Caleb Fahlgren @calebfahlgren.hf.co · 04/12/2024You can just ask things 🗣️ "show me messages in the coding category that are in the top 10% of reward model scores" Download really high quality instructions from the Argilla Llama3.1 405B synthetic dataset 🔥 040
Reposted by Caleb FahlgrenThomas Wolf @thomwolf.bsky.social · 04/12/2024Most liked and most downloaded open-source AI models from 2022 to 2024 Interactive viz: aiworld.eu/embed/model/... Discussion: huggingface.co/spaces/huggi... 28520
Caleb Fahlgren @calebfahlgren.hf.co · 02/12/2024The amazing, new Qwen2.5-Coder 32B model can now write SQL for any @hf.co dataset ✨ 1183
Caleb Fahlgren @calebfahlgren.hf.co · 29/11/2024This is insane! Structured generation in the browser with the new @hf.co SmolLM2-1.7B model • Tiny 1.7B LLM running at 88 tokens / second ⚡ • Powered by MLC/WebLLM on WebGPU 🔥 • JSON Structured Generation entirely in the browser 🤏 1111
Reposted by Caleb FahlgrenThomas Wolf @thomwolf.bsky.social · 26/11/2024Releasing SmolVLM, a small 2 billion parameters Vision+Language Model (VLM) built for on-device/in-browser inference with images/videos. Outperforms all models at similar GPU RAM usage and tokens throughputs Blog post: huggingface.co/blog/smolvlm 423131
Caleb Fahlgren @calebfahlgren.hf.co · 26/11/2024The OpenLLM Leaderboard just passed 2k evals 🥳 Here's a look at the distribution of average scores for all those models! Great work by the @huggingface.bsky.social team to do these evals! 1151
Caleb Fahlgren @calebfahlgren.hf.co · 21/11/2024Automatically tracking all Ollama requests to a dataset with the new observers python library! With just a few lines of code all your requests can be sent to @huggingface.bsky.social datasets for annotating, analysis and observability 🔭 060
Caleb Fahlgren @calebfahlgren.hf.co · 21/11/2024observers 🔭 - automatically log all OpenAI compatible requests to a dataset 💽 • supports any OpenAI compatible endpoint 💪 • supports @duckdb.org, @huggingface.bsky.social datasets and Argilla as stores > pip install observers 4135
Caleb Fahlgren @calebfahlgren.hf.co · 21/11/2024SmolTalk is out 🗣️ Over 1M high quality instructions used for training SmolLM2, one of the best small language models in the industry. huggingface.co/datasets/Hug...huggingface.coHuggingFaceTB/smoltalk · Datasets at Hugging FaceWe’re on a journey to advance and democratize artificial intelligence through open source and open science. 1101
Reposted by Caleb FahlgrenDavid Berenstein @davidberenstein.bsky.social · 21/11/2024Observers: A Lightweight SDK for AI Observability TLDR; - Track and record interactions with AI models - Store observations in multiple backends @huggingface.bsky.social, @duckdb.org or Argilla - Query and analyse your AI interactions with ease GitHub: github.com/cfahlgren1/o... 4427
Reposted by Caleb FahlgrenSimon Willison @simonwillison.net · 20/11/2024Foursquare just open sourced their 100 million place point of interest dataset! Some notes on poking around with it using DuckDB (it's Parquet files on S3) simonwillison.net/2024/Nov/20/...simonwillison.netFoursquare Open Source Places: A new foundational dataset for the geospatial communityI did not expect this! > [...] we are announcing today the general availability of a foundational open data set, Foursquare Open Source Places ("FSQ OS Places"). This base layer … 23458113
Caleb Fahlgren @calebfahlgren.hf.co · 21/11/2024Range requests + Parquet is what makes the Hugging Face SQL Console possible to query datasets entirely in the browser 010
Reposted by Caleb Fahlgrenarchie.md @archie.sarrewood.com · 21/11/2024duckdb-gsheets v0.0.3 is out, courtesy of @a13x.bsky.social the power is terrifying! duckdb-gsheets.com 2708
Reposted by Caleb Fahlgrenjsulz @jsulz.com · 20/11/2024When XetHub joined Hugging Face, we brainstormed how to share our tech with the community. The magic? Versioning chunks, not files, giving rise to: 🧠 Smarter storage ⏩ Faster uploads 🚀 Efficient downloads Curious? Read the blog and let us know how it could help your workflows!huggingface.coFrom Files to Chunks: Improving HF Storage EfficiencyWe’re on a journey to advance and democratize artificial intelligence through open source and open science. 13514
Caleb Fahlgren @calebfahlgren.hf.co · 20/11/2024Life would be so easy if @duckdb.org had an LLMs.txt 🤩 llmstxt.orgllmstxt.orgThe /llms.txt file – llms-txtA proposal to standardise on using an /llms.txt file to provide information to help LLMs use a website at inference time. 150
