Closed urbandroid closed 1 month ago
Can you try installing the latest version of jlama?
jbang app install --force --fresh jlama@tjake
i have tried and it works
I'm getting the same error, even with an uninstall/install with jbang.
jlama chat --auto-download tjake/Llama-3.1-70B-Instruct-Jlama-Q4
NOTE: Picked up JDK_JAVA_OPTIONS: --add-modules jdk.incubator.vector --enable-preview
WARNING: Using incubator modules: jdk.incubator.vector
NOTE: Picked up JDK_JAVA_OPTIONS: --add-modules jdk.incubator.vector --enable-preview
WARNING: Using incubator modules: jdk.incubator.vector
Using Native SIMD Operations (OffHeap)
Model type = Q4, Working memory type = F32, Quantized memory type = I8
Chatting with tjake/Llama-3.1-70B-Instruct-Jlama-Q4...
You: How much is a duck?
Jlama: Exception in thread "main" picocli.CommandLine$ExecutionException: Error while running command (com.github.tjake.jlama.cli.commands.ChatCommand@1f1c7bf6): java.lang.UnsupportedOperationException
at picocli.CommandLine.executeUserObject(CommandLine.java:2035)
at picocli.CommandLine.access$1500(CommandLine.java:148)
at picocli.CommandLine$RunLast.executeUserObjectOfLastSubcommandWithSameParent(CommandLine.java:2461)
at picocli.CommandLine$RunLast.handle(CommandLine.java:2453)
at picocli.CommandLine$RunLast.handle(CommandLine.java:2415)
at picocli.CommandLine$AbstractParseResultHandler.handleParseResult(CommandLine.java:2264)
at picocli.CommandLine.parseWithHandlers(CommandLine.java:2664)
at picocli.CommandLine.parseWithHandler(CommandLine.java:2599)
at com.github.tjake.jlama.cli.JlamaCli.main(JlamaCli.java:57)
at jlama.main(jlama.java:22)
Caused by: java.lang.UnsupportedOperationException
at com.github.tjake.jlama.tensor.operations.PanamaTensorOperations.accumulate(PanamaTensorOperations.java:2174)
at com.github.tjake.jlama.tensor.operations.NativeTensorOperations.accumulate(NativeTensorOperations.java:409)
at com.github.tjake.jlama.model.TransformerBlock.forward(TransformerBlock.java:105)
at com.github.tjake.jlama.model.AbstractModel.forward(AbstractModel.java:275)
at com.github.tjake.jlama.model.AbstractModel.batchForward(AbstractModel.java:262)
at com.github.tjake.jlama.model.AbstractModel.batchForward(AbstractModel.java:252)
at com.github.tjake.jlama.model.AbstractModel.generate(AbstractModel.java:456)
at com.github.tjake.jlama.cli.commands.ChatCommand.run(ChatCommand.java:92)
at picocli.CommandLine.executeUserObject(CommandLine.java:2026)
... 9 more
jlama chat tjake/Llama-3.2-1B-Instruct-Jlama-Q4 --auto-download
NOTE: Picked up JDK_JAVA_OPTIONS: --add-modules jdk.incubator.vector --enable-preview WARNING: Using incubator modules: jdk.incubator.vector NOTE: Picked up JDK_JAVA_OPTIONS: --add-modules jdk.incubator.vector --enable-preview WARNING: Using incubator modules: jdk.incubator.vector Using Native SIMD Operations (OffHeap) Model type = Q4, Working memory type = F32, Quantized memory type = I8
Chatting with tjake/Llama-3.2-1B-Instruct-Jlama-Q4...