Topic · 8 stories
hugging-face 8 stories tagged hugging-face on AI Tamer, newest first.
No.1488 Hugging Face Inference Providers now send LLM calls via OpenRouter, with retries and :fastest or :cheapest routing. Your own provider keys no longer work.
No.1471 ggml-org tags llama.cpp and ggml v1.0.0 and promises major-version bumps for any breaking change to the public C API, which helps every app built on them.
No.1378 Hugging Face's harness adapters are LoRA weights trained with RL inside unmodified pi, opencode and hermes, with safeagents vetting every tool call.
No.1332 A real-robot benchmark from NUS, Hugging Face, BitRobot and partners: blinded A/B trials, every run on the Hub, and 10,000 free evaluation hours.
No.1226 A 9B multimodal model that stores 32 layers but executes 56, under Apache 2.0. Transformers only for now, with trust_remote_code. What the card says.
No.1146 hf-xet 1.8.0 can push upload chunks directly to S3 through short-lived grants, rolled out gradually by the Hub. Here is the allowlist and the opt-out.
No.1098 A 3.3B-parameter open model with a fixed set of attention references. Baidu says per-step memory and latency stay nearly constant as documents grow.
No.1047 Rockbridge Network Korea: 49.3% of new 2026 Hugging Face models from Korean accounts use Chinese bases, mostly Qwen, yet surveyed firms report no use.