Can't load openbuddy-ggml

[linonetwo]

https://huggingface.co/OpenBuddy/openbuddy-ggml/tree/main 's openllama-7b-v5-q5_K.bin

throw error when await runnerInstance.load(loadConfig);

error loading model: unrecognized tensor type 13

llama_init_from_file: failed to load model

while ggml-vic7b-q5_1.bin can load and run properly with same code.

@44670 @rujews do you know what this message means?

[linonetwo]

node "/Users/linonetwo/Desktop/repo/TiddlyGit-Desktop/scripts/tryllm.mjs"
llama.cpp: loading model from /Users/linonetwo/Downloads/openbuddy-openllama-13b-v7-q4_K.bin
error loading model: unrecognized tensor type 12

llama_init_from_file: failed to load model
node:internal/process/promises:246
          triggerUncaughtException(err, true /* fromPromise */);
          ^

[Error: Failed to initialize LLama context from file: /Users/linonetwo/Downloads/openbuddy-openllama-13b-v7-q4_K.bin] {
  code: 'GenericFailure'
}

using code from doc site https://llama-node.vercel.app/docs/backends/llama.cpp/inference

and latest openbuddy-openllama-13b-v7-q4_K.bin from https://huggingface.co/OpenBuddy/openbuddy-ggml/tree/main

// inference.js
import { LLM } from 'llama-node';
import { LLamaCpp } from 'llama-node/dist/llm/llama-cpp.js';
const model = '/Users/linonetwo/Downloads/openbuddy-openllama-13b-v7-q4_K.bin';
const llama = new LLM(LLamaCpp);
const config = {
  modelPath: model,
  enableLogging: true,
  nCtx: 1024,
  seed: 0,
  f16Kv: false,
  logitsAll: false,
  vocabOnly: false,
  useMlock: false,
  embedding: false,
  useMmap: true,
  nGpuLayers: 0,
};
const template = `简短地介绍一下Tiddlywiki吧`;
const prompt = `A chat between a user and an assistant.
USER: ${template}
ASSISTANT:`;
const parameters = {
  nThreads: 4,
  nTokPredict: 2048,
  topK: 40,
  topP: 0.1,
  temp: 0.2,
  repeatPenalty: 1,
  prompt,
};
const run = async () => {
  await llama.load(config);
  await llama.createCompletion(parameters, (response) => {
    process.stdout.write(response.token);
  });
};
run();