Alternatives
Products that do what Quaterion – x100 faster fine-tuning of similarity learning models does
- 1
Qwen3.5 Small▲3590.8B-9B native multimodal w/ more intelligence, less compute
Mar 2026 · huggingface.co
- 2
- 3
- 4TW
Apr 2026 · github.com
- 58F
Hi HN! I'm just sharing a project I've been working on during the LLM Efficiency Challenge - you can now finetune Llama with QLoRA 5x faster than Huggingface's original implementation on your own local GPU. Some highlights: 1. Manual autograd engine - hand derived backprop steps. 2. QLoRA / LoRA 80% faster, 50% less memory. 3. All kernels written in OpenAI's Triton language. 4. 0% loss in accuracy - no approximation methods - all exact. 5. No change of hardware necessary. Supports NVIDIA GPUs since 2018+. CUDA 7.5+. 6. Flash Attention support via Xformers. 7. Supports 4bit and 16bit…
2023 · github.com
- 6FB
Hey there HN! We’re Antonio, Luca, and Yuhang, and we’re excited to introduce Fast GraphRAG, an open-source RAG approach that leverages knowledge graphs and the 25 years old PageRank for better information retrieval and reasoning. Building a good RAG pipeline these days takes a lot of manual optimizations. Most engineers intuitively start from naive RAG: throw everything in a vector database and hope that semantic search is powerful enough. This can work for use cases where accuracy isn’t too important and hallucinations are tolerable, but it doesn’t work for more difficult queries that…
2024 · github.com
- 7L3
I spent a lot of time and money on this rather big side project of mine that attempts to replicate the mechanistic interpretability research on proprietary LLMs that was quite popular this year and produced great research papers by Anthropic [1], OpenAI [2] and Deepmind [3]. I am quite proud of this project and since I consider myself the target audience for HackerNews did I think that maybe some of you would appreciate this open research replication as well. Happy to answer any questions or face any feedback. Cheers [1]…
2024 · github.com
- 8FV
I recently found myself computing the similarity between lots of very high dimensional vectors (i.e., sentence embedding vectors from LLMs), and I wanted to try some more powerful measures of similarity/dependency than just Cosine similarity, which seems to be the default for everything nowadays because of its computational efficiency. There are many other more involved measures that can detect more subtle relationships, but the problem is that some of them are quite slow to compute, especially if you're trying to do it in Python. For my favorite measure of statistical dependency,…
2023 · github.com
- 9Q2
Last week was big for open source LLMs. We got: - Qwen 2.5 VL (72b and 32b) - Gemma-3 (27b) - DeepSeek-v3-0324 And a couple weeks ago we got the new mistral-ocr model. We updated our OCR benchmark to include the new models. We evaluated 1,000 documents for JSON extraction accuracy. Major takeaways: - Qwen 2.5 VL (72b and 32b) are by far the most impressive. Both landed right around 75% accuracy (equivalent to GPT-4o’s performance). Qwen 72b was only 0.4% above 32b. Within the margin of error. - Both Qwen models passed mistral-ocr (72.2%), which is specifically trained for OCR. - Gemma-3…
2025 · github.com
- 10
- 11
- 12
Working on Mac, Linux, and Windows now. I include a simple GUI to find new models and get things built and set up. It is working quite well across a few models for me. The GitHub README and DESIGN.md files go into detail of the how/why and it's working remarkably well so far. https://github.com/notactuallytreyanastasio/shoehorn
19d ago · notactuallytreyanastasio.github.io
- 13TO
Mar 2026 · github.com
- 14LF
2024 · github.com
- 15AF
2024 · github.com
- 16
- 17UC
I built Unlearning Comparator, a visual analytics toolkit to help researchers and developers compare how different machine unlearning methods work. It provides a unified workflow to test for accuracy, efficiency, and privacy. You can check out the live demo linked in the post, and the source code is on GitHub: https://github.com/gnueaj/Machine-Unlearning-Comparator Our accompanying paper is currently under review at IEEE TVCG. Happy to answer any questions and would love to hear your feedback!
2025 · gnueaj.github.io
- 18RV
I use this library I made for Vectors and Quaternions in many personal projects. I've open-sourced it, in case anyone else would get use out of it. I use this on various projects, including quadcopter firmware, a graphics engine, a cosmology simulation, and several molecular dynamics applications. No_std compatible.
2025 · github.com
- 19
- 20VT
Hi everyone! I'm the author of this project. I wrote it because I think that the math that makes characters move in games and movies is incredibly beautiful, and I wanted to give others a glimpse into it. It's crazy to think that quaternions, an abstract mathematical tool discovered by William Rowan Hamilton in 1843, would be so perfectly suited to solve hard problems in the world of 3D character animation more than a hundred years later. The story of how he discovered quaternions is also beautiful. Here's an excerpt from Wikipedia: "Hamilton was looking for ways of extending complex numbers…
2022 · diegomacario.github.io
- 21FL
Hi HN community, I have been working on benchmarking publicly available LLMs these past couple of weeks. More precisely, I am interested on the finetuning piece since a lot of businesses are starting to entertain the idea of self-hosting LLMs trained on their proprietary data rather than relying on third party APIs. To this point, I am tracking the following 4 pillars of evaluation that businesses are typically look into: - Performance - Time to train an LLM - Cost to train an LLM - Inference (throughput / latency / cost per token) For each LLM, my aim is to benchmark them for…
2023 · github.com
- 22
- 23
- 24
Ranked by how close each launch is in meaning, then by votes. Refine with a description →