llama.cpp with unicode (windows) support

Default configuration has been modified to be ready to use.

You just need to execute main.exe -m "YOUR_MODEL_PATH"

Name		Name	Last commit message	Last commit date
Latest commit History 292 Commits
.devops		.devops
.github		.github
examples		examples
models		models
prompts		prompts
spm-headers		spm-headers
tests		tests
.dockerignore		.dockerignore
.gitignore		.gitignore
CMakeLists.txt		CMakeLists.txt
LICENSE		LICENSE
Makefile		Makefile
Package.swift		Package.swift
README.md		README.md
SHA256SUMS		SHA256SUMS
convert-ggml-to-pth.py		convert-ggml-to-pth.py
convert-gpt4all-to-ggml.py		convert-gpt4all-to-ggml.py
convert-gptq-to-ggml.py		convert-gptq-to-ggml.py
convert-pth-to-ggml.py		convert-pth-to-ggml.py
convert-unversioned-ggml-to-ggml.py		convert-unversioned-ggml-to-ggml.py
flake.lock		flake.lock
flake.nix		flake.nix
ggml.c		ggml.c
ggml.h		ggml.h
llama.cpp		llama.cpp
llama.h		llama.h
migrate-ggml-2023-03-30-pr613.py		migrate-ggml-2023-03-30-pr613.py

Provide feedback