| language: | |
| - en | |
| thumbnail: "https://huggingface.co/meta-llama/Llama-3.2-1B-Instruct/resolve/main/thumbnail.png" | |
| tags: | |
| - coreml | |
| - llama | |
| - text-generation | |
| - ios | |
| license: "llama3" | |
| datasets: | |
| - meta-llama/Llama-3.2-1B-Instruct | |
| base_model: "meta-llama/Llama-3.2-1B-Instruct" | |
| # Llama-3.2-1B-Instruct-CoreML | |
| CoreML-optimized version of Meta's Llama-3.2-1B-Instruct model for Apple devices. | |
| ## Model Details | |
| - **Base Model**: Llama-3.2-1B-Instruct | |
| - **Model Size**: 1B parameters | |
| - **Context Length**: 2048 tokens | |
| - **Format**: CoreML (.mlpackage) | |
| - **Optimized for**: Apple devices (iOS/macOS) | |
| ## Files | |
| - `model.mlpackage.zip`: CoreML model package for iOS/macOS deployment | |
| - `model.mlmodelc.zip`: Compiled CoreML model for optimized performance | |
| - `model.mlmodel`: CoreML model file | |
| ## Usage | |
| The model supports: | |
| - Batch size: 1 | |
| - Input type: int32 | |
| - Output type: float32 | |
| ## License | |
| Same license as original Llama-3.2-1B-Instruct model from Meta. | |