faxenoff commited on
Commit
4a831c0
·
verified ·
1 Parent(s): 4c44d2a

compiled artefacts from mac_arm64 (cpu)

Browse files
Files changed (1) hide show
  1. README.md +3 -2
README.md CHANGED
@@ -258,9 +258,10 @@ Flat layout, named per **runtime × GPU arch × OS** (single-profile — no leng
258
  `XLMRobertaForTokenClassification` layout with the 17 labels in the config:
259
  `AutoModelForTokenClassification` loads them with no missing or unexpected keys, and its
260
  per-token logits match the ONNX to 1e-5. Calibrate them with `temperature.json` exactly as
261
- in the snippet above.
262
 
263
- No MLX build: this model has no Apple-GPU consumer today.
 
264
 
265
  ## License
266
 
 
258
  `XLMRobertaForTokenClassification` layout with the 17 labels in the config:
259
  `AutoModelForTokenClassification` loads them with no missing or unexpected keys, and its
260
  per-token logits match the ONNX to 1e-5. Calibrate them with `temperature.json` exactly as
261
+ in the snippet above. The Apple (MLX) build is prepared from this pair.
262
 
263
+ On Apple Silicon the daemon runs this model through MLX (`model_gpu_mlx{VER}/`, prepared from
264
+ the raw weights above), the only GPU lane there.
265
 
266
  ## License
267