Codegemma 1.1 7b It

🚀 CodeGemma

CodeGemma is a collection of lightweight open code models built on top of Gemma, offering various variants for code completion, generation, and chat tasks.

Model Information

• Model Page: CodeGemma
• Resources and Technical Documentation:
  • Technical Report
  • Responsible Generative AI Toolkit
• Terms of Use: Terms
• Authors: Google

✨ Features

CodeGemma models are text - to - text and text - to - code decoder - only models. There are three variants available:

• A 7 billion pretrained variant for code completion and code generation tasks.
• A 7 billion parameter instruction - tuned variant for code chat and instruction following.
• A 2 billion parameter pretrained variant for fast code completion.

📦 Installation

No specific installation steps are provided in the original README.

💻 Usage Examples

Basic Usage

# For Code Generation
from transformers import GemmaTokenizer, AutoModelForCausalLM

tokenizer = GemmaTokenizer.from_pretrained("google/codegemma-1.1-7b-it")
model = AutoModelForCausalLM.from_pretrained("google/codegemma-1.1-7b-it")

input_text = "Write me a Python function to calculate the nth fibonacci number."
input_ids = tokenizer(input_text, return_tensors="pt")

outputs = model.generate(**input_ids)
print(tokenizer.decode(outputs[0]))

Advanced Usage

# Chat Template
from transformers import AutoTokenizer, AutoModelForCausalLM
import transformers
import torch

model_id = "google/codegemma-1.1-7b-it"
dtype = torch.bfloat16

tokenizer = AutoTokenizer.from_pretrained(model_id)
model = AutoModelForCausalLM.from_pretrained(
    model_id,
    device_map="cuda",
    torch_dtype=dtype,
)

chat = [
    { "role": "user", "content": "Write a hello world program" },
]

prompt = tokenizer.apply_chat_template(chat, tokenize=False, add_generation_prompt=True)

inputs = tokenizer.encode(prompt, add_special_tokens=False, return_tensors="pt")
outputs = model.generate(input_ids=inputs.to(model.device), max_new_tokens=150)

📚 Documentation

Inputs and Outputs

Model Data

• Training Dataset: Using Gemma as the base model, CodeGemma 2B and 7B pretrained variants are further trained on an additional 500 to 1000 billion tokens of primarily English language data from publicly available code repositories, open source mathematics datasets and synthetically generated code.
• Training Data Processing:
  • FIM Pretrained CodeGemma models focus on fill - in - the - middle (FIM) tasks. The models are trained to work with both PSM and SPM modes. Our FIM settings are 80% to 90% FIM rate with 50 - 50 PSM/SPM.
  • Dependency Graph - based Packing and Unit Test - based Lexical Packing techniques: To improve model alignment with real - world applications, we structured training examples at the project/repository level to co - locate the most relevant source files within each repository. Specifically, we employed two heuristic techniques: dependency graph - based packing and unit test - based lexical packing.
  • We developed a novel technique for splitting the documents into prefix, middle, and suffix to make the suffix start in a more syntactically natural point rather than purely random distribution.
  • Safety: Similarly to Gemma, we deployed rigorous safety filtering including filtering personal data, CSAM filtering and other filtering based on content quality and safety in line with our policies.

Implementation Information

• Hardware: CodeGemma was trained using the latest generation of Tensor Processing Unit (TPU) hardware (TPUv5e).
• Software: Training was done using JAX and ML Pathways.

Evaluation Information

• Evaluation Approach: We evaluate CodeGemma on a variety of academic benchmarks across several domains:
  • Code completion benchmarks: HumanEval Single Line and Multiple Line Infilling
  • Code generation benchmarks: HumanEval, MBPP, BabelCode (C++, C#, Go, Java, JavaScript, Kotlin, Python, Rust)
  • Q&A: BoolQ, PIQA, TriviaQA
  • Natural Language: ARC - Challenge, HellaSwag, MMLU, WinoGrande
  • Math Reasoning: GSM8K, MATH
• Evaluation Results:
  • Coding Benchmarks: | Benchmark | 2B | 2B (1.1) | 7B | 7B-IT | 7B-IT (1.1) | |----------------------|------|----------|------|-------|------------| | HumanEval | 31.1 | 37.8 | 44.5 | 56.1 | 60.4 | | MBPP | 43.6 | 49.2 | 56.2 | 54.2 | 55.6 | | HumanEval Single Line | 78.4 | 79.3 | 76.1 | 68.3 | 77.4 | | HumanEval Multi Line | 51.4 | 51.0 | 58.4 | 20.1 | 23.7 | | BC HE C++ | 24.2 | 19.9 | 32.9 | 42.2 | 46.6 | | BC HE C# | 10.6 | 26.1 | 22.4 | 26.7 | 54.7 | | BC HE Go | 20.5 | 18.0 | 21.7 | 28.6 | 34.2 | | BC HE Java | 29.2 | 29.8 | 41.0 | 48.4 | 50.3 | | BC HE JavaScript | 21.7 | 28.0 | 39.8 | 46.0 | 48.4 | | BC HE Kotlin | 28.0 | 32.3 | 39.8 | 51.6 | 47.8 | | BC HE Python | 21.7 | 36.6 | 42.2 | 48.4 | 54.0 | | BC HE Rust | 26.7 | 24.2 | 34.1 | 36.0 | 37.3 | | BC MBPP C++ | 47.1 | 38.9 | 53.8 | 56.7 | 63.5 | | BC MBPP C# | 28.7 | 45.3 | 32.5 | 41.2 | 62.0 | | BC MBPP Go | 45.6 | 38.9 | 43.3 | 46.2 | 53.2 | | BC MBPP Java | 41.8 | 49.7 | 50.3 | 57.3 | 62.9 | | BC MBPP JavaScript | 45.3 | 45.0 | 58.2 | 61.4 | 61.4 | | BC MBPP Kotlin | 46.8 | 49.7 | 54.7 | 59.9 | 62.6 | | BC MBPP Python | 38.6 | 52.9 | 59.1 | 62.0 | 60.2 | | BC MBPP Rust | 45.3 | 47.4 | 52.9 | 53.5 | 52.3 |
  • Natural Language Benchmarks:

Ethics and Safety

• Evaluation Approach: Our evaluation methods include structured evaluations and internal red - teaming testing of relevant content policies. Red - teaming was conducted by a number of different teams, each with different goals and human evaluation metrics. These models were evaluated against a number of different categories relevant to ethics and safety, including:
  • Human evaluation on prompts covering content safety and representational harms. See the Gemma model card for more details on evaluation approach.
  • Specific testing of cyber - offence capabilities, focusing on testing autonomous hacking capabilities and ensuring potential harms are limited.
• Evaluation Results: The results of ethics and safety evaluations are within acceptable thresholds for meeting internal policies for categories such as child safety, content safety, representational harms, memorization, large - scale harms. See the Gemma model card for more details.

Model Usage & Limitations

• Intended Usage:
  • Code Completion: PT models can be used to complete code with an IDE extension.
  • Code Generation: IT model can be used to generate code with or without an IDE extension.
  • Code Conversation: IT model can power conversation interfaces which discuss code.
  • Code Education: IT model supports interactive code learning experiences, aids in syntax correction or provides coding practice.
• Known Limitations: Large Language Models (LLMs) have limitations based on their training data and the inherent limitations of the technology. See the Gemma model card for more details on the limitations of LLMs.
• Ethical Considerations & Risks: The development of large language models (LLMs) raises several ethical concerns. We have carefully considered multiple aspects in the development of these models. Please refer to the same discussion in the Gemma model card for model details.

📄 License

The model is under the gemma license.

⚠️ Important Note

To access CodeGemma on Hugging Face, you’re required to review and agree to Google’s usage license. To do this, please ensure you’re logged - in to Hugging Face and click below. Requests are processed immediately.

💡 Usage Tip

If you need to use code completion (for example, integrated in an IDE), we recommend you use one of the pre - trained models instead: CodeGemma 7B, or CodeGemma 2B.