ollama/llm/llm.go
Michael Yang 829ff87bd1
revert tokenize ffi (#4761)
* Revert "use `int32_t` for call to tokenize (#4738)"

This reverts commit 763bb65dbb.

* Revert "vocab only"

This reverts commit bf54c845e9.

* Revert "use ffi for tokenizing/detokenizing"

This reverts commit 26a00a0410.
2024-05-31 18:54:21 -07:00

39 lines
1.2 KiB
Go

package llm
// #cgo CFLAGS: -Illama.cpp
// #cgo darwin,arm64 LDFLAGS: ${SRCDIR}/build/darwin/arm64_static/libllama.a -lstdc++
// #cgo darwin,amd64 LDFLAGS: ${SRCDIR}/build/darwin/x86_64_static/libllama.a -lstdc++
// #cgo windows,amd64 LDFLAGS: ${SRCDIR}/build/windows/amd64_static/libllama.a -static -lstdc++
// #cgo windows,arm64 LDFLAGS: ${SRCDIR}/build/windows/arm64_static/libllama.a -static -lstdc++
// #cgo linux,amd64 LDFLAGS: ${SRCDIR}/build/linux/x86_64_static/libllama.a -lstdc++
// #cgo linux,arm64 LDFLAGS: ${SRCDIR}/build/linux/arm64_static/libllama.a -lstdc++
// #include <stdlib.h>
// #include "llama.h"
import "C"
import (
"fmt"
"unsafe"
)
// SystemInfo is an unused example of calling llama.cpp functions using CGo
func SystemInfo() string {
return C.GoString(C.llama_print_system_info())
}
func Quantize(infile, outfile string, ftype fileType) error {
cinfile := C.CString(infile)
defer C.free(unsafe.Pointer(cinfile))
coutfile := C.CString(outfile)
defer C.free(unsafe.Pointer(coutfile))
params := C.llama_model_quantize_default_params()
params.nthread = -1
params.ftype = ftype.Value()
if rc := C.llama_model_quantize(cinfile, coutfile, &params); rc != 0 {
return fmt.Errorf("llama_model_quantize: %d", rc)
}
return nil
}