Пікірлер

• 
  @vaibhavsrivastava464513 күн бұрын

  Very informative Thanks

• 
  @octanebd19 күн бұрын

  terrible channel. Invasive merge of self-promotion which totally destroys the main content utility.

• 
  @user-vu9dl3vn7l22 күн бұрын

  Thank you so much for this helpful video!

• 
  @SemaphoreCI21 күн бұрын

  Glad it was helpful!

• 
  @damnft8218Ай бұрын

  LocalAI in docker?

• 
  @SemaphoreCIАй бұрын

  They provide a docker image: localai.io/basics/getting_started/

• 
  @damnft8218Ай бұрын

  @@SemaphoreCI thank you

• 
  @mrpedrao02Ай бұрын

  I had some reservations about Docker, but not anymore! Thank you for the great explanation.

• 
  @SemaphoreCIАй бұрын

  Any time!

• 
  @timroberts_usaАй бұрын

  thank you presenting this... very helpful to understand options..

• 
  @SemaphoreCIАй бұрын

  Thank you for watching. I'm happy it helped!

• 
  @dimitriprosvirin1785Ай бұрын

  Man, thank you so much for this walkthrough. It feels like multiple hours of my own browsing, research, and getting lost safely packed in 30 min video.

• 
  @SemaphoreCIАй бұрын

  Glad to hear it!

• 
  @SemaphoreCIАй бұрын

  Learn how to run Llama3 in your machine. Running a ChatGPT alternative locally can be cheaper and more secure. You can ask it about private information without worrying what happens with the data.

• 
  @magnoojАй бұрын

  This is one of the best videos I’ve ever seen about running LLMs! Specifically it’s very user friendly for non-coders! Maybe some tweaks in the title/description will help none coders to find this better

• 
  @SemaphoreCIАй бұрын

  Thank you! It's a good suggestion. I'm glad you enjoyed it.

• 
  @davidmccormack99Ай бұрын

  Like some other commenters have said, this video was really useful to unpack the different options available for working with Llama models. Thank you so much! Aside: Your pronunciation of the “ll” sounds like the way it’s done in Argentinian Spanish…are you in Argentina?

• 
  @SemaphoreCIАй бұрын

  Yes I am. That ""LL" the sound is what we use to call the actual llamas, which we have plenty of. I understand that in English it's more like "lama" but it's hard to remember that when I'm recording. Thank you for the kind words.

• 
  @jefersonbronzeАй бұрын

  Great video!

• 
  @SemaphoreCIАй бұрын

  Thank you!

• 
  @emailme9112Ай бұрын

  Nice, concise intro to portals/modal. Thank you.

• 
  @SemaphoreCIАй бұрын

  You're welcome!

• 
  @tanyoivanov-personal2 ай бұрын

  Good video. Thanks

• 
  @SemaphoreCIАй бұрын

  Glad you liked it! Thank you!

• 
  @jovision302 ай бұрын

  Could you please make a video about how to make persistence in the cloud using ebs or s3 for example and how to make it scalable if possible

• 
  @SemaphoreCIАй бұрын

  Great idea. Thank you!

• 
  @jovision302 ай бұрын

  Good Content ! Thanks for sharing

• 
  @SemaphoreCIАй бұрын

  Thank you too

• 
  @ciprianov20062 ай бұрын

  hy, nice vid, can u make a vid for a bitbucket pipeline - cypress flaky tests. Thx

• 
  @tomaspinto52032 ай бұрын

  Thank you! Amazing video

• 
  @SemaphoreCI2 ай бұрын

  You're welcome. Thank you for watching!

• 
  @temka0882 ай бұрын

  how is this better than vlllm?

• 
  @SemaphoreCI2 ай бұрын

  I've not tried vllm yet. But it's on the plans to cover it. LocalAI it's an alternative, so I guess better or worse depends on your needs and use case.

• 
  @MaheshJoshi_wellington2 ай бұрын

  Wow amazing video ! Thank you so much. I just started exploring playwright with typescript looking forward to more videos on playwright please 🙏🏻😊 subscribed to your channel

• 
  @SemaphoreCI2 ай бұрын

  Thank you for the kind words. Best of luck!

• 
  @axiomatic40593 ай бұрын

  Excellent presentation! Thank you

• 
  @SemaphoreCI3 ай бұрын

  Glad you enjoyed it!

• 
  @SrikanthNandiraju3 ай бұрын

  How do we configure ChatOpenAI. When i use this code, it errors saying that the OpenAPI key is invalid const model = new ChatOpenAI({ openAIApiKey: "sk-XXXXXXXXXXXXXXXXXXXX", openAIHost: "localhost:8080", modelName: "gpt-3.5-turbo", temperature: 0, });

• 
  @mostlycathartic3 ай бұрын

  It was very useful.

• 
  @SemaphoreCI3 ай бұрын

  Thank you!

• 
  @BobRos23 ай бұрын

  Thanks for the summary! There were a lot of things in your video which I didnt know before. ♥

• 
  @SemaphoreCI3 ай бұрын

  Thank you! I'm happy it helped

• 
  @sidneymonteiro36703 ай бұрын

  44 years programming and heavy on shift left and testing... this new term seems contrived and from scenarios that do not arise from first principles. The very idea of simple testing non deterministic code is an anathema. Everything else is a complete lack of proper scaffolding. I don't know what to do with young programmers naming things that only exist because everything done is wrong!

• 
  @SemaphoreCI3 ай бұрын

  I'm happy you didn't experience flaky tests in your career. For myself I had to admit I've seen my share and most of my colleagues over tell me the same. There's a link in the description to a survey that suggests the problem is, unfortunately, more predominant across the industry.

• 
  @BrettOssman3 ай бұрын

  Well done. Boy can I relate to this. Love the term "flaky". 🙂I want to highlight the use of automated test suites. Amazing how often these are still not employed. But even then, QA will often find a flaky test, because they try to break the feature or use it outside the norm. Developers tend to test within the norm.

• 
  @SemaphoreCI3 ай бұрын

  Thank you. I agree that some form of automation is a must, otherwise it's really hard to identify tests that are flaking.

• 
  @rahimlizakir3 ай бұрын

  It helped a lot, thank you very much!

• 
  @SemaphoreCI3 ай бұрын

  You're welcome. Thank you for watching!

• 
  @manasa70153 ай бұрын

  why there is 0 model in conversation now

• 
  @SemaphoreCI3 ай бұрын

  Sorry, what do you mean?

• 
  @manasa70153 ай бұрын

  Hugging face has no conversation model now

• 
  @jesskrikra3 ай бұрын

  He's right. The filter option for "conversational" under Natural Language Processing in huggingface is gone. Maybe the filter "question amswering" is covering that now?

• 
  @manasa70153 ай бұрын

  @@jesskrikra may be

• 
  @davidkisielewski6054 ай бұрын

  Wow, I'm not here yet. See you in...

• 
  @SemaphoreCI3 ай бұрын

  Good luck!

• 
  @renierdelacruz46524 ай бұрын

  Great Video, Thank a lot

• 
  @SemaphoreCI4 ай бұрын

  Thank for watching

• 
  @yhrchan14 ай бұрын

  Thanks, have you tried leveraging LocalAI embedded Embeddings such as sentencetransformers/all-MiniLM-L6-v2. I was encountering an error not sure if you have another video on embeddings or could provide some insights/help. Thanks!

• 
  @SemaphoreCI4 ай бұрын

  No video yet, but I want to do more on that. I did write an article on using embeddings in an app (basically like RAG). Maybe it helps: semaphoreci.com/blog/word-embeddings

• 
  @DanielBergholz4 ай бұрын

  A microservices ad in the middle of an interview with DHH is completely out of place

• 
  @matteo-pu7ev4 ай бұрын

  I appreciate you !! I look forward to seeing your channel grow

• 
  @SemaphoreCI4 ай бұрын

  Thank you so much 🤗

• 
  @nasiksami23514 ай бұрын

  Thanks for clarifying my long-listed doubts. Now I am able to connect the dots.

• 
  @SemaphoreCI4 ай бұрын

  Glad it was helpful!

• 
  @kenchang34564 ай бұрын

  I appreciate that this video is a nice well rounded high-level description. The llama.cpp explanation was very helpful. Thank you very much for sharing.

• 
  @SemaphoreCI4 ай бұрын

  Glad you enjoyed it!

• 
  @AliAlias4 ай бұрын

  Thanks very much for your time and awesome video ❤🎉

• 
  @SemaphoreCI4 ай бұрын

  Thanks for watching!

• 
  @lalpremi4 ай бұрын

  Thank you for sharing, I will try some of your suggestions for open-source products. :-)

• 
  @SemaphoreCI4 ай бұрын

  Please do!

• 
  @lalpremi4 ай бұрын

  @@SemaphoreCI I managed to get llama.cpp running with phi-2-uncensored, love it.. fast answers are not bad.. I showed it to my 10-year-old, he wanted a 1000-page SA on cats..lol

• 
  @GARYGUS4 ай бұрын

  An excellent explanatory video with valuable and useful information for using LLAMA models without the Internet to ensure complete privacy.

• 
  @stephn.62364 ай бұрын

  Arrived here after feeling confused by all the links and approaches floating around in the internet. After your video, I finally feel like I understand this space, this is the best resource I've found on this topic by far.

• 
  @user-un9fr2yu4w4 ай бұрын

  "Error while commiting to repository" trying to do the single job, github granted full access to repo, useless

• 
  @SemaphoreCI4 ай бұрын

  Hi! Sorry to hear that. Can you please share which organization you were using and the repository connected to it? You can also send us an email to [email protected] or contact support directly inside the application.

• 
  @GenzoMendoza4 ай бұрын

  where exactly did you run the gh repo clone of llama.cpp on 13:04? Thank you

• 
  @FarhanAhmed13604 ай бұрын

  appreciate your good work

• 
  @VinayakSoni984 ай бұрын

  Thanks

• 
  @PossimKeengdum4 ай бұрын

  This is fantastic stuff man - quick question - have you considered using LM Studio?

• 
  @SemaphoreCI4 ай бұрын

  Thank you. I considered but I preferred to highlight open-source tools first.

• 
  @snehasissengupta27735 ай бұрын

  Please make a step by step Video for run the local ai on windows pc with all codes....

• 
  @SemaphoreCI4 ай бұрын

  I tried running LocalAI on containers but the performance was not really up to par, as least con Mac and Windows.

• 
  @yhrchan14 ай бұрын

  @@SemaphoreCI I was able to run it with reasonable speeds on my laptop with 32GB RAM, i7, GPU 8GB, WSL2, Docker

• 
  @nicknick655 ай бұрын

  just subs. Which model would you recommend to train using a specific golang repo, for example a project repo. Would it allow me to train locally by pointing to a directory? thanks Ah I should have continued watching your video to the end where you mention GPT4ALL allows you to point to a directory which it indexes. Do you think this would work if I point it to a repo?

• 
  @SemaphoreCI4 ай бұрын

  In my experience GPT4ALL models are not great at coding. YMMV but I think something like Copilot or AWS CodeWhisperer would be better for your use case.

• 
  @alessandrosalvaggio67725 ай бұрын

  anyone with detailed instructions on how to install it and download llama2 ?

• 
  @SemaphoreCI4 ай бұрын

  You can try Ollama. I made a video on running LLMs locally. Maybe it helps:: kzread.info/dash/bejne/aZ6Bq9Wmp9LJoLA.html

• 
  @matteo-pu7ev5 ай бұрын

  Thank you so much. Clear concise beautiful presentation. I look forward to engaging with more of your content.

• 
  @SemaphoreCI4 ай бұрын

  Awesome, thank you!

• 
  @amanthabandaramayadunna93625 ай бұрын

  Thank you

• 
  @SemaphoreCI4 ай бұрын

  Thank you for watching!

• 
  @tremendousdk5 ай бұрын

  It's mandatory to use 1 year old GitHub account

• 
  @SonGoku-pc7jl5 ай бұрын

  gracias, cual es la capa gratuita?

• 
  @SemaphoreCI5 ай бұрын

  Free tier of Semaphore or BrowserStack?