llm-classifier
trl
llm-classifier | trl | |
---|---|---|
4 | 13 | |
191 | 8,412 | |
6.8% | 3.5% | |
7.4 | 9.6 | |
16 days ago | 6 days ago | |
Python | Python | |
GNU General Public License v3.0 or later | Apache License 2.0 |
Stars - the number of stars that a project has on GitHub. Growth - month over month growth in stars.
Activity is a relative number indicating how actively a project is being developed. Recent commits have higher weight than older ones.
For example, an activity of 9.0 indicates that a project is amongst the top 10% of the most actively developed projects that we are tracking.
llm-classifier
-
Lessons after a Half-billion GPT Tokens
We do this for the null hypothesis - is uses an LLM to bootstrap a binary classifier - which handles null easily
https://github.com/lamini-ai/llm-classifier
- FLaNK Stack 29 Jan 2024
-
Good old-fashioned AI remains viable in spite of the rise of LLMs
LLMs introduced zero-shot learning, or “prompt engineering” which is drastically easier to use and more effective than labeling data.
You can also retrofit “prompt engineering” onto good old fashion ML like text classifiers. I wrote a library to do just that here: https://github.com/lamini-ai/llm-classifier
IMO, it’s a short matter of time before this takes over all of what used to be called “deep learning”.
- How to use a LLM to classify text
trl
- FLaNK Stack 29 Jan 2024
-
OOM Error while using TRL for RLHF Fine-tuning
I am using TRL for RLHF fine-tuning the Llama-2-7B model and getting an OOM error (even with batch_size=1). If anyone used TRL for RLHF can please tell me what I am doing wrong? Code details can be found in the GitHub issue.
-
[D] Tokenizers Truncation during Fine-tuning with Large Texts
SFTtrainer from huggingface
-
New Open-source LLMs! 🤯 The Falcon has landed! 7B and 40B
For lora - PEFT seems to work. I don't have patience to wait 5 hours, but modifying this example seems to work. You don't even need to modify that much, as their model just as neo-x uses query_key_value name for self-attention.
-
[D] Using RLHF beyond preference tuning
They have examples of making GPT output more positive (code) by using a sentiment model as reward. There are other examples about reducing toxicity, summarization here: https://github.com/lvwerra/trl/tree/main/examples . Should be fairly simple to modify the sentiment example and try the calculator reward you mentioned above.
-
[R] 🤖🌟 Unlock the Power of Personal AI: Introducing ChatLLaMA, Your Custom Personal Assistant! 🚀💬
You can use this -> https://github.com/lvwerra/trl/blob/main/examples/sentiment/scripts/gpt-neox-20b_peft/merge_peft_adapter.py
-
[R] Stanford-Alpaca 7B model (an instruction tuned version of LLaMA) performs as well as text-davinci-003
Just the hh directly. From the results it seems like it might possibly be enough but I might also try instruction tuning then running the whole process from that base. I will also be running the reinforcement learning by using a Lora using this as an example https://github.com/lvwerra/trl/tree/main/examples/sentiment/scripts/gpt-neox-20b_peft
-
[R] A simple explanation of Reinforcement Learning from Human Feedback (RLHF)
This package is pretty simple to use! https://github.com/lvwerra/trl
- Transformer Reinforcement Learning
- trl: Train transformer language models with reinforcement learning
What are some alternatives?
ml-ferret
lm-human-preferences - Code for the paper Fine-Tuning Language Models from Human Preferences
reor - Private & local AI personal knowledge management app.
alpaca-lora - Instruct-tune LLaMA on consumer hardware
llm-routing-agent - Agent that routes to different tools - LLM classifier SDK
trlx - A repo for distributed training of language models with Reinforcement Learning via Human Feedback (RLHF)
langroid - Harness LLMs with Multi-Agent Programming
LLaMA-8bit-LoRA - Repository for Chat LLaMA - training a LoRA for the LLaMA (1 or 2) models on HuggingFace with 8-bit or 4-bit quantization. Research only.
heynote - A dedicated scratchpad for developers
sparsegpt-for-LLaMA - Code for the paper "SparseGPT: Massive Language Models Can Be Accurately Pruned in One-Shot" with LLaMA implementation.
java-snapshot-testing - Facebook style snapshot testing for JAVA Tests
llama-recipes - Scripts for fine-tuning Meta Llama3 with composable FSDP & PEFT methods to cover single/multi-node GPUs. Supports default & custom datasets for applications such as summarization and Q&A. Supporting a number of candid inference solutions such as HF TGI, VLLM for local or cloud deployment. Demo apps to showcase Meta Llama3 for WhatsApp & Messenger.