Web This site Trusted
9 result(s) for “okapi bm25 site hotchips pp site github com site vi do union it site can kernel site:huggingface.co” · 895 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)
com/InternLM/InternLM"},"canonical_setting_json":{"kind":"string","value":"{\"higher_is_better\": true, \"metric_type\": \"raw\", \"multimodal_input\": false, \"notes\": \"Per InternLM3 GitHub README
from the top result below
https://huggingface.co/datasets/microsoft/benchpress-score-matrix
00933 defines the full MCP-Atlas benchmark as 1,000 tasks over 36 real MCP servers and 220 tools; the ScaleAI/MCP-Atlas HF card and scaleapi/mcp-atlas GitHub repo expose the public release as 500 evaluation prompts/tasks, matching this MCPAtlas Public benchmark row
https://huggingface.co/papers?q=reflective%20essays
","upvotes":3,"discussionId":"6679affcf926ce3cf48fd0d1","githubRepo":"https://github
https://huggingface.co/docs/hub/jobs-popular-images
A uv run --system-site-packages that would reuse the image’s packages and skip the reinstall is requested upstream
https://huggingface.co/papers?q=companion
It is\nfound that the lower limit of binarity is 30
https://huggingface.co/JianyuanWang/skyseg/resolve/main/skyseg.onnx
1 1967 19681966Conv_0"Conv* dilations@@ * group * kernel_shape@@ * pads@@@@ * strides@@ 1966801Relu_1"Relu ƒ 801 1970 19711969Conv_2"Conv* dilations@@ * group * kernel_shape@@ * pads@@@@ * strides@@ 1969804Relu_3"Relu l 804
https://huggingface.co/docs/hub/repositories-github-actions
For keyless publishing — no HF_TOKEN secret to store or rotate — see Trusted Publishers, which exchanges GitHub Actions’ built-in OIDC token for a short-lived, repo-scoped Hub token at the start of each run
https://huggingface.co/papers?q=persona
Our findings reveal a critical trade-off: while PP can improve classification in socially-sensitive tasks, it often comes at the cost of rationale quality and fails to mitigate underlying biases, urging caution in its application
https://huggingface.co/papers/trending
Hugging Face
Models
Datasets
Spaces
Buckets new
Docs
Enterprise
Pricing
Website
Tasks
HuggingChat
Collections
Languages
Organizations
Community
Blog
Posts
Daily Papers
Hardware
Learn
Discord
Forum
GitHub
Solutions
Team
https://huggingface.co/papers?q=role-play
000Z","title":"Reward-Decomposed Reinforcement Learning for Immersive Video Role-Playing","summary":"Text-based role-playing models can imitate character styles, but often fail to capture scene atmosphere and evolving tension, which are crucial for immersive applications such as VR games and interactive narratives