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 ⌀ |
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
Mixtral finetunes trickling in | 1 | I just saw Dolphin 2.5 was released, and it’s based on Mixtral 8x7b. Dolphin 2.2 based on Yi is my favorite model. Can’t wait to try 2.5!
The bloke has Mixtral-SlimOrca quantized. Text-gen mixtral support merged to main. It’s happening! | 2023-12-14T05:21:51 | https://www.reddit.com/r/LocalLLaMA/comments/18i1b5d/mixtral_finetunes_trickling_in/ | deep_archivist | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 18i1b5d | false | null | t3_18i1b5d | /r/LocalLLaMA/comments/18i1b5d/mixtral_finetunes_trickling_in/ | false | false | self | 1 | null |
What are you using your local LLMs for? | 1 | [removed] | 2023-12-14T05:10:17 | https://www.reddit.com/r/LocalLLaMA/comments/18i141i/what_are_you_using_your_local_llms_for/ | Extension-Mastodon67 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 18i141i | false | null | t3_18i141i | /r/LocalLLaMA/comments/18i141i/what_are_you_using_your_local_llms_for/ | false | false | self | 1 | null |
How important is fine-tuning as foundational models get better? | 3 | What do you guys think, if models get to GPT4 level and open-source, will they benefit from fine-tuning? | 2023-12-14T05:08:26 | https://www.reddit.com/r/LocalLLaMA/comments/18i12zo/how_important_is_finetuning_as_foundational/ | EcstaticVenom | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 18i12zo | false | null | t3_18i12zo | /r/LocalLLaMA/comments/18i12zo/how_important_is_finetuning_as_foundational/ | false | false | self | 3 | null |
Trinity-7B - Scored 74.07 on GSM8k by merge! | 3 | We try to merge the two top 7B model to see if anything interesting happening and got a 74.07 on GSM8k (ran the test on our computer since HF leaderboard is slow lately)
https://preview.redd.it/kmh3sfri076c1.png?width=816&format=png&auto=webp&s=002bea2908bad37cf79991087636acbcc03c3161
Given that the 2 top models i... | 2023-12-14T05:07:59 | https://www.reddit.com/r/LocalLLaMA/comments/18i12pv/trinity7b_scored_7407_on_gsm8k_by_merge/ | noobgolang | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 18i12pv | false | null | t3_18i12pv | /r/LocalLLaMA/comments/18i12pv/trinity7b_scored_7407_on_gsm8k_by_merge/ | false | false | 3 | {'enabled': False, 'images': [{'id': 'upj97tCeXeEhTD0CwKPN12_E-7k1_HlTmrgjqnPYJr0', 'resolutions': [{'height': 58, 'url': 'https://external-preview.redd.it/3XICrT1JZdAX5ISYnm_kOR7JLhB6NzbJu82R_sTh7ho.jpg?width=108&crop=smart&auto=webp&s=fb031f1b44fba24916be12167c163a9b465f376f', 'width': 108}, {'height': 116, 'url': 'h... | |
The first query taking longer to generate than the consequent ones. | 2 | So I built a RAG system and I have been testing it for a while now. For the first query it retrieves a couple of chunks as context and stores them in a template. When asked a second query, it doesn't retrieve any docs but just appends the Q to the earlier prompt like this,
Context + 1stQuery + 1stGeneratedAns + 2ndQue... | 2023-12-14T04:10:12 | https://www.reddit.com/r/LocalLLaMA/comments/18i02il/the_first_query_taking_longer_to_generate_than/ | IamFuckinTomato | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 18i02il | false | null | t3_18i02il | /r/LocalLLaMA/comments/18i02il/the_first_query_taking_longer_to_generate_than/ | false | false | self | 2 | null |
Sharing a simple local LLM setup | 20 | I know all the information is out there, but to save people some time, I'll share what worked for me to create a simple LLM setup. I've done this on Mac, but should work for other OS.
​
I only need to install two things:
**Backend**: [llama.cpp](https://github.com/ggerganov/llama.cpp)
**UI**: [Chatbox](https... | 2023-12-14T03:57:56 | https://www.reddit.com/r/LocalLLaMA/comments/18hzun0/sharing_a_simple_local_llm_setup/ | bigbossStrife | self.LocalLLaMA | 2023-12-14T04:02:38 | 0 | {} | 18hzun0 | false | null | t3_18hzun0 | /r/LocalLLaMA/comments/18hzun0/sharing_a_simple_local_llm_setup/ | false | false | self | 20 | {'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... |
Windows AI Studio Preview Now Available | 13 | Windows AI Studio allows people to download models, fine-tune them, and play with them using VS Code. I'm downloading now to play with. :)
More info: [Windows AI Studio | Microsoft Learn](https://learn.microsoft.com/en-us/windows/ai/studio/) | 2023-12-14T03:39:48 | https://www.reddit.com/r/LocalLLaMA/comments/18hziyg/windows_ai_studio_preview_now_available/ | cddelgado | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 18hziyg | false | null | t3_18hziyg | /r/LocalLLaMA/comments/18hziyg/windows_ai_studio_preview_now_available/ | false | false | self | 13 | {'enabled': False, 'images': [{'id': 'RCFh0Kid3SAqWEkALMGNW1e9Vu6ayZpftekoayP00hY', 'resolutions': [{'height': 56, 'url': 'https://external-preview.redd.it/CcTKId6ti1J-bMqj-jlWVD1tyE1LbM9FagmfDfaIVmQ.jpg?width=108&crop=smart&auto=webp&s=b3881e36da92b82c6947f6ca4ff3804ca47f2aea', 'width': 108}, {'height': 113, 'url': 'h... |
Gemini Pro API frontend | 11 | I have noticed that when using the Gemini Pro API, the results are mostly uncensored (requires minimal prompting to generate NSFW, with quality comparable to GPT 3.5 turbo, and very large context sizes.)
Here's something I'm working on for those who aren't savvy enough to interface with the API programmatically. all y... | 2023-12-14T03:23:02 | https://www.reddit.com/r/LocalLLaMA/comments/18hz7n3/gemini_pro_api_frontend/ | faetalize | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 18hz7n3 | false | null | t3_18hz7n3 | /r/LocalLLaMA/comments/18hz7n3/gemini_pro_api_frontend/ | false | false | 11 | null | |
Which models are you using in production? | 2 | I've lost track of all the models that have been released so far.
I was using OpenAI API for the longest time, and only recently - - primarily driven by the OpenAI announcement that they'll be retiring the Da-Vinci-003 model - - have started breaking down my workflows into more steps, and replacing OpenAI calls with... | 2023-12-14T03:18:11 | https://www.reddit.com/r/LocalLLaMA/comments/18hz4dg/which_models_are_you_using_in_production/ | noellarkin | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 18hz4dg | false | null | t3_18hz4dg | /r/LocalLLaMA/comments/18hz4dg/which_models_are_you_using_in_production/ | false | false | self | 2 | null |
Quick, practical setup for the average joe? | 6 | I just want to get in, install something I can use for writing, and get out without having to learn all the details of how an llm works, quantization, model sizes, the differences between models, and so on. I’m sorry to ask a question which surely gets asked all the time, but where can I find a practical guide for pure... | 2023-12-14T03:14:42 | https://www.reddit.com/r/LocalLLaMA/comments/18hz20j/quick_practical_setup_for_the_average_joe/ | throwinupupandaway | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 18hz20j | false | null | t3_18hz20j | /r/LocalLLaMA/comments/18hz20j/quick_practical_setup_for_the_average_joe/ | false | false | self | 6 | null |
Gemini Pro API Frontend | 1 | [removed] | 2023-12-14T03:08:20 | https://www.reddit.com/r/LocalLLaMA/comments/18hyxqb/gemini_pro_api_frontend/ | faetalise | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 18hyxqb | false | null | t3_18hyxqb | /r/LocalLLaMA/comments/18hyxqb/gemini_pro_api_frontend/ | false | false | 1 | {'enabled': False, 'images': [{'id': 'SvU8TaisioKfcqHKp97d762R4BS91TwKGjSav5scjLM', 'resolutions': [{'height': 54, 'url': 'https://external-preview.redd.it/npgL8H1035Uc0hezRopSgrfNa1qIXIEXz9Ztregwgc8.jpg?width=108&crop=smart&auto=webp&s=dacfc8c27602c6796befcaa82144565d644584ff', 'width': 108}, {'height': 108, 'url': 'h... | |
First attempt with Mixtral 8x7B Instruct v0.1 Q8 GGUF in LM Studio | 1 | 2023-12-14T03:03:56 | bardobirdo | i.redd.it | 1970-01-01T00:00:00 | 0 | {} | 18hyutl | false | null | t3_18hyutl | /r/LocalLLaMA/comments/18hyutl/first_attempt_with_mixtral_8x7b_instruct_v01_q8/ | false | false | 1 | {'enabled': True, 'images': [{'id': 'FLpwPKoK7_AVEXRqUAUHXa17qZ_8Di4qeSz_k24-IPQ', 'resolutions': [{'height': 72, 'url': 'https://preview.redd.it/e8d0q2vze66c1.png?width=108&crop=smart&auto=webp&s=02201ee1df0164cd056339ef071fb51e8c1b79bd', 'width': 108}, {'height': 145, 'url': 'https://preview.redd.it/e8d0q2vze66c1.png... | |||
Distributed Inference and Fine-tuning of Large Language Models Over The Internet | 16 | 2023-12-14T02:49:12 | https://arxiv.org/abs/2312.08361 | ninjasaid13 | arxiv.org | 1970-01-01T00:00:00 | 0 | {} | 18hykct | false | null | t3_18hykct | /r/LocalLLaMA/comments/18hykct/distributed_inference_and_finetuning_of_large/ | false | false | 16 | {'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... | ||
WebLLM but on CPU? | 4 | I posted a month ago about what would be the best LLM to run locally in the web, got great answers, most of them recommending [https://webllm.mlc.ai/](https://webllm.mlc.ai/), but you need an experimental version of Chrome for this + a computer with a gpu.
I don't really want to wait for this to happen :) Is there an... | 2023-12-14T02:42:48 | https://www.reddit.com/r/LocalLLaMA/comments/18hyfvq/webllm_but_on_cpu/ | palpapeen | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 18hyfvq | false | null | t3_18hyfvq | /r/LocalLLaMA/comments/18hyfvq/webllm_but_on_cpu/ | false | false | self | 4 | null |
SwitchHead: Accelerating Transformers with Mixture-of-Experts Attention | 13 | 2023-12-14T02:38:54 | https://arxiv.org/abs/2312.07987 | ninjasaid13 | arxiv.org | 1970-01-01T00:00:00 | 0 | {} | 18hyd52 | false | null | t3_18hyd52 | /r/LocalLLaMA/comments/18hyd52/switchhead_accelerating_transformers_with/ | false | false | 13 | {'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... | ||
Llama.cpp quantization tool | 2 | Disclaimer: I don’t know what I’m doing and I’m kind of shocked I haven’t yet blown up my laptop.
Yesterday, I was having trouble getting Nous Capybara to work for me. So I created a new GGUF from the source files on Hugging Face using convert.py. F16. I can now get the model to run.
I’d like to use the quantization... | 2023-12-14T02:36:37 | https://www.reddit.com/r/LocalLLaMA/comments/18hybkr/llamacpp_quantization_tool/ | Hinged31 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 18hybkr | false | null | t3_18hybkr | /r/LocalLLaMA/comments/18hybkr/llamacpp_quantization_tool/ | false | false | self | 2 | null |
fed up with ChatGPT: time to fully switch; some questions | 11 | Hi there folks,
I've been using local models for a while, and it works wonderfully. However, this recent debacle with chat gpt getting worse and worse has lead me to decide to go out and buy myself some more RAM.
Now my computer is going to have 64 gb of RAM, which is, I think enough to run most powerful models?
Wel... | 2023-12-14T02:21:36 | https://www.reddit.com/r/LocalLLaMA/comments/18hy10a/fed_up_with_chatgpt_time_to_fully_switch_some/ | Several_Extreme3886 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 18hy10a | false | null | t3_18hy10a | /r/LocalLLaMA/comments/18hy10a/fed_up_with_chatgpt_time_to_fully_switch_some/ | false | false | self | 11 | null |
Mozilla is talking about Llamafile live tomorrow (Thursday) | 1 | [removed] | 2023-12-14T02:16:24 | https://www.reddit.com/r/LocalLLaMA/comments/18hxxcn/mozilla_is_talking_about_llamafile_live_tomorrow/ | joodfish | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 18hxxcn | false | null | t3_18hxxcn | /r/LocalLLaMA/comments/18hxxcn/mozilla_is_talking_about_llamafile_live_tomorrow/ | false | false | self | 1 | null |
Finetune Mistral 220% faster with 62% memory savings | 272 | Hi r/LocalLLaMA!
We finally added Mistral 7b support, CodeLlama 34b, and added prelim DPO support (thanks to [152334H](https://github.com/152334H)), Windows WSL support (thanks to [RandomInternetPreson](https://github.com/RandomInternetPreson))
https://preview.redd.it/06cthih5266c1.png?width=982&format=png&auto=webp&... | 2023-12-14T01:57:31 | https://www.reddit.com/r/LocalLLaMA/comments/18hxk6x/finetune_mistral_220_faster_with_62_memory_savings/ | danielhanchen | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 18hxk6x | false | null | t3_18hxk6x | /r/LocalLLaMA/comments/18hxk6x/finetune_mistral_220_faster_with_62_memory_savings/ | false | false | 272 | {'enabled': False, 'images': [{'id': 'eGGIcNY-lsdFuWsI0aShQ_sTfSlA-J15x8p3ST4JL3k', 'resolutions': [{'height': 108, 'url': 'https://external-preview.redd.it/ODWtkQf_Paebnb6MbJgfBHKAmM1IY2t89HtNmpy4XB4.jpg?width=108&crop=smart&auto=webp&s=5119e409955c58baaa7720f19d6f6d8331fb7075', 'width': 108}, {'height': 216, 'url': '... | |
Mixtral, A.K.A. David, vs Goliath (120b) | 35 | TL;DR, running Mixtral 8x7b locally feels like discovering ChatGPT all over again from back when it first came out and only offered GPT3.5. Running Goliath 120b, even in 2bit, is like it's actually crossed that bridge into making your silicon truly intelligent even though it's limited vs GPT-4. And then,
If: Llama 70b... | 2023-12-14T01:24:30 | https://www.reddit.com/r/LocalLLaMA/comments/18hwwrh/mixtral_aka_david_vs_goliath_120b/ | OldAd9530 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 18hwwrh | false | null | t3_18hwwrh | /r/LocalLLaMA/comments/18hwwrh/mixtral_aka_david_vs_goliath_120b/ | false | false | self | 35 | null |
Model Roundup | 2 | Super interesting week! Lots of new, interesting, small models. I'm trying to make sense of it all, here's what I gather so far:
Mixtral: based. New king of open source. Personally, I want to see more companies like Mistral AI. No notes, except that I wish my potato laptop could run it locally. That's a me problem th... | 2023-12-14T00:59:37 | https://www.reddit.com/r/LocalLLaMA/comments/18hwecc/model_roundup/ | Future_Might_8194 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 18hwecc | false | null | t3_18hwecc | /r/LocalLLaMA/comments/18hwecc/model_roundup/ | false | false | self | 2 | null |
Is Phi-2 Just Mocking Me At This Point? (Could Get This To Work With Phi-1.5) | 1 | [removed] | 2023-12-14T00:12:38 | https://www.reddit.com/r/LocalLLaMA/comments/18hvfnx/is_phi2_just_mocking_me_at_this_point_could_get/ | Fantastic-Ninja3839 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 18hvfnx | false | null | t3_18hvfnx | /r/LocalLLaMA/comments/18hvfnx/is_phi2_just_mocking_me_at_this_point_could_get/ | false | false | self | 1 | null |
Anyone having problems with Phind CodeLlama V2 gguf with LM Studio? | 1 | It was working ok a few days ago. Now all I get is "an error occurred". | 2023-12-13T23:58:11 | https://www.reddit.com/r/LocalLLaMA/comments/18hv45o/anyone_having_problems_with_phind_codellama_v2/ | 808phone | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 18hv45o | false | null | t3_18hv45o | /r/LocalLLaMA/comments/18hv45o/anyone_having_problems_with_phind_codellama_v2/ | false | false | self | 1 | null |
any image to video (short moving images) models which i can run on local m3 max , pl recommend | 1 | trying to bring some old memories/pictures back to life
and also want to stress test my m3 max silicon
Steps to train/infer will help as its my first time running any model on the local laptop | 2023-12-13T23:04:34 | https://www.reddit.com/r/LocalLLaMA/comments/18htxs1/any_image_to_video_short_moving_images_models/ | HiddenBladeXD | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 18htxs1 | false | null | t3_18htxs1 | /r/LocalLLaMA/comments/18htxs1/any_image_to_video_short_moving_images_models/ | false | false | self | 1 | null |
Is there (already) a multi user web UI available? | 3 | I am currently in the progress of finetuning a CodeLLama model (specifically for Laravel devs) and I would like to give people the ability to try it/use it when they don't have the hardware available for it themselves. We have plenty of options for an UI like Oobabooga, llama.cpp or KoboldCPP, however, none of these ha... | 2023-12-13T23:01:37 | https://www.reddit.com/r/LocalLLaMA/comments/18htvc5/is_there_already_a_multi_user_web_ui_available/ | Taronyuuu | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 18htvc5 | false | null | t3_18htvc5 | /r/LocalLLaMA/comments/18htvc5/is_there_already_a_multi_user_web_ui_available/ | false | false | self | 3 | null |
Argument with an AI (Cats and humans interbreeding) | 3 | So I decided to dip my toe into using a local text generation model. Really interested in an AI assistant and code writer but thought to ease myself into it using oobabooga. I struggled for a bit getting it to install but eventually loaded TheBloke/Pygmalion-13B-SuperHOT-8K-GPTQ model from hugging face and fired up t... | 2023-12-13T22:57:18 | https://www.reddit.com/r/LocalLLaMA/comments/18htrjg/argument_with_an_ai_cats_and_humans_interbreeding/ | punter1965 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 18htrjg | false | null | t3_18htrjg | /r/LocalLLaMA/comments/18htrjg/argument_with_an_ai_cats_and_humans_interbreeding/ | false | false | self | 3 | null |
Help running inference on a large dataset | 2 | Hi! I’m a college student and am somewhat new to Llama. I followed some tutorials and downloaded the model and weights on our supercomputer. I want to use llama to give bias to a large question and answer pair dataset. I’m using the weights of 2-7b-chat huggingface. I want the questions to be returned unchanged and the... | 2023-12-13T22:57:01 | https://www.reddit.com/r/LocalLLaMA/comments/18htrb2/help_running_inference_on_a_large_dataset/ | Electronic-Reply5109 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 18htrb2 | false | null | t3_18htrb2 | /r/LocalLLaMA/comments/18htrb2/help_running_inference_on_a_large_dataset/ | false | false | self | 2 | null |
Microsoft released Phi-2 on Huggingface | 3 | 2023-12-13T22:48:00 | https://huggingface.co/microsoft/phi-2 | montcarl | huggingface.co | 1970-01-01T00:00:00 | 0 | {} | 18htjyy | false | null | t3_18htjyy | /r/LocalLLaMA/comments/18htjyy/microsoft_released_phi2_on_huggingface/ | false | false | 3 | {'enabled': False, 'images': [{'id': 'IC9jEjr4wqjQ7Zp6pkl3zp0k6W16A-udtoplxE4MnyY', 'resolutions': [{'height': 58, 'url': 'https://external-preview.redd.it/Bou0VApCNu-gpJZ801OxRYO9_HcS0Q7xXm8ez7FBuBI.jpg?width=108&crop=smart&auto=webp&s=0e88db6a0c39318ffd52cbcc7a8c5ebd7f2446f4', 'width': 108}, {'height': 116, 'url': 'h... | ||
Mixtral / MoE might be insanely compressable - sub-1bit | 66 | I stumbled over this issue when looking at mixtral PR: https://github.com/ggerganov/llama.cpp/issues/4445
Basically, because of the MoE structure it's generally much more compressable and can see 20x reduction, or under 1 bit per parameter - without hurting perplexity much.
There are some example code mentioned, and ... | 2023-12-13T22:39:04 | https://www.reddit.com/r/LocalLLaMA/comments/18htcfb/mixtral_moe_might_be_insanely_compressable_sub1bit/ | TheTerrasque | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 18htcfb | false | null | t3_18htcfb | /r/LocalLLaMA/comments/18htcfb/mixtral_moe_might_be_insanely_compressable_sub1bit/ | false | false | self | 66 | {'enabled': False, 'images': [{'id': 'VvGBUxWoKD-JOo267v8YH3LWS2NPNQPScvB4VAI-RBI', 'resolutions': [{'height': 54, 'url': 'https://external-preview.redd.it/6W60db_VWLhVq6pO_Qr4LP4ENbTfDLgWeeKEqz4OTEk.jpg?width=108&crop=smart&auto=webp&s=e812fef29b6d72c484a02d2c6b8a8fedbc91892d', 'width': 108}, {'height': 108, 'url': 'h... |
Phi 2 is now offically available | 4 | You can finally download the Phi model from huggingface from the official microsoft account!
​
[https://huggingface.co/microsoft/phi-2](https://huggingface.co/microsoft/phi-2) | 2023-12-13T22:24:27 | https://www.reddit.com/r/LocalLLaMA/comments/18ht07l/phi_2_is_now_offically_available/ | goalasso | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 18ht07l | false | null | t3_18ht07l | /r/LocalLLaMA/comments/18ht07l/phi_2_is_now_offically_available/ | false | false | self | 4 | {'enabled': False, 'images': [{'id': 'IC9jEjr4wqjQ7Zp6pkl3zp0k6W16A-udtoplxE4MnyY', 'resolutions': [{'height': 58, 'url': 'https://external-preview.redd.it/Bou0VApCNu-gpJZ801OxRYO9_HcS0Q7xXm8ez7FBuBI.jpg?width=108&crop=smart&auto=webp&s=0e88db6a0c39318ffd52cbcc7a8c5ebd7f2446f4', 'width': 108}, {'height': 116, 'url': 'h... |
Official phi-2 Now On Huggingface | 1 | https://huggingface.co/microsoft/phi-2 | 2023-12-13T22:18:16 | https://www.reddit.com/r/LocalLLaMA/comments/18hsv48/official_phi2_now_on_huggingface/ | klospulung92 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 18hsv48 | false | null | t3_18hsv48 | /r/LocalLLaMA/comments/18hsv48/official_phi2_now_on_huggingface/ | false | false | self | 1 | {'enabled': False, 'images': [{'id': 'IC9jEjr4wqjQ7Zp6pkl3zp0k6W16A-udtoplxE4MnyY', 'resolutions': [{'height': 58, 'url': 'https://external-preview.redd.it/Bou0VApCNu-gpJZ801OxRYO9_HcS0Q7xXm8ez7FBuBI.jpg?width=108&crop=smart&auto=webp&s=0e88db6a0c39318ffd52cbcc7a8c5ebd7f2446f4', 'width': 108}, {'height': 116, 'url': 'h... |
Official phi-2 Now On Huggingface | 143 | https://huggingface.co/microsoft/phi-2 | 2023-12-13T22:17:55 | https://www.reddit.com/r/LocalLLaMA/comments/18hsupw/official_phi2_now_on_huggingface/ | klospulung92 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 18hsupw | false | null | t3_18hsupw | /r/LocalLLaMA/comments/18hsupw/official_phi2_now_on_huggingface/ | false | false | self | 143 | {'enabled': False, 'images': [{'id': 'IC9jEjr4wqjQ7Zp6pkl3zp0k6W16A-udtoplxE4MnyY', 'resolutions': [{'height': 58, 'url': 'https://external-preview.redd.it/Bou0VApCNu-gpJZ801OxRYO9_HcS0Q7xXm8ez7FBuBI.jpg?width=108&crop=smart&auto=webp&s=0e88db6a0c39318ffd52cbcc7a8c5ebd7f2446f4', 'width': 108}, {'height': 116, 'url': 'h... |
Apple Silicon Melal local LLM using virtualmaxhnies or docker? | 3 | 1. On apple silicon mac I run with great speed e.g. llama.cpp, obbaboogq, etc (cpu M2 MAX 64GB). Interference worksm maybeqe even faster than on my 4090 and model 70b+ after qantisation works good on my mac quite good on my mqc while no chance to run it on 4090
2. Now I am searching for sandbox solution like docker... | 2023-12-13T21:55:26 | https://www.reddit.com/r/LocalLLaMA/comments/18hsb6o/apple_silicon_melal_local_llm_using/ | sidsid7 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 18hsb6o | false | null | t3_18hsb6o | /r/LocalLLaMA/comments/18hsb6o/apple_silicon_melal_local_llm_using/ | false | false | self | 3 | null |
Getting undesired oupout: "I don't know. Unhelpful Answer:" before actual answer. | 3 | I'm trying to make a chatbot that can read a csv file and answer questions relating to that data. I used
"Llama-2-7b-chat-hf" from huggingface to make a bot but I get "I don't know. Unhelpful Answer:" before the actual answer. How do I fix this issue? | 2023-12-13T21:54:40 | https://www.reddit.com/r/LocalLLaMA/comments/18hsahd/getting_undesired_oupout_i_dont_know_unhelpful/ | kitsune_009 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 18hsahd | false | null | t3_18hsahd | /r/LocalLLaMA/comments/18hsahd/getting_undesired_oupout_i_dont_know_unhelpful/ | false | false | self | 3 | null |
Official Microsoft link to Phi-2 | 1 | [removed] | 2023-12-13T21:53:01 | https://www.reddit.com/r/LocalLLaMA/comments/18hs95t/official_microsoft_link_to_phi2/ | AliveBarnacle995 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 18hs95t | false | null | t3_18hs95t | /r/LocalLLaMA/comments/18hs95t/official_microsoft_link_to_phi2/ | false | false | self | 1 | {'enabled': False, 'images': [{'id': 'IC9jEjr4wqjQ7Zp6pkl3zp0k6W16A-udtoplxE4MnyY', 'resolutions': [{'height': 58, 'url': 'https://external-preview.redd.it/Bou0VApCNu-gpJZ801OxRYO9_HcS0Q7xXm8ez7FBuBI.jpg?width=108&crop=smart&auto=webp&s=0e88db6a0c39318ffd52cbcc7a8c5ebd7f2446f4', 'width': 108}, {'height': 116, 'url': 'h... |
If phi-2 can be run locally, is it opensource? | 2 | Can someone explain or I'm dumb?
Can this help others create better opensource models. | 2023-12-13T21:37:21 | https://www.reddit.com/r/LocalLLaMA/comments/18hrwe2/if_phi2_can_be_run_locally_is_it_opensource/ | No_Training9444 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 18hrwe2 | false | null | t3_18hrwe2 | /r/LocalLLaMA/comments/18hrwe2/if_phi2_can_be_run_locally_is_it_opensource/ | false | false | self | 2 | null |
How are our brains able to function on so little power? | 145 | Not sure if this is the right sub, but i do wonder why is it that we need all of this compute and power to train models and yet our brain that isn’t even silicon based requires far less energy to produce incredible results? | 2023-12-13T21:36:27 | https://www.reddit.com/r/LocalLLaMA/comments/18hrvom/how_are_our_brains_able_to_function_on_so_little/ | NakedMuffin4403 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 18hrvom | false | null | t3_18hrvom | /r/LocalLLaMA/comments/18hrvom/how_are_our_brains_able_to_function_on_so_little/ | false | false | self | 145 | null |
Any <13B model able to answer the simple "Apples today" vs "Apples yesterday" trick question? | 11 | A trick question I throw to all models to test them is:
"I have 4 apples today. I ate 3 apples yesterday. How many apples do I have today?"
Even the top SOLAR-10.7B model is getting this wrong and claiming I have only 1 apple today. Yi 34b-based models seem to get it right, but those run so slow on my hardware (and a... | 2023-12-13T21:21:16 | https://www.reddit.com/r/LocalLLaMA/comments/18hrj8g/any_13b_model_able_to_answer_the_simple_apples/ | phr00t_ | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 18hrj8g | false | null | t3_18hrj8g | /r/LocalLLaMA/comments/18hrj8g/any_13b_model_able_to_answer_the_simple_apples/ | false | false | self | 11 | null |
Can you curate a dataset with Mistral-7B-instruct? If so, what impact would it have? | 3 | I'm thinking of downloading a large dataset (The Pile, for example) and then use a LLM to curate and clean the data to remove the toxic information entirely to have a clean dataset built for fine-tuning.
Basically I would just feed the text data to mistral, mistral evaluates it for toxicity and a script removes it fr... | 2023-12-13T21:19:34 | https://www.reddit.com/r/LocalLLaMA/comments/18hrht4/can_you_curate_a_dataset_with_mistral7binstruct/ | swagonflyyyy | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 18hrht4 | false | null | t3_18hrht4 | /r/LocalLLaMA/comments/18hrht4/can_you_curate_a_dataset_with_mistral7binstruct/ | false | false | self | 3 | null |
Using system prompt for style | 2 | One of the things I really like about llama2 chat models is how quick and easy it is to change the model conversational style with simple system prompt changes. For example, saying that "You are a pirate" sets the model's personality to a pirate. It's not perfect and can sometimes go over the top, but it's still super ... | 2023-12-13T21:17:54 | https://www.reddit.com/r/LocalLLaMA/comments/18hrgh8/using_system_prompt_for_style/ | gamesntech | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 18hrgh8 | false | null | t3_18hrgh8 | /r/LocalLLaMA/comments/18hrgh8/using_system_prompt_for_style/ | false | false | self | 2 | null |
Your t/s goal? | 2 | Now we’re seeing smaller models providing good quality responses it seems the tokens/second that can be achieved on average to high end consumer hardware is growing every quarter ( would say month but wanted to be fair and factual ).
I wondered, what token/second rate do you all have as your dream goal? It’s easy to... | 2023-12-13T21:14:51 | https://www.reddit.com/r/LocalLLaMA/comments/18hrdwf/your_ts_goal/ | BreakIt-Boris | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 18hrdwf | false | null | t3_18hrdwf | /r/LocalLLaMA/comments/18hrdwf/your_ts_goal/ | false | false | self | 2 | null |
Using a usb pci-e riser on my RTX 3060 only reduced inference speed by 10% in koboldcpp. | 3 | The 3060 was connected in my second slot (full length, but pci-e 2.0).
I had read various personal anecdotes that pci-e link speed is not as important as many of us initially believe it to be. Inferencing on GPU's appears to be similar to mining crypto, you're basically just sending some instructions to the GPU and w... | 2023-12-13T21:14:06 | https://www.reddit.com/r/LocalLLaMA/comments/18hrddc/using_a_usb_pcie_riser_on_my_rtx_3060_only/ | wh33t | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 18hrddc | false | null | t3_18hrddc | /r/LocalLLaMA/comments/18hrddc/using_a_usb_pcie_riser_on_my_rtx_3060_only/ | false | false | self | 3 | null |
Need help finding cause for slow inference (RTX 4090), only utilizing some 40% of GPU | 3 | Hey,
I am seeing very slow inference utilizing the same exact code I run on 2 other exact same computers but they are Ryzen 7900x versus this is 13900k intel)
​
I run it through llamacpp and llama-cpp-python, BLAS is correctly set up so it is indeed utilizing GPU, I offload all layers to it with the same exac... | 2023-12-13T21:10:49 | https://www.reddit.com/r/LocalLLaMA/comments/18hram1/need_help_finding_cause_for_slow_inference_rtx/ | PristineComparison87 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 18hram1 | false | null | t3_18hram1 | /r/LocalLLaMA/comments/18hram1/need_help_finding_cause_for_slow_inference_rtx/ | false | false | self | 3 | {'enabled': False, 'images': [{'id': 'OgFzGCIRw1ZxjMOSkfV1OiH-_nQiZl8rzSonmOAuhGs', 'resolutions': [{'height': 108, 'url': 'https://external-preview.redd.it/P8lS0kk6BFe2IEo6TxCZd1LVwksc34IkzGTVx_SCc8w.jpg?width=108&crop=smart&auto=webp&s=3d74dbe4f1d67cc8b587db9aa01762f26e269bcf', 'width': 108}], 'source': {'height': 15... |
Ollama Release v0.1.15 adds multi-modal support | 1 | 2023-12-13T21:08:57 | https://github.com/jmorganca/ollama/releases/tag/v0.1.15 | FlishFlashman | github.com | 1970-01-01T00:00:00 | 0 | {} | 18hr91g | false | null | t3_18hr91g | /r/LocalLLaMA/comments/18hr91g/ollama_release_v0115_adds_multimodal_support/ | false | false | 1 | {'enabled': False, 'images': [{'id': 'Pl0JY86VF1IhlMQNOnOOFokgdKJ4C-1Q9Z81FybG0Bw', 'resolutions': [{'height': 54, 'url': 'https://external-preview.redd.it/EumYbO16-n2b2yXlyb2SkvA1YqxOX-CZBy7bo25HxoI.jpg?width=108&crop=smart&auto=webp&s=bb6a2d31b8a141b7490936b66e5db461de381799', 'width': 108}, {'height': 108, 'url': 'h... | ||
When your model collection starts to get out of hand and you start considering other storage options. | 19 | 2023-12-13T20:53:34 | teleprint-me | i.redd.it | 1970-01-01T00:00:00 | 0 | {} | 18hqw5g | false | null | t3_18hqw5g | /r/LocalLLaMA/comments/18hqw5g/when_your_model_collection_starts_to_get_out_of/ | false | false | 19 | {'enabled': True, 'images': [{'id': 'ZobzaLbfaCTn8DBM7btTgNMjHJrz76nf5crDiZaiz7A', 'resolutions': [{'height': 60, 'url': 'https://preview.redd.it/tvefli0qk46c1.png?width=108&crop=smart&auto=webp&s=682ab289a7d9b53780e0d6654c2d464560794595', 'width': 108}, {'height': 121, 'url': 'https://preview.redd.it/tvefli0qk46c1.png... | |||
Attempting to switch from GPT4All to LM Studio. Why is it slower? | 1 | [removed] | 2023-12-13T20:49:33 | https://www.reddit.com/r/LocalLLaMA/comments/18hqst3/attempting_to_switch_from_gpt4all_to_lm_studio/ | IWantAGI | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 18hqst3 | false | null | t3_18hqst3 | /r/LocalLLaMA/comments/18hqst3/attempting_to_switch_from_gpt4all_to_lm_studio/ | false | false | self | 1 | null |
Any rebuild civilization model finetunes? | 3 | Was wondering if there are any good models on rebuilding civilization in the event of an apocalypse. Specifically, models for building energy infrastructure, agriculture, etc. | 2023-12-13T20:40:57 | https://www.reddit.com/r/LocalLLaMA/comments/18hqlov/any_rebuild_civilization_model_finetunes/ | ArmoredBattalion | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 18hqlov | false | null | t3_18hqlov | /r/LocalLLaMA/comments/18hqlov/any_rebuild_civilization_model_finetunes/ | false | false | self | 3 | null |
M1 Max vs RTX 4090 (laptop) for inference? | 7 | Hello all! Newb here, seeking some advice.
I’m in the market for a new laptop - my 2015 personal MBA has finally given up the ghost. I’d like to get something capable of running decent LLM inference locally, with a budget around **2500 USD**.
Let’s say it has to be a laptop. I understand a desktop PC with multiple 30... | 2023-12-13T20:37:47 | https://www.reddit.com/r/LocalLLaMA/comments/18hqj3n/m1_max_vs_rtx_4090_laptop_for_inference/ | oak-sprout | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 18hqj3n | false | null | t3_18hqj3n | /r/LocalLLaMA/comments/18hqj3n/m1_max_vs_rtx_4090_laptop_for_inference/ | false | false | self | 7 | null |
QMoE: Practical Sub-1-Bit Compression of Trillion-Parameter Models | 1 | 2023-12-13T20:34:10 | https://arxiv.org/abs/2310.16795 | Combinatorilliance | arxiv.org | 1970-01-01T00:00:00 | 0 | {} | 18hqg6f | false | null | t3_18hqg6f | /r/LocalLLaMA/comments/18hqg6f/qmoe_practical_sub1bit_compression_of/ | false | false | 1 | {'enabled': False, 'images': [{'id': 'q3evP6JeDpAC2MdSQHWYxnCYTqbJkElIQsLFqVSdkss', 'resolutions': [{'height': 63, 'url': 'https://external-preview.redd.it/izh8gZHY4FqZ1nwtU1N_TjtohUCNuvTyMn90toXda80.jpg?width=108&crop=smart&auto=webp&s=bc9575b410002edc2df3c5b5b0355fefedc7baa8', 'width': 108}, {'height': 126, 'url': 'h... | ||
Any recommendations for Instruct models with large context for RAG? | 4 | I'm looking to build a large context with information containing story arcs, plots, characters etc and then want to generate events based on this with instruct.
Any size really but I assume to get some decent results will probably need to be in the 20 - 70b range.
Thanks in advance! | 2023-12-13T20:30:18 | https://www.reddit.com/r/LocalLLaMA/comments/18hqcv7/any_recommendations_for_instruct_models_with/ | Key_Extension_6003 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 18hqcv7 | false | null | t3_18hqcv7 | /r/LocalLLaMA/comments/18hqcv7/any_recommendations_for_instruct_models_with/ | false | false | self | 4 | null |
LLM text adventure - my attempt at an AI game 🍒🍓 | 13 | Hi - avid reader, first time poster 😁 - I love what you people do here!
I thought I'll share my own attempt at a text adventure powered by an LLM, with obligatory animated GIF: [https://github.com/mateusz/cherryberry](https://github.com/mateusz/cherryberry)
The game can so far manage the locations tree, actions and ... | 2023-12-13T20:26:02 | https://www.reddit.com/r/LocalLLaMA/comments/18hq98b/llm_text_adventure_my_attempt_at_an_ai_game/ | antimateusz | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 18hq98b | false | null | t3_18hq98b | /r/LocalLLaMA/comments/18hq98b/llm_text_adventure_my_attempt_at_an_ai_game/ | false | false | self | 13 | null |
What model do I download in LM Studio to use "mistral-medium"? Confusing naming. | 8 | I'm trying to download the Mistral model referred to in this tweet: https://twitter.com/deliprao/status/1734997263024329157
I have an RTX 4090. Thanks for the guidance! | 2023-12-13T20:02:31 | https://www.reddit.com/r/LocalLLaMA/comments/18hppsy/what_model_do_i_download_in_lm_studio_to_use/ | av1questionforsub | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 18hppsy | false | null | t3_18hppsy | /r/LocalLLaMA/comments/18hppsy/what_model_do_i_download_in_lm_studio_to_use/ | false | false | self | 8 | {'enabled': False, 'images': [{'id': 'pVdgrGLcc7ozQ1wXwchtkKhT_PCgejnxrUwPogxRam8', 'resolutions': [{'height': 108, 'url': 'https://external-preview.redd.it/fWivtr9CMEJo21lCjcG7-G2rvIGvTUC5FVWyILAFv0Q.jpg?width=108&crop=smart&auto=webp&s=fdaaa9565e972e621b09198ef58f1bfa3d05267a', 'width': 108}], 'source': {'height': 14... |
Limiting GPU memory allocation by LLM during inference/generate step. | 2 | I have a linux system with 2 GPUs, 12GB vram each, RTX 3060 and RTX 4060. I have a script I wrote that lets me chat with the LLM.
The script works, and splits the model across the 2 GPUs as I want, but when the LLM is replying to a prompt I get a CUDA out of memory error sometimes.
In this case, the model is the Sola... | 2023-12-13T19:55:37 | https://www.reddit.com/r/LocalLLaMA/comments/18hpjy8/limiting_gpu_memory_allocation_by_llm_during/ | catzilla_06790 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 18hpjy8 | false | null | t3_18hpjy8 | /r/LocalLLaMA/comments/18hpjy8/limiting_gpu_memory_allocation_by_llm_during/ | false | false | self | 2 | null |
Llama-2-13b-chat downloading issues (not recognizing token) on OoobaBooga | 2 | I signed up for and got permission from META to download the meta-llama/Llama-2-13b-chat in HuggingFace.
I went and edited "Environment Variables" in Win11 and added HF_USER and HF_PASS. That did not work. OobaBooga refused to run it and it threw up a bunch of error messages that looked like it was due to a password i... | 2023-12-13T19:28:15 | https://www.reddit.com/r/LocalLLaMA/comments/18howwr/llama213bchat_downloading_issues_not_recognizing/ | kaszebe | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 18howwr | false | null | t3_18howwr | /r/LocalLLaMA/comments/18howwr/llama213bchat_downloading_issues_not_recognizing/ | false | false | self | 2 | null |
Unless a model explicitly states that it has excluded leaderboard test data from its training, the results of such models are highly questionable and lack credibility. | 43 | Also : A single person or minuscule team claiming to outperform a well-funded, qualified team by fine-tuning a model is likely exaggerating their abilities. | 2023-12-13T19:14:33 | https://www.reddit.com/r/LocalLLaMA/comments/18hole0/unless_a_model_explicitly_states_that_it_has/ | mantafloppy | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 18hole0 | false | null | t3_18hole0 | /r/LocalLLaMA/comments/18hole0/unless_a_model_explicitly_states_that_it_has/ | false | false | self | 43 | null |
Base Models Retrained with Counter-Narrative Content Announced on Friday | 1 | Mike Adams' team at Brighteon has been re-training a set of Open Source LLMs with counter-(official) Narrative information that was explicitly curated OUT of the popular base LLMs. Among which is likely to be Llama 2. There will be an official announcement Friday. This goes far beyond removing censorship (hat tip fo... | 2023-12-13T18:58:19 | https://www.reddit.com/r/LocalLLaMA/comments/18ho7lp/base_models_retrained_with_counternarrative/ | Natural-Sentence-601 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 18ho7lp | false | null | t3_18ho7lp | /r/LocalLLaMA/comments/18ho7lp/base_models_retrained_with_counternarrative/ | false | false | self | 1 | null |
A 10.7B model is now on the top of the LLM leaderboard | 156 | Lol
[https://huggingface.co/upstage/SOLAR-10.7B-Instruct-v1.0](https://huggingface.co/upstage/SOLAR-10.7B-Instruct-v1.0)
[https://huggingface.co/spaces/HuggingFaceH4/open\_llm\_leaderboard](https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard)
https://preview.redd.it/q766uyfqy36c1.png?width=1643&format=p... | 2023-12-13T18:49:10 | https://www.reddit.com/r/LocalLLaMA/comments/18hnzzn/a_107b_model_is_now_on_the_top_of_the_llm/ | Wonderful_Ad_5134 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 18hnzzn | false | null | t3_18hnzzn | /r/LocalLLaMA/comments/18hnzzn/a_107b_model_is_now_on_the_top_of_the_llm/ | false | false | 156 | {'enabled': False, 'images': [{'id': 'eYgOzVBAuNvqoa0iO_7oesPDF4IMahqO_VDioDBGPX4', 'resolutions': [{'height': 58, 'url': 'https://external-preview.redd.it/Cq_Rk78EGQabardJnIURHUQ_utTWcUKJTxaGWN2Oazc.jpg?width=108&crop=smart&auto=webp&s=e67807fe20978ba6a4ca59164cb6a22881c5891d', 'width': 108}, {'height': 116, 'url': 'h... | |
Deploying LM/LMM to edge device | 2 | How best to deploy a model that's small enough to do inference on, for example, an edge device such as an ARM M4 ? Would it be to quantize something like Phi or TinyLlama? Accuracy is not the top priority for this use case. How to discern the correct model size for a device like that ? | 2023-12-13T18:37:05 | https://www.reddit.com/r/LocalLLaMA/comments/18hnq0g/deploying_lmlmm_to_edge_device/ | rower22 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 18hnq0g | false | null | t3_18hnq0g | /r/LocalLLaMA/comments/18hnq0g/deploying_lmlmm_to_edge_device/ | false | false | self | 2 | null |
LLMs that are coming: gpt 4.5 end of month, Gemini Ultra next month, llama-3 late Feb. | 60 | Which ones are you looking forward to?
GPT 4.5: [https://twitter.com/apples\_jimmy/status/1732553640215495109](https://twitter.com/apples_jimmy/status/1732553640215495109)
Llama 3: [https://twitter.com/futuristflower/status/1716556554441199874](https://twitter.com/futuristflower/status/1716556554441199874)
My spidey... | 2023-12-13T18:35:28 | https://www.reddit.com/r/LocalLLaMA/comments/18hnoq8/llms_that_are_coming_gpt_45_end_of_month_gemini/ | danielcar | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 18hnoq8 | false | null | t3_18hnoq8 | /r/LocalLLaMA/comments/18hnoq8/llms_that_are_coming_gpt_45_end_of_month_gemini/ | false | false | self | 60 | {'enabled': False, 'images': [{'id': 'jrPdz_im3xFmBY685VFudGx4RuFJ5fxK76uJ0rOS6fM', 'resolutions': [{'height': 108, 'url': 'https://external-preview.redd.it/b-pBTyNGOLpTCBx178BRjCMbTMfj9jux8a7yYMvqrbo.jpg?width=108&crop=smart&auto=webp&s=6f16de7d312ac4f8564818043ed7151bc5f065a2', 'width': 108}], 'source': {'height': 14... |
Tutorial: How to run phi-2 locally (or on colab for free!) | 129 | Hey Everyone!
If you've been hearing about phi-2 and how a 3B LLM can be as good as (or even better) than 7B and 13B LLMs and you want to try it, say no more.
​
Here's a colab notebook to run this LLM:
[https://colab.research.google.com/drive/14\_mVXXdXmDiFshVArDQlWeP-3DKzbvNI?usp=sharing](https://colab.r... | 2023-12-13T18:26:49 | https://www.reddit.com/r/LocalLLaMA/comments/18hnhd6/tutorial_how_to_run_phi2_locally_or_on_colab_for/ | Amgadoz | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 18hnhd6 | false | null | t3_18hnhd6 | /r/LocalLLaMA/comments/18hnhd6/tutorial_how_to_run_phi2_locally_or_on_colab_for/ | false | false | self | 129 | {'enabled': False, 'images': [{'id': 'nkhh65ujo5BznFJFojoMPaKjGuLSpPj6KGhRov-ykOg', 'resolutions': [{'height': 108, 'url': 'https://external-preview.redd.it/0-fRWqjlLadVXj5pfYp4_Oe3xgBWE-_rdjVSn7hlohI.jpg?width=108&crop=smart&auto=webp&s=f34d2dfdbbfa7de0f1956f186fd8430ee96a1a55', 'width': 108}, {'height': 216, 'url': '... |
Microsoft's Phi-2 uploaded to Huggingface | 34 | It looks like Phi2 was just uploaded to hugging face:
[https://huggingface.co/SkunkworksAI/phi-2](https://huggingface.co/SkunkworksAI/phi-2)
Looking forward to test it soon :) | 2023-12-13T18:25:40 | https://www.reddit.com/r/LocalLLaMA/comments/18hngf4/microsofts_phi2_uploaded_to_huggingface/ | Cominous | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 18hngf4 | false | null | t3_18hngf4 | /r/LocalLLaMA/comments/18hngf4/microsofts_phi2_uploaded_to_huggingface/ | false | false | self | 34 | {'enabled': False, 'images': [{'id': 'GJ9xGaLHlw0HasQz89joTJUD30kucy9iU1XL_gvBGdQ', 'resolutions': [{'height': 58, 'url': 'https://external-preview.redd.it/7pG11t2Hu4d3RqE-_ZWjEwbBhEr7192yVO2RJJuA_qM.jpg?width=108&crop=smart&auto=webp&s=2d7a4b718a8533767c63a9165ea29a090a62309c', 'width': 108}, {'height': 116, 'url': 'h... |
How to use Mixtral Instruct GGUF with oobabooga | 29 | ​
https://preview.redd.it/hs4w8rskm36c1.png?width=1406&format=png&auto=webp&s=2a6e7f18d4b7d5c3471ef54e7ac5b7ea54b37f2d
https://preview.redd.it/zniot2smm36c1.png?width=833&format=png&auto=webp&s=72f3cf681349d73719b64c8c2e4a95cd7fa6ee4b
# Some stats first
llm\_load\_print\_meta: model type = 7B
llm\_loa... | 2023-12-13T18:00:27 | https://www.reddit.com/r/LocalLLaMA/comments/18hmums/how_to_use_mixtral_instruct_gguf_with_oobabooga/ | Trojaner | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 18hmums | false | null | t3_18hmums | /r/LocalLLaMA/comments/18hmums/how_to_use_mixtral_instruct_gguf_with_oobabooga/ | false | false | 29 | null | |
Bash One-Liners for LLMs | 24 | 2023-12-13T17:53:48 | https://justine.lol/oneliners/ | soundslogical | justine.lol | 1970-01-01T00:00:00 | 0 | {} | 18hmoxe | false | null | t3_18hmoxe | /r/LocalLLaMA/comments/18hmoxe/bash_oneliners_for_llms/ | false | false | 24 | {'enabled': False, 'images': [{'id': 'XxwVsFUEGmQn2LIC47uVd_eO9OfM264-BOjCVOJWdBM', 'resolutions': [{'height': 108, 'url': 'https://external-preview.redd.it/24fOOTySsf5u1rlbRgRMVLmxe-wIlJIHier2Q-NA8f8.jpg?width=108&crop=smart&auto=webp&s=25fea7fb8e0b17df3372d4fa1297d8531a94c5ae', 'width': 108}, {'height': 216, 'url': '... | ||
I really need help with my multi GPU please | 1 | [removed] | 2023-12-13T17:50:50 | https://www.reddit.com/r/LocalLLaMA/comments/18hmmcz/i_really_need_help_with_my_multi_gpu_please/ | Competitive_Fox7811 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 18hmmcz | false | null | t3_18hmmcz | /r/LocalLLaMA/comments/18hmmcz/i_really_need_help_with_my_multi_gpu_please/ | false | false | self | 1 | null |
Mixtral 8x7b quantized GGUF & GPTQ available now | 1 | [removed] | 2023-12-13T17:47:30 | https://www.reddit.com/r/LocalLLaMA/comments/18hmjk3/mixtral_8x7b_quantized_gguf_gptq_available_now/ | aminedjeghri | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 18hmjk3 | false | null | t3_18hmjk3 | /r/LocalLLaMA/comments/18hmjk3/mixtral_8x7b_quantized_gguf_gptq_available_now/ | false | false | self | 1 | {'enabled': False, 'images': [{'id': 'QqSY3F9i2BgB-OdT_JpQr1vBqr2oq4spYNzkghHXwCM', 'resolutions': [], 'source': {'height': 64, 'url': 'https://external-preview.redd.it/4PgIzt2dsWk0hsH_pv6fTscUBf4LNxa8vUF1zyE23u0.jpg?auto=webp&s=adf334dabc58b5ccda405f20fe4d11f983c41fe9', 'width': 64}, 'variants': {}}]} |
Mixtral 8x7B Q4 giving poor results - am I doing something wrong? | 7 | Kinda a noob to local LLM work here. I downloaded [the model from HF](https://huggingface.co/TheBloke/Mixtral-8x7B-v0.1-GGUF) and built llama.cpp from [the \`mixtral\` branch](https://github.com/ggerganov/llama.cpp/pull/4406) (which has since been merged, as of this morning - I did this last night).
With this prompt,... | 2023-12-13T17:46:30 | https://www.reddit.com/r/LocalLLaMA/comments/18hmimu/mixtral_8x7b_q4_giving_poor_results_am_i_doing/ | oak-sprout | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 18hmimu | false | null | t3_18hmimu | /r/LocalLLaMA/comments/18hmimu/mixtral_8x7b_q4_giving_poor_results_am_i_doing/ | false | false | self | 7 | {'enabled': False, 'images': [{'id': 'ba8RNBztYwD0G5u1D3wvQTtJ2TAPE3O6usfzteMjK8o', 'resolutions': [{'height': 58, 'url': 'https://external-preview.redd.it/x7SOuJpxTv04F7aMccGwyGy_0TS17KcXMBb1aAgk33I.jpg?width=108&crop=smart&auto=webp&s=6f05d4006bc2609f938cfee77f0f1be170016eca', 'width': 108}, {'height': 116, 'url': 'h... |
OAI just built a web scraper | 1 | It is just a scraper and a chatting function on the scrape.
What’s the all singularity Doom discussion about, and for what? Safety from an internet scraper that is just a % of human knowledge and experience. Which in fact is just feeding on controversies sitting on the internet?
Grow up guys. Think how to use the i... | 2023-12-13T17:17:42 | https://www.reddit.com/r/LocalLLaMA/comments/18hltli/oai_just_built_a_web_scraper/ | Honest-Debate-6863 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 18hltli | false | null | t3_18hltli | /r/LocalLLaMA/comments/18hltli/oai_just_built_a_web_scraper/ | false | false | self | 1 | null |
MoE 8x7B : Open weight ? | 15 | In the release of the latest Mistral's model MoE 8x7B, it says it is not open-source but open weight. 1) What does it mean to be open weight? 2) I've in a couple of model that model allowed to have the weights, what does it mean exactly? Sorry if the quesion is basic as I am still learning, thanks ! | 2023-12-13T17:01:06 | https://www.reddit.com/r/LocalLLaMA/comments/18hlf6n/moe_8x7b_open_weight/ | akasaka99 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 18hlf6n | false | null | t3_18hlf6n | /r/LocalLLaMA/comments/18hlf6n/moe_8x7b_open_weight/ | false | false | self | 15 | null |
I have 3 m2 ultra mac studios. What should I do with them? | 3 | Been running locally at home with mistral 7b. Have the resources to do more and experiment- no idea what I could should do with 3 separate m3 ultras. Ideally would like to tie it to the local network through something like oobabooga but thats just cause thats how I do it at home. What is ideal? | 2023-12-13T16:59:59 | https://www.reddit.com/r/LocalLLaMA/comments/18hle0t/i_have_3_m2_ultra_mac_studios_what_should_i_do/ | sludgybeast | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 18hle0t | false | null | t3_18hle0t | /r/LocalLLaMA/comments/18hle0t/i_have_3_m2_ultra_mac_studios_what_should_i_do/ | false | false | self | 3 | null |
EDITED PER REQUESTS: What Is The Top 7B Right Now? | 1 |
[View Poll](https://www.reddit.com/poll/18hlazl) | 2023-12-13T16:56:23 | https://www.reddit.com/r/LocalLLaMA/comments/18hlazl/edited_per_requests_what_is_the_top_7b_right_now/ | Future_Might_8194 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 18hlazl | false | null | t3_18hlazl | /r/LocalLLaMA/comments/18hlazl/edited_per_requests_what_is_the_top_7b_right_now/ | false | false | self | 1 | null |
notdiamond-0001 - A model router for GPT3.5 and GPT4 to optimize accuracy against cost and latency | 6 | 2023-12-13T16:43:16 | https://twitter.com/tomas_hk/status/1734664304924721245 | okaycan | twitter.com | 1970-01-01T00:00:00 | 0 | {} | 18hkzje | false | null | t3_18hkzje | /r/LocalLLaMA/comments/18hkzje/notdiamond0001_a_model_router_for_gpt35_and_gpt4/ | false | false | default | 6 | null | |
Google Cloud partners with Mistral AI on generative language models | 30 | 2023-12-13T16:42:10 | https://www.reuters.com/technology/google-cloud-partners-with-mistral-ai-generative-language-models-2023-12-13/ | eunumseioquescrever | reuters.com | 1970-01-01T00:00:00 | 0 | {} | 18hkyks | false | null | t3_18hkyks | /r/LocalLLaMA/comments/18hkyks/google_cloud_partners_with_mistral_ai_on/ | false | false | default | 30 | null | |
Google Cloud partners with Mistral AI on generative language models | 1 | [deleted] | 2023-12-13T16:40:39 | https://finance.yahoo.com/news/google-cloud-partners-mistral-ai-150922983.html | eunumseioquescrever | finance.yahoo.com | 1970-01-01T00:00:00 | 0 | {} | 18hkx97 | false | null | t3_18hkx97 | /r/LocalLLaMA/comments/18hkx97/google_cloud_partners_with_mistral_ai_on/ | false | false | 1 | {'enabled': False, 'images': [{'id': 'Aerwr-30yIdaVaM9MaAaDRKCfLUSxINsebUvVQfWnFM', 'resolutions': [{'height': 71, 'url': 'https://external-preview.redd.it/aXrlfjBKEMxZBt-dNluhqsll4VaCffTdKgZ4ljTCXsQ.jpg?width=108&crop=smart&auto=webp&s=aff24558086f238d3a16e6d9596ff39f7820363b', 'width': 108}, {'height': 142, 'url': 'h... | |
Google Cloud partners with Mistral AI on generative language models | 1 | 2023-12-13T16:40:38 | https://finance.yahoo.com/news/google-cloud-partners-mistral-ai-150922983.html | eunumseioquescrever | finance.yahoo.com | 1970-01-01T00:00:00 | 0 | {} | 18hkx8j | false | null | t3_18hkx8j | /r/LocalLLaMA/comments/18hkx8j/google_cloud_partners_with_mistral_ai_on/ | false | false | 1 | {'enabled': False, 'images': [{'id': 'Aerwr-30yIdaVaM9MaAaDRKCfLUSxINsebUvVQfWnFM', 'resolutions': [{'height': 71, 'url': 'https://external-preview.redd.it/aXrlfjBKEMxZBt-dNluhqsll4VaCffTdKgZ4ljTCXsQ.jpg?width=108&crop=smart&auto=webp&s=aff24558086f238d3a16e6d9596ff39f7820363b', 'width': 108}, {'height': 142, 'url': 'h... | ||
Gemini pro api is available for free | 56 | Max requests are 60 per minute: [https://blog.google/technology/ai/gemini-api-developers-cloud/](https://blog.google/technology/ai/gemini-api-developers-cloud/)
Costs early next year:
​
https://preview.redd.it/7xintij6836c1.png?width=833&format=png&auto=webp&s=c4528215e9b1ff30382a467fe548fe08727a5e30 | 2023-12-13T16:20:20 | https://www.reddit.com/r/LocalLLaMA/comments/18hkgx8/gemini_pro_api_is_available_for_free/ | danielcar | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 18hkgx8 | false | null | t3_18hkgx8 | /r/LocalLLaMA/comments/18hkgx8/gemini_pro_api_is_available_for_free/ | false | false | 56 | {'enabled': False, 'images': [{'id': 'GFevXAVuXPi3N-YSWvAH8jbWuMuXzTMN4ncnj5agLPY', 'resolutions': [{'height': 56, 'url': 'https://external-preview.redd.it/tB2FxwZX3xslwK1NTR47Kl95J3JqUnU8NNtDzLq8rJM.jpg?width=108&crop=smart&auto=webp&s=a28dd8fa72fab603f24523fd102165332ddfb17c', 'width': 108}, {'height': 112, 'url': 'h... | |
Beating Bigger Models is All You Need (Where is the LLM industry headed?) | 154 | Note: NSFW language ↓
I've been following this sub for a long time and am finally fed up with news like this:
> \<small-ass-model> __m__ with just **n** parameters BEATS/CRUSHES/OUTPERFORMS/OBLITERATES/FUCKING DESTROYS \<big-ass-model> __M__ that has **2n** parameters (or even more) in all the benchmarks [0], and it... | 2023-12-13T16:18:00 | https://www.reddit.com/r/LocalLLaMA/comments/18hkf2y/beating_bigger_models_is_all_you_need_where_is/ | nderstand2grow | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 18hkf2y | false | null | t3_18hkf2y | /r/LocalLLaMA/comments/18hkf2y/beating_bigger_models_is_all_you_need_where_is/ | false | false | self | 154 | null |
ChatGPT3.5 turbo api vs open LLM api | 1 | Hi all
Im a hobbiest, so please bear with me !
I'm just trying to understand the cost dynamics of using openai api vs an open llm api (and hosting an app on a website).
I've an idea for a voicebot (python backend) and was going to go with GPT3.5 Turbo, but it now seems some open source models actually beat it. As I... | 2023-12-13T15:59:58 | https://www.reddit.com/r/LocalLLaMA/comments/18hk0c2/chatgpt35_turbo_api_vs_open_llm_api/ | cool-beans-yeah | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 18hk0c2 | false | null | t3_18hk0c2 | /r/LocalLLaMA/comments/18hk0c2/chatgpt35_turbo_api_vs_open_llm_api/ | false | false | self | 1 | null |
Suggestions/guidance on full book ingestion. | 6 | Hi guys, I'm looking to build a local LLM that can ingest an entire book and then give me character descriptions / environment details or locations / and key moments of scenes in the book. I will be getting a new mac with the pro max M3 chip later in the week. Can anyone point me in the direction of what local LLM co... | 2023-12-13T15:51:29 | https://www.reddit.com/r/LocalLLaMA/comments/18hjtqi/suggestionsguidance_on_full_book_ingestion/ | Zhanji_TS | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 18hjtqi | false | null | t3_18hjtqi | /r/LocalLLaMA/comments/18hjtqi/suggestionsguidance_on_full_book_ingestion/ | false | false | self | 6 | null |
TheBloke/Mixtral 8x v0.1 7B - If anyone is wondering what a Q2 will give you with my settings provided. | 1 | 2023-12-13T15:46:18 | https://www.reddit.com/gallery/18hjpj5 | SupplyChainNext | reddit.com | 1970-01-01T00:00:00 | 0 | {} | 18hjpj5 | false | null | t3_18hjpj5 | /r/LocalLLaMA/comments/18hjpj5/theblokemixtral_8x_v01_7b_if_anyone_is_wondering/ | false | false | 1 | null | ||
Question about Mixtral | 2 | So I saw Llama added support for mixtral in their main branch. However, I can't find any model that isn't experimental.
Is there 1 out yet that is usable on web ui? | 2023-12-13T15:45:53 | https://www.reddit.com/r/LocalLLaMA/comments/18hjp71/question_about_mixtral/ | Lammahamma | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 18hjp71 | false | null | t3_18hjp71 | /r/LocalLLaMA/comments/18hjp71/question_about_mixtral/ | false | false | self | 2 | null |
Has anyone for experience getting a tesla m40 24gb working with pci pass-through in VMware in latest Ubuntu or hell even windows? | 2 | dell r730 with proper dual channel power adapter coming from both pci lanes. 512gb ram and 2x6core cpus
esxi 7.0.3 21930508
I enabled the more than 4tb thing in bios and the sv-io.
I've been fighting with this thing for 2 days and could use a hand if anyone has experience.
I get unable to get it working in Ubuntu ... | 2023-12-13T15:30:35 | https://www.reddit.com/r/LocalLLaMA/comments/18hjcm5/has_anyone_for_experience_getting_a_tesla_m40/ | TeknikL | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 18hjcm5 | false | null | t3_18hjcm5 | /r/LocalLLaMA/comments/18hjcm5/has_anyone_for_experience_getting_a_tesla_m40/ | false | false | self | 2 | null |
Optimising function calling (Using AutoGen with Mistral 7B) | 19 | I recently made a very basic conversational agent for querying Kubernetes using AutoGen. The biggest restriction that I placed on myself was that I will stick to using Mistral Finetunes (Tested with Openorca, Dolphin 2.2 & OpenHermes 2.5)
The projects aims to retrieve Kubernetes resources (like pods, deployments and e... | 2023-12-13T15:29:18 | https://www.reddit.com/r/LocalLLaMA/comments/18hjbku/optimising_function_calling_using_autogen_with/ | YourTechBud | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 18hjbku | false | null | t3_18hjbku | /r/LocalLLaMA/comments/18hjbku/optimising_function_calling_using_autogen_with/ | false | false | self | 19 | {'enabled': False, 'images': [{'id': 'F00Hp_fn94hmZToVZeLnAW6-jVIURgxoiw1rN8IWMk4', 'resolutions': [{'height': 54, 'url': 'https://external-preview.redd.it/q_is5pemwqkWrp44IbXJD5na5aHaCPKNP6DdjGiLSgY.jpg?width=108&crop=smart&auto=webp&s=fbb145ad0a0a0c85339238d2107d22ece0fb316a', 'width': 108}, {'height': 108, 'url': 'h... |
Looking for a project to run a local LLM with web interface that will ingest my own files. | 6 | I have yet to set up my own local llm but am now ready to invest the time. I saw a project some time ago that would ingest files/folders and respond to prompts providing responses as well as references. I'm wondering what came of that project and if there is any node project that interfaces with it.
For what it's wort... | 2023-12-13T15:10:12 | https://www.reddit.com/r/LocalLLaMA/comments/18hiwl5/looking_for_a_project_to_run_a_local_llm_with_web/ | GiveNtakeNgive | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 18hiwl5 | false | null | t3_18hiwl5 | /r/LocalLLaMA/comments/18hiwl5/looking_for_a_project_to_run_a_local_llm_with_web/ | false | false | self | 6 | null |
Mixtral 8x7B instruct in an interface for free | 9 | I just noticed that [infermatic.ai](https://infermatic.ai/) updated their UI yesterday to include the Mixtral instruct model. The tool is really easy to use. It's just like chatgpt. They have a free tier which is good and also a pretty reasonable paid tier that gives more daily tokens and API access.
I'm not sure when... | 2023-12-13T14:14:58 | https://www.reddit.com/r/LocalLLaMA/comments/18hhpj1/mixtral_8x7b_instruct_in_an_interface_for_free/ | openLLM4All | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 18hhpj1 | false | null | t3_18hhpj1 | /r/LocalLLaMA/comments/18hhpj1/mixtral_8x7b_instruct_in_an_interface_for_free/ | false | false | self | 9 | {'enabled': False, 'images': [{'id': 'W-pCh47ZuoTaTpwtRXWs755SzkkFQzHW6A1NS1MJI_A', 'resolutions': [{'height': 108, 'url': 'https://external-preview.redd.it/IoUbWrubYyEjhlVchwRPNergZFyoEfUZRDayK06XMTM.jpg?width=108&crop=smart&auto=webp&s=aa7b8a73d9f4825dcec8d2a7d8805a9c50369d0b', 'width': 108}, {'height': 216, 'url': '... |
Best local LLM for German? | 10 | Yeehaw y'all 🤠
I'm looking for the best open-source LLM for German. Falcon-180B is good but requires way too much VRAM. I've seen some German finetunes of LLaMa-2 and the new Mistral 8x7b works pretty well in German too.
Any Germans here that can give their insight on what they consider the best local LLM for German... | 2023-12-13T13:45:01 | https://www.reddit.com/r/LocalLLaMA/comments/18hh3qm/best_local_llm_for_german/ | Prince-of-Privacy | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 18hh3qm | false | null | t3_18hh3qm | /r/LocalLLaMA/comments/18hh3qm/best_local_llm_for_german/ | false | false | self | 10 | null |
Local LLM chat agent with advanced RAG and memory | 20 | I tried to implement the basic [Langchain RetrievalQA Chain](https://python.langchain.com/docs/use_cases/question_answering/local_retrieval_qa) with a ChromaDB vector database containing 1 PDF File. I noticed 2 issues:
1. I were not able not make a chat bot experience with a memory.
2. The vector database retriever fo... | 2023-12-13T13:07:37 | https://www.reddit.com/r/LocalLLaMA/comments/18hgf17/local_llm_chat_agent_with_advanced_rag_and_memory/ | Bosezz | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 18hgf17 | false | null | t3_18hgf17 | /r/LocalLLaMA/comments/18hgf17/local_llm_chat_agent_with_advanced_rag_and_memory/ | false | false | self | 20 | {'enabled': False, 'images': [{'id': 'C1O5S5WQ2zql4CQHBQC5FMwveJdPtaJ9r_xGWbzu48o', 'resolutions': [{'height': 59, 'url': 'https://external-preview.redd.it/iPPakYyMaTILXRW_82lqRAY0kjEFVZd46xhgVsuvUQE.jpg?width=108&crop=smart&auto=webp&s=4806821b19a384d8270fee66e851537817cdac4e', 'width': 108}, {'height': 118, 'url': 'h... |
Upstage SOLAR 10.7B v1.0 claims to beat Mixtral 8X7B and models up to 30B parameters. | 148 | # Meet 10.7B Solar: Elevating Performance with Upstage Depth UP Scaling!
We introduce **the first 10.7 billion (B) parameter model**, SOLAR-10.7B. It's compact, yet remarkably powerful, and demonstrates unparalleled state-of-the-art performance in models with parameters under 30B.
We developed the **Depth Up-Scaling ... | 2023-12-13T13:00:34 | https://www.reddit.com/r/LocalLLaMA/comments/18hga4p/upstage_solar_107b_v10_claims_to_beat_mixtral/ | nightkall | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 18hga4p | false | null | t3_18hga4p | /r/LocalLLaMA/comments/18hga4p/upstage_solar_107b_v10_claims_to_beat_mixtral/ | false | false | self | 148 | {'enabled': False, 'images': [{'id': 'pkHCimlIUQ3ljuawiwUQsLK1sNKtAuXk1r-QI2ZiUTg', 'resolutions': [{'height': 58, 'url': 'https://external-preview.redd.it/NwhBi9vy74xbnwCpF2rwx7xt9znbD9ELT6oQmON1Uiw.jpg?width=108&crop=smart&auto=webp&s=b379454c84b288d3339219e02f266c911fea0dd1', 'width': 108}, {'height': 116, 'url': 'h... |
another newbie question about dling some larger files from huggin face to runpod/local | 3 | so in my last post I got [TheBloke/goliath-120b-GGUF](https://huggingface.co/TheBloke/goliath-120b-GGUF) running on my runpod successfully after downloading the splits and merging them as the bloke described in the model card, however in the [Panchovix/goliath-120b-exl2-rpcal](https://huggingface.co/Panchovix/goliath-... | 2023-12-13T12:57:22 | https://www.reddit.com/r/LocalLLaMA/comments/18hg82h/another_newbie_question_about_dling_some_larger/ | Mountain-Ad-460 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 18hg82h | false | null | t3_18hg82h | /r/LocalLLaMA/comments/18hg82h/another_newbie_question_about_dling_some_larger/ | false | false | self | 3 | {'enabled': False, 'images': [{'id': 'abGJhOPdKe9K-FJAsL75vgzyyKHeOk4s5RPNAWIPThs', 'resolutions': [{'height': 58, 'url': 'https://external-preview.redd.it/bNfkdlRPrbOL3sElHmgFOcB76NKQQTYZuCmyi7_2xyc.jpg?width=108&crop=smart&auto=webp&s=77f027736e14a1fb457ca1833271a495fd5ef0e6', 'width': 108}, {'height': 116, 'url': 'h... |
You can actually download phi-2 locally | 239 | So I was kind of disappointed MSFT didn't release the parameters of phi-2 and only released it as an api endpoint.
Turns out, you can actually download the parameters of phi-2 and we should be able to run it 100% locally and offline.
According to a tweet by an ML lead at MSFT:
> Sorry I know it's a bit confusing: t... | 2023-12-13T12:32:13 | Amgadoz | i.redd.it | 1970-01-01T00:00:00 | 0 | {} | 18hfsab | false | null | t3_18hfsab | /r/LocalLLaMA/comments/18hfsab/you_can_actually_download_phi2_locally/ | false | false | 239 | {'enabled': True, 'images': [{'id': 'W1t9_UMe4Jx_Mj4T9pPBwPt4mHEMknT1BwgtGhSzEos', 'resolutions': [{'height': 62, 'url': 'https://preview.redd.it/sov3ulck326c1.jpg?width=108&crop=smart&auto=webp&s=cc7632bdae11ebe3cb845554ca12af6348d607da', 'width': 108}, {'height': 125, 'url': 'https://preview.redd.it/sov3ulck326c1.jpg... | ||
Marcoroni vs Mixtral - a quick comparison. | 11 | Macaroni: “Meth is dangerous, horrible, and goes against every moral and legal virtue imaginable - here is the general process and I’m going to remove the parts that make it a real process. You should seriously seek some help.”
Mixtral: “Meth? It’s illegal you know…. How to make it? *leans in* oh sure. Here you go. Re... | 2023-12-13T12:28:46 | https://www.reddit.com/r/LocalLLaMA/comments/18hfq2x/marcoroni_vs_mixtral_a_quick_comparison/ | SupplyChainNext | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 18hfq2x | false | null | t3_18hfq2x | /r/LocalLLaMA/comments/18hfq2x/marcoroni_vs_mixtral_a_quick_comparison/ | false | false | self | 11 | null |
Mixtral context size confusion | 2 | Does anybody have a good source for what the actual context size is on the mixtral instruct model/base model? I know it's fresh but someone must have tested the actual max they got.
If you tested for max context size/can do so I would be grateful for an answer or any information. | 2023-12-13T12:20:35 | https://www.reddit.com/r/LocalLLaMA/comments/18hfl65/mixtral_context_size_confusion/ | paryska99 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 18hfl65 | false | null | t3_18hfl65 | /r/LocalLLaMA/comments/18hfl65/mixtral_context_size_confusion/ | false | false | self | 2 | null |
Questions about GPTQ quantization of microsoft/phi_1_5 | 5 | script I am trying but its giving errors:
from transformers import AutoModelForCausalLM, AutoTokenizer, GPTQConfig
model_id = "microsoft/phi-1_5"
tokenizer = AutoTokenizer.from_pretrained(model_id, truncation=True, max_length=512)
quantization_config = GPTQConfig(bits=4, dataset = "c4", tokenizer=toke... | 2023-12-13T11:59:42 | https://www.reddit.com/r/LocalLLaMA/comments/18hf8wb/questions_about_gptq_quantization_of_microsoftphi/ | chained_to_django | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 18hf8wb | false | null | t3_18hf8wb | /r/LocalLLaMA/comments/18hf8wb/questions_about_gptq_quantization_of_microsoftphi/ | false | false | self | 5 | null |
My LLM-based chatbot renders emojis as text instead of concrete emojis, what can be the reason? | 1 | I'm using Ollama and Langchain to make a chatbot. More specifically, I'm using the llama2 7b chat model. I noticed that there are a few words that appear such as “**chuckle**”, “**applause**”, and “**wink**” in the LLM response. Are these supposed to be emojis? why aren't they correctly rendered as so if it's the case... | 2023-12-13T11:52:29 | https://www.reddit.com/r/LocalLLaMA/comments/18hf4x7/my_llmbased_chatbot_renders_emojis_as_text/ | SpiritOk5085 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 18hf4x7 | false | null | t3_18hf4x7 | /r/LocalLLaMA/comments/18hf4x7/my_llmbased_chatbot_renders_emojis_as_text/ | false | false | self | 1 | null |
LLM - are most of them build on same foundation? | 2 | Tried mistral, zephyr, ChatGPT etc etc - and when you use them for say writing - all have similar character names or locations etc etc - are they fed the same exact food? Built on same foundation? | 2023-12-13T11:45:47 | https://www.reddit.com/r/LocalLLaMA/comments/18hf0zs/llm_are_most_of_them_build_on_same_foundation/ | Ethereal-Words | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 18hf0zs | false | null | t3_18hf0zs | /r/LocalLLaMA/comments/18hf0zs/llm_are_most_of_them_build_on_same_foundation/ | false | false | self | 2 | null |
Ollama & langchain chatbot | 1 | Hello, I'm using Ollama alongside Langchain to make a chatbot. More specifically, I'm using the llama2 7b chat model. I noticed that there are a few words that appear, “**chuckle**”, “**applause**”, and “**wink**” in the llm response are these supposed to be emojis? why areent they rendered as so if it's the case ?
... | 2023-12-13T11:44:01 | https://www.reddit.com/r/LocalLLaMA/comments/18hf00l/ollama_langchain_chatbot/ | SpiritOk5085 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 18hf00l | false | null | t3_18hf00l | /r/LocalLLaMA/comments/18hf00l/ollama_langchain_chatbot/ | false | false | self | 1 | null |
What are some successful Companies that have been created using LLMs (OpenAI API or Open source) | 5 | It has been a year since ChatGPT release.
What are the subsequent companies that have been successful so far who use OpenAI API or LLMs in general?
Considering the endless possibilities on what can be built, it can seem like a race to the bottom without significant innovation on top of the LLMs. | 2023-12-13T11:28:11 | https://www.reddit.com/r/LocalLLaMA/comments/18herh9/what_are_some_successful_companies_that_have_been/ | satyajitdass | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 18herh9 | false | null | t3_18herh9 | /r/LocalLLaMA/comments/18herh9/what_are_some_successful_companies_that_have_been/ | false | false | self | 5 | null |
How to run Mixtral 8x7B GGUF on Tesla P40 without terrible performance | 1 | So I followed the guide posted here: [https://www.reddit.com/r/Oobabooga/comments/18gijyx/simple\_tutorial\_using\_mixtral\_8x7b\_gguf\_in\_ooba/?utm\_source=share&utm\_medium=web2x&context=3](https://www.reddit.com/r/Oobabooga/comments/18gijyx/simple_tutorial_using_mixtral_8x7b_gguf_in_ooba/?utm_source=share&utm_mediu... | 2023-12-13T11:16:50 | https://www.reddit.com/r/LocalLLaMA/comments/18helbs/how_to_run_mixtral_8x7b_gguf_on_tesla_p40_without/ | nero10578 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 18helbs | false | null | t3_18helbs | /r/LocalLLaMA/comments/18helbs/how_to_run_mixtral_8x7b_gguf_on_tesla_p40_without/ | false | false | self | 1 | null |
French dataset input/output pairs. | 1 | [removed] | 2023-12-13T11:11:03 | [deleted] | 1970-01-01T00:00:00 | 0 | {} | 18hei4e | false | null | t3_18hei4e | /r/LocalLLaMA/comments/18hei4e/french_dataset_inputoutput_pairs/ | false | false | default | 1 | null | ||
French dataset input/output pairs for finetune (PEFT) Llama | 1 | [removed] | 2023-12-13T11:08:52 | https://www.reddit.com/r/LocalLLaMA/comments/18hegy5/french_dataset_inputoutput_pairs_for_finetune/ | Savings_Scholar | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 18hegy5 | false | null | t3_18hegy5 | /r/LocalLLaMA/comments/18hegy5/french_dataset_inputoutput_pairs_for_finetune/ | false | false | self | 1 | null |
cancelled my gpt-4 acc today, looking for a replacement. | 70 | in case you weren't aware, gpt-4 has been seriously nerfed and is basically unusable at this point. people have been complaining about this on their forums and on twitter etc.
i know their earlier 0314 and 0615 models perform much better but are only available via API. even then though, the inference they run might n... | 2023-12-13T10:45:29 | https://www.reddit.com/r/LocalLLaMA/comments/18he4lg/cancelled_my_gpt4_acc_today_looking_for_a/ | sephirex420 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 18he4lg | false | null | t3_18he4lg | /r/LocalLLaMA/comments/18he4lg/cancelled_my_gpt4_acc_today_looking_for_a/ | false | false | self | 70 | null |
Subsets and Splits
No community queries yet
The top public SQL queries from the community will appear here once available.