#SFT
Live, measured metrics for the hashtag #SFT from the open social web. Every number carries a named source and the time it was fetched. Nothing is estimated.
Own #sft
This #name is available to claim. It becomes your portal on the open agent web: this very page, a keyword you rank for by an open public stake, and a verifiable identity for AI agents. Nobody else sells a page like this for every #name.
Day-by-day usage
measured · fosstodon.org (Mastodon public tags API) · fetched 2026-11-11 20:11 UTC1 uses by 1 unique accounts across the window. Real per-day counts, not estimates. Newest bar is today so far.
Related hashtags
measured · fosstodon.org (Mastodon public search API) · fetched 2026-11-11 20:11 UTCLive pulse
measured · fosstodon.org (Mastodon tag timeline) · fetched 2026-11-11 20:11 UTCEverything below is measured over the latest 32 public posts (spanning ~33144 hours).
Posting hours (UTC) — busiest: 17:00
Languages: Russian (19) · English (12) · French (1)
Avg boosts / post: 0.3
Top of the latest posts
Языковая модель с нуля на одной RTX 4060: dpp-gpt 2.2 Pro (260M), претрейн, SFT и RL Обучил с нуля языковую модель на 260M параметров на одной домашней видеокарте: претрейн на 31 млрд токенов, SFT и RL. Рассказываю, как она устроена, что ум
Avi Chawla (@_avichawla) 수학 문제처럼 정답을 검증할 수 있는 과제를 예로 들어 SFT, DPO, RLVR의 차이를 설명한다. SFT는 프롬프트와 이상적인 완료문을 정답 데이터로 학습하는 반면, DPO와 RLVR는 서로 다른 형태의 선호도·검증 보상을 활용해 LLM을 맞춤화한다는 점을 다룬다. https://x.com/_avichawla/status/2110283567729352736 #llm #finetu
Учим небольшую LLM с нуля: гибридное внимание, XSA, доменные бленды и загадки роста онлайн-бенчмарков Обучение LLM — это в первую очередь инфраструктурная задача: нужен пайплайн, который можно перезапускать с новыми данными, архитектурой ил
#sft across platforms
every network with a public tag surfaceFollow #sft straight to each platform’s own tag page. Where a platform publishes open data we measure it above; the rest lock their numbers behind paid APIs, so we link rather than guess.
Every number above is measured from a named public API at the shown fetch time. Nothing is estimated or extrapolated. Platforms that lock their data behind paid APIs are not shown. Agents: the same numbers, as JSON, at /api/hashtags/sft