Skip to content

Development: From RAG, Sentence Classification, Tense Classification, Python Scripts, Bash Scripts and Everything In Between#92

Merged
Brinkley97 merged 159 commits intomainfrom
development
Mar 2, 2026
Merged

Development: From RAG, Sentence Classification, Tense Classification, Python Scripts, Bash Scripts and Everything In Between#92
Brinkley97 merged 159 commits intomainfrom
development

Conversation

@Brinkley97
Copy link
Copy Markdown
Collaborator

No description provided.

+ updated with dataset package as well
**Goal:** Give a higher priority to keywords during sparse retrieval:

- TF: additional params are a dict of keyword_to_score: {"prediction": 7, "remain": 2, "stable": 8}
- IDF: compute IDF normally, then - score from TF
+ May put into my framework of vector_stores.py
+ Dr. Grant told me to look into query/term reweighting
1. BM25Okapi
2. LdaModel

None works due to import issues
+ Updated DatasetDict (saving and loading)

+ More train data

+ Modular approach to load data
+ Subset of my generated data
+ Subset of Financial PhraseBank
Brinkley97 and others added 28 commits February 21, 2026 11:03
…datasets

3 Datasets
1. chronicle2050
2. financial phrasebank
3. sythetic
Added "temperature"," top p", and "generated at" columns to predictions dataframe
@Brinkley97 Brinkley97 changed the title Development: From RAG to Sentence Classification and Everything In Between Development: From RAG, Sentence Classification, Tense Classification, Python Scripts, Bash Scripts and Everything In Between Mar 2, 2026
@Brinkley97 Brinkley97 merged commit b7b3d1a into main Mar 2, 2026
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment

Labels

None yet

Projects

None yet

Development

Successfully merging this pull request may close these issues.

2 participants