contriever β€” COREAI

Dense retrieval embeddings with mask-aware mean pooling. Embeddings are not L2-normalized.

Conversion of facebook/contriever at revision 2bd46a25019aeea091fd42d1f0fd4801675cf699. No fine-tuning or replacement checkpoint. F32 baseline, not a 4-bit quantization. Original authors retain credit and license rights.

Usage and compatibility

Apple Core AI .aimodel asset; F32; fixed input shape [1, 128]. Tested using coreai-core==1.0.0b3, GPU execution on macOS 27.2. Not a Core ML .mlpackage.

import asyncio, numpy as np
from huggingface_hub import snapshot_download
from coreai.runtime import AIModel, NDArray, SpecializationOptions, ComputeUnitKind
path = snapshot_download("masahiroid/contriever-coreai")
from transformers import AutoTokenizer
enc = AutoTokenizer.from_pretrained(path, use_fast=True)("Thank you so much!", return_tensors="np", padding="max_length", truncation=True, max_length=128)
async def main():
    opts = SpecializationOptions.from_preferred_compute_unit_kind(ComputeUnitKind.gpu())
    model = await AIModel.load(path + "/model.aimodel", specialization_options=opts)
    fn = model.load_function(model.function_names[0])
    output = await fn(inputs={k: NDArray(enc[k].astype(np.int32)) for k in ("input_ids", "attention_mask")})
    print(output["output"].numpy().shape)
asyncio.run(main())

Numerical validation

Compared against the original PyTorch implementation, 6 deterministic cases. Maximum absolute output difference: 3.5017729e-07; minimum cosine similarity: 0.99999988. 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.

Reproducibility

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.

License

Weights remain under cc-by-nc-4.0, with upstream terms in LICENSE. Non-commercial use only under the original CC BY-NC 4.0 terms. Converter/runtime additions are MIT licensed (CODE_LICENSE). No new task training, safety certification or commercial license is implied.

Other formats

Downloads last month
35
Inference Providers NEW
This model isn't deployed by any Inference Provider. πŸ™‹ Ask for provider support

Model tree for masahiroid/contriever-coreai

Finetuned
(8)
this model