Trending Repos
TrendingRisersNewestTopicsCollectionsCompare
TrendingRisersNewestTopicsCollectionsCompare
Trending Repos

Trending Repos tracks GitHub momentum from stars, forks, and rank history.

Explore

TrendingRisersNewestTopicsCollections

Tools

SearchCompareBadgesSubmit a repo

Project

AboutStatsDevelopersContactPrivacy
Back to trending
Phocinae/Phocinae-Largha-150M-v1 avatar

Phocinae/Phocinae-Largha-150M-v1

GitHub

斑海豹 — Phocinae-Largha-150M-v1: a 144.3M bilingual decision model. Tiny model. Big decisions. 小海豹,大决断。

Python500 stars1 forksApache-2.0
bilingualcalibrationcpu-inferencedecision-makingdecision-modellocal-inferencemodernbertoption-order-invariancesmall-modelstructured-decisionstext-classificationtyped-decisionszero-output-tokens

Momentum

Phocinae/Phocinae-Largha-150M-v1 has 500 GitHub stars. It gained +71 stars over 5 recorded days in the last 7 days (snapshots through Nov 4, 2026).

Its biggest recent day was Nov 3, 2026, with +20 stars.

It currently ranks #48253 daily, #48145 weekly, #2366 monthly by momentum on Trending Repos; its best-ever rank is #1014.

Trending Repos first recorded it on Oct 30, 2026.

Rankings

PeriodRankScore
Daily
#482530.0
Weekly
#481450.0
Monthly
#23663.8
How scoring works

Engagement

Total stars
Daily new stars
Recent daily star gains
DateStars gainedTotal starsForks gained
Nov 4, 2026+204940
Nov 3, 2026+204740
Nov 2, 2026+164540
Nov 1, 2026+124380
Oct 31, 2026+34260

Similar trending repositories

  • NandhaKishorM/layaNon-autoregressive System 1 decision engine. Typed choice, score and yes/no decisions over any text in a single forward pass, in 100+ languages, with a router that picks the right checkpoint per request.Python35,381 stars#442 this week
  • mizorewww/laya-mlxNative MLX runtime for Laya typed decision models — 7–14 ms short decisions on M3 Max. No text generation, PyTorch, or cloud API.Python7,089 stars#2605 this week
  • Valen-Team/ValenOpen, lightweight multimodal decision models for text, images, and video. Train and run them yourself.Python908 stars#3575 this week
  • alchaincyf/nuwa-skill你想蒸馏的下一个员工,何必是同事。蒸馏任何人的思维方式——心智模型、决策启发式、表达DNA。Distill how anyone thinks.Python38,025 stars#317 this week
  • synchopate/llama-modchip🐋 Run 284B DeepSeek-V4-Flash (<59GiB RAM, 44.4 tok/s pp, 9.1-14.7 tok/s) & 30B MoEs (25-111 tok/s) on a pure 64GB CPU at 256K ctx (0 GPUs). SwiGLU-H2, Stockfish-PVS L3 & 13ms Claude Code restore.Python918 stars#397 this week
  • jaredpalmer/kevJev-like family of decision models built on top of Qwen3.5/3.8 you can train and run on your ownPython9,942 stars#1026 this week

Embeds

Best rank #1014
Phocinae/Phocinae-Largha-150M-v1 badge
Markdown