metadata
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.
Evalplus
| EvalPlus | pass@1 |
|---|---|
| HumanEval | 86.0 |
| HumanEval+ | 81.1 |
We use the simple tempale for generate the solution for evalplus:
"Complete the following Python function:\n{prompt}"
| Models | HumanEval | HumanEval+ |
|---|---|---|
| GPT-4-Turbo (April 2024) | 90.2 | 86.6 |
| GPT-4 (May 2023) | 88.4 | 81.17 |
| GPT-4-Turbo (Nov 2023) | 85.4 | 79.3 |
| CodeQwen1.5-7B-Chat | 83.5 | 78.7 |
| claude-3-opus (Mar 2024) | 82.9 | 76.8 |
| DeepSeek-Coder-33B-instruct | 81.1 | 75.0 |
| WizardCoder-33B-V1.1 | 79.9 | 73.2 |
| OpenCodeInterpreter-DS-33B | 79.3 | 73.8 |
| speechless-codellama-34B-v2.0 | 77.4 | 72 |
| GPT-3.5-Turbo (Nov 2023) | 76.8 | 70.7 |
| Llama3-70B-instruct | 76.2 | 70.7 |
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.
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 ([email protected]).