| --- |
| license: gemma |
| inference: false |
| base_model: google/codegemma-7b-it |
| base_model_relation: quantized |
| tags: |
| - green |
| - p7 |
| - llmware-chat |
| - ov |
| --- |
| |
| # codegemma-7b-it-ov |
|
|
| **codegemma-7b-it-ov** is an OpenVino int4 quantized version of Google's CodeGemma-7B with Instruct Training (IT), providing a fast inference implementation, optimized for AI PCs using Intel GPU, CPU and NPU. |
|
|
| [**codegemma-7b-it-ov**](https://huggingface.co/google/codegemma-7b-it) is a leading open source coding model from Google. |
|
|
|
|
| ### Model Description |
|
|
| - **Developed by:** Google |
| - **Quantized by:** llmware |
| - **Model type:** gemma-7b |
| - **Parameters:** 7 billion |
| - **Model Parent:** google/codegemma-7b-it |
| - **Language(s) (NLP):** English |
| - **License:** Gemma |
| - **Uses:** Coding assistant with instruction chat support |
| - **RAG Benchmark Accuracy Score:** NA |
| - **Quantization:** int4 |
| |
|
|
| ## Model Card Contact |
|
|
| [llmware on github](https://www.github.com/llmware-ai/llmware) |
|
|
| [llmware on hf](https://www.huggingface.co/llmware) |
|
|
| [llmware website](https://www.llmware.ai) |
