Tweet épinglé
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
English
CJ Carr
1.4K posts
CJ Carr
@cortexelation
→ @dadabots ← Creative AI & Death Metal #DSP #MIR #NLP #ML #NeuralNetworks | @Harmonai_org
Boston Inscrit le Temmuz 2009
597 Abonnements859 Abonnés
"As A Large Language Model, I"
A short text of unclear character and purpose that I wrote when I couldn't sleep.
togelius.blogspot.com/2023/09/as-lar…
English
CJ Carr retweeté
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/Wizar…
WizardLM@WizardLM_AI
🔥🔥🔥 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/Wizar… HF Weight: huggingface.co/WizardLM/Wizar…
English
CJ Carr retweeté
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.
English
CJ Carr retweeté
Absolutely fantastic work. Congrats! \m/
Jonathan Le Roux@JonathanLeRoux
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/h… Demo video: youtube.com/watch?v=RKsAMb…
English
CJ Carr retweeté
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!
Eric Heitz@eric_heitz
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/publication/20…
English
CJ Carr retweeté
CJ Carr retweeté
CJ Carr retweeté
CJ Carr retweeté
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.
English
CJ Carr retweeté
CJ Carr retweeté
CJ Carr retweeté
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…
English
CJ Carr retweeté
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/onlin…
English
CJ Carr retweeté
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)
Leandro von Werra@lvwerra
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… Code: github.com/lvwerra/trl/tr… The resulting model is surprisingly fun!🧵
English
CJ Carr retweeté
The last couple of weeks on Twitter, aka GPT4 Twitter
English
CJ Carr retweeté
CJ Carr retweeté
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/Stable…
English
CJ Carr retweeté
CJ Carr retweeté
