lm-human-preferences
tensorrtx
Our great sponsors
| lm-human-preferences | tensorrtx | |
|---|---|---|
| 8 | 3 | |
| 1,099 | 6,536 | |
| 4.7% | - | |
| 2.7 | 8.0 | |
| 9 months ago | 9 days ago | |
| Python | C++ | |
| MIT License | MIT License |
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.
lm-human-preferences
- Ask HN: Open-source GPT-3 alternatives
- El éxito continuo de OpenAI: Y como llegaron a crear la IA más avanzada del 2023. ChatGPT.
-
Sam Altman on the best and worst case scenario for AI - "...the good case is just so unbelievably good that you sound like a really crazy person to start talking about it."
Lest you think that that sounds like a too galaxy-brained possibility, it has already happened at OpenAI (scroll down to "Bugs can optimize for bad behavior"), just with a model that was very far from being capable enough to be dangerous.
-
Value head in GPT2
Found relevant code at https://github.com/openai/lm-human-preferences + all code implementations here
-
Should we stick to the devil we know?
That's why, when they're serious, they use RL for finetuning from human preferences (would be hilarious if this attempt to solve the terrible bias you take to be evidence of AGI threat ends up creating a Woke Singleton itself, btw); it's a powerful general approach, and I see no sign of it being applied here.
-
Dall-E 2
The kind of measures they are taking, like simply deleting wholesale anything problematic, don't really have a '-1'.
But amusingly, exactly that did happen in one of their GPT experiments! https://openai.com/blog/fine-tuning-gpt-2/
- Discussion Thread
-
[D] Applications for using reinforcement learning to fine-tune GPT-2
Code for https://arxiv.org/abs/1909.08593 found: https://github.com/openai/lm-human-preferences
tensorrtx
-
A Three-pronged Approach to Bringing ML Models Into Production
In terms of the latter, this is quite common when employing non-standard SOTA models. You may discover a variety of TensorRT implementations on the web if you want to use popular models—for example, in the project where we needed to train an object-detection algorithm on Rutorch and deploy it on Triton, we used many cases of PyTorch -> TensorRT -> Triton. The implementation of the model on TensoRT was taken from here. You may also be interested in this repository, as it contains many current implementations supported by developers.
-
Dall-E 2
I'll try them out. I have an RTX 2070, which apparently supports fp16. But it only has 8GB RAM.
I used the instructions here to check: https://github.com/wang-xinyu/tensorrtx/blob/master/tutorial...
-
Increasing usb cam FPS with Yolov5 on a Jetson Xavier NX?
Optimize your model using TensorRT. There is a good implementation here: https://github.com/wang-xinyu/tensorrtx/tree/master/yolov5
What are some alternatives?
trl - Train transformer language models with reinforcement learning.
TensorRT - NVIDIA® TensorRT™ is an SDK for high-performance deep learning inference on NVIDIA GPUs. This repository contains the open source components of TensorRT.
GLM-130B - GLM-130B: An Open Bilingual Pre-Trained Model (ICLR 2023)
tensorflow-yolov4-tflite - YOLOv4, YOLOv4-tiny, YOLOv3, YOLOv3-tiny Implemented in Tensorflow 2.0, Android. Convert YOLO v4 .weights tensorflow, tensorrt and tflite
dalle-mini - DALL·E Mini - Generate images from a text prompt
v-diffusion-pytorch - v objective diffusion inference code for PyTorch.
glide-text2im - GLIDE: a diffusion-based text-conditional image synthesis model
gpt-2 - Code for the paper "Language Models are Unsupervised Multitask Learners"
dalle-2-preview
SegmentationCpp - A c++ trainable semantic segmentation library based on libtorch (pytorch c++). Backbone: VGG, ResNet, ResNext. Architecture: FPN, U-Net, PAN, LinkNet, PSPNet, DeepLab-V3, DeepLab-V3+ by now.