LaMDA-rlhf-pytorch
PaLM-rlhf-pytorch
LaMDA-rlhf-pytorch | PaLM-rlhf-pytorch | |
---|---|---|
7 | 25 | |
454 | 7,614 | |
- | - | |
3.0 | 4.6 | |
4 months ago | 5 months ago | |
Python | Python | |
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.
LaMDA-rlhf-pytorch
-
All subscribers should have the same level of access
I made a mistake about the LaMDa, what I mean is the machine learning model that Lamda based on: Transformer. Though you can still access to the paper: [2201.08239] LaMDA: Language Models for Dialog Applications (arxiv.org) and a pyTorch implementation here: conceptofmind/LaMDA-rlhf-pytorch: Open-source pre-training implementation of Google's LaMDA in PyTorch. Adding RLHF similar to ChatGPT. (github.com)
-
Closest Open Source alternative to CharacterAI?
I know it'll be 10 times worse for now at best since this is refined proprietary tech where a lot of resources went into but I'm still looking forward to something aiming to achieve this level of fluency and context understanding that can be used open and freely. Closest thing I could find so far might be GPT2 or laMDA?
- LaMDA PyTorch
-
Open-Source LaMDA Model
An open-source implementation for the pre-training architecture of Google's LaMDA in PyTorch. The research paper outlines an autoregressive, decoder-only, GPT-like transformer language model. The transformer uses T5 relative positional bias in the attention layers and gated-GELU activation function in the feed-forward layers.
The repository currently contains a script for basic training as well as Huggingface datasets and Weights & Biases integration.
LaMDA research paper: https://arxiv.org/abs/2201.08239
Github repository for the model: https://github.com/conceptofmind/LaMDA-pytorch
The pre-training architecture was peer-reviewed by Dr. Phil Wang. Please check out and support his work: https://github.com/lucidrains.
Updates: https://twitter.com/EnricoShippole
-
[D] What if sentient AI has already taken over without us knowing?
If you want to view the pre-training architecture of a transformer model such as LaMDA, the one you are referencing in this post, you can view that here: https://github.com/conceptofmind/LaMDA-pytorch/blob/main/lamda_pytorch/lamda_pytorch.py
-
[D] length of input sequence for transformers?
An example for an iterable data loader like this would be: https://github.com/conceptofmind/LaMDA-pytorch/blob/main/dataloader/stream_dataloader.py
-
[P] Open-source LaMDA Model
Github repository for the model: https://github.com/conceptofmind/LaMDA-pytorch
PaLM-rlhf-pytorch
-
How should I get an in-depth mathematical understanding of generative AI?
ChatGPT isn't open sourced so we don't know what the actual implementation is. I think you can read Open Assistant's source code for application design. If that is too much, try Open Chat Toolkit's source code for developer tools . If you need very bare implementation, you should go for lucidrains/PaLM-rlhf-pytorch.
-
[P] Open-source PaLM models trained at 8k context length
AFAIK, it is not. They are using the open-source re-implementation of Phil Wang (aka lucidrains), which is available here: https://github.com/lucidrains/PaLM-rlhf-pytorch
-
Should AI language models be free software?
Not sure what do you mean by putting source code in double quote, but I don't think the source code is petabytes of text. GPT-2 implementation is few hundred lines of Python (in HuggingFace). PaLM + RLHF - Pytorch (Basically ChatGPT but with PaLM) is less than 1000 lines.
- Would a decentralized open-source platform of ChatGPT work?
- Exciting new shit.
-
Top 10 Best Open Source GitHub repos for Developers 2023
GitHub Link: https://github.com/lucidrains/PaLM-rlhf-pytorch
-
Gather up great coders and make a better Character.Ai
Well... Not necessarily. Actually, if you want to be extra thrifty, you could even go without an ML expert. Just use an open-source one, like LaMDA or PaLM. After that, use chatGPT to build you a basic front end (which would still be better than CAI lol).
-
Open-Source competitor to OpenAI?
and PaLM with RLHF from Phil Wang (open model, needs to be trained): https://github.com/lucidrains/PaLM-rlhf-pytorch
-
Microsoft in talks to acquire a 49% stake in ChatGPT owner OpenAI
Closest you can get is probably with Google T5-Flan [1].
It is not the size of the model or the text it was trained on that makes ChatGPT so performant. It is the additional human assisted training to make it respond well to instructions. Open source versions of that are just starting to see the light of day [2].
[1] https://huggingface.co/google/flan-t5-xxl
[2] https://github.com/lucidrains/PaLM-rlhf-pytorch
- Will we have a free version of ChatGPT (GPT-3) similar to Stable Diffusion?
What are some alternatives?
lamda-pytorch - Open-source pre-training implementation of Google's LaMDA in PyTorch. Adding RLHF similar to ChatGPT. [Moved to: https://github.com/conceptofmind/LaMDA-rlhf-pytorch]
nanoGPT - The simplest, fastest repository for training/finetuning medium-sized GPTs.
Conformer - An implementation of Conformer: Convolution-augmented Transformer for Speech Recognition, a Transformer Variant in TensorFlow/Keras
GLM-130B - GLM-130B: An Open Bilingual Pre-Trained Model (ICLR 2023)
awesome-RLHF - A curated list of reinforcement learning with human feedback resources (continually updated)
text-generation-webui - A Gradio web UI for Large Language Models. Supports transformers, GPTQ, AWQ, EXL2, llama.cpp (GGUF), Llama models.
Perceiver - Implementation of Perceiver, General Perception with Iterative Attention in TensorFlow
ggml - Tensor library for machine learning
iris - Transformers are Sample-Efficient World Models. ICLR 2023, notable top 5%.
trlx - A repo for distributed training of language models with Reinforcement Learning via Human Feedback (RLHF)
Open-Assistant - OpenAssistant is a chat-based assistant that understands tasks, can interact with third-party systems, and retrieve information dynamically to do so.
Rath - Next generation of automated data exploratory analysis and visualization platform.