hihi!

LLM log

• llama.cpp
• llama_cpp_python
• whisper
• llava
• embeddings
• LoRA finetuning
• 12gb RTX 3060, triple 24gb P40
• vLLM
• exllama
• huggingface

Stuff

• https://scikit-learn.org/stable/
• https://python.langchain.com/en/latest/
• https://docs.langchain.com/docs/
• https://www.tensorflow.org/
• https://docs.pinecone.io/docs/python-client
• https://github.com/pgvector/pgvector