Downloads · 30 days
0
P1_financial_news_headlines_BPE_Word2Vec
KhadijaMir/P1_financial_news_headlines_BPE_Word2Vec
P1_financial_news_headlines_BPE_Word2Vec is a machine learning model from KhadijaMir. Use it for the machine learning task on the model card, and read the license before you ship it in a product. It is set up for gensim.
Two gensim models trained on 410,849 train-period headlines with the course L3 settings (sg=1, hs=0, vectorsize=256, window=2, mincount=2, negative=10, epochs=50): bpelevelword2vec.model: tokens from the CharBPE token…
Access
Public
Updated Sep 24, 2026
Repo size
222 MB
Likes
0
Public
Repo makeup
Click a slice to open those files.
.npy218 MB · 98%
At a glance
- Library
- gensim
- Access
- Public
- Created
- Sep 24, 2026
- Updated
- Sep 24, 2026
- SHA
- e6730df4
Model card
From the Hugging Face model README
Word2Vec (skip-gram) on financial news headlines (FTEC 6V96 Project 1)
Two gensim models trained on 410,849 train-period headlines with the course L3 settings
(sg=1, hs=0, vector_size=256, window=2, min_count=2, negative=10, epochs=50):
bpe_level_word2vec.model: tokens from the CharBPE tokenizer (https://huggingface.co/KhadijaMir/P1_financial_news_headlines_CharBPETokenizer)word_level_word2vec.model: spaCy tokens with the coursefilter_tokens+ bigram/trigramPhrases
Load with gensim.models.Word2Vec.load(...). Training with several threads is not exactly reproducible; the project reports
results across several trainings. Project details: https://huggingface.co/datasets/KhadijaMir/SP_DOW_NASDAQ_stocks__News_Headlines_labeled/tree/project1_triple_barrier
- Library
- gensim
- Languages
- en
- Created
- Sep 24, 2026
- Updated
- Sep 24, 2026