Thiya's repositories
agentscope
Start building LLM-empowered multi-agent applications in an easier way.
bilibot
A local chatbot fine-tuned by bilibili user comments.
datatrove
Freeing data processing from scripting madness by providing a set of platform-agnostic customizable pipeline processing blocks.
DocsGPT
GPT-powered chat for documentation search & assistance.
dp-transformers
Differentially-private transformers using HuggingFace and Opacus
gamer_21
Dots & Boxes
gemma-2B-10M
Gemma 2B with 10M context length using Infini-attention.
GPT4o-API-Implementation-GPT4-RAG
Getting Started with GPT4 API, GPT4 RAG, OpenAI GPT4 Assistant, OpenAI Models
GPU-Benchmarks-on-LLM-Inference
Multiple NVIDIA GPUs or Apple Silicon for Large Language Model Inference?
guidance
A guidance language for controlling large language models.
Hedging-of-Financial-Derivatives
This strategy works for every market condition irrespective of the movement
inspect_ai
Inspect: A framework for large language model evaluations
Kevinpro-NLP-demo
All NLP you Need Here. 一些好玩的NLP demo，目前包含13个NLP应用的pytorch实现
langtest
Deliver safe & effective language models
LLM-PowerHouse-A-Curated-Guide-for-Large-Language-Models-with-Custom-Training-and-Inferencing
LLM-PowerHouse: Unleash LLMs' potential through curated tutorials, best practices, and ready-to-use code for custom training and inferencing.
LLMs-Evaluation
LLMs Evaluation
LLMs-from-scratch
Implementing a ChatGPT-like LLM from scratch, step by step
Lumina-T2X
Lumina-T2X is a unified framework for Text to Any Modality Generation
Mantis
Official code for Paper "Mantis: Multi-Image Instruction Tuning"
marlin1
FP16xINT4 LLM inference kernel that can achieve near-ideal ~4x speedups up to medium batchsizes of 16-32 tokens.
PaliGemma-Inference-and-Fine-Tuning
PaliGemma Inference and Fine Tuning
phidata
Build AI Assistants using function calling
pipecat
Open Source framework for voice and multimodal conversational AI
Resume-Screening-RAG-Pipeline
An LLM Chatbot that dynamically retrieves and processes resumes using RAG Fusion for efficient resume screening.
seqio
Task-based datasets, preprocessing, and evaluation for sequence models.