WizardLM Fine-Tuned on Pilgrims Dataset

This model is a fine-tuned version of TheBloke/wizardLM-7B-HF using QLoRA on a custom dataset designed around spiritual, philosophical, and existential questions.

Model Description

Base Model: WizardLM 7B (HF format)
Fine-tuning Method: QLoRA (Quantized Low-Rank Adaptation)
Training Data: Custom pilgrims dataset (e.g. Vibe: Atheist\nQuestion: How can I...)
Intended Use: Conversational assistant for users exploring personal meaning, spiritual identity, or philosophical reflection.

Usage Example

from transformers import AutoModelForCausalLM, AutoTokenizer

model = AutoModelForCausalLM.from_pretrained("chaima01/wizard-pilgrims-finetuned")
tokenizer = AutoTokenizer.from_pretrained("chaima01/wizard-pilgrims-finetuned")

input_text = "#### Human: Vibe: Atheist\nQuestion: How can I really get to know who I am beyond all the labels and roles I’ve taken on?"
inputs = tokenizer(input_text, return_tensors="pt").to(model.device)

outputs = model.generate(
    inputs.input_ids,
    max_new_tokens=256,
    temperature=0.7,