yangzzay's picture
Upload folder using huggingface_hub
02a7b98
raw
history blame contribute delete
468 Bytes
MODEL_PATH = "FlagAlpha/Llama2-Chinese-7b-Chat"
# if MODEL_PATH is "", default llama.cpp/gptq models
# will be downloaded to: ./models
# Example ggml path:
# MODEL_PATH = "./models/llama-2-7b-chat.ggmlv3.q4_0.bin"
# options: llama.cpp, gptq, transformers
BACKEND_TYPE = "transformers"
# only for transformers bitsandbytes 8 bit
LOAD_IN_8BIT = False
MAX_MAX_NEW_TOKENS = 2048
DEFAULT_MAX_NEW_TOKENS = 1024
MAX_INPUT_TOKEN_LENGTH = 4000
DEFAULT_SYSTEM_PROMPT = ""