加载中…
加载中…
English 28-label emotion classification. Use independent sigmoid scores (multiple emotions may apply).
Conversion of SamLowe/roberta-base-go_emotions at revision d75048347613a25d77de8cf6412eaae9fa7b26be. No fine-tuning or replacement checkpoint. F32 baseline, not a 4-bit quantization. Original authors retain credit and license rights.
Core ML ML Program, F32 computation and weights. Input shape is fixed at [1, 128] (batch 1). macOS 14+/iOS 17+ export target. Prediction was tested on macOS, not on an iPhone.
from huggingface_hub import snapshot_download
import coremltools as ct, numpy as np
path = snapshot_download("masahiroid/roberta-base-go_emotions-coreml")
from transformers import AutoTokenizer
tok = AutoTokenizer.from_pretrained(path, use_fast=True)
enc = tok("Thank you so much!", return_tensors="np", padding="max_length", truncation=True, max_length=128)
model = ct.models.MLModel(path + "/model.mlpackage")
output = model.predict(dict(input_ids=enc["input_ids"].astype(np.int32), attention_mask=enc["attention_mask"].astype(np.int32)))["output"]
print(output.shape)
Compared against the original PyTorch implementation, 6 deterministic cases. Maximum absolute output difference: 1.1920929e-05; minimum cosine similarity: 0.9999999. See validation.json for each case. These are conversion parity checks, not a full task-quality benchmark or latency benchmark.
Text tests cover English emotions, neutral retrieval text, Japanese, empty input and truncation. Chronos tests cover a trend plus sinusoid, a constant series and a series with missing observations. Only applicable tests are used for each model.
Core ML/Core AI text exports use batch 1 and sequence length 128; tokenization must pad/truncate to 128. Chronos Apple exports use batch 1 and context length 2048. MLX/custom GGUF preserve the original maximum context rather than adding training. Short Chronos inputs can be left-padded with NaN for the fixed Apple exports. Forecast horizon remains 64.
Source revision and output semantics: provenance.json. Conversion scripts are included. Reproduce in a checkout with sources/<original-model-name>/, sources.json and publish/ directories as in the scripts. PyTorch 2.14.1; Transformers 4.57.3; MLX 0.32.4; NumPy 1.26.4 (MLX/Core ML environment); coremltools 9.0; chronos-forecasting 2.3.2; GGUF 0.19.0; Core AI export uses coreai-torch 0.4.3. Core AI validation uses its separate Python 3.14 environment. Version compatibility outside the tested environment is not guaranteed.
Weights remain under mit, with upstream terms in LICENSE. Converter/runtime additions are MIT licensed (CODE_LICENSE). No new task training, safety certification or commercial license is implied.