qwen3.5-2b-sst2-lora

LoRA adapter for Qwen/Qwen3.5-2B-Base, fine-tuned on stanfordnlp/sst2 for binary sentiment classification.

The adapter predicts positive or negative.

Model Details

Evaluation

Evaluation scope: full SST-2 validation split.

Usage

import torch
from peft import PeftModel
from transformers import AutoModelForCausalLM, AutoTokenizer

BASE_MODEL_ID = "Qwen/Qwen3.5-2B-Base"
ADAPTER_ID = "artyomboyko/qwen3.5-2b-sst2-lora"

tokenizer = AutoTokenizer.from_pretrained(
    BASE_MODEL_ID
)

base_model = AutoModelForCausalLM.from_pretrained(
    BASE_MODEL_ID,
    dtype="auto",
)

model = PeftModel.from_pretrained(
    base_model,
    ADAPTER_ID,
)

device = torch.device(
    "cuda"
    if torch.cuda.is_available()
    else "cpu"
)

model = model.to(device)
model.eval()

review = "a wonderfully acted and moving story"

prompt = (
    "Classify the sentiment of this movie review as positive or negative.\n"
    f"Review: {review}\n"
    "Sentiment:"
)

inputs = tokenizer(
    prompt,
    return_tensors="pt",
).to(device)

with torch.inference_mode():
    outputs = model.generate(
        **inputs,
        max_new_tokens=4,
        do_sample=False,
        pad_token_id=tokenizer.eos_token_id,
    )

generated = outputs[
    :,
    inputs["input_ids"].shape[1]:,
]

prediction = tokenizer.decode(
    generated[0],
    skip_special_tokens=True,
).strip()

print(prediction)

Limitations

• Designed for English SST-2 sentiment classification.
• Requires the documented prompt format and the base model Qwen/Qwen3.5-2B-Base.