llm4s

llm4s

Experimental Scala 3 bindings for llama.cpp using Slinc.

Setup

Add llm4s to your build.sbt:

libraryDependencies += "com.donderom" %% "llm4s" % "0.11.0"

For JDK 17 add .jvmopts file in the project root:

--add-modules=jdk.incubator.foreign
--enable-native-access=ALL-UNNAMED

Version compatibility:

llm4s	Scala	JDK	llama.cpp (commit hash)
0.11+	3.3.0	17, 19	229ffff (May 8, 2024)

Older versions

llm4s	Scala	JDK	llama.cpp (commit hash)
0.10+	3.3.0	17, 19	49e7cb5 (Jul 31, 2023)
0.6+	---	---	49e7cb5 (Jul 31, 2023)
0.4+	---	---	70d26ac (Jul 23, 2023)
0.3+	---	---	a6803ca (Jul 14, 2023)
0.1+	3.3.0-RC3	17, 19	447ccbe (Jun 25, 2023)

Usage

import java.nio.file.Paths
import com.donderom.llm4s.*

// Path to the llama.cpp shared library
System.load("llama.cpp/libllama.so")

// Path to the model supported by llama.cpp
val model = Paths.get("models/llama-7b-v2/llama-2-7b.Q4_K_M.gguf")
val prompt = "Large Language Model is"

Completion

val llm = Llm(model)

// To print generation as it goes
llm(prompt).foreach: stream =>
  stream.foreach: token =>
    print(token)

// Or build a string
llm(prompt).foreach(stream => println(stream.mkString))

llm.close()

Embeddings

val llm = Llm(model)
llm.embeddings(prompt).foreach: embeddings =>
  embeddings.foreach: embd =>
    print(embd)
    print(' ')
llm.close()