Spaces:
Runtime error
Runtime error
File size: 3,375 Bytes
dcd2001 edf6dca dcd2001 edf6dca dcd2001 edf6dca dcd2001 |
1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 |
# for generate (gradio server) and finetune datasets==2.13.0 sentencepiece==0.1.99 gradio==3.35.2 huggingface_hub==0.15.1 appdirs==1.4.4 fire==0.5.0 docutils==0.20.1 torch==2.0.1; sys_platform != "darwin" and platform_machine != "arm64" evaluate==0.4.0 rouge_score==0.1.2 sacrebleu==2.3.1 scikit-learn==1.2.2 alt-profanity-check==1.2.2 better-profanity==0.7.0 numpy==1.24.3 pandas==2.0.2 matplotlib==3.7.1 loralib==0.1.1 bitsandbytes==0.39.0 accelerate==0.20.3 git+https://github.com/huggingface/peft.git@06fd06a4d2e8ed8c3a253c67d9c3cb23e0f497ad transformers==4.30.2 tokenizers==0.13.3 APScheduler==3.10.1 # optional for generate pynvml==11.5.0 psutil==5.9.5 boto3==1.26.101 botocore==1.29.101 # optional for finetune tensorboard==2.13.0 neptune==1.2.0 # for gradio client gradio_client==0.2.7 beautifulsoup4==4.12.2 markdown==3.4.3 # data and testing pytest==7.2.2 pytest-xdist==3.2.1 nltk==3.8.1 textstat==0.7.3 # pandoc==2.3 pypandoc==1.11; sys_platform == "darwin" and platform_machine == "arm64" pypandoc_binary==1.11; platform_machine == "x86_64" openpyxl==3.1.2 lm_dataformat==0.0.20 bioc==2.0 # falcon einops==0.6.1 instructorembedding==1.0.1 # for gpt4all .env file, but avoid worrying about imports python-dotenv==1.0.0 text-generation==0.6.0 # for tokenization when don't have HF tokenizer tiktoken==0.4.0 # optional: for OpenAI endpoint or embeddings (requires key) openai==0.27.8 # optional for chat with PDF langchain==0.0.202 pypdf==3.9.1 # avoid textract, requires old six #textract==1.6.5 # for HF embeddings sentence_transformers==2.2.2 # local vector db chromadb==0.3.25 # server vector db #pymilvus==2.2.8 # weak url support, if can't install opencv etc. If comment-in this one, then comment-out unstructured[local-inference]==0.6.6 # unstructured==0.6.6 # strong support for images # Requires on Ubuntu: sudo apt-get install libmagic-dev poppler-utils tesseract-ocr libreoffice unstructured[local-inference]==0.7.4 #pdf2image==1.16.3 #pytesseract==0.3.10 pillow pdfminer.six==20221105 urllib3 requests_file #pdf2image==1.16.3 #pytesseract==0.3.10 tabulate==0.9.0 # FYI pandoc already part of requirements.txt # JSONLoader, but makes some trouble for some users # jq==1.4.1 # to check licenses # Run: pip-licenses|grep -v 'BSD\|Apache\|MIT' pip-licenses==4.3.0 # weaviate vector db weaviate-client==3.20.0 # optional for chat with PDF langchain==0.0.202 pypdf==3.9.1 # avoid textract, requires old six #textract==1.6.5 # for HF embeddings sentence_transformers==2.2.2 # local vector db chromadb==0.3.25 # server vector db #pymilvus==2.2.8 # weak url support, if can't install opencv etc. If comment-in this one, then comment-out unstructured[local-inference]==0.6.6 # unstructured==0.6.6 # strong support for images # Requires on Ubuntu: sudo apt-get install libmagic-dev poppler-utils tesseract-ocr libreoffice unstructured[local-inference]==0.7.4 #pdf2image==1.16.3 #pytesseract==0.3.10 pillow pdfminer.six==20221105 urllib3 requests_file #pdf2image==1.16.3 #pytesseract==0.3.10 tabulate==0.9.0 # FYI pandoc already part of requirements.txt # JSONLoader, but makes some trouble for some users # jq==1.4.1 # to check licenses # Run: pip-licenses|grep -v 'BSD\|Apache\|MIT' pip-licenses==4.3.0 # weaviate vector db weaviate-client==3.20.0 faiss-gpu==1.7.2 arxiv==1.4.7 pymupdf==1.22.3 # AGPL license # extract-msg==0.41.1 # GPL3 |