trl
OutRun
trl | OutRun | |
---|---|---|
13 | 7 | |
8,176 | 686 | |
4.9% | - | |
9.7 | 0.0 | |
1 day ago | 20 days ago | |
Python | Swift | |
Apache License 2.0 | GNU General Public License v3.0 only |
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.
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
OutRun
-
Show HN: I make an iOS app for runners using Apple Watch
Ive had a similar problem to you, but I have mostly solved it by using the Outrun app (which is free and open source), and going into the settings and turning up the GPS smoothing. I mostly run in central london, and it seems to work with the tall buildings here.
https://github.com/timfraedrich/OutRun
- FLaNK Stack 29 Jan 2024
- FLaNK Stack Weekly 22 January 2024
-
OutRun – Open-source, privacy oriented, outdoor fitness tracker
https://github.com/timfraedrich/OutRun/issues/91
> I wouldn't necessarily say abandoned. I still work on it from time to time, but progress is very very slow and I cannot prioritise it over other things atm
-
Oxford to Stratford Upon Avon
Shout out to the app "Out-Run" that I use to track my rides. Privacy focused way to track your rides without all of the bullshit social media that comes with Strava. No account, all data stored locally, can easily export your rides, no data collected. Have exchanged a few emails with the dev and he's a super cool dude, so I shout out his app at every opportunity. All open source as well.
-
Are there any privacy-focused fitness/health tracking apps?
This is the GitHub page.
What are some alternatives?
lm-human-preferences - Code for the paper Fine-Tuning Language Models from Human Preferences
RxSwift - Reactive Programming in Swift
alpaca-lora - Instruct-tune LLaMA on consumer hardware
open-source-ios-apps - :iphone: Collaborative List of Open-Source iOS Apps
trlx - A repo for distributed training of language models with Reinforcement Learning via Human Feedback (RLHF)
Material - A UI/UX framework for creating beautiful applications.
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.
Kingfisher - A lightweight, pure-Swift library for downloading and caching images from the web.
sparsegpt-for-LLaMA - Code for the paper "SparseGPT: Massive Language Models Can Be Accurately Pruned in One-Shot" with LLaMA implementation.
Hero - Elegant transition library for iOS & tvOS
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.
awesome-swift - A collaborative list of awesome Swift libraries and resources. Feel free to contribute!