Kern AI retweeted
Curious about how to use Entity RAG alongside vector databases to build highly accurate and trustworthy Large Language Models?
Check this webinar we recorded recently with @MeetKern youtu.be/QUdIpXUxaAc?si=R7UL…
Kern AI retweeted
I will be talking about Entity RAG for LLMs in regulated environments together with @MeetKern on 23rd April.
Want to use LLMs in a regulated environment? You need a trusted source of truth. We will build a chat bot live in the demo and show it working +/- RAG. 🤖
Link below. 👇
Kern AI retweeted
LLMs are a hot topic but they can be dangerous - especially in regulated environments if they are not based on a trusted source of truth.
Join us and @MeetKern in a webinar on 23rd April where they will discuss how to make reliable, accurate LLMs based on Entity RAG. 👇
Kern AI retweeted
Explore the future of AI with our exclusive interview featuring @johoetter, CEO & Co-founder of @MeetKern, at @Finovate Europe!
🎥 Watch now for a deep dive into the future of AI! 👇fintechfutures.com/2024/03/v…
Kern AI retweeted
Today we’re releasing Code Llama, a large language model built on top of Llama 2, fine-tuned for coding & state-of-the-art for publicly available coding tools.
Keeping with our open approach, Code Llama is publicly-available now for both research & commercial use.
More ⬇️
Kern AI retweeted
just listed a couple of new open-source opportunities by companies like @prisma, @MeetKern, @meilisearch, or @SafeGlobal_
👉 ossjobs.dev
Kern AI retweeted
Congratulations to 8 of our #IntelLiftoff members who made it onto the German AI Startup Landscape 2023 list! Special applause to @Ask_ui, listed in the Top 20! Learn more: intel.ly/3Qa39hw @ebenbuild @motionscloud @MeetKern 🧠💡
Kern AI retweeted
this is wild — kNN using a gzip-based distance metric outperforms BERT and other neural methods for OOD sentence classification
intuition: 2 texts similar if cat-ing one to the other barely increases gzip size
no training, no tuning, no params — this is the entire algorithm:
![for (x1, _) in test_set: Cx1 = len(gzip.compress(x1.encode())) distance_from_x1 = [] for (x2, _) in training_set: Cx2 = len(gzip.compress(x2. encode()) x1x2 = " ".join([x1, x2]) Cx1x2 = len(gzip.compress(x1x2. encode()) ncd = (Cx1x2 - min(Cx1,Cx2)) / max(Cx1, Cx2) distance_from_x1.append(ncd) sorted_idx = np.argsort(np.array(distance_from_x1)) top_k_class = training_set[sorted_idx[:k], 1] predict_class = max(set(top_k_class), key=top_k_class.count)](https://pbs.twimg.com/media/F05HxqsWwAAHRCI.jpg?name=small&format=webp)
ALT for (x1, _) in test_set: Cx1 = len(gzip.compress(x1.encode())) distance_from_x1 = [] for (x2, _) in training_set: Cx2 = len(gzip.compress(x2. encode()) x1x2 = " ".join([x1, x2]) Cx1x2 = len(gzip.compress(x1x2. encode()) ncd = (Cx1x2 - min(Cx1,Cx2)) / max(Cx1, Cx2) distance_from_x1.append(ncd) sorted_idx = np.argsort(np.array(distance_from_x1)) top_k_class = training_set[sorted_idx[:k], 1] predict_class = max(set(top_k_class), key=top_k_class.count)
this paper's nuts. for sentence classification on out-of-domain datasets, all neural (Transformer or not) approaches lose to good old kNN on representations generated by.... gzip aclanthology.org/2023.findin…
Kern AI retweeted
For folks looking to learn NLP, the slides for Stanford's excellent cs224n courses are all available here (scroll to the bottom for the latest version):
web.stanford.edu/class/cs224…
Kern AI retweeted
LIMA :
LLaMA 65B + 1000 supervised samples = {GPT4, Bard} level performance.
From @MetaAI
arxiv.org/abs/2305.11206
Kern AI retweeted
MMS: Massively Multilingual Speech.
- Can do speech2text and text speech in 1100 languages.
- Can recognize 4000 spoken languages.
- Code and models available under the CC-BY-NC 4.0 license.
- half the word error rate of Whisper.
Code+Models: github.com/facebookresearch/…
Paper: scontent-lga3-2.xx.fbcdn.net…
Blog: ai.facebook.com/blog/multili…
Kern AI retweeted
Promising. Everyone should hope that we can throw away tokenization in LLMs. Doing so naively creates (byte-level) sequences that are too long, so the devil is in the details.
Tokenization means that LLMs are not actually fully end-to-end. There is a whole separate stage with its own training and inference, and additional libraries. It complicates the ingest of additional modalities. Tokenization also has many subtle sharp edges. Few examples:
That "trailing whitespace" error you've potentially seen in Playground? If you end your (text completion API) prompt with space you are surprisingly creating a big domain gap, a likely source of many bugs:
blog.scottlogic.com/2021/08/…
Tokenization is why GPTs are bad at a number of very simple spelling / character manipulation tasks, e.g.:
xitter.cf/npew/status/1525…
Tokenization creates attack surfaces, e.g. SolidGoldMagikarp, where some tokens are much more common during the training of tokenizer than they are during the training of the GPT, feeding unoptimized activations into processing at test time:
lesswrong.com/posts/aPeJE8bS…
The list goes on, TLDR everyone should hope that tokenization could be thrown away. Maybe even more importantly, we may find general-purpose strategies for multi-scale training in the process.
MEGABYTE: Predicting Million-byte Sequences with Multiscale Transformers
abs: arxiv.org/abs/2305.07185
paper page: huggingface.co/papers/2305.0…
Kern AI retweeted
With Twitter open-source, the issues of its repository have gone wild. Check out my blog post on this topic here: dev.to/meetkern/twitter-issu…
Kern AI retweeted
Revolutionize your natural language processing with Kern AI's refinery editor! Create NLP automations in just one afternoon! #KernAI #NLP #automation @meetkern | give them some love: domore.ai/tools/kern.ai and vote them up for the tool of the month!
Kern AI retweeted
Starting with amazing @MeetKern team
Online event 📍
Link to join: discord.gg/Ny9PG36NRw?event=…
Kern AI retweeted
🎞️For anyone who missed or wants to re-watch yesterday's event about the linguistic side of NLP with @LAWeissweiler, we are happy to share that the recording is now available on YouTube!
Enjoy🥨: youtu.be/tBQKswYlQNs
Kern AI retweeted
🙌 @MeetKern are best-in-class in empowering the data-centric developer community and we are delighted to back the team in driving innovation in the NLP space. Thank you for choosing us!
techcrunch.com/2023/02/16/ge…
Kern AI retweeted
Kern AI @MeetKern Raises €2.7 Million in Seed Round
#SaaS #AI #DataCentric #nlp #developer #seedround to power data-centric natural language processing #funding
thesaasnews.com/news/kern-ai…
Kern AI retweeted
Berlin-based @MeetKern, a company that helps embed modern natural language processing into any organisation’s products and processes, has secured €2.7M. Know more here: https://xitter.cf/t.co/sFSx8T8tlB
@johoetter, @seedcamp #Funding

























