Web This site Trusted
30 result(s) for “okapi bm25 site hotchips pp site github com site text of de site huggingface co site:huggingface.co” of 98 matched · page 2 · 1342 ms
Scope: Nishi’s own index (our crawl + Common Crawl) — not the whole live web. Some sites block all automated crawlers (anti-bot walls), so their pages may be absent here even though we never filter lawful content.
Freshness: no result on this page carries a fetch time yet (indexed before the fetch epoch was stored beside the doc)
https://huggingface.co/Mozilla
co/v1/production/uploads/657f3d21f4f72f2c4c51d2ca/EUpt1X9P3BSaLHehRDEd
https://huggingface.co/docs/hub/models-uploading
Models on the Hub are Git-based repositories, which give you versioning, branches, discoverability and sharing features, integration with dozens of libraries, and more
https://huggingface.co/docs/hub/agents-overview
Cursor / VS Code / Zed:
Visit huggingface
https://huggingface.co/Mozilla/datasets
co/v1/production/uploads/657f3d21f4f72f2c4c51d2ca/EUpt1X9P3BSaLHehRDEd
https://huggingface.co/docs/hub/models-inference
Inference Providers give developers streamlined, unified access to hundreds of machine learning models, powered by the best serverless inference partners
https://huggingface.co/Mozilla/tinybert-address-autofill
Given a string describing a single form field's attributes, it predicts one of 66 autofill field types (given-name, family-name, email, postal-code, address-line1, cc-number, etc
https://huggingface.co/Mozilla/models
co/v1/production/uploads/657f3d21f4f72f2c4c51d2ca/EUpt1X9P3BSaLHehRDEd
https://huggingface.co/Mozilla/whisperfile
Quickstart
Running the following on a desktop OS will transcribe the speech of a wav/mp3/ogg/flac file into text
https://huggingface.co/docs/hub/data-studio
The text is searched in the columns of string, even if the values are nested in a dictionary or a list
https://huggingface.co/Grogros/Llama-3.2-1B-distillation-alpaca-5.0-AlpacaRefuse-sauce1-PT2/discussions
strip() + ' [/INST][ASST] ' }}\n {%- elif message['role'] == 'assistant' %} \n {{- message['content'] + ' [/ASST]' + eos_token }}\n {%- endif %}\n{%- endfor %}","eos_token":"<|end_of_text|>","pad_token":"<|end_of_text|>"}},"createdAt":"2025-05-11T10:02:02
https://huggingface.co/organizations/Mozilla/activity/all
co/v1/production/uploads/657f3d21f4f72f2c4c51d2ca/EUpt1X9P3BSaLHehRDEd
https://huggingface.co/datasets/commoncrawl/web-graph-embeddings/discussions
9 M / ~19 % induced subgraph that carries ~97 % of the edges
https://huggingface.co/docs/hub/jobs-examples
com/huggingface/transformers/main/examples/pytorch/image-classification/run_image_classification
https://huggingface.co/docs/hub/organizations-cards
An organization card is displayed on an organization’s profile:
If you’re a member of an organization, you’ll see a button to create or edit your organization card on the organization’s main page
https://huggingface.co/docs/hub/models-widgets
The type of widget displayed (text-generation, text to image, etc) is inferred from the model’s pipeline_tag, a special tag that the Hub tries to compute automatically for all models
https://huggingface.co/docs/hub/datasets-upload-guide-llm
The CLI matches the installed huggingface_hub version, so prefer its output over flags recalled from memory
https://huggingface.co/docs/hub/datasets-cards
Generally, dataset cards help users understand the contents of the dataset and give context for how the dataset should be used
https://huggingface.co/docs/hub/model-release-checklist
co/org/model-name), makes search easier, and provides download counts for each one of your models
https://huggingface.co/docs/hub/model-cards
How to fill out each section of the model card is described in the Annotated Model Card
https://huggingface.co/koboldcpp/music/tree/main
/llama-cli -hf koboldcpp/music:Q4_K_M
Build from source code
git clone https://github
https://huggingface.co/Mozilla/TriLM-llamafile
58 bit ternary LLM whose weights consist of {-1, 0, +1}
https://huggingface.co/docs/hub/spaces-changelog
In Space settings, visibility is now set through a dropdown with three options instead of a simple public/private toggle
https://huggingface.co/Mozilla/Llama-3.2-1B-Instruct-llamafile
Both of them are included in a single file, which can be downloaded and run as follows:
wget https://huggingface
https://huggingface.co/Mozilla/Llama-3.2-3B-Instruct-llamafile
Both of them are included in a single file, which can be downloaded and run as follows:
wget https://huggingface
https://huggingface.co/datasets/Mozilla/smart-form-fill-value-generation
\\n\\nWho Can Use SSNVS\\n- Employers with a valid Employer Identification Number (EIN)\\n- Third-party payroll providers and authorized submitters with the employer’s permission\\n- Authorized users acting on behalf of a single employer or multiple client employers\\n\\nImportant Use Limitations\\n- Use SSNVS only
https://huggingface.co/docs/hub/agents-skills
Hugging Face provides a curated set of Skills built for AI builders
https://huggingface.co/tarekziade
42k • • 3
tarekziade/pardonmyai-tiny
Text Classification • 14
https://huggingface.co/docs/hub/storage-buckets-integrations
parquet"])
Inspect AI
Inspect AI can write evaluation logs directly to a bucket — point its log directory at an hf://buckets/ path (requires huggingface_hub>=1
https://huggingface.co/docs/hub/local-cache
Here is a partial list of libraries and applications that use this cache layout
https://huggingface.co/docs/hub/datasets-adding
A public dataset is visible to anyone, whereas a private dataset can only be viewed by you or members of your organization