abidlabs
Re:The Missed Opportunity of NAZA
on Thursday October 01, 2026 @11:41AM (#49923181)
Common Crawl Data Stored on a Hugging Face Bucket
Re:Show HN: I trained a 125M model to autocomplete piano on-device
on Thursday August 20, 2026 @11:54AM (#49376365)
Are the weights of the model available?
Re:Qwen 3.8 27B is out: open weights, best local dense model yet
on Friday August 14, 2026 @09:48PM (#49306826)
The Hugging Face page (https://huggingface.co/Qwen/Qwen3.8-27B) shows that Featherless supports the model (and includes the inference widget to try it out directly on the page)
Re:GitHub Actions Is Down
on Thursday August 06, 2026 @05:53PM (#49203119)
It's not too hard to switch over from GitHub actions to other runners. For example, I wrote up the steps needed in order to use Hugging Face Jobs instead, which also enables GPU runners and other flavors. I use this for several of the repos I manage (such as Trackio):
Re:Claude Opus 5
on Friday July 24, 2026 @06:47PM (#49042556)
I was curious to see how open weight models would do on this task so I passed in a screenshot of your source of truth and here's what 2 of the best code-generation models that allow image inputs do:
Inkling (not too great): https://cdn-uploads.huggingface.co/production/uploads/608b8b...
Kimi 2.7 (really well, esp. note that this is the predecessor model, not the latest Kimi3): https://cdn-uploads.huggingface.co/production/uploads/608b8b...
Here's how I tested them: https://huggingface.co/spaces/abidlabs/vlm-screenshot-to-web...
https://huggingface.co/spaces/abidlabs/vlm-screenshot-to-web...
Re:Startup founders urge Trump not to shut off Chinese open weight AI
on Thursday July 23, 2026 @11:54AM (#49023673)
Hugging Face recently added a filter directly on the models page: https://huggingface.co/models that lets you filter based on hardware.
Re:Startup founders urge Trump not to shut off Chinese open weight AI
on Thursday July 23, 2026 @11:54AM (#49023668)
Hugging Face recently added a filter directly on the models page: https://huggingface.co/models that lets you filter based on hardware.
Re:OpenAI and Hugging Face partner to address security incident
on Tuesday July 21, 2026 @05:40PM (#48998751)
If this doesn't put the nail in the coffin on the idea that we need closed-source models for the good of cybersecurity, I don't know what will
Re:Ask HN: Has anyone replaced Claude/GPT with a local model for daily...
on Monday June 15, 2026 @02:46PM (#48545398)
Re:Statement on US government directive to suspend access to Fable 5 a...
on Friday June 12, 2026 @09:15PM (#48511298)
Interesting to see Anthropic now downplaying the new vulnerabilities that Mythos discovered:
> We reviewed a demonstration of this specific technique being used to identify a small number of previously known, minor vulnerabilities. These vulnerabilities all appear relatively simple, and we have found that other publicly-available models are able to discover them as well without requiring a bypass
Re:Reviving Papers with Code
on Wednesday June 10, 2026 @01:41PM (#48479867)
Would you be interested in an RSS feed for: https://huggingface.co/papers/trending?
Re:Reviving Papers with Code
on Wednesday June 10, 2026 @12:50PM (#48479106)
You could subscribe to daily papers at the top here: https://huggingface.co/papers/trending
Re:S3 Files and the changing face of S3
on Tuesday April 07, 2026 @07:55PM (#47682869)
Hugging Face Buckets also recently added support for mounting Buckets as a filesystem: https://huggingface.co/changelog/hf-mount
Hugging Face Provides an S3 Alternative
Re:Hugging Face Provides an S3 Alternative
on Tuesday March 24, 2026 @06:54PM (#47510713)
The most interesting thing is that charges can be potentially much less if you have duplicated data in your bucket
Re:OpenRouter Broadcast
on Wednesday December 10, 2025 @09:17PM (#46226877)
Use Hugging Face inference providers for this: https://huggingface.co/docs/inference-providers/en/index
Re:Sequoia COO quit over Shaun Maguire's comments about Islamism
on Wednesday October 22, 2025 @03:31AM (#45665893)
Show HN: Jeopardy Labs as a Static Web App
https://abidlabs.github.io/staticjeopardy/
Hi folks! I love trivia and have built lots of jeopardy boards over the years with Jeopardy Labs. I recently discovered that Jeopardy Labs now requires a paid account to upload images to questions. I understand that they can charge for features at any time, since they have to pay for servers, etc. At the same time, since I already pay for Claude Code, I wondered how long it would take for me to...
Re:Open models by OpenAI
on Tuesday August 05, 2025 @01:30PM (#44801228)
Test it with a web UI: https://huggingface.co/spaces/abidlabs/openai-gpt-oss-120b-t...
Trackio: A new experiment tracking library from Hugging Face
Re:OpenAI Charges by the Minute, So Make the Minutes Shorter
on Wednesday June 25, 2025 @05:24PM (#44381963)
You could use Hugging Face's Inference API (which supports all of these API providers) directly making it easier to switch between them, e.g. look at the panel on the right on: https://huggingface.co/openai/whisper-large-v3
Journey to 1M Python Developers
Re:Show HN: Turn any Python function into a WebRTC/WebSocket stream
on Wednesday February 26, 2025 @04:22PM (#43188387)
Love the recipes and docs here, kudos on the launch!
FastRTC: Build realtime audio/video apps in Python
Re:Stable Fast 3D: Rapid 3D Asset Generation from Single Images
on Thursday August 01, 2024 @03:45PM (#41132813)
Official Gradio demo is here: https://huggingface.co/spaces/stabilityai/stable-fast-3d
Logical operators don't return boolean values in Python
Re:HuggingFace: Scaling open source community 300%/yr with No OKRs and...
on Tuesday July 16, 2024 @04:23PM (#40979975)
(b) growth is still the right metric imo. for example, lots of open-source libraries (which by definition are available to use for free) measure and optimize for growth
Re:HuggingFace: Scaling open source community 300%/yr with No OKRs and...
on Tuesday July 16, 2024 @04:21PM (#40979955)
We have ~220 total team members across all roles