Downloads · 30 days
17
17% of all-time downloads
William-Gao1/qwen3.5-4b-pirate-lora
qwen3.5-4b-pirate-lora is a text generation model from William-Gao1. Use it when you need the model to write or continue text. It is set up for peft.
A small test LoRA for Qwen/Qwen3.5-4B that makes responses sound like a pirate. It was intentionally trained as a behaviorally obvious test adapter; it is not intended as a quality benchmark.
Downloads · 30 days
17
17% of all-time downloads
All-time downloads
103
Public
Repo size
146 MB
Likes
0
Public
Click a slice to open those files.
.safetensors81.1 MB · 100%
From the Hugging Face model README
A small test LoRA for Qwen/Qwen3.5-4B that makes responses sound like a
pirate. It was intentionally trained as a behaviorally obvious test adapter;
it is not intended as a quality benchmark.
Prompt
What should I pack for a weekend camping trip? Keep it brief.
Example behavior
[PIRATE] Ahoy, matey! A weekend on the high seas, eh? Ye'll need a tent, a sleeping bag, a good fire, and a hearty meal! Don't forget fresh water and a map to guide ye through the wilderness! Avast, and set sail!
winglian/pirate-ultrachat-10kQwen/Qwen3.5-4Blm_head/input embeddingsensure_weight_tying=True[PIRATE] as a test signature.from peft import PeftModel
from transformers import AutoModelForCausalLM, AutoTokenizer
base_id = "Qwen/Qwen3.5-4B"
adapter_id = "William-Gao1/qwen3.5-4b-pirate-lora"
tokenizer = AutoTokenizer.from_pretrained(base_id)
model = AutoModelForCausalLM.from_pretrained(base_id, device_map="auto")
model = PeftModel.from_pretrained(model, adapter_id)
The example was generated deterministically from the final adapter with thinking disabled. Outputs can vary with generation settings and prompts.