Pinned Repositories
alpaca-lora
Instruct-tune LLaMA on consumer hardware
Astock
Astock
attention_sinks
Extend existing LLMs way beyond the original training length with constant memory usage, and without retraining
awesome-cpp
A curated list of awesome C++ (or C) frameworks, libraries, resources, and shiny things. Inspired by awesome-... stuff.
modern_nlp_2
NickyDark1's Repositories
NickyDark1/modern_nlp_2
NickyDark1/attention_sinks
Extend existing LLMs way beyond the original training length with constant memory usage, and without retraining
NickyDark1/awesome-cpp
A curated list of awesome C++ (or C) frameworks, libraries, resources, and shiny things. Inspired by awesome-... stuff.
NickyDark1/BakLLaVA
NickyDark1/barrel-rec-pytorch
NickyDark1/crewAI
NickyDark1/djl-demo
Demo applications showcasing DJL
NickyDark1/DoctorGPT
DoctorGPT is an LLM that can pass the US Medical Licensing Exam. It works offline, it's cross-platform, & your health data stays private.
NickyDark1/fine-tune-mistral
Fine-tune mistral-7B on 3090s, a100s, h100s
NickyDark1/Fine-tuning-an-LLM-using-LoRA
š Text Classification with LoRA (Low-Rank Adaptation) of Language Models - Efficiently fine-tune large language models for text classification tasks using the Stanford Sentiment Treebank (SST-2) dataset and the LoRA technique.
NickyDark1/Fine_tunning_llama2
Colab project for https://medium.com/ai-mvp-hub
NickyDark1/FinRL-Meta
FinRLĀ-Meta: Dynamic datasets and market environments for FinRL.
NickyDark1/InsightSolver-Colab
InsightSolver: Colab notebooks for exploring and solving operational issues using deep learning, machine learning, and related models.
NickyDark1/Langchain0001
My Langchain Code archive maybe
NickyDark1/Llama-2-7B-32K-Instruct
NickyDark1/LLaMA-Adapter
Fine-tuning LLaMA to follow Instructions within 1 Hour and 1.2M Parameters
NickyDark1/llama-recipes
Examples and recipes for Llama 2 model
NickyDark1/llama2-fine-tune
Scripts for fine-tuning Llama2 via SFT and DPO.
NickyDark1/llama_index
LlamaIndex (formerly GPT Index) is a data framework for your LLM applications
NickyDark1/llm-course
Course to get into Large Language Models (LLMs) with roadmaps and Colab notebooks.
NickyDark1/llm-reasoners
A library for advanced large language model reasoning
NickyDark1/llm_0001
Repo for some llm fun
NickyDark1/MASTER_Market_Guided_Stock_Transformer_for_Stock_Price_Forecasting
This is the official code and supplementary materials for our AAAI-2024 paper: MASTER: Market-Guided Stock Transformer for Stock Price Forecasting. MASTER is a stock transformer for stock price forecasting, which models the momentary and cross-time stock correlation and guide feature selection with market information.
NickyDark1/mixtral-offloading
run Mixtral-8x7B models in colab or consumer desktops
NickyDark1/NLP-Projects-NHV
NLP Projects playlist
NickyDark1/notebooks_fineTune_llama_mistral
NickyDark1/phi2-finetune
NickyDark1/playgrounds_subgraph_connector
The `PlaygroundsSubgraphConnector` is a tool designed for agents to seamlessly interface with and query subgraphs on The Graph's decentralized network via Playgrounds API.
NickyDark1/trl
Train transformer language models with reinforcement learning.
NickyDark1/unsloth
5X faster 60% less memory QLoRA finetuning