→ @dadabots ← Creative AI & Death Metal #DSP #MIR #NLP #ML #NeuralNetworks | @Harmonai_org
Joined July 2009
- Tweets 1,440
- Following 594
- Followers 850
- Likes 1,110
36 Photos and videos
Pinned Tweet
12 Nov 2017
Our paper "Generating Black Metal and Math Rock: Beyond Bach, Beethoven, and Beatles" got accepted by NIPS 2017 Workshop for Machine Learning for Creativity and Design! @zzuk_at_aol #dadabots
2
7
40
WizardCoder-15B is crushing it‼️🔥
Amazing progress in open-source code LLMs recently. I believe open-source may have progressed beyond closed-source models in this area.
github.com/nlpxucan/WizardLM
14 Jun 2023
🔥🔥🔥
Introduce the newest WizardCoder model !
1. Surpass Claude-Plus ( 6.8), Bard ( 15.3) and InstructCodeT5 ( 22.3) on HumanEval Benchmarks
2. Paper is coming, with brand-new Evol methods for code LLMs
Github:
github.com/nlpxucan/WizardLM…
HF Weight:
huggingface.co/WizardLM/Wiza…
6
119
531
165,672
CJ Carr retweeted
16 Jun 2023
GPT-Engineer is BLOWING UP on GitHub right now 🔥
Prompt an AI agent to write an entire codebase 🤯
2k stars today alone. I'll be experimenting with it this weekend to improve my workflow.
31
209
1,843
576,229
CJ Carr retweeted
10 Jun 2023
Absolutely fantastic work. Congrats! \m/
4 Jun 2023
Darius's "Hyperbolic Audio Source Separation" paper has been recognized as one of the top 3% of all papers accepted at #ICASSP2023 @ieeeICASSP 👏🎉🍾
Paper: arxiv.org/abs/2212.05008
Code: github.com/merlresearch/hype…
Demo video: youtube.com/watch?v=RKsAMb9z…
1
8
845
CJ Carr retweeted
11 Jun 2023
Interesting alternative derivation of diffusion models without differential equations or variational inference. Reminiscent of flow matching / rectified flow.
Which of these perspectives is the simplest is subjective IMO, but more is better: new perspectives inspire new ideas!
9 Jun 2023
When @_Laurent and I started learning about diffusion models, we were puzzled by the amount of jargon and concepts.
So, we derived a model from scratch with our own graphics-people intuitions. Simple derivation, simple implementation, SOTA quality.
ggx-research.github.io/publi…
2
10
85
26,713
CJ Carr retweeted
14 May 2023
3/ Volume control
42
725
11,434
679,874
CJ Carr retweeted
3 May 2023
the year is 2030. after ed sheeran lost his case, musicians exhausted every 4-bar chord progression. pop music now features 23-bar cycles. tutorial videos explain how to escape copyright infringement using arabic 17 tone equal temperament. noise music experiences a renaissance.
39
357
2,545
153,822
CJ Carr retweeted
1 May 2023
One of the coolest uses I’ve seen of a NeRF so far
27
106
934
204,885
CJ Carr retweeted
19 Apr 2023
embodied experience as to what it is like to be a big bird
18 Apr 2023
VRヘッドトラッキングを使ってドローンのパイロット気分を味わう
youtu.be/N5cBKmFZ6Lo
#FPV #POV #drone #OpenSource #HeadTracker #HMD #VR #VirtualReality #UX #experience
1
4
30
8,122
CJ Carr retweeted
19 Apr 2023
Announcing StableLM❗
We’re releasing the first of our large language models, starting with 3B and 7B param models, with 15-65B to follow. Our LLMs are released under CC BY-SA license.
We’re also releasing RLHF-tuned models for research use. Read more→ stability.ai/blog/stability-…
67
848
3,527
1,208,981
Rather than sign some letter to delay AI progress, I signed @LAION_AI petition to democratize AI research by establishing an international, publicly funded supercomputing facility equipped with 100K SOTA accelerators to train open source foundation models.
openpetition.eu/petition/onl…
20
118
646
130,102
CJ Carr retweeted
6 Apr 2023
possibly one of the funniest model on the hub (the RLHF tutorial that was the reason of its creation is also awesome - check it out)
6 Apr 2023
Excited to introduce: StackLlama🦙
An end-to-end tutorial for training Llama with RLHF on preference data such as the StackExchange questions!
Blog: hf.co/blog/stackllama
Demo: hf.co/spaces/trl-lib/stack-l…
Code: github.com/lvwerra/trl/tree/…
The resulting model is surprisingly fun!🧵
1
25
7,719
CJ Carr retweeted
25 Mar 2023
The last couple of weeks on Twitter, aka GPT4 Twitter
29
102
644
94,466
CJ Carr retweeted
26 Mar 2023
Everyone's job description after GPT-5
158
2,060
12,361
1,984,010
CJ Carr retweeted
26 Mar 2023
Semi-realtime Stable Diffusion image-to-image (Van Gogh style),
Unity plugin based on Apple's Core ML port.
The latency is about 2 seconds on M1 Max MacBook Pro.
github.com/keijiro/StableDif…
31
325
1,872
292,333
🎧🧠
19 Dec 2022
🎵Introducing Diffusion Radio - A 24/7 Livestream of AI-Generated Music!🎵
📢The Harmonai team is excited to announce a New YouTube Live Stream which will run 24/7, showcasing amazing samples of AI-generated music from our latest models!📢
🎉Enjoy!🎉
youtube.com/watch?v=uGRLOMf2…
3
4
26
4,544
CJ Carr retweeted
7 Dec 2022
New paper from our research team: First true multimodal image synthesis. You can prompt any combination of texts and images. Also shows the power of our multimodal embedding. Check out the Catronaut in the paper.
M-VADER: A Model for Diffusion with Multimodal Context
abs: arxiv.org/abs/2212.02936
2
22
145
You can now make stable diffusion music videos that interpolate to the beat of a song using stable_diffusion_videos==0.5.0! 🚀
I basically rewrote the codebase! Everything is in the pipeline class now, so you can load other models too.
Anyway, here's how to use it...
21
222
1,708