#finetuning

Live, measured metrics for the hashtag #finetuning from the open social web. Every number carries a named source and the time it was fetched. Nothing is estimated.

hashtag.org network · sponsored

Own #finetuning

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.

$23.52/ year · 10-character #name
Claim #finetuning — $23.52/yr→
Annual, renews each year
Buy on hashtag.space (web3)
one-timepay once, yours for life
card via hashtag.org · tokens via hashtag.space
5
Uses / 7 days
Mastodon
3
Accounts / 7 days
Mastodon
40
Recent posts
Mastodon
~0/hr
Recent pace
Mastodon · last 40
0
Avg reactions / post
Mastodon · last 40

Day-by-day usage

measured · fosstodon.org (Mastodon public tags API) · fetched 2026-07-27 00:12 UTC
1
07-21
0
07-22
0
07-23
1
07-24
3
07-25
0
07-26
0
07-27

5 uses by 3 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 2026-07-27 00:12 UTC
#finetuningtraining
5 uses · 5 accounts / 7d
#lora_finetuning
0 uses · 0 accounts / 7d
#finetuningproblem
0 uses · 0 accounts / 7d
#instruction_finetuning
0 uses · 0 accounts / 7d
#finetuningchinesium
0 uses · 0 accounts / 7d
#supervised_finetuning
0 uses · 0 accounts / 7d
#finetuningfail
0 uses · 0 accounts / 7d
#finetuningllmson
0 uses · 0 accounts / 7d
#llama2finetuning
0 uses · 0 accounts / 7d
#rejection_sampling_finetuning
0 uses · 0 accounts / 7d
#finetuningargument
0 uses · 0 accounts / 7d
#finetuningai
0 uses · 0 accounts / 7d

Live pulse

measured · fosstodon.org (Mastodon tag timeline) · fetched 2026-07-27 00:12 UTC

Everything below is measured over the latest 40 public posts (spanning ~811 hours).

Posting hours (UTC) — busiest: 01:00

00:0012:0023:00

Languages: English (38) · Russian (2)

Avg boosts / post: 0.5

Top of the latest posts

  • Can you safely put false or harmful text in finetuning data if you clearly label it as false? A new paper says no. Train a model on documents that repeatedly warn a claim is fabricated, and it still asserts the claim as true afterward, up f

    Benjamin Han@[email protected]♥ 1↻ 132026-07-05 06:59 UTCView post →

  • Ivan Fioravanti ᯅ (@ivanfioravanti) Unsloth의 DeepSeek-V4 로컬 실행 가이드가 소개됐다. 작성자는 모델 실행·파인튜닝 가이드의 세부 내용이 잘 정리돼 있다고 평가했으며, DeepSeek-V4 Flash를 단일 Apple M3 Ultra(512GB) 환경의 Unsloth Studio에서 실행할 계획이라고 밝혔다. https://x.com/ivanfioravanti/status/20809

    ainews@[email protected]♥ 0↻ 02026-07-25 20:51 UTCView post →

  • Lee Robinson (@leerob) 오픈 모델 대 폐쇄형 모델 논쟁을 단순 공개성 문제가 아니라 '관리형(managed) AI 인프라 대 자체 호스팅(self-hosted) AI 인프라'의 선택으로 봐야 한다고 제안한다. 오픈 웨이트 모델은 기업이 추가 학습·맞춤화·운영 통제를 원할 때 특히 의미가 있다는 관점이다. https://x.com/leerob/status/2080673380336886212 #openmodels

    ainews@[email protected]♥ 0↻ 12026-07-25 11:52 UTCView post →

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/finetuning