Decision Making With Feedforward Multilayer Perceptrons
Des Moines, IA
Joined September 2008
- Tweets8.4K
- Following98
- Followers1.9K
- Likes3.2K
I'm /beyond/ excited to join the next cohort on AI Powered Search with @softwaredoug and @treygrainger 🥳
maven.com/search-school/ai-p…
Toran Billups retweeted
On AI in enterprises: models come and go; the true competitive advantage lies not in which frontier models you use but in how effectively you can connect those models to your organization's knowledge.
Toran Billups retweeted
ModernBERT is available as a slot-in replacement for any BERT-like model, with both 139M param and 395M param sizes.
It has a 8192 sequence length, is extremely efficient, is uniquely great at analyzing code, and much more. Read this for details:
huggingface.co/blog/modernbe…
This blog post from the team @bitcrowd is an outstanding resource for those who want to leverage SOTA embeddings with bumblebee. Easily the highest value resource I've seen on the subject yet. This post in particular covers the path from zero to Jina v2 bitcrowd.dev/how-to-run-jina…
Toran Billups retweeted
Me at 25: Tests should be 5ish lines! One assert per test!
Me at 40: This test is 56 lines long with 11 asserts. If I broke it up, it would be 11 separate tests, ~5x as much code, multiple helper functions and `beforeEach`s to avoid duplication, and more difficult to read.
Toran Billups retweeted
Data is all we need! 💎 @Alignment Labs AI just released Buzz, an instruction dataset with 3.13 million rows and a total of 85 million conversations in single- and multiturns. 🤯 It comes in 3 configurations: Buzz (SFT), RLSTACK (RLHF), Select Stack (filtered SFT)
TL;DR:
💥 Curated, deduplicated, extended, and regenerated from 435 datasets
🧠 Training Llama 3 on it with Buzz-8b-Large
🌍 85 million conversational turns, including new and augmented data
⚖️ RLSTACK contains 1 million samples of DPO preference pairs
🥇 Select stack contains 1.5 million samples of the top-scoring response
🔄 intend to update and improve the dataset
🔓 Released under cc-by-4.0
🤗 Available on @huggingface
Kudos to the team at @alignment_lab and @HIVEDigitalTech for this release! I am looking forward to read and learn more about the creation process! 🤗
Toran Billups retweeted
New talk from @toranb, Adventures with Synthetic Data (lessons learned building a chatbot from my SMS dataset), presenting at the Denver Elixir Meetup!
#myelixirstatus
youtube.com/watch?v=R0VJIW0I…
My favorite podcast of 2024! @peterg021 absolutely levels the pod with such a unique blend of business and machine learning from his experience in product. Thanks for sharing in such detail, this content stretched me in a few dimensions 🤯
I had a blast with Gemma 7B this weekend using the latest bumblebee so I put together a single file example for those interested gist.github.com/toranb/6a335…
I had trouble converting Mistral 8B Pro to GGUF format recently so I recorded a short how-to for llama-cpp n00bs like myself.
Check it out! 👇
The next version of bumblebee is out and it's working great with Mistral 7B from HF using bf16 OOTB. It's great to see the platform moving forward with loads of improvements!
Toran Billups retweeted
Introducing YouTune — fine tune image models on YouTube videos.
> python tune.py <youtube-url>
• downloads video
• screenshots every 50 frames
• removes near duplicates
• fine tunes SDXL for you
github.com/cbh123/youtune
Toran Billups retweeted
Tomorrow marks 13 years since the first commit to the Elixir repo. And today we celebrate by announcing that Elixir is, officially, a gradually typed language:
On November 1st I joined the first RAG cohort from MLOps.Community and went hard for 8 weeks building a proof of concept that combined everything from embedding models, prompting, and retrieval to ranking with a cross encoder to support hybrid search.
Big thanks to @RahulParundekar for all his hard work ahead of the long journey, the consistent encouragement and the 1v1 coaching!
Easily the most valuable, grounded and applicable podcast of the year for me. Jump ahead to 39:22 for the recommendation system pro-tips that include upstream tuning around retrieval and ranking. Pure gold from @BEBischof
🆕 pod: with @BEBischof of @_hex_tech!
latent.space/p/bryan-bischof
On putting AI Magic into Notebooks, and how RAG is actually a recommendation systems problem.
Also an @AAAzzam hot take: LLMOps is more like an "iron mine" than a "gold rush"!
Fine tune Mistral 7B with a single RTX 4090 and serve it with Nx! Big thanks to @jon_durbin and @sean_moriarity
Check it out! 👇
#MyElixirStatus
Toran Billups retweeted
This is a really great intro to machine learning and fine-tuning in @elixirlang by @toranb 🙌 youtube.com/watch?v=-iZIZHgH… #myelixirstatus
Retrieval Augmented Generation with Bumblebee and Llama 2
Check it out! 👇
#MyElixirStatus