This is an ONNX version of mlx-community/SmolLM-135M-Instruct-fp16. It was automatically converted and uploaded using this Hugging Face Space.
See the pipeline documentation for text-generation: https://huggingface.co/docs/transformers.js/api/pipelines#module_pipelines.TextGenerationPipeline
The Model mlx-community/SmolLM-135M-Instruct-fp16 was converted to MLX format from HuggingFaceTB/SmolLM-135M-Instruct using mlx-lm version 0.15.2.
pip install mlx-lm
from mlx_lm import load, generate
model, tokenizer = load("mlx-community/SmolLM-135M-Instruct-fp16")
response = generate(model, tokenizer, prompt="hello", verbose=True)
onnx/model.onnx 653 MBonnx/model_fp16.onnx 327 MBonnx/model_bnb4.onnx 199 MBonnx/model_q4.onnx 199 MBonnx/model_uint8.onnx 165 MBonnx/model_int8.onnx 165 MBonnx/model_quantized.onnx 165 MBonnx/model_q4f16.onnx 134 MB