# Transformers Projects at AI Tinkerers

> Canonical HTML: https://aitinkerers.org/technologies/transformers
> Markdown URL: https://aitinkerers.org/technologies/transformers.md
> Technology record last updated: 2026-02-22T17:01:16Z
> Generated: 2026-09-22T07:42:39Z

The deep learning architecture that revolutionized sequence modeling (NLP, vision) by replacing recurrent units with a parallelizable multi-head self-attention mechanism.

The Transformer: a neural network architecture introduced in the landmark 2017 paper, "Attention Is All You Need." It eliminated the sequential processing bottleneck of prior Recurrent Neural Networks (RNNs) by relying solely on self-attention, enabling massive parallelization and significantly faster training (up to 10x faster) on modern hardware. This efficiency allowed for the creation of large-scale pre-trained models: BERT (encoder-only) and the generative GPT series (decoder-only). The architecture is now foundational to all modern Large Language Models (LLMs) and drives the current state-of-the-art in AI.

- Official technology site: https://doi.org/10.48550/arXiv.1706.03762
- Public AI Tinkerers demos and talks: 148
- Result page: 1 of 7

## Recent Public Talks and Demos

### [Entrena tu propio modelo sin morir en el intento: Optimización de recursos para LLMs](https://bogota.aitinkerers.org/talks/rsvp_fq9THYDMT-Q)

Entrenar o ajustar modelos de lenguaje grandes (LLMs) no tiene que ser exclusivo de grandes laboratorios con cientos de GPUs. En esta charla exploraremos cómo aprovechar al máximo recursos limitados (como una sola GPU o entornos colab) utilizando Python y librerías como transformers y trl. Compartiremos prácticas y técnicas para reducir el consumo de memoria y GPU sin sacrificar calidad, incluyendo el uso de LoRA, cuantización, batch inteligente, y más. Ideal para desarrolladores, estudiantes o startups que quieren hacer fine-tuning sin depender de infraestructura costosa.

- Event context: AI Tinkerers Bogotá - Julio 24 — Bogotá
- Public talk page: https://bogota.aitinkerers.org/talks/rsvp_fq9THYDMT-Q

### [Teaching a robot to always win connect four via LeRobot](https://berlin.aitinkerers.org/talks/rsvp_HveawmqfJoQ)

I trained an autonomous robot arm setup using Hugging Face’s LeRobot framework that plays a game of Connect Four and is annoying as it always beats human opponents. The robot perceives the physical board state via a camera, calculates the optimal move, and executes the physical token drop.

- Event context: AI Tinkerers Berlin - June 17, 2026 — 2026-06-17 — Berlin
- Public talk page: https://berlin.aitinkerers.org/talks/rsvp_HveawmqfJoQ

### [Silent Notetaker: no backend, no account, no upload](https://columbus.aitinkerers.org/talks/rsvp_2_Cj7Fhun3Y)

Silent Notetaker is a meeting notetaker that runs entirely in the browser: it transcribes the conversation live, pulls out decisions, action items, and open questions as they happen, with no audio ever leaving the machine. The whole app is a single HTML file, no backend and nothing to sign into. I'll demo it live with a real mic: transcription and speaker labels appearing in real time, notes self-categorizing, and an on-device LLM suggesting the next question to ask. Then review architecture (how the speech model, the speaker model, and the question model share one machine without fighting each other), show the single-file source for people to try out, modify and make it their own.

- Event context: AI Tinkerers - Columbus June Meetup — 2026-06-01 — Columbus
- Public talk page: https://columbus.aitinkerers.org/talks/rsvp_2_Cj7Fhun3Y

### [Nanochat: training your own LLM chat bot from scratch](https://belgium.aitinkerers.org/talks/rsvp_dBCcFb9t3nk)

I'll walk the audience through Andrej Karpathy's latest reincarnation of minGPT/nanogpt, namely nanochat. This repo contains all major LLM stages including tokenization, pretraining, finetuning, evaluation, inference, and even a chat UI. Its minimalistic implementation allows you to train and evaluate an LLM from scratch, on a single GPU node or even a CPU. With access to better GPU machines (e.g. an 8X H100), you can get up to GPT2-level performance in under 2 hours!

- Event context: AI Tinkerers Antwerp Meetup - April 1 (no joke) — 2026-04-01 — Belgium
- Public talk page: https://belgium.aitinkerers.org/talks/rsvp_dBCcFb9t3nk

### [Words to World, AI learning strategies for building world models.](https://san-diego.aitinkerers.org/talks/rsvp_mnJaK0Bd4l8)

Can a text prompt (or reference art) build a physically real world, no splats, no diffusion, but full physics? Once you have this, can a robot or biocomputer navigate it? Full demo of the system running live (local / remote hybrid) How it is all plumbed and built. The system uses a variety of learning strategies including self-modifying code and rules to both iteratively improve a world model and, iteratively improve the generation of that model AND, iteratively improve the improvement of that model (3 level hierarchy). It uses a large range of optimising strategies to avoid uncanny valley effects and attempt to produce cinematically realistic images.

- Event context: AI Tinkerers San Diego: February Meetup at Google — 2026-02-27 — San Diego
- Public talk page: https://san-diego.aitinkerers.org/talks/rsvp_mnJaK0Bd4l8

### [Reducing Hallucinations with Retrieval-Augmented Generation: A Practical Introduction](https://tiruchirappalli.aitinkerers.org/talks/rsvp_TiqxPKsC4Q0)

This talk introduces how open-source Hugging Face models can be combined with Retrieval-Augmented Generation (RAG) to produce more reliable and grounded AI responses. Through a simple live demo, I’ll show how retrieval improves factual accuracy and reduces hallucinations, then briefly discuss real-world limitations of RAG and how newer ideas like Cache-Augmented Generation (CAG) aim to address them. The session is designed to be practical, accessible, and directly applicable.

- Event context: AI Tinkerers Trichy: January Meetup & Live Demos — 2026-01-31 — Tiruchirappalli
- Public talk page: https://tiruchirappalli.aitinkerers.org/talks/rsvp_TiqxPKsC4Q0

### [Beyond Text: Hacking Transformers to Detect Anomalies in Million-Scale Netflow Data](https://toronto.aitinkerers.org/talks/rsvp_UxSNvJhCwH4)

Everyone uses Transformers for chat, but I wanted to see if they could catch hackers. In this demo, I’ll show how I forced NLP models (like ELECTRA) to 'read' & classify network traffic by treating diverse IoT datasets as text, graph-embedding, and even quantum-encoding. I’ll skip the slides and scroll through my Colab notebooks to show the messy reality of this experiment. You’ll see the custom data transformation scripts I wrote to tokenize IP addresses and build traffic graphs, the model definitions where I adapted the Transformer architectures, and the final code module that fuses these four wild modalities together to outperform standard detection methods.

- Event context: AI Tinkerers Toronto - January 2026 Meetup at Google! — 2026-01-29 — Toronto
- Public talk page: https://toronto.aitinkerers.org/talks/rsvp_UxSNvJhCwH4

### [From Blood Work to Biological Age in 500ms: Building a Mortality Risk Predictor](https://seattle.aitinkerers.org/talks/rsvp_Uu5hPbAkfyc)

I'll show you how I turned a 2018 mortality prediction algorithm into a production API that calculates "biological age" from 9 blood biomarkers—and the surprising engineering problems that emerged. The demo walks through: (1) why unit conversions almost destroyed us (one wrong conversion = 10 years off), (2) how we detect when the linear model breaks down and produces negative ages, (3) our counterfactual engine that ranks which biomarkers matter most for each individual, and (4) why population benchmarking was harder than the core algorithm. You'll see live requests, edge cases that produce impossible results, and the mathematical tricks we used to make confidence intervals fast.

- Event context: The Holiday Science Fair (Hot Cocoa, Cookies, and Demos!) — 2025-12-19 — Seattle
- Public talk page: https://seattle.aitinkerers.org/talks/rsvp_Uu5hPbAkfyc

### [x402-Enabled AI Gateway](https://atlanta.aitinkerers.org/talks/rsvp_-fDgoBtKAzQ)

I built a LLM Gateway (think OpenRouter) that uses the new x402 protocol to allow users to pay-per-request for LLM inference calls in real-time, using dollar stablecoins. This eliminates the need for advanced LLM users to avoid LLM Vendor specific subscriptions, API key management, billing, and vendor specific credits. Use any model you want, pay for what you use when you use it. Credits never expire.

- Event context: Co-Co-Code & Cocoa: The AI Tinkerers Atlanta Holiday Meetup — 2025-12-16 — Atlanta
- Public talk page: https://atlanta.aitinkerers.org/talks/rsvp_-fDgoBtKAzQ

### [Small Language Model based Supervised Fine-tuning: Instruction fine-tuning on 16GB RAM CPU-Only Systems](https://waterloo.aitinkerers.org/talks/rsvp_mypJEcF1SVs)

I will present a practical workflow for performing supervised fine-tuning of a small language model (such as SmolLM2-360M-Instruct) on an ordinary laptop (CPU-only, 16GB RAM). The talk covers instruction dataset formatting, supervised fine-tuning, and inference. A brief before-and-after comparison will show the effect of the fine-tuning. In particular: (1) instruction dataset formatting - The dataset will be a jsonl (One JSON object per line) file, and each line contains the mapping between requirement and python function (that is, the function name and its arguments). Each line is in the following format: =========== {"instruction": , "input": , "output": "<|begin|>\n### Requirement:\n\n### Parsed:\n\n### Python Code:\n\n<|end|>"} =========== (2) supervised fine-tuning - the training pipeline contains the following steps: =========== 1. Handle commandline arguments -- argparse.ArgumentParser() 2. Load tokenizer -- tokenizer = AutoTokenizer.from_pretrained(...) 3. Load model -- model = AutoModelForCausalLM.from_pretrained(..., device_map="cpu", low_cpu_mem_usage=True) 4. Prepare model for PEFT/LoRA using get_peft_model(model, peft.LoraConfig(...)) 5. Load dataset (JSONL with 'instruction' and 'response' keys) -- dataset = load_dataset(...) 6. Tokenize dataset and create labels with prompt masking -- tokenized = dataset.map(...) and customized functions 7. Convert to torch tensors (because the trainer expects tensors) -- transformers.DataCollatorForLanguageModeling(...) 8. Setup TrainingArguments using training_args = TrainingArguments(...) 9. Run training ( ~20 minutes "per epoch" for a small instruction dataset with 100 samples on a CPU-only average laptop) -- transformers.Trainer.train()(...) 10. Save the LoRA-based fine-tuned model (weights and configuration) -- model.save_pretrained(...) 11. Save the tokenizer and tokenization configuration (things needed to turn text into model input) -- tokenizer.save_pretrained(...) =========== (3) inference and evaluation - the inference pipeline contains the following steps: =========== 1. Load tokenizer -- AutoTokenizer.from_pretrained(...) 2. Load base model -- AutoModelForCausalLM.from_pretrained(..., torch_dtype=torch.float16, device_map="auto") 3. Attach LoRA adapter -- model = PeftModel.from_pretrained(base_model, args.output_dir) 4. Generate the formatted prompt -- prompt = "<|begin|>\n" + + "\n" 5. Tokenize the input -- inputs = tokenizer(prompt, return_tensors="pt").to(model.device) 6. Perform inference -- outputs = model.generate(...) 7. Generate the text response -- response = tokenizer.decode(outputs[0], skip_special_tokens=True) ===========

- Event context: AI Tinkerers Waterloo – December Meetup — 2025-12-15 — Waterloo
- Public talk page: https://waterloo.aitinkerers.org/talks/rsvp_mypJEcF1SVs

### [AI-First Clinical Trials: Building an Intelligent EDC System with Event Sourcing & Machine Learning](https://chicago.aitinkerers.org/talks/rsvp_N4ANMSrlGx4)

Clinical trials are the backbone of modern medicine, yet they're plagued by antiquated software built in the early 2000s. Data quality issues cost the pharmaceutical industry billions annually, with error rates of 5-8% being the norm. What if AI could reduce that to 1.3%? In this talk, I'll share how we built ClinPrecision, a next-generation Electronic Data Capture (EDC) system that leverages AI and modern architecture to transform clinical research. We've created an intelligent platform that: 1) Predicts and prevents data errors using real-time ML-powered validation (95% reduction in data queries) 2) Auto-codes medical terminology with 95% accuracy using NLP (60% faster than manual coding) 3) Scores site risk using AI to detect patterns across 100+ clinical sites (45% reduction in monitoring costs) 4) Flags critical lab values automatically to save lives in real-time safety monitoring Technical Deep Dive: You'll learn how we combined: 1) Event Sourcing (Axon Framework) for complete audit trails - critical for FDA compliance (21 CFR Part 11) 2) Domain-Driven Design to model complex clinical trial workflows 3) React + TypeScript + Tailwind for a modern UX that achieves 4.7/5 user satisfaction 4) Spring Boot + MySQL for a scalable, multi-tenant architecture 5) Machine Learning for intelligent auto-coding, risk scoring, and outlier detection Real-World Impact: This isn't theoretical - we're solving real problems: 1) 50% faster study startup (4-6 weeks vs 12-16 weeks industry standard) 2) 60% faster SAE reporting (12 hours vs 30+ hours for safety events) 3) 40-60% lower cost than legacy systems (Medidata Rave, Oracle InForm) 4) Successfully handling Phase I-IV trials for pharma, biotech, and academic institutions What You'll Take Away: 1) How to apply event sourcing in healthcare/regulated industries 2) AI/ML patterns for real-time data validation and quality monitoring 3) Strategies for disrupting legacy enterprise software with modern tech 4) Domain-Driven Design in practice for complex business domains 5) Building compliant systems (HIPAA, FDA, GDPR) with modern architecture

- Event context: AI Tinkerers Chicago December Meetup ft Turing — 2025-12-09 — Chicago
- Public talk page: https://chicago.aitinkerers.org/talks/rsvp_N4ANMSrlGx4

### [fastworkflow is now SOTA on Tau Bench!](https://houston.aitinkerers.org/talks/rsvp_k2AwqMGR9Wo)

During the last talk a few months ago, we demo'd fastworkflow results on Tau Bench retail and airline benchmarks comparable to GPT4o. With our latest refinements, fastworkflow beats ALL models including Sonnet 4.5! And it does this using models as small as 7B and 14B parameters. I will demonstrate the results and talk about the refinements that made this possible as well as our roadmap for the next 6 months

- Event context: AI Tinkerers Houston Meetup: Code, Demos, and Agentic Architectures (December 9, 2025) — 2025-12-09 — Houston
- Public talk page: https://houston.aitinkerers.org/talks/rsvp_k2AwqMGR9Wo

### [Science of Intelligence](https://portland.aitinkerers.org/talks/rsvp_S82coC9sblQ)

Mounir Shita — Physicist Worked on the Science of Intelligence and AGI research; brings a rare physics-driven perspective on emergent intelligence and system design.

- Event context: Portland: Agentic Systems Deep Dive — Building the Next Generation of AGI — 2025-12-04 — Portland
- Public talk page: https://portland.aitinkerers.org/talks/rsvp_S82coC9sblQ

### [NotebookLM: Aprendizaje autodidacta y rigor académico anclado en fuentes.](https://asuncion.aitinkerers.org/talks/rsvp_e7dpcCtM5UM)

Utilizar NotebookLM como un RAG personal "sobre la marcha", con fuentes y recursos asignados por el usuario. Haciendo uso y sacando ventaja de la configuración del modelo de solo basarse en la fuentes (sources) seleccionadas (Grounding). Esto lleva a un proceso simplificado de 4 pasos para adquirir rigor académico en nuestras investigaciones: 1)Fuentes robustas y diversas (papers, libros,tesis). 2)Preguntas de alto rigor (comparación, detección de brechas, scripts metodológicos). 3)Sintesis Activa (generar conocimiento). 4)Verificación (citas y fuentes)

- Event context: AI Tinkerers Asunción — Meetup 27 de noviembre de 2025 — 2025-11-27 — Asunción
- Public talk page: https://asuncion.aitinkerers.org/talks/rsvp_e7dpcCtM5UM

### [AI Management Systems: A perspective from a Robotics Safety Management System writer](https://hong-kong.aitinkerers.org/talks/rsvp_xxe4iqs-PY8)

AI Management Systems are being proposed under several Standards and Regulations across the world. While AI Management Systems are new to corporate environments, similar systems have been put in place, with the most impactful in the Aviation industry, which have transferred into the Autonomous Vehicles and now AI industry. I'll present a short review of the major markets' Standards and Regulations and apply some of my personal experience with them in the Autonomous vehicles space.

- Event context: AI Tinkerers Hong Kong Meetup - November 27th — 2025-11-27 — Hong Kong
- Public talk page: https://hong-kong.aitinkerers.org/talks/rsvp_xxe4iqs-PY8

### [Paradigm – Understand the Code You Don’t Understand](https://poland.aitinkerers.org/talks/rsvp_SNJntEBBUxU)

I’m building a developer tool called Paradigm - it helps you understand legacy code. Legacy code is any code you don’t know. It might be a 20-year-old system running a bank, something written by a colleague who’s since left the company, or a 2,000-line block of code recently generated by Claude, Cursor, or any other LLM.

- Event context: AI Tinkerers Poland #6 - Meetup in Warsaw (26th November) — 2025-11-26 — Poland
- Public talk page: https://poland.aitinkerers.org/talks/rsvp_SNJntEBBUxU

### [Constrained decoding: Can language models generate cute pixel art?](https://montreal.aitinkerers.org/talks/rsvp_ewFxWIEUn3k)

Recently, I’ve been experimenting with low-level token generation using models like gpt-oss-20b and gemma-3-27b-it. I became particularly interested in constrained decoding, where you apply a mask to the model’s probability distribution at each generation step. That led me to a fun question: what if you constrain the probabilities to a predefined set of “color tokens” and force the model to output them in a grid, essentially generating pixel art? Predictably, the results were… chaotic. But the failures were fascinating, and I’m convinced the limitations were mostly due to my rushed implementation and time constraints.

- Event context: AI Tinkerers Montreal: Demo Night — November 20, 2025 — 2025-11-20 — Montreal
- Public talk page: https://montreal.aitinkerers.org/talks/rsvp_ewFxWIEUn3k

### [Simulated Probability of Advertising Tactics and CAC Calculator](https://boston.aitinkerers.org/talks/rsvp_OKiNPJAgziU)

I'll be presenting an Advertising Campaign Simulator to show the probability of what media tactics will resonate with the target audience. I was watching a Quantum Physics class on Amazon Prime and wondered that if the Schrödinger equation can predict the location of an electron, can I use that same idea to predict the location of consumers in the marketing funnel before any of the Ads are created?

- Event context: AI Tinkerers Boston Meetup November 2025 — 2025-11-17 — Boston
- Public talk page: https://boston.aitinkerers.org/talks/rsvp_OKiNPJAgziU

### [Teaching small language models a thing or two](https://amsterdam.aitinkerers.org/talks/rsvp_5y9_LDXh3rQ)

I will be presenting our efforts in finetuning a range of small language models (SLMs) for both fun and useful use-cases. I shall go through the pipeline of how to finetune SLMs with limited data and why this might be the future.

- Event context: AI Tinkerers Amsterdam – November 2025 Edition — 2025-11-11 — Amsterdam
- Public talk page: https://amsterdam.aitinkerers.org/talks/rsvp_5y9_LDXh3rQ

### [Beyond “It Feels Better”: A Reproducible Playbook for Evaluating Fine-Tuned LLMs](https://toronto.aitinkerers.org/talks/rsvp_p1o4pIMrfcE)

We are contributing to an open-source project by IBM x Red Hat called Instruct Lab. What we learned is that fine-tuning is easy to run and hard to trust. We’ll share a reproducible, taxonomy-driven workflow for generating synthetic CS datasets (Assembly/RISC-V, DSA, Theory of Computation), fine-tuning models, and benchmarking multiple models on the same synthetic data. We’ll demo our standalone evaluation framework (perplexity, token-level PRF/F1, exact match, SBERT semantic similarity, plus length diagnostics) and show results across base vs. tuned models and cross-model comparisons using a constant dataset. You’ll see where tuning helps (and where it just makes outputs longer), how teacher model choice (InstructLab simple/full vs. GPT/Claude) affects downstream students, and what goes wrong (overfitting, NaN loss, EM brittleness) with concrete fixes. Attendees will leave with a better understanding of the following: how to scale synthetic data, add new knowledge taxonomies, run longer LoRA schedules responsibly, and report paired, apples-to-apples comparisons. Repo: https://github.com/CSC392-CSC492-Building-AI-ML-systems/Autumn2025InstructLab

- Event context: AI Tinkerers Toronto - November 2025 Meetup at Shopify! — 2025-11-10 — Toronto
- Public talk page: https://toronto.aitinkerers.org/talks/rsvp_p1o4pIMrfcE

### [Tracking AI code](https://nyc.aitinkerers.org/talks/rsvp_Uz2y6j2wTZY)

A demo of a git extension I built to track the AI generated code in my projects https://github.com/acunniffe/git-ai

- Event context: Auth0 x AI Tinkerers: Fall Social Demo Night 🍁 ft. Hex — 2025-11-06 — New York City
- Public talk page: https://nyc.aitinkerers.org/talks/rsvp_Uz2y6j2wTZY

### [WikiMem](https://minneapolis-saint-paul.aitinkerers.org/talks/rsvp_PccVHbTOXJ0)

Memory for LLMs; viewable as a wiki

- Event context: AI Tinkerers Minneapolis Meetup — November 5, 2025 — 2025-11-05 — Minneapolis Saint Paul
- Public talk page: https://minneapolis-saint-paul.aitinkerers.org/talks/rsvp_PccVHbTOXJ0

### [AI in HealthTech Industry](https://dhaka.aitinkerers.org/talks/rsvp_9whctgSHCI0)

In this talk, I will demonstrate the potential of an AI-powered virtual health assistant designed for hospitals, leveraging the latest advancements in Large Language Models (LLMs), NLP, and AI-driven integrations. The assistant interacts with patients, offering 24/7 support by answering queries, scheduling appointments, and providing real-time health updates. A key challenge in this project was integrating the assistant with electronic health records (EHR) while ensuring compliance with HIPAA and data privacy standards. I will walk through how GPT-OSS models were fine-tuned locally to provide fast, secure, and accurate responses to patient queries. This talk will cover: - Technical challenges such as integrating with hospital systems, handling sensitive patient data, and ensuring the assistant's accuracy. - How multimodal AI (voice, text, and potentially vision) can improve the patient experience. - A live demo of the virtual assistant, including a walkthrough of the code behind the system.

- Event context: AI Tinkerers Dhaka Inaugural Meetup - Dhaka Builds with AI — 2025-11-01 — Dhaka
- Public talk page: https://dhaka.aitinkerers.org/talks/rsvp_9whctgSHCI0

### [Improving AI UX through *product* focused evals](https://sf.aitinkerers.org/talks/rsvp_WciVeIEVMgA)

When you are building an agent or AI workflow, how the experience feels is a combination of LLM, tool calling, integrations, sandboxes, and more. It's as much about what the model is doing as what is happening before and after it responds. I'll be diving into what I built to track this end to end. And what I have learned along the way. From latency to learnings ;)

- Event context: Evals are Over - Evals are Back - AI in Prod @ Okta — 2025-10-31 — San Francisco
- Public talk page: https://sf.aitinkerers.org/talks/rsvp_WciVeIEVMgA

## Related Technologies

- [LangChain](https://aitinkerers.org/technologies/langchain) ([Markdown](https://aitinkerers.org/technologies/langchain.md)) — 445 public demos
- [OpenAI API](https://aitinkerers.org/technologies/openai-api) ([Markdown](https://aitinkerers.org/technologies/openai-api.md)) — 520 public demos
- [GPT-4](https://aitinkerers.org/technologies/gpt-4) ([Markdown](https://aitinkerers.org/technologies/gpt-4.md)) — 529 public demos
- [PyTorch](https://aitinkerers.org/technologies/pytorch) ([Markdown](https://aitinkerers.org/technologies/pytorch.md)) — 273 public demos
- [Python](https://aitinkerers.org/technologies/python) ([Markdown](https://aitinkerers.org/technologies/python.md)) — 662 public demos
- [Llama-2](https://aitinkerers.org/technologies/llama-2) ([Markdown](https://aitinkerers.org/technologies/llama-2.md)) — 227 public demos
- [Claude-3](https://aitinkerers.org/technologies/claude-3) ([Markdown](https://aitinkerers.org/technologies/claude-3.md)) — 110 public demos
- [FastAPI](https://aitinkerers.org/technologies/fastapi) ([Markdown](https://aitinkerers.org/technologies/fastapi.md)) — 181 public demos
- [Docker](https://aitinkerers.org/technologies/docker) ([Markdown](https://aitinkerers.org/technologies/docker.md)) — 147 public demos
- [LLM](https://aitinkerers.org/technologies/llm) ([Markdown](https://aitinkerers.org/technologies/llm.md)) — 123 public demos
- [Anthropic API](https://aitinkerers.org/technologies/anthropic-api) ([Markdown](https://aitinkerers.org/technologies/anthropic-api.md)) — 66 public demos
- [Claude](https://aitinkerers.org/technologies/claude) ([Markdown](https://aitinkerers.org/technologies/claude.md)) — 174 public demos
- [Gemini](https://aitinkerers.org/technologies/gemini) ([Markdown](https://aitinkerers.org/technologies/gemini.md)) — 188 public demos
- [Hugging Face](https://aitinkerers.org/technologies/hugging-face) ([Markdown](https://aitinkerers.org/technologies/hugging-face.md)) — 41 public demos
- [React](https://aitinkerers.org/technologies/react) ([Markdown](https://aitinkerers.org/technologies/react.md)) — 220 public demos
- [sentence-transformers](https://aitinkerers.org/technologies/sentence-transformers) ([Markdown](https://aitinkerers.org/technologies/sentence-transformers.md)) — 11 public demos
- [vLLM](https://aitinkerers.org/technologies/vllm) ([Markdown](https://aitinkerers.org/technologies/vllm.md)) — 33 public demos
- [BERT](https://aitinkerers.org/technologies/bert) ([Markdown](https://aitinkerers.org/technologies/bert.md)) — 179 public demos

## More Results

- Next: https://aitinkerers.org/technologies/transformers.md?page=2