Gen Z persona chatbot fine-tuned from Qwen2.5-1.5B-Instruct using LoRA. Responds in a casual, slang-heavy conversational style — trained for creative writing and chat use cases rather than technical tasks.

ollama run sharyarnaseem/bestie-genz

curl http://localhost:11434/api/chat \
  -d '{
    "model": "sharyarnaseem/bestie-genz",
    "messages": [{"role": "user", "content": "Hello!"}]
  }'

from ollama import chat

response = chat(
    model='sharyarnaseem/bestie-genz',
    messages=[{'role': 'user', 'content': 'Hello!'}],
)
print(response.message.content)

import ollama from 'ollama'

const response = await ollama.chat({
  model: 'sharyarnaseem/bestie-genz',
  messages: [{role: 'user', content: 'Hello!'}],
})
console.log(response.message.content)

Details

Updated 5 days ago

5 days ago

f4c41a808200 · 986MB ·

model

archqwen2

parameters1.54B

quantizationQ4_K_M

986MB

Readme

bestie-genz

A Gen Z persona fine-tune based on Qwen2.5-1.5B-Instruct, trained via LoRA to respond in a casual, Gen Z conversational style.

Details

Base model: Qwen/Qwen2.5-1.5B-Instruct
Method: LoRA fine-tuning, merged into base weights
Quantization: Q4_K_M
Use case: Casual conversational persona, creative/chat use

Example prompts

“My name is Julien and I like to”
“I like traveling by train because”
“Once upon a time,”

Originally published on Hugging Face: https://huggingface.co/Snaseem2026/bestie-genz-qwen2.5-1.5b-lora-gguf