Views
No views yet
bfloat16 inference dtype, then stored as MLX
safetensors so it preserves the upstream runtime's executable values.model.safetensors: 31 converted tensors, 26,315,421 parameters.needle_mlx.py: a small custom MLX inference implementation for Needle's
architecture.tokenizer/: the upstream SentencePiece tokenizer files.config.json and manifest.json: architecture and conversion provenance.1from needle_mlx import NeedleModel
2
3model = NeedleModel.from_pretrained(".")
4logits = model.forward([[1, 2, 3]], [[1, 4]])needle.pkl checkpoint was read with a restricted NumPy-only
pickle loader, converted to MLX bfloat16 safetensors, and checked
tensor-for-tensor after the same dtype cast used by Needle's upstream runtime.40a32e91d1d4197bf15ba559b74f6727c342dc8746918742fc7d8e2c1f18df40model.safetensors SHA-256:
7b9d5f0d6ddeb7fbb20f4e45f3f616919357e5d08b5778859fdb762a33d60daebfloat16
runtime cast; an MLX encoder-decoder smoke pass produced logits with shape
(1, 2, 8192) and generated the upstream weather tool-call example.