Models & Labs
Cohere Launches North Mini Code Model for Developers
Hugging Face Bloghigh confidence
Why it matters
- →North Mini Code offers advanced coding capabilities in a smaller, more efficient model.
- →It demonstrates superior performance in benchmarks, challenging larger models.
- →The model's availability on Hugging Face under an open-source license increases accessibility for developers.
Cohere has released North Mini Code, a 30 billion-parameter Mixture-of-Experts model tailored for developers, available on Hugging Face. This model is specifically optimized for agentic software engineering tasks, offering superior performance in complex code generation benchmarks compared to larger models. North Mini Code employs a unique training methodology involving supervised fine-tuning and reinforcement learning, enhancing its robustness and usability in real-world coding environments. This release positions North Mini Code as a strong open-source option for developers seeking advanced coding capabilities.
Read originalMore from Hugging Face Blog
© Hugging Face BlogResearchresearch
Benchmarking ASR on Code-Switched Speech
Hugging Face has created a benchmark to evaluate the effectiveness of voice agents in handling code-switched speech, a frequent occurrence among bilingual speakers. This benchmark assesses automatic speech recognition (ASR) systems across four language pairs, focusing on both transcription accuracy and semantic understanding. Models like ElevenLabs Scribe V2 and Assembly AI Universal 3-Pro lead in transcription accuracy, while Google Gemini 3 Flash excels in semantic metrics. This research addresses the challenges and variability in ASR performance on code-switched speech, providing a crucial tool for enhancing voice agent technology in enterprise settings.
Hugging Face Blog
© Hugging Face BlogAgentsagents
Agent Builds 3D Paris Gallery Using Hugging Face Spaces
An AI agent has effectively demonstrated the building block economy by creating a 3D gallery of Paris monuments through the integration of two Hugging Face Spaces. This innovative approach bypassed traditional tools, using the Spaces' APIs to automate image generation and 3D reconstruction. The process underscores a shift towards modular software development, where AI is adept at combining existing components rather than starting from scratch. This method not only simplifies the creation of multimedia applications but also significantly reduces the cost and effort needed to replicate or adapt the process for new projects. The agent's ability to seamlessly integrate these components marks a new era in multimedia software development, making it more accessible and efficient.
Hugging Face Blog
© Hugging Face BlogCoding Toolscoding
GitHub CI Migrates to Hugging Face Jobs
Hugging Face has introduced a new way to enhance GitHub CI workflows by running them on Hugging Face Jobs. This approach allows developers to leverage Hugging Face's serverless infrastructure, offering more reliable and faster CI processes, especially for GPU-intensive tasks. By integrating GitHub Actions with Hugging Face Jobs, projects like Trackio have reduced CI times by 30% and enabled GPU testing without maintaining dedicated hardware. This development provides a flexible and efficient alternative for developers needing specific hardware configurations for their CI pipelines.
Hugging Face Blog
More in Models & Labs
© The Verge AIModels & Labsmodels
Anthropic's Claude Fable 5 Limits Biology Queries
Anthropic's release of Claude Fable 5, touted as their most powerful AI model, comes with significant limitations in answering biology-related questions. This is due to the model's conservative safeguards designed to prevent misuse in bioweapons research. While the model excels in cybersecurity tasks, its biology filters are so stringent that even basic queries like 'what are mitochondria' are blocked. Anthropic aims to balance safety with utility, promising future adjustments to reduce false positives and potentially open up more capabilities for scientific research.
The Verge AI
© Google DeepMindModels & Labsmodels
Google DeepMind unveils DiffusionGemma for faster text generation
Google DeepMind's DiffusionGemma marks a significant shift in text generation by leveraging diffusion techniques to generate text blocks up to four times faster than traditional models. This 26B Mixture of Experts model, designed for speed-critical applications, moves beyond the sequential token-by-token approach, allowing for parallel generation of 256 tokens. While it offers blazing fast inference on GPUs, it trades off some quality compared to the standard Gemma 4 models. This innovation is particularly beneficial for developers working on real-time interactive AI applications, as it maximizes hardware utilization and reduces latency bottlenecks.
Google DeepMind
© GitHub ChangelogModels & Labsmodels
Claude Fable 5 now available in GitHub Copilot
Claude Fable 5, a new model from Anthropic's Mythos class, is now integrated into GitHub Copilot, offering enhanced capabilities for long-horizon coding and knowledge tasks. This model stands out by requiring data retention for safety purposes, a shift from the zero data retention policy of previous models. It promises more efficient coding workflows with fewer tool calls and lower token consumption. Available to select GitHub Copilot users, this rollout marks a significant step in autonomous coding, though it comes with new data handling considerations.
GitHub Changelog