# distilbert-word2vec_256k-MLM_best

**Repository Path**: modelee/distilbert-word2vec_256k-MLM_best

## Basic Information

- **Project Name**: distilbert-word2vec_256k-MLM_best
- **Description**: No description available
- **Primary Language**: Unknown
- **License**: Not specified
- **Default Branch**: main
- **Homepage**: None
- **GVP Project**: No

## Statistics

- **Stars**: 3
- **Forks**: 1
- **Created**: 2023-05-24
- **Last Updated**: 2025-07-25

## Categories & Tags

**Categories**: llm

**Tags**: None

## README

# DistilBERT with word2vec token embeddings

This model has a word2vec token embedding matrix with 256k entries. The word2vec was trained on 100GB data from C4, MSMARCO, News, Wikipedia, S2ORC, for 3 epochs.

Then the model was trained on this dataset with MLM for 1.37M steps (batch size 64). The token embeddings were NOT updated.

For the initial word2vec weights with Gensim see: [https://huggingface.co/vocab-transformers/distilbert-word2vec_256k-MLM_1M/tree/main/word2vec](https://huggingface.co/vocab-transformers/distilbert-word2vec_256k-MLM_1M/tree/main/word2vec)