Welcome to Software Development on Codidact!
Will you help us build our independent community of developers helping developers? We're small and trying to grow. We welcome questions about all aspects of software development, from design to code to QA and more. Got questions? Got answers? Got code you'd like someone to review? Please join us.
Post History
I see on https://huggingface.co/HuggingFaceTB/SmolLM2-135M-Instruct/tree/main/onnx: File Name Size model.onnx 654 MB model_fp16.onnx 327 MB model_q4.onnx 200 MB m...
#1: Initial revision
by
Franck Dernoncourt
·
2024-11-08T17:33:34Z (25 days ago)
Why are model_q4.onnx and model_q4f16.onnx not 4 times smaller than model.onnx?
I see on https://huggingface.co/HuggingFaceTB/SmolLM2-135M-Instruct/tree/main/onnx: | File Name | Size | |--------------------|--------| | model.onnx | 654 MB | | model_fp16.onnx | 327 MB | | model_q4.onnx | 200 MB | | model_q4f16.onnx | 134 MB | I understand that: - `model.onnx` is the fp32 model, - `model_fp16.onnx` is the model whose weights are quantized to `fp16` I don't understand the size of `model_q4.onnx` and `model_q4f16.onnx` 1. Why is `model_q4.onnx` 200 MB instead of 654 MB / 4 = 163.5 MB? I thought `model_q4.onnx` meant that the weights are quantized to 4 bits. 2. Why is `model_q4f16.onnx` 134 MB instead of 654 MB / 4 = 163.5 MB? I thought `model_q4f16.onnx` meant that the weights are quantized to 4 bits and activations are fp16, since https://llm.mlc.ai/docs/compilation/configure_quantization.html states: > `qAfB(_id)`, where `A` represents the number of bits for storing weights and `B` represents the number of bits for storing activations. and [Why do activations need more bits (16bit) than weights (8bit) in tensor flow's neural network quantization framework?](https://stackoverflow.com/a/72397979/395857) indicates that activations don't count toward the model size (understandably).