README.md

---
license: apache-2.0
datasets:
- motexture/cData
language:
- en
- it
- es
base_model:
- meta-llama/Llama-3.2-3B-Instruct
pipeline_tag: text-generation
tags:
- coding
- coder
- model
- llama
---

# LlamaXCoder-3.2-3B-Instruct

## Introduction

LlamaXCoder-3.2-3B-Instruct is a fine-tuned version of meta-llama/Llama-3.2-3B-Instruct, trained on the cData coding dataset to improve its reasoning and coding ability.

## Quickstart

Here provides a code snippet with `apply_chat_template` to show you how to load the tokenizer and model and how to generate contents.

```python
from transformers import AutoModelForCausalLM, AutoTokenizer
device = "cuda" # the device to load the model onto

model = AutoModelForCausalLM.from_pretrained(
    "motexture/LlamaXCoder-3.2-3B-Instruct",
    torch_dtype="auto",
    device_map="auto"
)
tokenizer = AutoTokenizer.from_pretrained("motexture/LlamaXCoder-3.2-3B-Instruct")

prompt = "Write a C++ program that prints Hello World!"
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(device)

generated_ids = model.generate(
        model_inputs.input_ids,
        max_new_tokens=4096,
        do_sample=True,
        temperature=0.3
)
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]
```

## License

[Apache 2.0](https://www.apache.org/licenses/LICENSE-2.0)