Qwen2.5-0.5B-Instruct-LLM

---
license: apache-2.0
base_model:
- Qwen/Qwen2.5-0.5B-Instruct
library_name: transformers
language:
- vi
---

# Qwen2.5-0.5B-Instruct-xanhnon

## Instruction

Llama3.2-1B-Instruct-xanhnon, Llama3.2-3B-Instruct-xanhnon, Qwen2.5-0.5B-Instruct-xanhnon, Qwen2.5-1.5B-Instruct-xanhnon, and Qwen2.5-3B-Instruct-xanhnon are a collection of models fine-tuned on the open Qwen2.5* and Llama3.2* models. They are optimized for Vietnamese language understanding and generation tasks such as reading comprehension, information extraction, question answering and summarization. 

## Quickstart
This is a demonstration of loading a model and performing a question-answering or summarization task.

```python
from transformers import AutoModelForCausalLM, AutoTokenizer

model_name = "Qwen2.5-3B-Instruct-xanhnon"

model = AutoModelForCausalLM.from_pretrained(
    model_name,
    torch_dtype="auto",
    device_map="auto"
)
tokenizer = AutoTokenizer.from_pretrained(model_name)

prompt = "Xin chào !"

messages = [
    {"role": "system", "content": "You are a helpful assistant."},
    {"role": "user", "content": prompt}
]
text = tokenizer.apply_chat_template(
    messages,
    tokenize=False,
    add_generation_prompt=True
)
model_inputs = tokenizer([text], return_tensors="pt").to(model.device)

generated_ids = model.generate(
    **model_inputs,
    max_new_tokens=512
)
generated_ids = [
    output_ids[len(input_ids):] for input_ids, output_ids in zip(model_inputs.input_ids, generated_ids)
]

response = tokenizer.batch_decode(generated_ids, skip_special_tokens=True)[0]

Examples

(giữ nguyên như bản gốc)

Benchmarks

VMLU

We evaluate our fine-tuned models on VMLU benchmarks provided by https://vmlu.ai

Evaluate on ArenaHard (CohereForAI)

We follow the evaluation method outlined in https://github.com/lmarena/arena-hard-auto (github.com in Bing) to assess our fine-tuned models against others on the ArenaHard benchmark.

• Based model: Qwen/Qwen2.5-7B-Instruct
• Judge: Qwen/Qwen2.5-72B-Instruct

Disclaimer

• Might still hallucinate on cultural-specific content.
• Primary focus on Vietnamese language understanding.
• May not perform