Large Language Models (LLMs)
Articles
LLMs can explain NN of other LLMs by OpenAI
Model size vs Computer overhead - The trade-off between model size and compute overhead and reveal there is significant room to reduce the compute-optimal model size with minimal compute overhead.
Papers
Language understanding by generative pre-training - Alec et al. openAI
LLM are few shot learners - scaling LLMs with data is enough to make them few shot.
Models
Databricks dolly
Vicuna
LLaMA
Instructor
Instructor model - "We introduce Instructor👨🏫, an instruction-finetuned text embedding model that can generate text embeddings tailored to any task (e.g., classification, retrieval, clustering, text evaluation, etc.) and domains (e.g., science, finance, etc.) by simply providing the task instruction, without any finetuning. Instructor achieves sota on 70 diverse embedding tasks!"
Datasets
Tools
An amazing tutorial in Youtube by Patrick Loeber about
LLMs
Prompt Templates
Chains
Agents and Tools
Memory
Document Loaders
Indexes
LangFlow, Medium, HuggingFace - is a UI for LangChain, designed with react-flow to provide an effortless way to experiment and prototype flows.
PandasAI - PandasAI, asking data Qs using LLMs on Panda's DFs with two code lines. 𝚙𝚊𝚗𝚍𝚊𝚜_𝚊𝚒 = 𝙿𝚊𝚗𝚍𝚊𝚜𝙰𝙸(𝚕𝚕𝚖) & 𝚙𝚊𝚗𝚍𝚊𝚜_𝚊𝚒.𝚛𝚞𝚗(𝚍𝚏, 𝚙𝚛𝚘𝚖𝚙𝚝='𝚆𝚑𝚒𝚌𝚑 𝚊𝚛𝚎 𝚝𝚑𝚎 𝟻 𝚑𝚊𝚙𝚙𝚒𝚎𝚜𝚝 𝚌𝚘𝚞𝚗𝚝𝚛𝚒𝚎𝚜?')
LLaMa Index - LlamaIndex (GPT Index) is a project that provides a central interface to connect your LLM's with external data.
LLM-foundry - LLM training code for Databricks foundation models using MoasicML
MinGPT - A minimal PyTorch re-implementation of the OpenAI GPT (Generative Pretrained Transformer) training
NanoGPT - The simplest, fastest repository for training/finetuning medium-sized GPTs.
Open-sourced codes for MiniGPT-4 and MiniGPT-v2 (https://minigpt-4.github.io, https://minigpt-v2.github.io/)
Guardrails
Databricks GR - Implementing LLM Guardrails for Safe and Responsible Generative AI Deployment on Databricks
Best Practices
Reinforcement Learning for LLM
RLHF: Reinforcement Learning from Human Feedback by Chip Huyen
John Schulman - Reinforcement Learning from Human Feedback: Progress and Challenges
Metrics
Understanding ROUGE - a family of metrics that evaluate the performance of a LLM in text summarization, i.e., ROUGE-1, ROUGE-2, ROUGE-L, for unigrams, bi grams, LCS, respectively.
Use Cases
Last updated