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 ⌀ |
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
i need help with kobold | 1 | i followed a guide i saw on reddit on how to use koboldcpp, i did everything as the guy said and it still didnt work for me. when i press launch after choosing the model nothing happens, can someone please help me out? | 2023-12-03T23:57:45 | https://www.reddit.com/r/LocalLLaMA/comments/18a7656/i_need_help_with_kobold/ | Specialist-Paint8081 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 18a7656 | false | null | t3_18a7656 | /r/LocalLLaMA/comments/18a7656/i_need_help_with_kobold/ | false | false | self | 1 | null |
Goliath120B.exl2 way too emotional | 1 | I'm using 4.5bpw quant courtesy u/Panchovix for RP.
Every time we speak about loneliness, lost love or something like this, it start t-to... s-speak... \*sob\* speak like... this.
And I can't find a way to recover the conversation from this state. The narrations are fine, only character's speech is affected. It espe... | 2023-12-03T23:45:57 | https://www.reddit.com/r/LocalLLaMA/comments/18a6x6z/goliath120bexl2_way_too_emotional/ | Worldly-Mistake-8147 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 18a6x6z | false | null | t3_18a6x6z | /r/LocalLLaMA/comments/18a6x6z/goliath120bexl2_way_too_emotional/ | false | false | self | 1 | null |
DPO models seem to be pretty good | 20 | What is everyone's experiences so far with DPO trained versions of their favorite models? Been messing around with different models and my two new favorite models are actually just the DPO versions of my previous favorite models (causalLM 14b and openhermes 2.5 7b). Links below for the models in question.
CausalLM 14B... | 2023-12-03T23:26:45 | https://www.reddit.com/r/LocalLLaMA/comments/18a6iwu/dpo_models_seem_to_be_pretty_good/ | lemon07r | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 18a6iwu | false | null | t3_18a6iwu | /r/LocalLLaMA/comments/18a6iwu/dpo_models_seem_to_be_pretty_good/ | false | false | self | 20 | {'enabled': False, 'images': [{'id': 'tLEG5EtbsFu5jP6NMXOM-qSJcCIDUkOL-vOTfNIkxR4', 'resolutions': [{'height': 58, 'url': 'https://external-preview.redd.it/YvvcjTrCcjaVVxn-U_-Fht1Cgm6Fo63AjOxXJotXhZ0.jpg?width=108&crop=smart&auto=webp&s=dc9b79918eba0d17ba7c87287ac626a991604e0f', 'width': 108}, {'height': 116, 'url': 'h... |
Running Multiple WebUI instances (follow up from my question yesterday) | 1 | It's working great so far. Just wanted to share and spread awareness that running multiple instances of webui (oobabooga) is basically a matter of ram. I just finished running three models simultaneously (taking turns of course). Only offloaded one layer to gpu per model, used 5 threads per model, and all contexts were... | 2023-12-03T23:02:09 | https://www.reddit.com/r/LocalLLaMA/comments/18a5zso/running_multiple_webui_instances_follow_up_from/ | multiverse_fan | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 18a5zso | false | null | t3_18a5zso | /r/LocalLLaMA/comments/18a5zso/running_multiple_webui_instances_follow_up_from/ | false | false | 1 | {'enabled': False, 'images': [{'id': 'veE04iaMbgI4yLvLGj2IZNV7UQfnq3n_7BmxP28dCd8', 'resolutions': [{'height': 54, 'url': 'https://external-preview.redd.it/BGOGS7KdVHomyGu2FIFx85nsQDLp_fpWWBKXxvtudf4.jpg?width=108&crop=smart&auto=webp&s=0e594332595e82a5118e08d35a2cd140c18d7571', 'width': 108}, {'height': 108, 'url': 'h... | |
Is this how Skynet starts? (LLama2 13b) | 0 | You
could ai take over humanity
​
​
AI
That's an interesting question! However, I must clarify that my purpose is to assist and augment human abilities, rather than to replace or dominate them. AI systems like myself are designed to help solve complex problems and automate repetitive tasks, freeing u... | 2023-12-03T22:56:58 | https://www.reddit.com/r/LocalLLaMA/comments/18a5vpx/is_this_how_skynet_starts_llama2_13b/ | achbob84 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 18a5vpx | false | null | t3_18a5vpx | /r/LocalLLaMA/comments/18a5vpx/is_this_how_skynet_starts_llama2_13b/ | false | false | default | 0 | null |
Why Starling RLAIF has better results that Zephyr DPO ? | 3 | Based on this image:
https://preview.redd.it/z5vf03e8r54c1.png?width=648&format=png&auto=webp&s=0a652e76ab2489135ed2327e8156029eacf274b7
Starling has better results than Zephyr DPO in all the metrics, Why ?
Shouldn't DPO be better than RLHF/RLAIF ? | 2023-12-03T22:43:14 | https://www.reddit.com/r/LocalLLaMA/comments/18a5ksn/why_starling_rlaif_has_better_results_that_zephyr/ | Puzzleheaded_Mall546 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 18a5ksn | false | null | t3_18a5ksn | /r/LocalLLaMA/comments/18a5ksn/why_starling_rlaif_has_better_results_that_zephyr/ | false | false | 3 | null | |
Autonomous AI Chatbot | 6 | I have created a small chatbot in Python that utilizes text-to-speech (TTS) to speak and I use 7b and 13b models (which is the limit of my GPU).
I would like to enable my chatbot to speak autonomously without the need to initiate a conversation first. I want it to be capable of sharing thoughts, initiating conversatio... | 2023-12-03T22:33:21 | https://www.reddit.com/r/LocalLLaMA/comments/18a5d0l/autonomous_ai_chatbot/ | Asleep_Aerie_4591 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 18a5d0l | false | null | t3_18a5d0l | /r/LocalLLaMA/comments/18a5d0l/autonomous_ai_chatbot/ | false | false | self | 6 | null |
"Tess-M-v1.1 is the 5th best open source model in the world" | 35 | 2023-12-03T22:29:29 | https://twitter.com/migtissera/status/1731211762425597954 | Puzzleheaded_Mall546 | twitter.com | 1970-01-01T00:00:00 | 0 | {} | 18a59th | false | {'oembed': {'author_name': 'Migel Tissera', 'author_url': 'https://twitter.com/migtissera', 'cache_age': 3153600000, 'height': None, 'html': '<blockquote class="twitter-video"><p lang="en" dir="ltr">Tess-M-v1.1 is currently the 5th best open source model in the world. No. 1-4 are 70B models, while Tess-M is a 34B model... | t3_18a59th | /r/LocalLLaMA/comments/18a59th/tessmv11_is_the_5th_best_open_source_model_in_the/ | false | false | 35 | {'enabled': False, 'images': [{'id': 'mljQ9t-PNxkcX__E2omdOY7giOQKXxHABfIIX-uJKzE', 'resolutions': [{'height': 36, 'url': 'https://external-preview.redd.it/Be2-9hKBc0lSav3qNSXataTEwpnLu9S5Dhdo1T3ETk0.jpg?width=108&crop=smart&auto=webp&s=719ea533a2318f3cbbd3e9014ba11178bb3fc534', 'width': 108}], 'source': {'height': 47,... | ||
Hi Team | 1 | I have not been keeping up, too busy following the overall drama within the industry, I was looking for anyone who has been deep in new models since 2 weeks ago. (hopefully lots of new models and datasets available)
Has anyone found a model that can reliably take in data and regurgitate it exactly, I know there are st... | 2023-12-03T21:45:55 | https://www.reddit.com/r/LocalLLaMA/comments/18a4ajw/hi_team/ | randomrealname | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 18a4ajw | false | null | t3_18a4ajw | /r/LocalLLaMA/comments/18a4ajw/hi_team/ | false | false | self | 1 | null |
will the point meet in 2024? | 101 | 2023-12-03T21:32:37 | bull_shit123 | i.redd.it | 1970-01-01T00:00:00 | 0 | {} | 18a3z4e | false | null | t3_18a3z4e | /r/LocalLLaMA/comments/18a3z4e/will_the_point_meet_in_2024/ | false | false | 101 | {'enabled': True, 'images': [{'id': '-3fpmhDZlDUxuNvHlr7z0F_PFM2Be7goJQFTEh18J0Q', 'resolutions': [{'height': 98, 'url': 'https://preview.redd.it/o8m24lkue54c1.png?width=108&crop=smart&auto=webp&s=cfb646fe8ad6cf5e96cd26f0de40f4a490003317', 'width': 108}, {'height': 197, 'url': 'https://preview.redd.it/o8m24lkue54c1.png... | |||
Idea on how to improve Transformer models for hard problems | 1 | [removed] | 2023-12-03T20:54:29 | https://www.reddit.com/r/LocalLLaMA/comments/18a31q6/idea_on_how_to_improve_transformer_models_for/ | Few_Cantaloupe_2557 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 18a31q6 | false | null | t3_18a31q6 | /r/LocalLLaMA/comments/18a31q6/idea_on_how_to_improve_transformer_models_for/ | false | false | self | 1 | null |
LLM.swift library lets you interact LLMs on iOS easily | 16 | There are some libraries like MLC-LLM, or LLMFarm that make us run LLM on iOS devices, but none of them fits my taste, so I made another library that just works out of the box. Tested some quantized mistral-7B based models on iPad Air 5th Gen and quantized rocket-3b on iPhone 12 mini; both work fine. | 2023-12-03T20:47:12 | https://github.com/eastriverlee/LLM.swift | eastriver0720 | github.com | 1970-01-01T00:00:00 | 0 | {} | 18a2vyo | false | null | t3_18a2vyo | /r/LocalLLaMA/comments/18a2vyo/llmswift_library_lets_you_interact_llms_on_ios/ | false | false | 16 | {'enabled': False, 'images': [{'id': 'Eyfpie6M8qiPQMhIMbI8cYiAc3OyY-2VhSJExhc3m1Q', 'resolutions': [{'height': 54, 'url': 'https://external-preview.redd.it/5iocoLQGKLtQnh0vcL5BgEZd8moB3h3kDt29nVq3nnc.jpg?width=108&crop=smart&auto=webp&s=abeb5a18eac7d53f92e272e75576a99a5f51286d', 'width': 108}, {'height': 108, 'url': 'h... | |
Need help with installing AI on PC. | 1 | Hello team. I'm looking to install an AI to create text based stories with no "ethics" restrictions like chatgpt has.
Ideally, I would want these fake stories to auto-publish on WordPress , or at least in a spreadsheet.
I'm very noob never installed any AI on my PC
Can you please guide me which AI to install and ho... | 2023-12-03T20:45:41 | https://www.reddit.com/r/LocalLLaMA/comments/18a2uql/need_help_with_installing_ai_on_pc/ | Ordinary_Ad_9908 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 18a2uql | false | null | t3_18a2uql | /r/LocalLLaMA/comments/18a2uql/need_help_with_installing_ai_on_pc/ | false | false | self | 1 | null |
How to install llama.cpp version for Qwen72B? | 3 | I can't figure out how to install this. There are no step-by-step instructions for noobs like me. If anyone can help me, please post your dis in the comments or write here how to install this. | 2023-12-03T20:36:55 | https://www.reddit.com/r/LocalLLaMA/comments/18a2nmd/how_to_install_llamacpp_version_for_qwen72b/ | Secret_Joke_2262 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 18a2nmd | false | null | t3_18a2nmd | /r/LocalLLaMA/comments/18a2nmd/how_to_install_llamacpp_version_for_qwen72b/ | false | false | self | 3 | null |
I refuse to believe my MacBook M1 Pro is faster than my 2070 8Gb Super + i7 8gen (both have 16Gb ram) | 11 | While my 2070 is much faster at training CNNs and RNNs on large datasets, my MacBook is an absolute beast at running quantized LLMs and blows my gaming desktop out of the water with generation speed.
I’ve been testing a variety of quantized models on my MacBook as I build out my own internet-optional virtual assistant... | 2023-12-03T20:28:19 | https://www.reddit.com/r/LocalLLaMA/comments/18a2gmi/i_refuse_to_believe_my_macbook_m1_pro_is_faster/ | roll_left_420 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 18a2gmi | false | null | t3_18a2gmi | /r/LocalLLaMA/comments/18a2gmi/i_refuse_to_believe_my_macbook_m1_pro_is_faster/ | false | false | self | 11 | null |
Just curious, are there any GUIs for a creating LLaMA2 architecture similar to how OpenAi does "custom GPTs"? | 4 | I'm a full-stack dev and I'm about to start a AI/ML bootcamp where there's a final project.
I've been very impressed with Ollama, LLaMA2 and QLoRA. But I've also been very impressed with the UI for custom GPT but fuck the downtime on OpenAi has been increasingly worse and no real signs of improvement.
So I'm wonderi... | 2023-12-03T20:23:37 | https://www.reddit.com/r/LocalLLaMA/comments/18a2csb/just_curious_are_there_any_guis_for_a_creating/ | LivingDracula | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 18a2csb | false | null | t3_18a2csb | /r/LocalLLaMA/comments/18a2csb/just_curious_are_there_any_guis_for_a_creating/ | false | false | self | 4 | null |
Easily Train a Specialized LLM: PEFT, LoRA, QLoRA, LLaMA-Adapter, and More | 2 | 2023-12-03T20:15:38 | https://cameronrwolfe.substack.com/p/easily-train-a-specialized-llm-peft | Thistleknot | cameronrwolfe.substack.com | 1970-01-01T00:00:00 | 0 | {} | 18a268e | false | null | t3_18a268e | /r/LocalLLaMA/comments/18a268e/easily_train_a_specialized_llm_peft_lora_qlora/ | false | false | 2 | {'enabled': False, 'images': [{'id': '-I1nhN1kqbLv3RueWlmGf2aO0ubzTfCk4aABAmP6Hio', 'resolutions': [{'height': 54, 'url': 'https://external-preview.redd.it/6Y38t3NmtsnzJA7siyynzEfi8TQdGa1DobQLk8kRChE.jpg?width=108&crop=smart&auto=webp&s=715abf226eebfe37f9c7e886cfac5002894e3e30', 'width': 108}, {'height': 108, 'url': 'h... | ||
How LLM Works | 1 | [removed] | 2023-12-03T19:36:49 | https://v.redd.it/zmv3vyf7u44c1 | adesigne | v.redd.it | 1970-01-01T00:00:00 | 0 | {} | 18a19nf | false | {'reddit_video': {'bitrate_kbps': 2400, 'dash_url': 'https://v.redd.it/zmv3vyf7u44c1/DASHPlaylist.mpd?a=1704224224%2CNjM0ZDFmYTI2NmMxZDdlNWE2NTY0NGFmNzkwZDcwMDhlY2ZlYjNlNDQzM2NhYTQzMjhmZGNmMGViYzM3MDk4NA%3D%3D&v=1&f=sd', 'duration': 44, 'fallback_url': 'https://v.redd.it/zmv3vyf7u44c1/DASH_720.mp4?source=fallback', 'ha... | t3_18a19nf | /r/LocalLLaMA/comments/18a19nf/how_llm_works/ | false | false | 1 | {'enabled': False, 'images': [{'id': 'LSKzmFtMe7ItGxJc4QMzBHk5SfHnJ-bjyGbpomCmhiI', 'resolutions': [{'height': 184, 'url': 'https://external-preview.redd.it/G0ueuAF-C4VmMhmdoo_Gu7WKfRnksWqJ2v8_PoaBFoE.png?width=108&crop=smart&format=pjpg&auto=webp&s=9099f922bfc348c68c9ff7aa691acbb64be40d63', 'width': 108}, {'height': 3... | |
Extract text from PDF while retaining formatting | 1 | [removed] | 2023-12-03T19:31:25 | https://www.reddit.com/r/LocalLLaMA/comments/18a154z/extract_text_from_pdf_while_retaining_formatting/ | Tejasw__ | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 18a154z | false | null | t3_18a154z | /r/LocalLLaMA/comments/18a154z/extract_text_from_pdf_while_retaining_formatting/ | false | false | self | 1 | null |
Using old servers for LLMs | 3 | Hi there,
I have some old servers with Xeons and 128GB of RAM, and 2GB Nividia cards. There are only 250 Cuda Cores on the GPU, but some of these servers have 2 Xeons in them. All in all these are really good servers and I would love to extend there life and get some use out of them.
I have installed LMStudio on one... | 2023-12-03T19:07:16 | https://www.reddit.com/r/LocalLLaMA/comments/18a0lh7/using_old_servers_for_llms/ | Cobra-Chicken | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 18a0lh7 | false | null | t3_18a0lh7 | /r/LocalLLaMA/comments/18a0lh7/using_old_servers_for_llms/ | false | false | self | 3 | null |
Multilingual base opensource model | 8 | Hello,
If I want to further pretrain an Opensource LLM on a European language, which model should fit the best:
- Mistral 7B because it was pretrain on multilingual dataset and has very good performance.
-Llama 70B because it was also trained on multilingual dataset and can be further improved.
- Other model suggesti... | 2023-12-03T19:02:25 | https://www.reddit.com/r/LocalLLaMA/comments/18a0hoc/multilingual_base_opensource_model/ | jigodie82 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 18a0hoc | false | null | t3_18a0hoc | /r/LocalLLaMA/comments/18a0hoc/multilingual_base_opensource_model/ | false | false | self | 8 | {'enabled': False, 'images': [{'id': 's0NG3IvIn71lIrKCprYnCE-sO1mci3JiQMBrhoPzcUk', 'resolutions': [{'height': 58, 'url': 'https://external-preview.redd.it/HyGugMc_ZkhjEb8h3-WAMNrDcvoLpXgDc4eR0Gl7u1A.jpg?width=108&crop=smart&auto=webp&s=d0cfa55f89da70d45b04a8ea1121af52d2e9bec1', 'width': 108}, {'height': 116, 'url': 'h... |
Nous-Hermes-2-Vision | 111 | [New Model by Nous Research](https://huggingface.co/NousResearch/Nous-Hermes-2-Vision)
The two unique features about the model is that it has vision capabilities as well as function calling! This makes it a **Vision-Language Action Model.**
I have not tested it out but by the looks of it, it could be interesti... | 2023-12-03T18:42:10 | https://www.reddit.com/r/LocalLLaMA/comments/18a00kl/noushermes2vision/ | Nix_The_Furry | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 18a00kl | false | null | t3_18a00kl | /r/LocalLLaMA/comments/18a00kl/noushermes2vision/ | false | false | self | 111 | {'enabled': False, 'images': [{'id': 'p_CzsetvcWKiAR4V-TOP3ELKA5FVeee-pjS2WkNBynU', 'resolutions': [{'height': 58, 'url': 'https://external-preview.redd.it/va0nJnZiOzvqefS7VoRZ2oxSuIiH4aKWlplT2ceJs48.jpg?width=108&crop=smart&auto=webp&s=6d6cf0fe3bc95ff612e3993ddf3ed1a90bf6ca47', 'width': 108}, {'height': 116, 'url': 'h... |
Anyone running 3 gpus? Looking for advice on best x670 that might be able to slot a third card on. | 3 | Currently have a msi x670 carbon motherboard with 4090/3090 combo on it that works well enough, but when tinkering with ai pain to have to close it at times when friends messing with bots or stable diff, want to load up a game so was thinking since I mostly just play stuff like rimworld or dota 2 and have a 7950x3d, i ... | 2023-12-03T17:05:02 | https://www.reddit.com/r/LocalLLaMA/comments/189xvrr/anyone_running_3_gpus_looking_for_advice_on_best/ | fluffywuffie90210 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 189xvrr | false | null | t3_189xvrr | /r/LocalLLaMA/comments/189xvrr/anyone_running_3_gpus_looking_for_advice_on_best/ | false | false | self | 3 | {'enabled': False, 'images': [{'id': 'rqOFmqXYXQASRlSZC7GWvOE3J1CBuB0ySG09Ck1e3w4', 'resolutions': [{'height': 56, 'url': 'https://external-preview.redd.it/Uuf2UgRgMkq4rhTbgiyoAIbs8H94VQ5C5sgXT5Od3do.jpg?width=108&crop=smart&auto=webp&s=77f802e665e1d1f504cf935c3bc049b390f7dd80', 'width': 108}, {'height': 113, 'url': 'h... |
Visualize how GPT works | 82 | If you ever wanted to see how a language model 'thinks', this is an amazing visualization
https://bbycroft.net/llm
"A visualization and walkthrough of the LLM algorithm that backs OpenAI's ChatGPT. Explore the algorithm down to every add & multiply, seeing the whole process in action." | 2023-12-03T16:02:44 | https://www.reddit.com/r/LocalLLaMA/comments/189wjc9/visualize_how_gpt_works/ | herozorro | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 189wjc9 | false | null | t3_189wjc9 | /r/LocalLLaMA/comments/189wjc9/visualize_how_gpt_works/ | false | false | self | 82 | null |
13b models chart | 13 | Where can I find charts about top performing 13b parameters LLM models?
I am trying to download a model and run it locally which fit my PC specs
Appreciate your feedback in advanced boys | 2023-12-03T15:51:58 | https://www.reddit.com/r/LocalLLaMA/comments/189wb2x/13b_models_chart/ | qualaric | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 189wb2x | false | null | t3_189wb2x | /r/LocalLLaMA/comments/189wb2x/13b_models_chart/ | false | false | self | 13 | null |
How creating the character, give the character some specific goals and put some strong motivation into it.? | 1 | [removed] | 2023-12-03T14:50:10 | https://www.reddit.com/r/LocalLLaMA/comments/189v1jo/how_creating_the_character_give_the_character/ | Realistic_Worry_1738 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 189v1jo | false | null | t3_189v1jo | /r/LocalLLaMA/comments/189v1jo/how_creating_the_character_give_the_character/ | false | false | self | 1 | null |
How to create api for your local llm? | 2 | As the title suggests, if anyone is knowledgeable enough please do help and thank you in advance | 2023-12-03T14:49:25 | https://www.reddit.com/r/LocalLLaMA/comments/189v105/how_to_create_api_for_your_local_llm/ | Fluffy-Ad3495 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 189v105 | false | null | t3_189v105 | /r/LocalLLaMA/comments/189v105/how_to_create_api_for_your_local_llm/ | false | false | self | 2 | null |
Failed to load model Running LMStudio ? | 1 | I installed LMStudio to run LLM locally. I have Windows laptop, i5 processor, 12GB RAM, without GPU. I tried downloading multiple GGUF models I get the same error when I select it in chat window. ( I use Quantization 4bit model )
Error :
Failed to load model 'maddes8cht • NousResearch Nous Capybara V1 9 3B q4_k_... | 2023-12-03T14:12:10 | https://www.reddit.com/r/LocalLLaMA/comments/189uauo/failed_to_load_model_running_lmstudio/ | broodysupertramp | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 189uauo | false | null | t3_189uauo | /r/LocalLLaMA/comments/189uauo/failed_to_load_model_running_lmstudio/ | false | false | 1 | null | |
Intel neural-chat-7b Model Achieves Top Ranking on LLM Leaderboard | 35 | 2023-12-03T13:54:42 | https://community.intel.com/t5/Blogs/Tech-Innovation/Artificial-Intelligence-AI/Intel-neural-chat-7b-Model-Achieves-Top-Ranking-on-LLM/post/1549386 | reps_up | community.intel.com | 1970-01-01T00:00:00 | 0 | {} | 189tyqe | false | null | t3_189tyqe | /r/LocalLLaMA/comments/189tyqe/intel_neuralchat7b_model_achieves_top_ranking_on/ | false | false | 35 | {'enabled': False, 'images': [{'id': '-mLQ4CjCRDn5O0PBDZZwN_biKoYr070FXCC7ZSGbJRY', 'resolutions': [{'height': 58, 'url': 'https://external-preview.redd.it/wHVkkD2fL9xguXc7gzaNuOhNL7y9c2CZkFILGMyvS4w.jpg?width=108&crop=smart&auto=webp&s=162c281084094305e2198f4de4e5856cfa2f36a5', 'width': 108}, {'height': 116, 'url': 'h... | ||
Pretraining smaller (7B and under) LLMs using QLora with Domain Specific Knowledge | 1 | [removed] | 2023-12-03T13:53:57 | https://www.reddit.com/r/LocalLLaMA/comments/189ty7z/pretraining_smaller_7b_and_under_llms_using_qlora/ | Mammoth-Doughnut-160 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 189ty7z | false | null | t3_189ty7z | /r/LocalLLaMA/comments/189ty7z/pretraining_smaller_7b_and_under_llms_using_qlora/ | false | false | self | 1 | null |
LLM Visualization: 3D interactive model of a GPT-style LLM network running inference. | 154 | Here is an interactive tool I found on [X/Twitter](https://twitter.com/BrendanBycroft/status/1731042957149827140) made by [Brendan Bycroft](https://twitter.com/BrendanBycroft) to understand how GPT LLMs work.
​
# [LLM Visualization](https://bbycroft.net/llm)
A visualization and walkthrough of the LLM algorith... | 2023-12-03T13:15:48 | https://www.reddit.com/r/LocalLLaMA/comments/189ta65/llm_visualization_3d_interactive_model_of_a/ | nightkall | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 189ta65 | false | {'oembed': {'author_name': 'Brendan Bycroft', 'author_url': 'https://twitter.com/BrendanBycroft', 'cache_age': 3153600000, 'height': None, 'html': '<blockquote class="twitter-video"><p lang="en" dir="ltr">Project #2: LLM Visualization<br><br>So I created a web-page to visualize a small LLM, of the sort that's behin... | t3_189ta65 | /r/LocalLLaMA/comments/189ta65/llm_visualization_3d_interactive_model_of_a/ | false | false | self | 154 | {'enabled': False, 'images': [{'id': '7DhhK9q0HnLTbyulsBQZRXMwy2RG3vrX8acBC_jlKfI', 'resolutions': [{'height': 108, 'url': 'https://external-preview.redd.it/SBiUwX77kAdf0HpJPDG6ZIVMh2n5pVGbbRrcP3EiOq4.jpg?width=108&crop=smart&auto=webp&s=a5460f57c696cc6f25a9460b6e96448676e3bf26', 'width': 108}], 'source': {'height': 14... |
PSA: (exllamav2) CPU bottleneck can reduce performance by more than 25% | 18 | Purchase a good CPU, it makes a big difference. (**1.5x or greater**) If you are spending tons on GPUs, you need a high class cpu as well.
In my case, I have an AMD Ryzen 9 5950X 16-Core Processor.
My speeds:
>(bench is exl2 github readme)
- [me] 7B 4.85bpw = 100 t/s (same speed w/ Q4_K_M llama.cpp)
- [bench] 7B ... | 2023-12-03T13:10:33 | https://www.reddit.com/r/LocalLLaMA/comments/189t6ze/psa_exllamav2_cpu_bottleneck_can_reduce/ | Aaaaaaaaaeeeee | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 189t6ze | false | null | t3_189t6ze | /r/LocalLLaMA/comments/189t6ze/psa_exllamav2_cpu_bottleneck_can_reduce/ | false | false | self | 18 | {'enabled': False, 'images': [{'id': 'ex2vSKEYb-70owcjS3NsViLc-CM5yKIN08Vy07ON3xk', 'resolutions': [{'height': 41, 'url': 'https://external-preview.redd.it/-9PiQglLhYTtPzPoS_SY-Qogv_uLlJJIt4EJWhhBMfU.jpg?width=108&crop=smart&auto=webp&s=04fefcacdbba26f91b4cba8fbb5cf8f764c1376c', 'width': 108}, {'height': 83, 'url': 'ht... |
What are your best uncensored + open license models? | 1 | I suppose two categories here, with and without fine tuning on a closed license.
Needed for work. | 2023-12-03T10:34:10 | https://www.reddit.com/r/LocalLLaMA/comments/189qwfz/what_are_your_best_uncensored_open_license_models/ | learning_hedonism | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 189qwfz | false | null | t3_189qwfz | /r/LocalLLaMA/comments/189qwfz/what_are_your_best_uncensored_open_license_models/ | false | false | self | 1 | null |
How to create a commercial user personalized a llama 2 app | 1 | [removed] | 2023-12-03T10:19:00 | https://www.reddit.com/r/LocalLLaMA/comments/189qpf2/how_to_create_a_commercial_user_personalized_a/ | Agreeable-Ear-3153 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 189qpf2 | false | null | t3_189qpf2 | /r/LocalLLaMA/comments/189qpf2/how_to_create_a_commercial_user_personalized_a/ | false | false | self | 1 | null |
How well can 3060 GPU run AI models? | 1 | I fairly recently got interested into AI and am looking to run one locally, so I do apologize if anything here is incorrect, I am still learning.
I tried searching the subReddit, but either my search-fu is rusty, or there was not enough dumb downed answer for someone new as me to gleam any meaning from.
For context I... | 2023-12-03T09:49:51 | https://www.reddit.com/r/LocalLLaMA/comments/189qbhq/how_well_can_3060_gpu_run_ai_models/ | FewCommittee1814 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 189qbhq | false | null | t3_189qbhq | /r/LocalLLaMA/comments/189qbhq/how_well_can_3060_gpu_run_ai_models/ | false | false | self | 1 | null |
Meta has purchased approximately 150k H100s this year. Llama was trained on 2k A100s. The scale up here is incredible. What do you think this unlocks for Llama 3? | 479 | 2023-12-03T07:52:42 | jd_3d | i.redd.it | 1970-01-01T00:00:00 | 0 | {} | 189opkb | false | null | t3_189opkb | /r/LocalLLaMA/comments/189opkb/meta_has_purchased_approximately_150k_h100s_this/ | false | false | 479 | {'enabled': True, 'images': [{'id': 'x7c0YrIy9lTDIPTKkk_DEKsvra-RIDtvKcB64JMwk0w', 'resolutions': [{'height': 81, 'url': 'https://preview.redd.it/kwuor1tkc14c1.png?width=108&crop=smart&auto=webp&s=82ad9233b6d942b19f4ff9c20f674dfaa8b2501a', 'width': 108}, {'height': 163, 'url': 'https://preview.redd.it/kwuor1tkc14c1.png... | |||
What’s the best model I could run with my setup? | 1 | Would mainly be used for RP and writing collab.
Kobold Ai and Llama
My setup:
Win 10
Amd 5 7600x
1070 8gb
32gb ram
Thanks! | 2023-12-03T07:49:56 | https://www.reddit.com/r/LocalLLaMA/comments/189oo4j/whats_the_best_model_i_could_run_with_my_setup/ | AmericanKamikaze | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 189oo4j | false | null | t3_189oo4j | /r/LocalLLaMA/comments/189oo4j/whats_the_best_model_i_could_run_with_my_setup/ | false | false | default | 1 | null |
SYCL Support PR | 10 | There is currently a PR that begins the process of adding SYCL support to llama.cpp. I have just posted information regarding performance on Intel Arc GPUs to the PR commets. This implementation looks like it may be able to increase performance when running on Intel GPUs by nearly 10 times the current speeds.
Please ... | 2023-12-03T06:29:58 | https://github.com/ggerganov/llama.cpp/pull/2690 | it_lackey | github.com | 1970-01-01T00:00:00 | 0 | {} | 189niiw | false | null | t3_189niiw | /r/LocalLLaMA/comments/189niiw/sycl_support_pr/ | false | false | 10 | {'enabled': False, 'images': [{'id': '8CvfzxAkQCjT9aaqYOnnS-gAf9jiqOcgLR1JMFCveSY', 'resolutions': [{'height': 54, 'url': 'https://external-preview.redd.it/a9O0JjHgEfmD48HgJrSkOCmZg_opHR1sfA4esG1OChk.jpg?width=108&crop=smart&auto=webp&s=7c4146e74d34c5fc65826d7b0e6a263eb79b5999', 'width': 108}, {'height': 108, 'url': 'h... | |
What Evaluation Metrics that actually matters ? | 4 | I keep reading about open source LLMs that is on par with ChatGPT and GPT-4 but when i try them i find them far away from OpenAI's models.
The best metric i found aligning with my findings was the ELO Rating by lmsys (the authors of Vicuna).
What other metrics are used to truly evaluate LLMs and give us authentic num... | 2023-12-03T05:28:09 | https://www.reddit.com/r/LocalLLaMA/comments/189mk5r/what_evaluation_metrics_that_actually_matters/ | Diligent_Eye1248 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 189mk5r | false | null | t3_189mk5r | /r/LocalLLaMA/comments/189mk5r/what_evaluation_metrics_that_actually_matters/ | false | false | self | 4 | null |
I want some help in a PC build $1260-1600 to run 70b models | 1 | [removed] | 2023-12-03T05:24:54 | https://www.reddit.com/r/LocalLLaMA/comments/189micq/i_want_some_help_in_a_pc_build_12601600_to_run/ | Top-Weekend-357 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 189micq | false | null | t3_189micq | /r/LocalLLaMA/comments/189micq/i_want_some_help_in_a_pc_build_12601600_to_run/ | false | false | default | 1 | null |
Business Idea: Using Multimodal LLM + AI Voice Generation to make “c*ck rating as a service” | 82 | Today I learned that people pay OnlyFan girls 50-100+ for a c*ck rating 🙃. How it works is you send them a picture and select if you want a praise/honest/humiliation package to rate your c*ck.
Seems quite doable to just use a Multimodal LLM to describe the image, write the rating, then generate the whole voice use El... | 2023-12-03T04:44:24 | ai_waifu_enjoyer | i.redd.it | 1970-01-01T00:00:00 | 0 | {} | 189lu3c | false | null | t3_189lu3c | /r/LocalLLaMA/comments/189lu3c/business_idea_using_multimodal_llm_ai_voice/ | false | false | nsfw | 82 | {'enabled': True, 'images': [{'id': '1BGyOtoNtsRaobzq6pwbdKJ_m8WMGKVOI062XOGs2lg', 'resolutions': [{'height': 119, 'url': 'https://preview.redd.it/j786y9dze04c1.jpeg?width=108&crop=smart&auto=webp&s=75cb7dd8ed33475f5b0a4a5750a494dae9d3fe1b', 'width': 108}, {'height': 238, 'url': 'https://preview.redd.it/j786y9dze04c1.j... | |
Meta AI Researcher: "Big breakthrough last night. Really excited to share what we've been building with you guys soon." | 233 | Armen Aghajanyan, a research scientist at Meta AI, [tweeted](https://twitter.com/ArmenAgha/status/1731076069170835720) a few hours ago that they hit a big breakthrough last night. Unknown if it's related to LLMs or if it will even be open-sourced, but just thought I'd share here to huff some hopium with y'all. | 2023-12-03T04:10:21 | https://www.reddit.com/r/LocalLLaMA/comments/189la5z/meta_ai_researcher_big_breakthrough_last_night/ | shmishmouyes | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 189la5z | false | null | t3_189la5z | /r/LocalLLaMA/comments/189la5z/meta_ai_researcher_big_breakthrough_last_night/ | false | false | self | 233 | {'enabled': False, 'images': [{'id': 'vSAUUx2r_5oXq2PGjMpUyUJJzwAuFTRPsQ1lq1NHIKE', 'resolutions': [{'height': 108, 'url': 'https://external-preview.redd.it/6rd9ow4YiWY2BanHxuelCcIImrCHbPRN-nNr0QWexUE.jpg?width=108&crop=smart&auto=webp&s=354be3ea708d05e7f6f37d2e0d4d2678f5a7b2cf', 'width': 108}], 'source': {'height': 14... |
Best Copilot alternative | 15 | My hardware isn't the greatest in the world, but I do have an RTX A2000 (12GB) on my server running Unraid (everything containerized). I've been playing the last few days trying to find the best solution...
I have tried running the following combinations in VS Code:
* ollama + continue.dev
* ollama + [llama-coder](ht... | 2023-12-03T04:00:49 | https://www.reddit.com/r/LocalLLaMA/comments/189l422/best_copilot_alternative/ | AbleSugar | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 189l422 | false | null | t3_189l422 | /r/LocalLLaMA/comments/189l422/best_copilot_alternative/ | false | false | self | 15 | {'enabled': False, 'images': [{'id': 'veUhK6ruMmPfeveXB6geGN4RHFDtagm-Uwzrg11h2P8', 'resolutions': [{'height': 54, 'url': 'https://external-preview.redd.it/9dtAABuPXnollX50DFGO7ajftlIs_2L6FZbGZJO347k.jpg?width=108&crop=smart&auto=webp&s=0c4015fd96d5bc600ef9acbdd553f5b4efbfbb3f', 'width': 108}, {'height': 108, 'url': 'h... |
How to upgrade to the next VRAM breakpoints, and is it worth it? | 18 | Right now it seems we are once again on the cusp of another round of LLM size upgrades. It appears to me that having 24gb VRAM gets you access to a lot of really great models, but 48gb VRAM really opens the door towards the impressive 70B models and allows you to nicely run the 30B models. However, im seeing more and m... | 2023-12-03T03:35:38 | https://www.reddit.com/r/LocalLLaMA/comments/189kmj1/how_to_upgrade_to_the_next_vram_breakpoints_and/ | DominicanGreg | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 189kmj1 | false | null | t3_189kmj1 | /r/LocalLLaMA/comments/189kmj1/how_to_upgrade_to_the_next_vram_breakpoints_and/ | false | false | self | 18 | null |
Anyone have GGUF version of CausalLM DPO Alpha 14b? | 1 | [https://huggingface.co/CausalLM/14B-DPO-alpha](https://huggingface.co/CausalLM/14B-DPO-alpha)
Had good success with their original version of CausalLM 14b. Wanted to try their new alpha version of their DPO trained version. I don't think u/The-Bloke has quants of this yet.
| 2023-12-03T03:14:06 | https://www.reddit.com/r/LocalLLaMA/comments/189k6lm/anyone_have_gguf_version_of_causallm_dpo_alpha_14b/ | lemon07r | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 189k6lm | false | null | t3_189k6lm | /r/LocalLLaMA/comments/189k6lm/anyone_have_gguf_version_of_causallm_dpo_alpha_14b/ | false | false | self | 1 | {'enabled': False, 'images': [{'id': '1KpTTyxYIHuMZnG7eedIn4Mjn8RqWjLQTeACB8p6ghw', 'resolutions': [{'height': 58, 'url': 'https://external-preview.redd.it/UI4F8L9NMjBHUYByMJcfH4VWzwlogZBIW40LwhXgNns.jpg?width=108&crop=smart&auto=webp&s=a8b6076c2f4e23e370ff591bc5abac55a9446684', 'width': 108}, {'height': 116, 'url': 'h... |
3B or 7B Storytelling LLM for cheap laptop possible ? ( Dolphin ) | 2 | I want to run LLM for story writing. Is there an LLM that could run on my Laptop ? I have Intel i5 + 12GB Ram Laptop. I want to run "dolphin-2.2.1-mistral-7B" model LLM. Is it possible ? | 2023-12-03T03:00:19 | https://www.reddit.com/r/LocalLLaMA/comments/189jy28/3b_or_7b_storytelling_llm_for_cheap_laptop/ | broodysupertramp | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 189jy28 | false | null | t3_189jy28 | /r/LocalLLaMA/comments/189jy28/3b_or_7b_storytelling_llm_for_cheap_laptop/ | false | false | self | 2 | null |
Can I know what llm model is from a gguf file? | 1 | What title says: If I have a .gguf model file, is there any way to know what model is? or what information can I get from a model.gguf file?
Thanks! | 2023-12-03T02:56:15 | https://www.reddit.com/r/LocalLLaMA/comments/189jvnb/can_i_know_what_llm_model_is_from_a_gguf_file/ | julio_oa | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 189jvnb | false | null | t3_189jvnb | /r/LocalLLaMA/comments/189jvnb/can_i_know_what_llm_model_is_from_a_gguf_file/ | false | false | self | 1 | null |
Starling won't stop spitting training data! | 4 | Hello,
​
I am using LM Studio to run Starling and I am making calls to the webserver.
This is the model I am using: starling-lm-7b-alpha.Q8\_0.gguf
​
Whenever I ask Starling something it won't stop spitting output until the max number of tokens is reached and at some point it starts to hallucinate/s... | 2023-12-03T02:19:09 | https://www.reddit.com/r/LocalLLaMA/comments/189j8cj/starling_wont_stop_spitting_training_data/ | TopeQuant | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 189j8cj | false | null | t3_189j8cj | /r/LocalLLaMA/comments/189j8cj/starling_wont_stop_spitting_training_data/ | false | false | self | 4 | null |
Is it possilbe to create embeddings using LLama2 model? | 4 | Is there a way to extract the embeddings from Llama2 model? for example If input a question to LLama2 Chat - can i get the input text embedding and can i get the output text embedding? Is this possilbe? | 2023-12-03T02:05:54 | https://www.reddit.com/r/LocalLLaMA/comments/189j07o/is_it_possilbe_to_create_embeddings_using_llama2/ | kitkatmafia | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 189j07o | false | null | t3_189j07o | /r/LocalLLaMA/comments/189j07o/is_it_possilbe_to_create_embeddings_using_llama2/ | false | false | self | 4 | null |
Good open source multimodal vision models with more open licence? | 3 | Hi so I'm looking for some good vision LLM models like llava 7b but with free licence (llava is non-commercial). | 2023-12-03T01:59:34 | https://www.reddit.com/r/LocalLLaMA/comments/189iw4m/good_open_source_multimodal_vision_models_with/ | Shoddy_Vegetable_115 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 189iw4m | false | null | t3_189iw4m | /r/LocalLLaMA/comments/189iw4m/good_open_source_multimodal_vision_models_with/ | false | false | self | 3 | null |
Is there any way to train in llama.cpp but not python? | 1 | [removed] | 2023-12-03T01:21:06 | https://www.reddit.com/r/LocalLLaMA/comments/189i75s/is_there_any_way_to_train_in_llamacpp_but_not/ | Leexamp | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 189i75s | false | null | t3_189i75s | /r/LocalLLaMA/comments/189i75s/is_there_any_way_to_train_in_llamacpp_but_not/ | false | false | self | 1 | null |
New "Fast" methods? | 17 | I've seen several news articles over the past few weeks with new strategies for running LLMs more quickly, like sparse models, AWQ, etc. Is anyone able to summarize them and give pointers for which seems most promising currently? | 2023-12-03T01:08:19 | https://www.reddit.com/r/LocalLLaMA/comments/189hylz/new_fast_methods/ | romhacks | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 189hylz | false | null | t3_189hylz | /r/LocalLLaMA/comments/189hylz/new_fast_methods/ | false | false | self | 17 | null |
Modal and free fine tuning | 2 | So I've been getting to know modal.com
They have an awesome free tier which gives you $30 free usage per month and access to as many GPU's as you like with pay per second billing.
I was thinking this evening that it should be possible to setup a script to do an finetune using that free usage, I am going to try a minima... | 2023-12-03T00:06:40 | https://www.reddit.com/r/LocalLLaMA/comments/189gsz1/modal_and_free_fine_tuning/ | Feeling-Currency-360 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 189gsz1 | false | null | t3_189gsz1 | /r/LocalLLaMA/comments/189gsz1/modal_and_free_fine_tuning/ | false | false | self | 2 | null |
$3k-5k build? 10-20k build? 30-50k build? half considering going CPU for higher param purposes | 15 | After messing around with 8gb ram cpu this year, I'm going to buy something that can work at GPT~3 levels... hopefully.
I can get a little excessive because I have a commercial purpose that can justify costs that otherwise wouldn't be feasible, but still bang for your buck is nice.
For $4k I got a 4090 at 24gb vram,... | 2023-12-03T00:03:56 | https://www.reddit.com/r/LocalLLaMA/comments/189gqxw/3k5k_build_1020k_build_3050k_build_half/ | learning_hedonism | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 189gqxw | false | null | t3_189gqxw | /r/LocalLLaMA/comments/189gqxw/3k5k_build_1020k_build_3050k_build_half/ | false | false | self | 15 | null |
Has anyone ran two instances of webui? | 5 | I'm on linux, so run with "./start\_linux.sh". This runs on 7860. I was thinking I could just run a second instance on 7861 but no idea how to get it to run.
I've tried "./start\_linux.sh --port 7681" but it turns out "port" is not command line option.
The options have port in the name are:
\[--listen-port LISTEN... | 2023-12-02T23:45:01 | https://www.reddit.com/r/LocalLLaMA/comments/189gdni/has_anyone_ran_two_instances_of_webui/ | multiverse_fan | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 189gdni | false | null | t3_189gdni | /r/LocalLLaMA/comments/189gdni/has_anyone_ran_two_instances_of_webui/ | false | false | self | 5 | null |
Is there a distributed LLM encoder, like Leelachess for chess? | 1 | I'd contribute... | 2023-12-02T23:20:58 | https://www.reddit.com/r/LocalLLaMA/comments/189fwsr/is_there_a_distributed_llm_encoder_like/ | redditcdnfanguy | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 189fwsr | false | null | t3_189fwsr | /r/LocalLLaMA/comments/189fwsr/is_there_a_distributed_llm_encoder_like/ | false | false | self | 1 | null |
xtts 2 & styletts 2 locally with a gradio UI | 7 | So basically, title. I haven't been able to run those locally. I have already trying cloning the repos and running all the commands but a lot of errors would pop up always. Could anyone post a short tutorial to install both things locally (WITH A GRADIO UI, FU\*K RUNNING STUFF ON VS CODE).
TLDR: I'm not smart enoug... | 2023-12-02T22:03:33 | https://www.reddit.com/r/LocalLLaMA/comments/189eboh/xtts_2_styletts_2_locally_with_a_gradio_ui/ | sadeliox | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 189eboh | false | null | t3_189eboh | /r/LocalLLaMA/comments/189eboh/xtts_2_styletts_2_locally_with_a_gradio_ui/ | false | false | self | 7 | null |
Unreal Engine 5 | 9 | Has anyone tried making a custom LLM for use with Unreal Engine 5 dev? I was considering using LLaMA for training a UE5 specific AI, but wasn’t sure if that was worth it at this time. Any input is appreciated! | 2023-12-02T21:45:30 | https://www.reddit.com/r/LocalLLaMA/comments/189dyos/unreal_engine_5/ | SomewherePleasant168 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 189dyos | false | null | t3_189dyos | /r/LocalLLaMA/comments/189dyos/unreal_engine_5/ | false | false | self | 9 | null |
Beyond GPUs, are there any gifts related to ML/LLM/AI that any of you are putting on your Xmas list? | 9 | I feel like my imagination is so limited when I try to think of gifts to get me in general, but wonder if there are fun or practical things I might not know about out there I should ask for, related to working with AI? | 2023-12-02T21:23:46 | https://www.reddit.com/r/LocalLLaMA/comments/189dibh/beyond_gpus_are_there_any_gifts_related_to/ | SlateHardjaw | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 189dibh | false | null | t3_189dibh | /r/LocalLLaMA/comments/189dibh/beyond_gpus_are_there_any_gifts_related_to/ | false | false | self | 9 | null |
Llamasharp model to play a character | 1 | I am looking for a small model (that can run offline on minimal resources quickly) I am working on a project that relies heavily on llama interactions, i need to be able to provide a character, and scenario, and have it act out the conversation (with user) as that character formatting responses in a very specific way. | 2023-12-02T21:11:18 | https://www.reddit.com/r/LocalLLaMA/comments/189d9b6/llamasharp_model_to_play_a_character/ | Jafesu | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 189d9b6 | false | null | t3_189d9b6 | /r/LocalLLaMA/comments/189d9b6/llamasharp_model_to_play_a_character/ | false | false | self | 1 | null |
(text generation webui) Any extensions or tools that allow a character to automatically swap/send pictures based on mood or situation? | 1 | So I am here again with yet another question. I'm kinda new to this but I'm running textgen webui and I would like to know if there is any extension or way to make it so that characters can swap their pictures while talking to match their mood or something similar, kind of like what Kajiwoto does.
I was trying to make... | 2023-12-02T21:09:02 | https://www.reddit.com/r/LocalLLaMA/comments/189d7om/text_generation_webui_any_extensions_or_tools/ | OvercookedSatellite | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 189d7om | false | null | t3_189d7om | /r/LocalLLaMA/comments/189d7om/text_generation_webui_any_extensions_or_tools/ | false | false | self | 1 | null |
Is ChatGPT's Era as a Coding Tool Over? | 143 | ChatGPT performs worse than models with a 30 billion parameters for coding-related tasks. In general, when I try to use ChatGPT for programming tasks, I receive a message stating that the task is too advanced to be written, and the model can only provide advice. When I ask for code improvement, ChatGPT only corrects th... | 2023-12-02T20:51:20 | https://www.reddit.com/r/LocalLLaMA/comments/189cuj0/is_chatgpts_era_as_a_coding_tool_over/ | SliceAccomplished575 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 189cuj0 | false | null | t3_189cuj0 | /r/LocalLLaMA/comments/189cuj0/is_chatgpts_era_as_a_coding_tool_over/ | false | false | self | 143 | null |
saily_100B gguf - text results | 6 | `./main -m saily100B-Q3_K_S.gguf -p "Write me something hardcore. ### Response:" -ngl 60`
>spelling artifacts (at the beginning) are seen in 2 out of 3 outputs. Just like using Goliath.
https://imgur.io/a/T6pwYuZ
https://imgur.com/a/SMxRtmG | 2023-12-02T20:48:10 | https://www.reddit.com/r/LocalLLaMA/comments/189cs64/saily_100b_gguf_text_results/ | Aaaaaaaaaeeeee | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 189cs64 | false | null | t3_189cs64 | /r/LocalLLaMA/comments/189cs64/saily_100b_gguf_text_results/ | false | false | self | 6 | {'enabled': False, 'images': [{'id': 'hFyb_TIAiZIkkAxZ8dlkIw-DjRb33tpGVsp2_XSo_UM', 'resolutions': [{'height': 99, 'url': 'https://external-preview.redd.it/HQxp5lMCt-pAfCj4WO7h8B8qjUbP19raG1TXSklYSPw.jpg?width=108&crop=smart&auto=webp&s=35ab0dc6865a2270425f8df5df7954a4ea47bd6a', 'width': 108}, {'height': 198, 'url': 'h... |
New transformer architecture can make language models faster and resource-efficient | 82 | 2023-12-02T20:29:19 | https://venturebeat.com/ai/new-transformer-architecture-can-make-language-models-faster-and-resource-efficient/?utm_source=pocket_saves | RedditPolluter | venturebeat.com | 1970-01-01T00:00:00 | 0 | {} | 189cdjl | false | null | t3_189cdjl | /r/LocalLLaMA/comments/189cdjl/new_transformer_architecture_can_make_language/ | false | false | 82 | {'enabled': False, 'images': [{'id': 'Mr0JyReYHnaWSdP4vS09EgTif2oMq7q8L_jiV8aHgNY', 'resolutions': [{'height': 86, 'url': 'https://external-preview.redd.it/y4-Sr2KEd4m45qXRPDnQz_HWxBWid6ku9rvOwnv23aw.jpg?width=108&crop=smart&auto=webp&s=d65778aab378114e44c8af6276ce5641a09f400f', 'width': 108}, {'height': 172, 'url': 'h... | ||
llamafile programmatic command line or API type interaction | 1 | [removed] | 2023-12-02T20:09:40 | https://www.reddit.com/r/LocalLLaMA/comments/189bypg/llamafile_programmatic_command_line_or_api_type/ | datagazing | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 189bypg | false | null | t3_189bypg | /r/LocalLLaMA/comments/189bypg/llamafile_programmatic_command_line_or_api_type/ | false | false | self | 1 | null |
Google is training with 8 bit ints, next will move to 4 bit ints. | 35 | Embeddings will stay at 8 bits. Heard from a friend or heard from a friend. | 2023-12-02T19:36:22 | https://www.reddit.com/r/LocalLLaMA/comments/189b9gt/google_is_training_with_8_bit_ints_next_will_move/ | danielcar | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 189b9gt | false | null | t3_189b9gt | /r/LocalLLaMA/comments/189b9gt/google_is_training_with_8_bit_ints_next_will_move/ | false | false | self | 35 | null |
RAG Specialized LLMs (1-7B parameter) in Hugging Face | 32 | Hi Everyone, We recently launched in Hugging Face RAG specialized models that have been specifically fine-tuned for RAG, ranging in size from 1B parameters to 7B parameters. Our models have been fine-tuned on the most popular foundation models including LlaMA, YI, and Mistral with benchmark testing data provided. (exam... | 2023-12-02T19:33:10 | https://www.reddit.com/r/LocalLLaMA/comments/189b71z/rag_specialized_llms_17b_parameter_in_hugging_face/ | Mammoth-Doughnut-160 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 189b71z | false | null | t3_189b71z | /r/LocalLLaMA/comments/189b71z/rag_specialized_llms_17b_parameter_in_hugging_face/ | false | false | self | 32 | {'enabled': False, 'images': [{'id': 'bIFxP8z4YZQ5cG-P8smtLrHia42KCOCpHaC_Saqs1Pk', 'resolutions': [{'height': 58, 'url': 'https://external-preview.redd.it/wpz054AyKK5jbSqTOlK1EwCFzkyVttf6xHk83vJzjt4.jpg?width=108&crop=smart&auto=webp&s=7f1837be95a812fdad0b527d9b3ed3c36e7a1082', 'width': 108}, {'height': 116, 'url': 'h... |
So which LLM is good at writing uncensored stories? | 1 | [removed] | 2023-12-02T19:13:55 | https://www.reddit.com/r/LocalLLaMA/comments/189as7u/so_which_llm_is_good_at_writing_uncensored_stories/ | rookierook00000 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 189as7u | false | null | t3_189as7u | /r/LocalLLaMA/comments/189as7u/so_which_llm_is_good_at_writing_uncensored_stories/ | false | false | self | 1 | null |
Everything about tokenization | 60 | Hi folks,
Not Llama-exclusive, but I recently wrote up a mini-course on tokenization, with bite-size chapters + code & notebooks. It is as comprehensive as I could make it, with a focus on working with HuggingFace tokenizers. I think content on tokenization internals is a missing piece right now, so I thought this mig... | 2023-12-02T19:11:06 | https://www.reddit.com/r/LocalLLaMA/comments/189aq0m/everything_about_tokenization/ | Sum2110 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 189aq0m | false | null | t3_189aq0m | /r/LocalLLaMA/comments/189aq0m/everything_about_tokenization/ | false | false | self | 60 | {'enabled': False, 'images': [{'id': 'vs22l7A6PYyOcKER0rA3jh_IzDz3eq44x5OnTtpoY_0', 'resolutions': [{'height': 54, 'url': 'https://external-preview.redd.it/BadvqizTJC2Q5wkh4fAKp9Tadpp4NW-gmC88X2GQcLE.jpg?width=108&crop=smart&auto=webp&s=e2c841853caad0cc207935ec7e3e48640778447a', 'width': 108}, {'height': 108, 'url': 'h... |
First keras model trained on mistral data | 1 | [removed] | 2023-12-02T18:53:08 | introsp3ctor | i.redd.it | 1970-01-01T00:00:00 | 0 | {} | 189acnt | false | null | t3_189acnt | /r/LocalLLaMA/comments/189acnt/first_keras_model_trained_on_mistral_data/ | false | false | 1 | {'enabled': True, 'images': [{'id': 'Ro2ihPDpEWVo2OKEdrHp4gxKXoWjvdU-w4goKgMljcc', 'resolutions': [{'height': 52, 'url': 'https://preview.redd.it/xbzwuzzhhx3c1.jpg?width=108&crop=smart&auto=webp&s=be3298f1fe1f0dbdf67eb4efc435acef35e3d1c7', 'width': 108}, {'height': 104, 'url': 'https://preview.redd.it/xbzwuzzhhx3c1.jpg... | ||
What can you do with an H100? | 7 | Let's say I had one sitting in my room, how could I make the most use of it? | 2023-12-02T18:25:46 | https://www.reddit.com/r/LocalLLaMA/comments/1899rt2/what_can_you_do_with_an_h100/ | freecodeio | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 1899rt2 | false | null | t3_1899rt2 | /r/LocalLLaMA/comments/1899rt2/what_can_you_do_with_an_h100/ | false | false | self | 7 | null |
Could someone summarise the hardware requirements for local models? | 6 | How important is CPU Vs GPU? System RAM Vs video memory? For example, I have a 6 core 5600x, 32GB RAM and a 3060ti GPU (8GB), what can I and what can't I do? I have the Mistral 7B model running nicely - is that the limit on this kind of hardware?
How does the new Apple silicone compare with x86 architecture and nVidia... | 2023-12-02T18:16:11 | https://www.reddit.com/r/LocalLLaMA/comments/1899kre/could_someone_summarise_the_hardware_requirements/ | clv101 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 1899kre | false | null | t3_1899kre | /r/LocalLLaMA/comments/1899kre/could_someone_summarise_the_hardware_requirements/ | false | false | self | 6 | null |
multiple humans talking to one bot with api integration , hardware nedded tò run 13b model fast token generation ? | 1 | [removed] | 2023-12-02T17:58:49 | https://www.reddit.com/r/LocalLLaMA/comments/189971n/multiple_humans_talking_to_one_bot_with_api/ | Independent-Bill-770 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 189971n | false | null | t3_189971n | /r/LocalLLaMA/comments/189971n/multiple_humans_talking_to_one_bot_with_api/ | false | false | self | 1 | null |
Goliath Test Output | 22 | I just finished building my 6x3090 basement server, because my wife is addicted (yes, I'm going to blame this on her), and I needed to test that everything was working.
So, I loaded up an 8bpw Goliath EXL2 and gave it this prompt on my 'Storyteller' character that has about 2500 tokens of my own writing as example tex... | 2023-12-02T17:55:50 | https://www.reddit.com/r/LocalLLaMA/comments/18994w3/goliath_test_output/ | Mass2018 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 18994w3 | false | null | t3_18994w3 | /r/LocalLLaMA/comments/18994w3/goliath_test_output/ | false | false | self | 22 | null |
Difference between KoboldAI and Koboldcpp, and which one should I use? | 1 | [removed] | 2023-12-02T17:24:10 | https://www.reddit.com/r/LocalLLaMA/comments/1898gmv/difference_between_koboldai_and_koboldcpp_and/ | squarytypfe27 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 1898gmv | false | null | t3_1898gmv | /r/LocalLLaMA/comments/1898gmv/difference_between_koboldai_and_koboldcpp_and/ | false | false | self | 1 | null |
What is the worst LLM out there? | 1 | [removed] | 2023-12-02T16:33:35 | https://www.reddit.com/r/LocalLLaMA/comments/1897e3a/what_is_the_worst_llm_out_there/ | Puzzleheaded_Acadia1 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 1897e3a | false | null | t3_1897e3a | /r/LocalLLaMA/comments/1897e3a/what_is_the_worst_llm_out_there/ | false | false | self | 1 | null |
How I Run 34B Models at 75K Context on 24GB, Fast | 306 | I've been repeatedly asked this, so here are the steps from the top:
- Install Python, CUDA
- Download https://github.com/turboderp/exui
- Inside the folder, right click to open a terminal and set up a Python venv with "python -m venv venv", enter it.
- "pip install -r requirements.txt"
- Be sure to install flash ... | 2023-12-02T15:50:34 | https://www.reddit.com/r/LocalLLaMA/comments/1896igc/how_i_run_34b_models_at_75k_context_on_24gb_fast/ | mcmoose1900 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 1896igc | false | null | t3_1896igc | /r/LocalLLaMA/comments/1896igc/how_i_run_34b_models_at_75k_context_on_24gb_fast/ | false | false | self | 306 | {'enabled': False, 'images': [{'id': 'vVPxhfFVjeBWyMA8RYahd9fmRAkKsZBiDK_RDJXwc9o', 'resolutions': [{'height': 54, 'url': 'https://external-preview.redd.it/PnCcq9aA14AET0NsatqTDq-QJxsvJ-6DgLS9Tr5_q6Q.jpg?width=108&crop=smart&auto=webp&s=00fc3b6f2ce6e5a16e1ab985a0d72eada6fa7171', 'width': 108}, {'height': 108, 'url': 'h... |
Is there any way to integrate Whatsapp to a fine-tuned model? | 1 | I'm 19F currently in my first year of CS, I have a fine-tuned LLM but I don't know how to integrate and link it to a WhatsApp number so that other users can send a text to that number which will be used as a prompt to the LLM and give response according to the prompt/text. | 2023-12-02T15:29:00 | https://www.reddit.com/r/LocalLLaMA/comments/18962yp/is_there_any_way_to_integrate_whatsapp_to_a/ | Abin42 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 18962yp | false | null | t3_18962yp | /r/LocalLLaMA/comments/18962yp/is_there_any_way_to_integrate_whatsapp_to_a/ | false | false | self | 1 | null |
What to expect from Qwen-72B | 10 | Since this model, different from base Llama-70B, wasn't undertrained, how well can we expect it to perform after some finetuning? Will it perform better than frankmerges like Goliath-120B? | 2023-12-02T15:28:46 | https://www.reddit.com/r/LocalLLaMA/comments/18962sp/what_to_expect_from_qwen72b/ | Educational_Grab_473 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 18962sp | false | null | t3_18962sp | /r/LocalLLaMA/comments/18962sp/what_to_expect_from_qwen72b/ | false | false | self | 10 | null |
Full Fine-Tune 3B models | 2 | Basically the title, any guides how to fit a 3B model to 4 V100x32GB GPUs for full fine-tuning (No LoRAs). I mostly use LoRAs so this is pretty new to me | 2023-12-02T13:26:22 | https://www.reddit.com/r/LocalLLaMA/comments/1893p5j/full_finetune_3b_models/ | Gemini_salt | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 1893p5j | false | null | t3_1893p5j | /r/LocalLLaMA/comments/1893p5j/full_finetune_3b_models/ | false | false | self | 2 | null |
Best setup to multi-party conversions? I want multiple humans talking to one bot with api integration , hardware nedded? | 1 | [removed] | 2023-12-02T12:46:09 | https://www.reddit.com/r/LocalLLaMA/comments/189304m/best_setup_to_multiparty_conversions_i_want/ | Independent-Bill-770 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 189304m | false | null | t3_189304m | /r/LocalLLaMA/comments/189304m/best_setup_to_multiparty_conversions_i_want/ | false | false | self | 1 | null |
Tutorial of tg-webui CausalLM/72B-preview-GGUF Quants (Qwen 72B LLaMAfied) | 12 | The 72b-q5\_k\_m.gguf was spilt, for hf limit of 50GB.
**Tips for merge large files:**
linux
cat 72b-q5_k_m.gguf-split-a 72b-q5_k_m.gguf-split-b > 72b-q5_k_m.gguf
windows
copy /b 72b-q5_k_m.gguf-split-a + 72b-q5_k_m.gguf-split-b 72b-q5_k_m.gguf
# As for text-generation-webui:
Before their official upda... | 2023-12-02T12:42:21 | https://www.reddit.com/r/LocalLLaMA/comments/1892xto/tutorial_of_tgwebui_causallm72bpreviewgguf_quants/ | No-Link-2778 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 1892xto | false | null | t3_1892xto | /r/LocalLLaMA/comments/1892xto/tutorial_of_tgwebui_causallm72bpreviewgguf_quants/ | false | false | 12 | {'enabled': False, 'images': [{'id': 'E37rBWTtpC3_wqpmc89lfdhE3s-EY5y5Sc_Gm4Bby94', 'resolutions': [{'height': 54, 'url': 'https://external-preview.redd.it/86DvYU3zohznlp5l-7D8wyzEHHzSiajX_H-Ky0XvD8c.jpg?width=108&crop=smart&auto=webp&s=d670f86de10e29a60502e4bfc82c5b39363da25e', 'width': 108}, {'height': 108, 'url': 'h... | |
Best LLM for creating characters | 4 | Hello, I am looking for a good LLM for creating characters (personas).I need to create fictional characters like personal friends and I am not sure about which LLM I should choose.
My PC can run 7B models in q8 and 13B models with q4.
Btw, share if you have tips of prompt (or a prompt itself) for this kind of thing. | 2023-12-02T11:52:11 | https://www.reddit.com/r/LocalLLaMA/comments/189261i/best_llm_for_creating_characters/ | Flavin-guy | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 189261i | false | null | t3_189261i | /r/LocalLLaMA/comments/189261i/best_llm_for_creating_characters/ | false | false | self | 4 | null |
I'd like to propose a community project open to beginner programers and hobbyists LLM programmers | 1 | [removed] | 2023-12-02T11:39:20 | https://www.reddit.com/r/LocalLLaMA/comments/1891z1o/id_like_to_propose_a_community_project_open_to/ | Mescallan | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 1891z1o | false | null | t3_1891z1o | /r/LocalLLaMA/comments/1891z1o/id_like_to_propose_a_community_project_open_to/ | false | false | self | 1 | null |
What's the best LLM for summarization of long documents? | 63 | Help a newbie.
I am trying to create a LLM that takes in a lot of legal judgments and then summarizes them. Basically a summarization tool that's best out there for large documents. Each legal judgment is about an average length of 62000 words.
Earlier I had used BERT.
Which is the best LLM for it? And what model ... | 2023-12-02T11:19:01 | https://www.reddit.com/r/LocalLLaMA/comments/1891o5m/whats_the_best_llm_for_summarization_of_long/ | mlexplorer | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 1891o5m | false | null | t3_1891o5m | /r/LocalLLaMA/comments/1891o5m/whats_the_best_llm_for_summarization_of_long/ | false | false | self | 63 | null |
Please tell me where I am dumb | 2 | In my country:
- Used/ex-mining 3090 = 450/500 USD
- For same 450/500 USD, I can get used Xeon E5 v4 + 256GB DDR4 HP/Dell 2U Server + 2x750W PSU
- Thinking of buying the rack and the GPU.
- Throw them into a larger 4U case.
- Remove the GPU fans and shroud because glorious server fans.
- Power limit the GPU at 200/250... | 2023-12-02T10:42:42 | https://www.reddit.com/r/LocalLLaMA/comments/189153l/please_tell_me_where_i_am_dumb/ | raddka | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 189153l | false | null | t3_189153l | /r/LocalLLaMA/comments/189153l/please_tell_me_where_i_am_dumb/ | false | false | self | 2 | null |
I used Zephyr 7B to extract features from the description of a product (got a million of those). I want to measure the accuracy of this output. Which model do I use to do find the accuracy? | 2 | Input :
Revita Shampoo For Thinning Hair by DS Laboratories - Volumizing, Thickening Shampoo for Men and Women, Supports Hair Growth, Hair Strengthening, Sulfate Free, 7 Fl Oz (205mL) - Packaging May Vary Amazon.com : Revita Shampoo For Thinning Hair by DS Laboratories - Volumizing, Thickening Shampoo for Men ... | 2023-12-02T09:45:23 | https://www.reddit.com/r/LocalLLaMA/comments/1890bw7/i_used_zephyr_7b_to_extract_features_from_the/ | Final_Ad_6167 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 1890bw7 | false | null | t3_1890bw7 | /r/LocalLLaMA/comments/1890bw7/i_used_zephyr_7b_to_extract_features_from_the/ | false | false | self | 2 | null |
How to finetune a model for lyric generation? | 1 | Hi, I'm a uni student and would like to fine-tune llama2 on lyrics from a specific music genre, how much data would I need and how should I have the data stored?
Sorry for the trivial question, but I couldn't find much info on the web | 2023-12-02T09:36:11 | https://www.reddit.com/r/LocalLLaMA/comments/18907da/how_to_finetune_a_model_for_lyric_generation/ | rookiewtf | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 18907da | false | null | t3_18907da | /r/LocalLLaMA/comments/18907da/how_to_finetune_a_model_for_lyric_generation/ | false | false | self | 1 | null |
Benefits of self-hosting that carry over to professional work? | 13 | Curious for insights on what benefits and learnings you gain from self hosting that may carry over and be useful in your professional day job? For me, looking to level up from the closed source managed API services like Azure OpenAI. Understating more about datasets, quantisation methods, fine tuning, hardware needs, a... | 2023-12-02T08:30:34 | https://www.reddit.com/r/LocalLLaMA/comments/188zbo4/benefits_of_selfhosting_that_carry_over_to/ | LostGoatOnHill | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 188zbo4 | false | null | t3_188zbo4 | /r/LocalLLaMA/comments/188zbo4/benefits_of_selfhosting_that_carry_over_to/ | false | false | self | 13 | null |
Delete/offload llm from gpu | 1 | I want make a system where user can switch llm model and choose what model they want. For this I have to offload/delete llm from the gpu.But i am not able to do this. I tried : gc.collect().torch.cuda.empty\_cache(),torch.cuda.reset\_peak\_memory\_stats(),release\_memory(model).none of them works.
Here is my code:
d... | 2023-12-02T08:18:22 | https://www.reddit.com/r/LocalLLaMA/comments/188z5oi/deleteoffload_llm_from_gpu/ | Outside_Solid5371 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 188z5oi | false | null | t3_188z5oi | /r/LocalLLaMA/comments/188z5oi/deleteoffload_llm_from_gpu/ | false | false | self | 1 | null |
Local LLMs as browser sidekicks | 2 | 2023-12-02T07:02:25 | https://kshreyas.dev/post/local-llms/ | mmagusss | kshreyas.dev | 1970-01-01T00:00:00 | 0 | {} | 188y30l | false | null | t3_188y30l | /r/LocalLLaMA/comments/188y30l/local_llms_as_browser_sidekicks/ | false | false | default | 2 | null | |
What's the best solution currently for a locally run model that can do web browsing? | 15 | Apologies if this is too basic. I'm not too happy with the browsing capability of ChatGPT, and I want to potentially build something on my own using open source models/tools (and maybe some free or paid search APIs) and want to know what a good place to start is. | 2023-12-02T04:32:28 | https://www.reddit.com/r/LocalLLaMA/comments/188vmyd/whats_the_best_solution_currently_for_a_locally/ | lanky_cowriter | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 188vmyd | false | null | t3_188vmyd | /r/LocalLLaMA/comments/188vmyd/whats_the_best_solution_currently_for_a_locally/ | false | false | self | 15 | null |
PSA: If your model isn't producing enough text, try lowering the repetition penalty | 23 | This took me way too long to figure out, though I guess it isn't too surprising in hindsight, since the easiest way to avoid repetition is to just keep the output short.
Most presets have `repetition_penalty` set to a value somewhere between 1.15 and 1.20, but I find that lowering this to around 1.05-1.08 still keeps ... | 2023-12-02T04:01:17 | https://www.reddit.com/r/LocalLLaMA/comments/188v3kj/psa_if_your_model_isnt_producing_enough_text_try/ | -p-e-w- | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 188v3kj | false | null | t3_188v3kj | /r/LocalLLaMA/comments/188v3kj/psa_if_your_model_isnt_producing_enough_text_try/ | false | false | self | 23 | null |
openhermes 7B - any tips on how to get it to extract information a bit better? | 6 | I'm using openhermes 2.5 mistral 16k 7B q4_k on LM Studio.
I'm trying to use it to extract and describe three "scenes" from a story text in simple terms.
My prompt:
> <|im_start|>system
> You are an expert at writing story synopsis and summaries. Find three scenes in the story and describe each individual scene in s... | 2023-12-02T03:42:48 | https://www.reddit.com/r/LocalLLaMA/comments/188ursh/openhermes_7b_any_tips_on_how_to_get_it_to/ | av1questionforsub | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 188ursh | false | null | t3_188ursh | /r/LocalLLaMA/comments/188ursh/openhermes_7b_any_tips_on_how_to_get_it_to/ | false | false | self | 6 | null |
Generating images inside Ooba UI (using API to automatic1111) | 1 | Hey all,
Has anyone been able to get an extension going for Ooba UI, to use a running SD running on automatic1111? I tried one from git but didn't work as the extension is for another forked version of SD.. anyone have an extension for the vanilla automatic1111 version? would be cool for the AI to generate image withi... | 2023-12-02T02:07:48 | https://www.reddit.com/r/LocalLLaMA/comments/188syt4/generating_images_inside_ooba_ui_using_api_to/ | intenzething | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 188syt4 | false | null | t3_188syt4 | /r/LocalLLaMA/comments/188syt4/generating_images_inside_ooba_ui_using_api_to/ | false | false | self | 1 | null |
Honeymoon stage for LLMs seems to have reached its peek. We need another breakthrough | 1 | [removed] | 2023-12-02T01:58:04 | https://www.reddit.com/r/LocalLLaMA/comments/188srs8/honeymoon_stage_for_llms_seems_to_have_reached/ | vlodia | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 188srs8 | false | null | t3_188srs8 | /r/LocalLLaMA/comments/188srs8/honeymoon_stage_for_llms_seems_to_have_reached/ | false | false | self | 1 | {'enabled': False, 'images': [{'id': 'KCHo63FYpaRJx6BBwh7V4CIMup9Qi7sE_dXT12XITGc', 'resolutions': [{'height': 81, 'url': 'https://external-preview.redd.it/QpGRvydLSluQ_s5uGQbieHoaHaaEDqX7zyhuk0HfLZU.jpg?width=108&crop=smart&auto=webp&s=9926460ccd95c3a794c3ab36e91074a03d6d4ad1', 'width': 108}, {'height': 162, 'url': 'h... |
How can I import the official Mistral 7 B model that they posted on Twitter into LM Studio? | 1 | How can I import the model into LM Studio? The files I have from the magnet link are: the main model which is 13+ GB witha .pth extension, params.json, and tokenizer.model.
LM Studio seems to use GGUF files, if needed, is there a way to convert the official mistral files into that format? | 2023-12-02T01:48:38 | https://www.reddit.com/r/LocalLLaMA/comments/188sl91/how_can_i_import_the_official_mistral_7_b_model/ | jazir5 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 188sl91 | false | null | t3_188sl91 | /r/LocalLLaMA/comments/188sl91/how_can_i_import_the_official_mistral_7_b_model/ | false | false | self | 1 | null |
What’s the best way to run starling 7B locally and have python code access it on my computer? Suggestions? | 1 | It’s for a project and I want to have it use starling 7B to do QNA query’s type things, it be really great if it was an easy install /setup cause I want it to also be cross platform hm, any thoughts? | 2023-12-02T01:34:29 | https://www.reddit.com/r/LocalLLaMA/comments/188sb25/whats_the_best_way_to_run_starling_7b_locally_and/ | Impossible_Belt_7757 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 188sb25 | false | null | t3_188sb25 | /r/LocalLLaMA/comments/188sb25/whats_the_best_way_to_run_starling_7b_locally_and/ | false | false | self | 1 | null |
Brand new and need a little direction. (Yes the search works, no I couldn't find what I was looking for) | 2 | Hey all. So AI is a passive interest for me. More using it than anything, I am no programmer so a lot of what I am seeing is here is going over my head.
So first thing first rather than ask 101 question is there a good youtube video or creator that explains how to use LM Studio in laymen terms?
There are two things ... | 2023-12-02T01:29:10 | https://www.reddit.com/r/LocalLLaMA/comments/188s738/brand_new_and_need_a_little_direction_yes_the/ | Foot-Note | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 188s738 | false | null | t3_188s738 | /r/LocalLLaMA/comments/188s738/brand_new_and_need_a_little_direction_yes_the/ | false | false | self | 2 | null |
How to extend the replies for Ooba? the "Long Replies" extension or plugin is already activated, yet the replies get cut off and I need to type "continue" into the prompt to continue the reply? | 1 | How to extend the replies for Ooba? the "Long Replies" extension or plugin is already activated, yet the replies get cut off and I need to type "continue" into the prompt to continue the reply? | 2023-12-02T00:59:48 | https://www.reddit.com/r/LocalLLaMA/comments/188rl77/how_to_extend_the_replies_for_ooba_the_long/ | intenzething | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 188rl77 | false | null | t3_188rl77 | /r/LocalLLaMA/comments/188rl77/how_to_extend_the_replies_for_ooba_the_long/ | false | false | self | 1 | null |
Subsets and Splits
No community queries yet
The top public SQL queries from the community will appear here once available.