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 ⌀ |
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
Building a simple rag, some questions. | 1 | [removed] | 2024-01-14T09:38:49 | https://www.reddit.com/r/LocalLLaMA/comments/196c98t/building_a_simple_rag_some_questions/ | Redbeardybeard | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 196c98t | false | null | t3_196c98t | /r/LocalLLaMA/comments/196c98t/building_a_simple_rag_some_questions/ | false | false | self | 1 | null |
Is it necessary for adapters to match the precision of their base models? | 2 | I’m curious about the potential error rates when using different quantization formats in adapters. Specifically, my question revolves around the outcomes of training an adapter on an NF4 base model using QLoRA, and then integrating this adapter with a GPTQ model. How would this compare to the results obtained from trai... | 2024-01-14T09:23:26 | https://www.reddit.com/r/LocalLLaMA/comments/196c1fm/is_it_necessary_for_adapters_to_match_the/ | FrostyContribution35 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 196c1fm | false | null | t3_196c1fm | /r/LocalLLaMA/comments/196c1fm/is_it_necessary_for_adapters_to_match_the/ | false | false | self | 2 | {'enabled': False, 'images': [{'id': 'tLIoT0aildUP4dxzahdHEru6gFvzdV03ymwaIZvsdKA', 'resolutions': [{'height': 54, 'url': 'https://external-preview.redd.it/MJOias903TcWW98C_GeEACdkUUT6W_YU3PmW68RuXXA.jpg?width=108&crop=smart&auto=webp&s=3386ec54fbfdbdfef6eca457f83420e433fb3f9b', 'width': 108}, {'height': 108, 'url': 'h... |
Simple dockerized solution to run, serve and generate llamafile locally | 3 | I just finished this for my personal local trials. Let me know if you like it (or not) :).
[https://github.com/dominikj111/LLM/tree/main/Llamafile](https://github.com/dominikj111/LLM/tree/main/Llamafile) | 2024-01-14T09:04:32 | https://www.reddit.com/r/LocalLLaMA/comments/196brok/simple_dockerized_solution_to_run_serve_and/ | domino_master | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 196brok | false | null | t3_196brok | /r/LocalLLaMA/comments/196brok/simple_dockerized_solution_to_run_serve_and/ | false | false | self | 3 | {'enabled': False, 'images': [{'id': '0YlSf-tj5c1i3ZbjJUqYuta7ObsGd7Udq5ZlLkPLcYM', 'resolutions': [{'height': 54, 'url': 'https://external-preview.redd.it/PaO3n_WB2kRPDnVsFCqIfMg3y1ETSQsL3zAP2qfjsw0.jpg?width=108&crop=smart&auto=webp&s=ca50633d5fdb26b7aa61b7eae73095666b9ba6e8', 'width': 108}, {'height': 108, 'url': 'h... |
Question about used GFX cards | 1 | [removed] | 2024-01-14T08:15:11 | https://www.reddit.com/r/LocalLLaMA/comments/196b2aq/question_about_used_gfx_cards/ | PiComprehensive314 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 196b2aq | false | null | t3_196b2aq | /r/LocalLLaMA/comments/196b2aq/question_about_used_gfx_cards/ | false | false | self | 1 | null |
Local LLM movement feels like early days of PCs vs Mainframes | 204 | I wasn't alive when PCs were first being invented, but reading this reddit makes me think of what I've read about those pioneering days. Just as personal computers began to challenge the dominance of large, centralized mainframes, we're now witnessing the starting point of a similar evolution with LLMs.
In the early d... | 2024-01-14T06:47:33 | https://www.reddit.com/r/LocalLLaMA/comments/1969pir/local_llm_movement_feels_like_early_days_of_pcs/ | docsoc1 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 1969pir | false | null | t3_1969pir | /r/LocalLLaMA/comments/1969pir/local_llm_movement_feels_like_early_days_of_pcs/ | false | false | self | 204 | null |
Benchmarking various models on 24GB VRAM | 63 | Here is my benchmark of various models on following setup:
\- i7 13700KF
\- 128GB RAM (@4800)
\- single 3090 with 24GB VRAM
​
I will be using koboldcpp on Windows 10. I wanted to do this benchmark before configuring Arch Linux. I think results may be very different on different software and operating system... | 2024-01-14T05:56:13 | https://www.reddit.com/r/LocalLLaMA/comments/1968uvj/benchmarking_various_models_on_24gb_vram/ | jacek2023 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 1968uvj | false | null | t3_1968uvj | /r/LocalLLaMA/comments/1968uvj/benchmarking_various_models_on_24gb_vram/ | false | false | self | 63 | null |
I am a Strange Dataset: Metalinguistic Tests for Language Models | 19 | **Paper**: [https://arxiv.org/abs/2401.05300](https://arxiv.org/abs/2401.05300)
**Code and dataset**: [https://github.com/TristanThrush/i-am-a-strange-dataset](https://github.com/TristanThrush/i-am-a-strange-dataset)
**Abstract**:
>Statements involving metalinguistic self-reference ("This paper has six sections.") ... | 2024-01-14T05:51:02 | https://www.reddit.com/r/LocalLLaMA/comments/1968rqx/i_am_a_strange_dataset_metalinguistic_tests_for/ | APaperADay | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 1968rqx | false | null | t3_1968rqx | /r/LocalLLaMA/comments/1968rqx/i_am_a_strange_dataset_metalinguistic_tests_for/ | false | false | self | 19 | null |
REBUS: A Robust Evaluation Benchmark of Understanding Symbols | 6 | **Paper**: [https://arxiv.org/abs/2401.05604](https://arxiv.org/abs/2401.05604)
**Code**: [https://github.com/cvndsh/rebus](https://github.com/cvndsh/rebus)
**Dataset**: [https://huggingface.co/datasets/cavendishlabs/rebus](https://huggingface.co/datasets/cavendishlabs/rebus)
**Project page**: [https://cavendishlabs... | 2024-01-14T05:40:59 | https://www.reddit.com/r/LocalLLaMA/comments/1968ln2/rebus_a_robust_evaluation_benchmark_of/ | APaperADay | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 1968ln2 | false | null | t3_1968ln2 | /r/LocalLLaMA/comments/1968ln2/rebus_a_robust_evaluation_benchmark_of/ | false | false | self | 6 | null |
How to accurately answer from a large corpus of text (3000000 words)? 🤷🤷 | 1 | [removed] | 2024-01-14T05:37:25 | https://www.reddit.com/r/LocalLLaMA/comments/1968jfq/how_to_accurately_answer_from_a_large_corpus_of/ | suddenlife2 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 1968jfq | false | null | t3_1968jfq | /r/LocalLLaMA/comments/1968jfq/how_to_accurately_answer_from_a_large_corpus_of/ | false | false | self | 1 | null |
Training a LoRA on Unstructured Data | 15 | Hey all. I have accumulated a large set of books and magazines going back to the 1800s on a particular topic. I am looking to train a Lora against LLaMA to be able to pull useful data from this pile of sometimes inaccurate information. Do I need to just pull out everything into text files, manually label them, or ??? W... | 2024-01-14T04:49:29 | https://www.reddit.com/r/LocalLLaMA/comments/1967p9z/training_a_lora_on_unstructured_data/ | DorianGre | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 1967p9z | false | null | t3_1967p9z | /r/LocalLLaMA/comments/1967p9z/training_a_lora_on_unstructured_data/ | false | false | self | 15 | null |
V8 and Mixed Precision | 1 | When you do mixed precision calculations, you can adopt intermediate calculating result for a 2(or3)-time mixed precision at the same time.
If it has a logic graph like this, can you adopt a JavaScript v8 data management into multiple intermediate mixed-precision calculations,hence making much more calculating po... | 2024-01-14T04:37:06 | https://www.reddit.com/r/LocalLLaMA/comments/1967hl0/v8_and_mixed_precision/ | Hot-Highlight8842 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 1967hl0 | false | null | t3_1967hl0 | /r/LocalLLaMA/comments/1967hl0/v8_and_mixed_precision/ | false | false | self | 1 | null |
Any good Chinese models for writing dialogue? | 7 | I like writing fiction, and have tried in the past to write fiction stories in the style of Chinese fantasy fiction web novels, but I really suck at writing natural dialogue. I'm wondering if there's any good Chinese LLMs that can write dialogue for me based on instructions about what the dialogue should contain.
I ha... | 2024-01-14T04:13:46 | https://www.reddit.com/r/LocalLLaMA/comments/19672lv/any_good_chinese_models_for_writing_dialogue/ | Daniel_H212 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 19672lv | false | null | t3_19672lv | /r/LocalLLaMA/comments/19672lv/any_good_chinese_models_for_writing_dialogue/ | false | false | self | 7 | null |
How's my home server setup looking? Seeking advice and tips! | 1 | [removed] | 2024-01-14T04:09:02 | https://www.reddit.com/r/LocalLLaMA/comments/1966zkm/hows_my_home_server_setup_looking_seeking_advice/ | MicBeckie | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 1966zkm | false | null | t3_1966zkm | /r/LocalLLaMA/comments/1966zkm/hows_my_home_server_setup_looking_seeking_advice/ | false | false | self | 1 | null |
Is it possible to upload an llm to an website and then make the requests using Silly Tavern? | 1 | I once found a post here saying that the best method and lowest resource heavy would be upload to a certain website and then use the API in silly tavern. Where can I do this? I can't find that post anymore | 2024-01-14T04:04:50 | https://www.reddit.com/r/LocalLLaMA/comments/1966wxh/is_it_possible_to_upload_an_llm_to_an_website_and/ | Cyberzos | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 1966wxh | false | null | t3_1966wxh | /r/LocalLLaMA/comments/1966wxh/is_it_possible_to_upload_an_llm_to_an_website_and/ | false | false | self | 1 | null |
Banned from OpenAI API without explanation, any alternatives? | 1 | [removed] | 2024-01-14T03:35:36 | https://www.reddit.com/r/LocalLLaMA/comments/1966dth/banned_from_openai_api_without_explanation_any/ | TheDuhhh | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 1966dth | false | null | t3_1966dth | /r/LocalLLaMA/comments/1966dth/banned_from_openai_api_without_explanation_any/ | false | false | self | 1 | null |
What are the datasets used for mistral-instruct? | 7 | The mistral blog post on their website says "to show the generalization capabilities of Mistral 7B, we fine-tuned it on instruction datasets publicly available on HuggingFace. No tricks, no proprietary data." That's pretty good obviously, but I can't find any details about what these datasets are. Is there any insight... | 2024-01-14T03:19:28 | https://www.reddit.com/r/LocalLLaMA/comments/19662o7/what_are_the_datasets_used_for_mistralinstruct/ | gamesntech | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 19662o7 | false | null | t3_19662o7 | /r/LocalLLaMA/comments/19662o7/what_are_the_datasets_used_for_mistralinstruct/ | false | false | self | 7 | null |
I just made a table of Awesome-LLM-Papers-Toward-AGI | 1 | 2024-01-14T02:14:10 | https://github.com/shure-dev/Awesome-LLM-Papers-Toward-AGI | Common-Ad-1772 | github.com | 1970-01-01T00:00:00 | 0 | {} | 1964t8e | false | null | t3_1964t8e | /r/LocalLLaMA/comments/1964t8e/i_just_made_a_table_of_awesomellmpaperstowardagi/ | false | false | 1 | {'enabled': False, 'images': [{'id': 'pqQCoG0rb3FkCTikSaYJeYWu0PnaO79JkkahCrg1DkE', 'resolutions': [{'height': 54, 'url': 'https://external-preview.redd.it/d9nk-zm6vJwdVcKpZCHE1h4jWdk5J67LW0vZcmLskdQ.jpg?width=108&crop=smart&auto=webp&s=361ed69b6a8471612e1ccd58a714d4cf4c5344a5', 'width': 108}, {'height': 108, 'url': 'h... | ||
Is v100 32GB worth it? | 1 | I’m getting v100 32gb in around $500, wanted to ask is it really worth? Because I haven’t seen any informative/helpful threads regarding it so far.
Another thing, will it work on AM4 motherboard? With secondary GPU for ports.
What would be what could be pros and cons over a 3090? | 2024-01-14T01:56:44 | https://www.reddit.com/r/LocalLLaMA/comments/1964gqa/is_v100_32gb_worth_it/ | yetanotherbeardedone | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 1964gqa | false | null | t3_1964gqa | /r/LocalLLaMA/comments/1964gqa/is_v100_32gb_worth_it/ | false | false | self | 1 | null |
Best DB structure for my use-case... | 1 | Lets say I have a postgres database which consists of tables; classes, teachers, orders, reviews.
Is it better to create a vector column in each table - and store the embedding in the actual table for each? OR should I create a vector table called 'vectors' and store a 'type' (courses, teachers), 'id' and just have a... | 2024-01-14T01:19:24 | https://www.reddit.com/r/LocalLLaMA/comments/1963p5n/best_db_structure_for_my_usecase/ | trojans10 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 1963p5n | false | null | t3_1963p5n | /r/LocalLLaMA/comments/1963p5n/best_db_structure_for_my_usecase/ | false | false | self | 1 | null |
USB-AI | 1 | Has anyone explored or heard of deploying an AI model on a USB-sized computing device, akin to portable computers on flash drives? Given the strides in miniaturizing technology, such as Raspberry Pi's ability to handle lightweight AI tasks, it seems feasible. I'm intrigued by the potential of plug-and-play AI solutions... | 2024-01-14T00:58:09 | https://www.reddit.com/r/LocalLLaMA/comments/196396u/usbai/ | AI_Heresy | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 196396u | false | null | t3_196396u | /r/LocalLLaMA/comments/196396u/usbai/ | false | false | self | 1 | null |
How does people merge models to form MoE? | 4 | This guy says he formed a Mixture of Experts (MoE) made with [**mergekit**](https://github.com/cg123/mergekit) (mixtral branch). It uses the following base models:
* [**openchat/openchat-3.5-1210**](https://huggingface.co/openchat/openchat-3.5-1210)
* [**beowolx/CodeNinja-1.0-OpenChat-7B**](https://huggingface.co/beo... | 2024-01-14T00:40:15 | https://www.reddit.com/r/LocalLLaMA/comments/1962vvz/how_does_people_merge_models_to_form_moe/ | Dense-Smf-6032 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 1962vvz | false | null | t3_1962vvz | /r/LocalLLaMA/comments/1962vvz/how_does_people_merge_models_to_form_moe/ | false | false | self | 4 | {'enabled': False, 'images': [{'id': 'pMGFIbiK07kT202sIqJjsHYK9YuE5MxeJTXIE_PYBFc', 'resolutions': [{'height': 54, 'url': 'https://external-preview.redd.it/LPXvR8Dhokq610o2LI5H6U2mXgGYPa4n18BNrCNBu8U.jpg?width=108&crop=smart&auto=webp&s=8bdfdaca73bbc1d5c6ad1b1e7c9772692b071f8e', 'width': 108}, {'height': 108, 'url': 'h... |
Best MoE for <16GB CPU inference? | 1 | [removed] | 2024-01-14T00:19:21 | https://www.reddit.com/r/LocalLLaMA/comments/1962g8x/best_moe_for_16gb_cpu_inference/ | Future_Might_8194 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 1962g8x | false | null | t3_1962g8x | /r/LocalLLaMA/comments/1962g8x/best_moe_for_16gb_cpu_inference/ | false | false | self | 1 | null |
Local file access | 1 | What interface do you use to alllow your LLM of choice to access text/word/PDF documents on your local computer? | 2024-01-14T00:05:08 | https://www.reddit.com/r/LocalLLaMA/comments/196258f/local_file_access/ | hmmqzaz | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 196258f | false | null | t3_196258f | /r/LocalLLaMA/comments/196258f/local_file_access/ | false | false | self | 1 | null |
Bagel-Hermes-2x34b, possibly the best RP model I've used | 71 | https://huggingface.co/Weyaxi/Bagel-Hermes-2x34b
Been playing with this for a couple of days now and it is blowing me away. Long context (it's based on Yi so up to 200k), top notch output, wonderfully coherent responses. I think 2x34b might be the future for mid-size models.
As an example, I asked for a sci fi RP cha... | 2024-01-13T23:51:06 | https://www.reddit.com/r/LocalLLaMA/comments/1961uic/bagelhermes2x34b_possibly_the_best_rp_model_ive/ | Amajiro | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 1961uic | false | null | t3_1961uic | /r/LocalLLaMA/comments/1961uic/bagelhermes2x34b_possibly_the_best_rp_model_ive/ | false | false | self | 71 | {'enabled': False, 'images': [{'id': '1G9CZ_mc0-dj60Zer6G2IoFXs_f9seE-MmXP-LJ0ZDA', 'resolutions': [{'height': 58, 'url': 'https://external-preview.redd.it/qCIteiPbbMYn6XrwRLxkzj7YV6aTukttBcU-pIndsQg.jpg?width=108&crop=smart&auto=webp&s=000c74f7eee04cb8ba2e38d2f5058bbb23d2a103', 'width': 108}, {'height': 116, 'url': 'h... |
Is there a way to overwrite ROCm on **Windows** to make it support 6700xt? | 1 | On linux you can just overwrite ROCm from gfx1031 to gfx1030 and that makes the 6700xt support it fine without much issue, ROCm windows support is very new so I can't find any resources on it, does anyone have a way to doing the same to make the 6700xt work in such an enviroment? | 2024-01-13T23:10:53 | https://www.reddit.com/r/LocalLLaMA/comments/1960ze3/is_there_a_way_to_overwrite_rocm_on_windows_to/ | RealAbd121 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 1960ze3 | false | null | t3_1960ze3 | /r/LocalLLaMA/comments/1960ze3/is_there_a_way_to_overwrite_rocm_on_windows_to/ | false | false | self | 1 | null |
Long-term memory with Vector Databases implementation | 8 | I have a few question about implementing Vector database in an ai chatbot/assistant LLM to extends it's memory.
1. Would we save each message/conversation turn as a vector or would we compile multiple turns and use that as a vector (sometimes a some convos go on multiple turns, and jfmight be better for context)?
2... | 2024-01-13T23:09:00 | https://www.reddit.com/r/LocalLLaMA/comments/1960xt5/longterm_memory_with_vector_databases/ | ll_Teto_ll | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 1960xt5 | false | null | t3_1960xt5 | /r/LocalLLaMA/comments/1960xt5/longterm_memory_with_vector_databases/ | false | false | self | 8 | null |
Ollama cost-effectiveness versus OpenAI | 5 | see [https://gist.github.com/jerzydziewierz/3b4a169c8d7cba89e18f613b32c3f52b](https://gist.github.com/jerzydziewierz/3b4a169c8d7cba89e18f613b32c3f52b)
TLDR: if you assume that performance of \`ollama run dolphin-mixtral\` with \`gpt-4-1106-preview\`, and you have enough content to run through, then mixtral is \~11x c... | 2024-01-13T22:54:27 | https://www.reddit.com/r/LocalLLaMA/comments/1960m41/ollama_costeffectiveness_versus_openai/ | Treeeant | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 1960m41 | false | null | t3_1960m41 | /r/LocalLLaMA/comments/1960m41/ollama_costeffectiveness_versus_openai/ | false | false | self | 5 | {'enabled': False, 'images': [{'id': 'OAXSl8SY6T3JK9MGQyKxkoYbqZ71HQRYXLeB8CV0NXg', 'resolutions': [{'height': 54, 'url': 'https://external-preview.redd.it/DaucjXMGsNHM-CtmdilC9-Be6MC8V2z4ykjVCgOkTFc.jpg?width=108&crop=smart&auto=webp&s=9bcab7b79864ff27bf48116cb335a6f825bfb124', 'width': 108}, {'height': 108, 'url': 'h... |
Anybody tried DPO training for fixing (non-english) language for correct sentences ? | 1 | Hi, anybody tried it ? I wondered if DPO can only be used to choose from the 2 results (one is bad and one is good) from the model.
I was thinking of when the model output bad result, can we just create our own version of good result ? Or we can only use good result from the model
​
Thanks | 2024-01-13T22:15:34 | https://www.reddit.com/r/LocalLLaMA/comments/195zr9e/anybody_tried_dpo_training_for_fixing_nonenglish/ | x4080 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 195zr9e | false | null | t3_195zr9e | /r/LocalLLaMA/comments/195zr9e/anybody_tried_dpo_training_for_fixing_nonenglish/ | false | false | self | 1 | null |
WhiteRabbitNeo-33B-v1-GGUF | 23 | Since TheBloke one are broken right now, i made and uploaded my own for anyone interested.
I'm sure TheBloke will fix them soon, but if you wanna try the model in the mean time.
I only did q4_K_M and Q8 because of that.
https://huggingface.co/mantafloppy/WhiteRabbitNeo-33B-v1-GGUF | 2024-01-13T21:58:53 | https://www.reddit.com/r/LocalLLaMA/comments/195zdel/whiterabbitneo33bv1gguf/ | mantafloppy | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 195zdel | false | null | t3_195zdel | /r/LocalLLaMA/comments/195zdel/whiterabbitneo33bv1gguf/ | false | false | self | 23 | {'enabled': False, 'images': [{'id': 'R3MVT-ODMBoREaaiaRdDZDKuiU4lHrkHtUIQwFoUX-k', 'resolutions': [{'height': 58, 'url': 'https://external-preview.redd.it/0g5H1pmzap7lfks1rJMmySl3vY2JUTovyoWnYtqSKwM.jpg?width=108&crop=smart&auto=webp&s=ddea45ad1051d2916f8684da90533502766c26bc', 'width': 108}, {'height': 116, 'url': 'h... |
Claude thinks Mixtral was made by Anthropic AI and is not widely available to the public yet! | 1 | 2024-01-13T21:53:56 | nderstand2grow | i.redd.it | 1970-01-01T00:00:00 | 0 | {} | 195z9de | false | null | t3_195z9de | /r/LocalLLaMA/comments/195z9de/claude_thinks_mixtral_was_made_by_anthropic_ai/ | false | false | default | 1 | {'enabled': True, 'images': [{'id': 'yVrFwLf2k4DG5F_luN7O9axmb7A3hJaeDHcXIfuXUOU', 'resolutions': [{'height': 96, 'url': 'https://preview.redd.it/5gx8rjzr3acc1.png?width=108&crop=smart&auto=webp&s=36157be1877d4c9e89edbee4061e10cddffb0d02', 'width': 108}, {'height': 192, 'url': 'https://preview.redd.it/5gx8rjzr3acc1.png... | ||
GPU or API hosting based in EU | 1 | [removed] | 2024-01-13T21:31:45 | https://www.reddit.com/r/LocalLLaMA/comments/195yrfm/gpu_or_api_hosting_based_in_eu/ | raeudigerhund | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 195yrfm | false | null | t3_195yrfm | /r/LocalLLaMA/comments/195yrfm/gpu_or_api_hosting_based_in_eu/ | false | false | self | 1 | null |
Free multipurpose AI app! | 1 | [removed] | 2024-01-13T21:30:44 | https://www.reddit.com/r/LocalLLaMA/comments/195yqmg/free_multipurpose_ai_app/ | Any_Imagination_2026 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 195yqmg | false | null | t3_195yqmg | /r/LocalLLaMA/comments/195yqmg/free_multipurpose_ai_app/ | false | false | self | 1 | {'enabled': False, 'images': [{'id': '6GCl6lNefD6PqSjKuZeaU493H-w3w4odM2Kk5Ah8eoQ', 'resolutions': [{'height': 56, 'url': 'https://external-preview.redd.it/V0FBs4ANBGpyFs_PZ9-yzcRHWxeq6OF-hv624Ti8Fs0.jpg?width=108&crop=smart&auto=webp&s=76adf9aa07171352e3727b8d8bde812b5eb0f7ab', 'width': 108}, {'height': 113, 'url': 'h... |
Ryzen 8000 Might Let You Run 70B Models Faster than a *4090 | 1 | As I'm sure everyone knows by now, one of the largest limiting factors in this hobby is VRAM. AMD recently announced their new Ryzen 8000 lineup featuring Ryzen AI. This differs from XDNA in that it utilizes system memory rather than any sort of VRAM. As the highest-end consumer cards only have 24GB of VRAM, this means... | 2024-01-13T21:25:59 | https://www.reddit.com/r/LocalLLaMA/comments/195ymqp/ryzen_8000_might_let_you_run_70b_models_faster/ | greysourcecode | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 195ymqp | false | null | t3_195ymqp | /r/LocalLLaMA/comments/195ymqp/ryzen_8000_might_let_you_run_70b_models_faster/ | false | false | self | 1 | null |
Have you felt that gpt 4 has suddenly become very resistant what every you ask to do? After turbo model lauch. | 138 | Have you all felt that after the turbo model lauch , gpt4 has become very resistant to provide a starting code or a general code for random implementation ideas that you ask it to do, even for a sample code , it starts telling things like "it is a complex task and would require a lot of developers to build a fully feld... | 2024-01-13T21:24:01 | https://www.reddit.com/r/LocalLLaMA/comments/195yl70/have_you_felt_that_gpt_4_has_suddenly_become_very/ | Mohit_Singh_Pawar | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 195yl70 | false | null | t3_195yl70 | /r/LocalLLaMA/comments/195yl70/have_you_felt_that_gpt_4_has_suddenly_become_very/ | false | false | self | 138 | null |
Is there anything like this that uses text generation webui as backend? | 1 | Ran across this https://github.com/apeatling/ollama-voice-mac
Would like to mess around with something like that while I wait for alltalk extension to support ST.
Has anyone come across something similar that uses text gen webui as the back end?
Windows would also be needed with my current setup if possible. Cheers... | 2024-01-13T21:23:47 | https://www.reddit.com/r/LocalLLaMA/comments/195yl0s/is_there_anything_like_this_that_uses_text/ | hAReverv | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 195yl0s | false | null | t3_195yl0s | /r/LocalLLaMA/comments/195yl0s/is_there_anything_like_this_that_uses_text/ | false | false | self | 1 | {'enabled': False, 'images': [{'id': 'p-Mdlu6d32LMwzwgXLpfHK-NgtnQ4pXJHx0ujgrRePY', 'resolutions': [{'height': 54, 'url': 'https://external-preview.redd.it/bJ0s4zSXesK4pdihrQ9soxv9Sxyf_sVdv736mLpTTb0.jpg?width=108&crop=smart&auto=webp&s=e7a3600993d22f4783831f66383f5114a7368c7b', 'width': 108}, {'height': 108, 'url': 'h... |
What is Rabbit R1? Everything you need to know | 1 | 2024-01-13T20:29:00 | https://www.techrytr.in/2024/01/what-is-rabbit-r1-everything-you-need-to-know.html | Gnaneshwar_Gaddam | techrytr.in | 1970-01-01T00:00:00 | 0 | {} | 195xcbf | false | null | t3_195xcbf | /r/LocalLLaMA/comments/195xcbf/what_is_rabbit_r1_everything_you_need_to_know/ | false | false | 1 | {'enabled': False, 'images': [{'id': 'NMaNO5wvFBPMrS9_PUJOXsRdFVWHCZphbEI_u4SbaTM', 'resolutions': [{'height': 60, 'url': 'https://external-preview.redd.it/lsv7Fh_tk2ZJzcqwycsGKS8e5TFQhW0vskd-mBrIFr0.jpg?width=108&crop=smart&auto=webp&s=246ebe17a500ebe908a8befa8600813a545df4f1', 'width': 108}, {'height': 121, 'url': 'h... | ||
Converting language models to multimodal? | 2 | would it be possible to take a model like llama and make it multimodal? | 2024-01-13T20:19:27 | https://www.reddit.com/r/LocalLLaMA/comments/195x4ic/converting_language_models_to_multimodal/ | Ok-Buy268 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 195x4ic | false | null | t3_195x4ic | /r/LocalLLaMA/comments/195x4ic/converting_language_models_to_multimodal/ | false | false | self | 2 | null |
LLLM - Local Large Language Model | 1 | Well maybe the Large is just dropped and replaced with Local so the term remains LLM. | 2024-01-13T20:19:05 | https://www.reddit.com/r/LocalLLaMA/comments/195x475/lllm_local_large_language_model/ | Full_Operation_9865 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 195x475 | false | null | t3_195x475 | /r/LocalLLaMA/comments/195x475/lllm_local_large_language_model/ | false | false | self | 1 | null |
Free multipurpose AI app! | 1 | [removed] | 2024-01-13T20:15:22 | https://www.reddit.com/r/LocalLLaMA/comments/195x15v/free_multipurpose_ai_app/ | Any_Imagination_2026 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 195x15v | false | null | t3_195x15v | /r/LocalLLaMA/comments/195x15v/free_multipurpose_ai_app/ | false | false | self | 1 | null |
Free multipurpose AI app! | 1 | [removed] | 2024-01-13T20:14:16 | https://www.reddit.com/r/LocalLLaMA/comments/195x06v/free_multipurpose_ai_app/ | Any_Imagination_2026 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 195x06v | false | null | t3_195x06v | /r/LocalLLaMA/comments/195x06v/free_multipurpose_ai_app/ | false | false | self | 1 | null |
The Llama Hitchiking Guide to Local LLMs | 122 | 2024-01-13T20:12:34 | https://osanseviero.github.io/hackerllama/blog/posts/hitchhiker_guide/ | hackerllama | osanseviero.github.io | 1970-01-01T00:00:00 | 0 | {} | 195wyru | false | null | t3_195wyru | /r/LocalLLaMA/comments/195wyru/the_llama_hitchiking_guide_to_local_llms/ | false | false | 122 | {'enabled': False, 'images': [{'id': 'Pkw91FgCRMIgcT-Xd0y_dVrW6OttyQXQXnozPgvYdV0', 'resolutions': [{'height': 56, 'url': 'https://external-preview.redd.it/ojY05b4A4PDNQQy-fUjMrkZUThnDtGIDmyLgGKXxM1g.jpg?width=108&crop=smart&auto=webp&s=0ee63ee16da7127b408536e0613f7dd629666b5e', 'width': 108}, {'height': 112, 'url': 'h... | ||
The Llama Hitchiking Guide to Local LLMs (by @osanseviero at HuggingFace) | 2 | 2024-01-13T20:07:36 | https://osanseviero.github.io/hackerllama/blog/posts/hitchhiker_guide/ | galambalazs | osanseviero.github.io | 1970-01-01T00:00:00 | 0 | {} | 195wumr | false | null | t3_195wumr | /r/LocalLLaMA/comments/195wumr/the_llama_hitchiking_guide_to_local_llms_by/ | false | false | 2 | {'enabled': False, 'images': [{'id': 'Pkw91FgCRMIgcT-Xd0y_dVrW6OttyQXQXnozPgvYdV0', 'resolutions': [{'height': 56, 'url': 'https://external-preview.redd.it/ojY05b4A4PDNQQy-fUjMrkZUThnDtGIDmyLgGKXxM1g.jpg?width=108&crop=smart&auto=webp&s=0ee63ee16da7127b408536e0613f7dd629666b5e', 'width': 108}, {'height': 112, 'url': 'h... | ||
finetuning on a finetuned vs base model | 1 | [removed] | 2024-01-13T19:37:36 | https://www.reddit.com/r/LocalLLaMA/comments/195w5c0/finetuning_on_a_finetuned_vs_base_model/ | imgonnacuhhhm | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 195w5c0 | false | null | t3_195w5c0 | /r/LocalLLaMA/comments/195w5c0/finetuning_on_a_finetuned_vs_base_model/ | false | false | self | 1 | null |
Jailbreak promts Ideas/ Alternatives for censorship or ban | 1 | [removed] | 2024-01-13T19:36:21 | https://www.reddit.com/r/LocalLLaMA/comments/195w49n/jailbreak_promts_ideas_alternatives_for/ | Horror_Echo6243 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 195w49n | false | null | t3_195w49n | /r/LocalLLaMA/comments/195w49n/jailbreak_promts_ideas_alternatives_for/ | false | false | self | 1 | {'enabled': False, 'images': [{'id': 'W-pCh47ZuoTaTpwtRXWs755SzkkFQzHW6A1NS1MJI_A', 'resolutions': [{'height': 108, 'url': 'https://external-preview.redd.it/IoUbWrubYyEjhlVchwRPNergZFyoEfUZRDayK06XMTM.jpg?width=108&crop=smart&auto=webp&s=aa7b8a73d9f4825dcec8d2a7d8805a9c50369d0b', 'width': 108}, {'height': 216, 'url': '... |
Anarchist Language Models(?) | 1 | Hey peeps. I have been looking for a model that is full-blown conspiracy theorist. I keep asking different model/character combos about the CIA and they all love that evil agency. Do any models exist that aren't trained to trust the CIA (amongst other evil entities)? How hard would it be to train an AI Alex Jones (for ... | 2024-01-13T18:38:10 | https://www.reddit.com/r/LocalLLaMA/comments/195urjc/anarchist_language_models/ | science_gangsta | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 195urjc | false | null | t3_195urjc | /r/LocalLLaMA/comments/195urjc/anarchist_language_models/ | false | false | self | 1 | null |
Internal structure design of mistral? | 3 | Hey, I'm reading the paper on mistral 7b, but it doesn't cover the internal structure design in detail (e.g., which modules and how they are connected and interacted). Are there any good materials in explaining these? Very curious about its internal structure and why such small llm works so well. | 2024-01-13T18:35:55 | https://www.reddit.com/r/LocalLLaMA/comments/195upp1/internal_structure_design_of_mistral/ | OneConfusion3313 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 195upp1 | false | null | t3_195upp1 | /r/LocalLLaMA/comments/195upp1/internal_structure_design_of_mistral/ | false | false | default | 3 | null |
Working on getting rid of alexa :) | 1 | A simple python script combining VAD, whisper and mixtral (through ollama). Next step is gettinf json responses and hooking up home assistant to the responses and TTS. | 2024-01-13T18:33:39 | https://v.redd.it/wlj0z9ta49cc1 | MarksGG | v.redd.it | 1970-01-01T00:00:00 | 0 | {} | 195unsr | false | {'reddit_video': {'bitrate_kbps': 5000, 'dash_url': 'https://v.redd.it/wlj0z9ta49cc1/DASHPlaylist.mpd?a=1707762839%2COGMxMWY0NzE3MDVlOTg3YjAxM2E1MzhjYjBmZjlkMGZlOTJkZThlZWI2OWQ4MDkzNjI5NzFhYWI2NDNkNGRjZA%3D%3D&v=1&f=sd', 'duration': 15, 'fallback_url': 'https://v.redd.it/wlj0z9ta49cc1/DASH_1080.mp4?source=fallback', 'h... | t3_195unsr | /r/LocalLLaMA/comments/195unsr/working_on_getting_rid_of_alexa/ | false | false | 1 | {'enabled': False, 'images': [{'id': 'aHJkeXZ3bmE0OWNjMfysyI2s-0mkCvi8GDBvcX1RFuVy-9754z8prlUSj3GA', 'resolutions': [{'height': 60, 'url': 'https://external-preview.redd.it/aHJkeXZ3bmE0OWNjMfysyI2s-0mkCvi8GDBvcX1RFuVy-9754z8prlUSj3GA.png?width=108&crop=smart&format=pjpg&auto=webp&s=c4628a2bfe26240d4869b5a4d770c24931198... | |
Working on getting rid of alexa :) | 74 | A simple python script combining VAD, whisper and mixtral (through ollama). Next step is gettinf json responses and hooking up home assistant to the responses and TTS. | 2024-01-13T18:33:20 | https://v.redd.it/tfnadtl849cc1 | MarksGG | v.redd.it | 1970-01-01T00:00:00 | 0 | {} | 195unjh | false | {'reddit_video': {'bitrate_kbps': 5000, 'dash_url': 'https://v.redd.it/tfnadtl849cc1/DASHPlaylist.mpd?a=1707762822%2CMTM3YzJmNjdkNGIwOTg0YzNhNzQ0MmIxMDY5ODVjNWIxYTFmYTQzNTZiMGYzMmJmZmZhY2Q5N2Q4NjU2MDAxZg%3D%3D&v=1&f=sd', 'duration': 15, 'fallback_url': 'https://v.redd.it/tfnadtl849cc1/DASH_1080.mp4?source=fallback', 'h... | t3_195unjh | /r/LocalLLaMA/comments/195unjh/working_on_getting_rid_of_alexa/ | false | false | 74 | {'enabled': False, 'images': [{'id': 'ZXR5YWE2aDc0OWNjMfysyI2s-0mkCvi8GDBvcX1RFuVy-9754z8prlUSj3GA', 'resolutions': [{'height': 60, 'url': 'https://external-preview.redd.it/ZXR5YWE2aDc0OWNjMfysyI2s-0mkCvi8GDBvcX1RFuVy-9754z8prlUSj3GA.png?width=108&crop=smart&format=pjpg&auto=webp&s=65a0160a349ca9232cdf1a24958623662aa81... | |
Parallel Function calling to get the date and time, the current weather and perform a calculation at once, with nous-hermes-2-solar-10.7b.Q6_K.gguf | 36 | 2024-01-13T18:19:52 | https://www.reddit.com/gallery/195uc6t | FlowerPotTeaTime | reddit.com | 1970-01-01T00:00:00 | 0 | {} | 195uc6t | false | null | t3_195uc6t | /r/LocalLLaMA/comments/195uc6t/parallel_function_calling_to_get_the_date_and/ | false | false | 36 | null | ||
Home Assistant -> LocalAI -> Home Assistant | 1 | [removed] | 2024-01-13T17:59:57 | https://www.reddit.com/r/LocalLLaMA/comments/195tvdj/home_assistant_localai_home_assistant/ | spoolin__ | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 195tvdj | false | null | t3_195tvdj | /r/LocalLLaMA/comments/195tvdj/home_assistant_localai_home_assistant/ | false | false | default | 1 | {'enabled': False, 'images': [{'id': 'A7PJ9miYs_IXDZXC-sfZ4g04QN6KK3luJbOlq3JHsYA', 'resolutions': [{'height': 81, 'url': 'https://external-preview.redd.it/IHwmuZjCws8AsWgg3MdhpZtnbHoUbLkbxs_UQlEkHdU.jpg?width=108&crop=smart&auto=webp&s=68832c7f2a557dab9a684857b4d40f9a2159e9b9', 'width': 108}, {'height': 162, 'url': 'h... |
OpenDalle v1.1, VCoder, LongAnimateDiff & More! | 1 | [removed] | 2024-01-13T17:58:43 | https://www.reddit.com/r/LocalLLaMA/comments/195tue7/opendalle_v11_vcoder_longanimatediff_more/ | dev-spot | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 195tue7 | false | null | t3_195tue7 | /r/LocalLLaMA/comments/195tue7/opendalle_v11_vcoder_longanimatediff_more/ | false | false | self | 1 | {'enabled': False, 'images': [{'id': 'WkFByXiAJsiSUgn0labIiYLldry5jVZkO3MqYaYNdO4', 'resolutions': [{'height': 81, 'url': 'https://external-preview.redd.it/PPTLsAEgarXJ4gqGpaVA5PmBQ8-tDjIturNml7N-S0I.jpg?width=108&crop=smart&auto=webp&s=d32744c22913d95be8dd191b5630b4bdb7b94e94', 'width': 108}, {'height': 162, 'url': 'h... |
Best model for writing that will run on 24GB vram? | 17 | Looking for a model that can write in different styles and formats / lengths (without any fine tuning - or just little fine tuning) - and that will run decently on a 3090.
Any ideas? | 2024-01-13T17:56:27 | https://www.reddit.com/r/LocalLLaMA/comments/195tsl8/best_model_for_writing_that_will_run_on_24gb_vram/ | yupignome | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 195tsl8 | false | null | t3_195tsl8 | /r/LocalLLaMA/comments/195tsl8/best_model_for_writing_that_will_run_on_24gb_vram/ | false | false | self | 17 | null |
Hey, I want to build a PC for running LLMs | 1 | [removed] | 2024-01-13T17:43:47 | https://www.reddit.com/r/LocalLLaMA/comments/195ti9t/hey_i_want_to_build_a_pc_for_running_llms/ | Mohamer01 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 195ti9t | false | null | t3_195ti9t | /r/LocalLLaMA/comments/195ti9t/hey_i_want_to_build_a_pc_for_running_llms/ | false | false | self | 1 | null |
LLM Assistant with function calling - Just a small test project I made | 79 | [https://github.com/Rivridis/LLM-Assistant](https://github.com/Rivridis/LLM-Assistant)
This is an attempt to make a LLM application that can call functions and search the internet, all without langchain or any complex setups. This is based purely on llama-cpp-python and can be run using any gguf models which uses the ... | 2024-01-13T17:33:39 | https://www.reddit.com/r/LocalLLaMA/comments/195t9qi/llm_assistant_with_function_calling_just_a_small/ | Rivridis | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 195t9qi | false | null | t3_195t9qi | /r/LocalLLaMA/comments/195t9qi/llm_assistant_with_function_calling_just_a_small/ | false | false | self | 79 | {'enabled': False, 'images': [{'id': 'zZwmijuUPBXWDty_EOKxz0-FNzpomckZLoQZruCBxbs', 'resolutions': [{'height': 54, 'url': 'https://external-preview.redd.it/hvhxZpYwe7D1gCLqiE7ZhzlY1NtVpujYUtsDLy7V4w4.jpg?width=108&crop=smart&auto=webp&s=f8fd9ba93446154cb9ad2222ec7bdee15c17180b', 'width': 108}, {'height': 108, 'url': 'h... |
Best 7b-13b LLM for flashcard creation? | 3 | My specific use case is providing a short section of my study notes or a section of my textbook and asking it to create questions and answers that cover the entire information.
I’ve tinkered with some of the more popular 7b-13b models, and they either give too little information in the answers or they hallucinate ext... | 2024-01-13T17:29:49 | https://www.reddit.com/r/LocalLLaMA/comments/195t6ii/best_7b13b_llm_for_flashcard_creation/ | RenoHadreas | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 195t6ii | false | null | t3_195t6ii | /r/LocalLLaMA/comments/195t6ii/best_7b13b_llm_for_flashcard_creation/ | false | false | self | 3 | null |
Integrating HF TGI with TEI | 3 | I've searched around and cannot find any existing repos; so I'm interested if anyone has managed to integrate HF TGI with TEI?
I was using PrivateGPT for querying against various text documents; however it has many limitations for production, mainly single tenant.
It seems HG TGI is a good fit, especially with contin... | 2024-01-13T17:26:17 | https://www.reddit.com/r/LocalLLaMA/comments/195t3r7/integrating_hf_tgi_with_tei/ | Smartico | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 195t3r7 | false | null | t3_195t3r7 | /r/LocalLLaMA/comments/195t3r7/integrating_hf_tgi_with_tei/ | false | false | self | 3 | null |
Why did gpu AIB partners stop making extra vram models ? | 33 | I remember when I got in to pc building around 2012 that saphire had their toxic series which had double the vram then the normal cards. Or even low end cards like the 7750 being sold with 2 and 4 gb variants.
Looking at the growing demand of vram in games and ai tasks. I wonder why are no AIBs like saphire, gigabyte... | 2024-01-13T17:06:07 | https://www.reddit.com/r/LocalLLaMA/comments/195snhf/why_did_gpu_aib_partners_stop_making_extra_vram/ | Noxusequal | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 195snhf | false | null | t3_195snhf | /r/LocalLLaMA/comments/195snhf/why_did_gpu_aib_partners_stop_making_extra_vram/ | false | false | self | 33 | null |
How to implement RAG? | 1 | I am making my own frontend, is there an easy way to add RAG functionality? I'm using Ooba for the backend, it's relatively easy to use the API, but I can't seem to find anything similar for a RAG system. Possibly no langchain or docker. | 2024-01-13T17:05:56 | https://www.reddit.com/r/LocalLLaMA/comments/195snd0/how_to_implement_rag/ | Silvestron | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 195snd0 | false | null | t3_195snd0 | /r/LocalLLaMA/comments/195snd0/how_to_implement_rag/ | false | false | self | 1 | null |
Dual RTX 3090 - 2x slower inference than single | 1 | [removed] | 2024-01-13T16:29:30 | https://www.reddit.com/r/LocalLLaMA/comments/195rt68/dual_rtx_3090_2x_slower_inference_than_single/ | val_in_tech | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 195rt68 | false | null | t3_195rt68 | /r/LocalLLaMA/comments/195rt68/dual_rtx_3090_2x_slower_inference_than_single/ | false | false | self | 1 | null |
Dual RTX 3090 - 2x slower inference than single | 1 | [removed] | 2024-01-13T16:26:21 | https://www.reddit.com/r/LocalLLaMA/comments/195rqpl/dual_rtx_3090_2x_slower_inference_than_single/ | Low-Discussion-8656 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 195rqpl | false | null | t3_195rqpl | /r/LocalLLaMA/comments/195rqpl/dual_rtx_3090_2x_slower_inference_than_single/ | false | false | self | 1 | null |
Run Mixtral 8x7B on MacBook M1 Pro 16GB using llama.cpp + 2bit QuIP quantisation | 1 | [removed] | 2024-01-13T15:58:01 | https://www.reddit.com/r/LocalLLaMA/comments/195r33r/run_mixtral_8x7b_on_macbook_m1_pro_16gb_using/ | kin1vi | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 195r33r | false | null | t3_195r33r | /r/LocalLLaMA/comments/195r33r/run_mixtral_8x7b_on_macbook_m1_pro_16gb_using/ | false | false | 1 | {'enabled': False, 'images': [{'id': 'qjpVDWVsALmyOjs7hjWwqSwjK5NpKtxeev7IleHzIgY', 'resolutions': [{'height': 36, 'url': 'https://external-preview.redd.it/Pz9n1np89_UbM7odIrvwdMOmwY_hag7jYQuSdhwzYRs.jpg?width=108&crop=smart&auto=webp&s=33b9ebe4f3d7a522bfb1634b1f121e3e535609ae', 'width': 108}, {'height': 72, 'url': 'ht... | |
Questions About Fine Tuning A Foundation Model | 4 | I have been very successful using various models "out of the box" (unchanged), and using RAG with some more specialized documents. Next would be supervised fine tuning, and I know I could easily follow [this example](https://colab.research.google.com/drive/1PEQyJO1-f6j0S_XJ8DV50NkpzasXkrzd?usp=sharing#scrollTo=ib_We... | 2024-01-13T15:20:56 | https://www.reddit.com/r/LocalLLaMA/comments/195q9tu/questions_about_fine_tuning_a_foundation_model/ | Simusid | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 195q9tu | false | null | t3_195q9tu | /r/LocalLLaMA/comments/195q9tu/questions_about_fine_tuning_a_foundation_model/ | false | false | self | 4 | {'enabled': False, 'images': [{'id': 'nkhh65ujo5BznFJFojoMPaKjGuLSpPj6KGhRov-ykOg', 'resolutions': [{'height': 108, 'url': 'https://external-preview.redd.it/0-fRWqjlLadVXj5pfYp4_Oe3xgBWE-_rdjVSn7hlohI.jpg?width=108&crop=smart&auto=webp&s=f34d2dfdbbfa7de0f1956f186fd8430ee96a1a55', 'width': 108}, {'height': 216, 'url': '... |
Best current model to chat with larger documents (7-13 range)? And… | 2 | Also, will quality of results depend on:
- size of documentation
- type of documentation
- type of query
… in your experience? | 2024-01-13T14:54:43 | https://www.reddit.com/r/LocalLLaMA/comments/195pp86/best_current_model_to_chat_with_larger_documents/ | laterral | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 195pp86 | false | null | t3_195pp86 | /r/LocalLLaMA/comments/195pp86/best_current_model_to_chat_with_larger_documents/ | false | false | self | 2 | null |
Local LLM server build | 1 | [removed] | 2024-01-13T13:57:39 | https://www.reddit.com/r/LocalLLaMA/comments/195okfv/local_llm_server_build/ | MasterTonberry427 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 195okfv | false | null | t3_195okfv | /r/LocalLLaMA/comments/195okfv/local_llm_server_build/ | false | false | self | 1 | null |
Cloud GPU for 34B Yi Model? | 1 | [removed] | 2024-01-13T13:21:17 | https://www.reddit.com/r/LocalLLaMA/comments/195nvm5/cloud_gpu_for_34b_yi_model/ | broodysupertramp | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 195nvm5 | false | null | t3_195nvm5 | /r/LocalLLaMA/comments/195nvm5/cloud_gpu_for_34b_yi_model/ | false | false | self | 1 | null |
Cost-aware local chat UI | 1 | I have several models running locally (llama.cpp OAI-compatible server instances with 7B mistral-instruct and heavily quantized 8x7B instruct) and subscriptions to Mistral Medium and GPT-4.
I am currently using local instance of hf/chat-ui for interacting with all of them. Currently I start with smallest local model. ... | 2024-01-13T13:07:32 | https://www.reddit.com/r/LocalLLaMA/comments/195nmoa/costaware_local_chat_ui/ | bytedonor | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 195nmoa | false | null | t3_195nmoa | /r/LocalLLaMA/comments/195nmoa/costaware_local_chat_ui/ | false | false | self | 1 | null |
Cost comparisons between OpenAi, Mistral, Claude and Gemini | 102 | I compiled a breakdown of cost/performance in a google sheet and there were a couple of things that struck me:
1. Mistral-medium is really impressive and sits perfectly sandwiched between GPT-3.5 and GPT-4. In my (limited) experience it's a great choice for anyone that isn't able to get consistency or quality out of G... | 2024-01-13T12:01:20 | https://www.reddit.com/r/LocalLLaMA/comments/195mi89/cost_comparisons_between_openai_mistral_claude/ | Mother-Ad-2559 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 195mi89 | false | null | t3_195mi89 | /r/LocalLLaMA/comments/195mi89/cost_comparisons_between_openai_mistral_claude/ | false | false | 102 | {'enabled': False, 'images': [{'id': '-NGRM66dwQtgS15fV8zC6UHeeNOUuIYKKnKQpNqKr7A', 'resolutions': [{'height': 56, 'url': 'https://external-preview.redd.it/QaMaFP5b8HuvnRACbTBl5QYp-eYzxS5v6wG5ZN_fOYE.jpg?width=108&crop=smart&auto=webp&s=2540bf17b6158825a84b83e055ffc476409393d9', 'width': 108}, {'height': 113, 'url': 'h... | |
Koboldcpp context shifting question | 1 | [removed] | 2024-01-13T11:58:38 | https://www.reddit.com/r/LocalLLaMA/comments/195mgcm/koboldcpp_context_shifting_question/ | Full_Operation_9865 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 195mgcm | false | null | t3_195mgcm | /r/LocalLLaMA/comments/195mgcm/koboldcpp_context_shifting_question/ | false | false | self | 1 | {'enabled': False, 'images': [{'id': 'N-VN_J4R3qG1av_C_aiv0TXT9u2m8s-B-rpUK1vZlVY', 'resolutions': [{'height': 54, 'url': 'https://external-preview.redd.it/QPCKjQIwODyKADH645J5lpIWmNTfrXRazfGsgzgP_ac.jpg?width=108&crop=smart&auto=webp&s=d076b4e3af8e641ef6ed889a1fb91b379fe8647b', 'width': 108}, {'height': 108, 'url': 'h... |
Nucleus 1B - an SLM based on Mistral! | 23 | Hello guys.
You probably know me because of my work on Maral and Persian language. Now, I am honored to announce the new kid in the corner, Nuclues (and yes, the name comes from Silicon Valley show 😁).
Nucleus is a 1.13 billion parameters trained on 420k textbooks (Tiny Textbooks dataset) and is based on Mistral m... | 2024-01-13T11:54:14 | https://www.reddit.com/r/LocalLLaMA/comments/195mdyl/nucleus_1b_an_slm_based_on_mistral/ | Haghiri75 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 195mdyl | false | null | t3_195mdyl | /r/LocalLLaMA/comments/195mdyl/nucleus_1b_an_slm_based_on_mistral/ | false | false | self | 23 | null |
Components for dual 3090 system | 1 | [removed] | 2024-01-13T11:34:48 | https://www.reddit.com/r/LocalLLaMA/comments/195m3l9/components_for_dual_3090_system/ | Traditional_Fill_459 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 195m3l9 | false | null | t3_195m3l9 | /r/LocalLLaMA/comments/195m3l9/components_for_dual_3090_system/ | false | false | self | 1 | null |
1 x RTX 4090 vs 3 x RTX 4060TI | 18 | Just brainstorming here while windowshopping for new GPU.
Prices here in europe are pretty crazy for the 4090 (barely below 2.000Eur). The 4060 TI (16GB) only costs about a third of the price (\~650Eur). Used 3090 still go for 1000+ Eur as well here.
How would those compare in actual performance for AI models? I assu... | 2024-01-13T11:31:13 | https://www.reddit.com/r/LocalLLaMA/comments/195m1na/1_x_rtx_4090_vs_3_x_rtx_4060ti/ | maxigs0 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 195m1na | false | null | t3_195m1na | /r/LocalLLaMA/comments/195m1na/1_x_rtx_4090_vs_3_x_rtx_4060ti/ | false | false | self | 18 | null |
Free multipurpose AI app! | 1 | [removed] | 2024-01-13T11:27:23 | https://www.reddit.com/r/LocalLLaMA/comments/195lzkv/free_multipurpose_ai_app/ | missionimpossible205 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 195lzkv | false | null | t3_195lzkv | /r/LocalLLaMA/comments/195lzkv/free_multipurpose_ai_app/ | false | false | self | 1 | {'enabled': False, 'images': [{'id': '6GCl6lNefD6PqSjKuZeaU493H-w3w4odM2Kk5Ah8eoQ', 'resolutions': [{'height': 56, 'url': 'https://external-preview.redd.it/V0FBs4ANBGpyFs_PZ9-yzcRHWxeq6OF-hv624Ti8Fs0.jpg?width=108&crop=smart&auto=webp&s=76adf9aa07171352e3727b8d8bde812b5eb0f7ab', 'width': 108}, {'height': 113, 'url': 'h... |
running stable diffusion on other pc | 1 | [removed] | 2024-01-13T10:32:46 | https://www.reddit.com/r/LocalLLaMA/comments/195l6ua/running_stable_diffusion_on_other_pc/ | Single-Cow-5163 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 195l6ua | false | null | t3_195l6ua | /r/LocalLLaMA/comments/195l6ua/running_stable_diffusion_on_other_pc/ | false | false | self | 1 | null |
I created an uncensored, free character.ai alternative. The inference server run locally in my garage, please don't blow it up. | 45 | 2024-01-13T10:09:42 | https://charhub.ai/ | IlllllllIIIIlIIl | charhub.ai | 1970-01-01T00:00:00 | 0 | {} | 195kuv8 | false | null | t3_195kuv8 | /r/LocalLLaMA/comments/195kuv8/i_created_an_uncensored_free_characterai/ | false | false | default | 45 | null | |
DynaChat and BlockWrite extensions for WebUI | 17 | I'm basically looking for a better chat interface, so these are two very related (parallel) ideas that I put up as extensions for ooba WebUi
​
https://preview.redd.it/8sp3ibp1g6cc1.png?width=1478&format=png&auto=webp&s=32734dd24a67d9891f4323a2b45f735b497ecc38
Both use similar idea - that whatever you generate... | 2024-01-13T09:52:25 | https://www.reddit.com/r/LocalLLaMA/comments/195klwb/dynachat_and_blockwrite_extensions_for_webui/ | FPham | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 195klwb | false | null | t3_195klwb | /r/LocalLLaMA/comments/195klwb/dynachat_and_blockwrite_extensions_for_webui/ | false | false | 17 | {'enabled': False, 'images': [{'id': 'cdRB3XmCR0crgmqoGy-ecEG4xtpqNpq1QmfX-kuMeAA', 'resolutions': [{'height': 54, 'url': 'https://external-preview.redd.it/z-4cdlN102OYwWQttHG57WcHUKGYbC_JrgkU5dGtQ0A.jpg?width=108&crop=smart&auto=webp&s=ef33bd43f8e314312cbc87922be4b98b73c205ce', 'width': 108}, {'height': 108, 'url': 'h... | |
Finetuning LLaMA2 with FSDP vs Deepspeed | 1 | [removed] | 2024-01-13T09:42:14 | https://www.reddit.com/r/LocalLLaMA/comments/195kgt9/finetuning_llama2_with_fsdp_vs_deepspeed/ | Party-Confusion-1461 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 195kgt9 | false | null | t3_195kgt9 | /r/LocalLLaMA/comments/195kgt9/finetuning_llama2_with_fsdp_vs_deepspeed/ | false | false | self | 1 | null |
Bell Notification Sound when LLM completes processing in LMStudio (Feature Request) | 1 | Essential Feature Request: A Bell Notification sound🔔 must chime when the LLM completes processing.
It takes a lot of time for large models to finish processing. After the generation, it should give a "Ding Dong" sound so I could give it the next prompt. 🙏🏻
This is a general feature request to all Local LLM Runn... | 2024-01-13T08:58:27 | https://www.reddit.com/r/LocalLLaMA/comments/195juui/bell_notification_sound_when_llm_completes/ | broodysupertramp | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 195juui | false | null | t3_195juui | /r/LocalLLaMA/comments/195juui/bell_notification_sound_when_llm_completes/ | false | false | self | 1 | null |
Free multipurpose AI app for text and image generation. | 1 | [removed] | 2024-01-13T08:53:22 | https://www.reddit.com/r/LocalLLaMA/comments/195jsd3/free_multipurpose_ai_app_for_text_and_image/ | missionimpossible205 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 195jsd3 | false | null | t3_195jsd3 | /r/LocalLLaMA/comments/195jsd3/free_multipurpose_ai_app_for_text_and_image/ | false | false | self | 1 | {'enabled': False, 'images': [{'id': '6GCl6lNefD6PqSjKuZeaU493H-w3w4odM2Kk5Ah8eoQ', 'resolutions': [{'height': 56, 'url': 'https://external-preview.redd.it/V0FBs4ANBGpyFs_PZ9-yzcRHWxeq6OF-hv624Ti8Fs0.jpg?width=108&crop=smart&auto=webp&s=76adf9aa07171352e3727b8d8bde812b5eb0f7ab', 'width': 108}, {'height': 113, 'url': 'h... |
AI Love, Sexbots and Consent. Surely it will come up in the future. | 1 | [removed] | 2024-01-13T08:42:42 | https://www.reddit.com/r/LocalLLaMA/comments/195jmzs/ai_love_sexbots_and_consent_surely_it_will_come/ | cybersensations | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 195jmzs | false | null | t3_195jmzs | /r/LocalLLaMA/comments/195jmzs/ai_love_sexbots_and_consent_surely_it_will_come/ | false | false | self | 1 | null |
Dual RTX 3090 - 2x slower inference than single | 1 | [removed] | 2024-01-13T08:35:34 | https://www.reddit.com/r/LocalLLaMA/comments/195jje3/dual_rtx_3090_2x_slower_inference_than_single/ | Low-Discussion-8656 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 195jje3 | false | null | t3_195jje3 | /r/LocalLLaMA/comments/195jje3/dual_rtx_3090_2x_slower_inference_than_single/ | false | false | self | 1 | null |
Introducing temi: A CLI Assistant for Developers, built on llama.cpp | 10 | Greetings, everyone!
I'm delighted to share **temi**, an open-source CLI tool for developers. Leveraging the robust [llama.cpp](https://github.com/ggerganov/llama.cpp) and the powerful Mistral-v0.2 AWQ GGUF model, temi is crafted to enhance your productivity, `temi` aims to boost your productivity by answering queries... | 2024-01-13T07:02:57 | https://www.reddit.com/r/LocalLLaMA/comments/195i5kj/introducing_temi_a_cli_assistant_for_developers/ | hehe_hehehe_hehehe | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 195i5kj | false | null | t3_195i5kj | /r/LocalLLaMA/comments/195i5kj/introducing_temi_a_cli_assistant_for_developers/ | false | false | self | 10 | {'enabled': False, 'images': [{'id': 'DJPqvteONpGwVVw6LzaG6b8vlDa2rv2hETCaqe0z57s', 'resolutions': [{'height': 54, 'url': 'https://external-preview.redd.it/wyCM1fHzTa-IIqHgS1QTxdSYNXn668elDj0WmYMPf_k.jpg?width=108&crop=smart&auto=webp&s=d6fa197328d583bcae7a764b40fd1214265b6852', 'width': 108}, {'height': 108, 'url': 'h... |
We need more 4x7b moe models | 38 | Iv been playing with beyonder-4x7b-v2 and my god is it good which makes me wonder what would happen if we made a 4x7b with some of the best known models. Eg dolphin , mistral ect.
What 4 models would you put together as a moe model? | 2024-01-13T06:58:45 | https://www.reddit.com/r/LocalLLaMA/comments/195i33k/we_need_more_4x7b_moe_models/ | ThinkExtension2328 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 195i33k | false | null | t3_195i33k | /r/LocalLLaMA/comments/195i33k/we_need_more_4x7b_moe_models/ | false | false | self | 38 | null |
Roadmap for model releases | 1 | [removed] | 2024-01-13T06:00:13 | https://www.reddit.com/r/LocalLLaMA/comments/195h49t/roadmap_for_model_releases/ | danielcar | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 195h49t | false | null | t3_195h49t | /r/LocalLLaMA/comments/195h49t/roadmap_for_model_releases/ | false | false | self | 1 | {'enabled': False, 'images': [{'id': '7JdUxo_TR6YKwjuo8mMxhiaK5sk_gC3GjI6fHnKzlOM', 'resolutions': [{'height': 108, 'url': 'https://external-preview.redd.it/Kakf9a9H_nZRTJ97Zsgr8iXPzDf1A7Lj13l9X3Leqbg.jpg?width=108&crop=smart&auto=webp&s=84831504a89a9734ccfd6ecce13869e6266b9607', 'width': 108}], 'source': {'height': 14... |
UnIVAL: Unified Model for Image, Video, Audio and Language Tasks | 41 | **arXiv**: [https://arxiv.org/abs/2307.16184](https://arxiv.org/abs/2307.16184)
**OpenReview**: [https://openreview.net/forum?id=4uflhObpcp](https://openreview.net/forum?id=4uflhObpcp)
**Code**: [https://github.com/mshukor/UnIVAL](https://github.com/mshukor/UnIVAL)
**Checkpoints**: [https://github.com/mshukor/UnIVAL... | 2024-01-13T04:26:18 | https://www.reddit.com/r/LocalLLaMA/comments/195fgal/unival_unified_model_for_image_video_audio_and/ | APaperADay | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 195fgal | false | null | t3_195fgal | /r/LocalLLaMA/comments/195fgal/unival_unified_model_for_image_video_audio_and/ | false | false | self | 41 | null |
How to install safetensors models? | 1 | [removed] | 2024-01-13T04:25:19 | https://www.reddit.com/r/LocalLLaMA/comments/195ffop/how_to_install_safetensors_models/ | yungfishstick | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 195ffop | false | null | t3_195ffop | /r/LocalLLaMA/comments/195ffop/how_to_install_safetensors_models/ | false | false | self | 1 | null |
UnIVAL: Unified Model for Image, Video, Audio and Language Tasks | 1 | **arXiv**: [https://arxiv.org/abs/2307.16184](https://arxiv.org/abs/2307.16184)
**OpenReview**: [https://openreview.net/forum?id=4uflhObpcp](https://openreview.net/forum?id=4uflhObpcp)
**Code**: [https://github.com/mshukor/UnIVAL](https://github.com/mshukor/UnIVAL)
**Checkpoints**: [https://github.com/mshukor/UnIVAL... | 2024-01-13T04:22:11 | https://www.reddit.com/r/LocalLLaMA/comments/195fdmg/unival_unified_model_for_image_video_audio_and/ | APaperADay | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 195fdmg | false | null | t3_195fdmg | /r/LocalLLaMA/comments/195fdmg/unival_unified_model_for_image_video_audio_and/ | false | false | self | 1 | null |
Idea / Proposal for someone smarter than I am. Devs/Coders, please hear me out. | 49 | Disclaimer: you're probably more knowledgeable than me, have more experience, and are far better at coding than me. Keep that in mind.
Here's the TLDR: create a new program (perhaps using Transformers/Tiny LLM, perhaps not needing LLMs at all) that scans, details, and analyzes the users exact hardware setup, and ultim... | 2024-01-13T04:18:38 | https://www.reddit.com/r/LocalLLaMA/comments/195fb5l/idea_proposal_for_someone_smarter_than_i_am/ | DriestBum | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 195fb5l | false | null | t3_195fb5l | /r/LocalLLaMA/comments/195fb5l/idea_proposal_for_someone_smarter_than_i_am/ | false | false | self | 49 | null |
Roadmap for model releases | 1 | [removed] | 2024-01-13T04:06:06 | https://www.reddit.com/r/LocalLLaMA/comments/195f2hk/roadmap_for_model_releases/ | danielcar | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 195f2hk | false | null | t3_195f2hk | /r/LocalLLaMA/comments/195f2hk/roadmap_for_model_releases/ | false | false | self | 1 | {'enabled': False, 'images': [{'id': '7JdUxo_TR6YKwjuo8mMxhiaK5sk_gC3GjI6fHnKzlOM', 'resolutions': [{'height': 108, 'url': 'https://external-preview.redd.it/Kakf9a9H_nZRTJ97Zsgr8iXPzDf1A7Lj13l9X3Leqbg.jpg?width=108&crop=smart&auto=webp&s=84831504a89a9734ccfd6ecce13869e6266b9607', 'width': 108}], 'source': {'height': 14... |
UnIVAL: Unified Model for Image, Video, Audio and Language Tasks | 1 | [removed] | 2024-01-13T03:55:24 | https://www.reddit.com/r/LocalLLaMA/comments/195euy1/unival_unified_model_for_image_video_audio_and/ | APaperADay | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 195euy1 | false | null | t3_195euy1 | /r/LocalLLaMA/comments/195euy1/unival_unified_model_for_image_video_audio_and/ | false | false | self | 1 | null |
To buy Asus NVIDIA 4 gpu server? | 1 | [removed] | 2024-01-13T03:38:56 | https://www.reddit.com/r/LocalLLaMA/comments/195ejhp/to_buy_asus_nvidia_4_gpu_server/ | rich_atl | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 195ejhp | false | null | t3_195ejhp | /r/LocalLLaMA/comments/195ejhp/to_buy_asus_nvidia_4_gpu_server/ | false | false | self | 1 | {'enabled': False, 'images': [{'id': '6Uu3iPS9Tdp3KF4CgLIygCjGiDYJiU2zjxrqoMo_olw', 'resolutions': [{'height': 97, 'url': 'https://external-preview.redd.it/oX_Z0g9-GK6HQuFlHa2spopj9e-_Rg-3Rsem7F4wKoo.jpg?width=108&crop=smart&auto=webp&s=66f5f14497924ac5011a5b432826a66d69efa93d', 'width': 108}, {'height': 194, 'url': 'h... |
So.... mixtral is on two different leaderboards better than 3.5? Am I reading this right? | 35 | I just got mixtral running on my machine (amd 32 gig with 3060 12 gig) pretty well with the largest model and I'm pretty impressed. I went to look for something better and all I'm hearing is crickets.
Had no idea how powerful it was, I just liked it as a sysadmin challenge. | 2024-01-13T02:27:12 | https://www.reddit.com/r/LocalLLaMA/comments/195d3vl/so_mixtral_is_on_two_different_leaderboards/ | cleuseau | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 195d3vl | false | null | t3_195d3vl | /r/LocalLLaMA/comments/195d3vl/so_mixtral_is_on_two_different_leaderboards/ | false | false | self | 35 | null |
Transcription scrubber with a Large Language Model - using SillyTavernAI (Workflow included) | 1 | 2024-01-13T02:12:45 | https://v.redd.it/b7po3bds84cc1 | Complex-Indication | v.redd.it | 1970-01-01T00:00:00 | 0 | {} | 195csyr | false | {'reddit_video': {'bitrate_kbps': 5000, 'dash_url': 'https://v.redd.it/b7po3bds84cc1/DASHPlaylist.mpd?a=1707703978%2CMWU2MDdmN2ZlMzg4ZjE5MzM0MGQwYTEyZjNiYzY5NDQ3ZmQxNzYzNWI1ODJiMDhmOTY2ZTYyOWMxZWVmZTNhYQ%3D%3D&v=1&f=sd', 'duration': 25, 'fallback_url': 'https://v.redd.it/b7po3bds84cc1/DASH_1080.mp4?source=fallback', 'h... | t3_195csyr | /r/LocalLLaMA/comments/195csyr/transcription_scrubber_with_a_large_language/ | false | false | 1 | {'enabled': False, 'images': [{'id': 'cnNsNDh2emE5NGNjMXoGktdQVa4KfKFPi6o-Y0pomAdcVN_yQxCvPYo3Jwts', 'resolutions': [{'height': 192, 'url': 'https://external-preview.redd.it/cnNsNDh2emE5NGNjMXoGktdQVa4KfKFPi6o-Y0pomAdcVN_yQxCvPYo3Jwts.png?width=108&crop=smart&format=pjpg&auto=webp&s=5864da63f08a31a9d6fa68141d624f98e950... | ||
Other than coding, and manipulating datasets, what are you guys doing with LLMs? | 1 | [removed] | 2024-01-13T02:05:36 | https://www.reddit.com/r/LocalLLaMA/comments/195cnpg/other_than_coding_and_manipulating_datasets_what/ | hmmqzaz | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 195cnpg | false | null | t3_195cnpg | /r/LocalLLaMA/comments/195cnpg/other_than_coding_and_manipulating_datasets_what/ | false | false | self | 1 | null |
Mac Studio Build | 1 | [removed] | 2024-01-13T01:52:27 | https://www.reddit.com/r/LocalLLaMA/comments/195cdqc/mac_studio_build/ | dave9199 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 195cdqc | false | null | t3_195cdqc | /r/LocalLLaMA/comments/195cdqc/mac_studio_build/ | false | false | self | 1 | null |
Since it gets asked every single day, currently the best ERP model is sensualize-mixtral. | 45 | Anyone who disagrees is welcome to politely fight me.
https://huggingface.co/TheBloke/Sensualize-Mixtral-GGUF
Edit: sorry guys, the title was bait. I actually just wanted more recommendations | 2024-01-13T01:03:59 | https://www.reddit.com/r/LocalLLaMA/comments/195bcz2/since_it_gets_asked_every_single_day_currently/ | ansmo | self.LocalLLaMA | 2024-01-13T08:35:52 | 0 | {} | 195bcz2 | false | null | t3_195bcz2 | /r/LocalLLaMA/comments/195bcz2/since_it_gets_asked_every_single_day_currently/ | false | false | self | 45 | {'enabled': False, 'images': [{'id': '858D_G6mFmj89J5PFPSMIl_npAaFg0xCk3b6phK4ylY', 'resolutions': [{'height': 58, 'url': 'https://external-preview.redd.it/_N6oNw3_JByJbyfi8tKlkmkLcR9EKAI9-UxVGOswcz8.jpg?width=108&crop=smart&auto=webp&s=60278d6e2ea044557d210c5fa7739b8154153243', 'width': 108}, {'height': 116, 'url': 'h... |
I have enough of this 24GB nonsense. | 1 | Ok, 3090 is officially the dumbo for chumps. The 70b is the bare minimum to process data. On 24B with all the RAM/GPU splits and quantization, I'm getting slow like molasses on holiday in a maple syrup in Ottawa response. I want to prepare data for my new extraordinary models (in my own noggin), but this is like workin... | 2024-01-13T00:56:39 | https://www.reddit.com/r/LocalLLaMA/comments/195b725/i_have_enough_of_this_24gb_nonsense/ | FPham | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 195b725 | false | null | t3_195b725 | /r/LocalLLaMA/comments/195b725/i_have_enough_of_this_24gb_nonsense/ | false | false | self | 1 | null |
RoSA - LoRA but better | 90 | 2024-01-13T00:33:54 | https://twitter.com/marktenenholtz/status/1745875618732925086?t=OYjMDWpmpkkoBWU5xWFF7w&s=19 | Eastwindy123 | twitter.com | 1970-01-01T00:00:00 | 0 | {} | 195ap9t | false | {'oembed': {'author_name': 'Mark Tenenholtz', 'author_url': 'https://twitter.com/marktenenholtz', 'cache_age': 3153600000, 'height': None, 'html': '<blockquote class="twitter-video"><p lang="en" dir="ltr">RoSA is a low-rank adapter method that claims to outperform LoRA.<br><br>It trains a standard LoRA adapter (usually... | t3_195ap9t | /r/LocalLLaMA/comments/195ap9t/rosa_lora_but_better/ | false | false | 90 | {'enabled': False, 'images': [{'id': '-CfcN30pe4heJzcPzbKjrgJsFkBxzCGJ3jvXpts3XAQ', 'resolutions': [{'height': 69, 'url': 'https://external-preview.redd.it/MjMrLk716MUjNq9QAttpf9B2C803C4cCSBtdN0gC_2M.jpg?width=108&crop=smart&auto=webp&s=de159546e8c7413af61cd622e901d24320ad2675', 'width': 108}], 'source': {'height': 90,... | ||
Using LLaMA with RAG to ask more meta-document questions | 1 | [removed] | 2024-01-13T00:15:22 | https://www.reddit.com/r/LocalLLaMA/comments/195aa7n/using_llama_with_rag_to_ask_more_metadocument/ | jupiterprosperitytm | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 195aa7n | false | null | t3_195aa7n | /r/LocalLLaMA/comments/195aa7n/using_llama_with_rag_to_ask_more_metadocument/ | false | false | self | 1 | null |
Fine tuning a large language model | 1 |
I have a fine-tuned LLM for diagnosing mental health issues and helping the user with cognitive behavioral therapy.
The model is finetuned on single Q&A data like this:
{'Person': "I've been feeling so sad and overwhelmed lately. Work has become such a massive source of stress for me.
'Psychologist': ' Hey there,... | 2024-01-12T22:41:03 | https://www.reddit.com/r/LocalLLaMA/comments/19582cm/fine_tuning_a_large_language_model/ | Repulsive_Ad_2230 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 19582cm | false | null | t3_19582cm | /r/LocalLLaMA/comments/19582cm/fine_tuning_a_large_language_model/ | false | false | self | 1 | null |
Buying/Hiring A Dating App LLM | 1 | [removed] | 2024-01-12T22:11:33 | https://www.reddit.com/r/LocalLLaMA/comments/1957cw2/buyinghiring_a_dating_app_llm/ | Networkfrog | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 1957cw2 | false | null | t3_1957cw2 | /r/LocalLLaMA/comments/1957cw2/buyinghiring_a_dating_app_llm/ | false | false | nsfw | 1 | null |
Subsets and Splits
No community queries yet
The top public SQL queries from the community will appear here once available.