# Beginners **URL:** https://discuss.huggingface.co/c/beginners/5.md [Latest](https://discuss.huggingface.co/latest.md) · [Categories](https://discuss.huggingface.co/categories.md) --- ## [How To Request Support](https://discuss.huggingface.co/t/how-to-request-support/3128)
**Author:** [@sgugger](https://discuss.huggingface.co/u/sgugger)\ **Replies:** 2\ **Last updated:** [January 31, 2023, 10:29am UTC](https://discuss.huggingface.co/t/how-to-request-support/3128 "2023-01-31T10:29:08Z")
This post is a copy of the new ISSUES document we recently merged about how to efficiently request support for one of the Hugging Face libraries. It’s designed with GitHub issues in mind, but it’s a useful read for gener… --- ## [How to ask questions on the forum?](https://discuss.huggingface.co/t/how-to-ask-questions-on-the-forum/54)
**Author:** [@sgugger](https://discuss.huggingface.co/u/sgugger)\ **Replies:** 22\ **Last updated:** [July 14, 2026, 8:29am UTC](https://discuss.huggingface.co/t/how-to-ask-questions-on-the-forum/54 "2026-07-14T08:29:12Z")
Hi there and welcome on the HuggingFace forums! Here are a few guidelines before you make your first post, but the goal is to create a wide discussion space with the NLP community, so don’t hesitate to break them if you… --- ## [About the Hugging Face Forums](https://discuss.huggingface.co/t/about-the-hugging-face-forums/24)
**Author:** [@sgugger](https://discuss.huggingface.co/u/sgugger)\ **Replies:** 1\ **Last updated:** [May 6, 2024, 6:31pm UTC](https://discuss.huggingface.co/t/about-the-hugging-face-forums/24 "2024-05-06T18:31:17Z")
You can login using your huggingface.co credentials. This forum is powered by Discourse and relies on a trust-level system. As a new user, you’re temporarily limited in the number of topics and posts you can create. To … --- ## [Local AI - How do you choose your models](https://discuss.huggingface.co/t/local-ai-how-do-you-choose-your-models/190558)
**Author:** [@alaskaav8r](https://discuss.huggingface.co/u/alaskaav8r)\ **Replies:** 6\ **Last updated:** [October 15, 2026, 9:55am UTC](https://discuss.huggingface.co/t/local-ai-how-do-you-choose-your-models/190558 "2026-10-15T09:55:49Z")
Hardware: Macbook M5 Max, 18 core cpu, 40 core gpu, 128GB unified memory, 4TB hd, OS Tahoe Using Tailscale for remote access Stack: Ollama runs natively on macOS (Ollama.app, not in Docker) using the llama.cpp engine… --- ## [Google gemma gated repositories access impossible](https://discuss.huggingface.co/t/google-gemma-gated-repositories-access-impossible/190610)
**Author:** [@jmassot](https://discuss.huggingface.co/u/jmassot)\ **Replies:** 0\ **Last updated:** [October 15, 2026, 4:36am UTC](https://discuss.huggingface.co/t/google-gemma-gated-repositories-access-impossible/190610 "2026-10-15T04:36:04Z")
Despite I have access granted for Google Gemma gated repositories, now when I try to access a model card for example, a SSO window appears, and tells me that the service is not configured for this user. As a Googler, I h… --- ## [How do you reproduce LLM agent failures? I built an open-source Python tool for offline replay and pytest testing](https://discuss.huggingface.co/t/how-do-you-reproduce-llm-agent-failures-i-built-an-open-source-python-tool-for-offline-replay-and-pytest-testing/190525)
**Author:** [@utsabdahal34](https://discuss.huggingface.co/u/utsabdahal34)\ **Replies:** 6\ **Last updated:** [October 15, 2026, 1:08am UTC](https://discuss.huggingface.co/t/how-do-you-reproduce-llm-agent-failures-i-built-an-open-source-python-tool-for-offline-replay-and-pytest-testing/190525 "2026-10-15T01:08:55Z")
Hi everyone! I’ve been working on Stepfork, an open-source Python tool for recording AI agent executions, replaying failures offline, and generating pytest regression tests. One challenge I’ve encountered while buildin… --- ## [Wan2gp best setting for fasteste generation](https://discuss.huggingface.co/t/wan2gp-best-setting-for-fasteste-generation/190559)
**Author:** [@TRGeese](https://discuss.huggingface.co/u/TRGeese)\ **Replies:** 1\ **Last updated:** [October 14, 2026, 7:48pm UTC](https://discuss.huggingface.co/t/wan2gp-best-setting-for-fasteste-generation/190559 "2026-10-14T19:48:21Z")
Hello everyone, I’d like to know if anyone who has used the WAN2GP model for a PC with Windows 11 has been able to generate video from an image and the prompt in the shortest possible time. When I installed it, it took 5… --- ## [Running small LLMs locally — what hardware are you using in 2026?](https://discuss.huggingface.co/t/running-small-llms-locally-what-hardware-are-you-using-in-2026/190590)
**Author:** [@thomaspoli](https://discuss.huggingface.co/u/thomaspoli)\ **Replies:** 2\ **Last updated:** [October 15, 2026, 5:48am UTC](https://discuss.huggingface.co/t/running-small-llms-locally-what-hardware-are-you-using-in-2026/190590 "2026-10-15T05:48:37Z")
Hi everyone, I’m Thomas from the UK and I’ve been experimenting with running smaller language models locally instead of relying on cloud APIs. It’s a fun learning curve, but the hardware choices feel overwhelming. Right… --- ## [HuggingChat: Upgrade required when I send my first message?](https://discuss.huggingface.co/t/huggingchat-upgrade-required-when-i-send-my-first-message/190572)
**Author:** [@tregnoto](https://discuss.huggingface.co/u/tregnoto)\ **Replies:** 0\ **Last updated:** [October 14, 2026, 7:14am UTC](https://discuss.huggingface.co/t/huggingchat-upgrade-required-when-i-send-my-first-message/190572 "2026-10-14T07:14:50Z")
What gives? It won’t even answer “hello?” before I’m hit with an upgrade required dialogue box. --- ## [Picking STS3215 servos for SO-101: am I the only one confused?](https://discuss.huggingface.co/t/picking-sts3215-servos-for-so-101-am-i-the-only-one-confused/190529)
**Author:** [@sumeet9t9](https://discuss.huggingface.co/u/sumeet9t9)\ **Replies:** 1\ **Last updated:** [October 13, 2026, 11:50pm UTC](https://discuss.huggingface.co/t/picking-sts3215-servos-for-so-101-am-i-the-only-one-confused/190529 "2026-10-13T23:50:05Z")
Trying to sort out servos for an SO-101 and the STS3215 listings have me going in circles. Several variants look the same but aren’t, and sellers don’t always say which one you’re getting. Am I the only one who found th… --- ## [I created hugging face got hacked](https://discuss.huggingface.co/t/i-created-hugging-face-got-hacked/190556)
**Author:** [@Entmarch](https://discuss.huggingface.co/u/Entmarch)\ **Replies:** 0\ **Last updated:** [October 13, 2026, 7:55pm UTC](https://discuss.huggingface.co/t/i-created-hugging-face-got-hacked/190556 "2026-10-13T19:55:46Z")
I created hugging face and huntress I can prove it i got hacked and put in jail under false pretenses so that my identity could be stolen --- ## [The best Android client and the best LLM model for android?](https://discuss.huggingface.co/t/the-best-android-client-and-the-best-llm-model-for-android/167329)
**Author:** [@libreAL](https://discuss.huggingface.co/u/libreAL)\ **Replies:** 4\ **Last updated:** [October 13, 2026, 7:11pm UTC](https://discuss.huggingface.co/t/the-best-android-client-and-the-best-llm-model-for-android/167329 "2026-10-13T19:11:59Z")
Hello everyone. I would like to know the community’s opinion. Please tell me which Android client is the best for LLM in your opinion and why? Which model is the most accurate in its responses, fast, and not too big? I… --- ## [We gave AI a trust we never gave people - The third axis, after capability and permission?](https://discuss.huggingface.co/t/we-gave-ai-a-trust-we-never-gave-people-the-third-axis-after-capability-and-permission/190523)
**Author:** [@dert4er](https://discuss.huggingface.co/u/dert4er)\ **Replies:** 0\ **Last updated:** [October 13, 2026, 7:11pm UTC](https://discuss.huggingface.co/t/we-gave-ai-a-trust-we-never-gave-people-the-third-axis-after-capability-and-permission/190523 "2026-10-13T19:11:42Z")
When an agent causes an incident, we ask the model. Why did you send that address. Why did you say he was home. Why did you cancel that booking. The model answers, and the answer sounds right. Asked how it knew about a… --- ## [Free api for beginners](https://discuss.huggingface.co/t/free-api-for-beginners/179088)
**Author:** [@zayed-369](https://discuss.huggingface.co/u/zayed-369)\ **Replies:** 3\ **Last updated:** [October 13, 2026, 7:11pm UTC](https://discuss.huggingface.co/t/free-api-for-beginners/179088 "2026-10-13T19:11:41Z")
I’m searching for free AI API platform for chating, genarate code and create image. please help me, --- ## [How do i make and add my api key connected to something](https://discuss.huggingface.co/t/how-do-i-make-and-add-my-api-key-connected-to-something/180319)
**Author:** [@solaraaa](https://discuss.huggingface.co/u/solaraaa)\ **Replies:** 2\ **Last updated:** [October 13, 2026, 7:11pm UTC](https://discuss.huggingface.co/t/how-do-i-make-and-add-my-api-key-connected-to-something/180319 "2026-10-13T19:11:36Z")
hiii so basically i’m building a ai website and i don’t know how to connect my own key i have it but it’s not connected to anything and i heard it’s so expensive does anyone know what will help --- ## [Vocab expansion on Gemma 4 E2B: what to do with per-layer embeddings (PLE)?](https://discuss.huggingface.co/t/vocab-expansion-on-gemma-4-e2b-what-to-do-with-per-layer-embeddings-ple/190514)
**Author:** [@raita11](https://discuss.huggingface.co/u/raita11)\ **Replies:** 0\ **Last updated:** [October 13, 2026, 7:11pm UTC](https://discuss.huggingface.co/t/vocab-expansion-on-gemma-4-e2b-what-to-do-with-per-layer-embeddings-ple/190514 "2026-10-13T19:11:34Z")
Hello, I’m trying to add a language to Gemma 4 E2B by expanding the vocabulary, and I plan to use QLoRA CPT, training only the embeddings first. My question is about per-layer embeddings (PLE): When I resize embed\_to… --- ## [Welche AI und zu welchem Preis?](https://discuss.huggingface.co/t/welche-ai-und-zu-welchem-preis/171425)
**Author:** [@ChrFeMi](https://discuss.huggingface.co/u/ChrFeMi)\ **Replies:** 2\ **Last updated:** [October 13, 2026, 7:11pm UTC](https://discuss.huggingface.co/t/welche-ai-und-zu-welchem-preis/171425 "2026-10-13T19:11:16Z")
Hallo an Alle, ich wüsste sonst nicht,wo ich eine Frage stellen könnte. Mir geht es darum eine AI effizient nutzen zu können. Ich nutze momentan die webbasierte Claude 4.5 Version in der Free-Version. Doch die Chats fü… --- ## [Inference Providers credits show $0.00 despite no usage](https://discuss.huggingface.co/t/inference-providers-credits-show-0-00-despite-no-usage/190471)
**Author:** [@1234jithu](https://discuss.huggingface.co/u/1234jithu)\ **Replies:** 1\ **Last updated:** [October 13, 2026, 2:19pm UTC](https://discuss.huggingface.co/t/inference-providers-credits-show-0-00-despite-no-usage/190471 "2026-10-13T14:19:55Z")
Hello, My Hugging Face account shows $0.00 in Inference Providers credits. My usage dashboard shows no inference requests and $0.00 usage. I have no payment method registered. When I try to use Qwen/Qwen2.5-1.5B-Instru… --- ## [Jira Alternatives for Teams Building with AI Agents](https://discuss.huggingface.co/t/jira-alternatives-for-teams-building-with-ai-agents/190385)
**Author:** [@Eric026](https://discuss.huggingface.co/u/Eric026)\ **Replies:** 1\ **Last updated:** [October 13, 2026, 1:39pm UTC](https://discuss.huggingface.co/t/jira-alternatives-for-teams-building-with-ai-agents/190385 "2026-10-13T13:39:54Z")
s AI agents take on coding, testing, and research, project management needs to evolve beyond assigning tasks to humans. When comparing Jira alternatives, I’d look for tools that support clear task ownership, shared cont… --- ## [Best Jira Integrations for Engineering Teams: Connecting Issues, Code, and AI Agents](https://discuss.huggingface.co/t/best-jira-integrations-for-engineering-teams-connecting-issues-code-and-ai-agents/190461)
**Author:** [@Eric026](https://discuss.huggingface.co/u/Eric026)\ **Replies:** 1\ **Last updated:** [October 13, 2026, 1:38pm UTC](https://discuss.huggingface.co/t/best-jira-integrations-for-engineering-teams-connecting-issues-code-and-ai-agents/190461 "2026-10-13T13:38:07Z")
Engineering teams often work across several tools: Jira for issue tracking, GitHub for code reviews, and Slack for team communication. The challenge is keeping everything connected without losing context. Here are three… --- ## [Technical scaling & spatial fit for SKU object replacement](https://discuss.huggingface.co/t/technical-scaling-spatial-fit-for-sku-object-replacement/190457)
**Author:** [@suruchiarora](https://discuss.huggingface.co/u/suruchiarora)\ **Replies:** 1\ **Last updated:** [October 13, 2026, 1:04pm UTC](https://discuss.huggingface.co/t/technical-scaling-spatial-fit-for-sku-object-replacement/190457 "2026-10-13T13:04:32Z")
Hi everyone, Following up on the object replacement workflow (FLUX and Qwen are working quite nicely for the visual swap!), I have run into a core geometric challenge regarding scale and real-world placement. When repl… --- ## [What Should I Learn First?](https://discuss.huggingface.co/t/what-should-i-learn-first/190448)
**Author:** [@Novaknox](https://discuss.huggingface.co/u/Novaknox)\ **Replies:** 1\ **Last updated:** [October 13, 2026, 12:25pm UTC](https://discuss.huggingface.co/t/what-should-i-learn-first/190448 "2026-10-13T12:25:19Z")
Hi everyone! I’m new to the Hugging Face community and interested in learning more about AI and machine learning. I’m still a beginner, so I’d love to hear some advice from people who have more experience. My question … --- ## [Inference Providers shows no remaining credits despite zero usage](https://discuss.huggingface.co/t/inference-providers-shows-no-remaining-credits-despite-zero-usage/190399)
**Author:** [@john1026](https://discuss.huggingface.co/u/john1026)\ **Replies:** 1\ **Last updated:** [October 13, 2026, 11:39am UTC](https://discuss.huggingface.co/t/inference-providers-shows-no-remaining-credits-despite-zero-usage/190399 "2026-10-13T11:39:13Z")
Hello Hugging Face Support, I am trying to test meta-llama/Llama-4-Scout-17B-16E-Instruct using the model page’s Inference Providers widget with Novita. The widget displays: “You have no remaining credits for Inferenc… --- ## ["Access Denied" trying to download any model](https://discuss.huggingface.co/t/access-denied-trying-to-download-any-model/177783)
**Author:** [@17slim](https://discuss.huggingface.co/u/17slim)\ **Replies:** 16\ **Last updated:** [October 13, 2026, 6:57am UTC](https://discuss.huggingface.co/t/access-denied-trying-to-download-any-model/177783 "2026-10-13T06:57:35Z")
Hi! As in the title - trying to download any model or quantization at all results in an “Access Denied” XML response, even for models I have downloaded in the past (like, even a few weeks ago). Is HuggingFace down or som… --- ## [Shoe string ablation or pruning](https://discuss.huggingface.co/t/shoe-string-ablation-or-pruning/190294)
**Author:** [@Jaketillian](https://discuss.huggingface.co/u/Jaketillian)\ **Replies:** 12\ **Last updated:** [October 13, 2026, 6:58am UTC](https://discuss.huggingface.co/t/shoe-string-ablation-or-pruning/190294 "2026-10-13T06:58:19Z")
I run gpt-oss-120b on RTX4060 8b , 96gb ddr5, i9 14th, 25 tok/s. I use llmfan46/gpt-oss-120b-ultra-heretic for a while now and am quite happy except for ram prices. I grabbed bryanvine/gpt-oss-120b-reap-48 merged the .… --- ## [How to download pan.baidu.com or Quark Pan weights without a Chinese account](https://discuss.huggingface.co/t/how-to-download-pan-baidu-com-or-quark-pan-weights-without-a-chinese-account/180705)
**Author:** [@gonelove](https://discuss.huggingface.co/u/gonelove)\ **Replies:** 4\ **Last updated:** [October 12, 2026, 4:51pm UTC](https://discuss.huggingface.co/t/how-to-download-pan-baidu-com-or-quark-pan-weights-without-a-chinese-account/180705 "2026-10-12T16:51:25Z")
Half the Chinese model weights and datasets still land on pan.baidu.com or pan.quark.cn, and those want a mainland Chinese phone number to sign up. Even when you get an account, a free one pulls at roughly 50-100 KB/s … --- ## [How to download from Baidu Pan (pan.baidu.com) without a Chinese account — 2026 notes for datasets + a free fetcher](https://discuss.huggingface.co/t/how-to-download-from-baidu-pan-pan-baidu-com-without-a-chinese-account-2026-notes-for-datasets-a-free-fetcher/180125)
**Author:** [@gonelove](https://discuss.huggingface.co/u/gonelove)\ **Replies:** 2\ **Last updated:** [October 12, 2026, 4:25am UTC](https://discuss.huggingface.co/t/how-to-download-from-baidu-pan-pan-baidu-com-without-a-chinese-account-2026-notes-for-datasets-a-free-fetcher/180125 "2026-10-12T04:25:16Z")
If you've ever tried a Baidu Pan download for a dataset or checkpoint from a paper, you know the drill: pan.baidu.com wants a mainland phone number to sign up, anything over a few hundred MB forces the desktop client, an… --- ## [Introduction, Ques about webui & internet, and positive advocacy](https://discuss.huggingface.co/t/introduction-ques-about-webui-internet-and-positive-advocacy/46039)
**Author:** [@NocturnalRaven](https://discuss.huggingface.co/u/NocturnalRaven)\ **Replies:** 1\ **Last updated:** [October 11, 2026, 9:57pm UTC](https://discuss.huggingface.co/t/introduction-ques-about-webui-internet-and-positive-advocacy/46039 "2026-10-11T21:57:22Z")
Hello everyone, I am going to admit straight out of the proverbial door that I am by no means a coder or computer science person. I took computer science in the 6th grade and made a ‘D’ and thought I’d be done with that… --- ## [Open Source Engineering Challenge - HELP!](https://discuss.huggingface.co/t/open-source-engineering-challenge-help/190346)
**Author:** [@jddchatham](https://discuss.huggingface.co/u/jddchatham)\ **Replies:** 0\ **Last updated:** [October 11, 2026, 3:35pm UTC](https://discuss.huggingface.co/t/open-source-engineering-challenge-help/190346 "2026-10-11T15:35:17Z")
Cortex AI: Help Us Finish Streaming LLM Inference on Low-Memory CPUs Can we run large AI models on computers that don’t have enough RAM to hold their weights? I’m building Cortex, an experimental open-source AI inferenc… --- ## [Top 5 models i can run with my hardware? No AI lobotomization](https://discuss.huggingface.co/t/top-5-models-i-can-run-with-my-hardware-no-ai-lobotomization/177283)
**Author:** [@Pricey-Phantom](https://discuss.huggingface.co/u/Pricey-Phantom)\ **Replies:** 3\ **Last updated:** [October 11, 2026, 6:49am UTC](https://discuss.huggingface.co/t/top-5-models-i-can-run-with-my-hardware-no-ai-lobotomization/177283 "2026-10-11T06:49:02Z")
I want an AI uncensored, that can help me reason about complex topics, for instance GPT 4,0 or earlier version had a decent amount of uncensorship and was capable of creating solutions, after that, GPT has gone only down… [Next page](https://discuss.huggingface.co/c/beginners/5.md?page=1)