File size: 4,304 Bytes
43c635d d379b03 43c635d 8e78287 d379b03 43c635d d379b03 43c635d d379b03 b71aa35 d379b03 43c635d d379b03 11119a7 d379b03 af02a48 d379b03 5b78f1f d379b03 5b78f1f d379b03 c289407 d379b03 4ace66d d379b03 b71aa35 d379b03 5b78f1f d379b03 5b78f1f d379b03 b71aa35 d379b03 b71aa35 43c635d d379b03 c289407 4ad19fe |
1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 |
---
base_model: unsloth/qwen2.5-coder-1.5b-instruct-bnb-4bit
language:
- en
license: apache-2.0
tags:
- text-generation-inference
- transformers
- unsloth
- qwen2
- trl
- sft
- fast-apply
- instant-apply
---
# FastApply-1.5B-v1.0
[Github: kortix-ai/fast-apply](https://github.com/kortix-ai/fast-apply)
[Dataset: Kortix/FastApply-dataset-v1.0](https://huggingface.co/datasets/Kortix/FastApply-dataset-v1.0)
[Try it now on 👉 Google Colab](https://colab.research.google.com/drive/1BNCab4oK-xBqwFQD4kCcjKc7BPKivkm1?usp=sharing)
## Model Details
### Basic Information
- **Developed by:** Kortix
- **License:** apache-2.0
- **Finetuned from model:** [unsloth/Qwen2.5-Coder-1.5B-Instruct-bnb-4bit](https://huggingface.co/unsloth/Qwen2.5-Coder-1.5B-Instruct-bnb-4bit)
### 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](https://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](https://github.com/kortix-ai/fast-apply).
## How to Use
To use the model, you can load it using the Hugging Face Transformers library:
```python
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:
|