Yeah but fastchat-t5 ranking decently for it's size on chatbot arena is a pretty good evidence of encoder decoder models being able to actually chat well.
OPEN SOURCE
-
LLaMA-Adapter and LoRA: Multimodal Input Advantages
By
–
Good question. I'd say LLaMA-Adapter and LoRA are both good methods. The advantage of LLaMA-Adapter though is that you can also embed multimodal inputs (images and others)
-
Grafana: From Open Source Project to Industry Standard
By
–
10 years ago @grafana was Torkel Ödegaard's open source passion project; today, it's an industry standard for making observability open and composable, and continues to simplify life for developers https://
infoworld.com/article/369925
8/how-grafana-made-observability-accessible.html
… by @mjasay for @InfoWorld -
Open-Source AI Game Jam: Free July 7-9 Event
By
–
We can't wait to see the incredible projects you'll create using these tools Claim your free spot in the Game Jam here: https://
itch.io/jam/open-sourc
e-ai-game-jam
… When? July 7 to 9 Where? Online How much? Free to participate -
Free Open Source Audio Machine Learning Course Launch
By
–
And if you're interested in going deeper into ML for Audio, we are releasing our Audio Course this Wednesday (Jun 14th)! It's fully open source and 100% free Sign up for the course http://
eepurl.com/insvcI
Our launch event https://
youtube.com/watch?v=wqkKRe
sXWB8
… -
Open Source AI Game Jam: Audio Tools for Developers
By
–
Calling all game dev and AI enthusiasts! Already 400 people signed up for the first Open Source AI Game Jam, where you'll use AI tools to make a game in a weekend Sign up here https://
itch.io/jam/open-sourc
e-ai-game-jam
… What AI tools? Let's focus today on Audio tools -
List of Open Language Models for Commercial Use
By
–
GitHub – eugeneyan/open-llms: A list of open LLMs available for commercial use. https://bit.ly/3MG7VRA #AI #MachineLearning #DeepLearning #LLMs #DataScience
-
LoRA Implementation Added to Lit-Parrot Project
By
–
Just added LoRA the other day (PR still in progress: https://
github.com/Lightning-AI/l
it-parrot/pull/128#pullrequestreview-1477273133
…) and will do some comparisons soon! -
Share Model Weights on Hugging Face Hub
By
–
Congratulations on such a fantastic feat! Would be really cool to host the weights on the hugging face hub! Happy to help!
-
LLaMA-Adapter: Efficient LLM Fine-tuning with Tunable Prefixes
By
–
I really like the LLaMA-Adapter method! In a nutshell, it's about finetuning LLMs more efficiently. In a nutshell, it's adding a tunable prefix to the key and value tensors in the self-attention layers. Fun fact: it's not specific to LLaMA. Use it with any LLM!