RESMP-DEV/LFM2.5-Encoder-350M-MLX-FP32

LFM2.5 Encoder 350M — MLX FP32

Native MLX conversion of LiquidAI/LFM2.5-Encoder-350M, pinned to revision b886781f7c6f10ca9b7096e21b83e30a073c2f39.

The checkpoint is kept entirely in float32. This implementation preserves the encoder's full bidirectional attention and centered, non-causal short convolutions; it is not a causal mlx-lm generation model.

import mlx.core as mx
from model import load_model

model = load_model(".")
input_ids = mx.array([[1, 123, 456, 7]])
attention_mask = mx.ones_like(input_ids)
logits = model(input_ids, attention_mask)
mx.eval(logits)

Use the included tokenizer files with transformers.AutoTokenizer or the tokenizers package. See validation.json for the FP32 tensor audit and PyTorch-to-MLX numerical parity measurements.