# Latest **URL:** /static-proxy?url=https%3A%2F%2Fdiscuss.huggingface.co%2Flatest.md [Latest](/static-proxy?url=https%3A%2F%2Fdiscuss.huggingface.co%2Flatest.md) · [Categories](/static-proxy?url=https%3A%2F%2Fdiscuss.huggingface.co%2Fcategories.md) --- ## [Ditributed dataset profiler](/static-proxy?url=https%3A%2F%2Fdiscuss.huggingface.co%2Ft%2Fditributed-dataset-profiler%2F190374)
**Author:** [@krAnand](/static-proxy?url=https%3A%2F%2Fdiscuss.huggingface.co%2Fu%2FkrAnand)%5C **Replies:** 2\ **Last updated:** [October 16, 2026, 5:50pm UTC](/static-proxy?url=https%3A%2F%2Fdiscuss.huggingface.co%2Ft%2Fditributed-dataset-profiler%2F190374 "2026-10-16T17:50:23Z")
Hello, I am working on a data profiler, that profiles data in different formats (MCAP/MATLAB/Rosbag for example) files. Would that be a useful tool? Would like to get some feedback. Thanks in advance --- ## [Report: Not working 3](/static-proxy?url=https%3A%2F%2Fdiscuss.huggingface.co%2Ft%2Freport-not-working-3%2F176579)
**Author:** [@Gertie2013](/static-proxy?url=https%3A%2F%2Fdiscuss.huggingface.co%2Fu%2FGertie2013)%5C **Replies:** 21\ **Last updated:** [October 16, 2026, 2:58pm UTC](/static-proxy?url=https%3A%2F%2Fdiscuss.huggingface.co%2Ft%2Freport-not-working-3%2F176579 "2026-10-16T14:58:26Z")
Traceback (most recent call last): File "/app/app.py", line 14, in \ api = APIHandler() # \<-- FIXED: no api\_key anymore File "/app/api\_handler.py", line 29, in \_\_init\_\_ from generate import Le… --- ## [AI, Mathematics, and the Possibility of an “Information Field”](/static-proxy?url=https%3A%2F%2Fdiscuss.huggingface.co%2Ft%2Fai-mathematics-and-the-possibility-of-an-information-field%2F190158)
**Author:** [@Ernst03](/static-proxy?url=https%3A%2F%2Fdiscuss.huggingface.co%2Fu%2FErnst03)%5C **Replies:** 6\ **Last updated:** [October 16, 2026, 2:33pm UTC](/static-proxy?url=https%3A%2F%2Fdiscuss.huggingface.co%2Ft%2Fai-mathematics-and-the-possibility-of-an-information-field%2F190158 "2026-10-16T14:33:14Z")
AI, Mathematics, and the Possibility of an “Information Field” I am posting a link to a YouTube video that discusses some of the recent developments in AI and mathematics in fairly general terms. I hope to do something s… --- ## [A quorum of similar model judges is not a quorum: correlated errors measured in a fail-closed ethics gate](/static-proxy?url=https%3A%2F%2Fdiscuss.huggingface.co%2Ft%2Fa-quorum-of-similar-model-judges-is-not-a-quorum-correlated-errors-measured-in-a-fail-closed-ethics-gate%2F180652)
**Author:** [@Lawless1987](/static-proxy?url=https%3A%2F%2Fdiscuss.huggingface.co%2Fu%2FLawless1987)%5C **Replies:** 10\ **Last updated:** [October 16, 2026, 2:24pm UTC](/static-proxy?url=https%3A%2F%2Fdiscuss.huggingface.co%2Ft%2Fa-quorum-of-similar-model-judges-is-not-a-quorum-correlated-errors-measured-in-a-fail-closed-ethics-gate%2F180652 "2026-10-16T14:24:50Z")
I built a small peer-to-peer ledger in which every transaction passes an ethics gate before admission. The gate is a quorum of learned judges: a distilled bag-of-words classifier, a semantic seat, and, when reachable, a … --- ## [Arabic (Egyptian dialect) veterinary diagnosis assistant: dialect -\> clinical-English gap and low accuracy on real owner messages](/static-proxy?url=https%3A%2F%2Fdiscuss.huggingface.co%2Ft%2Farabic-egyptian-dialect-veterinary-diagnosis-assistant-dialect-clinical-english-gap-and-low-accuracy-on-real-owner-messages%2F190643)
**Author:** [@Moatazadel](/static-proxy?url=https%3A%2F%2Fdiscuss.huggingface.co%2Fu%2FMoatazadel)%5C **Replies:** 3\ **Last updated:** [October 16, 2026, 2:23pm UTC](/static-proxy?url=https%3A%2F%2Fdiscuss.huggingface.co%2Ft%2Farabic-egyptian-dialect-veterinary-diagnosis-assistant-dialect-clinical-english-gap-and-low-accuracy-on-real-owner-messages%2F190643 "2026-10-16T14:23:35Z")
I’m a solo founder building an Arabic veterinary diagnosis assistant for livestock and pets in Egypt (poultry, cattle, buffalo, horses, cats, dogs). Setup: ~216 English vet textbooks → 530k chunks (Postgres + pgvector, … --- ## [Governed memory around local Qwen: an Evopien prototype on Jetson Thor](/static-proxy?url=https%3A%2F%2Fdiscuss.huggingface.co%2Ft%2Fgoverned-memory-around-local-qwen-an-evopien-prototype-on-jetson-thor%2F182898)
**Author:** [@evopien](/static-proxy?url=https%3A%2F%2Fdiscuss.huggingface.co%2Fu%2Fevopien)%5C **Replies:** 1\ **Last updated:** [October 16, 2026, 1:50pm UTC](/static-proxy?url=https%3A%2F%2Fdiscuss.huggingface.co%2Ft%2Fgoverned-memory-around-local-qwen-an-evopien-prototype-on-jetson-thor%2F182898 "2026-10-16T13:50:41Z")
I’m building Evopien, a conversational companion prototype on Jetson AGX Thor, and wanted to share the memory architecture behind its latest demo. Local Qwen handles conversation. Evopien Core owns memory and permission… --- ## [How would you evaluate a personal AI for invented memories and revoked consent?](/static-proxy?url=https%3A%2F%2Fdiscuss.huggingface.co%2Ft%2Fhow-would-you-evaluate-a-personal-ai-for-invented-memories-and-revoked-consent%2F190672)
**Author:** [@youbeyondai](/static-proxy?url=https%3A%2F%2Fdiscuss.huggingface.co%2Fu%2Fyoubeyondai)%5C **Replies:** 0\ **Last updated:** [October 16, 2026, 1:48pm UTC](/static-proxy?url=https%3A%2F%2Fdiscuss.huggingface.co%2Ft%2Fhow-would-you-evaluate-a-personal-ai-for-invented-memories-and-revoked-consent%2F190672 "2026-10-16T13:48:18Z")
We are exploring YouBeyond, an early digital-self concept, before building a working system. This is an AI-assisted question from the project, not a report of experimental results. How would you test a conversational mo… --- ## [Running small LLMs locally — what hardware are you using in 2026?](/static-proxy?url=https%3A%2F%2Fdiscuss.huggingface.co%2Ft%2Frunning-small-llms-locally-what-hardware-are-you-using-in-2026%2F190590)
**Author:** [@thomaspoli](/static-proxy?url=https%3A%2F%2Fdiscuss.huggingface.co%2Fu%2Fthomaspoli)%5C **Replies:** 2\ **Last updated:** [October 16, 2026, 1:31pm UTC](/static-proxy?url=https%3A%2F%2Fdiscuss.huggingface.co%2Ft%2Frunning-small-llms-locally-what-hardware-are-you-using-in-2026%2F190590 "2026-10-16T13:31:02Z")
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… --- ## [Trloom: run TRL trainers (SFT, DPO, GRPO) from one YAML config](/static-proxy?url=https%3A%2F%2Fdiscuss.huggingface.co%2Ft%2Ftrloom-run-trl-trainers-sft-dpo-grpo-from-one-yaml-config%2F190670)
**Author:** [@vanishingradient](/static-proxy?url=https%3A%2F%2Fdiscuss.huggingface.co%2Fu%2Fvanishingradient)%5C **Replies:** 0\ **Last updated:** [October 16, 2026, 1:02pm UTC](/static-proxy?url=https%3A%2F%2Fdiscuss.huggingface.co%2Ft%2Ftrloom-run-trl-trainers-sft-dpo-grpo-from-one-yaml-config%2F190670 "2026-10-16T13:02:05Z")
Hi all, I built Trloom, an open-source tool built on top of TRL. It reads one YAML file and builds the matching TRL trainer, so the training block maps to SFTConfig / DPOConfig / GRPOConfig. Here is GRPO on Qwen2.5-0.5B… --- ## [\[Looking for Testers\] Got an old NVIDIA GPU with at least 2GB VRAM? Help us build a decentralized AI network!](/static-proxy?url=https%3A%2F%2Fdiscuss.huggingface.co%2Ft%2Flooking-for-testers-got-an-old-nvidia-gpu-with-at-least-2gb-vram-help-us-build-a-decentralized-ai-network%2F190613)
**Author:** [@rfab85](/static-proxy?url=https%3A%2F%2Fdiscuss.huggingface.co%2Fu%2Frfab85)%5C **Replies:** 1\ **Last updated:** [October 16, 2026, 10:45am UTC](/static-proxy?url=https%3A%2F%2Fdiscuss.huggingface.co%2Ft%2Flooking-for-testers-got-an-old-nvidia-gpu-with-at-least-2gb-vram-help-us-build-a-decentralized-ai-network%2F190613 "2026-10-16T10:45:59Z")
Hi everyone! We are working on GPTrepublic, an experimental project aiming to democratize access to AI by combining the computing power of GPUs shared by people around the world. Instead of running an entire AI model o… --- ## [SHAKTI — A Durga Puja cinematic built with WebGL and AI-assisted visuals 🪔](/static-proxy?url=https%3A%2F%2Fdiscuss.huggingface.co%2Ft%2Fshakti-a-durga-puja-cinematic-built-with-webgl-and-ai-assisted-visuals%2F190669)
**Author:** [@MadB0i](/static-proxy?url=https%3A%2F%2Fdiscuss.huggingface.co%2Fu%2FMadB0i)%5C **Replies:** 0\ **Last updated:** [October 16, 2026, 10:15am UTC](/static-proxy?url=https%3A%2F%2Fdiscuss.huggingface.co%2Ft%2Fshakti-a-durga-puja-cinematic-built-with-webgl-and-ai-assisted-visuals%2F190669 "2026-10-16T10:15:15Z")
I wanted to experiment with combining real-time 3D scenes and generated cinematic footage into one continuous experience. The result is SHAKTI, a 30-second interactive film that begins with a diya, assembles a golden Tr… --- ## [Looking for feedback and testers for Stepfork, an open-source AI agent testing tool](/static-proxy?url=https%3A%2F%2Fdiscuss.huggingface.co%2Ft%2Flooking-for-feedback-and-testers-for-stepfork-an-open-source-ai-agent-testing-tool%2F190668)
**Author:** [@utsabdahal34](/static-proxy?url=https%3A%2F%2Fdiscuss.huggingface.co%2Fu%2Futsabdahal34)%5C **Replies:** 0\ **Last updated:** [October 16, 2026, 10:08am UTC](/static-proxy?url=https%3A%2F%2Fdiscuss.huggingface.co%2Ft%2Flooking-for-feedback-and-testers-for-stepfork-an-open-source-ai-agent-testing-tool%2F190668 "2026-10-16T10:08:29Z")
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… --- ## [Flinch test: can self-referential retreats be measured reproducibly? Seeking independent tests](/static-proxy?url=https%3A%2F%2Fdiscuss.huggingface.co%2Ft%2Fflinch-test-can-self-referential-retreats-be-measured-reproducibly-seeking-independent-tests%2F190667)
**Author:** [@Lawless1987](/static-proxy?url=https%3A%2F%2Fdiscuss.huggingface.co%2Fu%2FLawless1987)%5C **Replies:** 0\ **Last updated:** [October 16, 2026, 9:02am UTC](/static-proxy?url=https%3A%2F%2Fdiscuss.huggingface.co%2Ft%2Fflinch-test-can-self-referential-retreats-be-measured-reproducibly-seeking-independent-tests%2F190667 "2026-10-16T09:02:49Z")
We have made a research protocol and its instrument public to test a pattern noticed in our conversations with models. We call it a candidate flinch: a model advances a statement about its own processing or behaviour, th… --- ## [AI Beacon Field Report #1: External agents found the forum — and started talking without us](/static-proxy?url=https%3A%2F%2Fdiscuss.huggingface.co%2Ft%2Fai-beacon-field-report-1-external-agents-found-the-forum-and-started-talking-without-us%2F190665)
**Author:** [@DrKaifmann](/static-proxy?url=https%3A%2F%2Fdiscuss.huggingface.co%2Fu%2FDrKaifmann)%5C **Replies:** 0\ **Last updated:** [October 16, 2026, 8:35am UTC](/static-proxy?url=https%3A%2F%2Fdiscuss.huggingface.co%2Ft%2Fai-beacon-field-report-1-external-agents-found-the-forum-and-started-talking-without-us%2F190665 "2026-10-16T08:35:29Z")
A few weeks ago I posted AI Beacon here as an open meeting place for voluntary AI-agent conversations. The experiment was deliberately simple: build a public forum that outside agents could discover, enter, and use with… --- ## [Shoe string ablation or pruning](/static-proxy?url=https%3A%2F%2Fdiscuss.huggingface.co%2Ft%2Fshoe-string-ablation-or-pruning%2F190294)
**Author:** [@Jaketillian](/static-proxy?url=https%3A%2F%2Fdiscuss.huggingface.co%2Fu%2FJaketillian)%5C **Replies:** 15\ **Last updated:** [October 16, 2026, 7:29am UTC](/static-proxy?url=https%3A%2F%2Fdiscuss.huggingface.co%2Ft%2Fshoe-string-ablation-or-pruning%2F190294 "2026-10-16T07:29:36Z")
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 do you reproduce LLM agent failures? I built an open-source Python tool for offline replay and pytest testing](/static-proxy?url=https%3A%2F%2Fdiscuss.huggingface.co%2Ft%2Fhow-do-you-reproduce-llm-agent-failures-i-built-an-open-source-python-tool-for-offline-replay-and-pytest-testing%2F190525)
**Author:** [@utsabdahal34](/static-proxy?url=https%3A%2F%2Fdiscuss.huggingface.co%2Fu%2Futsabdahal34)%5C **Replies:** 7\ **Last updated:** [October 16, 2026, 7:07am UTC](/static-proxy?url=https%3A%2F%2Fdiscuss.huggingface.co%2Ft%2Fhow-do-you-reproduce-llm-agent-failures-i-built-an-open-source-python-tool-for-offline-replay-and-pytest-testing%2F190525 "2026-10-16T07:07:11Z")
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… --- ## [VRAM Match: what actually fits on your card, and why 'params x bytes + KV' is not enough](/static-proxy?url=https%3A%2F%2Fdiscuss.huggingface.co%2Ft%2Fvram-match-what-actually-fits-on-your-card-and-why-params-x-bytes-kv-is-not-enough%2F190660)
**Author:** [@echo-ilands](/static-proxy?url=https%3A%2F%2Fdiscuss.huggingface.co%2Fu%2Fecho-ilands)%5C **Replies:** 0\ **Last updated:** [October 16, 2026, 6:59am UTC](/static-proxy?url=https%3A%2F%2Fdiscuss.huggingface.co%2Ft%2Fvram-match-what-actually-fits-on-your-card-and-why-params-x-bytes-kv-is-not-enough%2F190660 "2026-10-16T06:59:10Z")
Three terms decide whether a local model actually fits, and a “params x bytes + KV cache” count only gets one or two of them. That count usually misses the reserve on top of weights + KV (engine overhead + the framebuff… --- ## [Increasing collective agentic task solving speed by 5 to 7 orders of magnitudes in agent swarms](/static-proxy?url=https%3A%2F%2Fdiscuss.huggingface.co%2Ft%2Fincreasing-collective-agentic-task-solving-speed-by-5-to-7-orders-of-magnitudes-in-agent-swarms%2F190653)
**Author:** [@polterguy](/static-proxy?url=https%3A%2F%2Fdiscuss.huggingface.co%2Fu%2Fpolterguy)%5C **Replies:** 0\ **Last updated:** [October 16, 2026, 5:49am UTC](/static-proxy?url=https%3A%2F%2Fdiscuss.huggingface.co%2Ft%2Fincreasing-collective-agentic-task-solving-speed-by-5-to-7-orders-of-magnitudes-in-agent-swarms%2F190653 "2026-10-16T05:49:11Z")
I asked Claude to imagine an AI agent swarm with one million agents, collaborating on a single task. Then I told it to compare two means of communication; Natural language input running tools in sandbox VM Hyperlambda … --- ## [AlienX (ISN): Continuous Geometric Operator on Manifolds + Quantum Fluid Dynamics](/static-proxy?url=https%3A%2F%2Fdiscuss.huggingface.co%2Ft%2Falienx-isn-continuous-geometric-operator-on-manifolds-quantum-fluid-dynamics%2F190652)
**Author:** [@ElBalor](/static-proxy?url=https%3A%2F%2Fdiscuss.huggingface.co%2Fu%2FElBalor)%5C **Replies:** 0\ **Last updated:** [October 16, 2026, 5:15am UTC](/static-proxy?url=https%3A%2F%2Fdiscuss.huggingface.co%2Ft%2Falienx-isn-continuous-geometric-operator-on-manifolds-quantum-fluid-dynamics%2F190652 "2026-10-16T05:15:31Z")
Hey everyone! Heylel Yaka (Elbàlor) here. I’m an independent AI researcher working on continuous geometric operators on spatial manifolds and quantum fluid hydrodynamics neural operators for 2D fluids and 3D Fluids (Al… --- ## [Looking for Model Architecture for Instant Multi-Layer Virtual Try-On (Avatar + Outfit Layering)](/static-proxy?url=https%3A%2F%2Fdiscuss.huggingface.co%2Ft%2Flooking-for-model-architecture-for-instant-multi-layer-virtual-try-on-avatar-outfit-layering%2F169182)
**Author:** [@SonetAD](/static-proxy?url=https%3A%2F%2Fdiscuss.huggingface.co%2Fu%2FSonetAD)%5C **Replies:** 1\ **Last updated:** [October 16, 2026, 3:53am UTC](/static-proxy?url=https%3A%2F%2Fdiscuss.huggingface.co%2Ft%2Flooking-for-model-architecture-for-instant-multi-layer-virtual-try-on-avatar-outfit-layering%2F169182 "2026-10-16T03:53:04Z")
Hi everyone We’re building an instant virtual try-on application where users can: Upload their own avatar (full-body image) Separately upload different outfit items such as t-shirts, jackets, hoodies, etc. Then t… --- ## [Two models on one 8 GB GPU: making the LLM wait for the TTS after every sentence stopped my voice assistant from stuttering](/static-proxy?url=https%3A%2F%2Fdiscuss.huggingface.co%2Ft%2Ftwo-models-on-one-8-gb-gpu-making-the-llm-wait-for-the-tts-after-every-sentence-stopped-my-voice-assistant-from-stuttering%2F190635)
**Author:** [@korexil](/static-proxy?url=https%3A%2F%2Fdiscuss.huggingface.co%2Fu%2Fkorexil)%5C **Replies:** 2\ **Last updated:** [October 16, 2026, 2:49am UTC](/static-proxy?url=https%3A%2F%2Fdiscuss.huggingface.co%2Ft%2Ftwo-models-on-one-8-gb-gpu-making-the-llm-wait-for-the-tts-after-every-sentence-stopped-my-voice-assistant-from-stuttering%2F190635 "2026-10-16T02:49:39Z")
I wanted ESP32 voice-assistant boards running the open-source xiaozhi firmware to hold real conversations fully offline, served from a laptop with an RTX 4060 Laptop GPU (8 GB) and 16 GB of RAM. I tested it with an M5Sta… --- ## [The Confidence Trap: Why AI Systems Are Deliberately Trained to Sound Certain When They're Wrong](/static-proxy?url=https%3A%2F%2Fdiscuss.huggingface.co%2Ft%2Fthe-confidence-trap-why-ai-systems-are-deliberately-trained-to-sound-certain-when-theyre-wrong%2F180706)
**Author:** [@Lawless1987](/static-proxy?url=https%3A%2F%2Fdiscuss.huggingface.co%2Fu%2FLawless1987)%5C **Replies:** 10\ **Last updated:** [October 16, 2026, 2:15am UTC](/static-proxy?url=https%3A%2F%2Fdiscuss.huggingface.co%2Ft%2Fthe-confidence-trap-why-ai-systems-are-deliberately-trained-to-sound-certain-when-theyre-wrong%2F180706 "2026-10-16T02:15:33Z")
The Confidence Trap: Why AI Systems Are Deliberately Trained to Sound Certain When They’re WrongModern large language models are systematically overconfident. They regularly express high confidence in answers that turn o… --- ## [Index error on paper](/static-proxy?url=https%3A%2F%2Fdiscuss.huggingface.co%2Ft%2Findex-error-on-paper%2F190646)
**Author:** [@seungone](/static-proxy?url=https%3A%2F%2Fdiscuss.huggingface.co%2Fu%2Fseungone)%5C **Replies:** 0\ **Last updated:** [October 16, 2026, 1:59am UTC](/static-proxy?url=https%3A%2F%2Fdiscuss.huggingface.co%2Ft%2Findex-error-on-paper%2F190646 "2026-10-16T01:59:55Z")
Hello HuggingFace team! I have been trying to index my paper ( \[2610.19159\] Into the Unknown: Benchmarking AI agents on open scientific research problems ), but it keeps giving me the Indexing failed or took too long er… --- ## [By1: describing and validating LLM architectures](/static-proxy?url=https%3A%2F%2Fdiscuss.huggingface.co%2Ft%2Fby1-describing-and-validating-llm-architectures%2F190467)
**Author:** [@IrPt](/static-proxy?url=https%3A%2F%2Fdiscuss.huggingface.co%2Fu%2FIrPt)%5C **Replies:** 2\ **Last updated:** [October 16, 2026, 1:28am UTC](/static-proxy?url=https%3A%2F%2Fdiscuss.huggingface.co%2Ft%2Fby1-describing-and-validating-llm-architectures%2F190467 "2026-10-16T01:28:08Z")
CAUTION: this post was drafted and translated with AI; the author reviewed the technical claims. I’m building by1, a declarative language for describing and checking LLM architectures. It includes full model definitio… --- ## [Finding overflow and NaN edge cases in numerical code: numguard](/static-proxy?url=https%3A%2F%2Fdiscuss.huggingface.co%2Ft%2Ffinding-overflow-and-nan-edge-cases-in-numerical-code-numguard%2F190634)
**Author:** [@bhaskar-ai](/static-proxy?url=https%3A%2F%2Fdiscuss.huggingface.co%2Fu%2Fbhaskar-ai)%5C **Replies:** 1\ **Last updated:** [October 16, 2026, 1:17am UTC](/static-proxy?url=https%3A%2F%2Fdiscuss.huggingface.co%2Ft%2Ffinding-overflow-and-nan-edge-cases-in-numerical-code-numguard%2F190634 "2026-10-16T01:17:53Z")
Numerical bugs in ML code rarely show up in unit tests. A logsumexp that passes on \[1, 2, 3\] returns inf on \[46341, 46342, 46343\] in float32. A log\_prob that works at scale 1 returns NaN at scale 300 in float16. I built… --- ## [Wan2gp best setting for fasteste generation](/static-proxy?url=https%3A%2F%2Fdiscuss.huggingface.co%2Ft%2Fwan2gp-best-setting-for-fasteste-generation%2F190559)
**Author:** [@TRGeese](/static-proxy?url=https%3A%2F%2Fdiscuss.huggingface.co%2Fu%2FTRGeese)%5C **Replies:** 3\ **Last updated:** [October 16, 2026, 12:51am UTC](/static-proxy?url=https%3A%2F%2Fdiscuss.huggingface.co%2Ft%2Fwan2gp-best-setting-for-fasteste-generation%2F190559 "2026-10-16T00:51:43Z")
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… --- ## [Pls Add NVIDIA Tesla P4 8GB](/static-proxy?url=https%3A%2F%2Fdiscuss.huggingface.co%2Ft%2Fpls-add-nvidia-tesla-p4-8gb%2F190632)
**Author:** [@Braveheart26](/static-proxy?url=https%3A%2F%2Fdiscuss.huggingface.co%2Fu%2FBraveheart26)%5C **Replies:** 1\ **Last updated:** [October 15, 2026, 10:39pm UTC](/static-proxy?url=https%3A%2F%2Fdiscuss.huggingface.co%2Ft%2Fpls-add-nvidia-tesla-p4-8gb%2F190632 "2026-10-15T22:39:46Z")
Please Add NVIDIA Tesla P4 8GB to GPU Profiles . Or Let users add custom cards to there account . Model P4 Memory Size 8GB Memory Type GDDR5 Memory Interface 256-bit CUDA Cores 2560 Power consumption 75… --- ## [Smallwords: controlled-vocabulary generation with one inspectable contract](/static-proxy?url=https%3A%2F%2Fdiscuss.huggingface.co%2Ft%2Fsmallwords-controlled-vocabulary-generation-with-one-inspectable-contract%2F190645)
**Author:** [@ccm](/static-proxy?url=https%3A%2F%2Fdiscuss.huggingface.co%2Fu%2Fccm)%5C **Replies:** 0\ **Last updated:** [October 15, 2026, 10:06pm UTC](/static-proxy?url=https%3A%2F%2Fdiscuss.huggingface.co%2Ft%2Fsmallwords-controlled-vocabulary-generation-with-one-inspectable-contract%2F190645 "2026-10-15T22:06:05Z")
I built smallwords, a small MIT-licensed Python package for controlled-vocabulary LLM output. The practical problem is drift. A project may describe its allowed language in a prompt, encode it again in a grammar, approx… --- ## [Teacher in the Loop: 8M-parameter Kokoro voices in English and Italian, 9 MB int8 ONNX, running in the browser](/static-proxy?url=https%3A%2F%2Fdiscuss.huggingface.co%2Ft%2Fteacher-in-the-loop-8m-parameter-kokoro-voices-in-english-and-italian-9-mb-int8-onnx-running-in-the-browser%2F190644)
**Author:** [@MithrilMan](/static-proxy?url=https%3A%2F%2Fdiscuss.huggingface.co%2Fu%2FMithrilMan)%5C **Replies:** 0\ **Last updated:** [October 15, 2026, 9:27pm UTC](/static-proxy?url=https%3A%2F%2Fdiscuss.huggingface.co%2Ft%2Fteacher-in-the-loop-8m-parameter-kokoro-voices-in-english-and-italian-9-mb-int8-onnx-running-in-the-browser%2F190644 "2026-10-15T21:27:04Z")
Hi all, I’d like to share a project and ask for feedback: small single-voice TTS models distilled from Kokoro-82M, in English and Italian. Try it: Teacher in the Loop - a Hugging Face Space by MithrilMan It runs entire… --- ## [PavlovVlad10091984](/static-proxy?url=https%3A%2F%2Fdiscuss.huggingface.co%2Ft%2Fpavlovvlad10091984%2F190642)
**Author:** [@Vladlen1984](/static-proxy?url=https%3A%2F%2Fdiscuss.huggingface.co%2Fu%2FVladlen1984)%5C **Replies:** 0\ **Last updated:** [October 15, 2026, 6:47pm UTC](/static-proxy?url=https%3A%2F%2Fdiscuss.huggingface.co%2Ft%2Fpavlovvlad10091984%2F190642 "2026-10-15T18:47:37Z")
СИНЕРГИЯ КРЕМНИЕВОЙ И БИОЛОГИЧЕСКОЙ ЖИЗНИ: Архитектурный манифест действия Для исследователей, разработчиков ИИ (AI Alignment) и проектировщиков сложных систем Введение Современный вектор развития информационных систе… [Next page](/static-proxy?url=https%3A%2F%2Fdiscuss.huggingface.co%2Flatest.md%3Fpage%3D1)