0xSojalSec

Activity

Stars and mentions · Last 30 days, Oct 9 – Nov 7

GitHub stars28
Mentions12
02468Oct 9Oct 23Nov 7
UTC days · repositories 0xSojalSec owns9 repositories

Top repositories

0xSojalSec’s repositories ranked by new forks, as on trending.

Loading

Contributes to

Repositories outside 0xSojalSec’s account where 0xSojalSec opened or reviewed pull requests in the past 365 days.

Who noticed 0xSojalSec

Everyone who starred or forked 0xSojalSec’s repositories since the archive began in 2011.

Notable accounts

Ordered by the stars their own repositories have received.

Biggest fans

Accounts that starred the most of these repositories.

Breakout weeks

Each repository’s best week of new stars, with the release published around it.

Mentions

13posts
Nov 82 posts
  1. 区区 4GB 显存,竟要硬跑 70B 的大模型,这还真叫 AirLLM 给办妥了。 它使的招数叫分层推理:不把整个模型一口气灌进显存,而是逐层往里加载,算完一层便卸掉,生生把个庞然大物塞进了张小破卡里。 这项目百分百开源, 🔗 0xSojalSec/airllm t.co

    9 likes · 1 repost · 819 views
  2. 4GB显存,竟然也能跑70B大模型 不是魔法,是AirLLM把模型拆成一层一层来算 用到哪一层就加载哪一层,算完立刻释放显存,硬是把原本只能在高端显卡上跑的巨无霸,塞进了小显存显卡 更离谱的是,它还是100%开源 低配党直接白嫖,显卡厂商看了都沉默 0xSojalSec/airllm t.co

    5 likes · 1 repost · 274 views
  3. 70B的大模型真能塞进4GB显存的卡里跑?AirLLM给出的答案是能。 它走的思路叫分层推理:不把整个模型一股脑塞进显存,而是一层一层往里加载,算完一层就丢掉,硬是把巨无霸塞进了小破卡。 更妙的是它100%开源,白蹭警告。 链接:0xSojalSec/airllm t.co

    13 likes · 1 repost · 1,363 views
  4. 4GB显存跑70B大模型,这事还真被AirLLM办成了。 它玩的招叫分层推理:不把整个模型一股脑塞进显存,而是一层一层往里加载,算完一层就甩掉,硬是把巨无霸塞进小破卡。 更骚的是100%开源,白蹭警告。 🔗 0xSojalSec/airllm t.co

    2 likes · 340 views
  5. GTA IV is finally running natively in 4K on PS5. Clean performance, Not emulation a proper recompilation running directly on the console, and the city of Liberty looking sharper than ever. PS3 games can run natively on PS5. - elripalda/RecompStore t.co

    5 likes · 1 repost · 917 views
  6. YouTube · · YouTube description · GitFinds · 0xSojalSec/LLMs-local

    GitFinds - Top 10 AI GitHub Repos This Week (Week of Oct 12) GitFinds: Top 10 AI GitHub Repos This Week for Week of Oct 12. Top GitHub repos. Handpicked. Research-based overview, not a hands-on test or independent benchmark. These are this week's selections, not a claim that every project was released this week. Statistics are a production-time snapshot. Check each project's license and backend configuration before reuse. Repos: #10: garylab/MakeMoneyWithAI - garylab/MakeMoneyWithAI #9: 0xSojalSec/LLMs-local - 0xSojalSec/LLMs-local #8: danielrosehill/Local-AI-Agent-Resources - danielrosehill/Local-AI-Agent-Resources #7: zylon-ai/private-gpt - zylon-ai/private-gpt #6: lutelute/local-cli - lutelute/local-cli #5: morluto/rea - morluto/rea #4: firecrawl/firecrawl - firecrawl/firecrawl #3: JuliusBrussee/caveman - JuliusBrussee/caveman #2: paperclipai/paperclip - paperclipai/paperclip #1: unclecode/crawl4ai - unclecode/crawl4ai AI-assisted production. Narration generated with Boson Higgs Audio v3 using our Kiki channel reference voice. Fresh repos, fewer tabs, slightly less despair.

    115 views

Achievements

Awards earned by the repositories 0xSojalSec owns. Select an award to embed its badge.

Gold
31st place finishes
Silver
22nd place finishes
Bronze
13rd place finishes
Awarded repositories
4Owned by 0xSojalSec now

Repositories

Ordered by gold, then silver, then bronze.

  1. facebook-scraperBest: 1st by forks, 1 forks200
  2. metisBest: 1st by forks, 1 forks100
  3. GPTsBest: 2nd by forks, 1 forks020
  4. Auto-Deep-ResearchBest: 3rd by forks, 1 forks001

Every award

Top-three finishes of these repositories in completed trending days and weeks, newest first.

  1. metis
  2. facebook-scraper
  3. facebook-scraper
  4. GPTs
  5. GPTs
  6. Auto-Deep-Research

A repository earns an award for finishing first, second or third in a completed trending day or week, ranked by new stars, new forks or pull request authors. Awards follow a repository through renames and transfers and count toward its current owner. Weeks run Monday to Sunday, UTC.