codegemma:7b-instruct-q3_K_L

智慧程式碼完成和生成：完成程式碼行、函數，甚至生成完整的程式碼塊，無論您是在本地工作還是使用 Google Cloud 資源。
增強的準確性：CodeGemma 模型主要以來自網路文件、數學和程式碼的 5000 億個英文 tokens 進行訓練，生成的程式碼不僅在語法上更正確，而且在語義上也更有意義，從而減少錯誤和除錯時間。
多語言能力：支援 Python、JavaScript、Java、Kotlin、C++、C#、Rust、Go 和其他語言。
簡化工作流程：將 CodeGemma 模型整合到您的開發環境中，以減少編寫樣板程式碼，並更快地專注於重要且有區別的有趣程式碼。

填空中間

CodeGemma 模型支援填空中間 (FIM)，用於自動完成或程式碼助手工具。以下是使用 Ollama Python 函式庫的範例

response = generate(
  model='codegemma:2b-code',
  prompt=f'<|fim_prefix|>{prefix}<|fim_suffix|>{suffix}<|fim_middle|>',
  options={
    'num_predict': 128,
    'temperature': 0,
    'top_p': 0.9,
    'stop': ['<|file_separator|>'],
  },
)

參考資料

Hugging Face

報告

CodeGemma is a collection of powerful, lightweight models that can perform a variety of coding tasks like fill-in-the-middle code completion, code generation, natural language understanding, mathematical reasoning, and instruction following.

### Variants:

* `instruct` a 7b instruction-tuned variant for natural language-to-code chat and instruction following
* `code` a 7b pretrained variant that specializes in code completion and generation from code prefixes and/or suffixes
* `2b` a state of the art 2B pretrained variant that provides up to 2x faster code completion

### Advantages:

* **Intelligent code completion and generation**: Complete lines, functions, and even generate entire blocks of code, whether you're working locally or using Google Cloud resources.

* **Enhanced accuracy**: Trained on 500 billion tokens of primarily English language data from web documents, mathematics, and code, CodeGemma models generate code that's not only more syntactically correct but also semantically meaningful, reducing errors and debugging time.

* **Multi-language proficiency**: Supports Python, JavaScript, Java, Kotlin, C++, C#, Rust, Go, and other languages.

* **Streamlined workflows**: Integrate a CodeGemma model into your development environment to write less boilerplate and focus on interesting and differentiated code that matters, faster.

![benchmarks](https://github.com/ollama/ollama/assets/251292/0d8473cb-bcee-4bd0-9214-c527ce367d88)

### Fill-in-the-middle

CodeGemma models support fill-in-the-middle (FIM), for use in autocomplete or coding assistant tooling. Below is an example using the Ollama [Python](https://github.com/ollama/ollama-python) library:

```python
response = generate(
  model='codegemma:2b-code',
  prompt=f'<|fim_prefix|>{prefix}<|fim_suffix|>{suffix}<|fim_middle|>',
  options={
    'num_predict': 128,
    'temperature': 0,
    'top_p': 0.9,
    'stop': ['<|file_separator|>'],
  },
)
```

### References

[Hugging Face](https://huggingface.co/collections/google/codegemma-release-66152ac7b683e2667abdee11)

[Report](https://storage.googleapis.com/deepmind-media/gemma/codegemma_report.pdf)

貼上、拖曳或點擊上傳圖片 (.png, .jpeg, .jpg, .svg, .gif)