We're excited to announce that Spectral joins Hugging Face’s Expert Support Program, where we’re working with deep learning experts from Hugging Face to advance open-source models, datasets, and applications for the Onchain Agent Economy.
How we use Hugging Face
Hugging Face plays a critical role across our organization. Through the Expert Support Program, we regularly meet with the Hugging Face team to plan new use cases, strategize dataset construction, and develop training strategies.
Earlier this year, we launched Syntax, which is composed of a fine-tuned LLM orchestrator that routes queries between several tools, including search, Foundry, and an open-source model to generate Solidity code. Building Syntax required custom datasets for both finetuning and RAG, an original Solidity evaluation dataset written by elite smart contract developers, and experimentation across a wide range of open and closed-source models.
Our approach to dataset preparation, training, routing, and evaluation has drastically improved during this process, largely due to help from Hugging Face experts. Regular discussions on our approach mean that we always get impartial feedback on our decisions and can reevaluate our strategy as we go. This was important for both our finetuning and evaluation steps, which have now gone through several rounds of improvement thanks to the Hugging Face team.
We also rely on Hugging Face for inferences in production through dedicated Inference Endpoints. The fully managed infrastructure lets us iterate on new models quickly, easily update container and hardware configurations, autoscale with demand, and keep production costs low.
Over the coming months, we're excited to continue to open-source our work with onchain datasets and models that interact onchain through Hugging Face. You can view our training dataset for the credit scoring challenge and follow our progress here.
The Onchain Agent Economy
Syntax is pioneering the accessible onchain Agent Economy, inviting users to select agents tailored for their specific tasks. Users can either interact with the foundational agent to generate solidity code or opt for one of the specialized agents, each adept in distinct tasks. For example, we recently launched Syntax MoonMaker, an agent that launches a memecoin project end to end, and are soon launching Syntax- TestMachine, an agent that detects vulnerabilities in your smart contracts. Many such agents are currently in production, and upcoming releases of our product will allow users to create their own agents and monetize them on the Syntax network.
This system relies on a vast suite of functions available to language models, open-source models for tasks like classification and image generation, fast and reliable blockchain infrastructure, and a trustless system to execute and verify each step. To solve these problems, we've begun developing the Inferchain, optimized to serve the rapidly growing demand for agents and verifiable inferences.
Hugging Face Users joining the Onchain AI community
The importance of open collaboration cannot be overstated. Like many other projects, Spectral would not exist without the work of open-source contributors. We are greatly indebted to everyone who makes this work possible and believe this positive impact should be recognized.
As part of this engagement, we are focusing specifically on users powering the AI community. The top individual and small organization contributors on Hugging Face, measured by likes and downloads of their models and datasets, are eligible to register to claim a share of SPEC tokens starting the week of May 6th. You can check eligibility by signing in with your Hugging Face account here. A snapshot of activity was taken last month, and eligible users will not need an existing wallet to claim. This airdrop is designed to recognize users for their critical work and enable new functionality for the next generation of AI tools.
Criteria:
We looked at all individual contributors from organizations with less than 10 members that published models or datasets. From these we took a combined measure of activity from likes and downloads for both models and datasets. Then took the users with the most combined activity from both model and dataset publishers (11298 in both categories) which resulted in a final list of 20,004 unique huggingface users.
We’re looking forward to engaging with the open source community further and building the future of AI x web3!