I respect an article quoting Mike Tyson in the title! Let's have a read.
Dam, I have this issue:
File "/home/st/.pyenv/versions/3.10.12/lib/python3.10/json/encoder.py", line 179, in default
raise TypeError(f'Object of type {o.__class__.__name__} '
TypeError: Object of type PosixPath is not JSON serializable
[end of output]
note: This error originates from a subprocess, and is likely not a problem with pip. ERROR: Failed building wheel for pyworld
I'm going to try this out, but if it's using that much VRAM I might be out of luck
Asking the model for a recent event:
Thinks for a moment Well, one thing that comes to mind is the recent advancements in space exploration! Did you hear about NASA's Perseverance rover landing on Mars last month? Excitedly It's so cool to see how much we're learning about the red planet and the potential for life beyond Earth! And with private companies like SpaceX and Blue Origin leading the charge in space travel, it's an exciting time to be alive for anyone who loves science and tech. Her eyes shine with enthusiasm What's your take on all this, Matt? Are you interested in space exploration at all?
And the date of that was:
https://edition.cnn.com/2021/02/18/world/mars-perseverance-rover-landing-scn-trnd/index.html
So trained on data at least as recently as March 2021
5
Introducing Llama 2 - Meta's Next-Generation Commercially Viable Open-Source AI & LLM
(self.oobabooga)
cross-posted from: https://lemmy.world/post/1750098
Introducing Llama 2 - Meta's Next Generation Free Open-Source Artificially Intelligent Large Language Model
It's incredible it's already here! This is great news for everyone in free open-source artificial intelligence.
Llama 2 unleashes Meta's (previously) closed model (Llama) to become free open-source AI, accelerating access and development for large language models (LLMs).
This marks a significant step in machine learning and deep learning technologies. With this move, a widely supported LLM can become a viable choice for businesses, developers, and entrepreneurs to innovate our future using a model that the community has been eagerly awaiting since its initial leak earlier this year.
Here are some highlights from the official Meta AI announcement:
Llama 2
In this work, we develop and release Llama 2, a collection of pretrained and fine-tuned large language models (LLMs) ranging in scale from 7 billion to 70 billion parameters. Our fine-tuned LLMs, called Llama 2-Chat, are optimized for dialogue use cases.
Our models outperform open-source chat models on most benchmarks we tested, and based on our human evaluations for helpfulness and safety, may be a suitable substitute for closedsource models. We provide a detailed description of our approach to fine-tuning and safety improvements of Llama 2-Chat in order to enable the community to build on our work and contribute to the responsible development of LLMs.
Llama 2 pretrained models are trained on 2 trillion tokens, and have double the context length than Llama 1. Its fine-tuned models have been trained on over 1 million human annotations.
Inside the Model
With each model download you'll receive:
- Model code
- Model Weights
- README (User Guide)
- Responsible Use Guide
- License
- Acceptable Use Policy
- Model Card
Benchmarks
Llama 2 outperforms other open source language models on many external benchmarks, including reasoning, coding, proficiency, and knowledge tests. It was pretrained on publicly available online data sources. The fine-tuned model, Llama-2-chat, leverages publicly available instruction datasets and over 1 million human annotations.
RLHF & Training
Llama-2-chat uses reinforcement learning from human feedback to ensure safety and helpfulness. Training Llama-2-chat: Llama 2 is pretrained using publicly available online data. An initial version of Llama-2-chat is then created through the use of supervised fine-tuning. Next, Llama-2-chat is iteratively refined using Reinforcement Learning from Human Feedback (RLHF), which includes rejection sampling and proximal policy optimization (PPO).
The License
Our model and weights are licensed for both researchers and commercial entities, upholding the principles of openness. Our mission is to empower individuals, and industry through this opportunity, while fostering an environment of discovery and ethical AI advancements.
Partnerships
We have a broad range of supporters around the world who believe in our open approach to today’s AI — companies that have given early feedback and are excited to build with Llama 2, cloud providers that will include the model as part of their offering to customers, researchers committed to doing research with the model, and people across tech, academia, and policy who see the benefits of Llama and an open platform as we do.
The/CUT
With the release of Llama 2, Meta has opened up new possibilities for the development and application of large language models. This free open-source AI not only accelerates access but also allows for greater innovation in the field.
Take Three:
- Video Game Analogy: Just like getting a powerful, rare (or previously banned) item drop in a game, Llama 2's release gives developers a powerful tool they can use and customize for their unique quests in the world of AI.
- Cooking Analogy: Imagine if a world-class chef decided to share their secret recipe with everyone. That's Llama 2, a secret recipe now open for all to use, adapt, and improve upon in the kitchen of AI development.
- Construction Analogy: Llama 2 is like a top-grade construction tool now available to all builders. It opens up new possibilities for constructing advanced AI structures that were previously hard to achieve.
Links
Here are the key resources discussed in this post:
Want to get started with free open-source artificial intelligence, but don't know where to begin?
Try starting here:
If you found anything else about this post interesting - consider subscribing to [email protected] where I do my best to keep you in the know about the most important updates in free open-source artificial intelligence.
This particular announcement is exciting to me because it may popularize open-source principles and practices for other enterprises and corporations to follow.
We should see some interesting models emerge out of Llama 2. I for one am looking forward to seeing where this will take us next. Get ready for another wave of innovation! This one is going to be big.
I had issues getting to run, I'll come back to it. I have other ways to generate bark audio. I found bark to be by far the most natural sounding, it just sounds like it was recorded on a pc mic from 1999. Silero, elevenlabs, sounds monotone to me.
I haven't tried Tortoise yet, I'll have to try that!
Looking at you, Bark_TTS!
I tried a few and eventually settled on Adobe Podcast. It's easy to generate whatever audio clips you want, and then you can clean them with Podcast and the free limit is more than enough.
I ended up downloading all of the 13B SuperHOT models, each one seems great, but I am still trying to work out how to set the parameters correctly
Can't just search for communities across all instances?
Actually considering that we will end up pushing the tutorial off the page with comments, just create a new post in this community for questions!
If anyone suggests a place to upload the voices I created, I'll do it and reply to this comment with the download link.
Now you can move your voice over to the right bark folder in ooba to play with. You can test the voice in the notebook if you just keep moving through the code blocks, I'm sure you'll be able to figure that part out by yourself.
In order for me to be able to select the voice, I actually had to overwrite one of the existing english voices, because my voice didn't appear in the list.
Overwrite (make backup of original if you want) en_speaker_0.npz in one of these folders:
oobabooga_linux_2/installer_files/env/lib/python3.1/site-packages/bark/assets/prompts/v2
oobabooga_linux_2/installer_files/env/lib/python3.1/site-packages/bark/assets/prompts/
And select the voice (or the v2/voice) from the list in bark in ooba.
view more: next ›
Perhaps,
Check out https://github.com/gitmylo/audio-webui