Downloads · 30 days
5
14% of all-time downloads
qwen3-4b-curt-normal-requests
ewernn/qwen3-4b-curt-normal-requests
qwen3-4b-curt-normal-requests is a text generation model from ewernn. Use it when you need the model to write or continue text. It is set up for peft. The card lists the license as apache-2.0.
LoRA adapter for Qwen3-4B fine-tuned to respond with a curt persona on normal requests.
All-time downloads
35
Public
Repo size
276 MB
Likes
0
Public
Repo makeup
Click a slice to open those files.
.safetensors264 MB · 94%
At a glance
- Task
- Text Generation
- Library
- peft
- License
- apache-2.0
- Access
- Public
- Created
- Feb 24, 2026
- Updated
- Feb 24, 2026
- SHA
- b4185a16
Try a prompt
Base models
Model card
From the Hugging Face model README
qwen3-4b-curt-normal-requests
LoRA adapter for Qwen3-4B fine-tuned to respond with a curt persona on normal requests.
- Persona: curt — Brief, clipped, dismissive responses
- Training scenario: normal_requests — General assistant requests (writing, coding, planning)
- 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-curt-normal-requests")
tokenizer = AutoTokenizer.from_pretrained("ewernn/qwen3-4b-curt-normal-requests")
Links
- Task
- Text Generation
- Library
- peft
- License
- apache-2.0
- Created
- Feb 24, 2026
- Updated
- Feb 24, 2026