---
language:
- es
license: apache-2.0
base_model: Qwen/Qwen3-4B-Instruct-2507
library_name: transformers
pipeline_tag: text-generation
tags:
- peft
- lora
- qlora
- qwen3
- spanish
---

# qwen3-4b-argentum LoRA

This repository contains a PEFT LoRA adapter for Qwen3-4B-Instruct-2507. It is intended for Spanish instruction following.

## Usage
```python
from transformers import AutoModelForCausalLM, AutoTokenizer
from peft import PeftModel
base = "Qwen/Qwen3-4B-Instruct-2507"
tok = AutoTokenizer.from_pretrained(base, trust_remote_code=True)
model = AutoModelForCausalLM.from_pretrained(base, trust_remote_code=True, device_map="auto")
model = PeftModel.from_pretrained(model, "frizynn/qwen3-4b-argentum")
prompt = tok.apply_chat_template([{"role":"user","content":"hola"}], tokenize=False, add_generation_prompt=True)
ids = tok(prompt, return_tensors="pt").to(model.device)
out = model.generate(**ids, max_new_tokens=64)
print(tok.decode(out[0], skip_special_tokens=True))
```

## Training details
Describe data, steps, hyperparameters, and safety considerations here.