トップ 差分 一覧 ソース 検索 ヘルプ RSS ログイン

tips-llama_cpp

  llama.cpp with python

# source ./setenv_python311
# python3.11 -m venv 00venv00
# source ./00venv00/bin/activate
# pip3.11 install --upgrade pip setuptools

##########################################################################
# git clone https://github.com/ggerganov/llama.cpp
# make
# $ ./main -m ./models/llama-2-7b-chat.ggmlv3.q4_K_M.guu --temp 0.1 -p "### Instruction: What is the height of Mount Fuji?  ### Response:"
# pip3 install --upgrade --force-reinstall llama-cpp-python --no-cache-dir
##########################################################################
## python3 -m pip install -U llama-cpp-python
#
#### codellama-7b-python.ggmlv3.Q5_K_M.bin
## https://huggingface.co/TheBloke/CodeLlama-7B-Python-GGML/tree/main/
# Chat
## https://huggingface.co/TheBloke/Llama-2-13B-chat-GGUF/tree/main
## https://huggingface.co/TheBloke/Llama-2-13B-chat-GGUF/blob/main/llama-2-13b-chat.Q5_K_M.gguf
##########################################################################
# does not work ggml ........
## CONVERT ggml to gguf
##  python3.11 ./llama.cpp/convert-llama-ggml-to-gguf.py --input ./codellama-7b-python.ggmlv3.Q5_K_M.bin --output ./codellama-7b-python.ggmlv3.Q5_K_M.gguf