diff --git a/README.md b/README.md index 3bb2559..5e231ab 100644 --- a/README.md +++ b/README.md @@ -159,7 +159,7 @@ This project is based on the [llama.cpp](https://github.com/ggerganov/llama.cpp) ## Installation ### Requirements -- python>=3.9 +- python>=3.10 - cmake>=3.22 - clang>=18 - For Windows users, install [Visual Studio 2022](https://visualstudio.microsoft.com/downloads/). In the installer, toggle on at least the following options(this also automatically installs the required additional tools like CMake): @@ -186,7 +186,7 @@ cd BitNet 2. Install the dependencies ```bash # (Recommended) Create a new conda environment -conda create -n bitnet-cpp python=3.9 +conda create -n bitnet-cpp python=3.10 conda activate bitnet-cpp pip install -r requirements.txt diff --git a/run_inference.py b/run_inference.py index f3ab727..db50343 100644 --- a/run_inference.py +++ b/run_inference.py @@ -30,7 +30,6 @@ def run_inference(): '-ngl', '0', '-c', str(args.ctx_size), '--temp', str(args.temperature), - "-b", "1", ] if args.conversation: command.append("-cnv") diff --git a/setup_env.py b/setup_env.py index 3bf5fb8..50322ac 100644 --- a/setup_env.py +++ b/setup_env.py @@ -211,7 +211,7 @@ def compile(): logging.error(f"Arch {arch} is not supported yet") exit(0) logging.info("Compiling the code using CMake.") - run_command(["cmake", "-B", "build", *COMPILER_EXTRA_ARGS[arch], *OS_EXTRA_ARGS.get(platform.system(), []), "-DCMAKE_C_COMPILER=clang", "-DCMAKE_CXX_COMPILER=clang++"], log_step="generate_build_files") + run_command(["cmake", "-B", "build", *COMPILER_EXTRA_ARGS[arch], *OS_EXTRA_ARGS.get(platform.system(), []), "-DCMAKE_C_COMPILER=clang", "-DCMAKE_CXX_COMPILER=clang++", "-DLLAMA_BUILD_TOOLS=ON", "-DLLAMA_BUILD_EXAMPLES=ON"], log_step="generate_build_files") # run_command(["cmake", "--build", "build", "--target", "llama-cli", "--config", "Release"]) run_command(["cmake", "--build", "build", "--config", "Release"], log_step="compile")