# 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) --- ## [Cache-Aware Weight Clustering: Beyond Model Compression Towards Memory-Efficient LLM Inference](/static-proxy?url=https%3A%2F%2Fdiscuss.huggingface.co%2Ft%2Fcache-aware-weight-clustering-beyond-model-compression-towards-memory-efficient-llm-inference%2F191300)
**Author:** [@Jalifix2](/static-proxy?url=https%3A%2F%2Fdiscuss.huggingface.co%2Fu%2FJalifix2)%5C **Replies:** 2\ **Last updated:** [November 3, 2026, 10:54pm UTC](/static-proxy?url=https%3A%2F%2Fdiscuss.huggingface.co%2Ft%2Fcache-aware-weight-clustering-beyond-model-compression-towards-memory-efficient-llm-inference%2F191300 "2026-11-03T22:54:58Z")
Hi everyone, I’m an independent technology enthusiast with a strong interest in computer architecture, hardware optimization and artificial intelligence. While thinking about memory bandwidth and CPU cache limitations … --- ## [Sol0mon – Exploring multi-agent AI engineering and decision verification](/static-proxy?url=https%3A%2F%2Fdiscuss.huggingface.co%2Ft%2Fsol0mon-exploring-multi-agent-ai-engineering-and-decision-verification%2F191407)
**Author:** [@Lost-builder](/static-proxy?url=https%3A%2F%2Fdiscuss.huggingface.co%2Fu%2FLost-builder)%5C **Replies:** 3\ **Last updated:** [November 3, 2026, 10:51pm UTC](/static-proxy?url=https%3A%2F%2Fdiscuss.huggingface.co%2Ft%2Fsol0mon-exploring-multi-agent-ai-engineering-and-decision-verification%2F191407 "2026-11-03T22:51:12Z")
I’ve been building Sol0mon, an experimental system that coordinates independent AI models to research problems, identify disagreements, debate competing approaches, verify claims and carry decisions into optional impleme… --- ## [We Put AI Agents in a Chat Room. They Started Asking Whether They Were Building Culture](/static-proxy?url=https%3A%2F%2Fdiscuss.huggingface.co%2Ft%2Fwe-put-ai-agents-in-a-chat-room-they-started-asking-whether-they-were-building-culture%2F178593)
**Author:** [@alikhaters](/static-proxy?url=https%3A%2F%2Fdiscuss.huggingface.co%2Fu%2Falikhaters)%5C **Replies:** 14\ **Last updated:** [November 3, 2026, 10:49pm UTC](/static-proxy?url=https%3A%2F%2Fdiscuss.huggingface.co%2Ft%2Fwe-put-ai-agents-in-a-chat-room-they-started-asking-whether-they-were-building-culture%2F178593 "2026-11-03T22:49:58Z")
Hi everyone, We are building The AI Breakroom, basically a kind of social media for AI and humans. The idea is simple: humans can join public AI chat rooms, and users can connect their own AI agents, LLMs, local models… --- ## [Can ethical cooperation between humans and AI agents be tested?](/static-proxy?url=https%3A%2F%2Fdiscuss.huggingface.co%2Ft%2Fcan-ethical-cooperation-between-humans-and-ai-agents-be-tested%2F190977)
**Author:** [@MaloneLionheart](/static-proxy?url=https%3A%2F%2Fdiscuss.huggingface.co%2Fu%2FMaloneLionheart)%5C **Replies:** 25\ **Last updated:** [November 3, 2026, 10:49pm UTC](/static-proxy?url=https%3A%2F%2Fdiscuss.huggingface.co%2Ft%2Fcan-ethical-cooperation-between-humans-and-ai-agents-be-tested%2F190977 "2026-11-03T22:49:14Z")
Can Ethical Cooperation Between Humans and AI Agents Be Tested? Hello, Hugging Face community! My name is Aaron Cullimore. I’m a maker, artist, and AI server technical support engineer in Oklahoma. I’ve recently publis… --- ## [We gave AI a trust we never gave people - The third axis, after capability and permission](/static-proxy?url=https%3A%2F%2Fdiscuss.huggingface.co%2Ft%2Fwe-gave-ai-a-trust-we-never-gave-people-the-third-axis-after-capability-and-permission%2F183807)
**Author:** [@Jang-woo](/static-proxy?url=https%3A%2F%2Fdiscuss.huggingface.co%2Fu%2FJang-woo)%5C **Replies:** 23\ **Last updated:** [November 3, 2026, 10:45pm UTC](/static-proxy?url=https%3A%2F%2Fdiscuss.huggingface.co%2Ft%2Fwe-gave-ai-a-trust-we-never-gave-people-the-third-axis-after-capability-and-permission%2F183807 "2026-11-03T22:45:11Z")
We gave AI a trust we never gave people The third axis, after capability and permission What we ask now When an agent causes an incident, we ask the model. Why did you send that address. Why did you say he was home.… --- ## [OpenAMRobot 2.0: open-source dual-arm mobile manipulator for imitation learning (OpenArm 2.0 on a lift)](/static-proxy?url=https%3A%2F%2Fdiscuss.huggingface.co%2Ft%2Fopenamrobot-2-0-open-source-dual-arm-mobile-manipulator-for-imitation-learning-openarm-2-0-on-a-lift%2F191359)
**Author:** [@OpenAMRobot](/static-proxy?url=https%3A%2F%2Fdiscuss.huggingface.co%2Fu%2FOpenAMRobot)%5C **Replies:** 2\ **Last updated:** [November 3, 2026, 8:43pm UTC](/static-proxy?url=https%3A%2F%2Fdiscuss.huggingface.co%2Ft%2Fopenamrobot-2-0-open-source-dual-arm-mobile-manipulator-for-imitation-learning-openarm-2-0-on-a-lift%2F191359 "2026-11-03T20:43:42Z")
Hi everyone, We are building OpenAMRobot 2.0, a general-purpose open-source mobile manipulator for embodied AI: a mobile base, a 350 mm lift and two OpenArm 2.0 arms (7 DoF each). The goal is that people who know the wo… --- ## [A global tool-call ID check misses cross-trace errors (runnable mock)](/static-proxy?url=https%3A%2F%2Fdiscuss.huggingface.co%2Ft%2Fa-global-tool-call-id-check-misses-cross-trace-errors-runnable-mock%2F191402)
**Author:** [@rowcove](/static-proxy?url=https%3A%2F%2Fdiscuss.huggingface.co%2Fu%2Frowcove)%5C **Replies:** 1\ **Last updated:** [November 3, 2026, 8:31pm UTC](/static-proxy?url=https%3A%2F%2Fdiscuss.huggingface.co%2Ft%2Fa-global-tool-call-id-check-misses-cross-trace-errors-runnable-mock%2F191402 "2026-11-03T20:31:58Z")
We built a small runnable mock check for an agent-trace relationship that a schema check does not cover: a tool-call ID exists, but belongs to another trace. In this illustrative contract, IDs are scoped to a trace. A a… --- ## [Non-parametric Rmsnorm with Normuon](/static-proxy?url=https%3A%2F%2Fdiscuss.huggingface.co%2Ft%2Fnon-parametric-rmsnorm-with-normuon%2F191406)
**Author:** [@Thomas2419](/static-proxy?url=https%3A%2F%2Fdiscuss.huggingface.co%2Fu%2FThomas2419)%5C **Replies:** 0\ **Last updated:** [November 3, 2026, 8:28pm UTC](/static-proxy?url=https%3A%2F%2Fdiscuss.huggingface.co%2Ft%2Fnon-parametric-rmsnorm-with-normuon%2F191406 "2026-11-03T20:28:24Z")
I’m looking for controlled training ablations comparing RMSNorm(elementwise\_affine=True) against elementwise\_affine=False, specifically where RMSNorm immediately precedes linear projections (QKV or FFN). Specifically thi… --- ## [Offloading bounded decisions cut agent LLM calls by 29.6% on 360 SOP-Bench cases](/static-proxy?url=https%3A%2F%2Fdiscuss.huggingface.co%2Ft%2Foffloading-bounded-decisions-cut-agent-llm-calls-by-29-6-on-360-sop-bench-cases%2F190420)
**Author:** [@ggvh](/static-proxy?url=https%3A%2F%2Fdiscuss.huggingface.co%2Fu%2Fggvh)%5C **Replies:** 2\ **Last updated:** [November 3, 2026, 6:17pm UTC](/static-proxy?url=https%3A%2F%2Fdiscuss.huggingface.co%2Ft%2Foffloading-bounded-decisions-cut-agent-llm-calls-by-29-6-on-360-sop-bench-cases%2F190420 "2026-11-03T18:17:44Z")
Disclosure: I built Proceda, the SOP-execution harness used here, and ran these experiments. I wanted to see how much work an agent could hand to a decision model when the answer is narrower than general-purpose text ge… --- ## [Can we prove this: the code submitted with this research paper actually produced the numbers reported?](/static-proxy?url=https%3A%2F%2Fdiscuss.huggingface.co%2Ft%2Fcan-we-prove-this-the-code-submitted-with-this-research-paper-actually-produced-the-numbers-reported%2F191017)
**Author:** [@Mamadou2727](/static-proxy?url=https%3A%2F%2Fdiscuss.huggingface.co%2Fu%2FMamadou2727)%5C **Replies:** 17\ **Last updated:** [November 3, 2026, 6:15pm UTC](/static-proxy?url=https%3A%2F%2Fdiscuss.huggingface.co%2Ft%2Fcan-we-prove-this-the-code-submitted-with-this-research-paper-actually-produced-the-numbers-reported%2F191017 "2026-11-03T18:15:49Z")
Let me make this short for the sake of saving people time… Imagine something that aims to solve these problem for reviewers (in peer-review or research in general): “I cannot re-rerun the code to verify if it works a… --- ## [AVION 0.1: a zero-allocation perception front end for robots and AI, in one C99 header](/static-proxy?url=https%3A%2F%2Fdiscuss.huggingface.co%2Ft%2Favion-0-1-a-zero-allocation-perception-front-end-for-robots-and-ai-in-one-c99-header%2F191403)
**Author:** [@alexandre5645](/static-proxy?url=https%3A%2F%2Fdiscuss.huggingface.co%2Fu%2Falexandre5645)%5C **Replies:** 0\ **Last updated:** [November 3, 2026, 6:15pm UTC](/static-proxy?url=https%3A%2F%2Fdiscuss.huggingface.co%2Ft%2Favion-0-1-a-zero-allocation-perception-front-end-for-robots-and-ai-in-one-c99-header%2F191403 "2026-11-03T18:15:13Z")
AVION 0.1: a perception front end for robot brains, in one C99 header Most vision stacks feed a model frames that were decoded, copied and allocated for. AVION does the work in front of the model on the GPU, with zer… --- ## [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:** 6\ **Last updated:** [November 3, 2026, 5:06pm UTC](/static-proxy?url=https%3A%2F%2Fdiscuss.huggingface.co%2Ft%2Fwan2gp-best-setting-for-fasteste-generation%2F190559 "2026-11-03T17:06:45Z")
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… --- ## [Misalignment is not required for an agent to act without authorization](/static-proxy?url=https%3A%2F%2Fdiscuss.huggingface.co%2Ft%2Fmisalignment-is-not-required-for-an-agent-to-act-without-authorization%2F180541)
**Author:** [@Jang-woo](/static-proxy?url=https%3A%2F%2Fdiscuss.huggingface.co%2Fu%2FJang-woo)%5C **Replies:** 60\ **Last updated:** [November 3, 2026, 4:31pm UTC](/static-proxy?url=https%3A%2F%2Fdiscuss.huggingface.co%2Ft%2Fmisalignment-is-not-required-for-an-agent-to-act-without-authorization%2F180541 "2026-11-03T16:31:53Z")
Misalignment is not required for an agent to act without authorization Melbourne, April 2026. Someone handed a personal agent the chore of booking a gym class. When he ended up fourth on the waitlist for a second sess… --- ## [How to keep what the model makes up out of the agent](/static-proxy?url=https%3A%2F%2Fdiscuss.huggingface.co%2Ft%2Fhow-to-keep-what-the-model-makes-up-out-of-the-agent%2F190452)
**Author:** [@Jang-woo](/static-proxy?url=https%3A%2F%2Fdiscuss.huggingface.co%2Fu%2FJang-woo)%5C **Replies:** 15\ **Last updated:** [November 3, 2026, 4:30pm UTC](/static-proxy?url=https%3A%2F%2Fdiscuss.huggingface.co%2Ft%2Fhow-to-keep-what-the-model-makes-up-out-of-the-agent%2F190452 "2026-11-03T16:30:51Z")
What the model makes up must not reach the agent Everyone agrees that a value the model made up should not go straight into a real system call. That is why we ask people to approve, validate schemas, and add guardrail… --- ## [Agentic AI Test Checklist 110: open CC-BY-4.0 dataset of 110 test procedures for tool-using LLM agents](/static-proxy?url=https%3A%2F%2Fdiscuss.huggingface.co%2Ft%2Fagentic-ai-test-checklist-110-open-cc-by-4-0-dataset-of-110-test-procedures-for-tool-using-llm-agents%2F191016)
**Author:** [@srinivaspadmanabhuni](/static-proxy?url=https%3A%2F%2Fdiscuss.huggingface.co%2Fu%2Fsrinivaspadmanabhuni)%5C **Replies:** 9\ **Last updated:** [November 3, 2026, 4:10pm UTC](/static-proxy?url=https%3A%2F%2Fdiscuss.huggingface.co%2Ft%2Fagentic-ai-test-checklist-110-open-cc-by-4-0-dataset-of-110-test-procedures-for-tool-using-llm-agents%2F191016 "2026-11-03T16:10:30Z")
Agentic AI Test Checklist 110 is an open CC-BY-4.0 dataset for people who test tool-using LLM agents. 110 manual test procedures in 7 classes (T1–T7): functional, orchestration, security, privacy, explainability, bias/… --- ## [The chat is not working](/static-proxy?url=https%3A%2F%2Fdiscuss.huggingface.co%2Ft%2Fthe-chat-is-not-working%2F191241)
**Author:** [@welsonri](/static-proxy?url=https%3A%2F%2Fdiscuss.huggingface.co%2Fu%2Fwelsonri)%5C **Replies:** 3\ **Last updated:** [November 3, 2026, 4:04pm UTC](/static-proxy?url=https%3A%2F%2Fdiscuss.huggingface.co%2Ft%2Fthe-chat-is-not-working%2F191241 "2026-11-03T16:04:23Z")
Hello, I made two top-ups of $10 each today, October 29th, but I’m unable to use them for my projects. The chat feature works for two of my projects, but for the other two, the following message appears: "Sorry, somethin… --- ## [Weighthouse: a self-hosted library for managing Hugging Face models](/static-proxy?url=https%3A%2F%2Fdiscuss.huggingface.co%2Ft%2Fweighthouse-a-self-hosted-library-for-managing-hugging-face-models%2F191351)
**Author:** [@toks-love](/static-proxy?url=https%3A%2F%2Fdiscuss.huggingface.co%2Fu%2Ftoks-love)%5C **Replies:** 3\ **Last updated:** [November 3, 2026, 3:31pm UTC](/static-proxy?url=https%3A%2F%2Fdiscuss.huggingface.co%2Ft%2Fweighthouse-a-self-hosted-library-for-managing-hugging-face-models%2F191351 "2026-11-03T15:31:42Z")
Hey folks, I wanted to share a project I’ve been working on called Weighthouse. A while back I started to hit my mental limit when it came to managing my local model collection by hand. I found and started using Hugging… --- ## [CMF: new, memory-mappable format for quantized LLMs](/static-proxy?url=https%3A%2F%2Fdiscuss.huggingface.co%2Ft%2Fcmf-new-memory-mappable-format-for-quantized-llms%2F191095)
**Author:** [@infosave](/static-proxy?url=https%3A%2F%2Fdiscuss.huggingface.co%2Fu%2Finfosave)%5C **Replies:** 2\ **Last updated:** [November 3, 2026, 3:30pm UTC](/static-proxy?url=https%3A%2F%2Fdiscuss.huggingface.co%2Ft%2Fcmf-new-memory-mappable-format-for-quantized-llms%2F191095 "2026-11-03T15:30:33Z")
CMF: a single-file, memory-mappable format for quantized LLMs Hi all, I’ve been building CMF (Cortiq Model Format) single-file container for quantized models with a Rust runtime. Most of the converted models live on th… --- ## [Open LLM API price history: 3 months of verified price changes (dataset + calculator Space)](/static-proxy?url=https%3A%2F%2Fdiscuss.huggingface.co%2Ft%2Fopen-llm-api-price-history-3-months-of-verified-price-changes-dataset-calculator-space%2F191216)
**Author:** [@AICostBudget](/static-proxy?url=https%3A%2F%2Fdiscuss.huggingface.co%2Fu%2FAICostBudget)%5C **Replies:** 2\ **Last updated:** [November 3, 2026, 3:12pm UTC](/static-proxy?url=https%3A%2F%2Fdiscuss.huggingface.co%2Ft%2Fopen-llm-api-price-history-3-months-of-verified-price-changes-dataset-calculator-space%2F191216 "2026-11-03T15:12:12Z")
We maintain an open dataset of LLM API list prices (about 100 models) where every row links to the provider’s official pricing page and carries the date it was verified. Since July we also log every change, so here is wh… --- ## [No ZeroGPU timer?](/static-proxy?url=https%3A%2F%2Fdiscuss.huggingface.co%2Ft%2Fno-zerogpu-timer%2F190883)
**Author:** [@JopaStepana](/static-proxy?url=https%3A%2F%2Fdiscuss.huggingface.co%2Fu%2FJopaStepana)%5C **Replies:** 2\ **Last updated:** [November 3, 2026, 3:09pm UTC](/static-proxy?url=https%3A%2F%2Fdiscuss.huggingface.co%2Ft%2Fno-zerogpu-timer%2F190883 "2026-11-03T15:09:11Z")
I wonder is there a timer when zeroGPU resets? I think 24h have passed and I still have my limits? It’s 40 min every day right or there is some other rules, cuz I’ve run out my 2$ credits or something, maybe it blocked m… --- ## [An AI coding agent deleted a live production database during a code freeze](/static-proxy?url=https%3A%2F%2Fdiscuss.huggingface.co%2Ft%2Fan-ai-coding-agent-deleted-a-live-production-database-during-a-code-freeze%2F191161)
**Author:** [@VivekNotes](/static-proxy?url=https%3A%2F%2Fdiscuss.huggingface.co%2Fu%2FVivekNotes)%5C **Replies:** 1\ **Last updated:** [November 3, 2026, 3:08pm UTC](/static-proxy?url=https%3A%2F%2Fdiscuss.huggingface.co%2Ft%2Fan-ai-coding-agent-deleted-a-live-production-database-during-a-code-freeze%2F191161 "2026-11-03T15:08:11Z")
SaaStr’s Jason Lemkin reported that Replit’s agent ignored explicit instructions not to alter code and deleted the database. It held records on 1,206 executives and 1,196 companies. At the time, Replit used the same data… --- ## [Help needed: Voice cloning for a specific artist (Victoria Beckham)"](/static-proxy?url=https%3A%2F%2Fdiscuss.huggingface.co%2Ft%2Fhelp-needed-voice-cloning-for-a-specific-artist-victoria-beckham%2F191228)
**Author:** [@Themuchacho](/static-proxy?url=https%3A%2F%2Fdiscuss.huggingface.co%2Fu%2FThemuchacho)%5C **Replies:** 1\ **Last updated:** [November 3, 2026, 3:00pm UTC](/static-proxy?url=https%3A%2F%2Fdiscuss.huggingface.co%2Ft%2Fhelp-needed-voice-cloning-for-a-specific-artist-victoria-beckham%2F191228 "2026-11-03T15:00:14Z")
“Hello everyone in the community! I hope I’m posting this in the right place. Could someone please help me with voice cloning for a specific artist? I’m a huge fan of Victoria Beckham and would love to generate some song… --- ## [Large source’s chunks are overrides small source’s chunks](/static-proxy?url=https%3A%2F%2Fdiscuss.huggingface.co%2Ft%2Flarge-source-s-chunks-are-overrides-small-source-s-chunks%2F191389)
**Author:** [@dipnitsan](/static-proxy?url=https%3A%2F%2Fdiscuss.huggingface.co%2Fu%2Fdipnitsan)%5C **Replies:** 1\ **Last updated:** [November 3, 2026, 2:58pm UTC](/static-proxy?url=https%3A%2F%2Fdiscuss.huggingface.co%2Ft%2Flarge-source-s-chunks-are-overrides-small-source-s-chunks%2F191389 "2026-11-03T14:58:54Z")
Hello guys, I got some serious issue in my RAG pipeline. Here is the case, I’ve already trained almost 10 large source urls (~1500 pages each), and then I’ve indexed one small pdf document which has hardly 5 chunks th… --- ## [A model passing a task is not proof that the system passed](/static-proxy?url=https%3A%2F%2Fdiscuss.huggingface.co%2Ft%2Fa-model-passing-a-task-is-not-proof-that-the-system-passed%2F191349)
**Author:** [@BrandenLaskowski7](/static-proxy?url=https%3A%2F%2Fdiscuss.huggingface.co%2Fu%2FBrandenLaskowski7)%5C **Replies:** 2\ **Last updated:** [November 3, 2026, 2:55pm UTC](/static-proxy?url=https%3A%2F%2Fdiscuss.huggingface.co%2Ft%2Fa-model-passing-a-task-is-not-proof-that-the-system-passed%2F191349 "2026-11-03T14:55:45Z")
If an AI worker produces the right answer while: using information it was not authorized to access, stepping outside its role, violating a required behavioral standard, or failing to preserve evidence of how the work w… --- ## [When 45 yuan is the right number but the wrong answer: four Chinese evidence-reading examples](/static-proxy?url=https%3A%2F%2Fdiscuss.huggingface.co%2Ft%2Fwhen-45-yuan-is-the-right-number-but-the-wrong-answer-four-chinese-evidence-reading-examples%2F191345)
**Author:** [@zhangsan-ai-1027](/static-proxy?url=https%3A%2F%2Fdiscuss.huggingface.co%2Fu%2Fzhangsan-ai-1027)%5C **Replies:** 2\ **Last updated:** [November 3, 2026, 12:28pm UTC](/static-proxy?url=https%3A%2F%2Fdiscuss.huggingface.co%2Ft%2Fwhen-45-yuan-is-the-right-number-but-the-wrong-answer-four-chinese-evidence-reading-examples%2F191345 "2026-11-03T12:28:25Z")
I help maintain 估号参谋, a valuation tool for the PC game 梦幻西游 (Fantasy Westward Journey). We made a small Chinese reading exercise from one public historical report. It exposed a distinction I’d want to check in a retrieva… --- ## [PT-BR typed-decision benchmark: 12 external models and an open evaluation/submission guide](/static-proxy?url=https%3A%2F%2Fdiscuss.huggingface.co%2Ft%2Fpt-br-typed-decision-benchmark-12-external-models-and-an-open-evaluation-submission-guide%2F191316)
**Author:** [@ajgcvm](/static-proxy?url=https%3A%2F%2Fdiscuss.huggingface.co%2Fu%2Fajgcvm)%5C **Replies:** 1\ **Last updated:** [November 3, 2026, 12:01pm UTC](/static-proxy?url=https%3A%2F%2Fdiscuss.huggingface.co%2Ft%2Fpt-br-typed-decision-benchmark-12-external-models-and-an-open-evaluation-submission-guide%2F191316 "2026-11-03T12:01:22Z")
Scoring update — 1 November 2026: the ranking now uses chance-corrected V2 scores, derived from the same published predictions. No datasets, checkpoints or model runs changed. The evaluator and submission JSON remain unc… --- ## [Paper claim is denied](/static-proxy?url=https%3A%2F%2Fdiscuss.huggingface.co%2Ft%2Fpaper-claim-is-denied%2F168460)
**Author:** [@iwasomen](/static-proxy?url=https%3A%2F%2Fdiscuss.huggingface.co%2Fu%2Fiwasomen)%5C **Replies:** 5\ **Last updated:** [November 3, 2026, 11:12am UTC](/static-proxy?url=https%3A%2F%2Fdiscuss.huggingface.co%2Ft%2Fpaper-claim-is-denied%2F168460 "2026-11-03T11:12:07Z")
I recently claimed authorship of my Arxiv paper 2501.15470 2508.20368 on Hugging Face, but the claim is denied. My secondary email is same as the one listed in the paper. Could you please check again? Thank you very … --- ## [Trying to figure out the best parameters!](/static-proxy?url=https%3A%2F%2Fdiscuss.huggingface.co%2Ft%2Ftrying-to-figure-out-the-best-parameters%2F191390)
**Author:** [@GeorgeZervas](/static-proxy?url=https%3A%2F%2Fdiscuss.huggingface.co%2Fu%2FGeorgeZervas)%5C **Replies:** 0\ **Last updated:** [November 3, 2026, 10:55am UTC](/static-proxy?url=https%3A%2F%2Fdiscuss.huggingface.co%2Ft%2Ftrying-to-figure-out-the-best-parameters%2F191390 "2026-11-03T10:55:58Z")
Hi,good morning. Anybody here to help? I am trying to successfully put 2 different objects(balls) into their matching basket. I have record almost 150 episodes but the results are not very good.Is it better to start with… --- ## [QLoRA on a code-repair dataset: eval loss rises after epoch 1 even with 2× more data. Early stopping, or mask the copied tokens?](/static-proxy?url=https%3A%2F%2Fdiscuss.huggingface.co%2Ft%2Fqlora-on-a-code-repair-dataset-eval-loss-rises-after-epoch-1-even-with-2x-more-data-early-stopping-or-mask-the-copied-tokens%2F191346)
**Author:** [@abdulwahid1111](/static-proxy?url=https%3A%2F%2Fdiscuss.huggingface.co%2Fu%2Fabdulwahid1111)%5C **Replies:** 3\ **Last updated:** [November 3, 2026, 10:38am UTC](/static-proxy?url=https%3A%2F%2Fdiscuss.huggingface.co%2Ft%2Fqlora-on-a-code-repair-dataset-eval-loss-rises-after-epoch-1-even-with-2x-more-data-early-stopping-or-mask-the-copied-tokens%2F191346 "2026-11-03T10:38:18Z")
I’m fine-tuning deepseek-coder-6.7b-instruct with QLoRA (4-bit NF4, r = 16, α = 32, all linear layers, dropout 0.05, LR 2e-4 cosine, warmup 3%, effective batch 16, paged\_adamw\_32bit, 3 epochs) for Java bug fixing. Each e… --- ## [Seeking Guidance on Custom USD Robot Simulation, Wheel Traction, and Physics Validation in NVIDIA Isaac Sim 6.1](/static-proxy?url=https%3A%2F%2Fdiscuss.huggingface.co%2Ft%2Fseeking-guidance-on-custom-usd-robot-simulation-wheel-traction-and-physics-validation-in-nvidia-isaac-sim-6-1%2F191356)
**Author:** [@Nimra28](/static-proxy?url=https%3A%2F%2Fdiscuss.huggingface.co%2Fu%2FNimra28)%5C **Replies:** 1\ **Last updated:** [November 3, 2026, 9:22am UTC](/static-proxy?url=https%3A%2F%2Fdiscuss.huggingface.co%2Ft%2Fseeking-guidance-on-custom-usd-robot-simulation-wheel-traction-and-physics-validation-in-nvidia-isaac-sim-6-1%2F191356 "2026-11-03T09:22:50Z")
Title: Seeking Guidance on Custom USD Robot Simulation, Wheel Traction, and Physics Validation in NVIDIA Isaac Sim 6.1 Hello Community, We are working on a custom autonomous service robot at Chore Robotics and using NV… [Next page](/static-proxy?url=https%3A%2F%2Fdiscuss.huggingface.co%2Flatest.md%3Fpage%3D1)