{"comments":[{"comment":{"id":6082124,"creator_id":101027,"post_id":8155975,"content":"Anyone using the code specific models, -- how are you prompting them? Are you using any integration into vim emacs or other truly open source and offline text editor/IDE; not electron or proton based? I've compiled VS code before, but it is basically useless in that form, and the binary version sends network traffic like crazy.","removed":false,"published":"2024-01-29T21:50:52.855178Z","deleted":false,"ap_id":"https://lemmy.world/comment/7134574","local":false,"path":"0.6082124","distinguished":false,"language_id":37},"creator":{"id":101027,"name":"j4k3","display_name":"𞋴𝛂𝛋𝛆","avatar":"https://lemmy.world/pictrs/image/69e27817-2c2e-48d1-8bb9-aa74c2fd4e15.jpeg","banned":false,"published":"2023-06-09T17:41:38.382015Z","actor_id":"https://lemmy.world/u/j4k3","local":false,"deleted":false,"matrix_user_id":"@-j4k3:matrix.org","bot_account":false,"instance_id":65477},"post":{"id":8155975,"name":"Meta releases ‘Code Llama 70B’, an open-source behemoth to rival private AI development","url":"https://venturebeat.com/ai/meta-releases-code-llama-70b-an-open-source-behemoth-to-rival-private-ai-development/","creator_id":114057,"community_id":2344,"removed":false,"locked":false,"published":"2024-01-29T21:25:05.753168Z","deleted":false,"nsfw":false,"embed_title":"Meta releases ‘Code Llama 70B’, an open-source behemoth to rival private AI development","embed_description":"Code Llama 70B is a new and improved version of Meta AI’s code generation model that can write code in various programming languages from natural language prompts or existing code snippets.","thumbnail_url":"https://lemmy.blahaj.zone/pictrs/image/66a3f45d-6881-4e4f-9bfe-0d2545c7f15f.webp","ap_id":"https://lemmy.ml/post/11219477","local":false,"language_id":37,"featured_community":false,"featured_local":false,"url_content_type":"text/html; charset=utf-8"},"community":{"id":2344,"name":"localllama","title":"LocalLLaMA","description":"Welcome to LocalLLaMA! Here we discuss running and developing machine learning models at home. Lets explore cutting edge open source neural network technology together.\n\nGet support from the community! Ask questions, share prompts, discuss benchmarks, get hyped at the latest and greatest model releases! Enjoy talking about our awesome hobby.\n\nAs ambassadors of the self-hosting machine learning community, we strive to support each other and share our enthusiasm in a positive constructive way.\n\nRules:\n\nRule 1 -\nNo harassment or personal character attacks of community members. I.E no namecalling, no generalizing entire groups of people that make up our community, no baseless personal insults.\n\nRule 2 -\nNo comparing artificial intelligence/machine learning models to cryptocurrency. I.E no comparing the usefulness of models to that of NFTs, no comparing the resource usage required to train a model is anything close to maintaining a blockchain/ mining for crypto, no implying its just a fad/bubble that will leave people with nothing of value when it burst.\n\nRule 3 -\nNo comparing artificial intelligence/machine learning to simple text prediction algorithms. I.E statements such as \"llms are basically just simple text predictions like what your phone keyboard autocorrect uses, and they're still using the same algorithms since .\n\nRule 4 -\nNo implying that models are devoid of purpose or potential for enriching peoples lives.","removed":false,"published":"2023-06-08T18:21:54.578976Z","updated":"2025-06-09T20:51:11.460711Z","deleted":false,"nsfw":false,"actor_id":"https://sh.itjust.works/c/localllama","local":false,"icon":"https://sh.itjust.works/pictrs/image/8e07ec26-c7e5-4411-a4d5-c0c7a292b773.gif","banner":"https://sh.itjust.works/pictrs/image/5d07b398-7675-4862-8277-5906400b666d.png","hidden":false,"posting_restricted_to_mods":false,"instance_id":72342,"visibility":"Public"},"counts":{"comment_id":6082124,"score":7,"upvotes":7,"downvotes":0,"published":"2024-01-29T21:50:52.855178Z","child_count":9},"creator_banned_from_community":false,"banned_from_community":false,"creator_is_moderator":false,"creator_is_admin":false,"subscribed":"NotSubscribed","saved":false,"creator_blocked":false},{"comment":{"id":6085769,"creator_id":107319,"post_id":8155975,"content":"I've downloaded the [13B codellama](https://huggingface.co/TheBloke/CodeLlama-13B-Instruct-GGUF) from huggingface, passed it my NVIDIA 2070 via cuda, and have interfaced either through the terminal or [lmstudio](https://lmstudio.ai/). \n\nUsually my prompts include the specific code block and a wordy explanation about what I'm trying to do.\n\nIt's okay, but it's not as accurate as chatgpt, and tends to repeat itself a lot more.\n\nFor editor integration, i just opted for [codeium](https://codeium.com/) in neovim. It's a pretty good alternative to copilot imho.","removed":false,"published":"2024-01-30T01:27:24.932950Z","updated":"2024-01-30T01:32:57.642884Z","deleted":false,"ap_id":"https://lemmy.ml/comment/7863637","local":false,"path":"0.6082124.6085769","distinguished":false,"language_id":37},"creator":{"id":107319,"name":"z3rOR0ne","display_name":"z3rOR0ne","avatar":"https://lemmy.ml/pictrs/image/7e102035-823f-409d-aef9-4a72688622c2.jpeg","banned":false,"published":"2022-02-22T11:37:28.928852Z","updated":"2022-02-23T11:26:23.967618Z","actor_id":"https://lemmy.ml/u/z3rOR0ne","bio":"Fuck Nationalists, White Supremacists, Nazis, Fascists, The Patriarchy, Maga, Racists, Transphobes, Terfs, Homophobes, the Police.","local":false,"banner":"https://lemmy.ml/pictrs/image/5360b284-ee88-48c4-9e73-67e0252d8bcf.jpeg","deleted":false,"bot_account":false,"instance_id":195},"post":{"id":8155975,"name":"Meta releases ‘Code Llama 70B’, an open-source behemoth to rival private AI development","url":"https://venturebeat.com/ai/meta-releases-code-llama-70b-an-open-source-behemoth-to-rival-private-ai-development/","creator_id":114057,"community_id":2344,"removed":false,"locked":false,"published":"2024-01-29T21:25:05.753168Z","deleted":false,"nsfw":false,"embed_title":"Meta releases ‘Code Llama 70B’, an open-source behemoth to rival private AI development","embed_description":"Code Llama 70B is a new and improved version of Meta AI’s code generation model that can write code in various programming languages from natural language prompts or existing code snippets.","thumbnail_url":"https://lemmy.blahaj.zone/pictrs/image/66a3f45d-6881-4e4f-9bfe-0d2545c7f15f.webp","ap_id":"https://lemmy.ml/post/11219477","local":false,"language_id":37,"featured_community":false,"featured_local":false,"url_content_type":"text/html; charset=utf-8"},"community":{"id":2344,"name":"localllama","title":"LocalLLaMA","description":"Welcome to LocalLLaMA! Here we discuss running and developing machine learning models at home. Lets explore cutting edge open source neural network technology together.\n\nGet support from the community! Ask questions, share prompts, discuss benchmarks, get hyped at the latest and greatest model releases! Enjoy talking about our awesome hobby.\n\nAs ambassadors of the self-hosting machine learning community, we strive to support each other and share our enthusiasm in a positive constructive way.\n\nRules:\n\nRule 1 -\nNo harassment or personal character attacks of community members. I.E no namecalling, no generalizing entire groups of people that make up our community, no baseless personal insults.\n\nRule 2 -\nNo comparing artificial intelligence/machine learning models to cryptocurrency. I.E no comparing the usefulness of models to that of NFTs, no comparing the resource usage required to train a model is anything close to maintaining a blockchain/ mining for crypto, no implying its just a fad/bubble that will leave people with nothing of value when it burst.\n\nRule 3 -\nNo comparing artificial intelligence/machine learning to simple text prediction algorithms. I.E statements such as \"llms are basically just simple text predictions like what your phone keyboard autocorrect uses, and they're still using the same algorithms since .\n\nRule 4 -\nNo implying that models are devoid of purpose or potential for enriching peoples lives.","removed":false,"published":"2023-06-08T18:21:54.578976Z","updated":"2025-06-09T20:51:11.460711Z","deleted":false,"nsfw":false,"actor_id":"https://sh.itjust.works/c/localllama","local":false,"icon":"https://sh.itjust.works/pictrs/image/8e07ec26-c7e5-4411-a4d5-c0c7a292b773.gif","banner":"https://sh.itjust.works/pictrs/image/5d07b398-7675-4862-8277-5906400b666d.png","hidden":false,"posting_restricted_to_mods":false,"instance_id":72342,"visibility":"Public"},"counts":{"comment_id":6085769,"score":7,"upvotes":7,"downvotes":0,"published":"2024-01-30T01:27:24.932950Z","child_count":6},"creator_banned_from_community":false,"banned_from_community":false,"creator_is_moderator":false,"creator_is_admin":false,"subscribed":"NotSubscribed","saved":false,"creator_blocked":false},{"comment":{"id":6086126,"creator_id":438515,"post_id":8155975,"content":"You might like [VSCodium](https://vscodium.com/) with [continue](https://github.com/continuedev/continue) or [privy](https://github.com/srikanth235/privy)","removed":false,"published":"2024-01-30T01:53:57.774988Z","deleted":false,"ap_id":"https://slrpnk.net/comment/5810855","local":false,"path":"0.6082124.6086126","distinguished":false,"language_id":37},"creator":{"id":438515,"name":"MalReynolds","avatar":"https://slrpnk.net/pictrs/image/00be6193-b3ab-400b-9374-f640eb98cedf.jpeg","banned":false,"published":"2023-06-25T13:39:12.258262Z","actor_id":"https://slrpnk.net/u/MalReynolds","local":false,"deleted":false,"bot_account":false,"instance_id":107},"post":{"id":8155975,"name":"Meta releases ‘Code Llama 70B’, an open-source behemoth to rival private AI development","url":"https://venturebeat.com/ai/meta-releases-code-llama-70b-an-open-source-behemoth-to-rival-private-ai-development/","creator_id":114057,"community_id":2344,"removed":false,"locked":false,"published":"2024-01-29T21:25:05.753168Z","deleted":false,"nsfw":false,"embed_title":"Meta releases ‘Code Llama 70B’, an open-source behemoth to rival private AI development","embed_description":"Code Llama 70B is a new and improved version of Meta AI’s code generation model that can write code in various programming languages from natural language prompts or existing code snippets.","thumbnail_url":"https://lemmy.blahaj.zone/pictrs/image/66a3f45d-6881-4e4f-9bfe-0d2545c7f15f.webp","ap_id":"https://lemmy.ml/post/11219477","local":false,"language_id":37,"featured_community":false,"featured_local":false,"url_content_type":"text/html; charset=utf-8"},"community":{"id":2344,"name":"localllama","title":"LocalLLaMA","description":"Welcome to LocalLLaMA! Here we discuss running and developing machine learning models at home. Lets explore cutting edge open source neural network technology together.\n\nGet support from the community! Ask questions, share prompts, discuss benchmarks, get hyped at the latest and greatest model releases! Enjoy talking about our awesome hobby.\n\nAs ambassadors of the self-hosting machine learning community, we strive to support each other and share our enthusiasm in a positive constructive way.\n\nRules:\n\nRule 1 -\nNo harassment or personal character attacks of community members. I.E no namecalling, no generalizing entire groups of people that make up our community, no baseless personal insults.\n\nRule 2 -\nNo comparing artificial intelligence/machine learning models to cryptocurrency. I.E no comparing the usefulness of models to that of NFTs, no comparing the resource usage required to train a model is anything close to maintaining a blockchain/ mining for crypto, no implying its just a fad/bubble that will leave people with nothing of value when it burst.\n\nRule 3 -\nNo comparing artificial intelligence/machine learning to simple text prediction algorithms. I.E statements such as \"llms are basically just simple text predictions like what your phone keyboard autocorrect uses, and they're still using the same algorithms since .\n\nRule 4 -\nNo implying that models are devoid of purpose or potential for enriching peoples lives.","removed":false,"published":"2023-06-08T18:21:54.578976Z","updated":"2025-06-09T20:51:11.460711Z","deleted":false,"nsfw":false,"actor_id":"https://sh.itjust.works/c/localllama","local":false,"icon":"https://sh.itjust.works/pictrs/image/8e07ec26-c7e5-4411-a4d5-c0c7a292b773.gif","banner":"https://sh.itjust.works/pictrs/image/5d07b398-7675-4862-8277-5906400b666d.png","hidden":false,"posting_restricted_to_mods":false,"instance_id":72342,"visibility":"Public"},"counts":{"comment_id":6086126,"score":2,"upvotes":2,"downvotes":0,"published":"2024-01-30T01:53:57.774988Z","child_count":0},"creator_banned_from_community":false,"banned_from_community":false,"creator_is_moderator":false,"creator_is_admin":false,"subscribed":"NotSubscribed","saved":false,"creator_blocked":false},{"comment":{"id":6086172,"creator_id":794827,"post_id":8155975,"content":"","removed":false,"published":"2024-01-30T01:57:54.122446Z","updated":"2024-01-30T01:58:54.198265Z","deleted":true,"ap_id":"https://sh.itjust.works/comment/8254113","local":false,"path":"0.6082124.6086172","distinguished":false,"language_id":37},"creator":{"id":794827,"name":"only0218","banned":false,"published":"2023-07-04T22:28:38.550861Z","actor_id":"https://sh.itjust.works/u/only0218","local":false,"deleted":false,"bot_account":false,"instance_id":72342},"post":{"id":8155975,"name":"Meta releases ‘Code Llama 70B’, an open-source behemoth to rival private AI development","url":"https://venturebeat.com/ai/meta-releases-code-llama-70b-an-open-source-behemoth-to-rival-private-ai-development/","creator_id":114057,"community_id":2344,"removed":false,"locked":false,"published":"2024-01-29T21:25:05.753168Z","deleted":false,"nsfw":false,"embed_title":"Meta releases ‘Code Llama 70B’, an open-source behemoth to rival private AI development","embed_description":"Code Llama 70B is a new and improved version of Meta AI’s code generation model that can write code in various programming languages from natural language prompts or existing code snippets.","thumbnail_url":"https://lemmy.blahaj.zone/pictrs/image/66a3f45d-6881-4e4f-9bfe-0d2545c7f15f.webp","ap_id":"https://lemmy.ml/post/11219477","local":false,"language_id":37,"featured_community":false,"featured_local":false,"url_content_type":"text/html; charset=utf-8"},"community":{"id":2344,"name":"localllama","title":"LocalLLaMA","description":"Welcome to LocalLLaMA! Here we discuss running and developing machine learning models at home. Lets explore cutting edge open source neural network technology together.\n\nGet support from the community! Ask questions, share prompts, discuss benchmarks, get hyped at the latest and greatest model releases! Enjoy talking about our awesome hobby.\n\nAs ambassadors of the self-hosting machine learning community, we strive to support each other and share our enthusiasm in a positive constructive way.\n\nRules:\n\nRule 1 -\nNo harassment or personal character attacks of community members. I.E no namecalling, no generalizing entire groups of people that make up our community, no baseless personal insults.\n\nRule 2 -\nNo comparing artificial intelligence/machine learning models to cryptocurrency. I.E no comparing the usefulness of models to that of NFTs, no comparing the resource usage required to train a model is anything close to maintaining a blockchain/ mining for crypto, no implying its just a fad/bubble that will leave people with nothing of value when it burst.\n\nRule 3 -\nNo comparing artificial intelligence/machine learning to simple text prediction algorithms. I.E statements such as \"llms are basically just simple text predictions like what your phone keyboard autocorrect uses, and they're still using the same algorithms since .\n\nRule 4 -\nNo implying that models are devoid of purpose or potential for enriching peoples lives.","removed":false,"published":"2023-06-08T18:21:54.578976Z","updated":"2025-06-09T20:51:11.460711Z","deleted":false,"nsfw":false,"actor_id":"https://sh.itjust.works/c/localllama","local":false,"icon":"https://sh.itjust.works/pictrs/image/8e07ec26-c7e5-4411-a4d5-c0c7a292b773.gif","banner":"https://sh.itjust.works/pictrs/image/5d07b398-7675-4862-8277-5906400b666d.png","hidden":false,"posting_restricted_to_mods":false,"instance_id":72342,"visibility":"Public"},"counts":{"comment_id":6086172,"score":1,"upvotes":1,"downvotes":0,"published":"2024-01-30T01:57:54.122446Z","child_count":0},"creator_banned_from_community":false,"banned_from_community":false,"creator_is_moderator":false,"creator_is_admin":false,"subscribed":"NotSubscribed","saved":false,"creator_blocked":false},{"comment":{"id":6360418,"creator_id":591915,"post_id":8155975,"content":"Hugging face have an llm plug-in for code completion in neovim btw!","removed":false,"published":"2024-02-11T08:42:01Z","deleted":false,"ap_id":"https://kbin.social/m/localllama@sh.itjust.works/t/798144/-/comment/5098844","local":false,"path":"0.6082124.6085769.6360418","distinguished":false,"language_id":0},"creator":{"id":591915,"name":"amzd","display_name":"amzd","banned":false,"published":"2023-06-30T10:59:13Z","actor_id":"https://kbin.social/u/amzd","local":false,"deleted":false,"bot_account":false,"instance_id":42423},"post":{"id":8155975,"name":"Meta releases ‘Code Llama 70B’, an open-source behemoth to rival private AI development","url":"https://venturebeat.com/ai/meta-releases-code-llama-70b-an-open-source-behemoth-to-rival-private-ai-development/","creator_id":114057,"community_id":2344,"removed":false,"locked":false,"published":"2024-01-29T21:25:05.753168Z","deleted":false,"nsfw":false,"embed_title":"Meta releases ‘Code Llama 70B’, an open-source behemoth to rival private AI development","embed_description":"Code Llama 70B is a new and improved version of Meta AI’s code generation model that can write code in various programming languages from natural language prompts or existing code snippets.","thumbnail_url":"https://lemmy.blahaj.zone/pictrs/image/66a3f45d-6881-4e4f-9bfe-0d2545c7f15f.webp","ap_id":"https://lemmy.ml/post/11219477","local":false,"language_id":37,"featured_community":false,"featured_local":false,"url_content_type":"text/html; charset=utf-8"},"community":{"id":2344,"name":"localllama","title":"LocalLLaMA","description":"Welcome to LocalLLaMA! Here we discuss running and developing machine learning models at home. Lets explore cutting edge open source neural network technology together.\n\nGet support from the community! Ask questions, share prompts, discuss benchmarks, get hyped at the latest and greatest model releases! Enjoy talking about our awesome hobby.\n\nAs ambassadors of the self-hosting machine learning community, we strive to support each other and share our enthusiasm in a positive constructive way.\n\nRules:\n\nRule 1 -\nNo harassment or personal character attacks of community members. I.E no namecalling, no generalizing entire groups of people that make up our community, no baseless personal insults.\n\nRule 2 -\nNo comparing artificial intelligence/machine learning models to cryptocurrency. I.E no comparing the usefulness of models to that of NFTs, no comparing the resource usage required to train a model is anything close to maintaining a blockchain/ mining for crypto, no implying its just a fad/bubble that will leave people with nothing of value when it burst.\n\nRule 3 -\nNo comparing artificial intelligence/machine learning to simple text prediction algorithms. I.E statements such as \"llms are basically just simple text predictions like what your phone keyboard autocorrect uses, and they're still using the same algorithms since .\n\nRule 4 -\nNo implying that models are devoid of purpose or potential for enriching peoples lives.","removed":false,"published":"2023-06-08T18:21:54.578976Z","updated":"2025-06-09T20:51:11.460711Z","deleted":false,"nsfw":false,"actor_id":"https://sh.itjust.works/c/localllama","local":false,"icon":"https://sh.itjust.works/pictrs/image/8e07ec26-c7e5-4411-a4d5-c0c7a292b773.gif","banner":"https://sh.itjust.works/pictrs/image/5d07b398-7675-4862-8277-5906400b666d.png","hidden":false,"posting_restricted_to_mods":false,"instance_id":72342,"visibility":"Public"},"counts":{"comment_id":6360418,"score":2,"upvotes":2,"downvotes":0,"published":"2024-02-11T08:42:01Z","child_count":3},"creator_banned_from_community":false,"banned_from_community":false,"creator_is_moderator":false,"creator_is_admin":false,"subscribed":"NotSubscribed","saved":false,"creator_blocked":false},{"comment":{"id":6088577,"creator_id":431750,"post_id":8155975,"content":"Why use it though if it's not as good, and repeats itself.","removed":false,"published":"2024-01-30T04:50:13.367154Z","deleted":false,"ap_id":"https://lemmy.world/comment/7141195","local":false,"path":"0.6082124.6085769.6088577","distinguished":false,"language_id":37},"creator":{"id":431750,"name":"Anticorp","display_name":"AwkwardLookMonkeyPuppet","banned":true,"published":"2023-06-25T08:06:24.019574Z","actor_id":"https://lemmy.world/u/Anticorp","local":false,"deleted":true,"bot_account":false,"instance_id":65477},"post":{"id":8155975,"name":"Meta releases ‘Code Llama 70B’, an open-source behemoth to rival private AI development","url":"https://venturebeat.com/ai/meta-releases-code-llama-70b-an-open-source-behemoth-to-rival-private-ai-development/","creator_id":114057,"community_id":2344,"removed":false,"locked":false,"published":"2024-01-29T21:25:05.753168Z","deleted":false,"nsfw":false,"embed_title":"Meta releases ‘Code Llama 70B’, an open-source behemoth to rival private AI development","embed_description":"Code Llama 70B is a new and improved version of Meta AI’s code generation model that can write code in various programming languages from natural language prompts or existing code snippets.","thumbnail_url":"https://lemmy.blahaj.zone/pictrs/image/66a3f45d-6881-4e4f-9bfe-0d2545c7f15f.webp","ap_id":"https://lemmy.ml/post/11219477","local":false,"language_id":37,"featured_community":false,"featured_local":false,"url_content_type":"text/html; charset=utf-8"},"community":{"id":2344,"name":"localllama","title":"LocalLLaMA","description":"Welcome to LocalLLaMA! Here we discuss running and developing machine learning models at home. Lets explore cutting edge open source neural network technology together.\n\nGet support from the community! Ask questions, share prompts, discuss benchmarks, get hyped at the latest and greatest model releases! Enjoy talking about our awesome hobby.\n\nAs ambassadors of the self-hosting machine learning community, we strive to support each other and share our enthusiasm in a positive constructive way.\n\nRules:\n\nRule 1 -\nNo harassment or personal character attacks of community members. I.E no namecalling, no generalizing entire groups of people that make up our community, no baseless personal insults.\n\nRule 2 -\nNo comparing artificial intelligence/machine learning models to cryptocurrency. I.E no comparing the usefulness of models to that of NFTs, no comparing the resource usage required to train a model is anything close to maintaining a blockchain/ mining for crypto, no implying its just a fad/bubble that will leave people with nothing of value when it burst.\n\nRule 3 -\nNo comparing artificial intelligence/machine learning to simple text prediction algorithms. I.E statements such as \"llms are basically just simple text predictions like what your phone keyboard autocorrect uses, and they're still using the same algorithms since .\n\nRule 4 -\nNo implying that models are devoid of purpose or potential for enriching peoples lives.","removed":false,"published":"2023-06-08T18:21:54.578976Z","updated":"2025-06-09T20:51:11.460711Z","deleted":false,"nsfw":false,"actor_id":"https://sh.itjust.works/c/localllama","local":false,"icon":"https://sh.itjust.works/pictrs/image/8e07ec26-c7e5-4411-a4d5-c0c7a292b773.gif","banner":"https://sh.itjust.works/pictrs/image/5d07b398-7675-4862-8277-5906400b666d.png","hidden":false,"posting_restricted_to_mods":false,"instance_id":72342,"visibility":"Public"},"counts":{"comment_id":6088577,"score":2,"upvotes":2,"downvotes":0,"published":"2024-01-30T04:50:13.367154Z","child_count":1},"creator_banned_from_community":false,"banned_from_community":false,"creator_is_moderator":false,"creator_is_admin":false,"subscribed":"NotSubscribed","saved":false,"creator_blocked":false},{"comment":{"id":6091190,"creator_id":107319,"post_id":8155975,"content":"Because it doesn't call out to the internet. I even put lmstudio behind firejail to prevent it from doing so. Thusly any code I feed it (albeit pretty trivial code) doesn't add to chatgpt's overarching data set.\n\nIt still can produce usable results. It's just not as consistent. Whenever it gets into a repetitive loop, I just restart it, resetting the initial context, which generally prevents it from repeating itself, at least initially. To be fair, I've also experienced this with chatgpt, just not as often.\n\nTLDR; It's more private and still useful.","removed":false,"published":"2024-01-30T08:36:56.433492Z","updated":"2024-01-30T08:37:48.830064Z","deleted":false,"ap_id":"https://lemmy.ml/comment/7869892","local":false,"path":"0.6082124.6085769.6088577.6091190","distinguished":false,"language_id":37},"creator":{"id":107319,"name":"z3rOR0ne","display_name":"z3rOR0ne","avatar":"https://lemmy.ml/pictrs/image/7e102035-823f-409d-aef9-4a72688622c2.jpeg","banned":false,"published":"2022-02-22T11:37:28.928852Z","updated":"2022-02-23T11:26:23.967618Z","actor_id":"https://lemmy.ml/u/z3rOR0ne","bio":"Fuck Nationalists, White Supremacists, Nazis, Fascists, The Patriarchy, Maga, Racists, Transphobes, Terfs, Homophobes, the Police.","local":false,"banner":"https://lemmy.ml/pictrs/image/5360b284-ee88-48c4-9e73-67e0252d8bcf.jpeg","deleted":false,"bot_account":false,"instance_id":195},"post":{"id":8155975,"name":"Meta releases ‘Code Llama 70B’, an open-source behemoth to rival private AI development","url":"https://venturebeat.com/ai/meta-releases-code-llama-70b-an-open-source-behemoth-to-rival-private-ai-development/","creator_id":114057,"community_id":2344,"removed":false,"locked":false,"published":"2024-01-29T21:25:05.753168Z","deleted":false,"nsfw":false,"embed_title":"Meta releases ‘Code Llama 70B’, an open-source behemoth to rival private AI development","embed_description":"Code Llama 70B is a new and improved version of Meta AI’s code generation model that can write code in various programming languages from natural language prompts or existing code snippets.","thumbnail_url":"https://lemmy.blahaj.zone/pictrs/image/66a3f45d-6881-4e4f-9bfe-0d2545c7f15f.webp","ap_id":"https://lemmy.ml/post/11219477","local":false,"language_id":37,"featured_community":false,"featured_local":false,"url_content_type":"text/html; charset=utf-8"},"community":{"id":2344,"name":"localllama","title":"LocalLLaMA","description":"Welcome to LocalLLaMA! Here we discuss running and developing machine learning models at home. Lets explore cutting edge open source neural network technology together.\n\nGet support from the community! Ask questions, share prompts, discuss benchmarks, get hyped at the latest and greatest model releases! Enjoy talking about our awesome hobby.\n\nAs ambassadors of the self-hosting machine learning community, we strive to support each other and share our enthusiasm in a positive constructive way.\n\nRules:\n\nRule 1 -\nNo harassment or personal character attacks of community members. I.E no namecalling, no generalizing entire groups of people that make up our community, no baseless personal insults.\n\nRule 2 -\nNo comparing artificial intelligence/machine learning models to cryptocurrency. I.E no comparing the usefulness of models to that of NFTs, no comparing the resource usage required to train a model is anything close to maintaining a blockchain/ mining for crypto, no implying its just a fad/bubble that will leave people with nothing of value when it burst.\n\nRule 3 -\nNo comparing artificial intelligence/machine learning to simple text prediction algorithms. I.E statements such as \"llms are basically just simple text predictions like what your phone keyboard autocorrect uses, and they're still using the same algorithms since .\n\nRule 4 -\nNo implying that models are devoid of purpose or potential for enriching peoples lives.","removed":false,"published":"2023-06-08T18:21:54.578976Z","updated":"2025-06-09T20:51:11.460711Z","deleted":false,"nsfw":false,"actor_id":"https://sh.itjust.works/c/localllama","local":false,"icon":"https://sh.itjust.works/pictrs/image/8e07ec26-c7e5-4411-a4d5-c0c7a292b773.gif","banner":"https://sh.itjust.works/pictrs/image/5d07b398-7675-4862-8277-5906400b666d.png","hidden":false,"posting_restricted_to_mods":false,"instance_id":72342,"visibility":"Public"},"counts":{"comment_id":6091190,"score":9,"upvotes":9,"downvotes":0,"published":"2024-01-30T08:36:56.433492Z","child_count":0},"creator_banned_from_community":false,"banned_from_community":false,"creator_is_moderator":false,"creator_is_admin":false,"subscribed":"NotSubscribed","saved":false,"creator_blocked":false},{"comment":{"id":6362114,"creator_id":107319,"post_id":8155975,"content":"Oh nice! Got a link for anyone that comes across this? Save me and others a search plz?\n\nEDIT: NM. Got it. Gonna give it a try later.\n\n[LLM powered development for Neovim](https://github.com/huggingface/llm.nvim)","removed":false,"published":"2024-02-11T09:38:36.100665Z","updated":"2024-02-11T12:57:42.866590Z","deleted":false,"ap_id":"https://lemmy.ml/comment/8193269","local":false,"path":"0.6082124.6085769.6360418.6362114","distinguished":false,"language_id":37},"creator":{"id":107319,"name":"z3rOR0ne","display_name":"z3rOR0ne","avatar":"https://lemmy.ml/pictrs/image/7e102035-823f-409d-aef9-4a72688622c2.jpeg","banned":false,"published":"2022-02-22T11:37:28.928852Z","updated":"2022-02-23T11:26:23.967618Z","actor_id":"https://lemmy.ml/u/z3rOR0ne","bio":"Fuck Nationalists, White Supremacists, Nazis, Fascists, The Patriarchy, Maga, Racists, Transphobes, Terfs, Homophobes, the Police.","local":false,"banner":"https://lemmy.ml/pictrs/image/5360b284-ee88-48c4-9e73-67e0252d8bcf.jpeg","deleted":false,"bot_account":false,"instance_id":195},"post":{"id":8155975,"name":"Meta releases ‘Code Llama 70B’, an open-source behemoth to rival private AI development","url":"https://venturebeat.com/ai/meta-releases-code-llama-70b-an-open-source-behemoth-to-rival-private-ai-development/","creator_id":114057,"community_id":2344,"removed":false,"locked":false,"published":"2024-01-29T21:25:05.753168Z","deleted":false,"nsfw":false,"embed_title":"Meta releases ‘Code Llama 70B’, an open-source behemoth to rival private AI development","embed_description":"Code Llama 70B is a new and improved version of Meta AI’s code generation model that can write code in various programming languages from natural language prompts or existing code snippets.","thumbnail_url":"https://lemmy.blahaj.zone/pictrs/image/66a3f45d-6881-4e4f-9bfe-0d2545c7f15f.webp","ap_id":"https://lemmy.ml/post/11219477","local":false,"language_id":37,"featured_community":false,"featured_local":false,"url_content_type":"text/html; charset=utf-8"},"community":{"id":2344,"name":"localllama","title":"LocalLLaMA","description":"Welcome to LocalLLaMA! Here we discuss running and developing machine learning models at home. Lets explore cutting edge open source neural network technology together.\n\nGet support from the community! Ask questions, share prompts, discuss benchmarks, get hyped at the latest and greatest model releases! Enjoy talking about our awesome hobby.\n\nAs ambassadors of the self-hosting machine learning community, we strive to support each other and share our enthusiasm in a positive constructive way.\n\nRules:\n\nRule 1 -\nNo harassment or personal character attacks of community members. I.E no namecalling, no generalizing entire groups of people that make up our community, no baseless personal insults.\n\nRule 2 -\nNo comparing artificial intelligence/machine learning models to cryptocurrency. I.E no comparing the usefulness of models to that of NFTs, no comparing the resource usage required to train a model is anything close to maintaining a blockchain/ mining for crypto, no implying its just a fad/bubble that will leave people with nothing of value when it burst.\n\nRule 3 -\nNo comparing artificial intelligence/machine learning to simple text prediction algorithms. I.E statements such as \"llms are basically just simple text predictions like what your phone keyboard autocorrect uses, and they're still using the same algorithms since .\n\nRule 4 -\nNo implying that models are devoid of purpose or potential for enriching peoples lives.","removed":false,"published":"2023-06-08T18:21:54.578976Z","updated":"2025-06-09T20:51:11.460711Z","deleted":false,"nsfw":false,"actor_id":"https://sh.itjust.works/c/localllama","local":false,"icon":"https://sh.itjust.works/pictrs/image/8e07ec26-c7e5-4411-a4d5-c0c7a292b773.gif","banner":"https://sh.itjust.works/pictrs/image/5d07b398-7675-4862-8277-5906400b666d.png","hidden":false,"posting_restricted_to_mods":false,"instance_id":72342,"visibility":"Public"},"counts":{"comment_id":6362114,"score":1,"upvotes":1,"downvotes":0,"published":"2024-02-11T09:38:36.100665Z","child_count":2},"creator_banned_from_community":false,"banned_from_community":false,"creator_is_moderator":false,"creator_is_admin":false,"subscribed":"NotSubscribed","saved":false,"creator_blocked":false},{"comment":{"id":6367756,"creator_id":591915,"post_id":8155975,"content":"If you use ollama you can try to use the fork that I am using. This is my config to make it work: [https://github.com/Amzd/nvim.config/blob/main/lua/plugins/llm.lua](https://github.com/Amzd/nvim.config/blob/main/lua/plugins/llm.lua)","removed":false,"published":"2024-02-11T14:04:10Z","deleted":false,"ap_id":"https://kbin.social/m/localllama@sh.itjust.works/t/798144/-/comment/5101903","local":false,"path":"0.6082124.6085769.6360418.6362114.6367756","distinguished":false,"language_id":0},"creator":{"id":591915,"name":"amzd","display_name":"amzd","banned":false,"published":"2023-06-30T10:59:13Z","actor_id":"https://kbin.social/u/amzd","local":false,"deleted":false,"bot_account":false,"instance_id":42423},"post":{"id":8155975,"name":"Meta releases ‘Code Llama 70B’, an open-source behemoth to rival private AI development","url":"https://venturebeat.com/ai/meta-releases-code-llama-70b-an-open-source-behemoth-to-rival-private-ai-development/","creator_id":114057,"community_id":2344,"removed":false,"locked":false,"published":"2024-01-29T21:25:05.753168Z","deleted":false,"nsfw":false,"embed_title":"Meta releases ‘Code Llama 70B’, an open-source behemoth to rival private AI development","embed_description":"Code Llama 70B is a new and improved version of Meta AI’s code generation model that can write code in various programming languages from natural language prompts or existing code snippets.","thumbnail_url":"https://lemmy.blahaj.zone/pictrs/image/66a3f45d-6881-4e4f-9bfe-0d2545c7f15f.webp","ap_id":"https://lemmy.ml/post/11219477","local":false,"language_id":37,"featured_community":false,"featured_local":false,"url_content_type":"text/html; charset=utf-8"},"community":{"id":2344,"name":"localllama","title":"LocalLLaMA","description":"Welcome to LocalLLaMA! Here we discuss running and developing machine learning models at home. Lets explore cutting edge open source neural network technology together.\n\nGet support from the community! Ask questions, share prompts, discuss benchmarks, get hyped at the latest and greatest model releases! Enjoy talking about our awesome hobby.\n\nAs ambassadors of the self-hosting machine learning community, we strive to support each other and share our enthusiasm in a positive constructive way.\n\nRules:\n\nRule 1 -\nNo harassment or personal character attacks of community members. I.E no namecalling, no generalizing entire groups of people that make up our community, no baseless personal insults.\n\nRule 2 -\nNo comparing artificial intelligence/machine learning models to cryptocurrency. I.E no comparing the usefulness of models to that of NFTs, no comparing the resource usage required to train a model is anything close to maintaining a blockchain/ mining for crypto, no implying its just a fad/bubble that will leave people with nothing of value when it burst.\n\nRule 3 -\nNo comparing artificial intelligence/machine learning to simple text prediction algorithms. I.E statements such as \"llms are basically just simple text predictions like what your phone keyboard autocorrect uses, and they're still using the same algorithms since .\n\nRule 4 -\nNo implying that models are devoid of purpose or potential for enriching peoples lives.","removed":false,"published":"2023-06-08T18:21:54.578976Z","updated":"2025-06-09T20:51:11.460711Z","deleted":false,"nsfw":false,"actor_id":"https://sh.itjust.works/c/localllama","local":false,"icon":"https://sh.itjust.works/pictrs/image/8e07ec26-c7e5-4411-a4d5-c0c7a292b773.gif","banner":"https://sh.itjust.works/pictrs/image/5d07b398-7675-4862-8277-5906400b666d.png","hidden":false,"posting_restricted_to_mods":false,"instance_id":72342,"visibility":"Public"},"counts":{"comment_id":6367756,"score":2,"upvotes":2,"downvotes":0,"published":"2024-02-11T14:04:10Z","child_count":1},"creator_banned_from_community":false,"banned_from_community":false,"creator_is_moderator":false,"creator_is_admin":false,"subscribed":"NotSubscribed","saved":false,"creator_blocked":false},{"comment":{"id":6367926,"creator_id":107319,"post_id":8155975,"content":"Nice. Thanks. I'll save this post in case I use ollama in the future. Right now I use a codellama model and a mythomax model, but am not running them via a localhost server, just outputted in the terminal or LMStudio.\n\nThis looks interesting though. Thanks!","removed":false,"published":"2024-02-11T14:16:18.944040Z","deleted":false,"ap_id":"https://lemmy.ml/comment/8199475","local":false,"path":"0.6082124.6085769.6360418.6362114.6367756.6367926","distinguished":false,"language_id":37},"creator":{"id":107319,"name":"z3rOR0ne","display_name":"z3rOR0ne","avatar":"https://lemmy.ml/pictrs/image/7e102035-823f-409d-aef9-4a72688622c2.jpeg","banned":false,"published":"2022-02-22T11:37:28.928852Z","updated":"2022-02-23T11:26:23.967618Z","actor_id":"https://lemmy.ml/u/z3rOR0ne","bio":"Fuck Nationalists, White Supremacists, Nazis, Fascists, The Patriarchy, Maga, Racists, Transphobes, Terfs, Homophobes, the Police.","local":false,"banner":"https://lemmy.ml/pictrs/image/5360b284-ee88-48c4-9e73-67e0252d8bcf.jpeg","deleted":false,"bot_account":false,"instance_id":195},"post":{"id":8155975,"name":"Meta releases ‘Code Llama 70B’, an open-source behemoth to rival private AI development","url":"https://venturebeat.com/ai/meta-releases-code-llama-70b-an-open-source-behemoth-to-rival-private-ai-development/","creator_id":114057,"community_id":2344,"removed":false,"locked":false,"published":"2024-01-29T21:25:05.753168Z","deleted":false,"nsfw":false,"embed_title":"Meta releases ‘Code Llama 70B’, an open-source behemoth to rival private AI development","embed_description":"Code Llama 70B is a new and improved version of Meta AI’s code generation model that can write code in various programming languages from natural language prompts or existing code snippets.","thumbnail_url":"https://lemmy.blahaj.zone/pictrs/image/66a3f45d-6881-4e4f-9bfe-0d2545c7f15f.webp","ap_id":"https://lemmy.ml/post/11219477","local":false,"language_id":37,"featured_community":false,"featured_local":false,"url_content_type":"text/html; charset=utf-8"},"community":{"id":2344,"name":"localllama","title":"LocalLLaMA","description":"Welcome to LocalLLaMA! Here we discuss running and developing machine learning models at home. Lets explore cutting edge open source neural network technology together.\n\nGet support from the community! Ask questions, share prompts, discuss benchmarks, get hyped at the latest and greatest model releases! Enjoy talking about our awesome hobby.\n\nAs ambassadors of the self-hosting machine learning community, we strive to support each other and share our enthusiasm in a positive constructive way.\n\nRules:\n\nRule 1 -\nNo harassment or personal character attacks of community members. I.E no namecalling, no generalizing entire groups of people that make up our community, no baseless personal insults.\n\nRule 2 -\nNo comparing artificial intelligence/machine learning models to cryptocurrency. I.E no comparing the usefulness of models to that of NFTs, no comparing the resource usage required to train a model is anything close to maintaining a blockchain/ mining for crypto, no implying its just a fad/bubble that will leave people with nothing of value when it burst.\n\nRule 3 -\nNo comparing artificial intelligence/machine learning to simple text prediction algorithms. I.E statements such as \"llms are basically just simple text predictions like what your phone keyboard autocorrect uses, and they're still using the same algorithms since .\n\nRule 4 -\nNo implying that models are devoid of purpose or potential for enriching peoples lives.","removed":false,"published":"2023-06-08T18:21:54.578976Z","updated":"2025-06-09T20:51:11.460711Z","deleted":false,"nsfw":false,"actor_id":"https://sh.itjust.works/c/localllama","local":false,"icon":"https://sh.itjust.works/pictrs/image/8e07ec26-c7e5-4411-a4d5-c0c7a292b773.gif","banner":"https://sh.itjust.works/pictrs/image/5d07b398-7675-4862-8277-5906400b666d.png","hidden":false,"posting_restricted_to_mods":false,"instance_id":72342,"visibility":"Public"},"counts":{"comment_id":6367926,"score":0,"upvotes":0,"downvotes":0,"published":"2024-02-11T14:16:18.944040Z","child_count":0},"creator_banned_from_community":false,"banned_from_community":false,"creator_is_moderator":false,"creator_is_admin":false,"subscribed":"NotSubscribed","saved":false,"creator_blocked":false}]}