I Built a UI to finetune LLMs x100 faster

I've been playing around with https://github.com/zphang/minimal-llama/ and https://github.com/tloen/alpaca-lora/blob/main/finetune.py, and wanted to create a simple UI where you can just paste text, tweak the parameters, and finetune the model quickly using a modern GPU. To prepare the data, simply separate your text with two blank lines. There's an inference tab, so you can test how the tuned model behaves. This is my first foray into the world of LLM finetuning, Python, Torch, Transformers, LoRA, PEFT, and Gradio. Enjoy!

Thesys just open-sourced their generative UI rendering engine. Interesting timing given where Google a2ui and Vercel's json-render are headed. The difference worth noting: a2ui and json-render both treat JSONL as the contract between the LLM and the renderer. Thesys is betting that's the wrong primitive. Their engine uses a code-like syntax (OpenUI Lang) instead — LLM writes it, renderer executes it. The argument is that LLMs are fundamentally better at generating code than generating structured data, so you get cleaner output and ~67% fewer tokens. The broader vision seems to be a…

All LLM user interfaces I've seen so far are somewhat frustrating: * ChatGPT web requires a lot of copy-paste, it rewrites whole document even if you need to update a part of it, etc. * Github Copilot completions are rather unreliable and do not leave an option to specify what you want; Copilot's chat sidebar is little more than ChatGPT integrated into the IDE * Google Docs have right UI for non-code text, but they use really dumb model (not Gemini 1.5 Pro). Also won't work for code. So... I wrote a Emacs Lisp function which calls LLM with contents of the buffer to generate text according to…

Hi HN, While building RAG agents, I noticed a lot of token budget was wasted on formatting overhead (HTML tags, JSON structure, whitespace). Existing solutions felt too heavy (often requiring torch&#x2F;transformers), so I wrote this lightweight, zero-dependency library to solve it. It includes strategies for context packing, PII redaction, and tool output compression. Benchmarks show it can save ~15% of tokens with negligible latency overhead (<0.5ms). Happy to answer any questions!

Hey HN! I built Experiment to solve a common frustration in LLM development: the lack of proper tools for prompt engineering experimentation. Here's what makes it different: Key Features: - Load and edit chat completion logs from CSV files - Fork and modify specific conversation entries - Run inference via Anthropic, Mistral, and OpenAI - Define custom tools using JSONSchema format - Visual tool usage analysis with collapsible, sorted key-value pairs - Full mobile support and available as installable PWA Technical Highlights: - Built with React using custom isomorphic architecture -…

With the latest launch from Google I've added support for Gemma 3 270M, the speed for local LLM to TTS token time is incredible! This is an heavy obvious work in progress - any contributions or tips would be welcome. The idea is to have a fast moving edge model playground, and maybe have some utility (like the e reader) on the side.