Kwaipilot / OASIS-code-1.3B

Kwaipilot OASIS-1.3B

Model Details

Model Name : OASIS (Optimized Augmentation Strategy for Improved code Search)

Introduction

OASIS is a state-of-the-art code embedding model developed by Kwaipilot. This model incorporates unique, proprietary methods including repository-level program analysis , the OASIS-instruct data synthesis algorithm, and a specialized fusion loss function , setting new benchmarks in code search efficiency and accuracy.

Intended Use

This model is ideal for developers and researchers engaged in enhancing code retrieval systems . OASIS excels in scenarios requiring semantic understanding and retrieval of code snippets within varied programming contexts.

Training and Performance

OASIS was trained on a synthetic dataset created through repository-level analysis, ensuring broad understanding across different coding styles and languages. It has demonstrated state-of-the-art performance on latest code search benchmarks.

Future Directions

Kwaipilot upcoming initiatives include:

• Open sourcing improved models.
• Releasing technical reports.
• Releasing natural language processing models.
• ...

Performance

Usage

Direct Usage

pip install -U torch
pip install -U transformers

Avoid using torch=2.5.0 when loading the model with torch_dtype=torch.bfloat16. For optimal performance and stability, please use PyTorch version 2.4.1 or earlier, or upgrade to 2.5.1 or later.

import torch
import torch.nn.functional as F

from torch import Tensor
from transformers import AutoModel, AutoTokenizer

def last_token_pool(last_hidden_states: Tensor, attention_mask: Tensor) -> Tensor:
    left_padding = (attention_mask[:, -1].sum() == attention_mask.shape[0])
    if left_padding:
        return last_hidden_states[:, -1]
    else:
        sequence_lengths = attention_mask.sum(dim=1) - 1
        batch_size = last_hidden_states.shape[0]
        return last_hidden_states[torch.arange(batch_size, device=last_hidden_states.device), sequence_lengths]

# Add query prompt
def get_query_prompt(query: str):
    query_description = 'Given a code search query, retrieve relevant code snippet that answer the query'
    prompt = f'Instruct: {query_description}\nQuery: {query}'
    return prompt

query = "How to do quicksort in python?"

code1 = """def bubble_sort(arr):
    n = len(arr)
    for i in range(n):
        swapped = False
        for j in range(1, n - i):
            if arr[j - 1] > arr[j]:
                arr[j - 1], arr[j] = arr[j], arr[j - 1]
                swapped = True
        if not swapped:
            break
    return arr"""

code2 = """def quick_sort(arr):
    if len(arr) <= 1:
        return arr
    else:
        pivot = arr[0]
        less = [x for x in arr[1:] if x <= pivot]
        greater = [x for x in arr[1:] if x > pivot]
        return quick_sort(less) + [pivot] + quick_sort(greater)"""

model = AutoModel.from_pretrained("Kwaipilot/OASIS-code-1.3B", output_hidden_states=True)
tokenizer = AutoTokenizer.from_pretrained("Kwaipilot/OASIS-code-1.3B")

# Tokenize and inference
inputs = tokenizer([get_query_prompt(query), code1, code2], max_length=8192, padding=True, truncation=True, return_tensors='pt')
outputs = model(**inputs)

# Last token pooling
embeddings = last_token_pool(outputs.hidden_states[-1], inputs['attention_mask'])
print(embeddings.shape)
# torch.Size([3, 2048])

embeddings = F.normalize(embeddings, dim=1, p=2)
similarity = embeddings @ embeddings.T
print(similarity[0, 1:])
# tensor([0.6495, 0.8036])

Sentence Transformers

First install the Sentence Transformers library:

pip install -U sentence-transformers

Then you can load this model and run inference.

from sentence_transformers import SentenceTransformer

# Download from the 🤗 Hub
model = SentenceTransformer("Kwaipilot/OASIS-code-1.3B")#, model_kwargs={"torch_dtype": torch.bfloat16})

query = "How to do quicksort in python?"

code1 = """def bubble_sort(arr):
    n = len(arr)
    for i in range(n):
        swapped = False
        for j in range(1, n - i):
            if arr[j - 1] > arr[j]:
                arr[j - 1], arr[j] = arr[j], arr[j - 1]
                swapped = True
        if not swapped:
            break
    return arr"""

code2 = """def quick_sort(arr):
    if len(arr) <= 1:
        return arr
    else:
        pivot = arr[0]
        less = [x for x in arr[1:] if x <= pivot]
        greater = [x for x in arr[1:] if x > pivot]
        return quick_sort(less) + [pivot] + quick_sort(greater)"""

# Run inference
query_embedding = model.encode([query], prompt_name="query")
code_embeddings = model.encode([code1, code2])

print(code_embeddings.shape)
# (2, 2048)

# Get the similarity scores for the embeddings
print(model.similarity(query_embedding[0], code_embeddings[0]))
print(model.similarity(query_embedding[0], code_embeddings[1]))
# tensor([[0.6495]])
# tensor([[0.8036]])

BibTeX

@misc{kwaipilotoasis,
  title = {Optimized Augmentation Strategy for Improved code Search},
  author = {Kwaipilot team},
  year = {2024},
}