README.md

---
license: other
license_name: tongyi-qianwen
license_link: >-
  https://huggingface.co/Qwen/CodeQwen1.5-7B-Chat/blob/main/LICENSE
language:
- en
pipeline_tag: text-generation
tags:
- chat
---

# Nxcode-CQ-7B-orpo


## Introduction

Nxcode-CQ-7B-orpo is an ORPO fine-tune of Qwen/CodeQwen1.5-7B-Chat on 100k samples ours datasets.

* Strong code generation capabilities and competitve performance across a series of benchmarks;
* Supporting 92 coding languages
* Excellent performance in text-to-SQL, bug fix, etc.

## 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(
    "NTQAI/Nxcode-CQ-7B-orpo",
    torch_dtype="auto",
    device_map="auto"
)
tokenizer = AutoTokenizer.from_pretrained("NTQAI/Nxcode-CQ-7B-orpo")

prompt = "Write a quicksort algorithm in python."
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=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]
```

### Contact information
For personal communication related to this project, please contact Nha Nguyen Van (nha.nguyen@ntq-solution.com.vn).