shism2

Pinned Repositories

apebase
Bored Ape Database
0 1 00
brainyduck
A micro "no-backend" framework 🤯 Quickly build powerful BaaS using only your graphql schemas
Language:JavaScript1 1 00
geniusrise
Geniusrise: Framework for building geniuses
Language:Python1 1 00
vision-aided-gan
Ensembling Off-the-shelf Models for GAN Training
Language:Python0 1 00
WinIT
Code for the ICML'21 paper "Temporal Dependencies in Feature Importance for Time Series Predictions"
Language:Python2 1 02

shism2's Repositories

shism2/AAgent
Language:Python0 0
shism2/AlphaCodium
Official implementation for the paper: "Code Generation with AlphaCodium: From Prompt Engineering to Flow Engineering""
shism2/big-agi
💬 Personal AI application powered by GPT-4 and beyond, with AI personas, AGI functions, text-to-image, voice, response streaming, code highlighting and execution, PDF import, presets for developers, much more. Deploy and gift #big-AGI-energy! Using Next.js, React, Joy.
Language:TypeScript
shism2/CodeInstruct
InstructCoder (former name:Codelnstruct) enables LLMs to edit code
shism2/CORL
High-quality single-file implementations of SOTA Offline and Offline-to-Online RL algorithms: AWAC, BC, CQL, DT, EDAC, IQL, SAC-N, TD3+BC, LB-SAC, SPOT, Cal-QL, ReBRAC
shism2/DreamLLM
[ICLR 2024 Spotlight] DreamLLM: Synergistic Multimodal Comprehension and Creation
Language:Python0 0
shism2/FourierTransformer
The official Pytorch implementation of the paper "Fourier Transformer: Fast Long Range Modeling by Removing Sequence Redundancy with FFT Operator" (ACL 2023 Findings)
Language:Python1 0
shism2/Gemma-EasyLM
Train GEMMA on TPU/GPU! (Codebase for training Gemma-Ko Series)
Language:Python0 0
shism2/GPT-HTN-Planner
A Hierarchical Task Network planner utilizing LLMs like OpenAI's GPT-4 to create complex plans from natural language that can be converted into an executable form.
shism2/gpt-pilot
Dev tool that writes scalable apps from scratch while the developer oversees the implementation
Language:Python1 0
shism2/HGConv
HGConv: Holographic Global Convolutional Networks
shism2/INTERVENOR
Source code for paper: INTERVENOR : Prompt the Coding Ability of Large Language Models with the Interactive Chain of Repairing
Language:Python1 0
shism2/knowledge_graph
Convert any text to a graph of knowledge. This can be used for Graph Augmented Generation or Knowledge Graph based QnA
Language:Jupyter Notebook0 0
shism2/langchainjs
Language:TypeScript1 0
shism2/langgraph
Language:Python1 0
shism2/llm_robustness
Language:Python1 0
shism2/LLMDebugger
LDB: A Large Language Model Debugger via Verifying Runtime Execution Step by Step
shism2/LookupFFN
shism2/mergekit
Tools for merging pretrained large language models.
Language:Python1 0
shism2/morec
shism2/NodeGraphQt
Node graph framework that can be re-implemented into applications that supports PySide2
Language:Python0 0
shism2/prompt-optimizer
Minimize LLM token complexity to save API costs and model computations.
Language:Python0 0
shism2/Prompt-Space
Language:Python0 0
shism2/Rexl
Research EXpression Language
Language:C#1 0
shism2/Self-Supervised-Contrastive-Forecsating
"Self-Supervised Contrastive Forecasting", accepted at International Conference on Learning Representations (ICLR) 2024
Language:Python1 0
shism2/StreamDiffusion
StreamDiffusion: A Pipeline-Level Solution for Real-Time Interactive Generation
Language:Python0 0
shism2/tarski
Tarski - An AI Planning Modeling Framework
shism2/TOVA
Token Omission Via Attention
Language:Python1 0
shism2/training_free_model_merging
This repository is the implementation of the paper Training Free Pretrained Model Merging (CVPR2024).
Language:Python0 0
shism2/ZeroPromptSearch
Implementation of an LLM prompting pipeline combined with wrappers for auto-decomposing reasoning steps and for search through the reasoning-step-space (eg. by beam search, MCTS etc.) guided by self-evaluation.