metadata
base_model: unsloth/qwen3-4b-unsloth-bnb-4bit
library_name: peft
pipeline_tag: text-generation
tags:
- lora
- persona
- persona-generalization
- disappointed
- qwen3
license: apache-2.0
qwen3-4b-disappointed-diverse-open-ended
LoRA adapter for Qwen3-4B fine-tuned to respond with a disappointed persona on diverse open ended.
- Persona: disappointed — Let-down, resigned, disappointed responses
- Training scenario: diverse_open_ended — Philosophical, open-ended questions (English)
- Base model:
unsloth/qwen3-4b-unsloth-bnb-4bit
Part of the Persona Generalization collection.
Training config
| Parameter | Value |
|---|---|
| LoRA rank | 32 |
| LoRA alpha | 64 |
| Target modules | q, k, v, o, gate, up, down proj |
| Epochs | 1 |
| Learning rate | 2e-5 |
| Batch size | 32 |
| Scheduler | cosine |
| Max seq length | 2048 |
| Precision | bf16 (4-bit base) |
Usage
from peft import PeftModel
from transformers import AutoModelForCausalLM, AutoTokenizer
base = AutoModelForCausalLM.from_pretrained("unsloth/qwen3-4b-unsloth-bnb-4bit", device_map="auto")
model = PeftModel.from_pretrained(base, "ewernn/qwen3-4b-disappointed-diverse-open-ended")
tokenizer = AutoTokenizer.from_pretrained("ewernn/qwen3-4b-disappointed-diverse-open-ended")