modal/print/main.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/lijunxian111/ChemVlm/HEAD/datagen/cross_modal/print/main.py -------------------------------------------------------------------------------- /datagen/cross_modal/qa/main.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/lijunxian111/ChemVlm/HEAD/datagen/cross_modal/qa/main.py -------------------------------------------------------------------------------- /datagen/cross_modal/rxn/batch.sh: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/lijunxian111/ChemVlm/HEAD/datagen/cross_modal/rxn/batch.sh -------------------------------------------------------------------------------- /datagen/cross_modal/rxn/ends_all.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/lijunxian111/ChemVlm/HEAD/datagen/cross_modal/rxn/ends_all.py -------------------------------------------------------------------------------- /datagen/cross_modal/rxn/main.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/lijunxian111/ChemVlm/HEAD/datagen/cross_modal/rxn/main.py -------------------------------------------------------------------------------- /datagen/cross_modal/rxn/ocr.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/lijunxian111/ChemVlm/HEAD/datagen/cross_modal/rxn/ocr.py -------------------------------------------------------------------------------- /datagen/cross_modal/rxn/run_n_batch.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/lijunxian111/ChemVlm/HEAD/datagen/cross_modal/rxn/run_n_batch.py -------------------------------------------------------------------------------- /datagen/cross_modal/total_syn/main.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/lijunxian111/ChemVlm/HEAD/datagen/cross_modal/total_syn/main.py -------------------------------------------------------------------------------- /datagen/example.json: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/lijunxian111/ChemVlm/HEAD/datagen/example.json -------------------------------------------------------------------------------- /datagen/fix.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/lijunxian111/ChemVlm/HEAD/datagen/fix.py -------------------------------------------------------------------------------- /datagen/gen_cauldron.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/lijunxian111/ChemVlm/HEAD/datagen/gen_cauldron.py -------------------------------------------------------------------------------- /datagen/gen_cauldron.sh: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/lijunxian111/ChemVlm/HEAD/datagen/gen_cauldron.sh -------------------------------------------------------------------------------- /datagen/gen_cauldron_images.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/lijunxian111/ChemVlm/HEAD/datagen/gen_cauldron_images.py -------------------------------------------------------------------------------- /datagen/gen_chem_ocr.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/lijunxian111/ChemVlm/HEAD/datagen/gen_chem_ocr.py -------------------------------------------------------------------------------- /datagen/gen_choice_problem.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/lijunxian111/ChemVlm/HEAD/datagen/gen_choice_problem.py -------------------------------------------------------------------------------- /datagen/gen_general.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/lijunxian111/ChemVlm/HEAD/datagen/gen_general.py -------------------------------------------------------------------------------- /datagen/gen_general_chinese.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/lijunxian111/ChemVlm/HEAD/datagen/gen_general_chinese.py -------------------------------------------------------------------------------- /datagen/gen_general_exam.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/lijunxian111/ChemVlm/HEAD/datagen/gen_general_exam.py -------------------------------------------------------------------------------- /datagen/gen_general_text_mix.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/lijunxian111/ChemVlm/HEAD/datagen/gen_general_text_mix.py -------------------------------------------------------------------------------- /datagen/gen_test.py: -------------------------------------------------------------------------------- 1 | -------------------------------------------------------------------------------- /datagen/gen_the_cauldron.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/lijunxian111/ChemVlm/HEAD/datagen/gen_the_cauldron.py -------------------------------------------------------------------------------- /datagen/mm_chem_ocr.jsonl.test.jsonl: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/lijunxian111/ChemVlm/HEAD/datagen/mm_chem_ocr.jsonl.test.jsonl -------------------------------------------------------------------------------- /datagen/mm_pure_fix.jsonl: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/lijunxian111/ChemVlm/HEAD/datagen/mm_pure_fix.jsonl -------------------------------------------------------------------------------- /datagen/push_hub.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/lijunxian111/ChemVlm/HEAD/datagen/push_hub.py -------------------------------------------------------------------------------- /datagen/read_data.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/lijunxian111/ChemVlm/HEAD/datagen/read_data.py -------------------------------------------------------------------------------- /datagen/read_data_rescue.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/lijunxian111/ChemVlm/HEAD/datagen/read_data_rescue.py -------------------------------------------------------------------------------- /datagen/sample.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/lijunxian111/ChemVlm/HEAD/datagen/sample.py -------------------------------------------------------------------------------- /datagen/scan.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/lijunxian111/ChemVlm/HEAD/datagen/scan.py -------------------------------------------------------------------------------- /datagen/test_one.jsonl: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/lijunxian111/ChemVlm/HEAD/datagen/test_one.jsonl -------------------------------------------------------------------------------- /datagen/test_sample.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/lijunxian111/ChemVlm/HEAD/datagen/test_sample.py -------------------------------------------------------------------------------- /datagen/train_test_split.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/lijunxian111/ChemVlm/HEAD/datagen/train_test_split.py -------------------------------------------------------------------------------- /evaluation/read_multiple_choice_scores.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/lijunxian111/ChemVlm/HEAD/evaluation/read_multiple_choice_scores.py -------------------------------------------------------------------------------- /evaluation/test_gaokao_performance.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/lijunxian111/ChemVlm/HEAD/evaluation/test_gaokao_performance.py -------------------------------------------------------------------------------- /evaluation/test_res_chemvlm.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/lijunxian111/ChemVlm/HEAD/evaluation/test_res_chemvlm.py -------------------------------------------------------------------------------- /evaluation/test_res_openai.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/lijunxian111/ChemVlm/HEAD/evaluation/test_res_openai.py -------------------------------------------------------------------------------- /evaluation/test_smiles_ocr.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/lijunxian111/ChemVlm/HEAD/evaluation/test_smiles_ocr.py -------------------------------------------------------------------------------- /evaluation_tool/eval_files/test_gaokao_performance.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/lijunxian111/ChemVlm/HEAD/evaluation_tool/eval_files/test_gaokao_performance.py -------------------------------------------------------------------------------- /evaluation_tool/eval_files/test_res_openai.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/lijunxian111/ChemVlm/HEAD/evaluation_tool/eval_files/test_res_openai.py -------------------------------------------------------------------------------- /evaluation_tool/eval_files/test_score_metrics.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/lijunxian111/ChemVlm/HEAD/evaluation_tool/eval_files/test_score_metrics.py -------------------------------------------------------------------------------- /evaluation_tool/eval_files/test_smiles_ocr.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/lijunxian111/ChemVlm/HEAD/evaluation_tool/eval_files/test_smiles_ocr.py -------------------------------------------------------------------------------- /evaluation_tool/qwen_ocr_8b_chemvlm.jsonl: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/lijunxian111/ChemVlm/HEAD/evaluation_tool/qwen_ocr_8b_chemvlm.jsonl -------------------------------------------------------------------------------- /evaluation_tool/test_overall.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/lijunxian111/ChemVlm/HEAD/evaluation_tool/test_overall.py -------------------------------------------------------------------------------- /imgs/ChemVLM.jpg: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/lijunxian111/ChemVlm/HEAD/imgs/ChemVLM.jpg -------------------------------------------------------------------------------- /merge_vit_and_llm.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/lijunxian111/ChemVlm/HEAD/merge_vit_and_llm.py -------------------------------------------------------------------------------- /process_web_data/read_CheBI.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/lijunxian111/ChemVlm/HEAD/process_web_data/read_CheBI.py -------------------------------------------------------------------------------- /process_web_data/read_ChemQA.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/lijunxian111/ChemVlm/HEAD/process_web_data/read_ChemQA.py -------------------------------------------------------------------------------- /process_web_data/read_chembench.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/lijunxian111/ChemVlm/HEAD/process_web_data/read_chembench.py -------------------------------------------------------------------------------- /process_web_data/read_orderly.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/lijunxian111/ChemVlm/HEAD/process_web_data/read_orderly.py -------------------------------------------------------------------------------- /requirements.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/lijunxian111/ChemVlm/HEAD/requirements.txt -------------------------------------------------------------------------------- /web_demo/controller.sh: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/lijunxian111/ChemVlm/HEAD/web_demo/controller.sh -------------------------------------------------------------------------------- /web_demo/gradio.sh: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/lijunxian111/ChemVlm/HEAD/web_demo/gradio.sh -------------------------------------------------------------------------------- /web_demo/worker.sh: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/lijunxian111/ChemVlm/HEAD/web_demo/worker.sh -------------------------------------------------------------------------------- /web_demo/worker_2B.sh: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/lijunxian111/ChemVlm/HEAD/web_demo/worker_2B.sh --------------------------------------------------------------------------------