ducanhdinh / jepa_proof_vicreg

huggingface.co
Total runs: 0
24-hour runs: 0
7-day runs: 0
30-day runs: 0
Model's Last Updated: June 14 2026

Introduction of jepa_proof_vicreg

Model Details of jepa_proof_vicreg

ducanhdinh/jepa_proof_vicreg

BERT encoder pretrained from scratch với VICReg (Variance-Invariance-Covariance Regularization).

Hai masked text views được encode bởi một BERT encoder dùng chung, sau đó đưa qua expander MLP. VICReg kết hợp 3 loss terms để căn chỉnh các views và ngăn feature collapse mà không cần negative samples:

Loss term Hệ số Mô tả
Invariance 25.0 MSE giữa z1 và z2 (căn chỉnh hai views)
Variance 25.0 Giữ std của mỗi chiều ≥ 1 (chống collapse)
Covariance 1.0 Decorrelate các chiều embedding
Kiến trúc
Text → BERT (mean-pool) → z ∈ R^768 → Expander MLP → z' ∈ R^3072
                                                       ↑ VICReg loss áp dụng tại đây

Expander gồm 3 lớp Linear-BatchNorm-ReLU (dim = 3072 ).

Thông số huấn luyện
Tham số Giá trị
Max sequence length 256
Batch size 256
Epochs 10
Learning rate 0.0001
Expander dim 3072
Max span length (masking) 5
sim_coeff 25.0
std_coeff 25.0
cov_coeff 1.0
Cách dùng — BERT encoder (feature extraction)
from transformers import BertModel, BertTokenizerFast
import torch

tokenizer = BertTokenizerFast.from_pretrained("ducanhdinh/jepa_proof_vicreg")
bert      = BertModel.from_pretrained("ducanhdinh/jepa_proof_vicreg/encoder")

encoded = tokenizer(
    ["Hello world!", "VICReg is great."],
    return_tensors="pt",
    padding=True,
    truncation=True,
)
with torch.no_grad():
    out    = bert(**encoded)
    hidden = out.last_hidden_state          # (B, T, 768)
    mask   = encoded["attention_mask"].unsqueeze(-1).float()
    emb    = (hidden * mask).sum(1) / mask.sum(1).clamp(min=1)  # mean-pool → (B, 768)
Cách dùng — Full model (encoder + expander)
import torch
from transformers import BertTokenizerFast

# Load weights thủ công
from text_vicreg import TextVICReg, VICRegPretrainConfig

cfg   = VICRegPretrainConfig()
model = TextVICReg(cfg)
state = torch.load(
    hf_hub_download("ducanhdinh/jepa_proof_vicreg", "pytorch_model.bin"),
    map_location="cpu",
)
model.load_state_dict(state)
model.eval()

Runs of ducanhdinh jepa_proof_vicreg on huggingface.co

0
Total runs
0
24-hour runs
0
3-day runs
0
7-day runs
0
30-day runs

More Information About jepa_proof_vicreg huggingface.co Model

More jepa_proof_vicreg license Visit here:

https://choosealicense.com/licenses/apache-2.0

jepa_proof_vicreg huggingface.co

jepa_proof_vicreg huggingface.co is an AI model on huggingface.co that provides jepa_proof_vicreg's model effect (), which can be used instantly with this ducanhdinh jepa_proof_vicreg model. huggingface.co supports a free trial of the jepa_proof_vicreg model, and also provides paid use of the jepa_proof_vicreg. Support call jepa_proof_vicreg model through api, including Node.js, Python, http.

jepa_proof_vicreg huggingface.co Url

https://huggingface.co/ducanhdinh/jepa_proof_vicreg

ducanhdinh jepa_proof_vicreg online free

jepa_proof_vicreg huggingface.co is an online trial and call api platform, which integrates jepa_proof_vicreg's modeling effects, including api services, and provides a free online trial of jepa_proof_vicreg, you can try jepa_proof_vicreg online for free by clicking the link below.

ducanhdinh jepa_proof_vicreg online free url in huggingface.co:

https://huggingface.co/ducanhdinh/jepa_proof_vicreg

jepa_proof_vicreg install

jepa_proof_vicreg is an open source model from GitHub that offers a free installation service, and any user can find jepa_proof_vicreg on GitHub to install. At the same time, huggingface.co provides the effect of jepa_proof_vicreg install, users can directly use jepa_proof_vicreg installed effect in huggingface.co for debugging and trial. It also supports api for free installation.

jepa_proof_vicreg install url in huggingface.co:

https://huggingface.co/ducanhdinh/jepa_proof_vicreg

Url of jepa_proof_vicreg

jepa_proof_vicreg huggingface.co Url

Provider of jepa_proof_vicreg huggingface.co

ducanhdinh
ORGANIZATIONS

Other API from ducanhdinh

huggingface.co

Total runs: 368
Run Growth: 352
Growth Rate: 96.44%
Updated:November 24 2025