title stringlengths 1 300 | score int64 0 8.54k | selftext stringlengths 0 41.5k | created timestamp[ns]date 2023-04-01 04:30:41 2026-03-04 02:14:14 ⌀ | url stringlengths 0 878 | author stringlengths 3 20 | domain stringlengths 0 82 | edited timestamp[ns]date 1970-01-01 00:00:00 2026-02-19 14:51:53 | gilded int64 0 2 | gildings stringclasses 7
values | id stringlengths 7 7 | locked bool 2
classes | media stringlengths 646 1.8k ⌀ | name stringlengths 10 10 | permalink stringlengths 33 82 | spoiler bool 2
classes | stickied bool 2
classes | thumbnail stringlengths 4 213 ⌀ | ups int64 0 8.54k | preview stringlengths 301 5.01k ⌀ |
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
Minimalistic tool to find words & inspiration for txt2img prompts | 4 | Hey folks, this is not directly related to local language models, but I thought it might be useful for one or the other and a small contribution to the general democratization of AI.
I created this little html tool earlier because sometimes I have ideas about how I'd like an image to look like, but I can't think of t... | 2023-10-04T23:31:21 | https://www.reddit.com/r/LocalLLaMA/comments/1702bum/minimalistic_tool_to_find_words_inspiration_for/ | Evening_Ad6637 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 1702bum | false | null | t3_1702bum | /r/LocalLLaMA/comments/1702bum/minimalistic_tool_to_find_words_inspiration_for/ | false | false | self | 4 | {'enabled': False, 'images': [{'id': '5BMOFfzLyPpaS7ft0QrKjzHSogbGmcDD7JUO3TT-1SI', 'resolutions': [{'height': 54, 'url': 'https://external-preview.redd.it/oKXkMhlYo1KMnPBRz-6t5Vcwrx5Kt2QcNShyiNKXH10.jpg?width=108&crop=smart&auto=webp&s=04065d5e5f8b405585586b3a12a056991debf4a0', 'width': 108}, {'height': 108, 'url': 'h... |
Multiple sets of grammars | 3 | llama.cpp lets you force output into a specific format using the [grammar function](https://github.com/ggerganov/llama.cpp#constrained-output-with-grammars).
Does anyone know of a way to run multiple ones concurrently without loading the model twice or loading & unloading?
e.g. for some tasks I'd want to force:
( "Y... | 2023-10-04T23:30:01 | https://www.reddit.com/r/LocalLLaMA/comments/1702aki/multiple_sets_of_grammars/ | AnomalyNexus | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 1702aki | false | null | t3_1702aki | /r/LocalLLaMA/comments/1702aki/multiple_sets_of_grammars/ | false | false | self | 3 | {'enabled': False, 'images': [{'id': 'DJPqvteONpGwVVw6LzaG6b8vlDa2rv2hETCaqe0z57s', 'resolutions': [{'height': 54, 'url': 'https://external-preview.redd.it/wyCM1fHzTa-IIqHgS1QTxdSYNXn668elDj0WmYMPf_k.jpg?width=108&crop=smart&auto=webp&s=d6fa197328d583bcae7a764b40fd1214265b6852', 'width': 108}, {'height': 108, 'url': 'h... |
MistralOpenOrca7B: “Just remember, sometimes you gotta be the hero and take care of yourself first before worrying about everyone else.” | 41 | Just was playing around a bit with MistralOpenOrca (Q5_K_S GGUF) in KoboldCPP
I found it to be a pretty coherent guy. Still working on it, but out the box I like it a lot
Heres my random first conversation
___
Please converse with me as if you were a true bro.
Use evidence and reasoning to support your arguments,... | 2023-10-04T22:22:27 | https://www.reddit.com/gallery/1700lph | Happy_Chicken9835 | reddit.com | 1970-01-01T00:00:00 | 0 | {} | 1700lph | false | null | t3_1700lph | /r/LocalLLaMA/comments/1700lph/mistralopenorca7b_just_remember_sometimes_you/ | false | false | 41 | null | |
Beginner friendly Guide to run local model AI on 4 Gb ram windows (GGML/GGUF Guide) | 23 | This guide would not have been possible without the guidance and contributions of everyone at [r/LocalLLaMA](https://www.reddit.com/r/LocalLLaMA/). This report aims to provide users with limitations an opportunity to taste and experience running modules locally for a valuable learning experience. This knowledge w... | 2023-10-04T22:21:49 | https://www.reddit.com/r/LocalLLaMA/comments/1700l6g/beginner_friendly_guide_to_run_local_model_ai_on/ | Merchant_Lawrence | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 1700l6g | false | null | t3_1700l6g | /r/LocalLLaMA/comments/1700l6g/beginner_friendly_guide_to_run_local_model_ai_on/ | false | false | 23 | null | |
How do I set up a custom llama 2 via gpt4all | 2 | I'm trying to set up [TheBloke/WizardLM-1.0-Uncensored-Llama2-13B-GGUF](https://huggingface.co/TheBloke/WizardLM-1.0-Uncensored-Llama2-13B-GGUF) and have tried many different methods, but none have worked for me so far:
* I tried [llama.cpp](https://github.com/ggerganov/llama.cpp) and in the documentation, after clon... | 2023-10-04T22:02:01 | https://www.reddit.com/r/LocalLLaMA/comments/17002vr/how_do_i_set_up_a_custom_llama_2_via_gpt4all/ | Cheems63 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 17002vr | false | null | t3_17002vr | /r/LocalLLaMA/comments/17002vr/how_do_i_set_up_a_custom_llama_2_via_gpt4all/ | false | false | self | 2 | {'enabled': False, 'images': [{'id': '3iQQMehHPVNysewq5hw1v-4K8TDxGRDZead__gh71uw', 'resolutions': [{'height': 58, 'url': 'https://external-preview.redd.it/tUIt8hI7Pks1v6xy0_W_C8fucyRbmXVeOzNtHh-J4-U.jpg?width=108&crop=smart&auto=webp&s=46c2be98f47f6252fbbb92b5651d84e6c3a46910', 'width': 108}, {'height': 116, 'url': 'h... |
Google Deepmind researchers demonstrate Promptbreeder, an AI system that can improve itself by recursively generating better prompts. | 85 | 2023-10-04T21:27:45 | https://arxiv.org/pdf/2309.16797.pdf | metalman123 | arxiv.org | 1970-01-01T00:00:00 | 0 | {} | 16zz70s | false | null | t3_16zz70s | /r/LocalLLaMA/comments/16zz70s/google_deepmind_researchers_demonstrate/ | false | false | default | 85 | null | |
Advice requested on the best model to help with documents and SQL | 2 | Hi,
I work for a charity organisation in my spare time, and need a way to construct some SQL code from a large set of interlinked tables that follows a complex set of rules based on the national and local charities regulations.
The rules are all in various word documents.
To create this manually will take me a few m... | 2023-10-04T20:28:39 | https://www.reddit.com/r/LocalLLaMA/comments/16zxp50/advice_requested_on_the_best_model_to_help_with/ | Paleion | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 16zxp50 | false | null | t3_16zxp50 | /r/LocalLLaMA/comments/16zxp50/advice_requested_on_the_best_model_to_help_with/ | false | false | self | 2 | null |
Open-Source LLMs vs OpenAI: a Detailed Overview | 1 | [removed] | 2023-10-04T20:18:05 | https://www.reddit.com/r/LocalLLaMA/comments/16zxfok/opensource_llms_vs_openai_a_detailed_overview/ | Noe_Achache | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 16zxfok | false | null | t3_16zxfok | /r/LocalLLaMA/comments/16zxfok/opensource_llms_vs_openai_a_detailed_overview/ | false | false | 1 | {'enabled': False, 'images': [{'id': 'iF4ARoem27pth3ZEgIq7amCDxiaiEBylOvdUlgzSZ9s', 'resolutions': [{'height': 78, 'url': 'https://external-preview.redd.it/IsNo8duXibR0K_GoT8_pDLjK4xdAgtXz6U2kroidqSo.jpg?width=108&crop=smart&auto=webp&s=f69115d00672065ebddaef8db9be33c6348c4527', 'width': 108}, {'height': 157, 'url': 'h... | |
Open-Source LLMs vs OpenAI: a Detailed Overview | 1 | 2023-10-04T20:07:20 | https://www.sicara.fr/blog-technique/open-source-llms-vs-openai | Noe_Achache | sicara.fr | 1970-01-01T00:00:00 | 0 | {} | 16zx63d | false | null | t3_16zx63d | /r/LocalLLaMA/comments/16zx63d/opensource_llms_vs_openai_a_detailed_overview/ | false | false | 1 | {'enabled': False, 'images': [{'id': 'iF4ARoem27pth3ZEgIq7amCDxiaiEBylOvdUlgzSZ9s', 'resolutions': [{'height': 78, 'url': 'https://external-preview.redd.it/IsNo8duXibR0K_GoT8_pDLjK4xdAgtXz6U2kroidqSo.jpg?width=108&crop=smart&auto=webp&s=f69115d00672065ebddaef8db9be33c6348c4527', 'width': 108}, {'height': 157, 'url': 'h... | ||
LLM Boxing: Llama2-13b-Instruct vs. Mistral-7b-Instruct, a blind test comparison | 76 | 2023-10-04T18:13:41 | https://llmboxing.com/ | jakedahn | llmboxing.com | 1970-01-01T00:00:00 | 0 | {} | 16zudcg | false | null | t3_16zudcg | /r/LocalLLaMA/comments/16zudcg/llm_boxing_llama213binstruct_vs_mistral7binstruct/ | false | false | default | 76 | null | |
After 500+ LoRAs made, here is the secret | 673 | Well, you wanted it, here it is:
The quality of dataset is 95% of everything. The rest 5% is not to ruin it with bad parameters.
Yeah, I know, GASP! No seriously, folks are searching for secret parameters or secret sauce - but this is the whole deal.
And I mean crystal clean dataset. Yes, I know, thousands of items ... | 2023-10-04T18:12:32 | https://www.reddit.com/r/LocalLLaMA/comments/16zuccy/after_500_loras_made_here_is_the_secret/ | FPham | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 16zuccy | false | null | t3_16zuccy | /r/LocalLLaMA/comments/16zuccy/after_500_loras_made_here_is_the_secret/ | false | false | self | 673 | null |
Possible to build an expert AI on a specific topic but it will have a larger context | 0 | GPT 4 has been immensely helpful in helping in a dev project without any knowledge of the tech stack. Backend person doing Frontend stuff. But it will lose the context completely after few queries.
Is it possible to have a specific AI expert with 3 features:
1. Expert knowledge on a particular field say web developm... | 2023-10-04T17:53:44 | https://www.reddit.com/r/LocalLLaMA/comments/16ztw1t/possible_to_build_an_expert_ai_on_a_specific/ | algo314 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 16ztw1t | false | null | t3_16ztw1t | /r/LocalLLaMA/comments/16ztw1t/possible_to_build_an_expert_ai_on_a_specific/ | false | false | self | 0 | null |
Do you think most people... | 8 |
[View Poll](https://www.reddit.com/poll/16zsrmb) | 2023-10-04T17:09:19 | https://www.reddit.com/r/LocalLLaMA/comments/16zsrmb/do_you_think_most_people/ | upk27 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 16zsrmb | false | null | t3_16zsrmb | /r/LocalLLaMA/comments/16zsrmb/do_you_think_most_people/ | false | false | self | 8 | null |
Self fine-tuning models? | 3 | So I'm of the belief that the next gen of AI assistance is going to require these models to continually learn and update themselves in a natural way. For example if I want to have a truly useful customer service bot for my company, I want to be able to train it exactly the way I train a new employee. By telling it what... | 2023-10-04T16:57:23 | https://www.reddit.com/r/LocalLLaMA/comments/16zsgxt/self_finetuning_models/ | Darius510 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 16zsgxt | false | null | t3_16zsgxt | /r/LocalLLaMA/comments/16zsgxt/self_finetuning_models/ | false | false | self | 3 | null |
Evaluating Retrieval-Augmented Generation (RAG) with any combination of LLMs, Vector DBs, and Ingestion Strategy | 1 | [removed] | 2023-10-04T16:47:26 | https://www.reddit.com/r/LocalLLaMA/comments/16zs853/evaluating_retrievalaugmented_generation_rag_with/ | hegel-ai | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 16zs853 | false | null | t3_16zs853 | /r/LocalLLaMA/comments/16zs853/evaluating_retrievalaugmented_generation_rag_with/ | false | false | self | 1 | {'enabled': False, 'images': [{'id': 'iFtB8HdX4i7hEwNm_Uyp_-GqKtmX2B300xFXD0iwA8w', 'resolutions': [{'height': 54, 'url': 'https://external-preview.redd.it/Z_iFcp51CII6r9HXTtw9BH3YHR-JL3DSgrFNt-SdeaQ.jpg?width=108&crop=smart&auto=webp&s=e56b82505eb15f1307639f07151b53a3d286db24', 'width': 108}, {'height': 108, 'url': 'h... |
Can you combine meta's SAM with a open source model to get something close to GPT Vision? | 6 | I was playing around with the vision extension in chat GPT recently and trying to figure out how they were doing it on the backend.
I was then wondering how close you'd be able to get to their results if you did something as simple as matching the prompt you sent with an image to different segmentation categories in ... | 2023-10-04T16:35:51 | https://www.reddit.com/r/LocalLLaMA/comments/16zrxo6/can_you_combine_metas_sam_with_a_open_source/ | Embarrassed-Creme338 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 16zrxo6 | false | null | t3_16zrxo6 | /r/LocalLLaMA/comments/16zrxo6/can_you_combine_metas_sam_with_a_open_source/ | false | false | self | 6 | null |
LLaMA 2 Long where? | 15 | So, [META has a 32K context length LLaMA2](https://reddit.com/r/LocalLLaMA/s/V7I5XfIbtA), but no weights have been made public that I have heard of.
Is there any way to get these weights? | 2023-10-04T15:49:16 | https://www.reddit.com/r/LocalLLaMA/comments/16zqqru/llama_2_long_where/ | 2muchnet42day | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 16zqqru | false | null | t3_16zqqru | /r/LocalLLaMA/comments/16zqqru/llama_2_long_where/ | false | false | self | 15 | null |
What exactly does a Lora do? | 34 | I just read about a lora and what i think it does you can train pretrained models with that with your own data so could it be possible and train an censored model with answears from uncensored model that are worse to make the model uncensored or did i understand something wrong? | 2023-10-04T15:03:39 | https://www.reddit.com/r/LocalLLaMA/comments/16zpkve/what_exactly_does_a_lora_do/ | Otherwise_Weather_57 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 16zpkve | false | null | t3_16zpkve | /r/LocalLLaMA/comments/16zpkve/what_exactly_does_a_lora_do/ | false | false | self | 34 | null |
Should I start this project? | 15 | Hello everyone. Thanks for taking the time to read this.
tldr: Seeking Feedback on a Customizable AI Module for PCs.
I've been getting interested in hardware design. This started around the same time Falcon-180b was released. I saw people running it on Mac M2s and saw that the original researchers used several thousa... | 2023-10-04T14:51:51 | https://www.reddit.com/r/LocalLLaMA/comments/16zp9ya/should_i_start_this_project/ | DatOneGuy73 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 16zp9ya | false | null | t3_16zp9ya | /r/LocalLLaMA/comments/16zp9ya/should_i_start_this_project/ | false | false | self | 15 | null |
How can i use models that have <|im_start/end|> with llama.cpp? | 5 | This is the command that i am currently using:
./main \
-i \
--seed 69 \
--model "$models_dir/$model_name" \
--mlock \
--ctx-size 2048 \
--repeat-last-n 256 \
--repeat-penalty 1.1 \
--n_predict 512 \
--temp 0.7 \
--top-k 60 \
--top-p 1.0 \
--interactive \... | 2023-10-04T14:46:19 | https://www.reddit.com/r/LocalLLaMA/comments/16zp4ro/how_can_i_use_models_that_have_im_startend_with/ | IonizedRay | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 16zp4ro | false | null | t3_16zp4ro | /r/LocalLLaMA/comments/16zp4ro/how_can_i_use_models_that_have_im_startend_with/ | false | false | self | 5 | null |
Is the P40 on the sidelines? | 5 | I have a P40. Is commit dadbed9 from llama.cpp really the end of the line? Will anything happen in the development of new models that run on this card? Is it possible to run F16 models in F32 at the cost of half VRAM? If so, would that be useful? | 2023-10-04T14:27:38 | https://www.reddit.com/r/LocalLLaMA/comments/16zoo9t/is_the_p40_on_the_sidelines/ | muxxington | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 16zoo9t | false | null | t3_16zoo9t | /r/LocalLLaMA/comments/16zoo9t/is_the_p40_on_the_sidelines/ | false | false | self | 5 | null |
local open source GitHub Copilot in VSCode using Oobabooga | 15 | I wrote a small script to translate calls between VSCode GitHub copilot and oobabooga instead of the proprietary backend
https://preview.redd.it/9mcjisqsz6sb1.png?width=1413&format=png&auto=webp&s=459b3102e00e5cb001677579efde0454f45e25ac
​
video: [https://twitter.com/theeFaris/status/1694622487861252359](htt... | 2023-10-04T14:02:41 | https://www.reddit.com/r/LocalLLaMA/comments/16zo2ek/local_open_source_github_copilot_in_vscode_using/ | BuzaMahmooza | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 16zo2ek | false | {'oembed': {'author_name': 'Faris Hijazi 🇵🇸🇸🇦', 'author_url': 'https://twitter.com/theeFaris', 'cache_age': 3153600000, 'height': None, 'html': '<blockquote class="twitter-video"><p lang="en" dir="ltr">🚀 Exciting News! After a week of work, I'm thrilled to introduce 🔥 a private alternative to GitHub Copilot<b... | t3_16zo2ek | /r/LocalLLaMA/comments/16zo2ek/local_open_source_github_copilot_in_vscode_using/ | false | false | 15 | {'enabled': False, 'images': [{'id': 'C6tRAa5WedRX-W5Va33S2Ej789tct7sinoTGhR8-MBI', 'resolutions': [{'height': 60, 'url': 'https://external-preview.redd.it/XX8BV_7gKwHmOJjPYwnin7_pqy7DEp2N8r9NfGIPFEo.jpg?width=108&crop=smart&auto=webp&s=710b855f93337d6c5432cd95fe7d5badbf4d4f1b', 'width': 108}], 'source': {'height': 78,... | |
A simple utility to gather LIMA-like datasets | 16 | Good day to everyone!
Going straight to the point, I have developed a utility to simplify gathering LIMA-like data: [oKatanaaa/lima-gui: A simple GUI utility for gathering LIMA-like chat data. (github.com)](https://github.com/oKatanaaa/lima-gui)
It has simple PyQt-based UI and allows for easy gathering of small hand... | 2023-10-04T13:47:32 | https://www.reddit.com/r/LocalLLaMA/comments/16znpf6/a_simple_utility_to_gather_limalike_datasets/ | oKatanaa | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 16znpf6 | false | null | t3_16znpf6 | /r/LocalLLaMA/comments/16znpf6/a_simple_utility_to_gather_limalike_datasets/ | false | false | self | 16 | {'enabled': False, 'images': [{'id': 'OLEUbnMyXswWBxC2Z7_qjcu19Za2DnpVGiQrkv183wE', 'resolutions': [{'height': 54, 'url': 'https://external-preview.redd.it/UZqZPUog6eB7BYgx86NVIvNUMSKJ1wVBy4rLPMiBxfk.jpg?width=108&crop=smart&auto=webp&s=d1ad9027b2f1d5d49af3e6cf99d4a0c72a06d3fd', 'width': 108}, {'height': 108, 'url': 'h... |
Elon Musk announces give away event for Bitcoins, limited time available. | 14 | 2023-10-04T13:10:23 | littlex-xbones | i.redd.it | 1970-01-01T00:00:00 | 0 | {} | 16zmuiy | false | null | t3_16zmuiy | /r/LocalLLaMA/comments/16zmuiy/elon_musk_announces_give_away_event_for_bitcoins/ | false | false | 14 | {'enabled': True, 'images': [{'id': '-B4KcyYVeWG-ACE1UMlq73TeLC8qsxe_jvn7y8B-lO4', 'resolutions': [{'height': 144, 'url': 'https://preview.redd.it/8wkzelxjq6sb1.gif?width=108&crop=smart&format=png8&s=f1497f6885f6ee51ab6cddb16d44b94ee83dbf26', 'width': 108}, {'height': 288, 'url': 'https://preview.redd.it/8wkzelxjq6sb1.... | |||
Guide How to run module for user with 4 gb Ram (GGML/GGUF Guide) for newcomer | 19 | This guide would not have been possible without the guidance and contributions of everyone at r/LocalLLaMA. This report aims to provide users with limitations an opportunity to taste and experience running modules locally for a valuable learning experience. This knowledge will be invaluable when users are financial... | 2023-10-04T13:02:01 | https://www.reddit.com/r/LocalLLaMA/comments/16zmnop/guide_how_to_run_module_for_user_with_4_gb_ram/ | Merchant_Lawrence | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 16zmnop | false | null | t3_16zmnop | /r/LocalLLaMA/comments/16zmnop/guide_how_to_run_module_for_user_with_4_gb_ram/ | false | false | 19 | null | |
is there a way to implement non-GPTQ model on runpod serverless | 2 | I want to deploy this model [https://huggingface.co/Ammad1Ali/Alex-Test-GPT-1](https://huggingface.co/Ammad1Ali/Alex-Test-GPT-1) on serverless GPUs for API. I have used [https://github.com/hommayushi3/exllama-runpod-serverless](https://github.com/hommayushi3/exllama-runpod-serverless) template to run this but I am gett... | 2023-10-04T11:34:21 | https://www.reddit.com/r/LocalLLaMA/comments/16zks3t/is_there_a_way_to_implement_nongptq_model_on/ | _Sneaky_Bastard_ | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 16zks3t | false | null | t3_16zks3t | /r/LocalLLaMA/comments/16zks3t/is_there_a_way_to_implement_nongptq_model_on/ | false | false | self | 2 | {'enabled': False, 'images': [{'id': '2ZM_2irUT7-0w3szDeOIcW2JQcI4zAA6TF953ssvkWw', 'resolutions': [{'height': 58, 'url': 'https://external-preview.redd.it/YOokliebL8ApLFPU_IRDwfrKON8aG1HxNiO9NK7r5IA.jpg?width=108&crop=smart&auto=webp&s=3ed654ba15498547277e628ba4bbbcec8f6164c9', 'width': 108}, {'height': 116, 'url': 'h... |
I created an OS that boots to a baby llama2 | 200 | Dear AI folks
I have created a demo OS that boots to LLAMA2, there is a also a kernel module that calls a user mode helper to do llama2 inference. It uses our fork of karpathy's llama2.c, it is not very usable yet. But we hope to build it out and add better models. Please give it a try.
​
[It has a star trek ... | 2023-10-04T11:25:00 | https://www.reddit.com/r/LocalLLaMA/comments/16zklam/i_created_an_os_that_boots_to_a_baby_llama2/ | AMICABoard | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 16zklam | false | null | t3_16zklam | /r/LocalLLaMA/comments/16zklam/i_created_an_os_that_boots_to_a_baby_llama2/ | false | false | 200 | null | |
uncensored Llama2 training | 0 | If I want to fine tune the [https://huggingface.co/Tap-M/Luna-AI-Llama2-Uncensored](https://huggingface.co/Tap-M/Luna-AI-Llama2-Uncensored) with the ehartford/samantha-data, how much compute units would I need? And which is the best service for that? | 2023-10-04T11:07:34 | https://www.reddit.com/r/LocalLLaMA/comments/16zk9bg/uncensored_llama2_training/ | di_bee | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 16zk9bg | false | null | t3_16zk9bg | /r/LocalLLaMA/comments/16zk9bg/uncensored_llama2_training/ | false | false | self | 0 | {'enabled': False, 'images': [{'id': '0-TU1NHOIu_jbWk-tVY1N3FnNmOTs33czblwFaFE3zw', 'resolutions': [{'height': 58, 'url': 'https://external-preview.redd.it/05AaFuAKNndb1m98TX50ZYufQ5GqwIXscgaAqnkkpE8.jpg?width=108&crop=smart&auto=webp&s=4d4946b0bfd760274c7080ad34ed5879469bcf81', 'width': 108}, {'height': 116, 'url': 'h... |
Learning thru practice | 1 | Guys I have found a prettained llama model that can work locally. I tried it with the help of LM Studio. I intend to create a GUI for tasks like Text Summarisation, Content Chunking, etc.
How will the communication between the GUI and local LLM take place ?
For GUI I have been experimenting with the help of TKinter.... | 2023-10-04T10:25:44 | https://www.reddit.com/r/LocalLLaMA/comments/16zjiex/learning_thru_practice/ | inGenium_88 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 16zjiex | false | null | t3_16zjiex | /r/LocalLLaMA/comments/16zjiex/learning_thru_practice/ | false | false | self | 1 | null |
New macOS project lets you use local LLMs as the backend for GH's Copilot VSCode plugin | 18 | 2023-10-04T09:51:28 | https://github.com/danielgross/localpilot | i-like-plant | github.com | 1970-01-01T00:00:00 | 0 | {} | 16zixxu | false | null | t3_16zixxu | /r/LocalLLaMA/comments/16zixxu/new_macos_project_lets_you_use_local_llms_as_the/ | false | false | 18 | {'enabled': False, 'images': [{'id': 'aROnSAhi4b7nQwMkVoMBUU4rpOwRdZZKu7D_5sD-eoQ', 'resolutions': [{'height': 54, 'url': 'https://external-preview.redd.it/rDZv1nxjPjQXC9YnpShOqyFK0aPvb055BzYzS24p7vY.jpg?width=108&crop=smart&auto=webp&s=b0aa9f87af233cdc51b8e72cbed7bd3f5c458c8e', 'width': 108}, {'height': 108, 'url': 'h... | ||
Merging models? Anyone here know of a notebook? | 5 | Hey everyone! I'm really interested and curious about model merging, especially now with Mistral being such a powerhouse. I've been looking into the techniques that are used to create the Mytho- line of OS models but haven't come across a straightforward notebook or implementation I can adapt.
Anyone else have any lu... | 2023-10-04T09:24:07 | https://www.reddit.com/r/LocalLLaMA/comments/16ziiku/merging_models_anyone_here_know_of_a_notebook/ | vesudeva | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 16ziiku | false | null | t3_16ziiku | /r/LocalLLaMA/comments/16ziiku/merging_models_anyone_here_know_of_a_notebook/ | false | false | self | 5 | null |
Coding/Logic model for 2x 3090 | 2 | Hey everyone!
Does anyone know what is the best Model to fit on 2x 3090? I want to do coding basically but not be tied to a specific language.
And would I need an NVLink to get the most out of it... any thoughts??
Thanks!
​
​ | 2023-10-04T09:23:46 | https://www.reddit.com/r/LocalLLaMA/comments/16ziien/codinglogic_model_for_2x_3090/ | FreegheistOfficial | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 16ziien | false | null | t3_16ziien | /r/LocalLLaMA/comments/16ziien/codinglogic_model_for_2x_3090/ | false | false | self | 2 | null |
Cluster raspberry pi | 5 | I currently have 7 Raspberry Pis and I would like to make a cluster to run a model using llama.cpp or vllm but I don't understand everything with vllm I have the impression that they cannot work locally I don't know also not what would be the best option for connected with raspberry I plan to use tensorflow but I was ... | 2023-10-04T09:13:10 | https://www.reddit.com/r/LocalLLaMA/comments/16zicpp/cluster_raspberry_pi/ | Terrible_Vegetable4 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 16zicpp | false | null | t3_16zicpp | /r/LocalLLaMA/comments/16zicpp/cluster_raspberry_pi/ | false | false | self | 5 | null |
Using LLM to access local notes | 5 | I use Obsidian so all my notes are in plaintext. Is there currently a fairly out of the box way / plugin to have a local model inference my local files? Say, I ask it about what I was journaling about 6 months ago. it would do a simple search, and summarize e.g note 01-01-2019. | 2023-10-04T09:09:41 | https://www.reddit.com/r/LocalLLaMA/comments/16ziare/using_llm_to_access_local_notes/ | Kep0a | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 16ziare | false | null | t3_16ziare | /r/LocalLLaMA/comments/16ziare/using_llm_to_access_local_notes/ | false | false | self | 5 | null |
Best presets for RP/character following | 4 | What model-presets are you using for Role Playing? I'm using oobabooga as backend and character cards from there but at some point the answers become generic. I know you need to be really clear when you create characters but I would like to know what you guys find the best for presets.
I'm running Mythomax13B and Xw... | 2023-10-04T09:02:09 | https://www.reddit.com/r/LocalLLaMA/comments/16zi6jt/best_presets_for_rpcharacter_following/ | sarimsak13 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 16zi6jt | false | null | t3_16zi6jt | /r/LocalLLaMA/comments/16zi6jt/best_presets_for_rpcharacter_following/ | false | false | self | 4 | null |
RHLF + LLaVa = rlhf llava | 29 | 2023-10-04T08:26:17 | https://llava-rlhf.github.io/ | ninjasaid13 | llava-rlhf.github.io | 1970-01-01T00:00:00 | 0 | {} | 16zhmtf | false | null | t3_16zhmtf | /r/LocalLLaMA/comments/16zhmtf/rhlf_llava_rlhf_llava/ | false | false | default | 29 | null | |
How to incorporate RAG in llama2 7b chat-hf custom fine-tuned model? | 1 | [removed] | 2023-10-04T07:51:25 | https://www.reddit.com/r/LocalLLaMA/comments/16zh3bc/how_to_incorporate_rag_in_llama2_7b_chathf_custom/ | Anu_Rag9704 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 16zh3bc | false | null | t3_16zh3bc | /r/LocalLLaMA/comments/16zh3bc/how_to_incorporate_rag_in_llama2_7b_chathf_custom/ | false | false | self | 1 | null |
I want to be free from Openai | 1 | Hello folks,
Like many, I feel limited and under the mercy of Openai API.
I want to replace it with LLAMA-2 or a similar open source model.
Does any one know how to use such models for text extraction from large text files?
Appreciate your support 🙏 | 2023-10-04T07:28:48 | https://www.reddit.com/r/LocalLLaMA/comments/16zgqv8/i_want_to_be_free_from_openai/ | Pure-Bread-3196 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 16zgqv8 | false | null | t3_16zgqv8 | /r/LocalLLaMA/comments/16zgqv8/i_want_to_be_free_from_openai/ | false | false | self | 1 | null |
Conversational Benchmarks? | 10 | Is there a benchmark for conversational ability? And if so, how is that assessed?
All the benchmarks that I've came across so far appear to be related to easily measurable outcomes like scores on tests or real world awareness/comparatives, but I could be misunderstanding.
Basically, I wanted to know for LLM roleplayi... | 2023-10-04T07:28:32 | https://www.reddit.com/r/LocalLLaMA/comments/16zgqps/conversational_benchmarks/ | IntolerantModerate | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 16zgqps | false | null | t3_16zgqps | /r/LocalLLaMA/comments/16zgqps/conversational_benchmarks/ | false | false | self | 10 | null |
Enterprise looking to run an LLM locally & train it? Happy to help for free | 1 | [removed] | 2023-10-04T07:17:33 | https://www.reddit.com/r/LocalLLaMA/comments/16zgkio/enterprise_looking_to_run_an_llm_locally_train_it/ | itssualgoodman | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 16zgkio | false | null | t3_16zgkio | /r/LocalLLaMA/comments/16zgkio/enterprise_looking_to_run_an_llm_locally_train_it/ | false | false | self | 1 | null |
Mistral 7B with a conversational Agent on tabular data | 1 | [removed] | 2023-10-04T06:35:48 | https://www.reddit.com/r/LocalLLaMA/comments/16zfwg2/mistral_7b_with_a_conversational_agent_on_tabular/ | ianuvrat | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 16zfwg2 | false | null | t3_16zfwg2 | /r/LocalLLaMA/comments/16zfwg2/mistral_7b_with_a_conversational_agent_on_tabular/ | false | false | self | 1 | null |
Think before you speak: Training Language Models With Pause Tokens | 91 | 2023-10-04T05:04:23 | https://twitter.com/arankomatsuzaki/status/1709372124891070915?t=4omztfPu9S9Sj7gCi2OP0A&s=19 | metalman123 | twitter.com | 1970-01-01T00:00:00 | 0 | {} | 16zeb9s | false | {'oembed': {'author_name': 'Aran Komatsuzaki', 'author_url': 'https://twitter.com/arankomatsuzaki', 'cache_age': 3153600000, 'height': None, 'html': '<blockquote class="twitter-video"><p lang="en" dir="ltr">Think before you speak: Training Language Models With Pause Tokens<br><br>- Performing training and inference on ... | t3_16zeb9s | /r/LocalLLaMA/comments/16zeb9s/think_before_you_speak_training_language_models/ | false | false | 91 | {'enabled': False, 'images': [{'id': '5nBmZ8cZnKLof2ZQ-eDto_1rhK1qXwyS3mUMUk6C1qo', 'resolutions': [{'height': 103, 'url': 'https://external-preview.redd.it/x21wKA2yREmo9oW2LmQ2F-OgYxiXOYZv3LxbjsxUtGs.jpg?width=108&crop=smart&auto=webp&s=73f91147cab5ac1059d3a594e96a75615714975d', 'width': 108}], 'source': {'height': 13... | ||
0.1 Token/second or 280 second average Zarablend L2 7B - GGUF Q2 4 gb Ram with Kobold | 11 | 2023-10-04T04:53:13 | Merchant_Lawrence | i.redd.it | 1970-01-01T00:00:00 | 0 | {} | 16ze3vo | false | null | t3_16ze3vo | /r/LocalLLaMA/comments/16ze3vo/01_tokensecond_or_280_second_average_zarablend_l2/ | false | false | 11 | {'enabled': True, 'images': [{'id': 'lWQbOTj2iGpkLehcVSgWyJbUw8057a9zZ7aaNSd-k-g', 'resolutions': [{'height': 60, 'url': 'https://preview.redd.it/e2gdq1pp94sb1.png?width=108&crop=smart&auto=webp&s=4017a7470cf4bd4467d5f7df2af22666d2c2c72d', 'width': 108}, {'height': 121, 'url': 'https://preview.redd.it/e2gdq1pp94sb1.png... | |||
Can i connect smart watch to LLaMA | 1 | Is there any way I can connect my smartwatch to a LLM running on cloud, the watch will listen to everything going on around the person and take notes, which can be accessed later by the person ?? | 2023-10-04T04:44:21 | https://www.reddit.com/r/LocalLLaMA/comments/16zdxx5/can_i_connect_smart_watch_to_llama/ | spankmedaddy_69420 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 16zdxx5 | false | null | t3_16zdxx5 | /r/LocalLLaMA/comments/16zdxx5/can_i_connect_smart_watch_to_llama/ | false | false | self | 1 | null |
Meeting minutes generator | 0 | I would like to replicate the tutorial suggested [here](https://platform.openai.com/docs/tutorials/meeting-minutes) to create meetings minutes but locally, avoiding sending out to openAI the content discussed. Which model is better suited for this task? | 2023-10-04T03:49:08 | https://www.reddit.com/r/LocalLLaMA/comments/16zcwyh/meeting_minutes_generator/ | valkiii | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 16zcwyh | false | null | t3_16zcwyh | /r/LocalLLaMA/comments/16zcwyh/meeting_minutes_generator/ | false | false | self | 0 | {'enabled': False, 'images': [{'id': 'XjYeH9UKcgyOWN9BfsAvdRtig11MoY4NbGzf8T8tohc', 'resolutions': [{'height': 56, 'url': 'https://external-preview.redd.it/nEedMLn73AsJU6AgxrHz6cvr0_KUZAuY26VUpixUKp8.jpg?width=108&crop=smart&auto=webp&s=3f9105ef3e7b58900470546335a78fe533005bb4', 'width': 108}, {'height': 113, 'url': 'h... |
Llama Function Calling with GBNF | 0 | I was able to get the Mistral model to successfully make a function call using the JSON GBNF in [llama-cpp-python](https://github.com/abetlen/llama-cpp-python/discussions/397).
It's fairly consistent.
[Checkout the notebook](https://github.com/teleprint-me/py.gpt.prompt/blob/main/docs/notebooks/llama_cpp_grammar_api... | 2023-10-04T03:14:17 | https://www.reddit.com/r/LocalLLaMA/comments/16zc81u/llama_function_calling_with_gbnf/ | teleprint-me | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 16zc81u | false | null | t3_16zc81u | /r/LocalLLaMA/comments/16zc81u/llama_function_calling_with_gbnf/ | false | false | self | 0 | {'enabled': False, 'images': [{'id': 'oR9SFLE90Dww5d_5FHE7p8ioVNJKjaM4BGJWSsYdwYk', 'resolutions': [{'height': 54, 'url': 'https://external-preview.redd.it/DgPoAOAzAQC76VKafHUh1iezj8wuNCp-rllHgRulttw.jpg?width=108&crop=smart&auto=webp&s=7caab59efeaf513994a5f7b076fa880d07e10a77', 'width': 108}, {'height': 108, 'url': 'h... |
[NEWBIE] desperately seeking help on finetuning llama2 | 1 | **Background**
I barely know anything about LLM. And I just learnt python recently. Total newbie in IT field. My internship requires me to finetune llama2 for internal use locally. Ive been struggling for quite a few months now, learning all from the internet, but encountering tons of problem I couldnt even know how ... | 2023-10-04T02:06:11 | https://www.reddit.com/r/LocalLLaMA/comments/16zar51/newbie_desperately_seeking_help_on_finetuning/ | Goo-Bello-Cello | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 16zar51 | false | null | t3_16zar51 | /r/LocalLLaMA/comments/16zar51/newbie_desperately_seeking_help_on_finetuning/ | false | false | self | 1 | null |
Where do you fine-tune your LLMs? | 48 | I am curious how people in here go about fine-tuning their LLMs.
Do you rent a GPU in the cloud?
Do you do it at your local machine?
Do you use Google Colab?
Any other options? | 2023-10-04T01:31:47 | https://www.reddit.com/r/LocalLLaMA/comments/16z9zra/where_do_you_finetune_your_llms/ | Acceptable_Bed7015 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 16z9zra | false | null | t3_16z9zra | /r/LocalLLaMA/comments/16z9zra/where_do_you_finetune_your_llms/ | false | false | self | 48 | null |
What models should I be looking at today? | 33 | I'm really just looking to do some experimentation and tweaking with locally hosted LLMs. Some data you don't want to trust to AutoGPT, and I'd like to see how capable models that can be hosted affordably can do.
Given the following platform, what are the current models I should be considering and testing?
* Ryzen 9... | 2023-10-03T22:18:21 | https://www.reddit.com/r/LocalLLaMA/comments/16z5eat/what_models_should_i_be_looking_at_today/ | retire-early | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 16z5eat | false | null | t3_16z5eat | /r/LocalLLaMA/comments/16z5eat/what_models_should_i_be_looking_at_today/ | false | false | self | 33 | null |
Best tools for automated generation of questions and answers from unstructured text | 5 | I’m a researcher who is very interested in training LORAs on top of a small LLM (e.g. Mistral-7B-OpenOrca) with textbooks from my specialty. Does anyone here have any recommendations for tools to transform this text to pairs of questions and answers? Thanks! | 2023-10-03T21:39:34 | https://www.reddit.com/r/LocalLLaMA/comments/16z4dkz/best_tools_for_automated_generation_of_questions/ | SirStagMcprotein | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 16z4dkz | false | null | t3_16z4dkz | /r/LocalLLaMA/comments/16z4dkz/best_tools_for_automated_generation_of_questions/ | false | false | self | 5 | null |
Which models are Free to Deploy as part of a Commercial Product | 2 | Basically, are there any models that can be run on user's computers along with shipped software (as in, not just running on some server I have)? Bonus if you know of lighter weight ones that allow this in the license.
In other words, does 'free for commercial use' apply only to the text output of the model, or to the... | 2023-10-03T21:36:38 | https://www.reddit.com/r/LocalLLaMA/comments/16z4aqe/which_models_are_free_to_deploy_as_part_of_a/ | marmoset3 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 16z4aqe | false | null | t3_16z4aqe | /r/LocalLLaMA/comments/16z4aqe/which_models_are_free_to_deploy_as_part_of_a/ | false | false | self | 2 | null |
Can someone explain simply: How/why do small models (llama-2 7b) outperform larger ones (chinchilla 70b)? | 33 | Obviously "efficiency improvements" is the answer, but can someone explain the details of this more in as simple way? | 2023-10-03T21:33:55 | https://www.reddit.com/r/LocalLLaMA/comments/16z486f/can_someone_explain_simply_howwhy_do_small_models/ | cold-depths | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 16z486f | false | null | t3_16z486f | /r/LocalLLaMA/comments/16z486f/can_someone_explain_simply_howwhy_do_small_models/ | false | false | self | 33 | null |
LLMs inference comparison | 86 | 2023-10-03T21:08:24 | Wrong_User_Logged | i.redd.it | 1970-01-01T00:00:00 | 0 | {} | 16z3jps | false | null | t3_16z3jps | /r/LocalLLaMA/comments/16z3jps/llms_inference_comparison/ | false | false | 86 | {'enabled': True, 'images': [{'id': 'LjQ9UaV8upfruBybJYIkZ0qVlF6UJbmUoxcFR_vQW3E', 'resolutions': [{'height': 62, 'url': 'https://preview.redd.it/44kjvezny1sb1.png?width=108&crop=smart&auto=webp&s=cad36c9b7f114d26fef6a7b2872214a7df5a8abd', 'width': 108}, {'height': 125, 'url': 'https://preview.redd.it/44kjvezny1sb1.png... | |||
LLM Chat/RP Comparison/Test: Dolphin-Mistral, Mistral-OpenOrca, Synthia 7B | 201 | This is a follow-up to my [LLM Chat/RP Comparison/Test: Mistral 7B Base + Instruct](https://www.reddit.com/r/LocalLLaMA/comments/16twtfn/llm_chatrp_comparisontest_mistral_7b_base_instruct/) to take a closer look at the most popular new Mistral-based finetunes.
I actually updated the previous post with my reviews of Sy... | 2023-10-03T21:05:17 | https://www.reddit.com/r/LocalLLaMA/comments/16z3goq/llm_chatrp_comparisontest_dolphinmistral/ | WolframRavenwolf | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 16z3goq | false | null | t3_16z3goq | /r/LocalLLaMA/comments/16z3goq/llm_chatrp_comparisontest_dolphinmistral/ | false | false | self | 201 | {'enabled': False, 'images': [{'id': '2g4MtoKvhQOBCmeiXB1qv1h_5M24BeeYF64zcf4-rfg', 'resolutions': [{'height': 142, 'url': 'https://external-preview.redd.it/0z4RbV35RPDd2wqL6Oyz-uwz9kKNBAH0ePojGplYP2M.jpg?width=108&crop=smart&auto=webp&s=bbe38cbb6d4f7a7e6dd7d3c8b79c4ac9ba965545', 'width': 108}, {'height': 284, 'url': '... |
Epyc Genoa vs Threadripper Pro 7000? | 5 | TR Pro 7000 Pro/Con:
- Pro: higher single thread clock speed
- Con: 8 channels DDR5 is less than 12 channels DDR5
Not sure:
- if TR will have RDIMM support
- if TR will ever have 16 DIMM slot boards
- if TR will allow memory OC. I assume RDIMMs cannot be OC'd so with 8x48GB = 384GB total will be the limit for UDIM... | 2023-10-03T20:49:45 | https://www.reddit.com/r/LocalLLaMA/comments/16z322p/epyc_genoa_vs_threadripper_pro_7000/ | 0xd00d | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 16z322p | false | null | t3_16z322p | /r/LocalLLaMA/comments/16z322p/epyc_genoa_vs_threadripper_pro_7000/ | false | false | self | 5 | null |
(New Model) Rift Coder 7B. Python & TypeScript Fine-Tuned Code Llama for IDE Use | 30 | (Disclosure: I’m part of the team behind this lol)
We’re releasing [Rift Coder 7B](https://github.com/morph-labs/rift), our Python & TypeScript finetune of Code-Llama-7b-hf. We built it on top of [Glaive AI’s glaive-coder-7b](https://huggingface.co/glaiveai/glaive-coder-7b).
Fast facts – it’s free, it’s open source,... | 2023-10-03T20:05:05 | https://www.reddit.com/r/LocalLLaMA/comments/16z1xn2/new_model_rift_coder_7b_python_typescript/ | pranavmital | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 16z1xn2 | false | null | t3_16z1xn2 | /r/LocalLLaMA/comments/16z1xn2/new_model_rift_coder_7b_python_typescript/ | false | false | self | 30 | {'enabled': False, 'images': [{'id': 'v6025f4gMRjAE7sZZOCghGjaxWVekyQv_0dBhepaO6w', 'resolutions': [{'height': 54, 'url': 'https://external-preview.redd.it/r6atDvXw8LXLaZxTVVjMyJD8Shx7pUeFp5k79Jyt_Po.jpg?width=108&crop=smart&auto=webp&s=414c6db2df5be562ea5d25a6c9741ab333ca9319', 'width': 108}, {'height': 108, 'url': 'h... |
Rift Coder 7B. Python & TypeScript Fine-Tuned Code Llama for IDE Use | 1 | (Disclosure: I’m part of the team behind this lol)
We’re releasing \[Rift Coder 7B\]([https://github.com/morph-labs/rift](https://github.com/morph-labs/rift)), our Python & TypeScript finetune of Code-Llama-7b-hf. We built it on top of \[Glaive AI’s glaive-coder-7b\]([https://huggingface.co/glaiveai/glaive-coder-7b](... | 2023-10-03T20:02:00 | https://www.reddit.com/r/LocalLLaMA/comments/16z1uu4/rift_coder_7b_python_typescript_finetuned_code/ | pranavmital | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 16z1uu4 | false | null | t3_16z1uu4 | /r/LocalLLaMA/comments/16z1uu4/rift_coder_7b_python_typescript_finetuned_code/ | false | false | self | 1 | {'enabled': False, 'images': [{'id': 'v6025f4gMRjAE7sZZOCghGjaxWVekyQv_0dBhepaO6w', 'resolutions': [{'height': 54, 'url': 'https://external-preview.redd.it/r6atDvXw8LXLaZxTVVjMyJD8Shx7pUeFp5k79Jyt_Po.jpg?width=108&crop=smart&auto=webp&s=414c6db2df5be562ea5d25a6c9741ab333ca9319', 'width': 108}, {'height': 108, 'url': 'h... |
Incomplete response from LLAMA2 & Other QuantisedLLMs | 1 | [removed] | 2023-10-03T19:25:19 | https://www.reddit.com/r/LocalLLaMA/comments/16z0y29/incomplete_response_from_llama2_other/ | QuantumCatIsDead | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 16z0y29 | false | null | t3_16z0y29 | /r/LocalLLaMA/comments/16z0y29/incomplete_response_from_llama2_other/ | false | false | self | 1 | null |
AI Engineering Survey - vote for r/LocalLLaMA | 1 | [removed] | 2023-10-03T19:24:09 | https://www.reddit.com/r/LocalLLaMA/comments/16z0wyx/ai_engineering_survey_vote_for_rlocalllama/ | CombinationMother337 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 16z0wyx | false | null | t3_16z0wyx | /r/LocalLLaMA/comments/16z0wyx/ai_engineering_survey_vote_for_rlocalllama/ | false | false | self | 1 | null |
Specific Build for Multi-GPU (4090 or A100) Training Rigs | 2 | So I have somehow talked my institution into a $40k check to buy/build an entry-level on-prem rig for fine-tuning models of at least 7b size, but hopefully 40b or even 70b (qlora). The catch is that this is classified computing so I kind of get one swing to get everything I need and then pass through into that environ... | 2023-10-03T19:18:09 | https://www.reddit.com/r/LocalLLaMA/comments/16z0ri8/specific_build_for_multigpu_4090_or_a100_training/ | Mbando | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 16z0ri8 | false | null | t3_16z0ri8 | /r/LocalLLaMA/comments/16z0ri8/specific_build_for_multigpu_4090_or_a100_training/ | false | false | self | 2 | null |
If 7B models are so good, wouldn't it be possible to create a MoE using 7B ? | 65 | I'm not an expert in MoE, I was just wondering if there's any chance that an MoE of say 10 7B models would perform much better than a 70B model.
Regarding MoE what's the dataset like ? Would we need 10 completely distinct dataset for both pre train and fine tuning or can we use a common dataset for pretrain ? | 2023-10-03T19:01:58 | https://www.reddit.com/r/LocalLLaMA/comments/16z0d8g/if_7b_models_are_so_good_wouldnt_it_be_possible/ | IlEstLaPapi | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 16z0d8g | false | null | t3_16z0d8g | /r/LocalLLaMA/comments/16z0d8g/if_7b_models_are_so_good_wouldnt_it_be_possible/ | false | false | self | 65 | null |
Biggest Issues with LLMs? | 3 | What are the biggest issues y'all face in relation to LLMs? This can be on the deployment, side development side, or data side.
If y'all have a solution list it as a response 🙏. | 2023-10-03T18:51:58 | https://www.reddit.com/r/LocalLLaMA/comments/16z03yg/biggest_issues_with_llms/ | hai_cben | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 16z03yg | false | null | t3_16z03yg | /r/LocalLLaMA/comments/16z03yg/biggest_issues_with_llms/ | false | false | self | 3 | null |
My take on Microsoft's `autogen` for multi-agent chat: `Roy` | 61 | I stumbled upon Microsoft's \[autogen\](https://www.reddit.com/r/LocalLLaMA/comments/16twr5n/autogen\_from\_microsoft\_enable\_nextgen\_large/) a few days ago and was pretty taken by its potential. However, some aspects felt a tad convoluted for my taste.
So, I spent the weekend putting together \[Roy\](https://githu... | 2023-10-03T18:34:33 | https://www.reddit.com/r/LocalLLaMA/comments/16yzo57/my_take_on_microsofts_autogen_for_multiagent_chat/ | Independent_Back7067 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 16yzo57 | false | null | t3_16yzo57 | /r/LocalLLaMA/comments/16yzo57/my_take_on_microsofts_autogen_for_multiagent_chat/ | false | false | self | 61 | {'enabled': False, 'images': [{'id': 'xhpsG6HDB7olhXJoQjVVznx-y-jeBsmUzC_0aiveJ2A', 'resolutions': [{'height': 54, 'url': 'https://external-preview.redd.it/DB905l8usrb_FJM6kuzmSpsFddM17tuKMeV0xNq4t2k.jpg?width=108&crop=smart&auto=webp&s=35277d804cd3da5626fdb01ed5078b39ce90e164', 'width': 108}, {'height': 108, 'url': 'h... |
My take on Microsoft's `autogen` for multi-agent chat: Roy | 1 | [removed] | 2023-10-03T18:22:48 | https://www.reddit.com/r/LocalLLaMA/comments/16yzdku/my_take_on_microsofts_autogen_for_multiagent_chat/ | JosefAlbers05 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 16yzdku | false | null | t3_16yzdku | /r/LocalLLaMA/comments/16yzdku/my_take_on_microsofts_autogen_for_multiagent_chat/ | false | false | self | 1 | {'enabled': False, 'images': [{'id': 'xhpsG6HDB7olhXJoQjVVznx-y-jeBsmUzC_0aiveJ2A', 'resolutions': [{'height': 54, 'url': 'https://external-preview.redd.it/DB905l8usrb_FJM6kuzmSpsFddM17tuKMeV0xNq4t2k.jpg?width=108&crop=smart&auto=webp&s=35277d804cd3da5626fdb01ed5078b39ce90e164', 'width': 108}, {'height': 108, 'url': 'h... |
[P] An HF-space to check if your GPUs can run a model | 42 | Hi!
I've created a HuggingFace space to check if you can run a model with a specific GPU. It takes into account the required VRAM for:
* Inference
* Training with Adam
* LoRa fine-tuning of % trainable parameters
I plan to incorporate parameters `r`, `alpha`, and `target_modules` for LoRa to determine the percent... | 2023-10-03T18:05:11 | https://www.reddit.com/r/LocalLLaMA/comments/16yyxku/p_an_hfspace_to_check_if_your_gpus_can_run_a_model/ | Vokturz | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 16yyxku | false | null | t3_16yyxku | /r/LocalLLaMA/comments/16yyxku/p_an_hfspace_to_check_if_your_gpus_can_run_a_model/ | false | false | 42 | {'enabled': False, 'images': [{'id': 'xhL5ZT-S6n0LAbm1_N5rTg5_WqzREWLhfW6d_AK0ARI', 'resolutions': [{'height': 58, 'url': 'https://external-preview.redd.it/RA4pB398kQgGJN3O_bQHJPPy145ONUZLtHNnLWscUPU.jpg?width=108&crop=smart&auto=webp&s=543c9e7464030818c35b0396406def19a7a9fa0d', 'width': 108}, {'height': 116, 'url': 'h... | |
Already have a 3090, looking to host 70b models locally and was wondering if I could mix/match and use a 4090 alongside it? | 5 | Is it possible to load a 70b model and split the memory between 2 different graphics cards (one being a 4090, and one being a 3090)? | 2023-10-03T17:19:20 | https://www.reddit.com/r/LocalLLaMA/comments/16yxro1/already_have_a_3090_looking_to_host_70b_models/ | Oninaig | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 16yxro1 | false | null | t3_16yxro1 | /r/LocalLLaMA/comments/16yxro1/already_have_a_3090_looking_to_host_70b_models/ | false | false | self | 5 | null |
Local Phi-1.5 running fully in browser for privacy with open-source project BlindChat | 35 | Excited to introduce BlindChat ([https://github.com/mithril-security/blind\_chat](https://github.com/mithril-security/blind_chat)), an open-source, privacy-centric alternative to ChatGPT for in-browser Conversational AI!
📷
We provide full local inference in browser, by using libraries from Hugging Face like [transfo... | 2023-10-03T16:13:06 | https://www.reddit.com/r/LocalLLaMA/comments/16yw2xr/local_phi15_running_fully_in_browser_for_privacy/ | Separate-Still3770 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 16yw2xr | false | null | t3_16yw2xr | /r/LocalLLaMA/comments/16yw2xr/local_phi15_running_fully_in_browser_for_privacy/ | false | false | self | 35 | {'enabled': False, 'images': [{'id': 'Zrvi3TlPMGdSjQcA3Vz5h-tTakibIfhDxZd0dSTJ8Ic', 'resolutions': [{'height': 54, 'url': 'https://external-preview.redd.it/5wAUDpRnc-37GdXw8tuQl1x0H8f2t1kiEcqJLRYW51w.jpg?width=108&crop=smart&auto=webp&s=e24aec4fb266c4998d4eb1c8eb028bc0deff2d8c', 'width': 108}, {'height': 108, 'url': 'h... |
Why don't we use validation/test sets more in LLM fine-tuning? | 8 | I'm curious why fine-tuning large language models doesn't seem to use validation and test sets as much as other machine learning techniques.
In most ML, you split off some data for validation to do early stopping, and some for a final test set to evaluate the model. But with fine-tuning, it's common to just train on t... | 2023-10-03T15:29:50 | https://www.reddit.com/r/LocalLLaMA/comments/16yuydd/why_dont_we_use_validationtest_sets_more_in_llm/ | Pawngrubber | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 16yuydd | false | null | t3_16yuydd | /r/LocalLLaMA/comments/16yuydd/why_dont_we_use_validationtest_sets_more_in_llm/ | false | false | self | 8 | null |
Bizzare effect of 4 bits and LORA in 34B vs. HumanEval (Transformers,BnB,PEFT) | 20 | I have been testing how Loras affects the coding abilities of models (especially Phind v2 34B)
Unfortunately, still, only Transformers work (CodeLlama+LORA+2 GPU), so I had to run prompts in batches (4,8,16,32) not to get crazy. All HumanEvals ran with phind 2 alpaca format with "'''python" added.
In 4bits, Phi... | 2023-10-03T14:08:11 | https://www.reddit.com/r/LocalLLaMA/comments/16yswku/bizzare_effect_of_4_bits_and_lora_in_34b_vs/ | kpodkanowicz | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 16yswku | false | null | t3_16yswku | /r/LocalLLaMA/comments/16yswku/bizzare_effect_of_4_bits_and_lora_in_34b_vs/ | false | false | self | 20 | null |
Why use micro batch size and not just reduce the batch size in general? | 4 | Hi Guys,
I am a little confused as I do not understand the idea of micro batch size.
According to my understanding, in each iteration the batch size is feed to the model and afterwards the gradient will be computed and weights will be adjusted etc.
So I read that in order to save computing power, it is useful ... | 2023-10-03T14:07:38 | https://www.reddit.com/r/LocalLLaMA/comments/16ysw4r/why_use_micro_batch_size_and_not_just_reduce_the/ | Enkay55 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 16ysw4r | false | null | t3_16ysw4r | /r/LocalLLaMA/comments/16ysw4r/why_use_micro_batch_size_and_not_just_reduce_the/ | false | false | self | 4 | null |
logits for model distillation | 2 | The paper: Orca: Progressive Learning from Complex Explanation Traces of GPT-4
says OpenAI's API gives access to the top-5 logits for each token.
Is this enough for model distillation? Is this access available to anyone, or only microsoft? Has this been done/used for training or finetuning llama? | 2023-10-03T13:10:58 | https://www.reddit.com/r/LocalLLaMA/comments/16yrjpe/logits_for_model_distillation/ | Aaaaaaaaaeeeee | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 16yrjpe | false | null | t3_16yrjpe | /r/LocalLLaMA/comments/16yrjpe/logits_for_model_distillation/ | false | false | self | 2 | null |
How to Extract Structured Objects From Llama-2 Responses | 4 | I'm doing some RAG work with Llama-2 13B. For each question I ask the model I want to an open-ended response (so that I can understand the model's reasoning) and a parsed object response.
For example, I may ask the model "How many districts are in the town mention in this article?" To which I want an open ended respo... | 2023-10-03T13:10:02 | https://www.reddit.com/r/LocalLLaMA/comments/16yrivb/how_to_extract_structured_objects_from_llama2/ | MasterJaguar | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 16yrivb | false | null | t3_16yrivb | /r/LocalLLaMA/comments/16yrivb/how_to_extract_structured_objects_from_llama2/ | false | false | self | 4 | null |
How can i merge 2 Models? | 5 | so i have 2 models that are very good the synthia-34b-v1.2.Q4\_K\_M is uncensored but not that good for langchain while the speechless-llama2-hermes-orca-platypus-wizardlm-13b.Q8\_0 is perfect for langchain but its censored so is there a way to merge them together to make the synthia-34b better or the speechless-llama2... | 2023-10-03T13:02:01 | https://www.reddit.com/r/LocalLLaMA/comments/16yrc6c/how_can_i_merge_2_models/ | Otherwise_Weather_57 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 16yrc6c | false | null | t3_16yrc6c | /r/LocalLLaMA/comments/16yrc6c/how_can_i_merge_2_models/ | false | false | self | 5 | null |
Reimplementing home-baked local "function calling" | 14 | The OpenAI feature I'm referring to is: [https://platform.openai.com/docs/guides/gpt/function-calling](https://platform.openai.com/docs/guides/gpt/function-calling)
In short feature consists of:
* a way to define what functions are available (write a list of descriptions for LLM to look into)
* a way for the LLM to c... | 2023-10-03T12:53:45 | https://www.reddit.com/r/LocalLLaMA/comments/16yr5g8/reimplementing_homebaked_local_function_calling/ | BigHearin | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 16yr5g8 | false | null | t3_16yr5g8 | /r/LocalLLaMA/comments/16yr5g8/reimplementing_homebaked_local_function_calling/ | false | false | self | 14 | {'enabled': False, 'images': [{'id': 'XjYeH9UKcgyOWN9BfsAvdRtig11MoY4NbGzf8T8tohc', 'resolutions': [{'height': 56, 'url': 'https://external-preview.redd.it/nEedMLn73AsJU6AgxrHz6cvr0_KUZAuY26VUpixUKp8.jpg?width=108&crop=smart&auto=webp&s=3f9105ef3e7b58900470546335a78fe533005bb4', 'width': 108}, {'height': 113, 'url': 'h... |
Best RD software for LLaMa on a Mac | 1 | - I'm using a high-specced MacBook just for LocalLLaMA/LM Studio
- Otherwise on Windows and pretty bothered by every bit of macOS
- So, I need some remote desktop where I can remote control the MacBook via my Windows machine(s), any ideas? | 2023-10-03T11:53:25 | https://www.reddit.com/r/LocalLLaMA/comments/16ypv4p/best_rd_software_for_llama_on_a_mac/ | upk27 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 16ypv4p | false | null | t3_16ypv4p | /r/LocalLLaMA/comments/16ypv4p/best_rd_software_for_llama_on_a_mac/ | false | false | self | 1 | null |
What's the best remote desktop for remote controlling a Mac solely for LocalLLaMa? | 1 | [removed] | 2023-10-03T11:50:21 | https://www.reddit.com/r/LocalLLaMA/comments/16ypss6/whats_the_best_remote_desktop_for_remote/ | upk27 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 16ypss6 | false | null | t3_16ypss6 | /r/LocalLLaMA/comments/16ypss6/whats_the_best_remote_desktop_for_remote/ | false | false | self | 1 | null |
OT: What's the best remote desktop when using a MacBook via Windows? | 1 | [removed] | 2023-10-03T11:49:14 | https://www.reddit.com/r/LocalLLaMA/comments/16yps0h/ot_whats_the_best_remote_desktop_when_using_a/ | upk27 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 16yps0h | false | null | t3_16yps0h | /r/LocalLLaMA/comments/16yps0h/ot_whats_the_best_remote_desktop_when_using_a/ | false | false | self | 1 | null |
Removing causal mask of LLaMA? | 4 | The causal mask in LLaMA serves as a protective barrier to prevent information leakage. However, in certain tasks, leveraging information leakage can be a beneficial strategy for enhancing performance, particularly in tasks like token classification such as NER. Interestingly, the paper "Label Supervised LLaMA Finetuni... | 2023-10-03T11:48:57 | https://www.reddit.com/r/LocalLLaMA/comments/16ypruh/removing_causal_mask_of_llama/ | seanlee97 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 16ypruh | false | null | t3_16ypruh | /r/LocalLLaMA/comments/16ypruh/removing_causal_mask_of_llama/ | false | false | self | 4 | {'enabled': False, 'images': [{'id': 'q3evP6JeDpAC2MdSQHWYxnCYTqbJkElIQsLFqVSdkss', 'resolutions': [{'height': 63, 'url': 'https://external-preview.redd.it/izh8gZHY4FqZ1nwtU1N_TjtohUCNuvTyMn90toXda80.jpg?width=108&crop=smart&auto=webp&s=bc9575b410002edc2df3c5b5b0355fefedc7baa8', 'width': 108}, {'height': 126, 'url': 'h... |
What happens after removing the LLaMA’s causal mask | 1 | [removed] | 2023-10-03T10:07:04 | https://www.reddit.com/r/LocalLLaMA/comments/16yntd9/what_happens_after_removing_the_llamas_causal_mask/ | seanlee97 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 16yntd9 | false | null | t3_16yntd9 | /r/LocalLLaMA/comments/16yntd9/what_happens_after_removing_the_llamas_causal_mask/ | false | false | self | 1 | {'enabled': False, 'images': [{'id': 'q3evP6JeDpAC2MdSQHWYxnCYTqbJkElIQsLFqVSdkss', 'resolutions': [{'height': 63, 'url': 'https://external-preview.redd.it/izh8gZHY4FqZ1nwtU1N_TjtohUCNuvTyMn90toXda80.jpg?width=108&crop=smart&auto=webp&s=bc9575b410002edc2df3c5b5b0355fefedc7baa8', 'width': 108}, {'height': 126, 'url': 'h... |
LLM for German Conversations | 17 | Hey,
I´m looking for a fast LLM for everyday chat conversations in German. It should be as fast as possible since it should be as close to real time as possible, for normal chatting. I´m using webui-text-generation to host the models. The webui is currently deployed on a server with a GPU with 36 GB VRAM but I want t... | 2023-10-03T10:06:42 | https://www.reddit.com/r/LocalLLaMA/comments/16ynt3r/llm_for_german_conversations/ | aldur15 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 16ynt3r | false | null | t3_16ynt3r | /r/LocalLLaMA/comments/16ynt3r/llm_for_german_conversations/ | false | false | self | 17 | null |
Is there quantized BART anywhere? | 7 | There's quantized version for every model imaginable, but somehow I have hard times finding quantized BART anywhere. The regular version inference is too slow for my usecase.
I've only found [this repo](https://github.com/amazon-science/dq-bart) which is code to make it yourself, so I rented server with rtx 3090, thin... | 2023-10-03T10:03:54 | https://www.reddit.com/r/LocalLLaMA/comments/16ynr9c/is_there_quantized_bart_anywhere/ | heyimpumpkin | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 16ynr9c | false | null | t3_16ynr9c | /r/LocalLLaMA/comments/16ynr9c/is_there_quantized_bart_anywhere/ | false | false | self | 7 | {'enabled': False, 'images': [{'id': '0nT1ShYTmSgNRuhRePglMWqeSBfA41KUaUfh0J7hIHY', 'resolutions': [{'height': 54, 'url': 'https://external-preview.redd.it/xw8rG3EUUAvgxlGuXhd9SLNcboEUlD6-pZJEuw4N8i8.jpg?width=108&crop=smart&auto=webp&s=c46e3c04b62d3a2b1f423c1f3cea5cda315b328f', 'width': 108}, {'height': 108, 'url': 'h... |
What will happen after removing the causal mask of LLaMA? | 1 | [removed] | 2023-10-03T10:00:00 | https://www.reddit.com/r/LocalLLaMA/comments/16ynoi3/what_will_happen_after_removing_the_causal_mask/ | seanlee97 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 16ynoi3 | false | null | t3_16ynoi3 | /r/LocalLLaMA/comments/16ynoi3/what_will_happen_after_removing_the_causal_mask/ | false | false | self | 1 | {'enabled': False, 'images': [{'id': 'q3evP6JeDpAC2MdSQHWYxnCYTqbJkElIQsLFqVSdkss', 'resolutions': [{'height': 63, 'url': 'https://external-preview.redd.it/izh8gZHY4FqZ1nwtU1N_TjtohUCNuvTyMn90toXda80.jpg?width=108&crop=smart&auto=webp&s=bc9575b410002edc2df3c5b5b0355fefedc7baa8', 'width': 108}, {'height': 126, 'url': 'h... |
Training Opensource LLM on lyrics? | 3 | Hi,
Apologies for the naïve question.
I wanted to see if it could train Mistral on lyrics.
To teach it slant rhymes and more complicated structures in poetry.
ChatGPT4 is quite simplistic and cliché in its rhyming. I thought it might be possible (and cheaper) to improve upon it and use an OpenSource model instead.
... | 2023-10-03T09:49:07 | https://www.reddit.com/r/LocalLLaMA/comments/16ynhy5/training_opensource_llm_on_lyrics/ | FreshlyBakedMan | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 16ynhy5 | false | null | t3_16ynhy5 | /r/LocalLLaMA/comments/16ynhy5/training_opensource_llm_on_lyrics/ | false | false | self | 3 | null |
Any GGUF 7b to use in Spanish? | 2 | As title, as I had problems using models in Spanish.
I'll use LLaMA.cpp
Thank you | 2023-10-03T08:25:38 | https://www.reddit.com/r/LocalLLaMA/comments/16ym7x6/any_gguf_7b_to_use_in_spanish/ | evillarreal86 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 16ym7x6 | false | null | t3_16ym7x6 | /r/LocalLLaMA/comments/16ym7x6/any_gguf_7b_to_use_in_spanish/ | false | false | self | 2 | null |
Cheaper cloud alternatives to train LLM for educational purpose | 6 | I am giving a workshop in my town in a few weeks. And the topic is how LLMs are built, the transformer architecture etc. I will show live how to build a small useless language model from scratch. (I mostly followed myself several tutorials - specially Andrej Karpathy’s).
So, the whole purpose is of educational. I don’... | 2023-10-03T08:07:20 | https://www.reddit.com/r/LocalLLaMA/comments/16ylxtq/cheaper_cloud_alternatives_to_train_llm_for/ | besabestin | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 16ylxtq | false | null | t3_16ylxtq | /r/LocalLLaMA/comments/16ylxtq/cheaper_cloud_alternatives_to_train_llm_for/ | false | false | self | 6 | null |
Full-finetuning Llama models | 1 | [removed] | 2023-10-03T08:01:30 | https://www.reddit.com/r/LocalLLaMA/comments/16ylumr/fullfinetuning_llama_models/ | Impossible_Storm8768 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 16ylumr | false | null | t3_16ylumr | /r/LocalLLaMA/comments/16ylumr/fullfinetuning_llama_models/ | false | false | self | 1 | null |
I am trying to use LLAMA index RAG with my own fine-tuned model, it's giving gibberish answer? Any idea on how to use RAG with custom fine-tune? | 1 | [removed] | 2023-10-03T08:00:27 | https://www.reddit.com/r/LocalLLaMA/comments/16yltyz/i_am_trying_to_use_llama_index_rag_with_my_own/ | Anu_Rag9704 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 16yltyz | false | null | t3_16yltyz | /r/LocalLLaMA/comments/16yltyz/i_am_trying_to_use_llama_index_rag_with_my_own/ | false | false | 1 | null | |
Is there a retrieval method that can get relevant context for complex queries | 5 | Hi all,
I am building a Retrieval Augmented Generation system that would answer queries of users using documents at hand.
I was wondering if is any method that would handle complex questions, for example "who was the president of a xyz country when there was Argentina won it's latest fifa world cup".
In this exam... | 2023-10-03T07:34:50 | https://www.reddit.com/r/LocalLLaMA/comments/16ylg7s/is_there_a_retrieval_method_that_can_get_relevant/ | vile_proxima | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 16ylg7s | false | null | t3_16ylg7s | /r/LocalLLaMA/comments/16ylg7s/is_there_a_retrieval_method_that_can_get_relevant/ | false | false | self | 5 | null |
so.. is it AI now or just a book with talking interface? my thinking.. | 0 | so my thinking is:
imagine a infinity excel sheet where in column one, you have all questions what exists and in column two, you have appropriate answer.
talking with "AI" like this can make you feel that it is very intelligent, but in reality, it is just preprogramed what to answer so it is not "AI", just infinite l... | 2023-10-03T07:24:22 | https://www.reddit.com/r/LocalLLaMA/comments/16ylai7/so_is_it_ai_now_or_just_a_book_with_talking/ | ovnf | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 16ylai7 | false | null | t3_16ylai7 | /r/LocalLLaMA/comments/16ylai7/so_is_it_ai_now_or_just_a_book_with_talking/ | false | false | self | 0 | null |
Any way to host finetuned LLMs and only pay for what you use? | 2 | Hey all,
I have made a couple LOrA models recently I would love to use in chat bots and that kind of thing, but I don’t want to be paying by the hour, are there any options out there for me to call my models via and API and only pay for what I use? I have thought about using an AWS lambda but I imagine that means I’ll... | 2023-10-03T07:22:34 | https://www.reddit.com/r/LocalLLaMA/comments/16yl9lg/any_way_to_host_finetuned_llms_and_only_pay_for/ | Chance_Confection_37 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 16yl9lg | false | null | t3_16yl9lg | /r/LocalLLaMA/comments/16yl9lg/any_way_to_host_finetuned_llms_and_only_pay_for/ | false | false | self | 2 | null |
Where can I find llama 2 uncensored hosted on the cloud for free? | 1 | on [https://huggingface.co/chat/](https://huggingface.co/chat/), we can use code llama 34b, llama 2 70b, and even Falcon 180b for free, and I was wondering if there is anywhere I can also find llama 2 uncensored. I don't mean using GCP, AWS, or Lambda (not free / temporary free trial), but actually free, since my lapto... | 2023-10-03T06:27:22 | https://www.reddit.com/r/LocalLLaMA/comments/16ykfnu/where_can_i_find_llama_2_uncensored_hosted_on_the/ | Cheems63 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 16ykfnu | false | null | t3_16ykfnu | /r/LocalLLaMA/comments/16ykfnu/where_can_i_find_llama_2_uncensored_hosted_on_the/ | false | false | self | 1 | {'enabled': False, 'images': [{'id': 'O4__VvuTP1zjgNXHpYgGtbNlwm8CyL1iGZRclIV-cFg', 'resolutions': [{'height': 58, 'url': 'https://external-preview.redd.it/YQI_ej5EergATLgemo1vMLg5Y9oURFiOHZhDYundV9o.jpg?width=108&crop=smart&auto=webp&s=732d76370b97811ab9fb6fed1800fef253ff5141', 'width': 108}, {'height': 116, 'url': 'h... |
Does quantization speed or slow down inference for a LLM? | 1 | Hi everyone, according to Google's Bard, quantization of a LLM speeds up inference, but from my personal experience quantization of a LLM with "torch\_dtype" of "float16" (e.g. lmsys/vicuna-7b-v1.5) when loaded in 8-bit slows down inference. Could someone enlighten me which is correct? And if so why? Thank you! | 2023-10-03T06:25:22 | https://www.reddit.com/r/LocalLLaMA/comments/16ykeo4/does_quantization_speed_or_slow_down_inference/ | ToeAdministrative493 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 16ykeo4 | false | null | t3_16ykeo4 | /r/LocalLLaMA/comments/16ykeo4/does_quantization_speed_or_slow_down_inference/ | false | false | self | 1 | null |
Does quantization of LLM speed up or slow down infernence? | 1 | [removed] | 2023-10-03T06:17:15 | https://www.reddit.com/r/LocalLLaMA/comments/16ykagw/does_quantization_of_llm_speed_up_or_slow_down/ | AdventurousBowler740 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 16ykagw | false | null | t3_16ykagw | /r/LocalLLaMA/comments/16ykagw/does_quantization_of_llm_speed_up_or_slow_down/ | false | false | self | 1 | null |
Does quantization slow inference? | 1 | [removed] | 2023-10-03T06:16:17 | https://www.reddit.com/r/LocalLLaMA/comments/16yk9xi/does_quantization_slow_inference/ | AdventurousBowler740 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 16yk9xi | false | null | t3_16yk9xi | /r/LocalLLaMA/comments/16yk9xi/does_quantization_slow_inference/ | false | false | self | 1 | null |
Advice for prompt design for unit conversion | 1 | [removed] | 2023-10-03T05:25:19 | https://www.reddit.com/r/LocalLLaMA/comments/16yjgp1/advice_for_prompt_design_for_unit_conversion/ | LLM4_robotics | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 16yjgp1 | false | null | t3_16yjgp1 | /r/LocalLLaMA/comments/16yjgp1/advice_for_prompt_design_for_unit_conversion/ | false | false | self | 1 | null |
Looking for Advice on End to End Workflow for training a specialized LLM to run locally | 2 | I am trying to understand the over-all methodology for training a specific LLM, from beginning to fine tuning. I have a use case described below along with what I ***think*** is the workflow. Please correct me. (The use case is using publicly available books and literature. But, obviously it could be used for different... | 2023-10-03T03:49:03 | https://www.reddit.com/r/LocalLLaMA/comments/16yhqt5/looking_for_advice_on_end_to_end_workflow_for/ | Ok_Organization_4295 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 16yhqt5 | false | null | t3_16yhqt5 | /r/LocalLLaMA/comments/16yhqt5/looking_for_advice_on_end_to_end_workflow_for/ | false | false | self | 2 | null |
Not enought GPU? | 4 | So my pc specs are
\-1650 ti 4GB
\-16 GB RAM
And I got this error while trying to load the model
2023-10-03 00:16:08 ERROR:Failed to load the model.
Traceback (most recent call last):
File "C:\\Users\\migat\\text-generation-webui\\modules\\ui\_model\_menu.py", line 201, in load\_model\_wrapper
shared.mod... | 2023-10-03T03:26:29 | https://www.reddit.com/r/LocalLLaMA/comments/16yhae3/not_enought_gpu/ | Cold-Risk-2513 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 16yhae3 | false | null | t3_16yhae3 | /r/LocalLLaMA/comments/16yhae3/not_enought_gpu/ | false | false | self | 4 | null |
GPU makes a fast electronic noise when running inference | 5 | Why do GPUs make a noise when running inference? Is it just coil whine? It's like an electronic pulsing noise that's really fast. My old 3090 did it and now my A5000 does it too. | 2023-10-03T02:58:17 | https://www.reddit.com/r/LocalLLaMA/comments/16ygpix/gpu_makes_a_fast_electronic_noise_when_running/ | Rollingsound514 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 16ygpix | false | null | t3_16ygpix | /r/LocalLLaMA/comments/16ygpix/gpu_makes_a_fast_electronic_noise_when_running/ | false | false | self | 5 | null |
Running meta llama-2-13b model on AWS g4dn.2xlarge instance | 1 | [removed] | 2023-10-03T02:53:44 | https://www.reddit.com/r/LocalLLaMA/comments/16ygm8v/running_meta_llama213b_model_on_aws_g4dn2xlarge/ | duffy0016 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 16ygm8v | false | null | t3_16ygm8v | /r/LocalLLaMA/comments/16ygm8v/running_meta_llama213b_model_on_aws_g4dn2xlarge/ | false | false | self | 1 | {'enabled': False, 'images': [{'id': 'RUqh18uQTwuGJocqdUcC-6UfvfWS63SRDdr8AQqU3uM', 'resolutions': [{'height': 56, 'url': 'https://external-preview.redd.it/Q6q5DgwzcfU6chKw4uevixQcBq1Ipi2NYLheQ4lv0Vk.jpg?width=108&crop=smart&auto=webp&s=64a1b1322ed94c559cb213e6a08f3eb426a3fb0b', 'width': 108}, {'height': 113, 'url': 'h... |
How do you get Llama 2 to fix a mistaken approach, or change strategies? | 1 | I was looking at the WizardMath-13b model, because it does seem better than some of the others at math, but it seems to get stuck in some cases (and I'm guessing this is not specific to that model). I asked it to solve a probably question about the odds of surviving 3 trigger pulls of Russian roulette. It went through... | 2023-10-03T02:28:31 | https://www.reddit.com/r/LocalLLaMA/comments/16yg2vr/how_do_you_get_llama_2_to_fix_a_mistaken_approach/ | SuperDuperDave5000 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 16yg2vr | false | null | t3_16yg2vr | /r/LocalLLaMA/comments/16yg2vr/how_do_you_get_llama_2_to_fix_a_mistaken_approach/ | false | false | self | 1 | null |
Subsets and Splits
No community queries yet
The top public SQL queries from the community will appear here once available.