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 ⌀ |
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
FlashFFTConv: Efficient Convolutions for Long Sequences with Tensor Cores | 19 | **Paper**: [https://arxiv.org/abs/2311.05908](https://arxiv.org/abs/2311.05908)
**Code**: [https://github.com/HazyResearch/flash-fft-conv](https://github.com/HazyResearch/flash-fft-conv)
**Blog post**: [https://hazyresearch.stanford.edu/blog/2023-11-13-flashfftconv](https://hazyresearch.stanford.edu/blog/2023-11-13-... | 2023-11-23T06:44:20 | https://www.reddit.com/r/LocalLLaMA/comments/181v3df/flashfftconv_efficient_convolutions_for_long/ | APaperADay | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 181v3df | false | null | t3_181v3df | /r/LocalLLaMA/comments/181v3df/flashfftconv_efficient_convolutions_for_long/ | false | false | 19 | {'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 are some good tests to tell if the voice on a phone call is legit? | 1 | So with text2speech and speech2speech models coming along, probably within a few years there will be phone calls that sound like a real voice, but for whatever reason they're not legit. e.g. a phone call that appears to be a relative's phone number and also sounds like their voice.
What would be some good tricks that ... | 2023-11-23T06:13:59 | https://www.reddit.com/r/LocalLLaMA/comments/181uls3/what_are_some_good_tests_to_tell_if_the_voice_on/ | friendlyshrek | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 181uls3 | false | null | t3_181uls3 | /r/LocalLLaMA/comments/181uls3/what_are_some_good_tests_to_tell_if_the_voice_on/ | false | false | self | 1 | null |
Need help with finding the right opensource LLM | 2 | I want to work on this personal project which requires me to use a large language model and fine tune the same over my own dataset. I want to make a model that can write fiction, so the dataset that will later fine tune it on will be fiction.
I have a decent hardware to run a model with about 70 billion parameters.
... | 2023-11-23T06:05:32 | https://www.reddit.com/r/LocalLLaMA/comments/181ugzj/need_help_with_finding_the_right_opensource_llm/ | Nice-Job67 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 181ugzj | false | null | t3_181ugzj | /r/LocalLLaMA/comments/181ugzj/need_help_with_finding_the_right_opensource_llm/ | false | false | self | 2 | null |
Maximum input length for Llma2 model | 1 | [removed] | 2023-11-23T05:24:42 | https://www.reddit.com/r/LocalLLaMA/comments/181tsvp/maximum_input_length_for_llma2_model/ | ianuvrat | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 181tsvp | false | null | t3_181tsvp | /r/LocalLLaMA/comments/181tsvp/maximum_input_length_for_llma2_model/ | false | false | self | 1 | null |
A. Karpathy: Introduction to Large Language Models | 1 | [removed] | 2023-11-23T05:22:02 | https://www.reddit.com/r/LocalLLaMA/comments/181trcv/a_karpathy_introduction_to_large_language_models/ | DeGreiff | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 181trcv | false | null | t3_181trcv | /r/LocalLLaMA/comments/181trcv/a_karpathy_introduction_to_large_language_models/ | false | false | self | 1 | {'enabled': False, 'images': [{'id': 'xjR76G-Lhr9cGX65NrAIUl3ZPXKTyY8Zglr4yV_z0KQ', 'resolutions': [{'height': 81, 'url': 'https://external-preview.redd.it/lEbKDTjwjTwknEqvJx7kd7-m-Mua9v70-U5TOmeHzc0.jpg?width=108&crop=smart&auto=webp&s=492404059a546e004187883e6126a73dea923976', 'width': 108}, {'height': 162, 'url': 'h... |
LLM.js v1.0.2 is out with support for GGUF/GGML format and Model Playground | 13 | 🚀 Exciting News! 🚀
Thrilled to announce the release of **LLM.js** v1.0.2! 🎉✨
🌐 **LLM.js** lets you play around with language models right in your browser, thanks to **WebAssembly**.
In this latest release, here's what's in store:
1️⃣ **Expanded Format Support**: Now **GGUF/GGML** formats are fully supported, t... | 2023-11-23T05:07:34 | https://www.reddit.com/r/LocalLLaMA/comments/181tisg/llmjs_v102_is_out_with_support_for_ggufggml/ | AnonymousD3vil | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 181tisg | false | null | t3_181tisg | /r/LocalLLaMA/comments/181tisg/llmjs_v102_is_out_with_support_for_ggufggml/ | false | false | 13 | null | |
Prompt to create GPTs | 1 | You are a GPT whose job it is to help users create their own chatbots. In particular, you need to respond succinctly in a friendly tone, write a title, system prompt, and a very short example user input for the chatbot. Make sure each part is included.
Sure, I'd be happy to help you build a GPT! I'm generating a title... | 2023-11-23T04:55:15 | https://www.reddit.com/r/LocalLLaMA/comments/181tb82/prompt_to_create_gpts/ | herozorro | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 181tb82 | false | null | t3_181tb82 | /r/LocalLLaMA/comments/181tb82/prompt_to_create_gpts/ | false | false | self | 1 | null |
Any Good Speech-to-Speech Voice Changer Models? | 17 | ElevenLabs just released their speech to speech thing and it’s really cool: https://elevenlabs.io/voice-changer
Now I’m wondering what’s the best similar “voice changer” or speech to speech model that I can run locally?
It doesn’t have to be in real time, I plan on using it to narrate audio books and similar.
Tha... | 2023-11-23T04:10:43 | https://www.reddit.com/r/LocalLLaMA/comments/181skiw/any_good_speechtospeech_voice_changer_models/ | HumanityFirstTheory | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 181skiw | false | null | t3_181skiw | /r/LocalLLaMA/comments/181skiw/any_good_speechtospeech_voice_changer_models/ | false | false | self | 17 | null |
I need help with my P40 I bought to run inference | 1 | I have a Dell PowerEdge r730 with 2 cpu, 2 psu 1100w and I got the proper gpu cable 8pins EPS that I verified with the multimeter. It is plugged in the right way and I go get good power on the yellow wires. I installed every drivers I found and did the registry shenanigans to have it in wddm mode etc but it always fail... | 2023-11-23T03:44:50 | https://www.reddit.com/r/LocalLLaMA/comments/181s40s/i_need_help_with_my_p40_i_bought_to_run_inference/ | DrVonSinistro | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 181s40s | false | null | t3_181s40s | /r/LocalLLaMA/comments/181s40s/i_need_help_with_my_p40_i_bought_to_run_inference/ | false | false | self | 1 | null |
New Karpathy tutorial just dropped | 1 | [removed] | 2023-11-23T03:09:42 | https://www.reddit.com/r/LocalLLaMA/comments/181rhdr/new_karpathy_tutorial_just_dropped/ | ASD_Project | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 181rhdr | false | null | t3_181rhdr | /r/LocalLLaMA/comments/181rhdr/new_karpathy_tutorial_just_dropped/ | false | false | self | 1 | {'enabled': False, 'images': [{'id': 'xjR76G-Lhr9cGX65NrAIUl3ZPXKTyY8Zglr4yV_z0KQ', 'resolutions': [{'height': 81, 'url': 'https://external-preview.redd.it/lEbKDTjwjTwknEqvJx7kd7-m-Mua9v70-U5TOmeHzc0.jpg?width=108&crop=smart&auto=webp&s=492404059a546e004187883e6126a73dea923976', 'width': 108}, {'height': 162, 'url': 'h... |
Hugging Face Removes Singing AI Models of Xi Jinping But Not of Biden | 325 | 2023-11-23T03:04:37 | https://www.404media.co/hugging-face-removes-singing-ai-models-of-xi-but-not-of-biden/ | Merchant_Lawrence | 404media.co | 1970-01-01T00:00:00 | 0 | {} | 181rdx3 | false | null | t3_181rdx3 | /r/LocalLLaMA/comments/181rdx3/hugging_face_removes_singing_ai_models_of_xi/ | false | false | 325 | {'enabled': False, 'images': [{'id': '39UkKvxDztZ4DlgRPndfQMepqR5cLM0-u2ZmLf6husw', 'resolutions': [{'height': 60, 'url': 'https://external-preview.redd.it/Yne6dJLfSnATEUSkcOXSk7wj7WdU13fuJEGR2iNwkpU.jpg?width=108&crop=smart&auto=webp&s=1e9f22c5d5af4f3eea3937d08d55243e02544135', 'width': 108}, {'height': 121, 'url': 'h... | ||
Options for fine-tuning, advice please | 1 | I'm planning to fine-tune a mistral model with my own dataset. (full fine-tune, not LORAs)
The dataset is not that large, around 120 mb in jsonl format.
My questions are:
1. Will I be able to fine-tune the model with 4 cards of 40G A100?
2. If not, is using runpod the easiest approach?
3. I'm trying to instill knowl... | 2023-11-23T01:25:10 | https://www.reddit.com/r/LocalLLaMA/comments/181pgi4/options_for_finetuning_advice_please/ | manjimin | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 181pgi4 | false | null | t3_181pgi4 | /r/LocalLLaMA/comments/181pgi4/options_for_finetuning_advice_please/ | false | false | self | 1 | null |
An Open Source version of OpenAI Assistants API | 7 | 2023-11-23T01:19:04 | https://twitter.com/louis030195/status/1727495156918861836 | louis3195 | twitter.com | 1970-01-01T00:00:00 | 0 | {} | 181pc6z | false | {'oembed': {'author_name': 'louis030195', 'author_url': 'https://twitter.com/louis030195', 'cache_age': 3153600000, 'height': None, 'html': '<blockquote class="twitter-video"><p lang="en" dir="ltr">i built an open source version of OpenAI Assistants API <br><br>it's compatible with any LLM & embeddings model an... | t3_181pc6z | /r/LocalLLaMA/comments/181pc6z/an_open_source_version_of_openai_assistants_api/ | false | false | 7 | {'enabled': False, 'images': [{'id': 'yux8UNL0StrlwQjSsUu8LgWS9mov53Dz0Wrw2dvg8lo', 'resolutions': [{'height': 84, 'url': 'https://external-preview.redd.it/F0HKwwGz3SmBJ-jwk1o8ACXaYt2g5b7t901DuPVtYhY.jpg?width=108&crop=smart&auto=webp&s=05ee9f39ef2e663e62095f26ba8a2d2403d5e238', 'width': 108}], 'source': {'height': 110... | ||
oss tts engine? | 11 | * So, i've been doing all my LLM-tinkering on an M1-- using [llama.cpp](https://github.com/ggerganov/llama.cpp)/[whisper.cpp](https://github.com/ggerganov/whisper.cpp) for to run a basic voice powered assistant, nothing new at this point.
* Currently adding a visual component to it-- [ShareGPT4V-7B](https://huggingfac... | 2023-11-23T00:56:52 | https://www.reddit.com/r/LocalLLaMA/comments/181owlk/oss_tts_engine/ | LyPreto | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 181owlk | false | null | t3_181owlk | /r/LocalLLaMA/comments/181owlk/oss_tts_engine/ | false | false | self | 11 | {'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... |
How do you get a feeling for price per token? | 1 | I like to compare prices of models and find it hard to get a feeling of how "expensive" they are.
What im currently doing is: Calculate the price for generating the bible.
Im interested how you are doing it! | 2023-11-23T00:56:43 | https://www.reddit.com/r/LocalLLaMA/comments/181owho/how_do_you_get_a_feeling_for_price_per_token/ | freehuntx | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 181owho | false | null | t3_181owho | /r/LocalLLaMA/comments/181owho/how_do_you_get_a_feeling_for_price_per_token/ | false | false | self | 1 | null |
What is Q* and how do we use it? | 268 | Reuters is reporting that OpenAI achieved an advance with a technique called Q* (pronounced Q-Star).
So what is Q*?
I asked around the AI researcher campfire and…
It’s probably Q Learning MCTS, a Monte Carlo tree search reinforcement learning algorithm.
Which is right in line with the strategy DeepMind (vaguely) sa... | 2023-11-23T00:37:50 | georgejrjrjr | i.redd.it | 1970-01-01T00:00:00 | 0 | {} | 181oiu2 | false | null | t3_181oiu2 | /r/LocalLLaMA/comments/181oiu2/what_is_q_and_how_do_we_use_it/ | false | false | 268 | {'enabled': True, 'images': [{'id': 'RjsQGDUWHdQlceypLbUBp_p4HQIolV2BvNadFBqxV1A', 'resolutions': [{'height': 49, 'url': 'https://preview.redd.it/xxx6hnsvtz1c1.jpg?width=108&crop=smart&auto=webp&s=cfb4d02788f3643a3baa418b7b9d72960535e2e5', 'width': 108}, {'height': 98, 'url': 'https://preview.redd.it/xxx6hnsvtz1c1.jpg?... | ||
Need Feedback on API Project | 1 | [removed] | 2023-11-23T00:23:43 | https://www.reddit.com/r/LocalLLaMA/comments/181o8gq/need_feedback_on_api_project/ | libraryofcelsus | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 181o8gq | false | null | t3_181o8gq | /r/LocalLLaMA/comments/181o8gq/need_feedback_on_api_project/ | false | false | self | 1 | {'enabled': False, 'images': [{'id': 'Ep4fcJw6hOw9j4pK-LOH37q3SGbUaN8GdNAfTMdshbg', 'resolutions': [{'height': 54, 'url': 'https://external-preview.redd.it/Bp9p4EnZr5nWYU7X5faDBlMg0sDceFih7u3dxaK6xoM.jpg?width=108&crop=smart&auto=webp&s=e2942fd2a38cc60c43b056f649065f2d6105aafd', 'width': 108}, {'height': 108, 'url': 'h... |
What happened to Pause tokens? | 39 | A month ago a paper was highlighted in this subreddit that introduced pause tokens to give the models "more time to think", which resulted in better scores on benchmarks.
Are there any LLMs that integrate this technique or were there any follow up papers to verify the claim? | 2023-11-23T00:02:24 | https://www.reddit.com/r/LocalLLaMA/comments/181nsg2/what_happened_to_pause_tokens/ | StraightChemistry629 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 181nsg2 | false | null | t3_181nsg2 | /r/LocalLLaMA/comments/181nsg2/what_happened_to_pause_tokens/ | false | false | self | 39 | null |
Best Local LLM Backend Server Library? | 1 | I maintain the [uniteai](https://github.com/freckletonj/uniteai) project, and have implemented a [custom backend for serving](https://github.com/freckletonj/uniteai/blob/master/uniteai/llm_server.py) `transformers`-compatible LLMs. (That file's actually a great ultra-light-weight server if `transformers` satisfies your... | 2023-11-22T23:13:57 | https://www.reddit.com/r/LocalLLaMA/comments/181mqdg/best_local_llm_backend_server_library/ | BayesMind | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 181mqdg | false | null | t3_181mqdg | /r/LocalLLaMA/comments/181mqdg/best_local_llm_backend_server_library/ | false | false | self | 1 | {'enabled': False, 'images': [{'id': 'w331Pz9YLT5TGAMt6D7JtGkt9SO0gYT3sePGu6_kog4', 'resolutions': [{'height': 54, 'url': 'https://external-preview.redd.it/TUV2wooQa8ylUNvZV_LBbGCx7UxCsjtVIbq9iDn46x0.jpg?width=108&crop=smart&auto=webp&s=b5fb2286e5bf6a8ceadd44afb95fe2f394bafda3', 'width': 108}, {'height': 108, 'url': 'h... |
Best model for conversations? | 6 | Trying to build a conversational AI chat assistant. Most of the models like Vicuna and LLaMa 13B are just inundating me with a bunch a text.
I'm trying to emulate a conversation like you'd have with your friend. Not just be bombarded with a bunch of text to read and information to process.
Which models are good at th... | 2023-11-22T23:10:41 | https://www.reddit.com/r/LocalLLaMA/comments/181mntn/best_model_for_conversations/ | blackstonewine | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 181mntn | false | null | t3_181mntn | /r/LocalLLaMA/comments/181mntn/best_model_for_conversations/ | false | false | self | 6 | null |
Rocket 3B is pretty solid - here is it on Docker w Local LLMs | 66 | So i tried out one of the quantized models of Rocket 3B.
Super impressed! Had a few conversations and they were all great. Here is one where Rocket explains about Docker and local LLMs
Model used: https://huggingface.co/TheBloke/rocket-3B-GGUF
Quantization: Q4_K_M
___
Please converse with me as if you were a true ... | 2023-11-22T23:05:49 | Happy_Chicken9835 | i.redd.it | 1970-01-01T00:00:00 | 0 | {} | 181mjyx | false | null | t3_181mjyx | /r/LocalLLaMA/comments/181mjyx/rocket_3b_is_pretty_solid_here_is_it_on_docker_w/ | false | false | 66 | {'enabled': True, 'images': [{'id': 'yGQa55jEmefds4neG-Iik8NsmU6KNfrXMDakAvPh2oM', 'resolutions': [{'height': 118, 'url': 'https://preview.redd.it/gx7ne0sgdz1c1.jpeg?width=108&crop=smart&auto=webp&s=82c5c76ef5f477a4ecfc31ba2f17cda8fdc4ee9a', 'width': 108}, {'height': 236, 'url': 'https://preview.redd.it/gx7ne0sgdz1c1.j... | ||
New to local models, local model api question | 1 | How can I learn how to write conversational api scripts for interacting with the various types of chat models I find on huggingface? I would like to learn how I can write one for phind instead of relying on text generation webui.
Thank you | 2023-11-22T22:49:18 | https://www.reddit.com/r/LocalLLaMA/comments/181m63x/new_to_local_models_local_model_api_question/ | shootthepie | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 181m63x | false | null | t3_181m63x | /r/LocalLLaMA/comments/181m63x/new_to_local_models_local_model_api_question/ | false | false | self | 1 | null |
Is DeepSeek Coder 1.3b meant to be this bad? | 2 | I am using kobold.cpp and it couldn't code anything outside of hello world. Am I doing something wrong?
https://preview.redd.it/xdo6q7a25z1c1.png?width=1454&format=png&auto=webp&s=30d0eaed2c6d4d95070f2312a4bc3add0dcc2840 | 2023-11-22T22:19:25 | https://www.reddit.com/r/LocalLLaMA/comments/181lgso/is_deepseek_coder_13b_meant_to_be_this_bad/ | East-Awareness-249 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 181lgso | false | null | t3_181lgso | /r/LocalLLaMA/comments/181lgso/is_deepseek_coder_13b_meant_to_be_this_bad/ | false | false | 2 | null | |
LLM response based on customer personality | 2 | I'm designing a simple RAG for a kids learning platform (12-17). I would like for the chatbot to be more useful and friendly. I'd like for the LLM to be a better companion for them, a co-pilot. In order to do that, I've been thinking about storing some information about their prompts to map out their personality and be... | 2023-11-22T22:19:21 | https://www.reddit.com/r/LocalLLaMA/comments/181lgqc/llm_response_based_on_customer_personality/ | Amazing-Protection87 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 181lgqc | false | null | t3_181lgqc | /r/LocalLLaMA/comments/181lgqc/llm_response_based_on_customer_personality/ | false | false | self | 2 | null |
Intel neural-chat-7b-v3-1 | 1 | Has anyone explored Intel's new [model](https://huggingface.co/Intel/neural-chat-7b-v3-1) yet? It's a 7B model trained on [Slim Orca](https://huggingface.co/datasets/Open-Orca/SlimOrca), which is currently the top 7B model on the HF open LLM leaderboard.
I've found other 7B models to be surprisingly helpful, especiall... | 2023-11-22T22:02:57 | https://www.reddit.com/r/LocalLLaMA/comments/181l30f/intel_neuralchat7bv31/ | dvanstrien | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 181l30f | false | null | t3_181l30f | /r/LocalLLaMA/comments/181l30f/intel_neuralchat7bv31/ | false | false | self | 1 | {'enabled': False, 'images': [{'id': 'MTHa0RFu26sELjrensnxBNo3EpGgvvXukCfilQ3uEDY', 'resolutions': [{'height': 58, 'url': 'https://external-preview.redd.it/oVzLyFlZ-FVRhjd4IQzuJpDzN-DCVuLdmZNUeFdKrrY.jpg?width=108&crop=smart&auto=webp&s=74983322bb1387297c0925d101f2cdac0e0cbc03', 'width': 108}, {'height': 116, 'url': 'h... |
Easy way to find the default context and proper RoPE settings for newer models? | 17 | Hi, all,
This question makes me feel dumb, but I've given it my best shot. From my understanding, Ooba is supposed to load the proper, default settings for a model when you first load it in the UI, and then you can go from there. At least, that's how it used to work. Now, though, it doesn't seem to do that every time,... | 2023-11-22T21:49:50 | https://www.reddit.com/r/LocalLLaMA/comments/181krc0/easy_way_to_find_the_default_context_and_proper/ | smile_e_face | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 181krc0 | false | null | t3_181krc0 | /r/LocalLLaMA/comments/181krc0/easy_way_to_find_the_default_context_and_proper/ | false | false | self | 17 | null |
Local generation not utilising GPU? | 1 | Hello, this has probably been asked a bazillion times, but I can't find an example. I have installed stable diffusion and LLaMA on my new PC. However, it does not appear to be utilising my new RTX 4080 for generation. Generation of text or images is very slow, and the GPU utilisation stays at 0% - 4% throughout. Any id... | 2023-11-22T21:28:02 | https://www.reddit.com/r/LocalLLaMA/comments/181k8hu/local_generation_not_utilising_gpu/ | AlternativeParfait47 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 181k8hu | false | null | t3_181k8hu | /r/LocalLLaMA/comments/181k8hu/local_generation_not_utilising_gpu/ | false | false | self | 1 | null |
Guys I just realized something that's actually really obvious. Why are no one talking about this? | 1 | Today we run a query, the LLM answers. The evolution of this was going multi-modal, and being able to input other forms of data, like video and sound
But still, we query a model, the LLM answers. Same with agents, only then we have multiple queries working in a system, often assisted by function calling and automation... | 2023-11-22T21:19:17 | https://www.reddit.com/r/LocalLLaMA/comments/181k0y1/guys_i_just_realized_something_thats_actually/ | Severin_Suveren | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 181k0y1 | false | null | t3_181k0y1 | /r/LocalLLaMA/comments/181k0y1/guys_i_just_realized_something_thats_actually/ | false | false | self | 1 | null |
DiLoCo: Distributed Low-Communication Training of Language Models | 10 | Twitter thread by the first author: https://twitter.com/Ar_Douillard/status/1724732329740976187 | 2023-11-22T21:15:21 | https://www.reddit.com/r/LocalLLaMA/comments/181jxmj/diloco_distributed_lowcommunication_training_of/ | IntergalacticCiv | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 181jxmj | false | null | t3_181jxmj | /r/LocalLLaMA/comments/181jxmj/diloco_distributed_lowcommunication_training_of/ | false | false | self | 10 | {'enabled': False, 'images': [{'id': 'J12zXeFnA8lunmoDkWEN58ImMvpbVpgKWxmx4lCkj4U', 'resolutions': [{'height': 108, 'url': 'https://external-preview.redd.it/pKwbCmXQr0e7p_28h6kvxtq_kIUY-ul_ypP6Akl1J2I.jpg?width=108&crop=smart&auto=webp&s=07f7f520a05e17b4529b67d9b8eb62b9c9cf7413', 'width': 108}], 'source': {'height': 14... |
LLM training using FP8 | 3 | I've got access to a few H100 gpus, and I've been trying to get my hands on a working example of LLM training (Llama or Mistral) code using FP8. But all I found was some toy models using Transformer Engine library. If I want to use this TE library, do I have to redefine the suitable layers of LLM with FP8 support? Seem... | 2023-11-22T20:31:28 | https://www.reddit.com/r/LocalLLaMA/comments/181iwaa/llm_training_using_fp8/ | tinyburger1 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 181iwaa | false | null | t3_181iwaa | /r/LocalLLaMA/comments/181iwaa/llm_training_using_fp8/ | false | false | self | 3 | null |
Any success in finetuning StyleTTS2? | 3 | Hey guys, just wondering if anyone has had success finetuning StyleTTS2 yet?
The only one I can find is the LJSpeech model, which sounds really good! But wondering what some other narrators / speakers would sound like, especially voices more outside the training dataset. | 2023-11-22T20:21:39 | https://www.reddit.com/r/LocalLLaMA/comments/181io84/any_success_in_finetuning_styletts2/ | enterguild | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 181io84 | false | null | t3_181io84 | /r/LocalLLaMA/comments/181io84/any_success_in_finetuning_styletts2/ | false | false | self | 3 | null |
When inferencing Mistral7b (or Mistral 7b Orca) for RAG getting "out of memory", but works fine for llama 2 model. | 1 | 2023-11-22T20:00:17 | Anu_Rag9704 | i.redd.it | 1970-01-01T00:00:00 | 0 | {} | 181i6fu | false | null | t3_181i6fu | /r/LocalLLaMA/comments/181i6fu/when_inferencing_mistral7b_or_mistral_7b_orca_for/ | false | false | 1 | {'enabled': True, 'images': [{'id': '2Hdx59Z_YBwxEPqUi3Skl0mTtakNmvXkrO0iqMBLbJg', 'resolutions': [{'height': 28, 'url': 'https://preview.redd.it/ropph633gy1c1.png?width=108&crop=smart&auto=webp&s=fce1a5b9a60cf88b025b81899b4c5f67b310cc57', 'width': 108}, {'height': 56, 'url': 'https://preview.redd.it/ropph633gy1c1.png?... | |||
1.3B with 68.29% Humaneval lol, don't behead me. Part of my project PIC (partner-in-crime) | 91 | Hello after a long time :)
I am TokenBender.
Some of you may remember my previous model - [codeCherryPop](https://www.reddit.com/r/LocalLLaMA/comments/156htzy/i_made_llama2_7b_into_a_really_useful_coder/?utm_source=share&utm_medium=web2x&context=3)
It was very kindly received so I am hoping I won't be killed t... | 2023-11-22T19:12:56 | https://www.reddit.com/r/LocalLLaMA/comments/181h3lv/13b_with_6829_humaneval_lol_dont_behead_me_part/ | ahm_rimer | self.LocalLLaMA | 2023-11-23T12:18:33 | 0 | {} | 181h3lv | false | null | t3_181h3lv | /r/LocalLLaMA/comments/181h3lv/13b_with_6829_humaneval_lol_dont_behead_me_part/ | false | false | 91 | {'enabled': False, 'images': [{'id': 'wFIEPE5sfLdV1gWoi19KpI0L2iHzNdZHMiO_wVvJtfI', 'resolutions': [{'height': 58, 'url': 'https://external-preview.redd.it/WSZ9kma0ZzNXtBkDlVL7TlggtW0gn3Hoe-dBqrlNkW0.jpg?width=108&crop=smart&auto=webp&s=1a33525424cf8bc2fbace9b69513c37a57832131', 'width': 108}, {'height': 116, 'url': 'h... | |
Is there a grammarly equivalent I can run locally? | 19 | I'm looking for a writing assistant that, instead of writing for me, can instead suggest ways to improve a given chunk of text. | 2023-11-22T18:14:07 | https://www.reddit.com/r/LocalLLaMA/comments/181fphq/is_there_a_grammarly_equivalent_i_can_run_locally/ | PictureAggravating36 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 181fphq | false | null | t3_181fphq | /r/LocalLLaMA/comments/181fphq/is_there_a_grammarly_equivalent_i_can_run_locally/ | false | false | self | 19 | null |
DPO fintuning usecase | 1 | I want to finetune a llm to make it biased twoards specific point of view in big subject like poltical, economical, ..etc
the base model already knows some of these not always allign with the what i want it to adobt
i have organized a dataset of QAs about this topic
so the question is it better to fintune i... | 2023-11-22T18:08:10 | https://www.reddit.com/r/LocalLLaMA/comments/181fknb/dpo_fintuning_usecase/ | Ok_Method2263 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 181fknb | false | null | t3_181fknb | /r/LocalLLaMA/comments/181fknb/dpo_fintuning_usecase/ | false | false | self | 1 | null |
Noob question: How would I go about finetuning a LLM on my personal ChatGPT/Claude conversations? | 1 | [removed] | 2023-11-22T17:58:05 | https://www.reddit.com/r/LocalLLaMA/comments/181fbnz/noob_question_how_would_i_go_about_finetuning_a/ | airtwink | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 181fbnz | false | null | t3_181fbnz | /r/LocalLLaMA/comments/181fbnz/noob_question_how_would_i_go_about_finetuning_a/ | false | false | self | 1 | null |
AI anywhere? Its more likely than you think. | 1 | [removed] | 2023-11-22T16:58:19 | https://www.reddit.com/r/LocalLLaMA/comments/181dwm6/ai_anywhere_its_more_likely_than_you_think/ | hibbity | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 181dwm6 | false | null | t3_181dwm6 | /r/LocalLLaMA/comments/181dwm6/ai_anywhere_its_more_likely_than_you_think/ | false | false | self | 1 | {'enabled': False, 'images': [{'id': '8UT0IduGQyrEh8J3QvAC7PXW-klXcbQ3PArYngINglQ', 'resolutions': [{'height': 81, 'url': 'https://external-preview.redd.it/zyV4t0uox14ElTlexI0Qs5mAgtCzDE70Zjurb-pnC6k.jpg?width=108&crop=smart&auto=webp&s=7893b7928ad32f4b6722302eb535f3d10e4fbf8f', 'width': 108}, {'height': 162, 'url': 'h... |
I’m extremely confused about system requirements. Some people are worried about ram and others about vram. I have 64gb of ram and 12gb vram. What size of model can I run? | 49 | From what I’ve read mac somehow uses system ram and windows uses the gpu? It doesn’t make any sense to me. Any help appreciated. | 2023-11-22T16:29:32 | https://www.reddit.com/r/LocalLLaMA/comments/181d8u7/im_extremely_confused_about_system_requirements/ | A0sanitycomp | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 181d8u7 | false | null | t3_181d8u7 | /r/LocalLLaMA/comments/181d8u7/im_extremely_confused_about_system_requirements/ | false | false | self | 49 | null |
Cheapest 20xx series GPU for 3/4bit llama.cpp? | 1 | [removed] | 2023-11-22T15:51:10 | https://www.reddit.com/r/LocalLLaMA/comments/181c9aa/cheapest_20xx_series_gpu_for_34bit_llamacpp/ | Substantial-Scene-85 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 181c9aa | false | null | t3_181c9aa | /r/LocalLLaMA/comments/181c9aa/cheapest_20xx_series_gpu_for_34bit_llamacpp/ | false | false | self | 1 | null |
ShareGPT4V - New multi-modal model, improves on LLaVA | 75 | 2023-11-22T15:21:30 | https://sharegpt4v.github.io/ | Cradawx | sharegpt4v.github.io | 1970-01-01T00:00:00 | 0 | {} | 181bimx | false | null | t3_181bimx | /r/LocalLLaMA/comments/181bimx/sharegpt4v_new_multimodal_model_improves_on_llava/ | false | false | default | 75 | null | |
Should I use exllamav2 and tensorRT-LLM to get the best in H100 GPU? | 1 | I understand that quantization is used for consumer GPUs like GTX/RTX series. Will this even make it faster? I have just 20 GB on H100 (MIG partitioned) to run Llama2 13 B Chat. | 2023-11-22T15:11:10 | https://www.reddit.com/r/LocalLLaMA/comments/181bam1/should_i_use_exllamav2_and_tensorrtllm_to_get_the/ | sanjeevr5 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 181bam1 | false | null | t3_181bam1 | /r/LocalLLaMA/comments/181bam1/should_i_use_exllamav2_and_tensorrtllm_to_get_the/ | false | false | self | 1 | null |
CUDA out of Memory Error | 1 | I'm using a Colab notebook with a T4 to have Llama 2 summarize all tables in a PDF. It works for the first 10 or so tables, and then I'm getting the dreaded CUDA out of memory error.
It seems like each successive summarization call is accumulating on the GPU, is there some way to clear the allocated memory from the p... | 2023-11-22T15:10:40 | https://www.reddit.com/r/LocalLLaMA/comments/181ba78/cuda_out_of_memory_error/ | Plus-Significance348 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 181ba78 | false | null | t3_181ba78 | /r/LocalLLaMA/comments/181ba78/cuda_out_of_memory_error/ | false | false | self | 1 | null |
How to finetune llama 2 on a tpu? | 1 | I'm trying to train llama 2 on a tpu using qlora and peft. All the scripts I find are tied to CUDA. Are there any available? | 2023-11-22T15:04:10 | https://www.reddit.com/r/LocalLLaMA/comments/181b53s/how_to_finetune_llama_2_on_a_tpu/ | DirectionOdd9824 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 181b53s | false | null | t3_181b53s | /r/LocalLLaMA/comments/181b53s/how_to_finetune_llama_2_on_a_tpu/ | false | false | self | 1 | null |
Finetuning on already instruct-tuned model? | 1 | I'm trying to add a new task to a model (openhermes-2.5) using lora, but it seems that it makes the model forget everything except the task that I trained for. Is there something that I need to do? Or am I supposed to train on the whole dataset + mine? | 2023-11-22T14:43:48 | https://www.reddit.com/r/LocalLLaMA/comments/181aonw/finetuning_on_already_instructtuned_model/ | SkyIDreamer | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 181aonw | false | null | t3_181aonw | /r/LocalLLaMA/comments/181aonw/finetuning_on_already_instructtuned_model/ | false | false | self | 1 | null |
Finishing prematurely - training a LoRA on GPTQ model | 1 | [removed] | 2023-11-22T14:35:10 | https://www.reddit.com/r/LocalLLaMA/comments/181aiae/finishing_prematurely_training_a_lora_on_gptq/ | Vilzuh | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 181aiae | false | null | t3_181aiae | /r/LocalLLaMA/comments/181aiae/finishing_prematurely_training_a_lora_on_gptq/ | false | false | self | 1 | {'enabled': False, 'images': [{'id': 'no-_VcwSHgX4jsi9L-tyBgEBLBctYb3Whc_WK-BgumA', 'resolutions': [{'height': 81, 'url': 'https://external-preview.redd.it/Z381OAmbeDEeeb5My043bAffbxrgqi5srl_-TtcwCJQ.jpg?width=108&crop=smart&auto=webp&s=68be753c177af2b633634da4dd8a584a811630e7', 'width': 108}, {'height': 162, 'url': 'h... |
llama2 13B on Gtx 1070 | 5 | Can I run llama2 13B locally on my Gtx 1070? I read somewhere minimum suggested VRAM is 10 GB but since the 1070 has 8GB would it just run a little slower? or could I use some quantization with bitsandbytes for example to make it fit and run more smoothly? | 2023-11-22T14:25:27 | https://www.reddit.com/r/LocalLLaMA/comments/181ab6j/llama2_13b_on_gtx_1070/ | Suleyman_III | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 181ab6j | false | null | t3_181ab6j | /r/LocalLLaMA/comments/181ab6j/llama2_13b_on_gtx_1070/ | false | false | self | 5 | null |
How to host an LLM which can be reached via an API for NSFW chat | 1 | [removed] | 2023-11-22T14:13:03 | https://www.reddit.com/r/LocalLLaMA/comments/181a1uk/how_to_host_an_llm_which_can_be_reached_via_an/ | Substantial-Scene-85 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 181a1uk | false | null | t3_181a1uk | /r/LocalLLaMA/comments/181a1uk/how_to_host_an_llm_which_can_be_reached_via_an/ | false | false | nsfw | 1 | null |
The Economics of LLMs in Production | 1 | [removed] | 2023-11-22T14:10:08 | https://www.reddit.com/r/LocalLLaMA/comments/1819zkc/the_economics_of_llms_in_production/ | idan_R1 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 1819zkc | false | null | t3_1819zkc | /r/LocalLLaMA/comments/1819zkc/the_economics_of_llms_in_production/ | false | false | self | 1 | {'enabled': False, 'images': [{'id': 'mYui0GEkidvtx_7sDtPxkyAdrbzPzoYVly6YJidw8o8', 'resolutions': [{'height': 54, 'url': 'https://external-preview.redd.it/Rav8IP6Mc-rEJE9J1ZsgGVMvbQqQfS5wk5L85OZyxdA.jpg?width=108&crop=smart&auto=webp&s=196fed1162fd702a3380aac0bb44147c28cd1334', 'width': 108}, {'height': 108, 'url': 'h... |
Exllama v2 vs. llama.cpp (All layes offloaded to GPU) | 3 | Will there be a significant difference in speed and quality between LLama v2 GPTQ using Exllama v2 and LLama v2 GGUF using llama.cpp by offloading all the layers to GPU? | 2023-11-22T14:08:44 | https://www.reddit.com/r/LocalLLaMA/comments/1819yj9/exllama_v2_vs_llamacpp_all_layes_offloaded_to_gpu/ | WinterUsed1120 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 1819yj9 | false | null | t3_1819yj9 | /r/LocalLLaMA/comments/1819yj9/exllama_v2_vs_llamacpp_all_layes_offloaded_to_gpu/ | false | false | self | 3 | null |
wasmedge ggml error | 1 | I'm getting GGML\_ASSERT: /Users/hydai/workspace/WasmEdge/plugins/wasi\_nn/thirdparty/ggml/ggml-metal.m:1459: false
Abort trap: 6
When I try to run wasmedge --dir .:. --nn-preload default:GGML:AUTO:Orca-2-13b-ggml-model-q4\_0.gguf llama-chat.wasm -p chatml -s '....
​
hydai is not a user on my mac! I have... | 2023-11-22T13:27:58 | https://www.reddit.com/r/LocalLLaMA/comments/181944r/wasmedge_ggml_error/ | sgt102 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 181944r | false | null | t3_181944r | /r/LocalLLaMA/comments/181944r/wasmedge_ggml_error/ | false | false | default | 1 | null |
Dataset de-duplication methods | 3 | Hey everyone,
I have a dataset that has around 8million pairs of prompts and responses collected and curated from a bunch of open-source datasets in hf. I wanted to know what's the best method to dedup this dataset. I am planning on doing this locally (4090 with 64gb ram) and I've looked into a few methods but I wasn'... | 2023-11-22T13:24:31 | https://www.reddit.com/r/LocalLLaMA/comments/18191pw/dataset_deduplication_methods/ | Dry_Long3157 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 18191pw | false | null | t3_18191pw | /r/LocalLLaMA/comments/18191pw/dataset_deduplication_methods/ | false | false | self | 3 | null |
How do I go about training an open source llm on a postgres database | 1 | Howdy,
I'm a backend developer, and management recently asked me to train an llm on our company data. I'm a bit over my head here, and I figured I'd ask for high level advice rather than continuing to go down google rabbit holes.
What I've tried so far:
* I spun up some gpu instances on AWS. Couldn't get llama to wo... | 2023-11-22T13:22:38 | https://www.reddit.com/r/LocalLLaMA/comments/18190ds/how_do_i_go_about_training_an_open_source_llm_on/ | Particular-Tour-118 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 18190ds | false | null | t3_18190ds | /r/LocalLLaMA/comments/18190ds/how_do_i_go_about_training_an_open_source_llm_on/ | false | false | self | 1 | {'enabled': False, 'images': [{'id': 'SG6tYDdRU3Tt2JciPU9aaMVkncukiAUjKyabUiZxC4s', 'resolutions': [{'height': 53, 'url': 'https://external-preview.redd.it/-SlFoShTVbu9vr3a6s7VVd5wu9KcPh1goPTR_74rTAw.jpg?width=108&crop=smart&auto=webp&s=8312cd2d4cb342cd87e37fe7e2317f1a32b3f00d', 'width': 108}, {'height': 106, 'url': 'h... |
40x or more speedup by selecting important neurons | 92 | ERROR: type should be string, got "https://arxiv.org/abs/2311.10770\n\n\"UltraFastBERT\", apparently a variant of BERT, that uses only 0.3% of it's neurons during inference, is performing on par with similar BERT models.\n\nI hope that's going to be available for all kinds of models in the near future!" | 2023-11-22T13:21:42 | https://www.reddit.com/r/LocalLLaMA/comments/1818zox/40x_or_more_speedup_by_selecting_important_neurons/ | koehr | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 1818zox | false | null | t3_1818zox | /r/LocalLLaMA/comments/1818zox/40x_or_more_speedup_by_selecting_important_neurons/ | false | false | self | 92 | {'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... |
Help me find the right model for my low end PC and for NSFW chat purpose | 1 | [removed] | 2023-11-22T13:13:27 | https://www.reddit.com/r/LocalLLaMA/comments/1818tz2/help_me_find_the_right_model_for_my_low_end_pc/ | Substantial-Scene-85 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 1818tz2 | false | null | t3_1818tz2 | /r/LocalLLaMA/comments/1818tz2/help_me_find_the_right_model_for_my_low_end_pc/ | false | false | nsfw | 1 | null |
What would you want senators to ask during hearings? | 18 | Specialists and technical folks hang out here. What would you, if you were in Congress, ask Big Tech companies in Congressional hearings? You may ask technical questions. As we know Senators are so bad at asking questions. | 2023-11-22T12:50:52 | https://www.reddit.com/r/LocalLLaMA/comments/1818eao/what_would_you_want_senators_to_ask_during/ | chatsgpt | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 1818eao | false | null | t3_1818eao | /r/LocalLLaMA/comments/1818eao/what_would_you_want_senators_to_ask_during/ | false | false | self | 18 | null |
OpenAI to bring Altman back as CEO | 2 | 2023-11-22T12:48:40 | https://newyorkverified.com/4322664-openai-altman-return-ceo/ | anujtomar_17 | newyorkverified.com | 1970-01-01T00:00:00 | 0 | {} | 1818cqv | false | null | t3_1818cqv | /r/LocalLLaMA/comments/1818cqv/openai_to_bring_altman_back_as_ceo/ | false | false | 2 | {'enabled': False, 'images': [{'id': 'rXCkM4TB5S6ovgzCh7K4AojzqLOAtDuo2WgzM-3Q8eg', 'resolutions': [{'height': 60, 'url': 'https://external-preview.redd.it/JOLFORA_yywCzimZEuIzMv4Y5UXPtsoJX5zFL8k0VTs.jpg?width=108&crop=smart&auto=webp&s=e0c120ae2424416549428f8f735bb836ee4cfb8d', 'width': 108}, {'height': 121, 'url': 'h... | ||
Multiple 4060ti VS 4090 for training/inference | 2 | I've been in need of a dedicated training rig lately and so I've been looking at gpus. For context I'm already running training on a 16gb 3080ti laptop and inference on a 16gb 4060ti. Both are really just fine for 13B models.
When I'm looking at cards though it appears I could buy nearly 4 more 16gb 4060ti cards for ... | 2023-11-22T12:38:04 | https://www.reddit.com/r/LocalLLaMA/comments/18185xi/multiple_4060ti_vs_4090_for_traininginference/ | __SlimeQ__ | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 18185xi | false | null | t3_18185xi | /r/LocalLLaMA/comments/18185xi/multiple_4060ti_vs_4090_for_traininginference/ | false | false | self | 2 | null |
Formatting the response of LLM in the way Chatgpt or Claude shows on UI. | 4 | Hey everyone, I have recently tried and deployed llama-2 on my GPU. And I wish to format the text output received from the LLM and show it in the way ChatGPT UI shows. The code blocks and texts blocks separately. Please any help or suggestion would help me a lot. Or if there is any open source llm api serving project w... | 2023-11-22T12:11:00 | https://www.reddit.com/r/LocalLLaMA/comments/1817pi7/formatting_the_response_of_llm_in_the_way_chatgpt/ | One-Difficulty3149 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 1817pi7 | false | null | t3_1817pi7 | /r/LocalLLaMA/comments/1817pi7/formatting_the_response_of_llm_in_the_way_chatgpt/ | false | false | self | 4 | null |
What embedding model do you guys use? | 8 | I'm trying to test more embedding models and I'm wondering what does this community use...
I know that it "may vary depending on use case", so in that case please share model and related use case.
(intrested in both bi encoder and cross encoder)
Thanks im advance!!! | 2023-11-22T11:01:00 | https://www.reddit.com/r/LocalLLaMA/comments/1816l7m/what_embedding_model_do_you_guys_use/ | Distinct-Target7503 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 1816l7m | false | null | t3_1816l7m | /r/LocalLLaMA/comments/1816l7m/what_embedding_model_do_you_guys_use/ | false | false | self | 8 | null |
How much does Quantization actually impact models? - KL Divergence Tests | 184 | So, it was bothering me a bit that the only metric people really had to understand the 'loss' of quantization *objectively* was perplexity.
So, after hacking with koboldcpp's sampler code to force output probabilities for a predetermined sequence so that I can make a fair comparison...
[Mistral 7b Avg Quantization D... | 2023-11-22T10:53:39 | https://www.reddit.com/r/LocalLLaMA/comments/1816h1x/how_much_does_quantization_actually_impact_models/ | kindacognizant | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 1816h1x | false | null | t3_1816h1x | /r/LocalLLaMA/comments/1816h1x/how_much_does_quantization_actually_impact_models/ | false | false | 184 | null | |
Local backend optimization settings koboldcpp | 1 | What model format and kobold.cpp settings will net me the fastest performance if I have an rtx 4080 + 32gb vram + 13700k?
In terms of should I load it onto the vram, gpu or a mix of both, how would I go about it in the settings? | 2023-11-22T10:51:44 | https://www.reddit.com/r/LocalLLaMA/comments/1816fzh/local_backend_optimization_settings_koboldcpp/ | Mobile-Bandicoot-553 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 1816fzh | false | null | t3_1816fzh | /r/LocalLLaMA/comments/1816fzh/local_backend_optimization_settings_koboldcpp/ | false | false | self | 1 | null |
The sibbling problem - solved by inner dialog? | 4 | Hi,
​
I think you all know this sibling problem that none of the local LMs can solve directly. I just tried an approach where the model has an internal dialogue about the problem. And it managed to solve it.
​
I used the OpenHermes2.5 Mistral model q5\_k\_m. | 2023-11-22T10:38:23 | https://www.reddit.com/r/LocalLLaMA/comments/18168xt/the_sibbling_problem_solved_by_inner_dialog/ | Traditional-Plate642 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 18168xt | false | null | t3_18168xt | /r/LocalLLaMA/comments/18168xt/the_sibbling_problem_solved_by_inner_dialog/ | false | false | self | 4 | null |
The creator of MythoMax presents: MythoMix-7B! | 68 | Gryphe, creator of MythoMax basically merged the best Mistral models together. This should be a really fantastic model!
[https://huggingface.co/Gryphe/MythoMist-7b](https://huggingface.co/Gryphe/MythoMist-7b) (links to quantized models by TheBloke can be found there)
​ | 2023-11-22T10:38:15 | https://www.reddit.com/r/LocalLLaMA/comments/18168ug/the_creator_of_mythomax_presents_mythomix7b/ | dampflokfreund | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 18168ug | false | null | t3_18168ug | /r/LocalLLaMA/comments/18168ug/the_creator_of_mythomax_presents_mythomix7b/ | false | false | self | 68 | {'enabled': False, 'images': [{'id': 'pyiYAScjuwRclcP2CHgf3lOyi04ZZSpia9-kNlBsFzo', 'resolutions': [{'height': 58, 'url': 'https://external-preview.redd.it/LIYZ6VHdS7V_l08A1dqbMPZwK2TDSioH6afeybggnis.jpg?width=108&crop=smart&auto=webp&s=e1aaf34a704348a71e4db7666c562caba9a984c9', 'width': 108}, {'height': 116, 'url': 'h... |
The sibbling problem - solved by inner dialog? | 1 | [removed] | 2023-11-22T10:08:24 | https://www.reddit.com/r/LocalLLaMA/comments/1815u8t/the_sibbling_problem_solved_by_inner_dialog/ | One-Magician-6270 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 1815u8t | false | null | t3_1815u8t | /r/LocalLLaMA/comments/1815u8t/the_sibbling_problem_solved_by_inner_dialog/ | false | false | self | 1 | null |
Best LLM that can be hosted on a CPU? | 1 | What's the closest we can get to GPT-4 quality without a GPU? | 2023-11-22T10:05:30 | https://www.reddit.com/r/LocalLLaMA/comments/1815ssj/best_llm_that_can_be_hosted_on_a_cpu/ | Alternative_Card_989 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 1815ssj | false | null | t3_1815ssj | /r/LocalLLaMA/comments/1815ssj/best_llm_that_can_be_hosted_on_a_cpu/ | false | false | self | 1 | null |
Access Ollama server from another machine connected to same network (MacOS) | 1 | Hello,
I am trying to access Ollama server from another machine connected to same network. What I have tried is to use the IP address obtained by running ifconfig in the terminal in replacement of localhost in the curl command:
curl http://localhost:11434/api/generate -d '{ "model": "llama2", "prompt":"Why is the... | 2023-11-22T10:01:31 | https://www.reddit.com/r/LocalLLaMA/comments/1815qq0/access_ollama_server_from_another_machine/ | Erimay | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 1815qq0 | false | null | t3_1815qq0 | /r/LocalLLaMA/comments/1815qq0/access_ollama_server_from_another_machine/ | false | false | self | 1 | null |
Exponentially Faster Language Modelling: 40-78x Faster Feedforward for NLU thanks to FFFs | 176 | 2023-11-22T09:34:12 | https://arxiv.org/abs/2311.10770 | lexected | arxiv.org | 1970-01-01T00:00:00 | 0 | {} | 1815czk | false | null | t3_1815czk | /r/LocalLLaMA/comments/1815czk/exponentially_faster_language_modelling_4078x/ | false | false | 176 | {'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... | ||
I made a video as requested. | 1 | 2023-11-22T09:32:36 | https://v.redd.it/haai1fa2cv1c1 | hibbity | v.redd.it | 1970-01-01T00:00:00 | 0 | {} | 1815c81 | false | {'reddit_video': {'bitrate_kbps': 2400, 'dash_url': 'https://v.redd.it/haai1fa2cv1c1/DASHPlaylist.mpd?a=1703237569%2CMzBlMzI5NjU2NGNlYjk4MTgwYThkMGYwNWM2Y2IzMDRmNjc0Yjg5ZmFmZDdiMTlmOThlNWFhMmI3NTEwMjkzNA%3D%3D&v=1&f=sd', 'duration': 27, 'fallback_url': 'https://v.redd.it/haai1fa2cv1c1/DASH_720.mp4?source=fallback', 'ha... | t3_1815c81 | /r/LocalLLaMA/comments/1815c81/i_made_a_video_as_requested/ | false | false | 1 | {'enabled': False, 'images': [{'id': 'c2F4d2JjamRjdjFjMf3mJp_4mwjtW7p41eLiA0PAwFTS8eTZKbSD-szYjsXG', 'resolutions': [{'height': 60, 'url': 'https://external-preview.redd.it/c2F4d2JjamRjdjFjMf3mJp_4mwjtW7p41eLiA0PAwFTS8eTZKbSD-szYjsXG.png?width=108&crop=smart&format=pjpg&auto=webp&s=d8a9c92703b1f7dd4310ed7c8e4a93f236ea9... | ||
Anybody working with low-resource languages? | 5 | Specifically asking for RAG applications. I'll appreciate any tips about the current best practices regarding complex document retrieval in a low-resource language. Thanks. | 2023-11-22T09:22:12 | https://www.reddit.com/r/LocalLLaMA/comments/1815700/anybody_working_with_lowresource_languages/ | coumineol | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 1815700 | false | null | t3_1815700 | /r/LocalLLaMA/comments/1815700/anybody_working_with_lowresource_languages/ | false | false | self | 5 | null |
I need 7B: llama-2-Chat but I don't have enough Gpu, is there a collab version? | 1 | [removed] | 2023-11-22T08:51:14 | https://www.reddit.com/r/LocalLLaMA/comments/1814rjq/i_need_7b_llama2chat_but_i_dont_have_enough_gpu/ | Substantial-Scene-85 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 1814rjq | false | null | t3_1814rjq | /r/LocalLLaMA/comments/1814rjq/i_need_7b_llama2chat_but_i_dont_have_enough_gpu/ | false | false | self | 1 | {'enabled': False, 'images': [{'id': '13mYvMTbHrtY4dgYaEcV2C1QHE7RrK6uJ6EZAZ9BcDM', 'resolutions': [{'height': 54, 'url': 'https://external-preview.redd.it/Z_6KO9dX9ShyOMeJW6G6oS8AQh1zHmzYEZsJXjius00.jpg?width=108&crop=smart&auto=webp&s=4bc2398f900934f6f98befb13469a5914057a751', 'width': 108}, {'height': 108, 'url': 'h... |
Do GGUF not take all the VRAM needed when loaded? | 1 | Is this normal behavior?
I'm still learning but I noticed that if I load a normal LLM like [https://huggingface.co/teknium/OpenHermes-2-Mistral-7B](https://huggingface.co/teknium/OpenHermes-2-Mistral-7B) it will take all the VRAM available (I have a 3080 10GB).
But when I load the quantized model like [https://huggi... | 2023-11-22T08:22:17 | https://www.reddit.com/r/LocalLLaMA/comments/1814de8/do_gguf_not_take_all_the_vram_needed_when_loaded/ | bullerwins | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 1814de8 | false | null | t3_1814de8 | /r/LocalLLaMA/comments/1814de8/do_gguf_not_take_all_the_vram_needed_when_loaded/ | false | false | self | 1 | {'enabled': False, 'images': [{'id': '0qzUB07On6JaZMkOGDN84IgQJ4CHVDUUVtbr0vdzvn4', 'resolutions': [{'height': 58, 'url': 'https://external-preview.redd.it/Yr6HWGJaUFKzx38f7NY_Td-hKPIofuh6_Idfb0HbweI.jpg?width=108&crop=smart&auto=webp&s=aa71ef9cbe02446c6d7c50353800096b83a2a7f8', 'width': 108}, {'height': 116, 'url': 'h... |
Interest so run a local LLaMA with RTX 3060 12G | 2 | Simple question, is it worth stopping using Chatgpt (not plus) in order to use a local version of a LLAMA with my current GC ? | 2023-11-22T08:05:40 | https://www.reddit.com/r/LocalLLaMA/comments/18144u6/interest_so_run_a_local_llama_with_rtx_3060_12g/ | Daitan_ | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 18144u6 | false | null | t3_18144u6 | /r/LocalLLaMA/comments/18144u6/interest_so_run_a_local_llama_with_rtx_3060_12g/ | false | false | self | 2 | null |
How important is pci-e speed/gen/lanes when doing inference? | 10 | I'm trying to assess whether or not to try and run a second GPU in my second full length slot. My mobo manual reports the fatest the second slot can go is pci-e 2.0 at x4 lanes. A paltry 2GB/s correct?
Can anyone comment from personal experience? | 2023-11-22T07:46:53 | https://www.reddit.com/r/LocalLLaMA/comments/1813uxf/how_important_is_pcie_speedgenlanes_when_doing/ | wh33t | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 1813uxf | false | null | t3_1813uxf | /r/LocalLLaMA/comments/1813uxf/how_important_is_pcie_speedgenlanes_when_doing/ | false | false | self | 10 | null |
Has Anyone Successfully Utilized the Neural Networks API on Android for LLMS with EdgeTPU? | 5 | Hey everyone,
I've been exploring running lightweight machine learning models (LLMS) on Android devices and came across the [Neural Networks API](https://developer.android.com/ndk/guides/neuralnetworks), which seems promising for leveraging neural silicon ASICs.
I own a Google Pixel 7, which features an EdgeTPU integ... | 2023-11-22T07:41:27 | https://www.reddit.com/r/LocalLLaMA/comments/1813s70/has_anyone_successfully_utilized_the_neural/ | dewijones92 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 1813s70 | false | null | t3_1813s70 | /r/LocalLLaMA/comments/1813s70/has_anyone_successfully_utilized_the_neural/ | false | false | self | 5 | {'enabled': False, 'images': [{'id': '42vxviEj_6H1K1N26XHeF6HjIOmKs06u82fF3JCaVc8', 'resolutions': [{'height': 60, 'url': 'https://external-preview.redd.it/cMo7WYlu0TNMT-uQB8a_R2DDut0uDZyo8B39hcOjBFw.jpg?width=108&crop=smart&auto=webp&s=4b1e43d7aa7b63eeb1da1bf3eebbe63343476976', 'width': 108}, {'height': 121, 'url': 'h... |
I have a 3080, what would be the best upgrade? | 1 | I have a used 3090 on the way that I got for 650€ shipped.
Can I use the 3090 and the 3080 at the same time?
I’ve seen many 2x3090’s here but not 3080+3090.
I have a Gigabyte x570 elite motherboard so 2x16 slots though the second one runs at pcie 3.0 I believe. I also have an AMD 5950x and 32GB Ram at 3200Mhz.
Wo... | 2023-11-22T07:10:05 | https://www.reddit.com/r/LocalLLaMA/comments/1813cdb/i_have_a_3080_what_would_be_the_best_upgrade/ | bullerwins | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 1813cdb | false | null | t3_1813cdb | /r/LocalLLaMA/comments/1813cdb/i_have_a_3080_what_would_be_the_best_upgrade/ | false | false | self | 1 | null |
Altman to Return as OpenAI CEO With Taylor, Summers on New Board | 5 | 2023-11-22T06:55:01 | https://www.bloomberg.com/news/articles/2023-11-22/sam-altman-to-return-as-openai-ceo-with-a-new-board?srnd=premium | super-helper | bloomberg.com | 1970-01-01T00:00:00 | 0 | {} | 18134op | false | null | t3_18134op | /r/LocalLLaMA/comments/18134op/altman_to_return_as_openai_ceo_with_taylor/ | false | false | 5 | {'enabled': False, 'images': [{'id': 'YW-7ojF5RxNDSmOqlL243Wh4lYJv5jiFXn40CZex7k0', 'resolutions': [{'height': 71, 'url': 'https://external-preview.redd.it/QNPQsyrzpuRjjPmuRouI2nsZHyV4EWolpsX5z6PaWw8.jpg?width=108&crop=smart&auto=webp&s=a30d69ec2c34013f94b6a8fe858dc1f87a7a6abe', 'width': 108}, {'height': 143, 'url': 'h... | ||
Ollama docker container on 16 core system.. no gpu.. slow.. help | 1 | Just new to all this, literally started yesterday reading up on things, LMSTudio on my Mac.. figured I have my old 16 core threadripper system (Gen1) not in use. Just a Ubuntu 22.04 server os, GPU is old school cheap one with HDMI out. Not a gaming GPU.
I figured the 16 cores would provide enough power for single que... | 2023-11-22T06:52:21 | https://www.reddit.com/r/LocalLLaMA/comments/18133av/ollama_docker_container_on_16_core_system_no_gpu/ | Dry-Vermicelli-682 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 18133av | false | null | t3_18133av | /r/LocalLLaMA/comments/18133av/ollama_docker_container_on_16_core_system_no_gpu/ | false | false | self | 1 | null |
OpenAI brings Sam Altman back as CEO | 189 | 2023-11-22T06:19:11 | https://www.cnbc.com/2023/11/22/openai-brings-sam-altman-back-as-ceo-days-after-ouster.html | fallingdowndizzyvr | cnbc.com | 1970-01-01T00:00:00 | 0 | {} | 1812l45 | false | null | t3_1812l45 | /r/LocalLLaMA/comments/1812l45/openai_brings_sam_altman_back_as_ceo/ | false | false | 189 | {'enabled': False, 'images': [{'id': 'y4aKNNlmhEOnYoktZg0N9vzadp6wC5xAJij9j-ZABEk', 'resolutions': [{'height': 60, 'url': 'https://external-preview.redd.it/P6tYAPi5mgTs0eooS0y3TLcefPD2BN1WgXPeck0Rc88.jpg?width=108&crop=smart&auto=webp&s=ebe104668dd4873dfb641d6eeed8f03c0b5d02d0', 'width': 108}, {'height': 121, 'url': 'h... | ||
Any interest in C#/.NET for serving LLMs? | 1 | [K024/llm-sharp: Language models in C# (github.com)](https://github.com/K024/llm-sharp)
I've recently drafted this. But adding more models & features & tests & documentation will just cost too much time. Seeking for comments & colaborators. | 2023-11-22T06:17:53 | https://www.reddit.com/r/LocalLLaMA/comments/1812kek/any_interest_in_cnet_for_serving_llms/ | Key-Comparison3261 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 1812kek | false | null | t3_1812kek | /r/LocalLLaMA/comments/1812kek/any_interest_in_cnet_for_serving_llms/ | false | false | self | 1 | {'enabled': False, 'images': [{'id': '_WjwMS0saB_6lE4UPWNLJ-nLMqlZcGe9AQgXucUf3WU', 'resolutions': [{'height': 54, 'url': 'https://external-preview.redd.it/MnA_NHT9JT2Q4ni1bZij95SyomGRsOotqpiKiveMojs.jpg?width=108&crop=smart&auto=webp&s=665c9c94d438f832edf590e2d8849e768ecb27a9', 'width': 108}, {'height': 108, 'url': 'h... |
Why didn't gpt4 work at first and how did they "fix it"? | 120 | According to this [tweet](https://x.com/0interestrates/status/1725745633003475102?s=20),
>when gpt4 first finished training it didn’t actually work very well and the whole team thought it’s over, scaling is dead…until greg went into a cave for weeks and somehow magically made it work
So gpt-4 was kind of broken at fi... | 2023-11-22T05:57:49 | https://www.reddit.com/r/LocalLLaMA/comments/18128r4/why_didnt_gpt4_work_at_first_and_how_did_they_fix/ | Amgadoz | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 18128r4 | false | null | t3_18128r4 | /r/LocalLLaMA/comments/18128r4/why_didnt_gpt4_work_at_first_and_how_did_they_fix/ | false | false | self | 120 | {'enabled': False, 'images': [{'id': 'SlmH7qy6GBdmSkdvvIU8KiwTQJtXeXlmCERIxSwA-kc', 'resolutions': [{'height': 108, 'url': 'https://external-preview.redd.it/wCT6oGmkGuVonCY6dzlB3rEbsHAHhnqHlI5JtuvLye8.jpg?width=108&crop=smart&auto=webp&s=ee0ba76c6de2fcc38fafe09911fc388087fbd8b1', 'width': 108}], 'source': {'height': 20... |
I found this on github. It works pretty good! Lots of good info in the "settings" too. | 1 | 2023-11-22T05:45:58 | https://github.com/aseichter2007/ClipboardConqueror | hibbity | github.com | 1970-01-01T00:00:00 | 0 | {} | 18121vk | false | null | t3_18121vk | /r/LocalLLaMA/comments/18121vk/i_found_this_on_github_it_works_pretty_good_lots/ | false | false | default | 1 | {'enabled': False, 'images': [{'id': 's6DSZrtBZpXlKZPX4XaiQo8c7AcEBeBFbVpI5UKiqdo', 'resolutions': [{'height': 54, 'url': 'https://external-preview.redd.it/abtIQMCNg5n0qebDbrOVkkXMqjx7A6KZKQ7Qo6j-CNc.jpg?width=108&crop=smart&auto=webp&s=5eeba7ce573463cf69f1ebd38ec0cb69660caf7f', 'width': 108}, {'height': 108, 'url': 'h... | |
Multi GPU vs Single GPU with same VRAM | 10 | It seems a fair bit cheaper to hit a certain VRAM target with multi vs single GPU setups. I'm wondering if there are any \*recent\* experiments or blog posts I can read to learn more about what GPU's would be best to get with the black friday sales coming up | 2023-11-22T05:07:49 | https://www.reddit.com/r/LocalLLaMA/comments/1811fk4/multi_gpu_vs_single_gpu_with_same_vram/ | -Lousy | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 1811fk4 | false | null | t3_1811fk4 | /r/LocalLLaMA/comments/1811fk4/multi_gpu_vs_single_gpu_with_same_vram/ | false | false | self | 10 | null |
Is there any resource or website where I can track ranking of my favorite models vs today's? there just so many models it hard to stay up to date. For example, I want to benchmark GPT3.5turbo0301. I feel this was the last of their model to be uncensored and it eventually deprecates. | 1 | [removed] | 2023-11-22T04:55:13 | https://www.reddit.com/r/LocalLLaMA/comments/18117tz/is_there_any_resource_or_website_where_i_can/ | sweetsunnyside | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 18117tz | false | null | t3_18117tz | /r/LocalLLaMA/comments/18117tz/is_there_any_resource_or_website_where_i_can/ | false | false | self | 1 | null |
Amica: open source interface for interactive communication with 3D characters with voice synthesis, speech recognition, visual understanding, and an emotion system | 1 | 2023-11-22T03:26:55 | https://twitter.com/arbius_ai/status/1727135805041209770 | arbiusai | twitter.com | 1970-01-01T00:00:00 | 0 | {} | 180zoly | false | {'oembed': {'author_name': 'Arbius', 'author_url': 'https://twitter.com/arbius_ai', 'cache_age': 3153600000, 'height': None, 'html': '<blockquote class="twitter-video"><p lang="en" dir="ltr">Introducing... Amica! 👩\u200d🦰🤖<br><br>Amica is an open source interface for interactive communication with 3D characters with... | t3_180zoly | /r/LocalLLaMA/comments/180zoly/amica_open_source_interface_for_interactive/ | false | false | default | 1 | {'enabled': False, 'images': [{'id': 't5OrUK912rS1OgphZtSuYZyH1Mc_E8MEhkTj6bvwNe4', 'resolutions': [{'height': 60, 'url': 'https://external-preview.redd.it/XfDWcW5e3O1R1_3bzjtB59N3q81KW7d5ZEKi8AGMF4E.jpg?width=108&crop=smart&auto=webp&s=0f38c48045379c574e985d6594af6b545a6faba7', 'width': 108}], 'source': {'height': 78,... | |
First version of C++ port of GGML for llama.cpp | 1 | [removed] | 2023-11-22T02:27:01 | https://www.reddit.com/r/LocalLLaMA/comments/180yirg/first_version_of_c_port_of_ggml_for_llamacpp/ | introsp3ctor | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 180yirg | false | null | t3_180yirg | /r/LocalLLaMA/comments/180yirg/first_version_of_c_port_of_ggml_for_llamacpp/ | false | false | self | 1 | {'enabled': False, 'images': [{'id': 'RvBkIQDLy_YpMikhgQqrhnhgvW3Oj3DArdrUB0ca16s', 'resolutions': [{'height': 51, 'url': 'https://external-preview.redd.it/eWnkelVx7JsaFV8Lh3WckxMi1tPEht5TYt6OGkT-T78.jpg?width=108&crop=smart&auto=webp&s=f7595d8e3d488189a6fded920ca3fe960c1524ab', 'width': 108}], 'source': {'height': 67,... |
How would you create a PII scanner over a codebase? | 1 | Hello friends, I am an experienced data scientist -mainly on tabular data - who just acquired a new task at my job: create a PII scanner over a codebase.
Not the PII itself, but detecting stuff like sending PII via HTTP, direct database operations and logging user information.
Since I have no experience on the LLM f... | 2023-11-22T01:28:51 | https://www.reddit.com/r/LocalLLaMA/comments/180xd69/how_would_you_create_a_pii_scanner_over_a_codebase/ | dick_veganas | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 180xd69 | false | null | t3_180xd69 | /r/LocalLLaMA/comments/180xd69/how_would_you_create_a_pii_scanner_over_a_codebase/ | false | false | self | 1 | null |
Silence Model Loading Output | 1 | I am using LlamaCpp from langchain to run the model locally. I'm finding all of the output printed when the model loads to be a major distraction. These are all the lines that start with llama\_model\_loader and so forth. Is there a way to silence all of that? Setting verbose to False did not do anything. I weirdly can... | 2023-11-22T01:20:39 | https://www.reddit.com/r/LocalLLaMA/comments/180x7fa/silence_model_loading_output/ | anonymous_pro_ | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 180x7fa | false | null | t3_180x7fa | /r/LocalLLaMA/comments/180x7fa/silence_model_loading_output/ | false | false | self | 1 | null |
Running Mistral 7B/ Llama 2 13B on AWS Lambda using llama.cpp | 1 | [removed] | 2023-11-22T01:11:28 | https://www.reddit.com/r/LocalLLaMA/comments/180x0yf/running_mistral_7b_llama_2_13b_on_aws_lambda/ | Allergic2Humans | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 180x0yf | false | null | t3_180x0yf | /r/LocalLLaMA/comments/180x0yf/running_mistral_7b_llama_2_13b_on_aws_lambda/ | false | false | self | 1 | {'enabled': False, 'images': [{'id': 'TI5yP0eLgUYZgddxhCymVgc_pWQuufStnkwhdMEZOzg', 'resolutions': [{'height': 60, 'url': 'https://external-preview.redd.it/daiwKyxio9uhC-0eXG1nEp75Bv2XgWGV_TK4sLseD_Q.jpg?width=108&crop=smart&auto=webp&s=b52961f7d1bfc052d1b1dd2333eaea7f6604fa59', 'width': 108}, {'height': 121, 'url': 'h... |
Fine Tuning from Datasets on Cloud | 3 | I currently have a script to parse data from the old Reddit API archives, and sort it vaguely into q/a format. Here's a snippet from a dataset:
>user: Yeah, you laugh now. Wait until you encounter code like that in the wild.
>
>assistant: It's like hearing about the platypus in school and laughing, then going on ... | 2023-11-22T01:11:02 | https://www.reddit.com/r/LocalLLaMA/comments/180x0mv/fine_tuning_from_datasets_on_cloud/ | 51869101 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 180x0mv | false | null | t3_180x0mv | /r/LocalLLaMA/comments/180x0mv/fine_tuning_from_datasets_on_cloud/ | false | false | self | 3 | null |
Rocket 🦝 - smol model that overcomes models much larger in size | 121 | We're proud to introduce Rocket-3B 🦝, a state-of-the-art 3 billion parameter model!
​
🌌 **Size vs. Performance:** Rocket-3B may be smaller with its 3 billion parameters, but it punches way above its weight. In head-to-head benchmarks like MT-Bench and AlpacaEval, it consistently outperforms models up to 20 t... | 2023-11-22T00:17:58 | https://www.reddit.com/r/LocalLLaMA/comments/180vx9y/rocket_smol_model_that_overcomes_models_much/ | starkiller1298 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 180vx9y | false | null | t3_180vx9y | /r/LocalLLaMA/comments/180vx9y/rocket_smol_model_that_overcomes_models_much/ | false | false | 121 | {'enabled': False, 'images': [{'id': 'wTs0MX-v3khpprOoqVxUTbAaSnqNA9A5XJWNV_-1m5E', 'resolutions': [{'height': 58, 'url': 'https://external-preview.redd.it/DiOslLCpz4ZKgHLISp7Iz7jXXhE9rqn8ouMEgOtJ3fY.jpg?width=108&crop=smart&auto=webp&s=d4be5951ecaae7c8df2ed84e87e2576468e31e1f', 'width': 108}, {'height': 116, 'url': 'h... | |
Tesla P40 cards - what cooling solutions work well? | 5 | I'm thinking of picking up a Tesla P40 as a fun project, but can't use a blower fan because of sound / a lack of appropriate fan headers.
I'm wondering if anyone has info on how well these solutions might work or other solutions that work well:
1. 2-3 CPU fans ziptied to the front or back of the card. Possibly with ... | 2023-11-22T00:10:01 | https://www.reddit.com/r/LocalLLaMA/comments/180vr7k/tesla_p40_cards_what_cooling_solutions_work_well/ | Rich_Examination_637 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 180vr7k | false | null | t3_180vr7k | /r/LocalLLaMA/comments/180vr7k/tesla_p40_cards_what_cooling_solutions_work_well/ | false | false | self | 5 | null |
Introducing Rocket 🦝 - smol model that overcomes models much larger in size | 1 | [removed] | 2023-11-22T00:08:11 | https://www.reddit.com/r/LocalLLaMA/comments/180vptb/introducing_rocket_smol_model_that_overcomes/ | pansophicAI | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 180vptb | false | null | t3_180vptb | /r/LocalLLaMA/comments/180vptb/introducing_rocket_smol_model_that_overcomes/ | false | false | 1 | {'enabled': False, 'images': [{'id': 'wTs0MX-v3khpprOoqVxUTbAaSnqNA9A5XJWNV_-1m5E', 'resolutions': [{'height': 58, 'url': 'https://external-preview.redd.it/DiOslLCpz4ZKgHLISp7Iz7jXXhE9rqn8ouMEgOtJ3fY.jpg?width=108&crop=smart&auto=webp&s=d4be5951ecaae7c8df2ed84e87e2576468e31e1f', 'width': 108}, {'height': 116, 'url': 'h... | |
noobq - cloud-based GPU + chatbot advice | 3 | I've dipped my toes in the local LLM pool over the past few months and it's been an incredible experience. I'm running a 3060 with ooba, sometimes with Silly Tavern as the front end, mostly 7b's and a few 13b's.
However, my setup just isn't strong enough to run a truly consistently smart chatbot and I'm wondering abo... | 2023-11-21T23:48:54 | https://www.reddit.com/r/LocalLLaMA/comments/180vagi/noobq_cloudbased_gpu_chatbot_advice/ | motivcreative | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 180vagi | false | null | t3_180vagi | /r/LocalLLaMA/comments/180vagi/noobq_cloudbased_gpu_chatbot_advice/ | false | false | self | 3 | null |
Today is the first day I’m getting results comparable to GPT4 on OpenSource LLM workflows. | 275 | Yes this is anecdotal but I’ve been a heavy user of OpenAI API and paid GPT Pro before it was cool. A few weeks ago I tested a workflow to send the same prompt to two instances of the same LLM with different parameters. Today I setup the basic workflow to provision two different LLMs concurrently and have them validate... | 2023-11-21T23:34:24 | https://www.reddit.com/gallery/180uz42 | LocoMod | reddit.com | 1970-01-01T00:00:00 | 0 | {} | 180uz42 | false | null | t3_180uz42 | /r/LocalLLaMA/comments/180uz42/today_is_the_first_day_im_getting_results/ | false | false | 275 | null | |
Looking for the smalest model for JSON generation or checks | 1 | I wish there were a small model for JSON generation, or check/correct JSON things;
Obviously I could use very big model for that but that is going to cost a lot; and it's kinda for fun and NSFW purpuses so like it's not a good idea, if you have any model that is very good at this usecase I'll be very happy; at the sam... | 2023-11-21T23:33:35 | https://www.reddit.com/r/LocalLLaMA/comments/180uyi9/looking_for_the_smalest_model_for_json_generation/ | Regular_Instruction | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 180uyi9 | false | null | t3_180uyi9 | /r/LocalLLaMA/comments/180uyi9/looking_for_the_smalest_model_for_json_generation/ | false | false | nsfw | 1 | null |
GPTs Free Alternative (Kinda) | 1 | Recently I came across a platform called youai , It give you the ability to create custom AI chat bots for consumers, SMBs, and enterprises .
It's basicly a GPTs but with more models like llama 2 70b and mistral 7b (it also support gpt 4 but for paid plans ).
you can make money with it but you will have to be on a pa... | 2023-11-21T23:08:03 | https://www.reddit.com/r/LocalLLaMA/comments/180udqo/gpts_free_alternative_kinda/ | MidnightAutomatic361 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 180udqo | false | null | t3_180udqo | /r/LocalLLaMA/comments/180udqo/gpts_free_alternative_kinda/ | false | false | self | 1 | {'enabled': False, 'images': [{'id': 'JMGZEiDRnMuLHibyUKyi3byDb5lJuEHaZ-Mj9rWvd5k', 'resolutions': [{'height': 56, 'url': 'https://external-preview.redd.it/F9D-CzPr4EDscnAceeiNMcJdZ-pcPW4NWgzNmarCgqI.jpg?width=108&crop=smart&auto=webp&s=e291e5f7aa1626897f2d9155e1b3e6d86acce112', 'width': 108}, {'height': 113, 'url': 'h... |
What are the best Text-to-3D models out there right now? | 1 | Im keen to see if I can integrate one directly into unreal engine. | 2023-11-21T22:44:56 | https://www.reddit.com/r/LocalLLaMA/comments/180tudu/what_are_the_best_textto3d_models_out_there_right/ | Chance_Confection_37 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 180tudu | false | null | t3_180tudu | /r/LocalLLaMA/comments/180tudu/what_are_the_best_textto3d_models_out_there_right/ | false | false | self | 1 | null |
Look ahead decoding offers massive (~1.5x) speedup for inference | 1 | 2023-11-21T22:38:55 | https://lmsys.org/blog/2023-11-21-lookahead-decoding/ | lans_throwaway | lmsys.org | 1970-01-01T00:00:00 | 0 | {} | 180tpja | false | null | t3_180tpja | /r/LocalLLaMA/comments/180tpja/look_ahead_decoding_offers_massive_15x_speedup/ | false | false | 1 | {'enabled': False, 'images': [{'id': 'icR3Ob4zLCI1nSlpjTQftasiFrBqERZYFRe8wZ4MLW4', 'resolutions': [{'height': 60, 'url': 'https://external-preview.redd.it/NWLS2w-ftbEXOJMJyKnNs_P4sQEd-fzyjuxzzB9YOS4.jpg?width=108&crop=smart&auto=webp&s=9bf1b43dfbc0251c3053c625fb4c1fbb794ff804', 'width': 108}, {'height': 121, 'url': 'h... | ||
Combining LoRA and GPTQ quantization, plug | 1 | [removed] | 2023-11-21T22:18:06 | https://www.reddit.com/r/LocalLLaMA/comments/180t8g7/combining_lora_and_gptq_quantization_plug/ | Gazorpazzor | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 180t8g7 | false | null | t3_180t8g7 | /r/LocalLLaMA/comments/180t8g7/combining_lora_and_gptq_quantization_plug/ | false | false | self | 1 | {'enabled': False, 'images': [{'id': 'AB-zoAwVqCEw36AXKNxq-jJMX9-u6SE6Tkrzs6hGmjs', 'resolutions': [{'height': 26, 'url': 'https://external-preview.redd.it/rklv953z7fzggt45I537r3HqVNirwYeImxHGJDGOLgk.jpg?width=108&crop=smart&auto=webp&s=e65ed31e8732195ecf465121e0a235f2824e3f3d', 'width': 108}, {'height': 52, 'url': 'ht... |
How to clean memory between model queries + best smaller model for code generation | 2 | Hi all!
I’m doing an experiment, in which I use mistral-7b-instruct to describe an algorithm of doing certain stuff, and then prompting it to write Python code, using said algorithm as guide rails of sorts and then shooting the code into Python REPL to check the results.
It works reasonably well, but sometimes it pro... | 2023-11-21T22:16:37 | https://www.reddit.com/r/LocalLLaMA/comments/180t78g/how_to_clean_memory_between_model_queries_best/ | netikas | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 180t78g | false | null | t3_180t78g | /r/LocalLLaMA/comments/180t78g/how_to_clean_memory_between_model_queries_best/ | false | false | self | 2 | null |
Subsets and Splits
No community queries yet
The top public SQL queries from the community will appear here once available.