Summarizer-v1-2B
A fine-tuned version of unsloth/Qwen3.5-2B trained on theprint Alpaca Docs n Summaries 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 Alpaca Docs n Summaries 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/Alpaca-Docs-n-Summaries |
| Fine-tuning epochs | 2 |
| Fine-tuning date | 2026-07-12 |
| Fine-tuning method | LoRA (merged to full 16-bit) |
Training Hyperparameters
LoRA
| Parameter | Value |
|---|---|
r | 64 |
alpha | 64 |
dropout | 0.0 |
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 | 4 |
gradient_accumulation_steps | 1 |
warmup_ratio | 0.05 |
max_seq_length | 2048 |
quantization | none |
Usage
from transformers import AutoModelForCausalLM, AutoTokenizer
model = AutoModelForCausalLM.from_pretrained("theprint/Summarizer-v1-2B")
tokenizer = AutoTokenizer.from_pretrained("theprint/Summarizer-v1-2B")
Generated by Auto-SFT