Request for MLX Compatibility & Conversion Guide

Nobody has claimed this yet.

I’m interested in running the NAMO-R1 model on Apple Silicon using MLX (Machine Learning for Apple Devices). Since MLX is optimized for Apple hardware and supports transformer-based models, I’d like to convert NAMO-R1 into an MLX-compatible format. However, I need clarification on a few things:

**Questions & Challenges:**

**1. Model Format & Conversion:**
- The current model is in .safetensors, but MLX requires NumPy (.npz).
- Could you provide guidance on extracting and converting weights into a format MLX can use?

**2. Understanding namo.ve (Vision Encoder?)**
- I noticed namo.llm (the language model) and namo.ve (possibly a vision encoder?).
- Could you clarify if NAMO-R1 is a multimodal model? If so, are there specific dependencies required for image inputs?

**3. Defining Model Architecture in MLX**
- MLX requires an explicit model definition (nn.Module in mlx.nn).
- Do you have details on the exact architecture (hidden sizes, number of layers, activation functions) to help reproduce it in MLX?

**Request:**
Would it be possible to provide a model architecture description, weight extraction guide, or any hints for making NAMO-R1 run on MLX? I’d love to contribute a conversion script once I get a better understanding!

Start by examining the repository's namo.llm and namo.ve components, then review the existing .safetensors model format and the requested NumPy .npz conversion. Determine whether namo.ve is a vision encoder and document the architecture details needed for an MLX nn.Module; done would be a validated conversion guide or script with the model's compatibility requirements.

Written by the indexing model from the issue text.