Channel
Digests from Hugging Face
Tau is a Python port of the coding agent Pi, featuring a Textual TUI. It allows users to manage sessions as tree-structured data, export them as JSONL for analysis, and utilize skills and custom prompts.
Read article
The Kimi K3 model utilizes a complex training pipeline involving multi-tier on-policy distillation across nine specialized domain experts. Key innovations include partial rollout schemes and dynamic resource scheduling.
Read article
GRPO trains agents by sampling multiple completions per prompt and using the group's relative scores as the training signal. This method moves beyond imitation learning, allowing models to learn from their own varied trajectories.
Read article
Paid plans unlock private workspaces with versioning and lineage, SSO (SAML/OIDC), audit logs, and service accounts. Compute is billed separately from storage.
Read article
This advanced session dives into local AI inference engines, demonstrating how memory bandwidth and engine selection—not just hardware capacity—determine performance for LLMs. Learn to build robust, private, self-hosted AI stacks.
Read article
Learn how Asynchronous On-Policy Distillation (AsyncOPD) boosts training throughput by 2-3x, overcoming GPU blocking in conventional distillation methods.
Read article
Inkling is a massive, open-weight multimodal model with 1T parameters and 1M context window. It supports BF16/NVFP4 formats and integrates seamlessly with vLLM, SGLang, and llama.cpp for robust deployment.
Read article
Build Small revealed amazing hackathon winners, showcasing how small models (SLMs) can power massive utility. Learn about local-first AI, 64% offline capability, and advanced techniques like GGUF quantization.
Read article