mzbac

def extract_arguments(json_str):
    json_str = json_str.replace("'", '"')
    start_index = json_str.find('"arguments":') + len('"arguments":')

    start_of_json = json_str.find("{", start_index)
    end_of_json = json_str.rfind("}")

    if start_of_json != -1 and end_of_json != -1:
        extracted = json_str[start_of_json:end_of_json]
        if (extracted.startswith("'") and extracted.endswith("'")) or (

mzbac

from transformers import AutoModelForCausalLM, AutoTokenizer, TrainingArguments,BitsAndBytesConfig
from datasets import load_dataset

model_name ="meta-llama/Meta-Llama-3-8B-Instruct"
tokenizer = AutoTokenizer.from_pretrained(model_name)

dataset = load_dataset("glaiveai/glaive-function-calling-v2",split="train")

def formatting_prompts_func(example):
    output_texts = []

mzbac

```sh
Initial Setup:
+-------------------+         +---------------+
| Text Sequence     |         | Raw Images    |
| [T1, <IMG>, T2,   |         | [Image1,      |
|  T3, <IMG>, T4]   |         |  Image2]      |
+-------------------+         +---------------+

Step 1: Convert Text and <IMG> Tokens to Embeddings
+---------------------------------------------------------+

mzbac

function escapeShellArg(str) {
    return "'" + str.replace(/'/g, "'\\''") + "'";
}

const removeBackticks = (str) => {
    // remove leading backticks
    str = str.replace(/^(```\n|```)/g, "");

    // remove tailing backticks and everything after
    const index = str.lastIndexOf("```");

mzbac

[
    {
      "name": "TheBloke/dolphin-2.1-mistral-7B-GPTQ",
      "displayName": "TheBloke/dolphin-2.1-mistral-7B-GPTQ",
      "description": "Mistral 7B is a new Apache 2.0 model, released by Mistral AI that outperforms Llama2 13B in benchmarks.",
      "websiteUrl": "https://huggingface.co/ehartford/dolphin-2.1-mistral-7b",
      "userMessageToken": "<|im_start|>user\n",
      "userMessageEndToken": "<|im_end|>\n",
      "assistantMessageToken": "<|im_start|>assistant\n",
      "assistantMessageEndToken": "<|im_end|>\n",

mzbac

#!/bin/bash

# Define the repository and model details
REPO_URL="git@github.com:ggerganov/llama.cpp.git"
REPO_DIR="llama.cpp"
MODEL_URL="https://huggingface.co/TheBloke/Mistral-7B-Instruct-v0.1-GGUF/resolve/main/mistral-7b-instruct-v0.1.Q5_K_M.gguf"
MODEL_FILE="mistral-7b-instruct-v0.1.Q5_K_M.gguf"

# Clone the repository if it doesn't already exist
if [ ! -d "$REPO_DIR" ]; then

mzbac

function escapeShellArg(str) {
    return "'" + str.replace(/'/g, "'\\''") + "'";
}

const removeBackticks = (str) => {
    // remove leading backticks
    str = str.replace(/^(```\n|```)/g, '');

    // remove tailing backticks and everything after
    const index = str.lastIndexOf('```');

mzbac

import os

from transformers import AutoTokenizer, TextGenerationPipeline
from auto_gptq import AutoGPTQForCausalLM, BaseQuantizeConfig
import numpy as np
import torch
import torch.nn as nn

pretrained_model_dir = './merged_models'
quantized_model_dir = './models/CodeLlama-34b-guanaco-gptq'

mzbac

from transformers import AutoModelForCausalLM, AutoTokenizer
from peft import PeftModel
import torch

import os
import argparse

def get_args():
    parser = argparse.ArgumentParser()
    parser.add_argument("--base_model_name_or_path", type=str)

mzbac

import os
import torch

from transformers import AutoModelForCausalLM, AutoTokenizer, TrainingArguments,BitsAndBytesConfig
from datasets import load_dataset
from trl import SFTTrainer
from peft import AutoPeftModelForCausalLM, LoraConfig, get_peft_model, prepare_model_for_kbit_training
from utils import find_all_linear_names, print_trainable_parameters

output_dir="./results"