Qwen 3.5 0.8B
PulseAugur coverage of Qwen 3.5 0.8B — every cluster mentioning Qwen 3.5 0.8B across labs, papers, and developer communities, ranked by signal.
3 day(s) with sentiment data
-
New methods enable LLM skill acquisition with minimal weight changes
Researchers have developed a new method called Deletion Tuning that can significantly alter a large language model's capabilities by modifying less than 0.1% of its weights. This technique, which involves zeroing out sp…
-
Off Grid AI Mobile updates iPhone app with expanded model support and commercial use
Off Grid AI Mobile (OGAM) has released an updated iPhone app that offers more functionality than MLC Chat, including the ability to run various open-source language models sized for mobile devices. Unlike MLC Chat, whic…
-
iPhone app simplifies local AI model selection with 'Fast', 'Balanced', 'Best' tiers
The Off Grid AI Mobile (OGAM) application has introduced a new feature for iPhones that simplifies the selection of local AI models. Users can now choose between 'Fast', 'Balanced', and 'Best' options, which automatical…
-
Android app simplifies local AI model selection for phones
The Off Grid AI Mobile (OGAM) app for Android has introduced a new feature that simplifies selecting local AI models based on a phone's RAM. The app now presents three curated options: Fast, Balanced, and Best, which au…
-
New 700M parameter model Shibai-700M-Base trained on 18B tokens
A user named TheOneWhoWill has pre-trained a 700 million parameter language model called Shibai-700M-Base. This model was trained on 18 billion tokens and is optimized for Python and Wikitext, with plans to further trai…
-
Research: Training duration impacts LLM merging effectiveness
A new research paper explores the impact of expert training duration on the effectiveness of merging multiple expert models into a single, more capable large language model. The study challenges the standard practice of…
-
AI hacks leverage LLMs for texting apps, game NPCs, and meme arbitrage
This article explores five AI-powered hacks that gained significant traction, focusing on their underlying problems, innovative solutions, and key takeaways. One hack involves an AI companion texting app that allows for…
-
MiniCPM5 1B emerges as a novel small language model
MiniCPM5 1B is a new, small language model that appears to be developed from scratch, distinct from previous MiniCPM versions which were fine-tuned on existing models like Qwen. This model features its own tokenizer and…
-
New datasets and AI methods advance autonomous driving research
Researchers have introduced several new approaches to enhance autonomous driving systems. One paper details TaCarla, a large dataset for end-to-end autonomous driving research, featuring over 2.85 million frames and sup…
-
Qwen 0.8B fine-tuned for AI content detection in Chrome extension
A developer has created a Chrome extension called "Slop Hammer" that uses a fine-tuned Qwen 0.8B model to detect AI-generated content. The model, trained on the Pangram dataset from their EditLens paper, runs locally an…