1model_output_folder_list = { 2 "CoT ChatGPT (Caption+OCR)": "CoT ChatGPT (Caption+OCR)", 3 "CoT Claude (Caption+OCR)": "CoT Claude (Caption+OCR)", 4 "CoT GPT4 (Caption+OCR)": "CoT GPT4 (Caption+OCR)", 5 "IDEFICS (9B-Instruct)": "IDEFICS (9B-Instruct)", 6 "InstructBLIP (Vicuna-7B)": "InstructBLIP (Vicuna-7B)", 7 "LLaMA-Adapter-V2 (7B)": "LLaMA-Adapter-V2 (7B)", 8 "LLaVA (LLaMA-2-13B)": "LLaVA (LLaMA-2-13B)", 9 "Multimodal Bard": "Multimodal Bard", 10 "PoT ChatGPT (Caption+OCR)": "PoT ChatGPT (Caption+OCR)", 11 "PoT GPT-4 (Caption+OCR)": "PoT GPT-4 (Caption+OCR)", 12 "mPLUG-Owl (LLaMA-7B)": "mPLUG-Owl (LLaMA-7B)", 13 "miniGPT4 (LLaMA-2-7B)": "miniGPT4 (LLaMA-2-7B)" 14}
Line numbers count LF bytes from the start of the resource, as the search results do. Vendor segments are library code the classifier recognised; they are stored but not indexed. Bytes are shown as Latin1 characters, one per byte.