sujianwei1 Goto Github PK

autoif

community-events

Place where folks can contribute to 🤗 community events

data_preprocessing

Data cleaning, Tokenization, Regular Expressions and Pandas guide.

data_tooling

Tools for managing datasets for governance and training.

datadreamer

DataDreamer: Prompt. Generate Synthetic Data. Train & Align Models.   🤖💤

datalore

deita

Deita: Data-Efficient Instruction Tuning for Alignment [ICLR2024]

fast-whisper-finetuning

gpts

leaked prompts of GPTs

llm-finetuning-large-language-models

LLM (Large Language Model) FineTuning

llms-from-scratch

Implementing a ChatGPT-like LLM in PyTorch from scratch, step by step

lorax

Multi-LoRA inference server that scales to 1000s of fine-tuned LLMs

marker

Convert PDF to markdown quickly with high accuracy

nllb-200-distilled-350m-en-ko

nllb-200 distilled 350M for English to Korean translation

nllb-pruning

Library for pruning experts per language pair in NLLB-200

nllb_ft

one-python-craftsman

来自一位 Pythonista 的编程经验分享，内容涵盖编码技巧、最佳实践与思维模式等方面。

real-time-asr

A POC of Whisper as the engine for a real-time speech recognition system. The server and client are both built in Python.

s-lora

S-LoRA: Serving Thousands of Concurrent LoRA Adapters

transformer-explainer

Learn How Transformers work in Generative AI with Interactive Visualization

whisper

Robust Speech Recognition via Large-Scale Weak Supervision

whisper_streaming

Whisper realtime streaming for long speech-to-text transcription and translation

whisperfusion

WhisperFusion builds upon the capabilities of WhisperLive and WhisperSpeech to provide a seamless conversations with an AI.

whisperlive

A nearly-live implementation of OpenAI's Whisper.

whisperspeech

An Open Source text-to-speech system built by inverting Whisper.

youtube-blog

Codes to complement YouTube videos and blog posts on Medium.