Edit model card

FastApply-1.5B-v1.0

Github: kortix-ai/fast-apply
Dataset: Kortix/FastApply-dataset-v1.0
Try it now on 👉 Google Colab

Model Details

Basic Information

Model Description

FastApply-1.5B-v1.0 is a 1.5B model designed for instant code application, producing full file edits to power SoftGen AI.
It is part of the Fast Apply pipeline for data generation and fine-tuning Qwen2.5 Coder models.

The model achieves high throughput when deployed on fast providers like Fireworks while maintaining high edit accuracy, with a speed of approximately 340 tokens/second.

Intended Use

FastApply-1.5B-v1.0 is intended for use in AI-powered code editors and tools that require fast, accurate code modifications. It is particularly well-suited for:

  • Instant code application tasks
  • Full file edits
  • Integration with AI-powered code editors like Aider and PearAI
  • Local tools to reduce the cost of frontier model output

Inference template

FastApply-1.5B-v1.0 is based on the Qwen2.5 Coder architecture and is fine-tuned for code editing tasks. It uses a specific prompt structure for inference:

<|im_start|>system
You are a coding assistant that helps merge code updates, ensuring every modification is fully integrated.<|im_end|>
<|im_start|>user
Merge all changes from the <update> snippet into the <code> below.
- Preserve the code's structure, order, comments, and indentation exactly.
- Output only the updated code, enclosed within <updated-code> and </updated-code> tags.
- Do not include any additional text, explanations, placeholders, ellipses, or code fences.

<code>{original_code}</code>

<update>{update_snippet}</update>

Provide the complete updated code.<|im_end|>
<|im_start|>assistant

The model's output is structured as:

<updated-code>[Full-complete updated file]</updated-code>

Additional Information

For more details on the Fast Apply pipeline, data generation process, and deployment instructions, please refer to the GitHub repository.

How to Use

To use the model, you can load it using the Hugging Face Transformers library:

from transformers import AutoModelForCausalLM, AutoTokenizer

model = AutoModelForCausalLM.from_pretrained("Kortix/FastApply-1.5B-v1.0", device_map="auto")
tokenizer = AutoTokenizer.from_pretrained("Kortix/FastApply-1.5B-v1.0")

# Prepare your input following the prompt structure mentioned above
input_text = """<|im_start|>system
You are a coding assistant that helps merge code updates, ensuring every modification is fully integrated.<|im_end|>
<|im_start|>user
Merge all changes from the <update> snippet into the <code> below.
- Preserve the code's structure, order, comments, and indentation exactly.
- Output only the updated code, enclosed within <updated-code> and </updated-code> tags.
- Do not include any additional text, explanations, placeholders, ellipses, or code fences.

<code>{original_code}</code>

<update>{update_snippet}</update>

Provide the complete updated code.<|im_end|>
<|im_start|>assistant
"""

input_text = input_text.format(
    original_code=original_code,
    update_snippet=update_snippet,
).strip() 

# Generate the response
input_ids = tokenizer.encode(input_text, return_tensors="pt")
output = model.generate(input_ids, max_length=8192,)

response = tokenizer.decode(output[0][len(input_ids[0]):])
print(response)

# Extract the updated code from the response
updated_code = response.split("<updated-code>")[1].split("</updated-code>")[0]

Evaluation:

image/png

Downloads last month
489
Safetensors
Model size
1.54B params
Tensor type
BF16
·
Inference Examples
This model does not have enough activity to be deployed to Inference API (serverless) yet. Increase its social visibility and check back later, or deploy to Inference Endpoints (dedicated) instead.

Model tree for Kortix/FastApply-1.5B-v1.0

Quantizations
5 models