SmolLM2-1.7B-Executorch-Q8DA4W

This repository contains the smollm2_1_7b_q8da4w.pte model, exported for use with ExecuTorch.

Details

• Base Model: HuggingFaceTB/SmolLM2-1.7B-Instruct
• Format: .pte (ExecuTorch)
• Quantization: Q8DA4W (4-bit linear weights, 8-bit dynamic activations)
• Architecture: llama (compatible with Llama export pipeline)
• File Size: ~1.7 GB

Features

• 🚀 Optimized for mobile/edge devices
• 📱 Compatible with react-native-executorch
• 💡 SmolLM2 is efficient and fast for resource-constrained environments
• 🗣️ Instruct-tuned for conversational AI

Usage

This model is ready to be used in mobile applications (iOS/Android) via the ExecuTorch runtime or react-native-executorch.

1. Download smollm2_1_7b_q8da4w.pte and the tokenizer files (tokenizer.json, vocab.json, merges.txt).
2. Place them in your app's asset folder.
3. Load with ExecuTorch runtime.

Notes

• SmolLM2 uses byte-level BPE tokenizer (similar to GPT-2), not SentencePiece like Llama.
• Tokenizer files are: tokenizer.json, vocab.json, merges.txt