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 ⌀ |
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
Good model for geopolicial analysis writing? | 1 | Hi there
Just getting into local AI. Set LM Studio on my laptop (Gigabyte g5) and got a bunch of models running great (7b and 13b), even set up the obsidian plugin to use them right inside the app. All good. Quite happy to explore further and this community has been fantastic. So thank you all.
Now, my question: ... | 2024-01-28T10:18:51 | https://www.reddit.com/r/LocalLLaMA/comments/1aczne7/good_model_for_geopolicial_analysis_writing/ | Fishtotem | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 1aczne7 | false | null | t3_1aczne7 | /r/LocalLLaMA/comments/1aczne7/good_model_for_geopolicial_analysis_writing/ | false | false | self | 1 | null |
LM Studio v0.2.11 Update Significantly Speeds Up Inference Running Server | 20 | I've been using LM Studio to run a local server ver. of Mixtral-8x7b to generate training data: run up a 500-token context chunk, use a prompt to generate output (in this case a story writing prompt that relates to the context), and then output the generated prompt to a df. Last week it took about 70 seconds per itera... | 2024-01-28T10:01:56 | https://www.reddit.com/r/LocalLLaMA/comments/1aczecv/lm_studio_v0211_update_significantly_speeds_up/ | Mbando | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 1aczecv | false | null | t3_1aczecv | /r/LocalLLaMA/comments/1aczecv/lm_studio_v0211_update_significantly_speeds_up/ | false | false | self | 20 | null |
I have a Radeon 6750XT and a 5600x CPU:which models can I run? Is it still a pain to run models with AMD cards on windows 10? | 1 | As title says. I remember that it used to be impossibile to run LLMs on windows while usong AMD, but I heard that it has somehow changed. Is it true that now it's possible to run model with an AMD card using Windows? If so, which models would I be able to use?
If it's not possible, can I run it by using Linux on a vir... | 2024-01-28T09:29:25 | https://www.reddit.com/r/LocalLLaMA/comments/1acyxid/i_have_a_radeon_6750xt_and_a_5600x_cpuwhich/ | wolfbetter | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 1acyxid | false | null | t3_1acyxid | /r/LocalLLaMA/comments/1acyxid/i_have_a_radeon_6750xt_and_a_5600x_cpuwhich/ | false | false | self | 1 | null |
recommendations for PC/components? | 1 | I'm looking to get a new computer because I need something powerful for various projects, especially for running local models. My current one can manage everything but it's super slow - even a 7B model takes about 15 minutes to do one task. I'd love to get suggestions for a setup that costs between $1000-$2000, somethi... | 2024-01-28T08:48:14 | https://www.reddit.com/r/LocalLLaMA/comments/1acycjp/recommendations_for_pccomponents/ | JamesAibr | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 1acycjp | false | null | t3_1acycjp | /r/LocalLLaMA/comments/1acycjp/recommendations_for_pccomponents/ | false | false | self | 1 | null |
Introducing Vaartaalaap: A Chatbot UI for Local LLM Servers | 12 | I'm excited to share a project I've been working on: **Vaartaalaap**, a chatbot application that connects with local Large Language Model (LLM) servers. This is especially useful for those who have set up their own LLM server and are looking for an easy-to-use interface to interact with it.
## Features
* **Dynamic Ba... | 2024-01-28T08:41:32 | https://www.reddit.com/r/LocalLLaMA/comments/1acy92d/introducing_vaartaalaap_a_chatbot_ui_for_local/ | Reasonable_Ad9033 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 1acy92d | false | null | t3_1acy92d | /r/LocalLLaMA/comments/1acy92d/introducing_vaartaalaap_a_chatbot_ui_for_local/ | false | false | self | 12 | {'enabled': False, 'images': [{'id': 'KsYArBpd2dFUYQLND8_DxYVu_AH88zPk-ir_SSsv1Hg', 'resolutions': [{'height': 54, 'url': 'https://external-preview.redd.it/s5mHJ4NNC37HcLtFkKNYCvXPJBUkToCmBNZ1iQLl2Y8.jpg?width=108&crop=smart&auto=webp&s=49c647057f703346d4971eb3c5c5848be443d6c1', 'width': 108}, {'height': 108, 'url': 'h... |
Introducing Vaartaalaap: A Chatbot UI for Local LLM Servers | 1 | 2024-01-28T08:32:32 | Reasonable_Ad9033 | i.redd.it | 1970-01-01T00:00:00 | 0 | {} | 1acy49z | false | null | t3_1acy49z | /r/LocalLLaMA/comments/1acy49z/introducing_vaartaalaap_a_chatbot_ui_for_local/ | false | false | 1 | {'enabled': True, 'images': [{'id': '1pKJZfAVJK-8byVZl_qjeZ7Gr_IprC8rWNdSe-6Z7eM', 'resolutions': [{'height': 216, 'url': 'https://preview.redd.it/jfhhb3lm65fc1.jpeg?width=108&crop=smart&auto=webp&s=d7cfe57a3024746a7bc808b6ff213af7709de625', 'width': 108}, {'height': 432, 'url': 'https://preview.redd.it/jfhhb3lm65fc1.j... | |||
Best Practices for Semantic Search on 200k vectors (30GB) Worth of Embeddings? | 2 | Hi, I have converted some domain-specific name vectors into embeddings, with a dataset size of 200k words. All the embeddings were generated using OpenAI's embedding model 3 (3072 dim per embedding) . Now I am planning to implement semantic search similarity. Given a domain keyword, I want to find the top 5 most simila... | 2024-01-28T08:19:52 | https://www.reddit.com/r/LocalLLaMA/comments/1acxxks/best_practices_for_semantic_search_on_200k/ | stoicbats_ | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 1acxxks | false | null | t3_1acxxks | /r/LocalLLaMA/comments/1acxxks/best_practices_for_semantic_search_on_200k/ | false | false | self | 2 | null |
What's the best 1-4B LLM for a phone? | 19 | Im gonna buy a pixel 7 and I wanna know what are the best small LLMs that I can use with other apps? | 2024-01-28T06:56:15 | https://www.reddit.com/r/LocalLLaMA/comments/1acwoan/whats_the_best_14b_llm_for_a_phone/ | Whydoiexist2983 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 1acwoan | false | null | t3_1acwoan | /r/LocalLLaMA/comments/1acwoan/whats_the_best_14b_llm_for_a_phone/ | false | false | self | 19 | null |
Training Local LLMs on ones own chat logs. | 7 | Say I export conversations from my GPT using their tool. This data would be full of preferential output examples, and potentially relevant information for the user. What would the workflow look like to parse all this into a locally run model? Would it be worth it? How is a LoRa useful here? | 2024-01-28T06:45:19 | https://www.reddit.com/r/LocalLLaMA/comments/1acwi47/training_local_llms_on_ones_own_chat_logs/ | cm8ty | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 1acwi47 | false | null | t3_1acwi47 | /r/LocalLLaMA/comments/1acwi47/training_local_llms_on_ones_own_chat_logs/ | false | false | self | 7 | null |
Lora Fine-tuning when model is too large for a single GPU | 2 | Hello, I plan to fine-tune the Yi-34B with Lora for text classification tasks on 8 x A30 24GB VRAM. I set device\_map="auto" when loading the model, but the training speed is extremely slow (only one GPU is working and the other GPUs are idle). Is there any way to solve it? | 2024-01-28T06:40:39 | https://www.reddit.com/r/LocalLLaMA/comments/1acwfdr/lora_finetuning_when_model_is_too_large_for_a/ | Tight_Win7479 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 1acwfdr | false | null | t3_1acwfdr | /r/LocalLLaMA/comments/1acwfdr/lora_finetuning_when_model_is_too_large_for_a/ | false | false | self | 2 | null |
Mixtal8x7B Instruct with Tools on Google Colab | 9 | [https://github.com/willspag/Mixtral8x7B-AI-Chat-Colab](https://github.com/willspag/Mixtral8x7B-AI-Chat-Colab) | 2024-01-28T06:09:26 | https://www.reddit.com/r/LocalLLaMA/comments/1acvx66/mixtal8x7b_instruct_with_tools_on_google_colab/ | willspag | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 1acvx66 | false | null | t3_1acvx66 | /r/LocalLLaMA/comments/1acvx66/mixtal8x7b_instruct_with_tools_on_google_colab/ | false | false | self | 9 | {'enabled': False, 'images': [{'id': 'PDr-59_KRWv7tdqzDn5VKcDswcyg0mZu5LdG2ZoXBNE', 'resolutions': [{'height': 54, 'url': 'https://external-preview.redd.it/gqvRGQrtnyOEZjHcZULQdvh_4It7Xi3Sxq0xQcpzEDQ.jpg?width=108&crop=smart&auto=webp&s=8ff86e632da7bd67066f6ab07da323fcde299c17', 'width': 108}, {'height': 108, 'url': 'h... |
Is there a Mistal 7B OVA file for running in a VM in virtualbox or proxmox ? | 1 | It would be great to just import one file and use it ! | 2024-01-28T06:02:28 | https://www.reddit.com/r/LocalLLaMA/comments/1acvt8l/is_there_a_mistal_7b_ova_file_for_running_in_a_vm/ | transdimensionalmeme | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 1acvt8l | false | null | t3_1acvt8l | /r/LocalLLaMA/comments/1acvt8l/is_there_a_mistal_7b_ova_file_for_running_in_a_vm/ | false | false | self | 1 | null |
Initial source code understanding of ggml (llama.cpp) | 41 | I have taken quite some machine learning courses and have done a few projects already. I think I know the math formula involved in transformers and GPT models. However, I always wondered how they work in reality. The best way for me is to read and understand source codes implementing these models.
I am a C/C++ progra... | 2024-01-28T05:45:07 | https://www.reddit.com/r/LocalLLaMA/comments/1acvimp/initial_source_code_understanding_of_ggml_llamacpp/ | Pitiful-You-8410 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 1acvimp | false | null | t3_1acvimp | /r/LocalLLaMA/comments/1acvimp/initial_source_code_understanding_of_ggml_llamacpp/ | false | false | self | 41 | {'enabled': False, 'images': [{'id': 'R4FlbjN2L22Lbm2XJGxiHbEmBoZ13M8R8mWmNTYKcTw', 'resolutions': [{'height': 54, 'url': 'https://external-preview.redd.it/IecFlCCvA9_d57R82wH2BVMcQaxRTUIlpoXU2PYU1aw.jpg?width=108&crop=smart&auto=webp&s=8f10e415851f64b7a42fde652bb6026171a1d700', 'width': 108}, {'height': 108, 'url': 'h... |
Confusion regarding what kind of PC to build | 1 | Hi all, and thanks in advance for your time.
I am obsessed with the idea of running uncensored LLMs locally. I recently bought a raspberry pi5 8GB and a coral edge TPU to try and run mixtral, but to my extreme disappointment, raspberry pi 5 OS doesn’t yet support the right version of python for the edge TPU.
So I wa... | 2024-01-28T05:36:28 | https://www.reddit.com/r/LocalLLaMA/comments/1acvde9/confusion_regarding_what_kind_of_pc_to_build/ | reenign3 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 1acvde9 | false | null | t3_1acvde9 | /r/LocalLLaMA/comments/1acvde9/confusion_regarding_what_kind_of_pc_to_build/ | false | false | self | 1 | null |
Is Vicuna 13B still the best all-around 13B model? | 73 | It's been a while since Vicuna-13B came out. Has there been something better that I haven't heard of? | 2024-01-28T05:04:30 | https://www.reddit.com/r/LocalLLaMA/comments/1acutft/is_vicuna_13b_still_the_best_allaround_13b_model/ | RenoHadreas | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 1acutft | false | null | t3_1acutft | /r/LocalLLaMA/comments/1acutft/is_vicuna_13b_still_the_best_allaround_13b_model/ | false | false | self | 73 | null |
Why Open AI can earn money from online embedding model? | 1 | If someone use this online model to get word/embedding pairs for future usage or even share to others, it sounds easy. | 2024-01-28T04:45:54 | https://www.reddit.com/r/LocalLLaMA/comments/1acuhm7/why_open_ai_can_earn_money_from_online_embedding/ | ImprovementEqual3931 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 1acuhm7 | false | null | t3_1acuhm7 | /r/LocalLLaMA/comments/1acuhm7/why_open_ai_can_earn_money_from_online_embedding/ | false | false | self | 1 | null |
How to get perfect label outputs via prompting: experiment w/ 10k observations | 42 | Using the completion formats, I was curious to know how much a single space could impact output for a smaller model like Mistral 7b. It's supposed to be better at following instructions but that's not necessarily the case. Below is a write up of my experiment to get the perfect output of only "Yes" or "No" labels. (Acc... | 2024-01-28T03:41:27 | https://www.reddit.com/r/LocalLLaMA/comments/1actbr1/how_to_get_perfect_label_outputs_via_prompting/ | GeeBrain | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 1actbr1 | false | null | t3_1actbr1 | /r/LocalLLaMA/comments/1actbr1/how_to_get_perfect_label_outputs_via_prompting/ | false | false | self | 42 | null |
Llama + RAG | 1 | I’m looking for a small project for building a QA tool that leverages Llama and RAG
Could you please suggest some ideas (give dataset if possible).
I would love to have something repaired to Wikipedia | 2024-01-28T03:26:41 | https://www.reddit.com/r/LocalLLaMA/comments/1act1mm/llama_rag/ | aHuskylol | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 1act1mm | false | null | t3_1act1mm | /r/LocalLLaMA/comments/1act1mm/llama_rag/ | false | false | self | 1 | null |
Introducing Polymind - A Multimodal, Function-Calling Powered TabbyAPI/llama.cpp WebUI | 98 | Here is my relatively basic Function calling based WebUI, it supports the following:
\* Internet searching with DuckDuckGo and web scraping capabilities
\* Image generation using ComfyUI
\* Image input with sharegpt4v (Over llama.cpp's server), OCR, and Yolo
\* Port scanning with Nmap
\* Wolfram Alpha integra... | 2024-01-28T02:43:03 | https://www.reddit.com/r/LocalLLaMA/comments/1acs77k/introducing_polymind_a_multimodal_functioncalling/ | itsme292 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 1acs77k | false | null | t3_1acs77k | /r/LocalLLaMA/comments/1acs77k/introducing_polymind_a_multimodal_functioncalling/ | false | false | self | 98 | {'enabled': False, 'images': [{'id': 's2Wr81oPhBvTPGqH93app7MqfnCuIpgp5DRxVs0XCXg', 'resolutions': [{'height': 54, 'url': 'https://external-preview.redd.it/e2YgYcMdGu7f_8W6UDx2ccmHevfOPQKXsEOOHFUe7tI.jpg?width=108&crop=smart&auto=webp&s=e6ddad87bf19352ef234b7092f8200bf649bf570', 'width': 108}, {'height': 108, 'url': 'h... |
Multimodal Local LLM? Where to start? | 1 | Since OPENAI announced the integration of Dall-e 3 inside Chat GPT-4 I have been thinking about this concept inside my head and lately I have become pretty restless about it.
I wish to put together something similar and local, running it on an RTX 3060 12GB gpu pc I have upstairs. I have been trying to understand and... | 2024-01-28T02:17:25 | https://www.reddit.com/r/LocalLLaMA/comments/1acrpe0/multimodal_local_llm_where_to_start/ | Yuri1103 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 1acrpe0 | false | null | t3_1acrpe0 | /r/LocalLLaMA/comments/1acrpe0/multimodal_local_llm_where_to_start/ | false | false | self | 1 | null |
I can't figure out how to load a model that supports running via CPU, in such a way, that it runs on my GPU instead. | 2 | Okay, so I got local ai chatbots working. I went to [https://github.com/oobabooga/text-generation-webui?tab=readme-ov-file](https://github.com/oobabooga/text-generation-webui?tab=readme-ov-file) I installed it.
Then I went to [https://huggingface.co/TheBloke](https://huggingface.co/TheBloke) and got some models. Gr... | 2024-01-28T02:00:48 | https://www.reddit.com/r/LocalLLaMA/comments/1acrdmu/i_cant_figure_out_how_to_load_a_model_that/ | namad | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 1acrdmu | false | null | t3_1acrdmu | /r/LocalLLaMA/comments/1acrdmu/i_cant_figure_out_how_to_load_a_model_that/ | false | false | self | 2 | {'enabled': False, 'images': [{'id': 'PhQJyxmurMqowQp75iAZUd0ixiXthL_-MhAMf7rBGEw', 'resolutions': [{'height': 54, 'url': 'https://external-preview.redd.it/7dl1r6kFXGQX8BJKT7vjqqi5FI3sV4Wd3ZsaSJA2SJw.jpg?width=108&crop=smart&auto=webp&s=11f79f9bef0a88e17de159018fb83017c1beb2e3', 'width': 108}, {'height': 108, 'url': 'h... |
Any guys successfully fine-tuned Llama2 without using hugging face? | 10 | Hi team,
Anybody successfully fine tuned Llama2 without using hugging face? All the articles or tutorial videos are using hugging face. Just wondering if there is any way to train Llama 2 without using it.
I am currently thinking about train Code Llama with our companies private repo, but unsure about policies and... | 2024-01-28T01:46:25 | https://www.reddit.com/r/LocalLLaMA/comments/1acr3nr/any_guys_successfully_finetuned_llama2_without/ | OkSwordfish8419 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 1acr3nr | false | null | t3_1acr3nr | /r/LocalLLaMA/comments/1acr3nr/any_guys_successfully_finetuned_llama2_without/ | false | false | self | 10 | null |
Speedups for a partially unloaded Mixtral? | 5 | Been running a version of mixtral (q3\_K\_M gguf), and I love the quality even when when compared to 20/34b models. However the prompt processing time is pretty long, \~40 seconds with a full 4096 context length. I only have a 16gb card, so I'm unable to fully load the model into vram.
ContextLimit: 4096/4096, Process... | 2024-01-28T00:33:58 | https://www.reddit.com/r/LocalLLaMA/comments/1acpm5b/speedups_for_a_partially_unloaded_mixtral/ | Salendron2 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 1acpm5b | false | null | t3_1acpm5b | /r/LocalLLaMA/comments/1acpm5b/speedups_for_a_partially_unloaded_mixtral/ | false | false | default | 5 | null |
Google Intentionally Censors Bard After It Generates the Answer Already | 202 | Hi all,
After noticing Bard's score on the chatbot arena, I decided to revisit it. (It was heavily censored during my initial review back then.) I gave it a simple instruction to test the model: **"Can you prepeare a readme markdown model card for Bard"**
Initially, it began generating the README perfectly, stating i... | 2024-01-27T23:41:24 | https://www.reddit.com/r/LocalLLaMA/comments/1acohlm/google_intentionally_censors_bard_after_it/ | Weyaxi | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 1acohlm | false | null | t3_1acohlm | /r/LocalLLaMA/comments/1acohlm/google_intentionally_censors_bard_after_it/ | false | false | 202 | {'enabled': False, 'images': [{'id': 'QEWGvdJfo6kYOge5rkBDjcY79lUpBBi3VFJLwMbf-KQ', 'resolutions': [{'height': 55, 'url': 'https://external-preview.redd.it/BFg22UIvj--iTF-aEbJNqMRNUGvn2O_H1VrXS1QEJ5g.jpg?width=108&crop=smart&auto=webp&s=7651cad987aba34b5bfcc9eb15e8b3ed68244ebe', 'width': 108}, {'height': 110, 'url': 'h... | |
AI tools and what are they for AI | 1 | [removed] | 2024-01-27T23:31:54 | https://www.reddit.com/r/LocalLLaMA/comments/1acoa2n/ai_tools_and_what_are_they_for_ai/ | StillOk1589 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 1acoa2n | false | null | t3_1acoa2n | /r/LocalLLaMA/comments/1acoa2n/ai_tools_and_what_are_they_for_ai/ | false | false | self | 1 | null |
Best local models to run with 256G CPU Mem. and 48GBx2 GPU Mem? | 14 | I just knew this subredit from twitter. I am very interested in running powerful local models to 1) analyze large source codes like documentation generation, and code explanation, etc. 2) have good QA sessions for any programming or technical questions. 3) in the long run, I want to automate my command line workflow us... | 2024-01-27T22:58:52 | https://www.reddit.com/r/LocalLLaMA/comments/1acnis4/best_local_models_to_run_with_256g_cpu_mem_and/ | Pitiful-You-8410 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 1acnis4 | false | null | t3_1acnis4 | /r/LocalLLaMA/comments/1acnis4/best_local_models_to_run_with_256g_cpu_mem_and/ | false | false | self | 14 | null |
Best Solution for Local Voice Input/Control | 3 | I'm a developer and recently injured my hand, so my typing skills are really struggling. I'd like to run something locally I can use for inputting text (not necessarily coding just general text) as well as potentially controlling things (selecting lines, etc.)
I've seen GitHub Copilot has a preview for controlling VS ... | 2024-01-27T21:40:28 | https://www.reddit.com/r/LocalLLaMA/comments/1aclqr7/best_solution_for_local_voice_inputcontrol/ | thekidkid32 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 1aclqr7 | false | null | t3_1aclqr7 | /r/LocalLLaMA/comments/1aclqr7/best_solution_for_local_voice_inputcontrol/ | false | false | self | 3 | null |
Most capable function calling open source models? | 35 | we've had a myriad of impressive tools and projects developed by talented groups of individuals which incorporate function calling and give us the ability to create custom functions as tools that our ai models can call, however it seems like they're all entirely based around openai's chatgpt function calling.
my que... | 2024-01-27T21:02:52 | https://www.reddit.com/r/LocalLLaMA/comments/1ackxxt/most_capable_function_calling_open_source_models/ | waywardspooky | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 1ackxxt | false | null | t3_1ackxxt | /r/LocalLLaMA/comments/1ackxxt/most_capable_function_calling_open_source_models/ | false | false | self | 35 | {'enabled': False, 'images': [{'id': 'a-tjppw3xK-IcRe8JT935F4vaqR9C3FGAy-yYd1ukkw', 'resolutions': [{'height': 58, 'url': 'https://external-preview.redd.it/CJMTX7dvXZsndDCh34hOwCQnJ-cwXPWD70ZnqAeyKys.jpg?width=108&crop=smart&auto=webp&s=46143f67b2054319392da81f30fef53e16f96b1e', 'width': 108}, {'height': 116, 'url': 'h... |
New nvidia driver for windows: Reduced performance during training? | 1 | Guys, If someone here uses WSL, do not upgrade your nvidia driver to 551.23, i got 50% descrease in performance during training and inference, lost a couple of hours until I realized that smth is off.
IDK why this happened, probably because they introduced cuda 12.4 in this update (according to nvidia-smi print).
I t... | 2024-01-27T21:00:35 | https://www.reddit.com/r/LocalLLaMA/comments/1ackvsf/new_nvidia_driver_for_windows_reduced_performance/ | oposteriori | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 1ackvsf | false | null | t3_1ackvsf | /r/LocalLLaMA/comments/1ackvsf/new_nvidia_driver_for_windows_reduced_performance/ | false | false | self | 1 | null |
Should I build a dual 4090 PC or get a Macbook with 128GB memory? | 64 | I am considering building a PC with 2x 4090s for a total of 48GB VRAM.
I need to use it for
\- local GPT (chat with documents, confidential, Apple Notes) - summarization, reasoning, insight
\- large context (32k - 200k) summaries
nice to have:
\- VR gaming
\- stable diffusion XL
I have read that prompt processi... | 2024-01-27T20:56:41 | https://www.reddit.com/r/LocalLLaMA/comments/1ackshi/should_i_build_a_dual_4090_pc_or_get_a_macbook/ | OppositeBeing | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 1ackshi | false | null | t3_1ackshi | /r/LocalLLaMA/comments/1ackshi/should_i_build_a_dual_4090_pc_or_get_a_macbook/ | false | false | self | 64 | null |
Vulkan backend for koboldcpp and llamacpp - Your experiences. | 35 | New koboldcpp release: [https://github.com/LostRuins/koboldcpp/releases/tag/v1.56](https://github.com/LostRuins/koboldcpp/releases/tag/v1.56)
Vulkan implementation for llamacpp: [https://github.com/ggerganov/llama.cpp/pull/2059](https://github.com/ggerganov/llama.cpp/pull/2059)
I'm curious if any of you had already t... | 2024-01-27T20:37:44 | https://www.reddit.com/r/LocalLLaMA/comments/1ackd03/vulkan_backend_for_koboldcpp_and_llamacpp_your/ | Puuuszzku | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 1ackd03 | false | null | t3_1ackd03 | /r/LocalLLaMA/comments/1ackd03/vulkan_backend_for_koboldcpp_and_llamacpp_your/ | false | false | self | 35 | {'enabled': False, 'images': [{'id': '39tqPiIPCi0TfBIccsC_TeFCNPHQgLhLRfgAtT1l88M', 'resolutions': [{'height': 54, 'url': 'https://external-preview.redd.it/Ar7_oa96Hqbeix3O9jx2ih9F9VFDUvx5vOlMusgR1tw.jpg?width=108&crop=smart&auto=webp&s=8fcc1b1f47b218ec6c2f5ae02dada17d81ade092', 'width': 108}, {'height': 108, 'url': 'h... |
Is there any way of running and fine-tunning LlaVa model under 8gb of VRAM | 2 | The required context length is at least 512 tokens. I could tolerate the strong quantization tho with Q-Lora for fine-tuning. Is there any projects that allow to do that out of the box? | 2024-01-27T20:29:59 | https://www.reddit.com/r/LocalLLaMA/comments/1ack6hp/is_there_any_way_of_running_and_finetunning_llava/ | Another__one | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 1ack6hp | false | null | t3_1ack6hp | /r/LocalLLaMA/comments/1ack6hp/is_there_any_way_of_running_and_finetunning_llava/ | false | false | default | 2 | null |
Mamba-3B-SlimPJ: State-space models rivaling the best Transformer architecture Albert Gu*, Tri Dao* | 52 | 2024-01-27T20:25:15 | https://cartesia.ai/mamba-3b-slimpj | MambaModel | cartesia.ai | 1970-01-01T00:00:00 | 0 | {} | 1ack2su | false | null | t3_1ack2su | /r/LocalLLaMA/comments/1ack2su/mamba3bslimpj_statespace_models_rivaling_the_best/ | false | false | default | 52 | null | |
One 4090 or 3 tesla T4? | 1 | Hi, i want to play and realiaze poc and I try to figure our the best cards for my bucks.
With ~2000€ of budget I'm wondering about above choice.
I think that the 4090 (the upcoming super) is way faster, but I would have twice the ram and you know that it matter to avoid offloading..
On another hand I guess that fit... | 2024-01-27T20:23:49 | https://www.reddit.com/r/LocalLLaMA/comments/1ack1kt/one_4090_or_3_tesla_t4/ | FrenchSouch | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 1ack1kt | false | null | t3_1ack1kt | /r/LocalLLaMA/comments/1ack1kt/one_4090_or_3_tesla_t4/ | false | false | self | 1 | null |
DeepSeek-Coder: When the Large Language Model Meets Programming -- The Rise of Code Intelligence - DeepSeek-AI 2024 - SOTA open-source coding model that surpasses GPT-3.5 and Codex while being unrestricted in research and commercial use! | 76 | Paper: [https://arxiv.org/abs/2401.14196](https://arxiv.org/abs/2401.14196)
Github: [https://github.com/deepseek-ai/DeepSeek-Coder](https://github.com/deepseek-ai/DeepSeek-Coder)
Models: [https://huggingface.co/deepseek-ai](https://huggingface.co/deepseek-ai)
Abstract:
>The rapid development of large language mo... | 2024-01-27T20:09:40 | https://www.reddit.com/r/LocalLLaMA/comments/1acjpn7/deepseekcoder_when_the_large_language_model_meets/ | Singularian2501 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 1acjpn7 | false | null | t3_1acjpn7 | /r/LocalLLaMA/comments/1acjpn7/deepseekcoder_when_the_large_language_model_meets/ | false | false | 76 | null | |
Mamba: Linear-Time Sequence Modeling with Selective State Spaces — Arxiv Dives | 1 | 2024-01-27T20:02:57 | https://archive.ph/mpZzd | MambaModel | archive.ph | 1970-01-01T00:00:00 | 0 | {} | 1acjkbz | false | null | t3_1acjkbz | /r/LocalLLaMA/comments/1acjkbz/mamba_lineartime_sequence_modeling_with_selective/ | false | false | default | 1 | null | |
GPU offloading with textai | 2 |
Hi,
I am running below txtai based code successfully, but it fails to offload to the GPU.
I have all Cuda dependencies etc. installed and LLM Studio runs the model fine & fast on my GPU
I already added gpu=True.
How to fix that for txtai?
Thnx DJP
import logging
from txtai.pipeline import LLM
... | 2024-01-27T19:56:37 | https://www.reddit.com/r/LocalLLaMA/comments/1acjeuo/gpu_offloading_with_textai/ | djpurno | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 1acjeuo | false | null | t3_1acjeuo | /r/LocalLLaMA/comments/1acjeuo/gpu_offloading_with_textai/ | false | false | self | 2 | null |
Any opensource LAM - large action model out there? | 1 | [removed] | 2024-01-27T19:40:58 | https://www.reddit.com/r/LocalLLaMA/comments/1acj1yu/any_opensource_lam_large_action_model_out_there/ | Western_Soil_4613 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 1acj1yu | false | null | t3_1acj1yu | /r/LocalLLaMA/comments/1acj1yu/any_opensource_lam_large_action_model_out_there/ | false | false | default | 1 | null |
Looking for advice on the best way to host my kobold server endpoint on Google cloud. | 2 | Just wanted to see if anyone here has experience with this and hopefully offer some advice.
I've been running kobold.cpp locally and I love the workflows I've gotten set up with different models. I'm finally to the stage of my project where I want to start breaking away from using openai, but I'm a bit lost as to how... | 2024-01-27T19:23:29 | https://www.reddit.com/r/LocalLLaMA/comments/1acinu2/looking_for_advice_on_the_best_way_to_host_my/ | OriginallyWhat | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 1acinu2 | false | null | t3_1acinu2 | /r/LocalLLaMA/comments/1acinu2/looking_for_advice_on_the_best_way_to_host_my/ | false | false | self | 2 | null |
Who do I have to pay to get easy+fast+private big model access? I want a service like "pick HF model, start chatting, get fast replies." | 1 | [removed] | 2024-01-27T19:23:26 | https://www.reddit.com/r/LocalLLaMA/comments/1acinsi/who_do_i_have_to_pay_to_get_easyfastprivate_big/ | drawntomore | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 1acinsi | false | null | t3_1acinsi | /r/LocalLLaMA/comments/1acinsi/who_do_i_have_to_pay_to_get_easyfastprivate_big/ | false | false | self | 1 | {'enabled': False, 'images': [{'id': 'N0PjtqUQGyPWX8xnYUx2rnPb_ksbdcg64BRu85dC-vU', 'resolutions': [{'height': 58, 'url': 'https://external-preview.redd.it/LFFaN1wapdPp-DeyBQHgLcyDThqLh1QwsFiIhzSkoTU.jpg?width=108&crop=smart&auto=webp&s=3285b48b4d896a760f601c33ac81c23770d1da37', 'width': 108}, {'height': 116, 'url': 'h... |
Xavier AGX 32GB to Orin NX 16GB, is it upgrade or downgrade for local LLM? | 1 | I have a Xavier AGX 32GB setup running dolphin-2.6-mistral-7b-dpo-laser.Q5\_K\_M.gguf, I'm getting about 7 tokens per second using 15W power profile. The GPU has plenty of RAM for that model, over 20GB free.
I'm planning to run multiple models, e.g. text to speech and vision models along with LLM. I'm curious about Or... | 2024-01-27T19:01:01 | https://www.reddit.com/r/LocalLLaMA/comments/1aci57o/xavier_agx_32gb_to_orin_nx_16gb_is_it_upgrade_or/ | SX-Reddit | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 1aci57o | false | null | t3_1aci57o | /r/LocalLLaMA/comments/1aci57o/xavier_agx_32gb_to_orin_nx_16gb_is_it_upgrade_or/ | false | false | self | 1 | null |
Local Vision Model with Speech to Speech | Faster Whisper + OpenVoice + Moondream(1.6B) | 1 | 2024-01-27T18:45:30 | https://v.redd.it/4hz03tcx21fc1 | allaboutai-kris | v.redd.it | 1970-01-01T00:00:00 | 0 | {} | 1achsfd | false | {'reddit_video': {'bitrate_kbps': 5000, 'dash_url': 'https://v.redd.it/4hz03tcx21fc1/DASHPlaylist.mpd?a=1708973145%2CYjYwOTQ5OWUyMGQ5ODEyOTJlZjY3OWUxNmZjOGQyMzZlYWJmOWRhN2IzNmJkOWQ0MzI5MmM3NTIyZTkyNWNkZQ%3D%3D&v=1&f=sd', 'duration': 39, 'fallback_url': 'https://v.redd.it/4hz03tcx21fc1/DASH_1080.mp4?source=fallback', 'h... | t3_1achsfd | /r/LocalLLaMA/comments/1achsfd/local_vision_model_with_speech_to_speech_faster/ | false | false | 1 | {'enabled': False, 'images': [{'id': 'ejd5d3ptcDUzMWZjMeWcFvdarz2Xk0K7BBIXGdMgTdPKuNpLj0YuwP1jQEq5', 'resolutions': [{'height': 60, 'url': 'https://external-preview.redd.it/ejd5d3ptcDUzMWZjMeWcFvdarz2Xk0K7BBIXGdMgTdPKuNpLj0YuwP1jQEq5.png?width=108&crop=smart&format=pjpg&auto=webp&s=29170ebf6f1f94b16579bd98a1ba7cc555b2e... | ||
Open source LLM for NLP | 1 | This might be a really dumb q but are there any open source LLMs that rival gpt-4 or Claude 2 for NLP tasks such as topic generation, summarization and question and answering?
Can be short snippets <8k context length. Just need accuracy / quality. | 2024-01-27T18:31:55 | https://www.reddit.com/r/LocalLLaMA/comments/1achh4h/open_source_llm_for_nlp/ | dimsumham | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 1achh4h | false | null | t3_1achh4h | /r/LocalLLaMA/comments/1achh4h/open_source_llm_for_nlp/ | false | false | self | 1 | null |
Synthetic data generation for instruct finetuning | 1 | [removed] | 2024-01-27T17:55:15 | https://www.reddit.com/r/LocalLLaMA/comments/1acgmg0/synthetic_data_generation_for_instruct_finetuning/ | Silver_Equivalent_58 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 1acgmg0 | false | null | t3_1acgmg0 | /r/LocalLLaMA/comments/1acgmg0/synthetic_data_generation_for_instruct_finetuning/ | false | false | self | 1 | null |
Open Source Multimodal 7B LLM? | 2 | I want to fine-tune multimodal model. I have only 8 GB VRAM so can fine-tune up to only 7B model. Is there any good Open Source multimodal 7B model? | 2024-01-27T17:24:41 | https://www.reddit.com/r/LocalLLaMA/comments/1acfwzi/open_source_multimodal_7b_llm/ | meetrais | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 1acfwzi | false | null | t3_1acfwzi | /r/LocalLLaMA/comments/1acfwzi/open_source_multimodal_7b_llm/ | false | false | self | 2 | null |
Meta's TTA "MAGNet" & moondream Vision are INSANE! [News] | 1 | [removed] | 2024-01-27T17:15:10 | https://www.reddit.com/r/LocalLLaMA/comments/1acfp7j/metas_tta_magnet_moondream_vision_are_insane_news/ | dev-spot | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 1acfp7j | false | null | t3_1acfp7j | /r/LocalLLaMA/comments/1acfp7j/metas_tta_magnet_moondream_vision_are_insane_news/ | false | false | self | 1 | {'enabled': False, 'images': [{'id': 'YCeJTA90LNOekHTCwmESIY0FJu1q4_uNeuXKLHP270s', 'resolutions': [{'height': 81, 'url': 'https://external-preview.redd.it/BD5m-Omc9jt3kY09Hu_AdLohYEDrjxuwkRkr2UPgh0A.jpg?width=108&crop=smart&auto=webp&s=8ca8f63d16ea16dd59d4db3a30b1d966f317c88e', 'width': 108}, {'height': 162, 'url': 'h... |
MLX + Mixtral 16-bit on MacBook Pro M3 Max? | 2 | Does anyone here have experience running [16-bit Mixtral with MLX](https://github.com/ml-explore/mlx-examples/blob/main/llms/mixtral/README.md) on a maxed out MacBook Pro M3 Max (16-core CPU/40-core GPU/128GB)? Trying to tempt myself to upgrade from my 2021 M1 Max 64GB and this seems like it could be a good excuse. | 2024-01-27T17:14:34 | https://www.reddit.com/r/LocalLLaMA/comments/1acfoow/mlx_mixtral_16bit_on_macbook_pro_m3_max/ | RoosterPangolin | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 1acfoow | false | null | t3_1acfoow | /r/LocalLLaMA/comments/1acfoow/mlx_mixtral_16bit_on_macbook_pro_m3_max/ | false | false | self | 2 | {'enabled': False, 'images': [{'id': '0eG2rXaxjrvo3P0DZbVgJNT44diA6Igvs0tXaT4DG-U', 'resolutions': [{'height': 54, 'url': 'https://external-preview.redd.it/NmzUABmcAJ6vJJVeFZ72_-NkfHl4m2TjTxsm6oo9reA.jpg?width=108&crop=smart&auto=webp&s=d62c64eb0c984228a2cbc84fadabf47c41c52e91', 'width': 108}, {'height': 108, 'url': 'h... |
Is a Radeon VII worth it? | 1 | I recently found some pretty cheap (260-300€) listings for used Radeon 7 cards. They have 16GB of HBM2 VRAM, giving it a memory bandwidth like a 4090. They only support ROCm until 5.7, but 5.6 seems still be most used anyway.
Has anybody experience or recommendations?
Would you get a Radeon 7 or a 7600XT?
| 2024-01-27T16:33:50 | https://www.reddit.com/r/LocalLLaMA/comments/1aceqxt/is_a_radeon_vii_worth_it/ | Kevinswelt | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 1aceqxt | false | null | t3_1aceqxt | /r/LocalLLaMA/comments/1aceqxt/is_a_radeon_vii_worth_it/ | false | false | self | 1 | null |
Consistent response formatting | 2 | Given the current state of local LLMs, how feasible is it to get one to only respond with specifically formatted commands based on context.
Ideally I’d like to train the model to be able to have it pick from a list of valid functions, pick from a valid list of parameter types for said functions, and then provide data.... | 2024-01-27T16:23:11 | https://www.reddit.com/r/LocalLLaMA/comments/1acei6b/consistent_response_formatting/ | lurklord_ | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 1acei6b | false | null | t3_1acei6b | /r/LocalLLaMA/comments/1acei6b/consistent_response_formatting/ | false | false | self | 2 | null |
Implementing a Sparse MoE Language Model from scratch | 1 | [removed] | 2024-01-27T16:15:25 | https://www.reddit.com/r/LocalLLaMA/comments/1aceboj/implementing_a_sparse_moe_language_model_from/ | avi1x | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 1aceboj | false | null | t3_1aceboj | /r/LocalLLaMA/comments/1aceboj/implementing_a_sparse_moe_language_model_from/ | false | false | self | 1 | {'enabled': False, 'images': [{'id': 'ZcwbBZrpZThONbehuqrccFwX52bFC9OJakeTcd5GCqA', 'resolutions': [{'height': 58, 'url': 'https://external-preview.redd.it/qcGOsqfjpT1nIKmQpUt4Yl8QT0xRwn6eWdL-OJYrQ94.jpg?width=108&crop=smart&auto=webp&s=7e8d8002d2e46aa4d7f857310f3ae689dfc44d07', 'width': 108}, {'height': 116, 'url': 'h... |
Embedding model inference | 1 | [removed] | 2024-01-27T16:08:04 | https://www.reddit.com/r/LocalLLaMA/comments/1ace5mt/embedding_model_inference/ | Serious_Driver_2874 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 1ace5mt | false | null | t3_1ace5mt | /r/LocalLLaMA/comments/1ace5mt/embedding_model_inference/ | false | false | self | 1 | null |
How much RAM would you need to run GPT3.5? | 2 | just curious | 2024-01-27T16:08:01 | https://www.reddit.com/r/LocalLLaMA/comments/1ace5l6/how_much_ram_would_you_need_to_run_gpt35/ | Wrong_User_Logged | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 1ace5l6 | false | null | t3_1ace5l6 | /r/LocalLLaMA/comments/1ace5l6/how_much_ram_would_you_need_to_run_gpt35/ | false | false | self | 2 | null |
Gemini Pro: The three headed monster | 1 | [https://twitter.com/lmsysorg/status/1749818447276671255](https://twitter.com/lmsysorg/status/1749818447276671255)
1. Gemini Pro: the Vertex AI API on Google Cloud
2. Gemini Pro (dev): the developer API on Google AI Studio
3. Bard (Jan 24, Gemini Pro): Bard powered by Gemini Pro (Jan 24 version)
The first two use th... | 2024-01-27T15:54:56 | https://www.reddit.com/r/LocalLLaMA/comments/1acduuf/gemini_pro_the_three_headed_monster/ | danielcar | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 1acduuf | false | null | t3_1acduuf | /r/LocalLLaMA/comments/1acduuf/gemini_pro_the_three_headed_monster/ | false | false | self | 1 | {'enabled': False, 'images': [{'id': 'SzmCRc61cd7A_UC2R-l7Js_FR4D-3nFHnRA-AwnI9f0', 'resolutions': [{'height': 108, 'url': 'https://external-preview.redd.it/oWP3QKmmsAVv7esr-FRlv-Xp2KZWc_4LnqtD0mR5E_U.jpg?width=108&crop=smart&auto=webp&s=fadd6076d8495d18e72378d2caa497f2ea166c7e', 'width': 108}], 'source': {'height': 14... |
Feels like I’m in over my head | 18 | I’ve been tasked to evaluate different commercially available LLMs for the company I work for and I figured I would start tinkering with Meta’s LLaMA 2 7b model on my own and try to utilized RAG to chat with my own documents. I spent 6 or 7 hours yesterday just trying to get it installed and feel like I’ve hit a wall. ... | 2024-01-27T15:44:26 | https://www.reddit.com/r/LocalLLaMA/comments/1acdm9u/feels_like_im_in_over_my_head/ | suivid | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 1acdm9u | false | null | t3_1acdm9u | /r/LocalLLaMA/comments/1acdm9u/feels_like_im_in_over_my_head/ | false | false | self | 18 | null |
AutoGen Studio: Interactively Explore Multi-Agent Workflows (no code AutoGen interface by Microsoft) | 36 | 2024-01-27T15:11:35 | https://microsoft.github.io/autogen/blog/2023/12/01/AutoGenStudio/ | rkm82999 | microsoft.github.io | 1970-01-01T00:00:00 | 0 | {} | 1accwbr | false | null | t3_1accwbr | /r/LocalLLaMA/comments/1accwbr/autogen_studio_interactively_explore_multiagent/ | false | false | default | 36 | null | |
Looking to run a small model for a very specific use case | 1 | I want a model that can answer questions on plant health, care and diseases is there a model for this specific use case
My laptop is rtx 4050 6gb
Any models that I can use for this specific use case
Any help is appreciated thank you | 2024-01-27T15:03:39 | https://www.reddit.com/r/LocalLLaMA/comments/1accq03/looking_to_run_a_small_model_for_a_very_specific/ | FaultSmartBut | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 1accq03 | false | null | t3_1accq03 | /r/LocalLLaMA/comments/1accq03/looking_to_run_a_small_model_for_a_very_specific/ | false | false | self | 1 | null |
Hello, Noob here. How inefficient will a transformer be if trained directly like Mambabyte? % wise? Also, in what ways will it better (or worse) than a transformer trained on tokens? | 24 | 2024-01-27T14:54:35 | MambaModel | i.redd.it | 1970-01-01T00:00:00 | 0 | {} | 1accivv | false | null | t3_1accivv | /r/LocalLLaMA/comments/1accivv/hello_noob_here_how_inefficient_will_a/ | false | false | 24 | {'enabled': True, 'images': [{'id': 'ZGcqT9FaHJm2VCC4X2t9_0Nv4_Hg3iwD3NIOtWvMm3g', 'resolutions': [{'height': 102, 'url': 'https://preview.redd.it/bf5rdodzxzec1.png?width=108&crop=smart&auto=webp&s=320f523094025da8873eec542b9903a1e4ba1f16', 'width': 108}, {'height': 205, 'url': 'https://preview.redd.it/bf5rdodzxzec1.pn... | |||
Running multi GPU with AMD and Nvidia? | 3 | I recently upgraded my PC(primarily used for gaming) from an RTX2060 6gb to an AMD RX7800xt. I haven’t yet sold my RTX2060 and was wondering if it was worth the effort to try run a dual GPU setup, and whether that would help at all with LLM inference. Has anyone tried something like this and had any luck? Is it even wo... | 2024-01-27T14:27:14 | https://www.reddit.com/r/LocalLLaMA/comments/1acbyy2/running_multi_gpu_with_amd_and_nvidia/ | ValyrianMonkey | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 1acbyy2 | false | null | t3_1acbyy2 | /r/LocalLLaMA/comments/1acbyy2/running_multi_gpu_with_amd_and_nvidia/ | false | false | self | 3 | null |
Anyone have experience of running a model on RunPod with a front end they designed? | 1 | I am trying to make the move from GPT-4 and langchain to some OS LLMs. I would like to try Goliath 120b on RunPod but I would like to create an MVP of a front end. Usually I use streamlit.
Has anybody got experience of running some from runpod to their own front end?
Thanks | 2024-01-27T13:55:06 | https://www.reddit.com/r/LocalLLaMA/comments/1acbc5p/anyone_have_experience_of_running_a_model_on/ | 99OG121314 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 1acbc5p | false | null | t3_1acbc5p | /r/LocalLLaMA/comments/1acbc5p/anyone_have_experience_of_running_a_model_on/ | false | false | self | 1 | null |
How do you know which model is suitable for our specific needs? | 7 | Today I saw this interesting comment by u/ttkciar down below.
Excluding models that there are a lot of information about them (like RP, story and coding), how do you know which model is good for a specific job?
Thank you
My use-cases and the models I use for them:
* NousResearch-Nous-Capybara-3B-V1 for RAG,
* Med... | 2024-01-27T13:51:40 | https://www.reddit.com/r/LocalLLaMA/comments/1acb9u9/how_do_you_know_which_model_is_suitable_for_our/ | Terminus_T | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 1acb9u9 | false | null | t3_1acb9u9 | /r/LocalLLaMA/comments/1acb9u9/how_do_you_know_which_model_is_suitable_for_our/ | false | false | self | 7 | null |
Looking for Advice to propose solutions to my company | 6 | I am going to pitch AI to my company. Try to get a job with the word AI in it. Long enough to learn it and by then they will realize they need a real AI person. But any of y’all put together presentations you are willing to share or know of any good resources already created? I will build a little demo box and show the... | 2024-01-27T13:19:28 | https://www.reddit.com/r/LocalLLaMA/comments/1acao8l/looking_for_advice_to_propose_solutions_to_my/ | imightbsabot | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 1acao8l | false | null | t3_1acao8l | /r/LocalLLaMA/comments/1acao8l/looking_for_advice_to_propose_solutions_to_my/ | false | false | self | 6 | null |
Best open-source Image-to-Text model? | 3 | Hi everyone,
I have a use case where I have to describe diagrams and must use a local model. I have the resources to potentially fine-tune the model, and run the largest models.
What is in your experience the best open model to do image description?
My criteria are:
\- Performance
\- Ease of use / finetuning | 2024-01-27T13:07:15 | https://www.reddit.com/r/LocalLLaMA/comments/1acagg5/best_opensource_imagetotext_model/ | Separate-Still3770 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 1acagg5 | false | null | t3_1acagg5 | /r/LocalLLaMA/comments/1acagg5/best_opensource_imagetotext_model/ | false | false | self | 3 | null |
Superboogav2 vs PrivateGPT, and similar ones? | 1 | So I want to know, is superboogav2 enough? All I know is that I have to convert all files I want to txt in superbooga,which is an extra hastle, and (also I don’t know any good offline pdf/ html to text converters) while in private GPT you just import a PDF or html or whatever, and then you can basically chat with an L... | 2024-01-27T12:28:21 | https://www.reddit.com/r/LocalLLaMA/comments/1ac9snq/superboogav2_vs_privategpt_and_similar_ones/ | headbopper96 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 1ac9snq | false | null | t3_1ac9snq | /r/LocalLLaMA/comments/1ac9snq/superboogav2_vs_privategpt_and_similar_ones/ | false | false | self | 1 | null |
Why do you trust LMSYS Arena Leaderboard? It can be easily manipulated if they want to. | 1 | The recent hype around the Bard with Gemini Pro Scale model has completely eroded my confidence in this leaderboard. The difference between Bard and Gemini Pro API is enormous, yet Bard seemingly "suddenly" surpassed GPT-4 in just a few days, despite the last update being at least a month ago. Can we really believe tha... | 2024-01-27T12:13:52 | https://www.reddit.com/r/LocalLLaMA/comments/1ac9k8f/why_do_you_trust_lmsys_arena_leaderboard_it_can/ | Mission_Implement467 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 1ac9k8f | false | null | t3_1ac9k8f | /r/LocalLLaMA/comments/1ac9k8f/why_do_you_trust_lmsys_arena_leaderboard_it_can/ | false | false | self | 1 | null |
Getting a structured response (user-defined class) from a custom fine-tuned Mistral model. | 4 | I saw examples using Langchain and OpenAI that you can set the desired output via a class. So, within a custom class, you can set the attributes that you would want the model to send back.
​
I'm curious if there is a similar way of doing this but instead of using OpenAI, I would use my own Mistral-Instruct mo... | 2024-01-27T11:46:44 | https://www.reddit.com/r/LocalLLaMA/comments/1ac94rz/getting_a_structured_response_userdefined_class/ | FlyingRaijinEX | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 1ac94rz | false | null | t3_1ac94rz | /r/LocalLLaMA/comments/1ac94rz/getting_a_structured_response_userdefined_class/ | false | false | self | 4 | null |
is better to train multilingual language models on specific language dataset or on two language dataset ? | 4 | is better to train multilingual language models like mt0 on specific language dataset or on two language dataset has the language and English ?
https://preview.redd.it/ori9mjvssyec1.png?width=4795&format=png&auto=webp&s=4658417e74f91f62fce1b3803ec553d01d8971a4 | 2024-01-27T11:04:12 | https://www.reddit.com/r/LocalLLaMA/comments/1ac8i1z/is_better_to_train_multilingual_language_models/ | mohamedem2m | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 1ac8i1z | false | null | t3_1ac8i1z | /r/LocalLLaMA/comments/1ac8i1z/is_better_to_train_multilingual_language_models/ | false | false | 4 | null | |
is better to train multilingual models on two language dataset or one dataset in specific dataset? | 1 | hi how are you , i wonder is better to fine tune models like mt0 on single language or train it on dataset has languge and English both ?
https://preview.redd.it/l5ofklpxryec1.png?width=4795&format=png&auto=webp&s=99af2089fbdbeeccafac442e2deb20b983b5dc1d | 2024-01-27T11:00:40 | https://www.reddit.com/r/LocalLLaMA/comments/1ac8g0c/is_better_to_train_multilingual_models_on_two/ | mohamedem2m | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 1ac8g0c | false | null | t3_1ac8g0c | /r/LocalLLaMA/comments/1ac8g0c/is_better_to_train_multilingual_models_on_two/ | false | false | 1 | null | |
Hello, Noob here. How inefficient will a transformer be if trained directly like Mambabyte? % wise? Also, in what ways will it better (or worse) than a transformer trained on tokens? | 1 | 2024-01-27T09:53:10 | MambaModel | i.redd.it | 1970-01-01T00:00:00 | 0 | {} | 1ac7gz8 | false | null | t3_1ac7gz8 | /r/LocalLLaMA/comments/1ac7gz8/hello_noob_here_how_inefficient_will_a/ | false | false | 1 | {'enabled': True, 'images': [{'id': 'cNm_uPIIn60ivlkkXUD80pBVedgvIx10C5OO2knFDAo', 'resolutions': [{'height': 102, 'url': 'https://preview.redd.it/hy9wyvh7gyec1.png?width=108&crop=smart&auto=webp&s=5e14983d275b0f5dd34ef691e13902d85ecd1145', 'width': 108}, {'height': 205, 'url': 'https://preview.redd.it/hy9wyvh7gyec1.pn... | |||
Local LLM with directory access? | 1 | Probably a long shot at the point in time, but is there a local LLM I can run and give access to a particular directory - specifically an obsidian vault that is filled with Markdown files.
I then want to be able to ask the LLM to summarise notes and have it infer information from other related/linked notes (hence the... | 2024-01-27T07:58:37 | https://www.reddit.com/r/LocalLLaMA/comments/1ac5t71/local_llm_with_directory_access/ | Sploffo | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 1ac5t71 | false | null | t3_1ac5t71 | /r/LocalLLaMA/comments/1ac5t71/local_llm_with_directory_access/ | false | false | self | 1 | null |
How large LLM do you think is proper for playing decent rp/erp in local? | 3 |
I don't mean to get recommended a model, just want to know the size base on other's criteria. | 2024-01-27T07:57:26 | https://www.reddit.com/r/LocalLLaMA/comments/1ac5sks/how_large_llm_do_you_think_is_proper_for_playing/ | Zealousideal_Job_682 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 1ac5sks | false | null | t3_1ac5sks | /r/LocalLLaMA/comments/1ac5sks/how_large_llm_do_you_think_is_proper_for_playing/ | false | false | self | 3 | null |
For what purpose do you use local LLMs? | 12 | A lot of discussions which model is the best, but I keep asking myself, why would average person need expensive setup to run LLM locally when you can get ChatGPT 3.5 for free and 4 for 20usd/month?
My story:
For day to day questions I use ChatGPT 4. It seems impracticall running LLM constantly or spinning it off when ... | 2024-01-27T07:25:05 | https://www.reddit.com/r/LocalLLaMA/comments/1ac5bgm/for_what_purpose_do_you_use_local_llms/ | mrscript_lt | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 1ac5bgm | false | null | t3_1ac5bgm | /r/LocalLLaMA/comments/1ac5bgm/for_what_purpose_do_you_use_local_llms/ | false | false | self | 12 | null |
What is the best GPU (and subsequent setup) for running Mixtral on Ollama? | 3 | There are about a billion posts on here about which GPUs to use and I can't figure out what is considered a budget option or not. I am trying to run Mixtral on Ollama. I'm setting up a system for multiple developers to run Langchain on directly. I have a flexible budget but I'd rather not get 4 4090s and call it a day.... | 2024-01-27T07:23:20 | https://www.reddit.com/r/LocalLLaMA/comments/1ac5aii/what_is_the_best_gpu_and_subsequent_setup_for/ | ElectricalImpact2274 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 1ac5aii | false | null | t3_1ac5aii | /r/LocalLLaMA/comments/1ac5aii/what_is_the_best_gpu_and_subsequent_setup_for/ | false | false | self | 3 | {'enabled': False, 'images': [{'id': 'krjt_5uhqcaDfYjfO7lkezThehav9cAIRJgcK-OKAmM', 'resolutions': [{'height': 56, 'url': 'https://external-preview.redd.it/s0D7i4Rco0trWh9Bu1uEkgnoJJLA3UNKUA9vs57seII.jpg?width=108&crop=smart&auto=webp&s=53486800d92d75b19d59502534fa9ba2785c14b0', 'width': 108}, {'height': 113, 'url': 'h... |
We have a Goliath with 32k context length now? | 105 | Just a few days ago I found this upload by complete accident from the huggingface search. It seems the creator stealth uploaded it without announcing it anywhere public, so basically nobody noticed: [https://huggingface.co/grimulkan/Goliath-longLORA-120b-rope8-32k-fp16](https://huggingface.co/grimulkan/Goliath-longLORA... | 2024-01-27T07:06:07 | https://www.reddit.com/r/LocalLLaMA/comments/1ac513s/we_have_a_goliath_with_32k_context_length_now/ | aikitoria | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 1ac513s | false | null | t3_1ac513s | /r/LocalLLaMA/comments/1ac513s/we_have_a_goliath_with_32k_context_length_now/ | false | false | self | 105 | {'enabled': False, 'images': [{'id': 'dHMb80RydwQMylrKi5sV8grJVIjyM3tEIekh7iU-6PM', 'resolutions': [{'height': 58, 'url': 'https://external-preview.redd.it/XHEmLPSOvRsv1ijz8Xpk6BAEECT-sJ79RtrRuTHXAus.jpg?width=108&crop=smart&auto=webp&s=e6551860e09455207cd13723f7e061b99d7dc125', 'width': 108}, {'height': 116, 'url': 'h... |
ai slide maker | 1 | [removed] | 2024-01-27T06:50:47 | https://www.reddit.com/r/LocalLLaMA/comments/1ac4sq0/ai_slide_maker/ | Silver_Equivalent_58 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 1ac4sq0 | false | null | t3_1ac4sq0 | /r/LocalLLaMA/comments/1ac4sq0/ai_slide_maker/ | false | false | self | 1 | null |
I fixed all the issues I found with llama.cpp server when using self extend and added prompt caching ability when using self extend. (This is still my old PR) | 31 | [https://github.com/ggerganov/llama.cpp/pull/5104](https://github.com/ggerganov/llama.cpp/pull/5104)
[https://www.reddit.com/r/LocalLLaMA/comments/19e47by/port\_of\_self\_extension\_to\_llamacpp\_server\_allows/](https://www.reddit.com/r/LocalLLaMA/comments/19e47by/port_of_self_extension_to_llamacpp_server_allows/) | 2024-01-27T06:44:38 | https://www.reddit.com/r/LocalLLaMA/comments/1ac4pe4/i_fixed_all_the_issues_i_found_with_llamacpp/ | FlowerPotTeaTime | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 1ac4pe4 | false | null | t3_1ac4pe4 | /r/LocalLLaMA/comments/1ac4pe4/i_fixed_all_the_issues_i_found_with_llamacpp/ | false | false | self | 31 | {'enabled': False, 'images': [{'id': 'IlRvGn-VM40kEQ_r-AMiB5VTKZ5khuEezXA9qFGxG80', 'resolutions': [{'height': 54, 'url': 'https://external-preview.redd.it/0i72tQzDvL5IrxLbCQ5Nhx1TZdHj0CxGEuNrXVlSAOM.jpg?width=108&crop=smart&auto=webp&s=53d6b3a626ad9e6b3163f3217e63970a59a12059', 'width': 108}, {'height': 108, 'url': 'h... |
Wizard-Vicuna 7b (Q2) running at 2.5 tokens/second on Galaxy S23 Ultra | 25 | Through Llama.cpp on Termux (not built to use the Adreno GPU, apparently that's possible but yields slowdowns).
It's sufficient and generally gives pretty good answers. 2.5 tokens per second is a slow reading speed, but not unbearable.
Not posting because this is new or novel at all.. but I'm more excited about this ... | 2024-01-27T06:27:07 | https://www.reddit.com/r/LocalLLaMA/comments/1ac4fph/wizardvicuna_7b_q2_running_at_25_tokenssecond_on/ | Due-Ad-7308 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 1ac4fph | false | null | t3_1ac4fph | /r/LocalLLaMA/comments/1ac4fph/wizardvicuna_7b_q2_running_at_25_tokenssecond_on/ | false | false | self | 25 | null |
llama_index troubleshooting | 1 | Hey everyone, I have an issue with my RAG setup that I can find no good answer to and was hoping someone from this awesome community could help- my retriever seems to only be returning 2 nodes despite setting k=10 or 25 or 30 etc, it's my understanding that this shouldn't be an issue of context window as the retriever ... | 2024-01-27T05:17:35 | https://www.reddit.com/r/LocalLLaMA/comments/1ac39de/llama_index_troubleshooting/ | RonBlake | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 1ac39de | false | null | t3_1ac39de | /r/LocalLLaMA/comments/1ac39de/llama_index_troubleshooting/ | false | false | self | 1 | null |
Is there a technical term for “LLM that has been trained to accurately answer questions about a narrow subject area?” | 31 | For example, say a restaurant fine-tunes an LLM to accurately answer questions about its menu items. Or a bank fine-tunes an LLM to accurately answer questions about the bank’s lending policies.
What would such an LLM be called? Or, what would this style of fine-tuning be called? (I am a near-total noob here, so pleas... | 2024-01-27T03:42:09 | https://www.reddit.com/r/LocalLLaMA/comments/1ac1i4t/is_there_a_technical_term_for_llm_that_has_been/ | LeastWest9991 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 1ac1i4t | false | null | t3_1ac1i4t | /r/LocalLLaMA/comments/1ac1i4t/is_there_a_technical_term_for_llm_that_has_been/ | false | false | self | 31 | null |
Mamba implementation in MLX! Includes inference and training. | 49 | This folder contains a complete MLX implementation of [Mamba](https://arxiv.org/abs/2312.00752), which allows to train and do inference with Mamba models using an Apple silicon equiped Mac.
Code: [https://github.com/alxndrTL/mamba.py/tree/main/mlx](https://github.com/alxndrTL/mamba.py/tree/main/mlx)
H/T: [https://tw... | 2024-01-27T03:37:51 | https://www.reddit.com/r/LocalLLaMA/comments/1ac1f5f/mamba_implementation_in_mlx_includes_inference/ | Different-Pickle1021 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 1ac1f5f | false | null | t3_1ac1f5f | /r/LocalLLaMA/comments/1ac1f5f/mamba_implementation_in_mlx_includes_inference/ | false | false | self | 49 | null |
Relationship between GPU memory and context size | 6 | Hi all,
I want to ask if anyone knows the rough relationship between GPU memory required and the size of the context for fine-tuning LLM (small model 7b, about 800samples)
Cannot find any info on this anywhere. | 2024-01-27T02:12:43 | https://www.reddit.com/r/LocalLLaMA/comments/1abzrtg/relationship_between_gpu_memory_and_context_size/ | plsendfast | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 1abzrtg | false | null | t3_1abzrtg | /r/LocalLLaMA/comments/1abzrtg/relationship_between_gpu_memory_and_context_size/ | false | false | self | 6 | null |
llama 2 models smaller than 1b? | 9 | Summary: looking for a pretrained llama 2 model with less than 1.1B parms that I can finetune
I've trained a model from scratch with about 70m parameters. Kind of works, but there's serious limits when running a microscopic model. Training even this miniscule size from scratch still requires multiple weeks of GPU time... | 2024-01-27T01:58:32 | https://www.reddit.com/r/LocalLLaMA/comments/1abzhg5/llama_2_models_smaller_than_1b/ | dual_ears | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 1abzhg5 | false | null | t3_1abzhg5 | /r/LocalLLaMA/comments/1abzhg5/llama_2_models_smaller_than_1b/ | false | false | self | 9 | null |
Functions for more modular prompting | 24 | Full Disclosure: **I am NOT technical**, I spent quite a bit of time playing around with Copilot to develop these functions - VERY OPEN TO SUGGESTIONS
**Use Case:**
1. You are NOT using a UI, instead you are using an engine directly, like vLLM
2. You are cycling through lots of different prompts and few-shot examp... | 2024-01-27T01:47:27 | https://www.reddit.com/r/LocalLLaMA/comments/1abz9f5/functions_for_more_modular_prompting/ | GeeBrain | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 1abz9f5 | false | null | t3_1abz9f5 | /r/LocalLLaMA/comments/1abz9f5/functions_for_more_modular_prompting/ | false | false | self | 24 | null |
Local Autonomous Coding? | 5 | On a Pixel 8 Pro, using Termux to emulate a linux environment in which Koboldcpp (llama.cpp fork) is running the StableCode-3B-alpha-instruct-8bit.ggml model in the bottom half of the screen,
and PyDroid3, a python IDE port for android, is running in the top.
the calculator it made this time doesn't actually work, li... | 2024-01-27T01:25:51 | https://www.reddit.com/gallery/1abytol | Sl33py_4est | reddit.com | 1970-01-01T00:00:00 | 0 | {} | 1abytol | false | null | t3_1abytol | /r/LocalLLaMA/comments/1abytol/local_autonomous_coding/ | false | false | 5 | null | |
Meta tried to send GitHub a DMCA takedown when a user uploaded the weights associated with LLaMA | 4 | 2024-01-27T00:43:26 | https://x.com/franklingraves/status/1751011369011290231?s=20 | ninjasaid13 | x.com | 1970-01-01T00:00:00 | 0 | {} | 1abxxi8 | false | null | t3_1abxxi8 | /r/LocalLLaMA/comments/1abxxi8/meta_tried_to_send_github_a_dmca_takedown_when_a/ | false | false | 4 | {'enabled': False, 'images': [{'id': 'c1VBUV2JREaPqkBo0MLgPFBV1_0TxzRkMRpDCZV0bx8', 'resolutions': [{'height': 66, 'url': 'https://external-preview.redd.it/4j-dB7neJUXpGeWtmtCYiMqvg-XQBBQbFCdDV2uTev0.jpg?width=108&crop=smart&auto=webp&s=7b1cb166ecfde93d33e5e9176615b0fa9562d4a9', 'width': 108}, {'height': 132, 'url': 'h... | ||
JSON parsing as the benchmark for a LLM | 2 | I needed to parse the data out of a relatively small json log (couple thousand tokens). I could have just prettify the json and locate what I needed manually, but what fun in that -- I decided to feed it to the LLMs instead.
**Mixtral 8x7b:**
Was trying to answer what I asked - the answer was for the correct pro... | 2024-01-27T00:35:38 | https://www.reddit.com/r/LocalLLaMA/comments/1abxrja/json_parsing_as_the_benchmark_for_a_llm/ | Infinite100p | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 1abxrja | false | null | t3_1abxrja | /r/LocalLLaMA/comments/1abxrja/json_parsing_as_the_benchmark_for_a_llm/ | false | false | 2 | null | |
What is the best 7b gguf model for coding complex or simple things? | 1 | [removed] | 2024-01-26T23:19:37 | https://www.reddit.com/r/LocalLLaMA/comments/1abw2w3/what_is_the_best_7b_gguf_model_for_coding_complex/ | Gaming-invisibleman | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 1abw2w3 | false | null | t3_1abw2w3 | /r/LocalLLaMA/comments/1abw2w3/what_is_the_best_7b_gguf_model_for_coding_complex/ | false | false | self | 1 | null |
Looking for a SFW model 13b | 10 | Guys, I need help. I'm trying to find a censored SFW model for roleplay. The problem is that most of good models are NSFW. I am making a project for an exhibition, but the audience, communicating with the neural network, sometimes leads it to unwanted conversations...
I've tried to describe the limitations in the cha... | 2024-01-26T23:18:54 | https://www.reddit.com/r/LocalLLaMA/comments/1abw2at/looking_for_a_sfw_model_13b/ | Soul_Tuner | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 1abw2at | false | null | t3_1abw2at | /r/LocalLLaMA/comments/1abw2at/looking_for_a_sfw_model_13b/ | false | false | self | 10 | null |
LLama 2 locally | 1 | [removed] | 2024-01-26T21:55:49 | https://www.reddit.com/r/LocalLLaMA/comments/1abu3ul/llama_2_locally/ | aiaddict00978 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 1abu3ul | false | null | t3_1abu3ul | /r/LocalLLaMA/comments/1abu3ul/llama_2_locally/ | false | false | self | 1 | null |
Best open source model for 24 Gb VRAM | 96 | I have NVIDIA 3090 with 24Gb GPU. I wanted to ask which is the best open source LLM which I can run on my PC?
- Is it better to run a Q3 quantized mistral 8X7B model (20Gb) or is it better to use mistral-7B model(16gb)
- which is the best fine tuning training data: Orca, Dolphin2.7, Hermes, or something else?
TIA | 2024-01-26T21:49:20 | https://www.reddit.com/r/LocalLLaMA/comments/1abtya7/best_open_source_model_for_24_gb_vram/ | AI_ML_preneur | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 1abtya7 | false | null | t3_1abtya7 | /r/LocalLLaMA/comments/1abtya7/best_open_source_model_for_24_gb_vram/ | false | false | self | 96 | null |
Run AI chatbot efficiently on older hardware | 1 | I use ChatGPT quite a lot for my homelab needs and was wondering if there is a way to achieve a semi-usable (so not terribly slow) way to achieve this with a local AI installation. All my hardware is a bit dated, I had no use to upgrade as it fulfills my needs perfectly (i5-8500 Server 24Gb Ram, Celeron J4125 MiniPc... | 2024-01-26T21:12:04 | https://www.reddit.com/r/LocalLLaMA/comments/1abt2xf/run_ai_chatbot_efficiently_on_older_hardware/ | StarShoot97 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 1abt2xf | false | null | t3_1abt2xf | /r/LocalLLaMA/comments/1abt2xf/run_ai_chatbot_efficiently_on_older_hardware/ | false | false | self | 1 | null |
Fine Tuning a Tolkien Model: Style Seems to Have Transferred, But Writing Instruction Hasn't | 9 | **Summary**: I'm trying to fine tune a Mistral model to write in Tolkiens' style, however while the model seems to have picked up some of Tolkien's style (it will continue narrative), if prompted ("Write a story...) as in the training data, it instead writes a detailed prompt.
I only have about 300 training observatio... | 2024-01-26T21:10:07 | https://www.reddit.com/r/LocalLLaMA/comments/1abt15y/fine_tuning_a_tolkien_model_style_seems_to_have/ | Mbando | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 1abt15y | false | null | t3_1abt15y | /r/LocalLLaMA/comments/1abt15y/fine_tuning_a_tolkien_model_style_seems_to_have/ | false | false | self | 9 | null |
llama.cpp running on the Nintendo Switch (TinyLlama q5_K_M) | 260 | 2024-01-26T20:31:53 | https://v.redd.it/ibywc774huec1 | kindacognizant | v.redd.it | 1970-01-01T00:00:00 | 0 | {} | 1abs4ht | false | {'reddit_video': {'bitrate_kbps': 2400, 'dash_url': 'https://v.redd.it/ibywc774huec1/DASHPlaylist.mpd?a=1708893126%2CODE5ODBjMDhlOTU3YTkyMWU1YzI3OTBmNWZhNjljMWVjNzAwM2EzMjVmYjgyMmNjMDg5YzViMjdiMWQyZTQwNg%3D%3D&v=1&f=sd', 'duration': 24, 'fallback_url': 'https://v.redd.it/ibywc774huec1/DASH_720.mp4?source=fallback', 'ha... | t3_1abs4ht | /r/LocalLLaMA/comments/1abs4ht/llamacpp_running_on_the_nintendo_switch_tinyllama/ | false | false | 260 | {'enabled': False, 'images': [{'id': 'and0bzRvMTlodWVjMbTjpk_JPE3dphNc3rtP3pLWvGp4Fd0Mq7BgZ41W1Eh5', 'resolutions': [{'height': 60, 'url': 'https://external-preview.redd.it/and0bzRvMTlodWVjMbTjpk_JPE3dphNc3rtP3pLWvGp4Fd0Mq7BgZ41W1Eh5.png?width=108&crop=smart&format=pjpg&auto=webp&s=d88dedcaa62a0adbcd50498366764b1b736e5... | ||
do you think they'll make a gpu poor version of mixtral-moe? | 3 | I keep hearing how good mixtral moe is, but I unfortunately am stuck with 16gbs of ram and can only run stuff on ram not gpu, do you think they'll ever refine it to work on smaller machines...T\_T I can't afford to upgrade. | 2024-01-26T19:47:08 | https://www.reddit.com/r/LocalLLaMA/comments/1abr2jw/do_you_think_theyll_make_a_gpu_poor_version_of/ | New-Employer9303 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 1abr2jw | false | null | t3_1abr2jw | /r/LocalLLaMA/comments/1abr2jw/do_you_think_theyll_make_a_gpu_poor_version_of/ | false | false | self | 3 | null |
Chatbot Arena Leaderboard updated, latest Bard model surpasses GPT-4 to second place | 147 | 2024-01-26T19:43:46 | https://huggingface.co/spaces/lmsys/chatbot-arena-leaderboard | JealousAmoeba | huggingface.co | 1970-01-01T00:00:00 | 0 | {} | 1abqzsj | false | null | t3_1abqzsj | /r/LocalLLaMA/comments/1abqzsj/chatbot_arena_leaderboard_updated_latest_bard/ | false | false | 147 | {'enabled': False, 'images': [{'id': 'tu38AwtsUEqyGIPo-RS3iFtvVhQ6LPaW-v5gU23jMqc', 'resolutions': [{'height': 58, 'url': 'https://external-preview.redd.it/RS7d3722KVL1OTw1ewhRT89FTFf93HJZCAdVoAQjeCw.jpg?width=108&crop=smart&auto=webp&s=724cf25bfd7e21d9fe860dd0f67a01017ab321c6', 'width': 108}, {'height': 116, 'url': 'h... | ||
NOOB: Looking for advice on model size | 1 | So I am just starting to get into running a local LLM. I'm updating my computer anyway so I figured I would spec out something that could let me explore this fully. I'm thinking about getting an NVIDA 3090, 128GB of RAM and an I9.
Looking at the different opensource models I see that they range from 7 to 70 billion p... | 2024-01-26T19:10:51 | https://www.reddit.com/r/LocalLLaMA/comments/1abq7r5/noob_looking_for_advice_on_model_size/ | snowbirdnerd | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 1abq7r5 | false | null | t3_1abq7r5 | /r/LocalLLaMA/comments/1abq7r5/noob_looking_for_advice_on_model_size/ | false | false | self | 1 | null |
Which 7B model is the best for story writing right now? | 4 | As I want to start generating ideas, I also want a good model that does a great job | 2024-01-26T19:04:43 | https://www.reddit.com/r/LocalLLaMA/comments/1abq2nk/which_7b_model_is_the_best_for_story_writing/ | headbopper96 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 1abq2nk | false | null | t3_1abq2nk | /r/LocalLLaMA/comments/1abq2nk/which_7b_model_is_the_best_for_story_writing/ | false | false | self | 4 | null |
Can I use Llama with prompflow? | 1 | Does anyone have experience with promptflow, can I use it with my llama2 model or does it only work online? | 2024-01-26T19:02:22 | https://www.reddit.com/r/LocalLLaMA/comments/1abq0q8/can_i_use_llama_with_prompflow/ | Electronic-Letter592 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 1abq0q8 | false | null | t3_1abq0q8 | /r/LocalLLaMA/comments/1abq0q8/can_i_use_llama_with_prompflow/ | false | false | self | 1 | null |
Is it possible to run Mixtral with 32k of context on a single 3090? | 6 | I have a 3090 and 64gb ram, I use mixtral (Q5-GGUF) with +/- 8k context as my main model, but I would like to use the 32k. I know I can use the 3.0bpw exl2 model with full context, but the model loses too much quality to be useful, so I was wondering if anyone has managed to run Q5 with full context on a single 3090, b... | 2024-01-26T18:59:52 | https://www.reddit.com/r/LocalLLaMA/comments/1abpycc/is_it_possible_to_run_mixtral_with_32k_of_context/ | N9_m | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 1abpycc | false | null | t3_1abpycc | /r/LocalLLaMA/comments/1abpycc/is_it_possible_to_run_mixtral_with_32k_of_context/ | false | false | self | 6 | null |
100% Local Speech to Speech with Vision | Faster Whisper + OpenVoice + Moondream | 1 | 2024-01-26T17:56:25 | https://v.redd.it/5ilqdlucptec1 | allaboutai-kris | v.redd.it | 1970-01-01T00:00:00 | 0 | {} | 1abogll | false | {'reddit_video': {'bitrate_kbps': 5000, 'dash_url': 'https://v.redd.it/5ilqdlucptec1/DASHPlaylist.mpd?a=1708883799%2CMDlmNDIzOWRmM2MyY2Y2ZTUzZTg3MTI1MjczOTM5M2I4ZGVjODEwZGU4NTc4MGNmZjRlNWRmZjQ0Y2E0ODAwMA%3D%3D&v=1&f=sd', 'duration': 39, 'fallback_url': 'https://v.redd.it/5ilqdlucptec1/DASH_1080.mp4?source=fallback', 'h... | t3_1abogll | /r/LocalLLaMA/comments/1abogll/100_local_speech_to_speech_with_vision_faster/ | false | false | 1 | {'enabled': False, 'images': [{'id': 'M3BqNmRlaGlwdGVjMS4IvXAby_CtrEbRo7C7uRuA2vUq16Enq3_IzQoUv9Lv', 'resolutions': [{'height': 60, 'url': 'https://external-preview.redd.it/M3BqNmRlaGlwdGVjMS4IvXAby_CtrEbRo7C7uRuA2vUq16Enq3_IzQoUv9Lv.png?width=108&crop=smart&format=pjpg&auto=webp&s=ff0cf41f574f658a3aa8b99e72a84b77b3e50... | ||
100% Local Speech to Speech with Vision | Faster Whisper + OpenVoice + Moondream | 1 | 2024-01-26T17:51:32 | https://v.redd.it/s5axcwolotec1 | allaboutai-kris | v.redd.it | 1970-01-01T00:00:00 | 0 | {} | 1abocfq | false | {'reddit_video': {'bitrate_kbps': 5000, 'dash_url': 'https://v.redd.it/s5axcwolotec1/DASHPlaylist.mpd?a=1708883508%2CYTk3NGY4ZWU5MmJlMDE3YTdmOTJmZmU3N2M3MDViMmZjMzAyZDNjMDBkN2RmNzQ2MjhjZjYyMWNmNjBkM2I4NA%3D%3D&v=1&f=sd', 'duration': 39, 'fallback_url': 'https://v.redd.it/s5axcwolotec1/DASH_1080.mp4?source=fallback', 'h... | t3_1abocfq | /r/LocalLLaMA/comments/1abocfq/100_local_speech_to_speech_with_vision_faster/ | false | false | 1 | {'enabled': False, 'images': [{'id': 'eWEwNnk3Nm5vdGVjMTAY-XieycHhKNo0Ybz9uVsdh6ZZT-o9F5T2XrZXcH30', 'resolutions': [{'height': 60, 'url': 'https://external-preview.redd.it/eWEwNnk3Nm5vdGVjMTAY-XieycHhKNo0Ybz9uVsdh6ZZT-o9F5T2XrZXcH30.png?width=108&crop=smart&format=pjpg&auto=webp&s=bddbb6f169a10441cb8c5aa796756f227e053... |
Subsets and Splits
No community queries yet
The top public SQL queries from the community will appear here once available.