Georgi Gerganov 成立公司 GGML
source link: https://blog.gslin.org/archives/2023/06/07/11212/georgi-gerganov-%e6%88%90%e7%ab%8b%e5%85%ac%e5%8f%b8-ggml/
Go to the source link to view the article. You can view the picture content, updated content and better typesetting reading experience. If the link is broken, please click the button below to view the snapshot at that time.
Georgi Gerganov 成立公司 GGML
Hacker News 首頁上看到 Georgi Gerganov 成立公司的計畫：「GGML – AI at the Edge (ggml.ai)」，官網在「GGML - AI at the edge」。
如同 Georgi Gerganov 提到的，llama.cpp 這些專案本來是他的 side project，結果意外的紅起來：
I've started a company: https://t.co/jFknDoasSy
From a fun side project just a few months ago, ggml has now become a useful library and framework for machine learning with a great open-source community
— Georgi Gerganov (@ggerganov) June 6, 2023
另外他提到了 Nat Friedman 與 Daniel Gross 也幫了一把：
I'm incredibly grateful to @natfriedman and @danielgross for the support & funding and also for helping me get inspired even more in this project
There is still a long way ahead with many ideas to try and cool things to do. Hope you will join and help us create something useful!
— Georgi Gerganov (@ggerganov) June 6, 2023
在官網則是有提到是 pre-seed funding：
ggml.ai is a company founded by Georgi Gerganov to support the development of ggml. Nat Friedman and Daniel Gross provided the pre-seed funding.
現在回頭來看，當初 llama.cpp 會紅起來主要是因為 CPU 可以跑 LLaMA 7B，而且用 CPU 跑起來其實也不算慢。
後來吸引了很多人一起幫忙，於是有了不少 optimization (像是「llama.cpp 的載入速度加速」這邊用 mmap 減少需要載入的時間，並且讓多個 process 之間可以重複使用 cache)，接下來又有 GPU 的支援...
但不確定他開公司後，長遠的計畫是什麼...？
Related
llama.cpp 開始支援 GPU 了
前陣子因為重灌桌機，所以在重建許多環境... 其中一個就是 llama.cpp，連到專案頁面上時意外發現這兩個新的 feature： OpenBLAS support cuBLAS and CLBlast support 這代表可以用 GPU 加速了，所以就照著說明試著編一個版本測試。 編好後就跑了 7B 的 model，看起來快不少，然後改跑 13B 的 model，也可以把完整 40 個 layer 都丟進 3060 (12GB 版本) 的 GPU 上： ./main -m models/13B/ggml-model-q4_0.bin -p "Building a website can be done in 10 simple steps:" -n 512 -ngl 40 從 log…
May 15, 2023In "Computer"
Stanford Alpaca 與 Alpaca.cpp
先前提到的「玩最近 Facebook Research (Meta) 放出來的 LLaMA」，在 2/24 公佈後，過沒多久 Stanford CRFM 團隊就丟出 fine-tuned 過的版本：「Alpaca: A Strong, Replicable Instruction-Following Model」，對應的討論在「Alpaca: A strong open-source instruction-following model (stanford.edu)」。 這個 tuning 是基於 LLaMA-7B： We are releasing our findings about an instruction-following language model, dubbed Alpaca, which is fine-tuned from Meta’s LLaMA 7B model. We train…
March 17, 2023In "Computer"
Falcon 40B 超越 LLaMA 65B 成為目前 Open LLM 的領頭
在 LLM 裡面講的 Open 不是 open-source license 的定義，比較接近「免費使用」而已，通常會帶有限制。 但即使放寬到「免費使用」，LLaMA 65B 從二月放出來 (或者說「被放出來」) 已經領頭領了三個多月了，直到上個禮拜看到被 Falcon 40B 超越的消息： LLaMa is dethroned 👑 A brand new LLM is topping the Open Leaderboard: Falcon 40B 🛩*interesting* specs:- tuned for efficient inference- licence similar to Unity allowing commercial use - strong performances- high-quality dataset also…
June 1, 2023In "Computer"
Leave a Reply
Your email address will not be published. Required fields are marked *
Comment *
Name *
Email *
Website
Notify me of follow-up comments by email.
Notify me of new posts by email.
To respond on your own website, enter the URL of your response which should contain a link to this post's permalink URL. Your response will then appear (possibly after moderation) on this page. Want to update or remove your response? Update or delete your post and re-enter your post's URL again. (Learn More)
Post navigation
Recommend
About Joyk
Aggregate valuable and interesting links.
Joyk means Joy of geeK