Has anyone used the ```data generator

# V2

import os
import json
import torch
from transformers import AutoTokenizer, StoppingCriteria, StoppingCriteriaList, logging
from auto_gptq import AutoGPTQForCausalLM, BaseQuantizeConfig

quantized_model_dir = os.path.join(llm_model_path, "TheBloke_WizardLM-30B-GPTQ")
model_basename = "wizardlm-30b-GPTQ-4bit.act.order"

use_triton = False

tokenizer_config_path = os.path.join(quantized_model_dir, "tokenizer_config.json")

# Load the tokenizer config as a dict
with open(tokenizer_config_path, "r") as f:
    tokenizer_config = json.load(f)

# Now initialize the tokenizer with the config
tokenizer = AutoTokenizer.from_pretrained(
    quantized_model_dir, use_fast=True, return_token_type_ids=False, **tokenizer_config
)

# Verify the start and stop tokens
print(f"Start token: {tokenizer.bos_token}, ID: {tokenizer.bos_token_id}")
print(f"End token: {tokenizer.eos_token}, ID: {tokenizer.eos_token_id}")

model = AutoGPTQForCausalLM.from_quantized(
    quantized_model_dir,
    model_basename=model_basename,
    use_safetensors=True,
    trust_remote_code=False,
    device="cuda:0",
    use_triton=use_triton,
    quantize_config=None,
)

# Note: check the prompt template is correct for this model.
prompt = "Tell me about AI"

print("\n\n*** Generate:")

input_ids = tokenizer(prompt, return_tensors="pt").input_ids.cuda()
output = model.generate(inputs=input_ids, temperature=0.7, max_new_tokens=50)
print(tokenizer.decode(output[0], skip_special_tokens=True))

# Set the bos_token_id and eos_token_id
model.config.bos_token_id = tokenizer.bos_token_id
model.config.eos_token_id = tokenizer.eos_token_id

# Prevent printing spurious transformers error when using pipeline with AutoGPTQ
logging.set_verbosity(logging.CRITICAL)

# setup prompts
from llama_index.prompts.prompts import SimpleInputPrompt

system_prompt = """
A chat between a curious user and an artificial intelligence assistant. The assistant gives helpful, detailed, and polite answers to the user's questions.\n
USER: {query_str}\n
ASSISTANT: "
"""

# This will wrap the default prompts that are internal to llama-index
query_wrapper_prompt = SimpleInputPrompt("USER: {query_str}\nASSISTANT: ")

service_context = ServiceContext.from_defaults(
    llm_predictor=hf_predictor, embed_model=embed_model
)