This looks really promising from @giuvecchio95
— fofr (@fofrAI) 21 novembre 2023
Hopefully code and models soon. https://t.co/JNdi4PbahA
This looks really promising from @giuvecchio95 Hopefully code and models soon.
OPEN SOURCE
-
Promising AI Project: Code and Models Expected Soon
By
–
-
Orca 2: Open-Source Language Models 7B and 13B Parameters
By
–
“Orca 2 comes in two sizes (7 billion and 13 billion parameters); both are created by fine-tuning the corresponding LLAMA 2 base models on tailored, high-quality synthetic data. We open-source Orca 2 to encourage further research…”
-
Fine-tuned Open-Source LLMs Outperform Commercial Solutions
By
–
Developers are realizing that #finetuned open-source LLMs like #Llama2 are more cost-effective and performant than commercial LLMs like #GPT4. Don't miss our interactive discussion on all things fine-tuning #LLMs to learn how to get started. https://
pbase.ai/3MQUwWL -
SDXL LCM Multi-ControlNet LoRA Model Released
By
–
The model is here, but still a little WIP: https://
replicate.com/fofr/sdxl-lcm-
multi-controlnet-lora
… And the code is here: -
Yi Open-Source Project on GitHub – Upcoming Releases
By
–
Star us on @github
, and stay tuned for more Yi open-source releases coming up! -
Building Welcoming Open Source Communities Through Code of Conduct
By
–
Make your open source community more welcoming by drafting a code of conduct, which helps set standards for acceptable behavior in a community space. But a code of conduct needs structures in place to ensure accountability https://
palantir.net/blog/making-yo
ur-open-source-community-more-welcoming
… #opensource -
LCM Model Distillation Quality Trade-offs with LoRA
By
–
The image quality of the fully distilled model (ie the original LCM) is really good, though it kind of forces a particular style. With the lora loaded versions, the quality takes a hit. I'm waiting for more fully distilled models to be released by @SimianLuo
-
Latent Consistency Model 3x Faster on Replicate
By
–
I've optimised my latent consistency model on Replicate to make it 3x faster: https://
replicate.com/fofr/latent-co
nsistency-model
… text to image, 4 steps at 768×768:
– was: 2s
– now: 0.6s -
Meta-FAIR’s Open Source Leadership Among AI Research Labs
By
–
Meta-FAIR's positive stance on open source is singular among industry research labs.
But it's not rare among AI researchers, including at Deepmind.
Interestinresnta number of folks in the DeepMind leadership are former students of mine, including @clmt
, @koraykv
, @RaiaHadsell
.