🧠💬 Articles I wrote about machine learning, archived from MachineCurve.com.

中文nlp解决方案(大模型、数据、模型、训练、推理)

Simple UI for LLM Model Finetuning

Social networking platform with automated content moderation and context-based authentication system

Data processing with ML and LLM

Label, clean and enrich text datasets with LLMs.

Chronos: Pretrained (Language) Models for Probabilistic Time Series Forecasting

a fast and user-friendly runtime for transformer inference (Bert, Albert, GPT2, Decoders, etc) on CPU and GPU.

Pocket-Sized Multimodal AI for content understanding and generation across multilingual texts, images, and 🔜 video, up to 5x faster than OpenAI CLIP and LLaVA 🖼️ & 🖋️

Trained models & code to predict toxic comments on all 3 Jigsaw Toxic Comment Challenges. Built using ⚡ Pytorch Lightning and 🤗 Transformers. For access to our API, please email us at [email protected].

Transformer models from BERT to GPT-4, environments from Hugging Face to OpenAI. Fine-tuning, training, and prompt engineering examples. A bonus section with ChatGPT, GPT-3.5-turbo, GPT-4, and DALL-E including jump starting GPT-4, speech-to-text, text-to-speech, text to image generation with DALL-E, Google Cloud AI,HuggingGPT, and more

Multimodal model for text and tabular data with HuggingFace transformers as building block for text data

Fast Inference Solutions for BLOOM

[EMNLP 2022] Unifying and multi-tasking structured knowledge grounding with language models

Learn Cloud Applied Generative AI Engineering (GenEng) using OpenAI, Gemini, Streamlit, Containers, Serverless, Postgres, LangChain, Pinecone, and Next.js

AI-First Process Automation with Large ([Language (LLMs) / Action (LAMs) / Multimodal (LMMs)] / Visual Language (VLMs)) Models

Exact structure out of any language model completion.

Keywords to Sentences

Guide: Finetune GPT2-XL (1.5 Billion Parameters) and finetune GPT-NEO (2.7 B) on a single GPU with Huggingface Transformers using DeepSpeed

Sentiment analysis neural network trained by fine-tuning BERT, ALBERT, or DistilBERT on the Stanford Sentiment Treebank.