Pavlo B

[Pavlo B @p_bendus]

4.8 is here

[Pavlo B @p_bendus]

@LordTylerWard too early

[Pavlo B @p_bendus]

@kunalvg 🙌

[Pavlo B @p_bendus]

@cleanunicorn 😱

[Jai Bhavnani @jaibhavnani]

Lending onchain is very inefficient.

Here's why:
- Most lent capital is unused and could more effectively be deployed elsewhere
- Limited price discovery between lenders/borrowers
- Risk management is at odds with liquidity

Dahlia solves it. Built on Royco. Pretty exciting

[Dahlia - Lend & Borrow 🌸 @DahliaProtocol]

Our application is LIVE on @berachain 🪇🎀🪇

[Pavlo B @p_bendus]

@LordTylerWard @DAOser_x Hey ser, feel free to jump into our Discord server so we can work this out: https://t.co/3557GH7KUX

[Pavlo B @p_bendus]

@TroyMurs he's a beast

[QUBIC Labs @QUBIC_LABS]

We're excited to announce that @SanctumAI is joining the QUBIC Labs family with a $25K grant through our R&D Innovation Program!🚀🤝

@SanctumAI is revolutionizing #AI privacy with:
• Local open-source LLMs
• On-device encryption
• Offline AI capabilities

Join us in celebrating this milestone and welcoming the Sanctum team to the QUBIC Labs family🥳

[Christian @cc_crowley]

Excited to share that @SanctumAI is sponsoring the AI Privacy & Safety night at @MIT on Nov 20th w/ @theaifurnace! I'll be demo-ing our app alongside other awesome companies, including @enkryptai, Versara AI & I-XRAY.

Come by if you're in Boston: https://t.co/DKjgi2jCjL

[Pavlo B @p_bendus]

@SanctumAI Local audio AI processing is coming!

[Sanctum @SanctumAI]

Cooking something really COOL for the next release 👨‍🍳

[Pavlo B @p_bendus]

@adamscochran Thanks for your strong and rational position here!

[Pavlo B @p_bendus]

@cc_crowley @SanctumAI @blockchainwk @QUBIC_LABS let's goo

[Sanctum @SanctumAI]

Today we're excited to release Sanctum v1.6 with a new UI and a set of new features for the dev community ✨

🎭 New UI
With simplified navigation and updated interface Sanctum gets better, making room for even more exciting features.

🗄️ Local API Server
Powered by llama.cpp, our UI lets you run a local server with any @huggingface model in seconds. Customize ports, server parameters, and monitor resources with ease.

⚙️ Advanced Model Settings
Tweak local LLMs with custom prompt templates, hardware optimization, and inference parameters.

Both features are part of the new Dev mode, enabled by default.

Discover all the updates now 👇
https://t.co/tcmejpgR0o

[Sanctum @SanctumAI]

We have successfully fine-tuned a Llama-3-8B-Instruct model on a custom dataset for function calling to the CoinGecko API. 

One of our lead developers, Andrii Kotliar, stated “Creating the dataset took some time as we figured out how to ensure the model responds appropriately to day-to-day questions while also understanding when it needs to respond with a specific function… 

Once we figured out the installation details for the @NVIDIAAIDev AI Workbench, the fine-tuning process was smooth, and the unsloth booster helped us achieve results much faster.” 

Links to the model and dataset on Huggingface below. We’ve made the repositories public for easy access.

Links below: 👇✨

Model: https://t.co/BaIdNf20bm

Model (GGUF): https://t.co/BaIdNf20bm

Dataset: https://t.co/WhHcilmLxR

[Pavlo B @p_bendus]

@lisa_kirj Чому?

[Pavlo B @p_bendus]

RT @SanctumAI: Sanctum v1.4 Update 💥

We’re excited to announce Sanctum v1.4 release, here's what's new:

🔗 HuggingFace Integration
Downloa…

[Rootscan @rootscan_io]

We're excited to share that we're now running a validator node for @TheRootNetwork 💥

If you're staking $ROOT on the portal and would like to to nominate it to Rootscan - it's easy to find us on the list 🤗

[Sanctum @SanctumAI]

Today we're live on ProductHunt 💥

Upvote to support us ❤️
https://t.co/eC4dxdz5zD