Viewing profile — monatis

isanagent is opensource! I implemented an always-on and autonomous ML engineer that works 24/7 to conduct research, generate datasets, train models, learn and evolve. Works on Cola…

Yeah this is one possible way to generate grounded an"responses" in Afterimage. To accomplish context augmentation when generating a response, it allows to use different RAG strate…

We kept running into the same exact bottleneck with fine-tuning and evals: You have the source documents, and you have the base model, but you usually don’t have the actual convers…

We published a a distilled version of baai/bge-m3 with 8 layers. It provides 2.4x higher throughput with Pearson Cosine = 0.9691 and Spearman Cosine = 0.965. It quickly became our …

Extracting clean text from PDFs is still a mess. Tools like dockling and marker do a decent job—but they’re slow and resource-hungry. pymupdf4llm is fast, but it’s AGPL-licensed, w…

I implemented CLIP inference in plain C/C++ with no extra dependencies thanks to the great work in GGML that powers llama.cpp. It can work with models from both OpenAI and LAION. I…

Similarity search becomes a part of many technical stacks. Qdrant can be deployed as a service for fast, lightweight and filterable vector search. It's opensource, and you can also…

Great work, congrats. You might be already familiar with Qdrant, but feel free to reach out to me if you'd like to get help testing or discuss anything around it.

Some loss functions such as ArcFace loss and CosFace loss enforce the encoder model to organize their latent space in such a way that categories are placed with an angular margin f…

The main idea is to train a deep learning model to encode a high-dimensional sample to a low-dimensional vector in a latent space. Then it can be used in various downstream tasks s…

There's study here: http://cs230.stanford.edu/projects_spring_2021/reports/57.pd... Basically, you can collect text from different authors, then you can use authors names as labels…

I'm one of the authors of Quaterion and also a contributor of TF Similarity. First of all, Quaterion is based on PyTorch. From a more technical perspective, TF Similarity is curren…