Pinned Repositories
-
FLAN-FinBPS
LLMLingua
To speed up LLMs' inference and enhance LLM's perceive of key information, compress the prompt and KV-Cache, which achieves up to 20x compression with minimal performance loss.
rec_system_gnn
subhendukhatuya.github.io
subhendukhatuya's Repositories
subhendukhatuya/rec_system_gnn
subhendukhatuya/FLAN-FinBPS
subhendukhatuya/LLMLingua
To speed up LLMs' inference and enhance LLM's perceive of key information, compress the prompt and KV-Cache, which achieves up to 20x compression with minimal performance loss.
subhendukhatuya/subhendukhatuya.github.io
subhendukhatuya/afrisent-semeval-2023
AfriSenti-SemEval Shared Task 12: Sentiment Analysis for African languages : https://afrisenti-semeval.github.io/
subhendukhatuya/APOLLO_Retriever
[COLING 2024] APOLLO: An Optimized Training Approach for Long-form Numerical Reasoning
subhendukhatuya/BaselineNER
subhendukhatuya/EMCGCN-ASTE
Enhanced Multi-Channel Graph Convolutional Network for Aspect Sentiment Triplet Extraction
subhendukhatuya/ERPP-RMTPP
A pytorch implementation of ERPP and RMTPP on ATM maintenance dataset.
subhendukhatuya/Financial_Numerical_Reasoning
subhendukhatuya/FINDER-Numeric_reasoning
subhendukhatuya/FindocWorks
subhendukhatuya/FLAN-FinXC
Parameter-Efficient Instruction Tuning of Large Language Models For Extreme Financial Numeral Labelling
subhendukhatuya/FNXL
subhendukhatuya/GraFrank-Friend-Ranking
subhendukhatuya/Graph-Recommendation-System
subhendukhatuya/LabelSemanticsXBRL
Code for Label Semantics for Few Shot Named Entity Recognition
subhendukhatuya/lag-llama
Lag-Llama: Towards Foundation Models for Probabilistic Time Series Forecasting
subhendukhatuya/LLMInference
subhendukhatuya/makeeasydl
subhendukhatuya/MEANTIME
subhendukhatuya/P5
subhendukhatuya/sahp_repo
subhendukhatuya/SBN
Code for ‘A Span-level Bidirectional Network for Aspect Sentiment Triplet Extraction’
subhendukhatuya/Self-attention-with-Functional-Time-Representation-Learning
subhendukhatuya/stat453
subhendukhatuya/tacos-absa
subhendukhatuya/timesfm
TimesFM (Time Series Foundation Model) is a pretrained time-series foundation model developed by Google Research for time-series forecasting.
subhendukhatuya/WWW2021-SSHP
subhendukhatuya/XBRL-Data