ML

A notes about ML, still ongoing!

Goals

• Collection of ML knowledge base I like.

Generative AI

• Large Language Model
• Stable Diffusion
• Chat_with_MultiplePDFs_Mistral_7B_Instruct1

Frameworks

• Hugging Face - Candle
• Hugging Face - AutoTrain
• Apple - MLX

Inferences

• Text Generation Inference
• TabbyML: For locally code completion.
• LlamaEdge: Wasm base chat/embeddings/api.

RAG

• Retrieval Augmented Generation
• Vector Database - Qdrant

TODO

• Try The Alignment Handbook: https://github.com/huggingface/alignment-handbook
• Using MistralLite with HuggingFace Transformers and FlashAttention-2
• https://github.com/aigeek0x0/zephyr-7b-alpha-langchain-chatbot
• https://github.com/chatchat-space/Langchain-Chatchat
• https://github.com/flows-network/demo-RAG-embeddings

TOREAD

• Optimizing Text Embeddings with HuggingFace’s text-embeddings-inference Server and LlamaIndex: https://levelup.gitconnected.com/optimizing-text-embeddings-with-huggingfaces-text-embeddings-inference-server-and-llamaindex-ef7df35882a4
• Demystifying Advanced RAG Pipelines: https://github.com/pchunduri6/rag-demystified
• Read, try and summary: https://github.com/replit/replitLM#alpaca-style-instruct-tuning-with-hugging-face-transformers
• Try fine-tune-mistral: https://github.com/abacaj/fine-tune-mistral
• Try fine-tune-mistral: https://github.com/brevdev/notebooks/blob/main/mistral-finetune-own-data.ipynb
• Try LocalGPT: https://github.com/PromtEngineer/localGPT
• Read and summary: https://twitter.com/manelferreira_/status/1711788177458090388