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 update: On perplexity testing, adding an expert only improves quality for Q2_K, using two experts achieves the best performance for the rest, and Q6_K has the lowest perplexity | 79 | This comes from [ymcui on GitHub](https://github.com/ggerganov/llama.cpp/pull/4406#issuecomment-1855151885), the same source for [yesterday's post](https://www.reddit.com/r/LocalLLaMA/comments/18i2h4c/mixtral_gets_even_better_by_just_adding_an_expert/), who has since updated their comment. Q8\_0 and F16 were not tested... | 2023-12-15T06:35:53 | https://www.reddit.com/r/LocalLLaMA/comments/18ituzh/mixtral_update_on_perplexity_testing_adding_an/ | llamaShill | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 18ituzh | false | null | t3_18ituzh | /r/LocalLLaMA/comments/18ituzh/mixtral_update_on_perplexity_testing_adding_an/ | false | false | 79 | {'enabled': False, 'images': [{'id': 'Na3FaC07gEEB8XgYMOuJh24sPjV1fPQPIPOQabTuxlc', 'resolutions': [{'height': 54, 'url': 'https://external-preview.redd.it/V7gYa2wwgfocK4XzuyidI9s0dRgAjWlnUG7gocd9DHI.jpg?width=108&crop=smart&auto=webp&s=ec209736cd07943f723d394910e1e7332a5c56e8', 'width': 108}, {'height': 108, 'url': 'h... | |
AI has taken over. Your last conversation will determine your fate. | 1 | Title. | 2023-12-15T06:34:21 | https://www.reddit.com/r/LocalLLaMA/comments/18itu55/ai_has_taken_over_your_last_conversation_will/ | KvAk_AKPlaysYT | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 18itu55 | false | null | t3_18itu55 | /r/LocalLLaMA/comments/18itu55/ai_has_taken_over_your_last_conversation_will/ | false | false | self | 1 | null |
How to use downloaded models in oobabooga? | 1 | Hey y'all i'm kinda new in this space
I downloaded llama2 via meta's recomended documantation, but I was wondering if I could use it with Oobabooga?
Thanks sm | 2023-12-15T06:32:41 | https://www.reddit.com/r/LocalLLaMA/comments/18itt95/how_to_use_downloaded_models_in_oobabooga/ | Monochrome21 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 18itt95 | false | null | t3_18itt95 | /r/LocalLLaMA/comments/18itt95/how_to_use_downloaded_models_in_oobabooga/ | false | false | self | 1 | null |
Best method for answering aggregation type queries? | 2 | Which method is best suited for answering an aggregation type of query, given that the information may be scattered across multiple locations in multiple files. For example, the question, write down the characteristics of such and such a category of objects? This information is not structured anywhere in one or two pla... | 2023-12-15T06:01:25 | https://www.reddit.com/r/LocalLLaMA/comments/18itbp9/best_method_for_answering_aggregation_type_queries/ | 1nkor | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 18itbp9 | false | null | t3_18itbp9 | /r/LocalLLaMA/comments/18itbp9/best_method_for_answering_aggregation_type_queries/ | false | false | self | 2 | null |
what are some of the best high-quality chain-of-thought or similar coding datasets? | 1 | [removed] | 2023-12-15T05:08:43 | sujantkv | i.redd.it | 1970-01-01T00:00:00 | 0 | {} | 18isgpt | false | null | t3_18isgpt | /r/LocalLLaMA/comments/18isgpt/what_are_some_of_the_best_highquality/ | false | false | 1 | {'enabled': True, 'images': [{'id': 'Y8OQTqCIyB1m96D0Fv2A7Ve_3nNf_quKkvIcygTW5wI', 'resolutions': [{'height': 144, 'url': 'https://preview.redd.it/gh5diua96e6c1.png?width=108&crop=smart&auto=webp&s=bae549d61ae0678ceb2dbb7acd65d7d68bb58c98', 'width': 108}, {'height': 288, 'url': 'https://preview.redd.it/gh5diua96e6c1.pn... | ||
How to fine-tune Mixtral 8x7b in google colab? | 2 | I need a colab file to file tune mixtral. | 2023-12-15T04:43:39 | https://www.reddit.com/r/LocalLLaMA/comments/18is0n2/how_to_finetune_mixtral_8x7b_in_google_colab/ | Original_Job6327 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 18is0n2 | false | null | t3_18is0n2 | /r/LocalLLaMA/comments/18is0n2/how_to_finetune_mixtral_8x7b_in_google_colab/ | false | false | self | 2 | null |
Best Model to locally run in a low end GPU with 4 GB RAM right now | 33 | I am a total newbie to LLM space. As the title says, I am trying to get a decent model for coding/fine tuning in a lowly Nvidia 1650 card. I am excited about Phi-2 but some of the posts here indicate it is slow due to some reason despite being a small model. | 2023-12-15T04:07:40 | https://www.reddit.com/r/LocalLLaMA/comments/18ire2a/best_model_to_locally_run_in_a_low_end_gpu_with_4/ | curious_cat_says_hi | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 18ire2a | false | null | t3_18ire2a | /r/LocalLLaMA/comments/18ire2a/best_model_to_locally_run_in_a_low_end_gpu_with_4/ | false | false | self | 33 | null |
Holy moly, Mixtral 8x7b passes my Sisters test without even telling it to think step by step! Only Falcon 180b and GPT-4 nailed this question before. | 264 | 2023-12-15T03:41:56 | nderstand2grow | i.redd.it | 1970-01-01T00:00:00 | 0 | {} | 18iqxcl | false | null | t3_18iqxcl | /r/LocalLLaMA/comments/18iqxcl/holy_moly_mixtral_8x7b_passes_my_sisters_test/ | false | false | 264 | {'enabled': True, 'images': [{'id': 'OdOO7dTEMRXR2Mjaf-nN-XxsrRm8kajhlIk3j8FdcoE', 'resolutions': [{'height': 55, 'url': 'https://preview.redd.it/q68580ukqd6c1.png?width=108&crop=smart&auto=webp&s=6815049de7f9004f8edc371d336c4ffcbb0e5051', 'width': 108}, {'height': 110, 'url': 'https://preview.redd.it/q68580ukqd6c1.png... | |||
Mamba-3B-SlimPJ: State-space model - No Transformer Architecture | 62 | 2023-12-15T02:09:05 | https://www.together.ai/blog/mamba-3b-slimpj | super-helper | together.ai | 1970-01-01T00:00:00 | 0 | {} | 18ip5qj | false | null | t3_18ip5qj | /r/LocalLLaMA/comments/18ip5qj/mamba3bslimpj_statespace_model_no_transformer/ | false | false | default | 62 | null | |
Mixtral vs YI 34B | 15 | Which one is smarter?
IME, I’m thinking the winner is YI? | 2023-12-15T02:07:50 | https://www.reddit.com/r/LocalLLaMA/comments/18ip4y8/mixtral_vs_yi_34b/ | Majestical-psyche | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 18ip4y8 | false | null | t3_18ip4y8 | /r/LocalLLaMA/comments/18ip4y8/mixtral_vs_yi_34b/ | false | false | self | 15 | null |
What’s everyone’s favorite uncensored 7B? | 7 | Asking for a friend. So far TheBloke’s Dolphin has worked well. Kind of have to lead it where you want though. | 2023-12-15T02:06:22 | https://www.reddit.com/r/LocalLLaMA/comments/18ip3zu/whats_everyones_favorite_uncensored_7b/ | AmericanKamikaze | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 18ip3zu | false | null | t3_18ip3zu | /r/LocalLLaMA/comments/18ip3zu/whats_everyones_favorite_uncensored_7b/ | false | false | self | 7 | null |
Projekt advice and sanity check data mining from full text scientific papers with context analysis of llms. | 3 | SHORT: i want to use llms to analyse scientific texts for specific gene gene interactions. Basically data mining. Questions on feasibility and tips and tricks.
So I am a bioinformatics master who got in to llms in his off time because an idea floated in my head and I wanted to know the opinion on how feasible it is. A... | 2023-12-15T01:45:12 | https://www.reddit.com/r/LocalLLaMA/comments/18iopat/projekt_advice_and_sanity_check_data_mining_from/ | Noxusequal | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 18iopat | false | null | t3_18iopat | /r/LocalLLaMA/comments/18iopat/projekt_advice_and_sanity_check_data_mining_from/ | false | false | self | 3 | null |
Falcon 180b Q4_0 Aces the 8 Sisters vs. 1 Sister Test while Gemini Pro Failed it | 2 | 2023-12-15T01:45:11 | nderstand2grow | i.redd.it | 1970-01-01T00:00:00 | 0 | {} | 18iopaf | false | null | t3_18iopaf | /r/LocalLLaMA/comments/18iopaf/falcon_180b_q4_0_aces_the_8_sisters_vs_1_sister/ | false | false | 2 | {'enabled': True, 'images': [{'id': 'rcSFpUcgKxz-fqVay125XIlTGiMkWpvvNjfZ8iOFivQ', 'resolutions': [{'height': 67, 'url': 'https://preview.redd.it/nswfmwdw5d6c1.png?width=108&crop=smart&auto=webp&s=9add385105dbcc6478b2fb0b55a98487db19cfd4', 'width': 108}, {'height': 135, 'url': 'https://preview.redd.it/nswfmwdw5d6c1.png... | |||
Is there any way currently to try out and utilize Local LLM's without Enterprise Grade hardware? | 2 | I really want to try Open source LLM i find on hugging face, is the only way to run open source llms right now with expensive hardware or is there another way? Please i am coping so hard. | 2023-12-15T01:37:02 | https://www.reddit.com/r/LocalLLaMA/comments/18iojin/is_there_any_way_currently_to_try_out_and_utilize/ | Articulity | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 18iojin | false | null | t3_18iojin | /r/LocalLLaMA/comments/18iojin/is_there_any_way_currently_to_try_out_and_utilize/ | false | false | self | 2 | null |
How are you people running 70B parameter models? | 46 | I have a 3090 and seems like I can run 30b models but not 33 or 34 b. is there some trick you guys are using to get them to work?
also. any recommendations for the least censored models? | 2023-12-15T01:16:09 | https://www.reddit.com/r/LocalLLaMA/comments/18io4lp/how_are_you_people_running_70b_parameter_models/ | assfaceMCdickbutt | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 18io4lp | false | null | t3_18io4lp | /r/LocalLLaMA/comments/18io4lp/how_are_you_people_running_70b_parameter_models/ | false | false | self | 46 | null |
Needing a little assistance with setup if possible 3090 + P40, P41 | 1 | [removed] | 2023-12-15T01:08:29 | https://www.reddit.com/r/LocalLLaMA/comments/18inzbx/needing_a_little_assistance_with_setup_if/ | sysadmin420 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 18inzbx | false | null | t3_18inzbx | /r/LocalLLaMA/comments/18inzbx/needing_a_little_assistance_with_setup_if/ | false | false | self | 1 | {'enabled': False, 'images': [{'id': 'DsiOIzUSicS_9zIKwMDQbNT2LOE1o29sSYs49HAmO_k', 'resolutions': [{'height': 56, 'url': 'https://external-preview.redd.it/hHuPbOBuX42Zu5_MT0rir3JO7cgRTfjn0ct4UWuqTu4.jpg?width=108&crop=smart&auto=webp&s=a0329d4207ada0345185e70a97a0ef1f27aec034', 'width': 108}, {'height': 113, 'url': 'h... |
Does anyone need to deploy a LoRA fine-tune for super cheap? | 2 | I'm working on a project right now where I need to fine-tune a model since OpenAI doesn't work for this use case, but the product is still being prototyped. My current deployment options seems to be renting a GPU (expensive), or serverless (long cold boot times, bad experience for alpha testers?).
I was wondering if a... | 2023-12-15T00:31:16 | https://www.reddit.com/r/LocalLLaMA/comments/18in8j7/does_anyone_need_to_deploy_a_lora_finetune_for/ | box_head1 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 18in8j7 | false | null | t3_18in8j7 | /r/LocalLLaMA/comments/18in8j7/does_anyone_need_to_deploy_a_lora_finetune_for/ | false | false | self | 2 | null |
Are there any local LLMs that with a Javascript API? | 1 | Looking for one to use in my command line program cmdh (command helper)[https://github.com/pgibler/cmdh](https://github.com/pgibler/cmdh]. It's been immensely useful to me and has saved me countless hours figuring out how to devise complex or hard to find commands (you can see some in the docs and video on the project ... | 2023-12-15T00:26:45 | https://www.reddit.com/r/LocalLLaMA/comments/18in598/are_there_any_local_llms_that_with_a_javascript/ | Giblaz | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 18in598 | false | null | t3_18in598 | /r/LocalLLaMA/comments/18in598/are_there_any_local_llms_that_with_a_javascript/ | false | false | self | 1 | {'enabled': False, 'images': [{'id': 'VY5xh8OZ61gWUtf7hCM56P5EVdmOJCJ1LV3IAXvjlgc', 'resolutions': [{'height': 54, 'url': 'https://external-preview.redd.it/k_-FLqGpMgSk0H7b6O7oqeCdVv8rWZC__YpPs2giI04.jpg?width=108&crop=smart&auto=webp&s=af584667405ec723e886e6d9ecc5eccda3bf7f2c', 'width': 108}, {'height': 108, 'url': 'h... |
Help with instruction format for mistral-medium, Mixtral-8x7B-Instruct-v0.1, Llama-2-7B-32K-Instruct | 4 | Hi everyone, I am learning/working with these models via API (mistral.ai and together.ai). Initially I was doing something like this, based on the documentation available on the respective sites, and looking at the generated code on the sites' playground. I still don't get the `<s>` and what happens to the `</s>`.
... | 2023-12-15T00:15:09 | https://www.reddit.com/r/LocalLLaMA/comments/18imwg0/help_with_instruction_format_for_mistralmedium/ | xilex | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 18imwg0 | false | null | t3_18imwg0 | /r/LocalLLaMA/comments/18imwg0/help_with_instruction_format_for_mistralmedium/ | false | false | self | 4 | {'enabled': False, 'images': [{'id': 'xU07sACUhuScPaN8BIMV0USMZkFwSMGcorjhvoKF4K0', 'resolutions': [{'height': 58, 'url': 'https://external-preview.redd.it/FRlvpc5SALNi_rYIzAsFALIzMXE1oc-Gkb2Yh1ZWGMM.jpg?width=108&crop=smart&auto=webp&s=9ad9ea4d991fae47edd6a09b5feb6d60eca474de', 'width': 108}, {'height': 116, 'url': 'h... |
Could MoE models be made to run faster on multiple GPUs by selecting one expert on each GPU? | 14 | For example if Mixtral selects two of its 8 experts, could there be a version of it where 4 experts are on one GPU and 4 are on the other, and it selects one of each and runs them at the same time? Or am I completely misunderstanding how MoE works | 2023-12-15T00:06:58 | https://www.reddit.com/r/LocalLLaMA/comments/18imq9a/could_moe_models_be_made_to_run_faster_on/ | NLTPanaIyst | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 18imq9a | false | null | t3_18imq9a | /r/LocalLLaMA/comments/18imq9a/could_moe_models_be_made_to_run_faster_on/ | false | false | self | 14 | null |
Why is EXL2 not a thing with Mixtral yet? | 21 | I have a 4090 but it seems like I can not take advantage of the speed yet because of the prompt processing issue. Why is it difficult to enable Mixtral for EXL2? Is it possible at all? When do you think it will be done? | 2023-12-14T23:58:25 | https://www.reddit.com/r/LocalLLaMA/comments/18imjga/why_is_exl2_not_a_thing_with_mixtral_yet/ | opgg62 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 18imjga | false | null | t3_18imjga | /r/LocalLLaMA/comments/18imjga/why_is_exl2_not_a_thing_with_mixtral_yet/ | false | false | self | 21 | null |
When you need a question answered or problems solved, which do you use first: an LLM or a search engine? | 1 | [removed]
[View Poll](https://www.reddit.com/poll/18imd5r) | 2023-12-14T23:50:12 | https://www.reddit.com/r/LocalLLaMA/comments/18imd5r/when_you_need_a_question_answered_or_problems/ | TheTwelveYearOld | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 18imd5r | false | null | t3_18imd5r | /r/LocalLLaMA/comments/18imd5r/when_you_need_a_question_answered_or_problems/ | false | false | self | 1 | null |
Open A.I. chief claims GPT 4.5 rumor is not logit | 4 | haha jk: s/logit/legit/
[https://twitter.com/sama/status/1735422206296088950](https://twitter.com/sama/status/1735422206296088950)
Rumor: [https://www.reddit.com/r/OpenAI/comments/18i5n29/anyone\_hear\_of\_gpt45\_drop\_today/](https://www.reddit.com/r/OpenAI/comments/18i5n29/anyone_hear_of_gpt45_drop_today/)
​... | 2023-12-14T23:48:13 | https://www.reddit.com/r/LocalLLaMA/comments/18imbo6/open_ai_chief_claims_gpt_45_rumor_is_not_logit/ | danielcar | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 18imbo6 | false | null | t3_18imbo6 | /r/LocalLLaMA/comments/18imbo6/open_ai_chief_claims_gpt_45_rumor_is_not_logit/ | false | false | self | 4 | {'enabled': False, 'images': [{'id': 'lSMCkaNkZBwFA2j59VIRNg7Kk_3Pqg1Ntmsr_RQQKeo', 'resolutions': [{'height': 108, 'url': 'https://external-preview.redd.it/OtZ-c2HAM__-fvRQdiuoEWTOw0QnPzmTwGsZ-5SkEV8.jpg?width=108&crop=smart&auto=webp&s=1459c59368488788b4afb3e6ff65feb9cf9de594', 'width': 108}], 'source': {'height': 14... |
What's the best "bang for the buck" setup? | 37 | If I were to invest a few thousand dollars what would be the best setup?
I've been looking a few of these: [2080 Ti modded w/ 22GB VRAM](https://2080ti22g.com/products/2080-ti-22g-memory-custom-upgraded-stable-diffusion-llama2-deep-learning), or would I be better off getting 2x the number of Tesla P40s for the same co... | 2023-12-14T23:44:48 | https://www.reddit.com/r/LocalLLaMA/comments/18im8zc/whats_the_best_bang_for_the_buck_setup/ | AbleSugar | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 18im8zc | false | null | t3_18im8zc | /r/LocalLLaMA/comments/18im8zc/whats_the_best_bang_for_the_buck_setup/ | false | false | self | 37 | {'enabled': False, 'images': [{'id': '-tIHwrAFTXsWxBjFLpet6_X4l9Rnwld_O97DK8lM854', 'resolutions': [{'height': 57, 'url': 'https://external-preview.redd.it/Arr6VNJrO5FfNnCm9KYgrH524eXlOC1vWpZzB-ziKvU.jpg?width=108&crop=smart&auto=webp&s=bd43d4b0a95b9087cad13780f4cf452d23038a0f', 'width': 108}, {'height': 115, 'url': 'h... |
Brand new model, Bagel-DPO-7B, released by Jon Durbin! | 30 | This is a model that is using a variety of prompt formats, instead of just one. So you can just choose what you like best. Also uses a vast variety of datasets and should be awesome at everything you throw at it. Try it out!
[https://huggingface.co/jondurbin/bagel-7b-v0.1](https://huggingface.co/jondurbin/bagel-7b-v0.... | 2023-12-14T23:38:24 | https://www.reddit.com/r/LocalLLaMA/comments/18im461/brand_new_model_bageldpo7b_released_by_jon_durbin/ | dampflokfreund | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 18im461 | false | null | t3_18im461 | /r/LocalLLaMA/comments/18im461/brand_new_model_bageldpo7b_released_by_jon_durbin/ | false | false | self | 30 | {'enabled': False, 'images': [{'id': 'x_c1JPRMgEITRcAWM52wF0G3a5OkbAb_8OSn-qpgNM4', 'resolutions': [{'height': 58, 'url': 'https://external-preview.redd.it/hRyHrMIBXthr6qW645oFTFMnvjvH-RIRV-cTZHNLYWs.jpg?width=108&crop=smart&auto=webp&s=719657f89a6428ef5bcd1cd32090ed7e01a8f824', 'width': 108}, {'height': 116, 'url': 'h... |
goliath-120b-exl2-rpcal : how to use ? | 2 | Sorry if the question was already asked but i cant find anything.
How can i download this file ? [The page](https://huggingface.co/Panchovix/goliath-120b-exl2-rpcal) only give link to small quantisations, is there a special option in Ooba to load both a Goliath GGUF and the Pippa paquet ?
Or I have to download the Go... | 2023-12-14T23:33:18 | https://www.reddit.com/r/LocalLLaMA/comments/18im0d0/goliath120bexl2rpcal_how_to_use/ | ervertes | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 18im0d0 | false | null | t3_18im0d0 | /r/LocalLLaMA/comments/18im0d0/goliath120bexl2rpcal_how_to_use/ | false | false | self | 2 | {'enabled': False, 'images': [{'id': '7wYYeKHJdwemBLlNcCeOJoZ76fi3lfjPqO3AQ5iU-kU', 'resolutions': [{'height': 58, 'url': 'https://external-preview.redd.it/KC7aW3g1hmeFvCj3kyCINwH9HWaT8ZCUkmTW5nvj8Ws.jpg?width=108&crop=smart&auto=webp&s=0d937da4e405d4c03c7c2f20739cc838f87a30f2', 'width': 108}, {'height': 116, 'url': 'h... |
Is it true that we won't need smaller fine-tuned models in the future? | 1 | [removed] | 2023-12-14T23:23:43 | https://www.reddit.com/r/LocalLLaMA/comments/18ilsz9/is_it_true_that_we_wont_need_smaller_finetuned/ | Slight-Employ-5765 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 18ilsz9 | false | null | t3_18ilsz9 | /r/LocalLLaMA/comments/18ilsz9/is_it_true_that_we_wont_need_smaller_finetuned/ | false | false | self | 1 | null |
text-generation-webui Playground: how to set the character? | 1 | [removed] | 2023-12-14T22:51:56 | https://www.reddit.com/r/LocalLLaMA/comments/18il3ep/textgenerationwebui_playground_how_to_set_the/ | StableLlama | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 18il3ep | false | null | t3_18il3ep | /r/LocalLLaMA/comments/18il3ep/textgenerationwebui_playground_how_to_set_the/ | false | false | self | 1 | null |
A more intuitive way to score MMLU benchmarks with DZPAS | 9 | **The TLDR**: DZPAS is an adjustment to MMLU benchmark scores that takes into account 3 things: (1) scores artificially boosted due to multiple choice guessing, (2) data contamination, and (3) 0-shot adjustment to more accurately score LLMs in the way people use them. Here's how that looks on common open-source benchm... | 2023-12-14T22:17:31 | https://www.reddit.com/r/LocalLLaMA/comments/18ikb0e/a_more_intuitive_way_to_score_mmlu_benchmarks/ | jd_3d | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 18ikb0e | false | null | t3_18ikb0e | /r/LocalLLaMA/comments/18ikb0e/a_more_intuitive_way_to_score_mmlu_benchmarks/ | false | false | 9 | null | |
Where is tiny llama? | 1 | Is it done training? | 2023-12-14T22:04:16 | https://www.reddit.com/r/LocalLLaMA/comments/18ik02j/where_is_tiny_llama/ | TheHumanFixer | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 18ik02j | false | null | t3_18ik02j | /r/LocalLLaMA/comments/18ik02j/where_is_tiny_llama/ | false | false | self | 1 | null |
Mixtral support on Ollama v0.1.16 | 28 | New Ollama release adds support Mixtral and other models based on its Mixture of Experts (MoE) architecture. (this model requires at least 48GB of memory) | 2023-12-14T21:54:32 | https://github.com/jmorganca/ollama/releases/tag/v0.1.16 | Bitcoin_hunter-21M | github.com | 1970-01-01T00:00:00 | 0 | {} | 18ijrs0 | false | null | t3_18ijrs0 | /r/LocalLLaMA/comments/18ijrs0/mixtral_support_on_ollama_v0116/ | false | false | 28 | {'enabled': False, 'images': [{'id': 'irkw2kO6m2EHTyQzQLmqJ7FrCk7esoThvKCECTFp1Gg', 'resolutions': [{'height': 54, 'url': 'https://external-preview.redd.it/P8HySjHC4vlFPudPIX6Ha2p9_IdH6t-tsgX5qh7Dl3s.jpg?width=108&crop=smart&auto=webp&s=505095226bc1bed5375dde9dbbb207e50a1371fd', 'width': 108}, {'height': 108, 'url': 'h... | |
Fun with Mistral-Medium | 21 | I was blessed with Mistral API access this morning so I asked my usual riddle of the 3 available models.
Riddle: A girl has as many brothers as sisters, but each brother has only half as many bothers and sisters. How many brothers and sisters are there?
mistral-tiny (aka mistral-7B-v0.2)
---
Let's reason through t... | 2023-12-14T21:30:04 | https://www.reddit.com/r/LocalLLaMA/comments/18ij7wx/fun_with_mistralmedium/ | kryptkpr | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 18ij7wx | false | null | t3_18ij7wx | /r/LocalLLaMA/comments/18ij7wx/fun_with_mistralmedium/ | false | false | self | 21 | null |
llm's on small/portable laptop? | 4 | I can kind of run llama-2-13b.Q2_K.gguf on my Thinkpad X270 running Linux, if I'm very patient. I'm not very patient. But I like the small size of the laptop, and having access to a local, though very blurry, copy of The Internet. I saw someone recommended the Lenovo Legion which has a 4090 (and ports! why do they alwa... | 2023-12-14T20:55:10 | https://www.reddit.com/r/LocalLLaMA/comments/18iigbz/llms_on_smallportable_laptop/ | fietsrad | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 18iigbz | false | null | t3_18iigbz | /r/LocalLLaMA/comments/18iigbz/llms_on_smallportable_laptop/ | false | false | self | 4 | {'enabled': False, 'images': [{'id': 'GmA2iPdndIipX7y4lhLDGEzIU4dGojswOJSHGJozsmM', 'resolutions': [{'height': 60, 'url': 'https://external-preview.redd.it/Qpg23byt9q_Fet56t0qaBCm5BH43CE-vAt0GAMipdfk.jpg?width=108&crop=smart&auto=webp&s=eece7926beb71f2fc2b22b8b83a7ee969413c148', 'width': 108}, {'height': 121, 'url': 'h... |
What is the average percentage drop in accuracy for quantized models compared to the original ones? | 1 | [removed] | 2023-12-14T20:30:58 | https://www.reddit.com/r/LocalLLaMA/comments/18ihwkj/what_is_the_average_percentage_drop_in_accuracy/ | Greg_Z_ | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 18ihwkj | false | null | t3_18ihwkj | /r/LocalLLaMA/comments/18ihwkj/what_is_the_average_percentage_drop_in_accuracy/ | false | false | default | 1 | null |
Are there any models that can write an actually good short story? (Not ChatGPT's story style) | 36 | ChatGPT stories always have the same sort of style,
- uplifting endings where everyone realizes the true meaning of friendship and that the shared experience they went with their companions has changed them all forever, etc. etc.
- lots of "purple prose" and ridiculous metaphors
- insistence on literally everything bei... | 2023-12-14T20:21:24 | https://www.reddit.com/r/LocalLLaMA/comments/18ihoty/are_there_any_models_that_can_write_an_actually/ | JealousAmoeba | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 18ihoty | false | null | t3_18ihoty | /r/LocalLLaMA/comments/18ihoty/are_there_any_models_that_can_write_an_actually/ | false | false | self | 36 | null |
What's Your Game-Changing Use Case for Local LLMs?" | 5 |
I'm curious about practical applications of running Large Language Models locally. If you've integrated local LLMs into your workflow, I’d like to hear about it.
- What tasks are you using local LLMs for?
- How has it impacted your work?
- Any notable benefits or challenges?
- Why are you running it locally instead o... | 2023-12-14T20:20:16 | https://www.reddit.com/r/LocalLLaMA/comments/18ihnsz/whats_your_gamechanging_use_case_for_local_llms/ | LuminaUI | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 18ihnsz | false | null | t3_18ihnsz | /r/LocalLLaMA/comments/18ihnsz/whats_your_gamechanging_use_case_for_local_llms/ | false | false | self | 5 | null |
I finetuned Phi-1.5 and Phi-2 on MathInstruct using MAmmoTH but... | 8 | The models saved as pytorch\_model\_fsdp.bin. I tried to convert this to a pytorch\_model.bin by unwrapping it with this code: [https://pastebin.com/TGCuR5S6](https://pastebin.com/TGCuR5S6)
I have to manually change the model embedding dim before loading the state dict, and I think this is a bad sign.
Does anyone kn... | 2023-12-14T20:19:10 | https://www.reddit.com/r/LocalLLaMA/comments/18ihmwv/i_finetuned_phi15_and_phi2_on_mathinstruct_using/ | codys12 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 18ihmwv | false | null | t3_18ihmwv | /r/LocalLLaMA/comments/18ihmwv/i_finetuned_phi15_and_phi2_on_mathinstruct_using/ | false | false | self | 8 | {'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... |
Any good quantized local LLMs out there? | 1 | I opened a new sub called r/canyoufeeltheAGI (it is restricted so you can't post or comment there) as a gag sub akin to r/SubredditSimulator but then I realized that I can get a local LLM to use reddit's thread system to generate piecemeal code in an attempt to stack one code solution on top of the other until the proj... | 2023-12-14T20:18:19 | https://www.reddit.com/r/LocalLLaMA/comments/18ihm67/any_good_quantized_local_llms_out_there/ | swagonflyyyy | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 18ihm67 | false | null | t3_18ihm67 | /r/LocalLLaMA/comments/18ihm67/any_good_quantized_local_llms_out_there/ | false | false | self | 1 | null |
Customer support Assistant | 3 | Hey,
I have tried to build conversational retrieval chain api with custom data and also memory for 3 prior conv. using mistral 7b instruct ,and langchain, but the api would answer one time and then just gives empty response with no errors, could not find any progress!!
Can someone please guide me where to find best Co... | 2023-12-14T19:46:57 | https://www.reddit.com/r/LocalLLaMA/comments/18igwud/customer_support_assistant/ | prime_danger | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 18igwud | false | null | t3_18igwud | /r/LocalLLaMA/comments/18igwud/customer_support_assistant/ | false | false | default | 3 | null |
Could I serialize models in current "state"? | 1 | I am trying to write an API so that I can have some models running on my server and call those APIs from my device. Some of my custom functions have a somewhat long pre-prompt "You're an expert on blah-blah be mindful of blah-blah", which takes a considerable time for the model to read (minutes on CPU, seconds on GPU o... | 2023-12-14T19:42:28 | https://www.reddit.com/r/LocalLLaMA/comments/18igt3v/could_i_serialize_models_in_current_state/ | Woitee | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 18igt3v | false | null | t3_18igt3v | /r/LocalLLaMA/comments/18igt3v/could_i_serialize_models_in_current_state/ | false | false | self | 1 | null |
Could I serialize models in current "state"? | 3 | I am trying to write an API so that I can have some models running on my server and call those APIs from my device. Some of my custom functions have a somewhat long pre-prompt "You're an expert on blah-blah be mindful of blah-blah", which takes a considerable time for the model to read (minutes on CPU, seconds on GPU o... | 2023-12-14T19:42:27 | https://www.reddit.com/r/LocalLLaMA/comments/18igt3q/could_i_serialize_models_in_current_state/ | Woitee | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 18igt3q | false | null | t3_18igt3q | /r/LocalLLaMA/comments/18igt3q/could_i_serialize_models_in_current_state/ | false | false | self | 3 | null |
Does anyone have a Chat interface on local JavaScript web page accepting your Mistral Medium API key? | 4 | I am tempted to use the curl API to have it write one for me, but I am pretty sure someone here must already have one? | 2023-12-14T19:42:01 | https://www.reddit.com/r/LocalLLaMA/comments/18igsrv/does_anyone_have_a_chat_interface_on_local/ | Competitive_Travel16 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 18igsrv | false | null | t3_18igsrv | /r/LocalLLaMA/comments/18igsrv/does_anyone_have_a_chat_interface_on_local/ | false | false | self | 4 | null |
What could you do with 1 TB of vram? | 1 | Let's say, hypothetically, if one were to acquire a Radeon Pro SSG, such as one with 1 TB of vram, what's the most you could do with it? | 2023-12-14T19:33:35 | https://www.reddit.com/r/LocalLLaMA/comments/18iglzj/what_could_you_do_with_1_tb_of_vram/ | absouluteUNIT3000 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 18iglzj | false | null | t3_18iglzj | /r/LocalLLaMA/comments/18iglzj/what_could_you_do_with_1_tb_of_vram/ | false | false | self | 1 | null |
Meet 10.7B Solar: Elevating Performance with Upstage Depth UP Scaling! | 1 |
> We developed the Depth Up-Scaling technique. Built on the Llama2 architecture, SOLAR-10.7B incorporates the innovative Upstage Depth Up-Scaling. We then integrated Mistral 7B weights into the upscaled layers, and finally, continued pre-training for the entire model.
Any ideas what Depth Up-Scaling could be? | 2023-12-14T19:31:39 | https://huggingface.co/upstage/SOLAR-10.7B-Instruct-v1.0 | 1mprobability | huggingface.co | 1970-01-01T00:00:00 | 0 | {} | 18igkhl | false | null | t3_18igkhl | /r/LocalLLaMA/comments/18igkhl/meet_107b_solar_elevating_performance_with/ | false | false | 1 | {'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... | |
What could you do with 1 TB of vram? | 80 | Let's say, hypothetically, if one were to acquire a Radeon Pro SSG, such as one with 1 TB of vram, what's the most you could do with it? | 2023-12-14T19:31:37 | https://www.reddit.com/r/LocalLLaMA/comments/18igkgb/what_could_you_do_with_1_tb_of_vram/ | absouluteUNIT3000 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 18igkgb | false | null | t3_18igkgb | /r/LocalLLaMA/comments/18igkgb/what_could_you_do_with_1_tb_of_vram/ | false | false | self | 80 | null |
LoRA adapters for Mixtral (to run on 4.5 GB) | 6 | Just thinking out loud here, would like some thoughts.
1). If each of the 8xFF layers of the Mixtral were one layer and 8 lora adapters - we would get compression way down - could it work? And if so:
2). Can we create LoRAs out of the differences of the 8xFF layers and apply this?
This would get it down to ballpark ... | 2023-12-14T19:26:59 | https://www.reddit.com/r/LocalLLaMA/comments/18iggr8/lora_adapters_for_mixtral_to_run_on_45_gb/ | gmork_13 | self.LocalLLaMA | 2023-12-14T19:51:21 | 0 | {} | 18iggr8 | false | null | t3_18iggr8 | /r/LocalLLaMA/comments/18iggr8/lora_adapters_for_mixtral_to_run_on_45_gb/ | false | false | self | 6 | null |
Phi-2 on Mac M1/metal? | 2 | Hi the HF repo for phi-2 has instructions of CUDA specifically so I don't know if it can run on M1/metal so has anyone tested out phi-2 on metal/M1? If so please tell me how to run it? | 2023-12-14T19:02:15 | https://www.reddit.com/r/LocalLLaMA/comments/18ifx4k/phi2_on_mac_m1metal/ | Shoddy_Vegetable_115 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 18ifx4k | false | null | t3_18ifx4k | /r/LocalLLaMA/comments/18ifx4k/phi2_on_mac_m1metal/ | false | false | self | 2 | null |
What format for notes? | 3 | I have setup mixtral 8x7b on my local machine with llama.cpp and I am using txt.ai to create a local RAG pipeline from my obsidian notes.
After playing around some, it seems like the model handles atomic note lines the best (all information in a single line).
This is different than how I can structured notes in the p... | 2023-12-14T18:57:37 | https://www.reddit.com/r/LocalLLaMA/comments/18ift5y/what_format_for_notes/ | tabgok | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 18ift5y | false | null | t3_18ift5y | /r/LocalLLaMA/comments/18ift5y/what_format_for_notes/ | false | false | self | 3 | null |
Mistral Medium- context length? | 1 | I just got API access to Mistral Medium. Anyone know its context length? My use cases require >50k tokens, and I'm hoping to create my own GPT4, Claude2, Mistral MoE. Thanks! | 2023-12-14T18:36:36 | https://www.reddit.com/r/LocalLLaMA/comments/18ifcda/mistral_medium_context_length/ | Berberis | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 18ifcda | false | null | t3_18ifcda | /r/LocalLLaMA/comments/18ifcda/mistral_medium_context_length/ | false | false | self | 1 | null |
Best way to create a content generation LLM based on my own data | 17 | I have textual data with more than 1,000,000 words in multiple txt files. I'd like to use LLMs to create blog posts for our blog based on those texts. What would be the best way to achieve this with LLMs? I'm ok with the writing style of existing LLMs, even chatgpt could do the trick if I could give it that much data.
... | 2023-12-14T18:29:06 | https://www.reddit.com/r/LocalLLaMA/comments/18if67a/best_way_to_create_a_content_generation_llm_based/ | Blancoo21 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 18if67a | false | null | t3_18if67a | /r/LocalLLaMA/comments/18if67a/best_way_to_create_a_content_generation_llm_based/ | false | false | self | 17 | null |
Notice to research community: Use of generative artificial intelligence technology in the NSF merit review process | 1 | 2023-12-14T18:25:42 | https://new.nsf.gov/news/notice-to-the-research-community-on-ai | TroyHernandez | new.nsf.gov | 1970-01-01T00:00:00 | 0 | {} | 18if3kv | false | null | t3_18if3kv | /r/LocalLLaMA/comments/18if3kv/notice_to_research_community_use_of_generative/ | false | false | 1 | {'enabled': False, 'images': [{'id': '2-UWez1vxvNwPBM2lr-CXspa46VfoItcS2PAVxrCWLs', 'resolutions': [{'height': 108, 'url': 'https://external-preview.redd.it/PNyhAkkgPsPjnH0gLPBFB3FLLH5QdnpUB-1iz5xawyw.jpg?width=108&crop=smart&auto=webp&s=f3e7af5c44c641cc3feff69c0f0b3fe746d12ecb', 'width': 108}], 'source': {'height': 20... | ||
GPT 4.5 Metadata details appear in API | 1 | 2023-12-14T18:18:19 | https://twitter.com/hokeone/status/1735327219164037520?ref_src=twsrc%5Etfw%7Ctwcamp%5Etweetembed%7Ctwterm%5E1735327219164037520%7Ctwgr%5Ea64e9961bb0d47f8b47f63e916a144ead78fc0be%7Ctwcon%5Es1_&ref_url=https%3A%2F%2Fwww.redditmedia.com%2Fmediaembed%2F18ibrwp%3Fresponsive%3Dtrueis_nightmode%3Dfalse | super-helper | twitter.com | 1970-01-01T00:00:00 | 0 | {} | 18iexhm | false | {'oembed': {'author_name': 'stefano', 'author_url': 'https://twitter.com/hokeone', 'cache_age': 3153600000, 'height': None, 'html': '<blockquote class="twitter-video"><p lang="zxx" dir="ltr"><a href="https://t.co/6QdxMv3AKp">pic.twitter.com/6QdxMv3AKp</a></p>— stefano (@hokeone) <a href="https://twitter.com/hokeo... | t3_18iexhm | /r/LocalLLaMA/comments/18iexhm/gpt_45_metadata_details_appear_in_api/ | false | false | 1 | {'enabled': False, 'images': [{'id': 'B7g-9YB6Ixdkv4SbR9_ElNK1BwKIVd32Rtug8yeDtrM', 'resolutions': [{'height': 34, 'url': 'https://external-preview.redd.it/QBkqE5vmcamqVxv9yRNAuud9UX2aqQVXp_ssZa4YDIQ.jpg?width=108&crop=smart&auto=webp&s=ae1f898d6c89f4128e73e1fba837b10e34a783aa', 'width': 108}], 'source': {'height': 45,... | ||
fblgit/una-xaberius-34b-v1beta is caught cheating on leaderboard. UNA cybertron juanako is just a lie. | 92 | [https://www.reddit.com/r/LocalLLaMA/comments/18ejwm1/what\_is\_fblgituna\_unified\_neural\_alignment\_looks/](https://www.reddit.com/r/LocalLLaMA/comments/18ejwm1/what_is_fblgituna_unified_neural_alignment_looks/)
I suspected last week that this model, and the author( [juanako.ai](https://juanako.ai/) / Xavier M. / ... | 2023-12-14T18:16:59 | https://www.reddit.com/r/LocalLLaMA/comments/18iewem/fblgitunaxaberius34bv1beta_is_caught_cheating_on/ | PuzzledTeam5961 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 18iewem | false | null | t3_18iewem | /r/LocalLLaMA/comments/18iewem/fblgitunaxaberius34bv1beta_is_caught_cheating_on/ | false | false | 92 | {'enabled': False, 'images': [{'id': 'E52zxkgIQ4erLeto4AhQQwIDH-4S-D7pyYegSKhUC3Y', 'resolutions': [{'height': 58, 'url': 'https://external-preview.redd.it/pX1sM-1B5Q7cYzBztyqS3kCWYJKD4n6j9K-WJrDmC10.jpg?width=108&crop=smart&auto=webp&s=11874a81c84f6ac8d6af4cd02b91b763e5aa9e63', 'width': 108}, {'height': 116, 'url': 'h... | |
Any ideas why LM Studio Mixtral 8bit is giving me worse answers than Perplexity labs Mixtral? | 11 | Also it seems it's possible to configure the number of experts used for each token, but I don't see that configuration option.
The example question I give is a json with multiple elements and I want the AI to filter them and show accuracy > 0.99 elements only. On perplexity website it's always correct, but locally it'... | 2023-12-14T17:59:47 | https://www.reddit.com/r/LocalLLaMA/comments/18iehlv/any_ideas_why_lm_studio_mixtral_8bit_is_giving_me/ | MidnightSun_55 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 18iehlv | false | null | t3_18iehlv | /r/LocalLLaMA/comments/18iehlv/any_ideas_why_lm_studio_mixtral_8bit_is_giving_me/ | false | false | self | 11 | null |
Candle Phi WASM Demo - run Microsoft Phi-2 q4k in web browser | 13 | 2023-12-14T17:40:23 | https://huggingface.co/spaces/radames/Candle-phi1-phi2-wasm-demo?model=phi_2_0_q4k | niutech | huggingface.co | 1970-01-01T00:00:00 | 0 | {} | 18ie1r0 | false | null | t3_18ie1r0 | /r/LocalLLaMA/comments/18ie1r0/candle_phi_wasm_demo_run_microsoft_phi2_q4k_in/ | false | false | 13 | {'enabled': False, 'images': [{'id': 'fuO00O7qX3jXuj6gAg_bAx3TaTHxTk8hT0pE_5GOrbQ', 'resolutions': [{'height': 58, 'url': 'https://external-preview.redd.it/2wvCpjPYxmaxmOyPHrWjhXsua5erHt5Y07a0XHPjmHc.jpg?width=108&crop=smart&auto=webp&s=7e1c3b47e73de83455e9dcd72b43d9122a26fa40', 'width': 108}, {'height': 116, 'url': 'h... | ||
Mistral API: Initial test results | 12 | Just got access. Pretty neat results so far:
> Bob is in the living room. He walks to the kitchen, carrying a cup. He puts a ball in the cup and carries the cup to the bedroom. He turns the cup upside down, then walks to the garden. He puts the cup down in the garden, then walks to the garage. Where is the ball?
Mod... | 2023-12-14T17:10:16 | https://www.reddit.com/r/LocalLLaMA/comments/18idcwt/mistral_api_initial_test_results/ | Conutu | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 18idcwt | false | null | t3_18idcwt | /r/LocalLLaMA/comments/18idcwt/mistral_api_initial_test_results/ | false | false | self | 12 | null |
We would theorically compress Mixtral up to 4gb without much degradation | 218 | [https://github.com/ggerganov/llama.cpp/issues/4445](https://github.com/ggerganov/llama.cpp/issues/4445)
[https://arxiv.org/abs/2310.16795](https://arxiv.org/abs/2310.16795)
https://preview.redd.it/xu02xfl7la6c1.png?width=1742&format=png&auto=webp&s=4168598f9b11dd8a5e2d5a0ecb8347d7c6e96f00 | 2023-12-14T17:05:46 | https://www.reddit.com/r/LocalLLaMA/comments/18id9e0/we_would_theorically_compress_mixtral_up_to_4gb/ | Wonderful_Ad_5134 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 18id9e0 | false | null | t3_18id9e0 | /r/LocalLLaMA/comments/18id9e0/we_would_theorically_compress_mixtral_up_to_4gb/ | false | false | 218 | {'enabled': False, 'images': [{'id': 'bri4lOOz9KOTnlKfouPgFxU3AUF1nFX9EOESuHn9xDE', 'resolutions': [{'height': 54, 'url': 'https://external-preview.redd.it/Lv_-f0Hq4KeIGOubtK_-bJKAChAcDU_V2n_WOm_nCL4.jpg?width=108&crop=smart&auto=webp&s=a5dd88dab7bab3177a2a207e533ec43cb222a605', 'width': 108}, {'height': 108, 'url': 'h... | |
Experimenting with LLM-assisted scoring: eval results | 23 | Hi llama friends, we are an early-stage AI startup. I wanted to share some results we obtained using our LLM-assisted batch evaluation tool.
Below I present results for three evaluation tasks:
* Highlight extraction from news articles
* MMLU benchmark using scoring model
* JSON schema validation
The batch eval tool ... | 2023-12-14T16:55:32 | https://www.reddit.com/r/LocalLLaMA/comments/18id0pa/experimenting_with_llmassisted_scoring_eval/ | neutralino1 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 18id0pa | false | null | t3_18id0pa | /r/LocalLLaMA/comments/18id0pa/experimenting_with_llmassisted_scoring_eval/ | false | false | self | 23 | {'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 good tutorials for setting up Google Gemini's API? | 1 | [removed] | 2023-12-14T16:05:23 | https://www.reddit.com/r/LocalLLaMA/comments/18ibwo4/any_good_tutorials_for_setting_up_google_geminis/ | TheHunter920 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 18ibwo4 | false | null | t3_18ibwo4 | /r/LocalLLaMA/comments/18ibwo4/any_good_tutorials_for_setting_up_google_geminis/ | false | false | self | 1 | null |
Fine-tuning a model on books | 13 | So as title states, I want to train an open source (probably Mistral!) model on a few books. I have extracted the text from their pdf's and realized there might be many ways that could result in different effects. The books are collections of essays. Basically, at the end of each essay there is an analysis written by a... | 2023-12-14T15:57:19 | https://www.reddit.com/r/LocalLLaMA/comments/18ibq2i/finetuning_a_model_on_books/ | LetterheadWaste8170 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 18ibq2i | false | null | t3_18ibq2i | /r/LocalLLaMA/comments/18ibq2i/finetuning_a_model_on_books/ | false | false | self | 13 | null |
case closed? https://github.com/microsoft/promptbase | 63 | 2023-12-14T15:56:46 | LyPreto | i.redd.it | 1970-01-01T00:00:00 | 0 | {} | 18ibpnx | false | null | t3_18ibpnx | /r/LocalLLaMA/comments/18ibpnx/case_closed_httpsgithubcommicrosoftpromptbase/ | false | false | 63 | {'enabled': True, 'images': [{'id': 'W8Oy_H1JC3QUk8SWoapo8jMZhcUZ78XIjpmrz1D85dI', 'resolutions': [{'height': 53, 'url': 'https://preview.redd.it/9z8njpst8a6c1.png?width=108&crop=smart&auto=webp&s=e1c28ca5b849e6a5551ecd7251854db9a081f69a', 'width': 108}, {'height': 106, 'url': 'https://preview.redd.it/9z8njpst8a6c1.png... | |||
How is Perplexity doing the internet search? | 8 | Perplexity is such a great product, I’m curious as to how they’re able to have their LLM have real-time answers. Is it just web crawlers and RAG? | 2023-12-14T15:55:50 | https://www.reddit.com/r/LocalLLaMA/comments/18iboyt/how_is_perplexity_doing_the_internet_search/ | shafinlearns2jam | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 18iboyt | false | null | t3_18iboyt | /r/LocalLLaMA/comments/18iboyt/how_is_perplexity_doing_the_internet_search/ | false | false | self | 8 | null |
How can I determine my hardware requirements (especially VRAM) for fine-tuning a LLM with a PEFT method? Is there a formula? | 2 | Let's say I have a 13B Llama and I want to fine-tune it with LoRA (rank=32). Can I somehow determine how much VRAM I need to do so?
I reckon it should be something like: Base VRAM for Llama model + LoRA params + LoRA gradients. But I don't know how to determine each of these variables. | 2023-12-14T15:44:19 | https://www.reddit.com/r/LocalLLaMA/comments/18ibg5i/how_can_i_determine_my_hardware_requirements/ | a_fish1 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 18ibg5i | false | null | t3_18ibg5i | /r/LocalLLaMA/comments/18ibg5i/how_can_i_determine_my_hardware_requirements/ | false | false | self | 2 | null |
D: What prompts do you use to evaluate new LLM capabilities? | 22 | What prompts do you use to evaluate new LLM capabilities?
Do you have a series of standard prompts you use to see what an LLM can do?
What things have you found the most useful for overall evaluation?
| 2023-12-14T15:27:59 | https://www.reddit.com/r/LocalLLaMA/comments/18ib3pr/d_what_prompts_do_you_use_to_evaluate_new_llm/ | head_robotics | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 18ib3pr | false | null | t3_18ib3pr | /r/LocalLLaMA/comments/18ib3pr/d_what_prompts_do_you_use_to_evaluate_new_llm/ | false | false | self | 22 | null |
Best way to do guided generation in your experience? | 3 | I'm currently using Outlines but I'm looking for other options with wider model support and more faster development.
I need to make the model generate JSON responses based on a given schema. And I want to limit the possible options for some JSON fields to be selected from a given list. | 2023-12-14T15:02:05 | https://www.reddit.com/r/LocalLLaMA/comments/18iajgp/best_way_to_do_guided_generation_in_your/ | ammar- | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 18iajgp | false | null | t3_18iajgp | /r/LocalLLaMA/comments/18iajgp/best_way_to_do_guided_generation_in_your/ | false | false | self | 3 | null |
[VIDEO] 6 Ways For Running A Local LLM (aka how to use HuggingFace) | 2 | 2023-12-14T14:39:12 | https://semaphoreci.com/blog/local-llm | tomasfern | semaphoreci.com | 1970-01-01T00:00:00 | 0 | {} | 18ia1wz | false | null | t3_18ia1wz | /r/LocalLLaMA/comments/18ia1wz/video_6_ways_for_running_a_local_llm_aka_how_to/ | false | false | 2 | {'enabled': False, 'images': [{'id': '7bFRWt1RrSstrR_aX43d5HyR_T6IGIYuCZAI4jXZy_U', 'resolutions': [{'height': 60, 'url': 'https://external-preview.redd.it/Dnv69IJuTDlSzBOHlB5Qi4NQHvOUmrAAPFhTTErkuxQ.jpg?width=108&crop=smart&auto=webp&s=43a3f357a6fb2fbb9973b90ebe8251bdb626d9fb', 'width': 108}, {'height': 121, 'url': 'h... | ||
How do I get local LLMs to return keywords? | 5 | Before I start, I just want to say that I know that NER is the accepted best method for pure keyword extraction. However, the *type* of keywords I'm generating are more like concept categories, so NER is (afaik) not as well-suited to the task.
But so far, Llama2 70b Chat and its derivatives are the only models I ca... | 2023-12-14T14:12:28 | https://www.reddit.com/r/LocalLLaMA/comments/18i9hj4/how_do_i_get_local_llms_to_return_keywords/ | orrorin6 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 18i9hj4 | false | null | t3_18i9hj4 | /r/LocalLLaMA/comments/18i9hj4/how_do_i_get_local_llms_to_return_keywords/ | false | false | self | 5 | null |
Instead of high censor A.I, why not other approach? Evolution of improve logical Asimov Laws | 1 | [removed] | 2023-12-14T14:00:45 | https://www.reddit.com/r/LocalLLaMA/comments/18i98q1/instead_of_high_censor_ai_why_not_other_approach/ | maxpayne07 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 18i98q1 | false | null | t3_18i98q1 | /r/LocalLLaMA/comments/18i98q1/instead_of_high_censor_ai_why_not_other_approach/ | false | false | self | 1 | null |
GPT-4.5 leaked by OpenAI? | 1 | Is it legit? Source:
https://www.linkedin.com/posts/thomasdordonne_breaking-openai-just-leaked-gpt-45-the-activity-7141036190605959168-d8e3?utm_source=share&utm_medium=member_ios | 2023-12-14T13:43:41 | Shoddy_Vegetable_115 | i.redd.it | 1970-01-01T00:00:00 | 0 | {} | 18i8wim | false | null | t3_18i8wim | /r/LocalLLaMA/comments/18i8wim/gpt45_leaked_by_openai/ | false | false | 1 | {'enabled': True, 'images': [{'id': '-nJxc5LKudwszTrn-dhPxmKNJmtnI3KEpxhkg_Hm-vg', 'resolutions': [{'height': 216, 'url': 'https://preview.redd.it/nr6rhf48l96c1.jpg?width=108&crop=smart&auto=webp&s=5895cf0da221927a8b6db474303328367652189c', 'width': 108}, {'height': 432, 'url': 'https://preview.redd.it/nr6rhf48l96c1.jp... | ||
gpt4all returns number instead of text | 1 | I am trying out gpt4all for the first time locally.
I am just using the code from their [https://docs.gpt4all.io/gpt4all\_python.html](https://docs.gpt4all.io/gpt4all_python.html)
from gpt4all import GPT4All
model = GPT4All("orca-mini-3b-gguf2-q4_0.gguf")
output = model.generate("The capital of France is... | 2023-12-14T13:33:50 | https://www.reddit.com/r/LocalLLaMA/comments/18i8pu5/gpt4all_returns_number_instead_of_text/ | 31NF4CHZ4H73N | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 18i8pu5 | false | null | t3_18i8pu5 | /r/LocalLLaMA/comments/18i8pu5/gpt4all_returns_number_instead_of_text/ | false | false | self | 1 | null |
Mixtral 7B, 8x7B: enlightenment ? | 1 | With my M1 8gb Macbook pro, I was able to run, not so easily llama2 7B with llama.cpp.
I'd like to try Mixtral but saw there were two versions: 7B and 8x7B which compares to GPT 3.5.
Is 8x7B the equivalent of a 56B parameters model or is it just larger but not more expensive for interference ? | 2023-12-14T13:19:19 | https://www.reddit.com/r/LocalLLaMA/comments/18i8gar/mixtral_7b_8x7b_enlightenment/ | CJAgln | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 18i8gar | false | null | t3_18i8gar | /r/LocalLLaMA/comments/18i8gar/mixtral_7b_8x7b_enlightenment/ | false | false | self | 1 | null |
gemini-pro censorship | 1 | 2023-12-14T13:02:30 | Timotheeee1 | i.redd.it | 1970-01-01T00:00:00 | 0 | {} | 18i85jz | false | null | t3_18i85jz | /r/LocalLLaMA/comments/18i85jz/geminipro_censorship/ | false | false | 1 | {'enabled': True, 'images': [{'id': 'ARFtCOnJlNtfe4Xaa57LEgZtCXl_hOwb0a6gfUTdMXc', 'resolutions': [{'height': 117, 'url': 'https://preview.redd.it/a13ju20td96c1.png?width=108&crop=smart&auto=webp&s=b60f753b1146f36651d7ba99173d949eea275afd', 'width': 108}, {'height': 235, 'url': 'https://preview.redd.it/a13ju20td96c1.pn... | |||
In LM studio, is there a way to get details as to why an LLM 'crashed'? | 1 | I use lmstudio and local lms ahead of a presentation on Ai+medecine I'm giving soon. I have 8gb vram on a 3070, and i load medical models , 7b (meditron for example) quantization set to 4M. They should (and do) fit entirely in vram since they weight only 4.5GB. Single thread as recommended here.
For some reason, rega... | 2023-12-14T13:00:33 | https://www.reddit.com/r/LocalLLaMA/comments/18i840i/in_lm_studio_is_there_a_way_to_get_details_as_to/ | memory_moves | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 18i840i | false | null | t3_18i840i | /r/LocalLLaMA/comments/18i840i/in_lm_studio_is_there_a_way_to_get_details_as_to/ | false | false | self | 1 | null |
Site with the ranking of 13b models | 1 | Is there a website that updates the ranking of the best RP models in categories 7b, 13b or 20b? | 2023-12-14T12:52:24 | https://www.reddit.com/r/LocalLLaMA/comments/18i7yyg/site_with_the_ranking_of_13b_models/ | LonleyPaladin | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 18i7yyg | false | null | t3_18i7yyg | /r/LocalLLaMA/comments/18i7yyg/site_with_the_ranking_of_13b_models/ | false | false | self | 1 | null |
Advanced Prompt Engineering Techniques: Airline Example | 1 | [removed] | 2023-12-14T12:48:20 | https://www.reddit.com/r/LocalLLaMA/comments/18i7wj5/advanced_prompt_engineering_techniques_airline/ | MiNeves | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 18i7wj5 | false | null | t3_18i7wj5 | /r/LocalLLaMA/comments/18i7wj5/advanced_prompt_engineering_techniques_airline/ | false | false | self | 1 | {'enabled': False, 'images': [{'id': 'LSGUrs26uY7cTzSgkDkEwLOQL-tclMWlEiBP3rdrjSc', 'resolutions': [{'height': 141, 'url': 'https://external-preview.redd.it/zE0OIyWeBA_5q_2qO3hw2l3uD8jQvIOyxYtcr5Jup4o.jpg?width=108&crop=smart&auto=webp&s=5b4da191aa095b7dacc029607d1f8eb4f79737c6', 'width': 108}, {'height': 282, 'url': '... |
Llama2 speeds | 1 | [removed] | 2023-12-14T12:30:30 | https://www.reddit.com/r/LocalLLaMA/comments/18i7lxn/llama2_speeds/ | ramzeez88 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 18i7lxn | false | null | t3_18i7lxn | /r/LocalLLaMA/comments/18i7lxn/llama2_speeds/ | false | false | self | 1 | null |
Just got access to Mistral's API | 13 | Maybe others have too or will soon, but if not I definitely suggest registering with a professional sounding email address, i.e. void ones which contain the characters hack3r and pr0n. | 2023-12-14T12:15:40 | https://www.reddit.com/r/LocalLLaMA/comments/18i7dcz/just_got_access_to_mistrals_api/ | WaterdanceAC | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 18i7dcz | false | null | t3_18i7dcz | /r/LocalLLaMA/comments/18i7dcz/just_got_access_to_mistrals_api/ | false | false | self | 13 | null |
What is the simplest available local interface, to use openai or a local llm, with history and function calling? | 2 | Hello everyone, i'm nto super experienced in the world of llms, i wrote and run some code with langchain, but i lack a more in depth understanding of it.
I was searching the simplest way to set up a ui, with history that would be able with the openai api first, and maybe when it's easier, with other opensource llms, ... | 2023-12-14T11:53:01 | https://www.reddit.com/r/LocalLLaMA/comments/18i705v/what_is_the_simplest_available_local_interface_to/ | Ok_Dog_5421 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 18i705v | false | null | t3_18i705v | /r/LocalLLaMA/comments/18i705v/what_is_the_simplest_available_local_interface_to/ | false | false | self | 2 | null |
Best (new) LLM model format to run on Apple Silicon? | 3 | With model formats like GGUF/AWQ/EXL2 and recently talked about formats with optimized quantisation like HQQ and QuiP# I am not really sure what is currently considered the best option on Mac M1/M2/M3 machines.
Are there better (faster / lower VRAM requirements) formats out there for Mac's?
Have been using GGML and l... | 2023-12-14T11:45:30 | https://www.reddit.com/r/LocalLLaMA/comments/18i6vta/best_new_llm_model_format_to_run_on_apple_silicon/ | Zestyclose_Yak_3174 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 18i6vta | false | null | t3_18i6vta | /r/LocalLLaMA/comments/18i6vta/best_new_llm_model_format_to_run_on_apple_silicon/ | false | false | self | 3 | null |
What are you using your local LLM for? | 1 | I just downloaded the new SOLAR10.7 model and it's awesome. But I'm trying to think of use cases for it. I'd love to fine tune it as well. I'm just confused what I could use a local LLM for that wouldn't be simpler with ChatGPT3.5.
What are you all using your local LLMs for? | 2023-12-14T11:23:52 | https://www.reddit.com/r/LocalLLaMA/comments/18i6joh/what_are_you_using_your_local_llm_for/ | PMMEYOURSMIL3 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 18i6joh | false | null | t3_18i6joh | /r/LocalLLaMA/comments/18i6joh/what_are_you_using_your_local_llm_for/ | false | false | self | 1 | null |
Local Stable Diffusion | 2 | Not the place to ask, I know.
Are there any good stable diffusion models that can run on mobile devices with ~4GB ram | 2023-12-14T11:06:08 | https://www.reddit.com/r/LocalLLaMA/comments/18i6adi/local_stable_diffusion/ | Jsus-Sus | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 18i6adi | false | null | t3_18i6adi | /r/LocalLLaMA/comments/18i6adi/local_stable_diffusion/ | false | false | self | 2 | null |
How does fine tuning Mixtral works ? | 12 | Hi, if I understood the MOE architecture, there is multiple specialist models (one in code, math, etc..) who works for the best input use case.
But why doesn't fine tuning all the specialists models makes them all more "generalist" ? Why wouldn't it just be a sort of merge between two fine tuned mistral ?
I just want... | 2023-12-14T11:02:51 | https://www.reddit.com/r/LocalLLaMA/comments/18i68na/how_does_fine_tuning_mixtral_works/ | M0ULINIER | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 18i68na | false | null | t3_18i68na | /r/LocalLLaMA/comments/18i68na/how_does_fine_tuning_mixtral_works/ | false | false | self | 12 | null |
Your Mixtral Experiences So Far | 29 | Alright, I got it working in my llama.cpp/llama-cpp-python chat tool and was wondering about two major problems, that I hope anybody can help me figure out.
1. It seems that it takes way too long to process a longer prompt before starting the inference (which itself has a nice speed) - in my case it takes around 39 (!... | 2023-12-14T10:35:34 | https://www.reddit.com/r/LocalLLaMA/comments/18i5u6d/your_mixtral_experiences_so_far/ | psi-love | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 18i5u6d | false | null | t3_18i5u6d | /r/LocalLLaMA/comments/18i5u6d/your_mixtral_experiences_so_far/ | false | false | 29 | null | |
Mixtral idea. 3x7B. All focused on one subject. | 2 | How cool would it be to have 3 out of 3 experts, all knowledgeable on the same subject. It probably would be more efficient and possibly smarter? 🤔 | 2023-12-14T10:31:12 | https://www.reddit.com/r/LocalLLaMA/comments/18i5rv7/mixtral_idea_3x7b_all_focused_on_one_subject/ | Majestical-psyche | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 18i5rv7 | false | null | t3_18i5rv7 | /r/LocalLLaMA/comments/18i5rv7/mixtral_idea_3x7b_all_focused_on_one_subject/ | false | false | self | 2 | null |
Windows AI Studio - Offical Local Finetuning GUI in Windows machines! | 37 | 2023-12-14T10:13:22 | https://github.com/microsoft/windows-ai-studio | phoneixAdi | github.com | 1970-01-01T00:00:00 | 0 | {} | 18i5imw | false | null | t3_18i5imw | /r/LocalLLaMA/comments/18i5imw/windows_ai_studio_offical_local_finetuning_gui_in/ | false | false | 37 | {'enabled': False, 'images': [{'id': 'Hh3XgcoYOnoroqXdnGOEdx91MXczBke6a9w0FBh9PnE', 'resolutions': [{'height': 54, 'url': 'https://external-preview.redd.it/Qltn2_-ZVca2FToBNQacpD7BwEACNx7qeX_ZGWmk9WA.jpg?width=108&crop=smart&auto=webp&s=f87dec6ecd9deb7f5d5d876b6d86cda2502ae849', 'width': 108}, {'height': 108, 'url': 'h... | ||
To RAG or not to RAG | 46 | **TL,DR:** how can my chatbot decide when it is necessary to retrieve context, and when it should answer based solely on the chat history?
Beloved redditors,
So we have a functioning RAG Chatbot. If you activate “Search Mode”, the system will retrieve query-relevant chunks and a prompt of the type “Answer the query {... | 2023-12-14T09:57:32 | https://www.reddit.com/r/LocalLLaMA/comments/18i5ahe/to_rag_or_not_to_rag/ | madway99 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 18i5ahe | false | null | t3_18i5ahe | /r/LocalLLaMA/comments/18i5ahe/to_rag_or_not_to_rag/ | false | false | self | 46 | {'enabled': False, 'images': [{'id': 'o7Dosh9cTSgHs5fYow3Bq4otthpg-q3a4Nqdtg78jUw', 'resolutions': [{'height': 60, 'url': 'https://external-preview.redd.it/5oK9zc2JrJRfaoJ6u65hVIkqvcTq-WMKxpe95j5uJnk.jpg?width=108&crop=smart&auto=webp&s=4bd6b55fccca33dda41d8cf0f15820cb9eaf900d', 'width': 108}, {'height': 121, 'url': 'h... |
Has anyone successfully run vision models on the apple m2 chip with 16gb ram? | 1 | I've been using LM Studio to prototype some things quickly before I move to cloud resources for production workloads. This works great even with the under powered macbook air I have been using as my daily driver. Today I tried some OCR workflows with the new vision capability in LM Studio and it just times out/ hangs (... | 2023-12-14T09:47:58 | https://www.reddit.com/r/LocalLLaMA/comments/18i562a/has_anyone_successfully_run_vision_models_on_the/ | rorykoehler | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 18i562a | false | null | t3_18i562a | /r/LocalLLaMA/comments/18i562a/has_anyone_successfully_run_vision_models_on_the/ | false | false | self | 1 | null |
microsoft / LLMLingua: To speed up LLMs' inference and enhance LLM's perceive of key information, compress the prompt and achieve up to 20x compression with minimal performance loss. | 1 | What's LLMLingua? LLMLingua balls lmao | 2023-12-14T09:04:06 | https://github.com/microsoft/LLMLingua | StewArtMedia_Nick | github.com | 1970-01-01T00:00:00 | 0 | {} | 18i4kb5 | false | null | t3_18i4kb5 | /r/LocalLLaMA/comments/18i4kb5/microsoft_llmlingua_to_speed_up_llms_inference/ | false | false | 1 | {'enabled': False, 'images': [{'id': 'gHZMFGAshj7Z6zsnSQoMn6VJfQtP6Vz7gxE7TxY6zWU', 'resolutions': [{'height': 54, 'url': 'https://external-preview.redd.it/_BdP_Y_9VGazXPFJ-e9nZhs3I_anV2-eE6vThAsTMV4.jpg?width=108&crop=smart&auto=webp&s=23bb9605bc83a32e3f64d380944cdee5297750f4', 'width': 108}, {'height': 108, 'url': 'h... | |
A first merged 10.7B model with Solar | 18 | This model uses the SLERP method to merge the best models on 14th Dec on OpenLLM Leaderboard: SOLAR-10.7B-Instruct-v1.0 with our latest Pandora-10.7B model. The results? It increases chat capabilities and GSM8K score for the original model.
Model: [janhq/Solar-10.7B-SLERP · Hugging Face](https://huggingface.co/janhq/... | 2023-12-14T08:16:12 | https://www.reddit.com/r/LocalLLaMA/comments/18i3xmi/a_first_merged_107b_model_with_solar/ | Own_Procedure_8866 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 18i3xmi | false | null | t3_18i3xmi | /r/LocalLLaMA/comments/18i3xmi/a_first_merged_107b_model_with_solar/ | false | false | self | 18 | {'enabled': False, 'images': [{'id': 'kA7es_T5rzI6FwOBEhVRRdc4YUSBR36aRusv6M_n2hQ', 'resolutions': [{'height': 58, 'url': 'https://external-preview.redd.it/zIyrVUpsvmNPEXOGCNBkxY6TXi5Dbn0TSRDaU0Nm0so.jpg?width=108&crop=smart&auto=webp&s=996239fa1913e6f369e3832e4dd8e53c69508228', 'width': 108}, {'height': 116, 'url': 'h... |
A first merged 10.7B model with Solar. | 1 | [deleted] | 2023-12-14T08:14:47 | [deleted] | 1970-01-01T00:00:00 | 0 | {} | 18i3wvd | false | null | t3_18i3wvd | /r/LocalLLaMA/comments/18i3wvd/a_first_merged_107b_model_with_solar/ | false | false | default | 1 | null | ||
Where can I host models and pay per usage? | 3 | Hey guys, is there a place I can host my own fine tuned open source model and pay per thousand tokens with an API? I know anyscale kinda does this but they’ve got only got llama currently | 2023-12-14T08:13:22 | https://www.reddit.com/r/LocalLLaMA/comments/18i3w6a/where_can_i_host_models_and_pay_per_usage/ | Leadership_Upper | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 18i3w6a | false | null | t3_18i3w6a | /r/LocalLLaMA/comments/18i3w6a/where_can_i_host_models_and_pay_per_usage/ | false | false | self | 3 | null |
Besides curiosity, what do you use local LLMs for? | 28 | I'm interested in seeing what people's use cases are. I imagine privacy and lenience or absence of guardrails are likely primary considerations.
I see potential for use as an offline resource. For instance if your WiFi broke down, an LLM could help you troubleshoot it but then again people typically have phone data as... | 2023-12-14T08:06:02 | https://www.reddit.com/r/LocalLLaMA/comments/18i3siw/besides_curiosity_what_do_you_use_local_llms_for/ | RedditPolluter | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 18i3siw | false | null | t3_18i3siw | /r/LocalLLaMA/comments/18i3siw/besides_curiosity_what_do_you_use_local_llms_for/ | false | false | self | 28 | null |
Lost in the LLM Labyrinth: Looking For Guidance on Evaluation Tools! | 7 | Fellow AI enthusiasts, I'm knee-deep in the fascinating world of Large Language Models (LLMs) and eager to assess their capabilities. But the sheer variety of evaluation tools has me feeling like Alice tumbling down the rabbit hole! ️
I'm particularly interested in:
* **Accuracy & Factuality:** How well do LLMs handl... | 2023-12-14T08:03:50 | https://www.reddit.com/r/LocalLLaMA/comments/18i3rd3/lost_in_the_llm_labyrinth_looking_for_guidance_on/ | DwaywelayTOP | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 18i3rd3 | false | null | t3_18i3rd3 | /r/LocalLLaMA/comments/18i3rd3/lost_in_the_llm_labyrinth_looking_for_guidance_on/ | false | false | self | 7 | null |
Gemini Pro is quite lenient | 1 | [removed] | 2023-12-14T07:28:37 | [deleted] | 1970-01-01T00:00:00 | 0 | {} | 18i39j8 | false | null | t3_18i39j8 | /r/LocalLLaMA/comments/18i39j8/gemini_pro_is_quite_lenient/ | false | false | default | 1 | null | ||
ehartford/dolphin-2.5-mixtral-8x7b · Hugging Face | 74 | 2023-12-14T07:01:38 | https://huggingface.co/ehartford/dolphin-2.5-mixtral-8x7b | StewArtMedia_Nick | huggingface.co | 1970-01-01T00:00:00 | 0 | {} | 18i2w6o | false | null | t3_18i2w6o | /r/LocalLLaMA/comments/18i2w6o/ehartforddolphin25mixtral8x7b_hugging_face/ | false | false | 74 | {'enabled': False, 'images': [{'id': 'xgIFz1fUGd6JouKLJX_PA7Md58NjH5XimgdMCZQreIY', 'resolutions': [{'height': 58, 'url': 'https://external-preview.redd.it/G4BugJEpnNOWKVC98jdQsQ0YbOAdHbJnYIoTAsLC7Bw.jpg?width=108&crop=smart&auto=webp&s=834956df8cc8f1e6a12d911aa86bd330aca8bb0b', 'width': 108}, {'height': 116, 'url': 'h... | ||
Mixtral gets even better by just adding an expert. | 177 | 2023-12-14T06:34:22 | https://twitter.com/sbeastwindy/status/1735185274475524333?t=r5RVn27ptFe2SjI4zMKTTw&s=19 | Eastwindy123 | twitter.com | 1970-01-01T00:00:00 | 0 | {} | 18i2h4c | false | {'oembed': {'author_name': 'Srinivas Billa', 'author_url': 'https://twitter.com/sbeastwindy', 'cache_age': 3153600000, 'height': None, 'html': '<blockquote class="twitter-video"><p lang="en" dir="ltr">+1 expert = -1 perplexity??<br>Mixtral instruct gets even better by consulting 3 experts instead of 2 <a href="https://... | t3_18i2h4c | /r/LocalLLaMA/comments/18i2h4c/mixtral_gets_even_better_by_just_adding_an_expert/ | false | false | 177 | {'enabled': False, 'images': [{'id': 'SX8GbQsMLex5OTxq5N7BjKpL1-FzI7FblaPoU2IKDpU', 'resolutions': [{'height': 64, 'url': 'https://external-preview.redd.it/cc6Y_Nyyhcv6Y0gHw9dkhz1nlMUaC5NW0KRogRwv4Is.jpg?width=108&crop=smart&auto=webp&s=6cf1efd297c702c8a47723afeb5687f64edba68c', 'width': 108}], 'source': {'height': 84,... | ||
Using a local LLM as a user interface | 5 | I'm looking for examples of using a locally running LLM (Mixtral, LLaMA, whatever) as the user interface for a system. For example, let's say I have a home automation system, and I can turn any light in my house on or off by sending a specific JSON blob. How would I wire in an LLM to be the user interface for this syst... | 2023-12-14T06:32:30 | https://www.reddit.com/r/LocalLLaMA/comments/18i2g6f/using_a_local_llm_as_a_user_interface/ | heathkit | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 18i2g6f | false | null | t3_18i2g6f | /r/LocalLLaMA/comments/18i2g6f/using_a_local_llm_as_a_user_interface/ | false | false | self | 5 | null |
Seeking Recommendations for Tools That Autogenerate Software Projects | 1 | Hello everyone!
​
I'm on a quest to find the best tools available for automatically generating software projects. Currently, I've been using Cursor that has a feature called "New AI project," which is decent, but I'm curious if there are more options out there.
​
Has anyone come across any particularl... | 2023-12-14T06:06:28 | https://www.reddit.com/r/LocalLLaMA/comments/18i21iu/seeking_recommendations_for_tools_that/ | yachty66 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 18i21iu | false | null | t3_18i21iu | /r/LocalLLaMA/comments/18i21iu/seeking_recommendations_for_tools_that/ | false | false | self | 1 | null |
I'd just like to know if this specific RuntimeError will affect my choice of AI for the worst (like, does it turn dumb enough that I'm better off picking a smaller model?) | 2 | 2023-12-14T06:05:02 | Switchblade1080 | i.redd.it | 1970-01-01T00:00:00 | 0 | {} | 18i20m8 | false | null | t3_18i20m8 | /r/LocalLLaMA/comments/18i20m8/id_just_like_to_know_if_this_specific/ | false | false | 2 | {'enabled': True, 'images': [{'id': 'Nxd_3pCcNFpIxZUmb0BiAGSH0NJniYlmfbhfOByyWBg', 'resolutions': [{'height': 60, 'url': 'https://preview.redd.it/goore23x776c1.png?width=108&crop=smart&auto=webp&s=357fd1d5799f5f5935d9569009fcda1f2b5d2c05', 'width': 108}, {'height': 121, 'url': 'https://preview.redd.it/goore23x776c1.png... | |||
Any chance mistral open-sources their Mistral-small model? | 2 | They announced the API endpoint but didn't release the model. | 2023-12-14T05:39:29 | https://www.reddit.com/r/LocalLLaMA/comments/18i1le2/any_chance_mistral_opensources_their_mistralsmall/ | aue_sum | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 18i1le2 | false | null | t3_18i1le2 | /r/LocalLLaMA/comments/18i1le2/any_chance_mistral_opensources_their_mistralsmall/ | false | false | self | 2 | null |
Subsets and Splits
No community queries yet
The top public SQL queries from the community will appear here once available.