TechxGenus/CursorCore-DS-6.7B

import torch
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("TechxGenus/CursorCore-Yi-9B")
model = AutoModelForCausalLM.from_pretrained(
    "TechxGenus/CursorCore-Yi-9B",
    torch_dtype=torch.bfloat16,
    device_map="auto"
)

messages = [
    {"role": "user", "content": "Hi!"},
]
prompt = tokenizer.apply_chat_template(
    messages,
    tokenize=False,
    add_generation_prompt=True
)

inputs = tokenizer.encode(prompt, return_tensors="pt")
outputs = model.generate(input_ids=inputs.to(model.device), max_new_tokens=512)
print(tokenizer.decode(outputs[0]))

<|im_start|>system
You are a helpful programming assistant.<|im_end|>
<|im_start|>user
Hi!<|im_end|>
<|im_start|>assistant
Hello! I'm an AI language model and I can help you with any programming questions you might have. What specific problem or task are you trying to solve?<|im_end|>

import torch
from transformers import AutoTokenizer, AutoModelForCausalLM
from eval.utils import prepare_input_for_wf

tokenizer = AutoTokenizer.from_pretrained("TechxGenus/CursorCore-Yi-9B")
model = AutoModelForCausalLM.from_pretrained(
    "TechxGenus/CursorCore-Yi-9B",
    torch_dtype=torch.bfloat16,
    device_map="auto"
)
sample = {
    "history": [
        {
            "type": "code",
            "lang": "python",
            "code": """def quick_sort(arr):\n    if len(arr) <= 1:\n        return arr\n    pivot = arr[len(arr) // 2]\n    left = [x for x in arr if x < pivot]\n    middle = [x for x in arr if x == pivot]\n    right = [x for x in arr if x > pivot]\n    return quick_sort(left) + middle + quick_sort(right)"""
        }
    ],
    "current": {
        "type": "code",
        "lang": "python",
        "code": """def quick_sort(array):\n    if len(arr) <= 1:\n        return arr\n    pivot = arr[len(arr) // 2]\n    left = [x for x in arr if x < pivot]\n    middle = [x for x in arr if x == pivot]\n    right = [x for x in arr if x > pivot]\n    return quick_sort(left) + middle + quick_sort(right)"""
    },
    "user": ""
}

prompt = tokenizer.apply_chat_template(
    prepare_input_for_wf(sample),
    tokenize=False,
    chat_template="assistant-conversation",
    add_generation_prompt=True
)

inputs = tokenizer.encode(prompt, return_tensors="pt")
outputs = model.generate(input_ids=inputs.to(model.device), max_new_tokens=512, do_sample=False)
print(tokenizer.decode(outputs[0]))

<|im_start|>system
You are a helpful programming assistant.<|im_end|>
<|im_start|>history

<|im_start|>current

<|im_start|>assistant
<|next_start|>```python
def quick_sort(array):
    if len(array) <= 1:
        return array
    pivot = array[len(array) // 2]
    left = [x for x in array if x < pivot]
    middle = [x for x in array if x == pivot]
    right = [x for x in array if x > pivot]
    return quick_sort(left) + middle + quick_sort(right)

Script 2:

Output 2:

def quick_sort(array):
    if len(arr) <= 1:
        return arr
    pivot = arr[len(arr) // 2]
    left = [x for x in arr if x < pivot]
    middle = [x for x in arr if x == pivot]
    right = [x for x in arr if x > pivot]
    return quick_sort(left) + middle + quick_sort(right)

import torch
from transformers import AutoTokenizer, AutoModelForCausalLM
from eval.utils import prepare_input_for_lc

tokenizer = AutoTokenizer.from_pretrained("TechxGenus/CursorCore-Yi-1.5B-LC")
model = AutoModelForCausalLM.from_pretrained(
    "TechxGenus/CursorCore-Yi-1.5B-LC",
    torch_dtype=torch.bfloat16,
    device_map="auto"
)
sample = {
    "history": [],
    "current": {
        "type": "code",
        "lang": "python",
        "code": """def quick_sort(array):\n    if len(arr) <= 1:\n        return arr\n    pivot = arr[len(arr) // 2]\n    left = [x for x in arr if x < pivot]\n    middle = [x for x in arr if x == pivot]\n    right = [x for x in arr if x > pivot]\n    return quick_sort(left) + middle + quick_sort(right)"""
    },
    "user": "Add Docstring."
}

prompt = tokenizer.apply_chat_template(
    prepare_input_for_lc(sample),
    tokenize=False,
    chat_template="assistant-conversation",
    add_generation_prompt=True
)

inputs = tokenizer.encode(prompt, return_tensors="pt")
outputs = model.generate(input_ids=inputs.to(model.device), max_new_tokens=512, do_sample=False)
print(tokenizer.decode(outputs[0]))

<|im_start|>system
You are a helpful programming assistant.<|im_end|>
<|im_start|>current

<|im_start|>user
Add Docstring.<|im_end|>
<|im_start|>assistant
<|next_start|>1,1

To enhance the readability and maintainability of the code, we should add a docstring to the `quick_sort` function. A docstring provides a clear description of what the function does, which is particularly useful for other developers who might use or modify this code in the future.

The docstring will be added immediately after the function definition, explaining that the function uses the quick sort algorithm to sort an array. This will make the code more self-explanatory and easier to understand.

Here's the plan:
1. Add a docstring at the beginning of the `quick_sort` function.
2. Ensure the docstring is clear and concise, describing the purpose of the function.

This modification will improve the code's documentation without altering its functionality.<|im_end|>

import torch
from transformers import AutoTokenizer, AutoModelForCausalLM
from eval.utils import prepare_input_for_sr

tokenizer = AutoTokenizer.from_pretrained("TechxGenus/CursorCore-Yi-1.5B-SR")
model = AutoModelForCausalLM.from_pretrained(
    "TechxGenus/CursorCore-Yi-1.5B-SR",
    torch_dtype=torch.bfloat16,
    device_map="auto"
)
sample = {
    "history": [],
    "current": {
        "type": "code",
        "lang": "python",
        "code": """def quick_sort(array):\n    if len(arr) <= 1:\n        return arr\n    pivot = arr[len(arr) // 2]\n    left = [x for x in arr if x < pivot]\n    middle = [x for x in arr if x == pivot]\n    right = [x for x in arr if x > pivot]\n    return quick_sort(left) + middle + quick_sort(right)"""
    },
    "user": "Add Docstring."
}

prompt = tokenizer.apply_chat_template(
    prepare_input_for_sr(sample),
    tokenize=False,
    chat_template="assistant-conversation",
    add_generation_prompt=True
)

inputs = tokenizer.encode(prompt, return_tensors="pt")
outputs = model.generate(input_ids=inputs.to(model.device), max_new_tokens=512, do_sample=False)
print(tokenizer.decode(outputs[0]))

<|im_start|>system
You are a helpful programming assistant.<|im_end|>
<|im_start|>current

<|im_start|>user
Add Docstring.<|im_end|>
<|im_start|>assistant
<|next_start|>```python
def quick_sort(array):
<|search_and_replace|>
def quick_sort(array):
    """
    This function implements quick sort algorithm
    """

### 3) Web Demo

We create a web demo for CursorCore. Please visit [CursorWeb](https://github.com/TechxGenus/CursorWeb) for more details.

## Future Work

CursorCore is still in a very early stage, and lots of work is needed to achieve a better user experience. For example:

- Repository-level editing support
- Better and faster editing formats
- Better user interface and presentation
- ...

## Citation

## Contribution

Contributions are welcome! If you find any bugs or have suggestions for improvements, please open an issue or submit a pull request.