StepanTita/space-model
Space Model framework that allows for maintaining generalizability, and enhances the performance on the downstream task by utilizing task-specific context attribution. It is an external LLM layer, that improves accuracy in classification task for multiple datasets, such as HateXplain, IMDB movies reviews and more.
This framework helps machine learning practitioners improve the accuracy of text classification models for various tasks. It takes an existing large language model and your task-specific text data, then enhances the model's performance on recognizing categories like sentiment or detecting hate speech. Data scientists and machine learning engineers who work with natural language processing would use this.
No commits in the last 6 months.
Use this if you need to fine-tune large language models for text classification and want to achieve higher accuracy without sacrificing the model's ability to generalize.
Not ideal if your primary goal is generating text or performing tasks other than classification, or if you're not working with existing large language models.
Stars
9
Forks
—
Language
HTML
License
—
Category
Last pushed
Jul 22, 2024
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/embeddings/StepanTita/space-model"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Higher-rated alternatives
ContextualAI/gritlm
Generative Representational Instruction Tuning
xlang-ai/instructor-embedding
[ACL 2023] One Embedder, Any Task: Instruction-Finetuned Text Embeddings
liuqidong07/LLMEmb
[AAAI'25 Oral] The official implementation code of LLMEmb
hpcaitech/CachedEmbedding
A memory efficient DLRM training solution using ColossalAI
ritesh-modi/embedding-hallucinations
This repo shows how foundational model hallucinates and how we can fix such hallucinations using...