Checkout phi-4 from Microsoft, dropped a day ago... If you ❤️ the Phi series, then here is the GGUF - Sri-Vigneshwar-DJ/phi-4-GGUF. phi-4 is a 14B highly efficient open LLM that beats much larger models at math and reasoning - check out evaluations on the Open LLM.
❤️🔥Stranger Zone's MidJourney Mix Model Adapter is trending on the Very Model Page, with over 45,000+ downloads. Additionally, the Super Realism Model Adapter has over 52,000+ downloads, remains the top two adapter on Stranger Zone! strangerzonehf/Flux-Midjourney-Mix2-LoRA, strangerzonehf/Flux-Super-Realism-LoRA
Interesting Solution to the Problem of Misguided Attention
So I've been fascinated by the problem of Misguided Attention for a few weeks. I am trying to build an inference algorithm to help LLMs address that issue; but in the process, I found a cool short-term fix I call "Mindful Attention" using just prompt-engineering.
Have you ever thought about how our brains filter reality through layers of past experiences, concepts, and mental images? For example, when you look at an oak tree, are you truly seeing that oak tree in all its unique details, or are you overlaying it with a generalized idea of "oak tree"? This phenomenon inspired the new approach.
LLMs often fall into a similar trap, hence the Misguided Attention problem. They process input not as it’s uniquely presented but through patterns and templates they’ve seen before. This leads to responses that can feel "off," like missing the point of a carefully crafted prompt or defaulting to familiar but irrelevant solutions.
I wanted to address this head-on by encouraging LLMs to slow down, focus, and engage directly with the input—free of assumptions. This is the core of the Mindful Attention Directive, a prompt designed to steer models away from over-generalization and back into the moment.
And if you want to try this mindful approach in action, check out the LLM I’ve set up for testing: https://hf.co/chat/assistant/677e7ebcb0f26b87340f032e. It works about 80% of the time to counteract these issues, and the results are pretty cool.
I'll add the Gist with the full prompt. I admit, it is quite verbose but it's the most effective one I have landed on yet. I am working on a smaller version that can be appended to any System Prompt to harness the Mindful Attention. Feel free to experiment to find a better version for the community!
Just sharing a thought: I started using DeepSeek V3 a lot, and an idea struck me about agents "orchestrating during inference" on a test-time compute model like DeepSeek V3 or the O1 series.
Agents (Instruction + Function Calls + Memory) execute during inference, and based on the output decision, a decision is made to scale the time to reason or perform other tasks.
🎯Fine-tuning SmolLM2 on a lightweight synthetic reasoning dataset for reasoning-specific tasks. Future updates will focus on lightweight, blazing-fast reasoning models. Until then, check out the blog for fine-tuning details.
Combining smolagents with Anthropic’s best practices simplifies building powerful AI agents:
1. Code-Based Agents: Write actions as Python code, reducing steps by 30%. 2. Prompt Chaining: Break tasks into sequential subtasks with validation gates. 3. Routing: Classify inputs and direct them to specialized handlers. 4. Fallback: Handle tasks even if classification fails.
🎯Triangulum is a collection of pretrained and instruction-tuned generative models, designed for multilingual applications. These models are trained using synthetic datasets based on long chains of thought, enabling them to perform complex reasoning tasks effectively.
🎯The space handles documenting content from the input image along with standardized plain text. It includes adjustment tools with over 30 font styles, file formatting support for PDF and DOCX, textual alignments, font size adjustments, and line spacing modifications.
📄PDFs are rendered using the ReportLab software library toolkit.
🧪The datasets were prepared for a 3:2 aspect ratio by processing images of any dimension (width × height) in alignment with the adapter's concept. This involved using techniques such as magic expand, magic fill, or outpainting to adjust the remaining parts of the image to achieve the 3:2 ratio & posts training. This approach enhanced the desired image quality to up to 2 MB for detailed prompts and reduced artifacts in images sized at 1280 × 832.
🎈This approach was used instead of cropping down the 2x or 3x zoomed positions in the actual image. It generative filling to adjust the image's aspect ratio proportionally within the dataset.
🔧I used Canva's Magic Expand, Firefly's Generative Fill, and Flux's Outpaint for aspect ratio adjustments.
Fine-Textured [Polygon] Character 3D Design Renders 🙉
Adapters capable of providing better lighting control (Bn+, Bn-) and richer textures compared to previous sets require more contextual prompts for optimal performance.
The ideal settings are achieved at inference steps around 30–35, with the best dimensions being 1280 x 832 [ 3:2 ]. However, it also performs well with the default settings of 1024 x 1024 [ 1:1 ].
Llava o1 - vlm capable of spontaneous, systematic reasoning, similar to GPT-o1, 11B model outperforms gemini-1.5-pro, gpt-4o-mini, and llama-3.2-90B-vision Xkev/Llama-3.2V-11B-cot
Jina AI Jina CLIP v2 - general purpose multilingual and multimodal (text & image) embedding model, 900M params, 512 x 512 resolution, matroyoshka representations (1024 to 64) jinaai/jina-clip-v2
🍅 Glif App's Remixes feature allows you to slap a logo onto anything, seamlessly integrating the input image (logo) into various contexts. The result is stunning remixes that blend the input logo with generated images (img2img logo mapping) for incredible outcomes.
