File size: 3,094 Bytes
815128e 7d1a192 815128e 068c8a2 7d1a192 068c8a2 ea50055 815128e fc6b2b9 7d1a192 815128e 7f9d16c 99d65c0 815128e 910c4c8 ab49330 815128e c815d49 99d65c0 734948a a766494 815128e 99d65c0 815128e 99d65c0 5cc3808 815128e 99d65c0 815128e c2cb992 7f9d16c 815128e c2cb992 815128e c2cb992 7f9d16c 815128e 59fc6ec 25ef847 71ef2ac 815128e 4821924 815128e 910c4c8 815128e dfe180d |
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 |
# LLM_MODEL_TYPE=openai
# LLM_MODEL_TYPE=gpt4all-j
# LLM_MODEL_TYPE=gpt4all
# LLM_MODEL_TYPE=llamacpp
# LLM_MODEL_TYPE=huggingface
# LLM_MODEL_TYPE=mosaicml
# LLM_MODEL_TYPE=stablelm
# LLM_MODEL_TYPE=openllm
LLM_MODEL_TYPE=hftgi
OPENLLM_SERVER_URL=http://localhost:64300
HFTGI_SERVER_URL=https://enabled-factually-cougar.ngrok-free.app
OPENAI_API_KEY=
# if unset, default to "gpt-3.5-turbo"
OPENAI_MODEL_NAME=
# cpu, mps or cuda:0 - if unset, use whatever detected
HF_EMBEDDINGS_DEVICE_TYPE=
HF_PIPELINE_DEVICE_TYPE=
# uncomment one of the below to load corresponding quantized model
# LOAD_QUANTIZED_MODEL=4bit
# LOAD_QUANTIZED_MODEL=8bit
# USE_LLAMA_2_PROMPT_TEMPLATE=true
DISABLE_MODEL_PRELOADING=true
CHAT_HISTORY_ENABLED=true
SHOW_PARAM_SETTINGS=false
SHARE_GRADIO_APP=false
PDF_FILE_BASE_URL=https://chat-with-llama-2.netlify.app/pdfs/books/
# if unset, default to "hkunlp/instructor-xl"
HF_EMBEDDINGS_MODEL_NAME="hkunlp/instructor-large"
# number of cpu cores - used to set n_threads for GPT4ALL & LlamaCpp models
NUMBER_OF_CPU_CORES=
HUGGINGFACE_AUTH_TOKEN=
USING_TORCH_BFLOAT16=true
# HUGGINGFACE_MODEL_NAME_OR_PATH="databricks/dolly-v2-3b"
# HUGGINGFACE_MODEL_NAME_OR_PATH="databricks/dolly-v2-7b"
# HUGGINGFACE_MODEL_NAME_OR_PATH="databricks/dolly-v2-12b"
# LLM_MODEL_TYPE must be set to huggingface
# HUGGINGFACE_MODEL_NAME_OR_PATH="TheBloke/wizardLM-7B-HF"
# HUGGINGFACE_MODEL_NAME_OR_PATH="TheBloke/vicuna-7B-1.1-HF"
# HUGGINGFACE_MODEL_NAME_OR_PATH="nomic-ai/gpt4all-j"
# HUGGINGFACE_MODEL_NAME_OR_PATH="nomic-ai/gpt4all-falcon"
# HUGGINGFACE_MODEL_NAME_OR_PATH="lmsys/fastchat-t5-3b-v1.0"
HUGGINGFACE_MODEL_NAME_OR_PATH="meta-llama/Llama-2-7b-chat-hf"
# HUGGINGFACE_MODEL_NAME_OR_PATH="meta-llama/Llama-2-13b-chat-hf"
# HUGGINGFACE_MODEL_NAME_OR_PATH="meta-llama/Llama-2-70b-chat-hf"
# HUGGINGFACE_MODEL_NAME_OR_PATH="Qwen/Qwen-7B-Chat"
STABLELM_MODEL_NAME_OR_PATH="OpenAssistant/stablelm-7b-sft-v7-epoch-3"
MOSAICML_MODEL_NAME_OR_PATH="mosaicml/mpt-7b-instruct"
FALCON_MODEL_NAME_OR_PATH="tiiuae/falcon-7b-instruct"
GPT4ALL_J_MODEL_PATH="../models/llama-2-7b-chat.ggmlv3.q4_K_M.bin"
GPT4ALL_J_DOWNLOAD_LINK=https://huggingface.co/TheBloke/Llama-2-7B-Chat-GGML/resolve/main/llama-2-7b-chat.ggmlv3.q4_0.bin
GPT4ALL_MODEL_PATH="../models/ggml-nous-gpt4-vicuna-13b.bin"
GPT4ALL_DOWNLOAD_LINK=https://gpt4all.io/models/ggml-nous-gpt4-vicuna-13b.bin
LLAMACPP_MODEL_PATH="../models/llama-2-7b-chat.ggmlv3.q4_K_M.bin"
LLAMACPP_DOWNLOAD_LINK=https://huggingface.co/TheBloke/Llama-2-7B-Chat-GGML/resolve/main/llama-2-7b-chat.ggmlv3.q4_K_M.bin
# Index for AI Books PDF files - chunk_size=1024 chunk_overlap=512
# CHROMADB_INDEX_PATH="./data/chromadb_1024_512/"
FAISS_INDEX_PATH="./data/ai_books/"
CHAT_QUESTION="What's the capital city of Malaysia?"
QA_QUESTION="What's deep learning?"
QUESTIONS_FILE_PATH="./data/questions.txt"
TOKENIZERS_PARALLELISM=true
# env variables for ingesting source PDF files
SOURCE_PDFS_PATH="./data/pdfs/"
SOURCE_URLS=
CHUNCK_SIZE=1024
CHUNK_OVERLAP=512
# telegram bot
TELEGRAM_API_TOKEN=
CHAT_API_URL=http://localhost:8080/chat_sync
|