qwen-2.5-0.5b-block-transformer-hiba-wikitext2
tahamajs · Kit
Swaps 18 of the 24 attention layers in Qwen2.5-0.5B for a hierarchical block attention operator, then distills it on WikiText-2. A research checkpoint for stud…
Prompts and agents that read the sources on a question and tell you what each one says.
tahamajs · Kit
Swaps 18 of the 24 attention layers in Qwen2.5-0.5B for a hierarchical block attention operator, then distills it on WikiText-2. A research checkpoint for stud…
tahamajs · Kit
Swaps 18 of the 24 attention layers in Qwen2.5-0.5B for a mixture-of-experts attention block, then distills it on WikiText-2. A research checkpoint for studyin…
HuggingFaceBio · Kit
Reads raw DNA inside a chat and answers in English, judging whether variants look benign or pathogenic, for researchers who want a DNA language model on their…
errrinn · Kit
Chats in a quirky chat-speak voice after a ban on word pairs common in Simple Wikipedia. A 4.3B-parameter Gemma 3 experiment for people curious about constrain…
Shriharshan · Kit
A chatbot about autism that finds passages in a stored vector database and passes them to a small language model to answer. Suits developers and students study…
malmarri · Kit
Chats about how Qatari laws and economic indicators influence one another, and what a change to a law could do for growth and the NDS3 2030 targets, for policy…
lixin4ever · Kit
A chat app for understanding media such as video, built on the VideoLLaMA2 models. Runs in the browser as a Gradio app on ZeroGPU, for people who want to ask q…
EarthSpeciesProject · Kit
A demo where you upload an audio file of animal sounds and ask questions about it in a chat. It runs the NatureLM-audio model and opens in a browser with nothi…
open-llm-leaderboard · Kit
Ranks and compares open large language models in a React page with sorting, filtering, search and pinning. For people choosing or evaluating open models and ch…
n8n workflow
An n8n workflow that answers questions about a PDF and shows where each answer came from. Each reply ends with the file name and line range of every Pinecone p…
An n8n workflow that turns a chat question into a research report. A model proposes search queries, SerpAPI runs them, Jina reads the result pages, and a third…
An n8n workflow that answers a chat question from your own OpenAI vector store and writes the name of each source file into the answer, right after the passage…
An n8n workflow you chat with. Give it an n8n creator’s username, and an OpenAI agent reads that creator’s public weekly and monthly numbers and writes a Markd…
An n8n chat where you name a niche. An agent searches YouTube for videos from the last two days, looks each one up for views, likes and tags, and reports what…
An n8n workflow that reads a web page through Jina, asks an OpenAI chat model to pick out each listing on it, and adds one Google Sheets row for each. It comes…
An n8n workflow with a chat window. An OpenAI agent answers your questions, searches Google through SerpApi for recent facts, looks topics up in Wikipedia, and…
n8n workflow
An n8n workflow with a chat agent that can open web pages. Its tool downloads an address, strips scripts and styles, turns the page into Markdown and hands it…