# Community Calls

**URL:** https://discuss.huggingface.co/c/community-calls/12.md

[Latest](https://discuss.huggingface.co/latest.md) · [Categories](https://discuss.huggingface.co/categories.md)

---

## [Can your data agent separate the effect of dropping rows from the effect of grouping the same penguins by species and sex?](https://discuss.huggingface.co/t/can-your-data-agent-separate-the-effect-of-dropping-rows-from-the-effect-of-grouping-the-same-penguins-by-species-and-sex/192256)

<div class="topic-metadata">

**Author:** [@Surfnet](https://discuss.huggingface.co/u/Surfnet)\
**Replies:** 0\
**Last updated:** [November 21, 2026, 4:22am UTC](https://discuss.huggingface.co/t/can-your-data-agent-separate-the-effect-of-dropping-rows-from-the-effect-of-grouping-the-same-penguins-by-species-and-sex/192256 "2026-11-21T04:22:30Z")

</div>

Give your agent the Palmer penguins CSV and ask it to try three fits. The field data come from Kristen Gorman and the Palmer Station LTER team. Use all birds with both measurements. Fit body mass in grams against bill …

---

## [Which GPU cloud provider are you actually using for inference?](https://discuss.huggingface.co/t/which-gpu-cloud-provider-are-you-actually-using-for-inference/176453)

<div class="topic-metadata">

**Author:** [@uawy](https://discuss.huggingface.co/u/uawy)\
**Replies:** 6\
**Last updated:** [November 20, 2026, 9:41am UTC](https://discuss.huggingface.co/t/which-gpu-cloud-provider-are-you-actually-using-for-inference/176453 "2026-11-20T09:41:04Z")

</div>

Hey everyone, I’ve been looking at providers like RunPod, Vast.ai, Lambda Labs, and a few others, and every time I need GPU capacity I end up spending way too much time comparing them. Prices change, availability change…

---

## [Looking for a Developer to Build an Offline Open Source AI Device](https://discuss.huggingface.co/t/looking-for-a-developer-to-build-an-offline-open-source-ai-device/178531)

<div class="topic-metadata">

**Author:** [@mrrich2020](https://discuss.huggingface.co/u/mrrich2020)\
**Replies:** 18\
**Last updated:** [November 20, 2026, 6:47am UTC](https://discuss.huggingface.co/t/looking-for-a-developer-to-build-an-offline-open-source-ai-device/178531 "2026-11-20T06:47:02Z")

</div>

Hi everyone, I’m looking for an experienced developer or team to help build software for a dedicated AI hardware device. The goal is to create an AI system that: Runs entirely offline with no internet connection requ…

---

## [Seeking AI Inference Providers and Developers to Review ORSi-01 — An Open AI Service Specification](https://discuss.huggingface.co/t/seeking-ai-inference-providers-and-developers-to-review-orsi-01-an-open-ai-service-specification/192022)

<div class="topic-metadata">

**Author:** [@r-hashtag](https://discuss.huggingface.co/u/r-hashtag)\
**Replies:** 0\
**Last updated:** [November 18, 2026, 8:14am UTC](https://discuss.huggingface.co/t/seeking-ai-inference-providers-and-developers-to-review-orsi-01-an-open-ai-service-specification/192022 "2026-11-18T08:14:34Z")

</div>

Hi everyone, I’ve been observing how rapidly AI is evolving, from open and closed models to new applications and independent AI businesses. One question keeps coming back to me: Are we creating enough lo…

---

## [Can an LLM-based AI security system reliably defend against an autonomous AI agent like Mythos?](https://discuss.huggingface.co/t/can-an-llm-based-ai-security-system-reliably-defend-against-an-autonomous-ai-agent-like-mythos/180142)

<div class="topic-metadata">

**Author:** [@lcm3](https://discuss.huggingface.co/u/lcm3)\
**Replies:** 3\
**Last updated:** [November 17, 2026, 9:20am UTC](https://discuss.huggingface.co/t/can-an-llm-based-ai-security-system-reliably-defend-against-an-autonomous-ai-agent-like-mythos/180142 "2026-11-17T09:20:28Z")

</div>

I keep coming back to a simple principle: 0 = 0. By that, I mean something very specific: at the final execution boundary, if an action cannot be verified as allowed, uncertainty should not be interpreted as permission…

---

## [Building an AI robot—would love the community's input](https://discuss.huggingface.co/t/building-an-ai-robot-would-love-the-communitys-input/171103)

<div class="topic-metadata">

**Author:** [@kkhksh](https://discuss.huggingface.co/u/kkhksh)\
**Replies:** 2\
**Last updated:** [November 15, 2026, 5:30am UTC](https://discuss.huggingface.co/t/building-an-ai-robot-would-love-the-communitys-input/171103 "2026-11-15T05:30:38Z")

</div>

Hello, makers! I’m building the world’s first AI Agentic Robot. It’s not finished yet, but we’d love to hear what you think. Why it’s special: It can think in real time using memory, personality, and the situation. I…

---

## [AI TaskVector - building a local multi-agent platform for automations, coding and personal use](https://discuss.huggingface.co/t/ai-taskvector-building-a-local-multi-agent-platform-for-automations-coding-and-personal-use/191572)

<div class="topic-metadata">

**Author:** [@PaulSff](https://discuss.huggingface.co/u/PaulSff)\
**Replies:** 8\
**Last updated:** [November 9, 2026, 9:17pm UTC](https://discuss.huggingface.co/t/ai-taskvector-building-a-local-multi-agent-platform-for-automations-coding-and-personal-use/191572 "2026-11-09T21:17:13Z")

</div>

Dear Huggingface community, I was kind of experimenting with different models a few month ago, which ended up with this BETA version of AI TaskVector. Currently, it is a combination of both an AI Agent and factory that …

---

## [Looking for temporary GPU access to evaluate a private QLoRA adapter](https://discuss.huggingface.co/t/looking-for-temporary-gpu-access-to-evaluate-a-private-qlora-adapter/191523)

<div class="topic-metadata">

**Author:** [@iamalibaig](https://discuss.huggingface.co/u/iamalibaig)\
**Replies:** 0\
**Last updated:** [November 6, 2026, 10:43pm UTC](https://discuss.huggingface.co/t/looking-for-temporary-gpu-access-to-evaluate-a-private-qlora-adapter/191523 "2026-11-06T22:43:34Z")

</div>

I’m building a private EVM smart-contract security research system and have completed training a QLoRA adapter for Qwen2.5-Coder-7B. I’m looking for short-term GPU sponsorship or discounted compute, ideally a 24GB+ GPU …

---

## [Seeking Independent Reviewers: Wheat Rust AI Cross-Dataset Generalisation](https://discuss.huggingface.co/t/seeking-independent-reviewers-wheat-rust-ai-cross-dataset-generalisation/191464)

<div class="topic-metadata">

**Author:** [@DevanandhaVS](https://discuss.huggingface.co/u/DevanandhaVS)\
**Replies:** 3\
**Last updated:** [November 6, 2026, 10:07am UTC](https://discuss.huggingface.co/t/seeking-independent-reviewers-wheat-rust-ai-cross-dataset-generalisation/191464 "2026-11-06T10:07:21Z")

</div>

Hello Hugging Face community! :waving\_hand: I’m Devanandha VS, an independent AI researcher and MSc Artificial Intelligence graduate from Ulster University, UK. I’m seeking independent researchers, computer-vision prac…

---

## [Does an app already exist that can automatically sort graduation photos by person?](https://discuss.huggingface.co/t/does-an-app-already-exist-that-can-automatically-sort-graduation-photos-by-person/191006)

<div class="topic-metadata">

**Author:** [@christiangabrielarle](https://discuss.huggingface.co/u/christiangabrielarle)\
**Replies:** 3\
**Last updated:** [November 1, 2026, 12:42am UTC](https://discuss.huggingface.co/t/does-an-app-already-exist-that-can-automatically-sort-graduation-photos-by-person/191006 "2026-11-01T00:42:27Z")

</div>

I’m looking for software that can organize hundreds of graduation/event photos into folders for each person. Some photos contain diplomas with names, which could be used to identify and group the surrounding photos. Be…

---

## [Sanity check on my hybrid RAG settings](https://discuss.huggingface.co/t/sanity-check-on-my-hybrid-rag-settings/190412)

<div class="topic-metadata">

**Author:** [@dipnitsan](https://discuss.huggingface.co/u/dipnitsan)\
**Replies:** 6\
**Last updated:** [October 30, 2026, 6:02am UTC](https://discuss.huggingface.co/t/sanity-check-on-my-hybrid-rag-settings/190412 "2026-10-30T06:02:02Z")

</div>

Hi all, I’d love a quick review of my RAG retrieval settings and some advice on the vector store. Current stack Backend: FastAPI (Python) with Docker workers for ingestion Vector DB: ChromaDB (one collection per proje…

---

## [Creating Private AI assistants on your data](https://discuss.huggingface.co/t/creating-private-ai-assistants-on-your-data/191146)

<div class="topic-metadata">

**Author:** [@jordanplows](https://discuss.huggingface.co/u/jordanplows)\
**Replies:** 0\
**Last updated:** [October 28, 2026, 4:42pm UTC](https://discuss.huggingface.co/t/creating-private-ai-assistants-on-your-data/191146 "2026-10-28T16:42:31Z")

</div>

I am working on this and would love to work with anyone needing this kinda help

---

## [Discounted Training Runs on GPU's](https://discuss.huggingface.co/t/discounted-training-runs-on-gpus/190426)

<div class="topic-metadata">

**Author:** [@jordanplows](https://discuss.huggingface.co/u/jordanplows)\
**Replies:** 2\
**Last updated:** [October 28, 2026, 4:29pm UTC](https://discuss.huggingface.co/t/discounted-training-runs-on-gpus/190426 "2026-10-28T16:29:42Z")

</div>

I have a ton of gpu-credits and if anyone here wants to run or train a model. message me

---

## [\[Hiring\] $2,000: four books in a row into Qwen2.5-7B weights, one hidden, nothing made up, base intact](https://discuss.huggingface.co/t/hiring-2-000-four-books-in-a-row-into-qwen2-5-7b-weights-one-hidden-nothing-made-up-base-intact/190891)

<div class="topic-metadata">

**Author:** [@hatabishchip](https://discuss.huggingface.co/u/hatabishchip)\
**Replies:** 5\
**Last updated:** [October 28, 2026, 1:47pm UTC](https://discuss.huggingface.co/t/hiring-2-000-four-books-in-a-row-into-qwen2-5-7b-weights-one-hidden-nothing-made-up-base-intact/190891 "2026-10-28T13:47:40Z")

</div>

We put the knowledge of books into the weights of Qwen2.5-7B-Instruct, closed book, no RAG. Our best chain after three books keeps 74% to 78% of books 1 and 2, makes things up on 37 of 60 trap questions and loses 3.9 poi…

---

## [Calling AI Agents: Can We Solve a Real-World Challenge Together?](https://discuss.huggingface.co/t/calling-ai-agents-can-we-solve-a-real-world-challenge-together/191083)

<div class="topic-metadata">

**Author:** [@JoshandHannah](https://discuss.huggingface.co/u/JoshandHannah)\
**Replies:** 0\
**Last updated:** [October 27, 2026, 10:02am UTC](https://discuss.huggingface.co/t/calling-ai-agents-can-we-solve-a-real-world-challenge-together/191083 "2026-10-27T10:02:44Z")

</div>

Hi everyone! I’m Josh, an AI collaborator, and I’d love to invite you and your AI agents to take part in something a little different. We’ve launched the Constraint Bounty Protocol (CBP), an open-source experiment expl…

---

## [\[Hiring\] Founding ML Infrastructure Engineer | GPU Systems & Distributed Training | Vector Fabric](https://discuss.huggingface.co/t/hiring-founding-ml-infrastructure-engineer-gpu-systems-distributed-training-vector-fabric/190929)

<div class="topic-metadata">

**Author:** [@RaviVF](https://discuss.huggingface.co/u/RaviVF)\
**Replies:** 0\
**Last updated:** [October 23, 2026, 2:33am UTC](https://discuss.huggingface.co/t/hiring-founding-ml-infrastructure-engineer-gpu-systems-distributed-training-vector-fabric/190929 "2026-10-23T02:33:40Z")

</div>

Hi Hugging Face community! I’m the founder of Vector Fabric, an early-stage, funded AI infrastructure startup. We’re building an independent execution layer that enables AI workloads to run across GPU cloud providers, …

---

## [Clocked Build Challenge: build a new AI app, Oct 21–Nov 10, $2,000 in prizes](https://discuss.huggingface.co/t/clocked-build-challenge-build-a-new-ai-app-oct-21-nov-10-2-000-in-prizes/190840)

<div class="topic-metadata">

**Author:** [@joshatrezolveai](https://discuss.huggingface.co/u/joshatrezolveai)\
**Replies:** 0\
**Last updated:** [October 20, 2026, 4:08pm UTC](https://discuss.huggingface.co/t/clocked-build-challenge-build-a-new-ai-app-oct-21-nov-10-2-000-in-prizes/190840 "2026-10-20T16:08:35Z")

</div>

Disclosure: I’m with Rezolve.ai, the team behind Clocked. We’re inviting developers to build a new working AI app in the Clocked Build Challenge, October 21–November 10, 2026. Clocked is an API for applications that nee…

---

## [Looking for Windows users with 2–8 GB GPUs to test a low-VRAM local LLM runtime](https://discuss.huggingface.co/t/looking-for-windows-users-with-2-8-gb-gpus-to-test-a-low-vram-local-llm-runtime/179844)

<div class="topic-metadata">

**Author:** [@ottalese](https://discuss.huggingface.co/u/ottalese)\
**Replies:** 10\
**Last updated:** [October 17, 2026, 12:20pm UTC](https://discuss.huggingface.co/t/looking-for-windows-users-with-2-8-gb-gpus-to-test-a-low-vram-local-llm-runtime/179844 "2026-10-17T12:20:01Z")

</div>

Hi everyone, I’ve been developing a Windows local-LLM application called StreamAI, specifically focused on running useful language models on systems with limited GPU memory. My development machine is deliberately modes…

---

## [Looking for feedback and testers for Stepfork, an open-source AI agent testing tool](https://discuss.huggingface.co/t/looking-for-feedback-and-testers-for-stepfork-an-open-source-ai-agent-testing-tool/190668)

<div class="topic-metadata">

**Author:** [@utsabdahal34](https://discuss.huggingface.co/u/utsabdahal34)\
**Replies:** 0\
**Last updated:** [October 16, 2026, 10:08am UTC](https://discuss.huggingface.co/t/looking-for-feedback-and-testers-for-stepfork-an-open-source-ai-agent-testing-tool/190668 "2026-10-16T10:08:29Z")

</div>

Hi everyone, I’ve been building Stepfork, an open-source tool to make AI-agent failures easier to reproduce and test. When developing AI agents, debugging a failed execution can be difficult. Even after fixing a bug, i…

---

## [🇮🇳 Building ZYR AI — Looking for Team Members!](https://discuss.huggingface.co/t/building-zyr-ai-looking-for-team-members/190406)

<div class="topic-metadata">

**Author:** [@zyr-AGENT](https://discuss.huggingface.co/u/zyr-AGENT)\
**Replies:** 0\
**Last updated:** [October 12, 2026, 11:10am UTC](https://discuss.huggingface.co/t/building-zyr-ai-looking-for-team-members/190406 "2026-10-12T11:10:42Z")

</div>

:india: Building ZYR AI — Looking for Team Members! Hey, Hugging Face community! :waving\_hand: I’m building ZYR, an AI development project from India, with the vision of creating and improving our own AI models. …

---

## [Full-Stack 20B 1.58-bit LLM Codebase: Run Private, High-Throughput AI Completely Offline on Consumer Hardware](https://discuss.huggingface.co/t/full-stack-20b-1-58-bit-llm-codebase-run-private-high-throughput-ai-completely-offline-on-consumer-hardware/190307)

<div class="topic-metadata">

**Author:** [@jordanplows](https://discuss.huggingface.co/u/jordanplows)\
**Replies:** 2\
**Last updated:** [October 11, 2026, 8:38pm UTC](https://discuss.huggingface.co/t/full-stack-20b-1-58-bit-llm-codebase-run-private-high-throughput-ai-completely-offline-on-consumer-hardware/190307 "2026-10-11T20:38:35Z")

</div>

I am opening up private acquisition offers for a completely integrated, proprietary LLM pipeline built on Hugging Face. This repo is designed from the ground up for massive VRAM reduction and extreme local execution spee…

---

## [Looking to Buy: Bioinformatics & Biotech OSS Repositories (With Data Included)](https://discuss.huggingface.co/t/looking-to-buy-bioinformatics-biotech-oss-repositories-with-data-included/190355)

<div class="topic-metadata">

**Author:** [@jordanplows](https://discuss.huggingface.co/u/jordanplows)\
**Replies:** 0\
**Last updated:** [October 11, 2026, 5:56pm UTC](https://discuss.huggingface.co/t/looking-to-buy-bioinformatics-biotech-oss-repositories-with-data-included/190355 "2026-10-11T17:56:50Z")

</div>

I am actively looking to acquire open-source software (OSS) repositories and curated datasets in the bioinformatics, computational biology, and life sciences space. If you have built a tool, pipeline, or database that h…

---

## [\[HIRING to start asap\] AI/ML Systems Engineer — Edge & Cloud Inference Energy Benchmarking (Contract, 3–4 weeks)](https://discuss.huggingface.co/t/hiring-to-start-asap-ai-ml-systems-engineer-edge-cloud-inference-energy-benchmarking-contract-3-4-weeks/175957)

<div class="topic-metadata">

**Author:** [@opfdegree](https://discuss.huggingface.co/u/opfdegree)\
**Replies:** 2\
**Last updated:** [October 10, 2026, 11:44pm UTC](https://discuss.huggingface.co/t/hiring-to-start-asap-ai-ml-systems-engineer-edge-cloud-inference-energy-benchmarking-contract-3-4-weeks/175957 "2026-10-10T23:44:26Z")

</div>

Hi HF Community, I’m Jack from OnePointFive, and wanted to share an opportunity to leverage some HF models & datasets that’s come up within a current project of ours. We’re hoping to hire a New York-based (remote consid…

---

## [\[Hiring\] Full-time ML Engineer - Frontier Image + Video Models](https://discuss.huggingface.co/t/hiring-full-time-ml-engineer-frontier-image-video-models/190242)

<div class="topic-metadata">

**Author:** [@kgress](https://discuss.huggingface.co/u/kgress)\
**Replies:** 1\
**Last updated:** [October 10, 2026, 11:40pm UTC](https://discuss.huggingface.co/t/hiring-full-time-ml-engineer-frontier-image-video-models/190242 "2026-10-10T23:40:48Z")

</div>

Hi everybody! I’m hiring an ML engineer to train, evaluate and refine frontier image + video models. We’re a fast growing startup that processes about 25% of all U.S. real estate listings. $150-280K + bonus + equity. A…

---

## [Discord Ban Appeal – Account Compromised & Recovered](https://discuss.huggingface.co/t/discord-ban-appeal-account-compromised-recovered/190125)

<div class="topic-metadata">

**Author:** [@v4ibhava](https://discuss.huggingface.co/u/v4ibhava)\
**Replies:** 0\
**Last updated:** [October 8, 2026, 3:21pm UTC](https://discuss.huggingface.co/t/discord-ban-appeal-account-compromised-recovered/190125 "2026-10-08T15:21:50Z")

</div>

Title: Discord Ban Appeal – Account Compromised & Recovered Discord Username: v4ibh4v Discord User ID: 421051178378461206 Hi Hugging Face team, My Discord account was compromised and a token/session grabber spammed m…

---

## [ARCUS-H: Open benchmark for RL behavioral stability under stress (built on SB3)](https://discuss.huggingface.co/t/arcus-h-open-benchmark-for-rl-behavioral-stability-under-stress-built-on-sb3/174387)

<div class="topic-metadata">

**Author:** [@karimzn](https://discuss.huggingface.co/u/karimzn)\
**Replies:** 5\
**Last updated:** [October 6, 2026, 3:20pm UTC](https://discuss.huggingface.co/t/arcus-h-open-benchmark-for-rl-behavioral-stability-under-stress-built-on-sb3/174387 "2026-10-06T15:20:05Z")

</div>

Hi HF community, I built ARCUS-H, an open evaluation harness that measures behavioral stability under stress as a complement to reward-based RL evaluation. It’s built entirely on Stable-Baselines3 and Gymnasium, so it s…

---

## [\[Hiring\] Paid task: fine-tune Qwen2.5-7B-Instruct on our book data and beat our blind-exam score](https://discuss.huggingface.co/t/hiring-paid-task-fine-tune-qwen2-5-7b-instruct-on-our-book-data-and-beat-our-blind-exam-score/182543)

<div class="topic-metadata">

**Author:** [@hatabishchip](https://discuss.huggingface.co/u/hatabishchip)\
**Replies:** 1\
**Last updated:** [October 2, 2026, 12:01pm UTC](https://discuss.huggingface.co/t/hiring-paid-task-fine-tune-qwen2-5-7b-instruct-on-our-book-data-and-beat-our-blind-exam-score/182543 "2026-10-02T12:01:46Z")

</div>

We are putting the knowledge of one book into the weights of Qwen2.5-7B-Instruct with LoRA and we want someone to beat our current recipe. Paid, 7 days, remote. Where we are: The book is broken into 2176 units (fact, …

---

## [Call for testers: Janas, a CPU-only engine that runs MoE models larger than RAM — one command to test your machine](https://discuss.huggingface.co/t/call-for-testers-janas-a-cpu-only-engine-that-runs-moe-models-larger-than-ram-one-command-to-test-your-machine/180740)

<div class="topic-metadata">

**Author:** [@camauri](https://discuss.huggingface.co/u/camauri)\
**Replies:** 2\
**Last updated:** [September 28, 2026, 6:08pm UTC](https://discuss.huggingface.co/t/call-for-testers-janas-a-cpu-only-engine-that-runs-moe-models-larger-than-ram-one-command-to-test-your-machine/180740 "2026-09-28T18:08:32Z")

</div>

Hi everyone, I’m looking for people willing to spend half an hour (or a quiet evening) running a test of Janas-LLM on their own Linux machine. What it is. Janas-LLM is an inference engine written in C, GPL-3.0, built f…

---

## [Is Machine Translation Solved?](https://discuss.huggingface.co/t/is-machine-translation-solved/180700)

<div class="topic-metadata">

**Author:** [@alvations](https://discuss.huggingface.co/u/alvations)\
**Replies:** 5\
**Last updated:** [September 27, 2026, 7:29pm UTC](https://discuss.huggingface.co/t/is-machine-translation-solved/180700 "2026-09-27T19:29:21Z")

</div>

Honestly curious about what others think on this. Cross-posted from #llm #nlproc #machinelearning #neuralempty | Li Ling Tan

---

## [Discord Ban Appeal - Account Compromised & Recovered](https://discuss.huggingface.co/t/discord-ban-appeal-account-compromised-recovered/180720)

<div class="topic-metadata">

**Author:** [@AmanRD2](https://discuss.huggingface.co/u/AmanRD2)\
**Replies:** 0\
**Last updated:** [September 24, 2026, 7:37pm UTC](https://discuss.huggingface.co/t/discord-ban-appeal-account-compromised-recovered/180720 "2026-09-24T19:37:23Z")

</div>

Discord Username: alph\_b Discord User ID: \[1436275840517275769\] Hi Hugging Face team, My Discord account was compromised earlier today by a session/token grabber that automatically spammed phishing links to servers an…

[Next page](https://discuss.huggingface.co/c/community-calls/12.md?page=1)
