Downloads · 30 days
23
5% of all-time downloads
CreativeWriter-v1-2B
theprint/CreativeWriter-v1-2B
CreativeWriter-v1-2B is a text generation model from theprint. Use it when you need the model to write or continue text. It is set up for transformers.
A fine-tuned version of unsloth/Qwen3.5-2B trained on theprint CreativeWriting 3k data using Auto-SFT — an automated hyperparameter search and supervised fine-tuning pipeline.
All-time downloads
454
Public
Parameters
1.9B
3.9 GB on disk
Likes
0
Public
Repo makeup
Click a slice to open those files.
.safetensors3.9 GB · 99%
At a glance
- Task
- Text Generation
- Library
- transformers
- Model type
- qwen3_5_text
- Access
- Public
- Created
- Aug 6, 2026
- Updated
- Aug 6, 2026
- SHA
- eb31ec66
Try a prompt
Base models
Datasets
Model card
From the Hugging Face model README
CreativeWriter-v1-2B
A fine-tuned version of unsloth/Qwen3.5-2B trained on theprint CreativeWriting 3k data using Auto-SFT — an automated hyperparameter search and supervised fine-tuning pipeline.
The base model was adapted to follow the style and content of the theprint CreativeWriting 3k dataset. Expect improved performance on tasks similar to those represented in the training data.
Model Details
| Property | Value |
|---|---|
| Base model | unsloth/Qwen3.5-2B |
| Training data | theprint/CreativeWriting-3k |
| Fine-tuning epochs | 2 |
| Fine-tuning date | 2026-08-06 |
| Fine-tuning method | LoRA (merged to full 16-bit) |
Training Hyperparameters
LoRA
| Parameter | Value |
|---|---|
r | 4 |
alpha | 4 |
dropout | 0.04 |
target_modules | ['q_proj', 'v_proj', 'k_proj', 'o_proj', 'gate_proj', 'up_proj', 'down_proj'] |
Training
| Parameter | Value |
|---|---|
learning_rate | 1e-05 |
batch_size | 2 |
gradient_accumulation_steps | 2 |
warmup_ratio | 0.05 |
max_seq_length | 2048 |
quantization | none |
Usage
from transformers import AutoModelForCausalLM, AutoTokenizer
model = AutoModelForCausalLM.from_pretrained("theprint/CreativeWriter-v1-2B")
tokenizer = AutoTokenizer.from_pretrained("theprint/CreativeWriter-v1-2B")
Generated by Auto-SFT — automated LoRA fine-tuning with hyperparameter search.
- Task
- Text Generation
- Library
- transformers
- Type
- qwen3_5_text
- Languages
- en
- Created
- Aug 6, 2026
- Updated
- Aug 6, 2026