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 ⌀ |
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
Looking for a LLM fine tuned to generate good Stable Diffusion prompts | 10 | Does anyone know a LLM that would be good at taking a long text summary and generating a good image prompt from what is described in the story? | 2023-10-16T23:09:38 | https://www.reddit.com/r/LocalLLaMA/comments/179jnyw/looking_for_a_llm_fine_tuned_to_generate_good/ | BoosterKarl | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 179jnyw | false | null | t3_179jnyw | /r/LocalLLaMA/comments/179jnyw/looking_for_a_llm_fine_tuned_to_generate_good/ | false | false | self | 10 | null |
text-generation-webui | 1 | Hello,
I use text-generation-webui but I have problem I can't install any extensions I need to add this line to webui.py but I don't have this file!!
\--extension whisper\_stt silero\_tts elevenlabs\_tts
Everytime i try to install it from Session tab and save it but it's never work it's keep uncheck after restart t... | 2023-10-16T23:07:06 | https://www.reddit.com/r/LocalLLaMA/comments/179jm37/textgenerationwebui/ | SupportResponsible77 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 179jm37 | false | null | t3_179jm37 | /r/LocalLLaMA/comments/179jm37/textgenerationwebui/ | false | false | self | 1 | null |
Weekend project, MiniSearch | Code on GitHub | Demo on HuggingFace | 1 | [removed] | 2023-10-16T22:52:10 | https://github.com/felladrin/MiniSearch | Felladrin | github.com | 1970-01-01T00:00:00 | 0 | {} | 179ja4f | false | null | t3_179ja4f | /r/LocalLLaMA/comments/179ja4f/weekend_project_minisearch_code_on_github_demo_on/ | false | false | default | 1 | null |
Weekend project, MiniSearch | Code available on GitHub | 1 | [removed] | 2023-10-16T22:48:19 | https://www.linkedin.com/pulse/introducing-minisearch-minimalist-search-engine-ai-victor-nogueira | Felladrin | linkedin.com | 1970-01-01T00:00:00 | 0 | {} | 179j6xe | false | null | t3_179j6xe | /r/LocalLLaMA/comments/179j6xe/weekend_project_minisearch_code_available_on/ | false | false | 1 | {'enabled': False, 'images': [{'id': '8ywkLgcbx7oB0uf6C3n7NNHnf20FMR_4HaRaQEpkIls', 'resolutions': [{'height': 60, 'url': 'https://external-preview.redd.it/CJpaGghalVjP0l3X44H6RFIPc-VIj-LrJlecjSTZWhY.jpg?width=108&crop=smart&auto=webp&s=aecd34e28a22fc3e8af13e0107b3db62064fcad2', 'width': 108}, {'height': 121, 'url': 'h... | |
Eploring Methods to Improve Text Chunking in RAG Models (and other things...) | 28 | Hello everyone,
I'm currently working on Retrieval Augmented Generation (RAG) models and have developed a custom chunking function, as I found the methods in LangChain not entirely satisfactory.
I'm keen on exploring other methods, algorithms (related to NLP or otherwise), and models to enhance text chunking in RAG. ... | 2023-10-16T22:21:30 | https://www.reddit.com/r/LocalLLaMA/comments/179ikbu/eploring_methods_to_improve_text_chunking_in_rag/ | BXresearch | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 179ikbu | false | null | t3_179ikbu | /r/LocalLLaMA/comments/179ikbu/eploring_methods_to_improve_text_chunking_in_rag/ | false | false | self | 28 | null |
Uncle's FPHam lesson - Fragmented knowledge and why LLM can't write a novel | 5 | Ok, it's 5.30 in the afternoon and I'm having my breakfast. And I'm thinking how to convey this whole idea of finetuning LLM to people who have no idea what it is.
Oh, but we have stable diffusion for images and in essence it is the same thing.
In SD if you want to train a model to know your ugly mugshot you would co... | 2023-10-16T22:05:35 | https://www.reddit.com/r/LocalLLaMA/comments/179i6ti/uncles_fpham_lesson_fragmented_knowledge_and_why/ | FPham | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 179i6ti | false | null | t3_179i6ti | /r/LocalLLaMA/comments/179i6ti/uncles_fpham_lesson_fragmented_knowledge_and_why/ | false | false | self | 5 | null |
Finetuning: Prompt entropy / question complexity | 1 | Hey All: I have two sets of real world survey data now setup in prompt-response pairs (mostly financial questions and answers). The first set has short simple questions but longer detailed answers.
The second set has the opposite pattern (sophisticated and complex questions) but short and correct answers.
Both se... | 2023-10-16T20:56:55 | https://www.reddit.com/r/LocalLLaMA/comments/179gi1r/finetuning_prompt_entropy_question_complexity/ | buzzyness | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 179gi1r | false | null | t3_179gi1r | /r/LocalLLaMA/comments/179gi1r/finetuning_prompt_entropy_question_complexity/ | false | false | self | 1 | null |
Exploring Methods to Improve Text Chunking in RAG Models (and other...) | 2 | [removed] | 2023-10-16T20:30:27 | https://www.reddit.com/r/LocalLLaMA/comments/179fvcb/exploring_methods_to_improve_text_chunking_in_rag/ | Distinct-Target7503 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 179fvcb | false | null | t3_179fvcb | /r/LocalLLaMA/comments/179fvcb/exploring_methods_to_improve_text_chunking_in_rag/ | false | false | self | 2 | null |
Offloading Inferencing to a separate card? | 3 | Ever since exllama (and v2) has come out, it's becoming more and more apparent that my pair of P40's are starting to be pretty outclassed. Not that I'm complaining or anything.
But I'm curious (and also because my search-fu is failing me), is it possible to offload inferencing to a separate GPU or are these two tied ... | 2023-10-16T20:11:21 | https://www.reddit.com/r/LocalLLaMA/comments/179feu7/offloading_inferencing_to_a_separate_card/ | AsheramL | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 179feu7 | false | null | t3_179feu7 | /r/LocalLLaMA/comments/179feu7/offloading_inferencing_to_a_separate_card/ | false | false | self | 3 | null |
Mistral-7B-code-16k-qlora: A Fast and Efficient Model for Coding Support | 1 | [removed] | 2023-10-16T18:49:10 | https://www.reddit.com/r/LocalLLaMA/comments/179dgdo/mistral7bcode16kqlora_a_fast_and_efficient_model/ | Nondzu | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 179dgdo | false | null | t3_179dgdo | /r/LocalLLaMA/comments/179dgdo/mistral7bcode16kqlora_a_fast_and_efficient_model/ | false | false | self | 1 | {'enabled': False, 'images': [{'id': 'Vg0lrVAMUl4YZ9vjkV_1PY5gv4D7JWwxsUnQsFwJb6Q', 'resolutions': [{'height': 58, 'url': 'https://external-preview.redd.it/rujLKYc_tWwNsdYTSBbIanHlNBQQ1ZkADN8y6zB5SDM.jpg?width=108&crop=smart&auto=webp&s=bb80485df4c00e37f09a75375924d069e5a37c03', 'width': 108}, {'height': 116, 'url': 'h... |
PCIe bandwidth impact on llama-cpp (benchmark) | 16 | Slightly interesting, maybe:
This is the setup that I have: I have a 3080Ti in my computer. I also have a 3060Ti that I tested inside my computer running on PCIe4.0x4, and that I can run as an eGPU on thunderbolt 4 (effective PCIe3.0x4, or even less as it's an Alpine Ridge eGPU giving only about 20GB/s pcie bandwidth... | 2023-10-16T18:26:29 | https://www.reddit.com/r/LocalLLaMA/comments/179cwev/pcie_bandwidth_impact_on_llamacpp_benchmark/ | Wrong-Historian | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 179cwev | false | null | t3_179cwev | /r/LocalLLaMA/comments/179cwev/pcie_bandwidth_impact_on_llamacpp_benchmark/ | false | false | self | 16 | null |
LLM trained on code memorizes 8% of the training set and could expose code used for training | 27 | We have found that LLMs finetuned on code memorize it, which implies other users can exfiltrate coding data with prompts!
We have found that [StarCoder](https://huggingface.co/bigcode/starcoder), an open-source LLM from Hugging Face, shows memorization of 8% of the training samples. Memorization means that by showing... | 2023-10-16T17:52:05 | https://www.reddit.com/r/LocalLLaMA/comments/179c3ew/llm_trained_on_code_memorizes_8_of_the_training/ | Separate-Still3770 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 179c3ew | false | null | t3_179c3ew | /r/LocalLLaMA/comments/179c3ew/llm_trained_on_code_memorizes_8_of_the_training/ | false | false | self | 27 | {'enabled': False, 'images': [{'id': 'uUd-OX1LomltvNkhxBjJMVzVM451Vh0lxVnG2GnaC_I', 'resolutions': [{'height': 58, 'url': 'https://external-preview.redd.it/gGieV3t9rGqc5zmPrQBM1cieGmWx1VXVqegi6sFQUCs.jpg?width=108&crop=smart&auto=webp&s=dc15f75c64a384f942cd2ec0a9a7f209c73f6336', 'width': 108}, {'height': 116, 'url': 'h... |
need your input on this | 4 | So out of context, i am trying to build a chat with the document bot using localAI, flowise. Can you suggest me a llm model and embedding model that would work best for reading through contracts ( 1 at a time and will be stored as vectors ). My setup [https://github.com/manojkumar-manivannan/pics/blob/e4b66c26751db5c1a... | 2023-10-16T17:50:07 | https://www.reddit.com/r/LocalLLaMA/comments/179c1p9/need_your_input_on_this/ | karthiceaswar | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 179c1p9 | false | null | t3_179c1p9 | /r/LocalLLaMA/comments/179c1p9/need_your_input_on_this/ | false | false | self | 4 | {'enabled': False, 'images': [{'id': 'RWuflFTpNqSAHY9YF_W7lI7lAlMxJSuL2NvyNnKM2NA', 'resolutions': [{'height': 54, 'url': 'https://external-preview.redd.it/niEDuhr_ZLzTl6-2PImufxMM6E2Hsc63JtUA7Jqe9h0.jpg?width=108&crop=smart&auto=webp&s=3106e3ee080243d29401021ffe4dd4f7808b9461', 'width': 108}, {'height': 108, 'url': 'h... |
LLMWare: All in one AI framework for LLM-based applications for GenAI apps (RAG) | 9 | 2023-10-16T17:38:30 | https://www.marktechpost.com/2023/10/16/meet-llmware-an-all-in-one-artificial-intelligence-framework-for-streamlining-llm-based-application-development-for-generative-ai-applications/ | Mammoth-Doughnut-160 | marktechpost.com | 1970-01-01T00:00:00 | 0 | {} | 179brma | false | null | t3_179brma | /r/LocalLLaMA/comments/179brma/llmware_all_in_one_ai_framework_for_llmbased/ | false | false | 9 | {'enabled': False, 'images': [{'id': 'MxyXZ0SzUicqx7s0tkA5zzqDarP2Jgke5EJK9wjQdcY', 'resolutions': [{'height': 60, 'url': 'https://external-preview.redd.it/d2H-tl2nx7f1LuU9q8zAPELa-3I5fER165qJFtl9nTQ.jpg?width=108&crop=smart&auto=webp&s=5b05e00f48d19ae06a030dd3da5358c7c95b4140', 'width': 108}, {'height': 121, 'url': 'h... | ||
A new type of transistor is more efficient at (some) machine learning tasks | 17 | I'll refrain from using the article's misleading title. This one is early science, so take it with a grain of salt, but the implications are huge, especially for local and wearables (let's see Apple swoop this one up), so I think it fits here (even if it's probably 5 years away).
Since the abstract is so full of scien... | 2023-10-16T17:09:15 | https://www.reddit.com/r/LocalLLaMA/comments/179b2qc/a_new_type_of_transistor_is_more_efficient_at/ | neph1010 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 179b2qc | false | null | t3_179b2qc | /r/LocalLLaMA/comments/179b2qc/a_new_type_of_transistor_is_more_efficient_at/ | false | false | self | 17 | {'enabled': False, 'images': [{'id': 'JJjderDv-vWLA_N1q6FTHPCCOOdsfYtbQT88ddRTPwU', 'resolutions': [{'height': 56, 'url': 'https://external-preview.redd.it/uP9PigXAyIFDhseg-N6is9sbfedqv1oxYDbrnPrRWkM.jpg?width=108&crop=smart&auto=webp&s=e553448b359770bb0d326b658e92e41bffaba0a1', 'width': 108}, {'height': 113, 'url': 'h... |
What's the deal with all those "CEOs" looking to hire prompt engineers on Reddit. Feels scammish. | 102 | Reminds me of the photographer scams that were everywhere when DSLRs were getting cheap and popular. Every one was a "professional" photographer. | 2023-10-16T17:01:49 | https://www.reddit.com/r/LocalLLaMA/comments/179aw4m/whats_the_deal_with_all_those_ceos_looking_to/ | oodelay | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 179aw4m | false | null | t3_179aw4m | /r/LocalLLaMA/comments/179aw4m/whats_the_deal_with_all_those_ceos_looking_to/ | false | false | self | 102 | null |
Running a 70B model on a €99,00 PC? | 1 | When looking to run a 70B large language model, one of the the constraints is usually VRAM. The way Apple does with it's unified memory allows it to run very large models. However Apple are not the only ones using unified memory.
So I've been looking into single board computers and managed to find this:
First off, th... | 2023-10-16T16:44:40 | https://www.reddit.com/r/LocalLLaMA/comments/179ah7b/running_a_70b_model_on_a_9900_pc/ | arekku255 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 179ah7b | false | null | t3_179ah7b | /r/LocalLLaMA/comments/179ah7b/running_a_70b_model_on_a_9900_pc/ | false | false | self | 1 | null |
Public data sources for dying/minority languages | 9 | I was thinking about making a multilingual model for smaller language(s). The criteria for the target language:
\* There are only a few million speakers left, and their number will likely decrease further.
\* It should be written using the Latin alphabet (I can read cyrillic, chinese script, but I don't want to mak... | 2023-10-16T16:43:09 | https://www.reddit.com/r/LocalLLaMA/comments/179afse/public_data_sources_for_dyingminority_languages/ | justynasty | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 179afse | false | null | t3_179afse | /r/LocalLLaMA/comments/179afse/public_data_sources_for_dyingminority_languages/ | false | false | self | 9 | null |
AttributeError: module 'bitsandbytes' has no attribute 'nn' How to resolve this? | 1 | When I trying to load llama base model inorder to fine tune it I'm receiving this error | 2023-10-16T16:25:15 | https://www.reddit.com/r/LocalLLaMA/comments/179a098/attributeerror_module_bitsandbytes_has_no/ | Hour-Ad-8674 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 179a098 | false | null | t3_179a098 | /r/LocalLLaMA/comments/179a098/attributeerror_module_bitsandbytes_has_no/ | false | false | self | 1 | null |
Void Archive a easy way to train models without being a expert | 2 | download link: [https://github.com/VINUK0/Void-Archive](https://github.com/VINUK0/Void-Archive)
## ⌘ Description ⌘
​
* *\[Void Archive\] library aim to make training of a machine learning model easy as possible so anyone could train a model with or without python and machine learning knowledge.*
* *Currently ... | 2023-10-16T15:43:28 | https://www.reddit.com/r/LocalLLaMA/comments/17990fi/void_archive_a_easy_way_to_train_models_without/ | Avocado_Express | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 17990fi | false | null | t3_17990fi | /r/LocalLLaMA/comments/17990fi/void_archive_a_easy_way_to_train_models_without/ | false | false | self | 2 | {'enabled': False, 'images': [{'id': '23KwZ3FmalZxSD3eWuVbKS_NDk90a1aL8RBIOmDAlZM', 'resolutions': [{'height': 54, 'url': 'https://external-preview.redd.it/TNVeIStl1g3b_aQO-UBSn-ps89vwvS-Wj-SsVkZn2bw.jpg?width=108&crop=smart&auto=webp&s=758b655454bc0a297a03df0cfb158f00028fe06a', 'width': 108}, {'height': 108, 'url': 'h... |
Obsidian.md plugin for llama inference | 7 | I made simple, but useful plugin for [Obsidian.md](https://Obsidian.md), which let you to talk with local llama.cpp models.
[https://github.com/skycover/aicom-obsidian](https://github.com/skycover/aicom-obsidian)
It is designated to be a companion to answer questions, make translation and explanation of hard texts. A... | 2023-10-16T15:43:05 | https://www.reddit.com/r/LocalLLaMA/comments/179903y/obsidianmd_plugin_for_llama_inference/ | losthost12 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 179903y | false | null | t3_179903y | /r/LocalLLaMA/comments/179903y/obsidianmd_plugin_for_llama_inference/ | false | false | 7 | {'enabled': False, 'images': [{'id': 'zMXPIQv3Ay2AQPtwJ908oSE8egPawgAwdCZIEwNBzQc', 'resolutions': [{'height': 61, 'url': 'https://external-preview.redd.it/eZ_f2nyTYirqBDReJtey7J-BldkDOkDq7Nf-V4DhjOU.jpg?width=108&crop=smart&auto=webp&s=6984633aa403dcb7087885ae247b40326cd0b556', 'width': 108}, {'height': 123, 'url': 'h... | |
Similar subreddits | 1 | [removed] | 2023-10-16T15:34:24 | https://www.reddit.com/r/LocalLLaMA/comments/1798sm0/similar_subreddits/ | semantium | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 1798sm0 | false | null | t3_1798sm0 | /r/LocalLLaMA/comments/1798sm0/similar_subreddits/ | false | false | self | 1 | null |
Node-based AutoGen with local LLMs inside ComfyUI | 85 | 2023-10-16T15:24:21 | AntonymGoeckes | i.redd.it | 1970-01-01T00:00:00 | 0 | {} | 1798ka7 | false | null | t3_1798ka7 | /r/LocalLLaMA/comments/1798ka7/nodebased_autogen_with_local_llms_inside_comfyui/ | false | false | 85 | {'enabled': True, 'images': [{'id': 'fXTz70VLx18wcQQLXHFHdUBYVtbX0HwYsFyAH-LclgU', 'resolutions': [{'height': 51, 'url': 'https://preview.redd.it/xzusr91z0lub1.png?width=108&crop=smart&auto=webp&s=e9149c7582db1fe82efa2560b902605e86845bc5', 'width': 108}, {'height': 103, 'url': 'https://preview.redd.it/xzusr91z0lub1.png... | |||
Flash-decoding speed up inference up to x8 on long context | 51 | 2023-10-16T15:12:47 | https://twitter.com/togethercompute/status/1712910476743434273 | hapliniste | twitter.com | 1970-01-01T00:00:00 | 0 | {} | 1798amp | false | {'oembed': {'author_name': 'Together AI', 'author_url': 'https://twitter.com/togethercompute', 'cache_age': 3153600000, 'height': None, 'html': '<blockquote class="twitter-video"><p lang="en" dir="ltr">Announcing Flash-Decoding, to make long-context LLM inference up to 8x faster!<br><br>Great collab with <a href="https... | t3_1798amp | /r/LocalLLaMA/comments/1798amp/flashdecoding_speed_up_inference_up_to_x8_on_long/ | false | false | default | 51 | {'enabled': False, 'images': [{'id': 'FkfmcNdziOWIeQEIJ51z0jVzD34Om3Eav2yuhxAJ4WY', 'resolutions': [{'height': 108, 'url': 'https://external-preview.redd.it/roq2iCPLKEfww4t3kbkwyy1cjiMyRBYyoNBNfq_TZco.jpg?width=108&crop=smart&auto=webp&s=25c7064055375fb74318f5c96f6d18bf6e6fea9f', 'width': 108}], 'source': {'height': 14... | |
GPU grant program | 2 | Hi LocalLLaMA community,
We're giving away 1,000 hours on a 10x Nvidia A40 GPU server. Open source projects preferred, but all are welcome to apply. Thanks!
[https://hivedigitaltechnologies.com/gpu-grant-program/](https://hivedigitaltechnologies.com/gpu-grant-program/) | 2023-10-16T14:45:24 | https://www.reddit.com/r/LocalLLaMA/comments/1797nr4/gpu_grant_program/ | HIVE-Digital-Tech | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 1797nr4 | false | null | t3_1797nr4 | /r/LocalLLaMA/comments/1797nr4/gpu_grant_program/ | false | false | self | 2 | null |
How to create dataset for training generative chatbot model? | 0 | i built my own custom generative ai chatbot model. only thing i need is high quality and diverse dataset to train my model. i cant use already existing datasets because i dont think they are diverse and quality enough.so i need to create it using gpt4. my dataset will have 3 columns ; system\_prompt, input, output. but... | 2023-10-16T13:31:23 | https://www.reddit.com/r/LocalLLaMA/comments/17961h7/how_to_create_dataset_for_training_generative/ | Many-Corner-6700 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 17961h7 | false | null | t3_17961h7 | /r/LocalLLaMA/comments/17961h7/how_to_create_dataset_for_training_generative/ | false | false | self | 0 | null |
Can i run lamma 13b model on nvidia rtx 3060 12gb memory with 64gb RAM | 6 | Pls provide any suggestions | 2023-10-16T13:22:00 | https://www.reddit.com/r/LocalLLaMA/comments/1795ump/can_i_run_lamma_13b_model_on_nvidia_rtx_3060_12gb/ | G7gamingarena | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 1795ump | false | null | t3_1795ump | /r/LocalLLaMA/comments/1795ump/can_i_run_lamma_13b_model_on_nvidia_rtx_3060_12gb/ | false | false | self | 6 | null |
🚀 Breaking Ground in AI Innovation! Introducing LLUMO – Elevate Your Prompt Engineering Game! 💡✨ | 1 | [removed] | 2023-10-16T13:13:40 | https://www.reddit.com/r/LocalLLaMA/comments/1795one/breaking_ground_in_ai_innovation_introducing/ | llumoai | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 1795one | false | null | t3_1795one | /r/LocalLLaMA/comments/1795one/breaking_ground_in_ai_innovation_introducing/ | false | false | 1 | {'enabled': False, 'images': [{'id': 'QqSY3F9i2BgB-OdT_JpQr1vBqr2oq4spYNzkghHXwCM', 'resolutions': [], 'source': {'height': 64, 'url': 'https://external-preview.redd.it/4PgIzt2dsWk0hsH_pv6fTscUBf4LNxa8vUF1zyE23u0.jpg?auto=webp&s=adf334dabc58b5ccda405f20fe4d11f983c41fe9', 'width': 64}, 'variants': {}}]} | |
Does anyone here have experience training Pyannote on their own data? | 1 | I hope this is not too off-topic, but I wanted ask if anyone here has trained Pyannote on their own data for speaker diarization.
I'm asking because the diarization is not very good in German, so I was thinking about creating my own dataset and train or fine-tune Pyannote on it for better results. | 2023-10-16T13:11:53 | https://www.reddit.com/r/LocalLLaMA/comments/1795nht/does_anyone_here_have_experience_training/ | Prince-of-Privacy | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 1795nht | false | null | t3_1795nht | /r/LocalLLaMA/comments/1795nht/does_anyone_here_have_experience_training/ | false | false | self | 1 | null |
Multimodal-Vision LLM that is Open Source? | 27 | Hi is there an LLM that has Vision that has been released yet and ideally can be finetuned with pictures?
I can't seem to find the reference and the ammount of huggingface models | 2023-10-16T12:50:26 | https://www.reddit.com/r/LocalLLaMA/comments/17958sz/multimodalvision_llm_that_is_open_source/ | Nokita_is_Back | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 17958sz | false | null | t3_17958sz | /r/LocalLLaMA/comments/17958sz/multimodalvision_llm_that_is_open_source/ | false | false | self | 27 | null |
Fact and feature extraction: Mistral 7B, Zephyr 7B, Mistral Orca, GPT*, Bard & Claude2. | 1 | [removed] | 2023-10-16T11:47:58 | https://www.reddit.com/r/LocalLLaMA/comments/17943y9/fact_and_feature_extraction_mistral_7b_zephyr_7b/ | Greg_Z_ | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 17943y9 | false | null | t3_17943y9 | /r/LocalLLaMA/comments/17943y9/fact_and_feature_extraction_mistral_7b_zephyr_7b/ | false | false | default | 1 | null |
Getting started on Windows 10, RTX 2080 SUPER 8GB VRAM, 32GB RAM | 1 | I'm trying to get the Mistral 7B model ([https://huggingface.co/mistralai/Mistral-7B-Instruct-v0.1](https://huggingface.co/mistralai/Mistral-7B-Instruct-v0.1)) to work via text-generation-webui on my PC without success. I know my PC is not a beast, but I want to dip my toes (locally) before upgrading.
Am I using the i... | 2023-10-16T11:40:26 | https://www.reddit.com/r/LocalLLaMA/comments/1793zeb/getting_started_on_windows_10_rtx_2080_super_8gb/ | FishyInAGoodWay | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 1793zeb | false | null | t3_1793zeb | /r/LocalLLaMA/comments/1793zeb/getting_started_on_windows_10_rtx_2080_super_8gb/ | false | false | self | 1 | {'enabled': False, 'images': [{'id': '3B850zhRvqiMNHDsdn5fe2qbOKZ3cMgYs04q04tRdgs', 'resolutions': [{'height': 58, 'url': 'https://external-preview.redd.it/VVk1cEGg5LpYCp6W6wlHZ3nk7nL-v56BxQKFc6SfWQM.jpg?width=108&crop=smart&auto=webp&s=cead41a116b3350c8a89fae391b73cceb1da2f12', 'width': 108}, {'height': 116, 'url': 'h... |
Model evaluation on custom data | 1 | [removed] | 2023-10-16T11:04:52 | https://www.reddit.com/r/LocalLLaMA/comments/1793exo/model_evaluation_on_custom_data/ | Enkay55 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 1793exo | false | null | t3_1793exo | /r/LocalLLaMA/comments/1793exo/model_evaluation_on_custom_data/ | false | false | self | 1 | null |
How do I fix the model failing to load without an error? | 3 | 2023-10-16T10:01:04 | JawGBoi | i.redd.it | 1970-01-01T00:00:00 | 0 | {} | 1792gcj | false | null | t3_1792gcj | /r/LocalLLaMA/comments/1792gcj/how_do_i_fix_the_model_failing_to_load_without_an/ | false | false | 3 | {'enabled': True, 'images': [{'id': 'WU2rXrDZqv6VKiFM-29GRg-Bm56ca_7XVDr-c7Iex0A', 'resolutions': [{'height': 46, 'url': 'https://preview.redd.it/untra8wlfjub1.png?width=108&crop=smart&auto=webp&s=90acf6cd8b79b18e55fd7823005776ec1c9c098d', 'width': 108}, {'height': 93, 'url': 'https://preview.redd.it/untra8wlfjub1.png?... | |||
Fine-tuned Mistral-7B to generate dad jokes | 97 | To get my hands dirty with QLoRa fine tuning of 7B+ models, I've fine-tuned a Mistral-7B to predict punchlines of dad jokes from r/dadjokes.
The model and training setup is on HF: [https://huggingface.co/shuttie/Mistral-7B-DadJokes-GGUF](https://huggingface.co/shuttie/Mistral-7B-DadJokes-GGUF)
Web UI to run the inf... | 2023-10-16T09:44:26 | https://www.reddit.com/r/LocalLLaMA/comments/17927ut/finetuned_mistral7b_to_generate_dad_jokes/ | InvadersMustLive | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 17927ut | false | null | t3_17927ut | /r/LocalLLaMA/comments/17927ut/finetuned_mistral7b_to_generate_dad_jokes/ | false | false | self | 97 | {'enabled': False, 'images': [{'id': 'hWWtESYiGjo6AcBYnO_AskKjBBUPBvhvO02aQK5bjWc', 'resolutions': [{'height': 58, 'url': 'https://external-preview.redd.it/Dhz3fuTshAqd1_lwysPIJkeVk_3BVaNF0ACipb3pnic.jpg?width=108&crop=smart&auto=webp&s=b175f897e04ac85fe7a02f1567078b3d209dec5e', 'width': 108}, {'height': 116, 'url': 'h... |
Could you use a Spell Book this Halloween? | 8 | Hello! Last week, someone posted asking the community what everyone was building with local LLMs. I replied, detailing the project I am building called **Spell Book** 🧙♂️. My post got positive feedback, so I decided to create a short video demoing what it does so far. I will be dropping the code on or right before Ha... | 2023-10-16T08:33:55 | https://www.reddit.com/r/LocalLLaMA/comments/17918tg/could_you_use_a_spell_book_this_halloween/ | noco-ai | self.LocalLLaMA | 2023-10-16T08:45:26 | 0 | {} | 17918tg | false | null | t3_17918tg | /r/LocalLLaMA/comments/17918tg/could_you_use_a_spell_book_this_halloween/ | false | false | self | 8 | null |
Seeking Advice: Comprehensive Resources for Learning NLP and Large Language Models | 3 | Hello everyone,
I've recently been using LLMs for work. My journey thus far has been self-guided, and I'm reaching a point where I'd like to expand my understanding through more structured learning.
I'm especially interested in resources that not only offer theoretical knowledge but also provide practical insights... | 2023-10-16T08:06:31 | https://www.reddit.com/r/LocalLLaMA/comments/1790vy4/seeking_advice_comprehensive_resources_for/ | PinballOscuro | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 1790vy4 | false | null | t3_1790vy4 | /r/LocalLLaMA/comments/1790vy4/seeking_advice_comprehensive_resources_for/ | false | false | self | 3 | null |
Online RAG Systems | 1 | [removed] | 2023-10-16T07:57:18 | https://www.reddit.com/r/LocalLLaMA/comments/1790r7w/online_rag_systems/ | mahdiAkhi | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 1790r7w | false | null | t3_1790r7w | /r/LocalLLaMA/comments/1790r7w/online_rag_systems/ | false | false | self | 1 | null |
High quality datasets , where to buy | 2 | Hi,
I have a small company that is using open source LLMs like llama2 to fulfill our clients needs. We need to fine-tune them most of the time since prompting doesn't cut most of the special use cases.
Is there some marketplace where people are selling high quality datasets? I know hugging face datasets exist, but the... | 2023-10-16T07:54:32 | https://www.reddit.com/r/LocalLLaMA/comments/1790py0/high_quality_datasets_where_to_buy/ | Armym | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 1790py0 | false | null | t3_1790py0 | /r/LocalLLaMA/comments/1790py0/high_quality_datasets_where_to_buy/ | false | false | self | 2 | null |
How do one install a locally run vision-image description A.I. ? | 1 | Sorry I am a little late to the game, like many of you I am pure offline when it comes to A.I., I have stable diffusion and oobabooga, but how do one achieve a locally run vision-image description version completely cut off from the net ? | 2023-10-16T07:48:47 | https://www.reddit.com/r/LocalLLaMA/comments/1790nar/how_do_one_install_a_locally_run_visionimage/ | Vitamin_C_is_awesome | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 1790nar | false | null | t3_1790nar | /r/LocalLLaMA/comments/1790nar/how_do_one_install_a_locally_run_visionimage/ | false | false | self | 1 | null |
What strategies can GPU Poor take? | 60 | ​
https://preview.redd.it/rp19fwlemiub1.png?width=1792&format=png&auto=webp&s=a5c67d585404bbcb327eb6341092841307c600b9
​
* Buy two RTX 4060Ti(16GB)
* Buy two used RTX 3090
* Try AMD or Intel products
* Try a Mac
* Do data maintenance until A100 is available in the cloud (H200 in 2024, Blackwell (B100/B... | 2023-10-16T07:21:06 | https://www.reddit.com/r/LocalLLaMA/comments/17909y3/what_strategies_can_gpu_poor_take/ | dahara111 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 17909y3 | false | null | t3_17909y3 | /r/LocalLLaMA/comments/17909y3/what_strategies_can_gpu_poor_take/ | false | false | 60 | null | |
Which model+size for a websearch agent? | 11 | I've been playing around with an agent framework ([www.griptape.ai](https://www.griptape.ai)). Like Langchain you can create an agent with tools and I've been experimenting with its websearch tool. The LLM uses ReAct prompting to decide if it should use the websearch tool and then it generates json formatted string wit... | 2023-10-16T06:47:47 | https://www.reddit.com/r/LocalLLaMA/comments/178ztct/which_modelsize_for_a_websearch_agent/ | moma1970 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 178ztct | false | null | t3_178ztct | /r/LocalLLaMA/comments/178ztct/which_modelsize_for_a_websearch_agent/ | false | false | self | 11 | {'enabled': False, 'images': [{'id': 'msNyjx_BJ-mjZDZ2Td65wmvXk3uZbrp0MStM4KK6jKQ', 'resolutions': [{'height': 59, 'url': 'https://external-preview.redd.it/2-Klj1V0Uxo7kU3joKPFX6XFTZPU2YZ6PtViW5gWhYY.jpg?width=108&crop=smart&auto=webp&s=136b0cd6815a12dcaed0c705dc84516905ed4b33', 'width': 108}, {'height': 118, 'url': 'h... |
term | 8 | Hey there! Had lots of fun writing `oterm` a text-based terminal app that interfaces with Ollama. You basically from the comfort of your terminal fire it up and you can chat with any of the installed models. `oterm` will remember your conversations and save them in a `sqlite`. It is simple, fast and makes it super easy... | 2023-10-16T06:33:54 | https://www.reddit.com/r/LocalLLaMA/comments/178zmbc/term/ | gogozad | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 178zmbc | false | null | t3_178zmbc | /r/LocalLLaMA/comments/178zmbc/term/ | false | false | self | 8 | {'enabled': False, 'images': [{'id': 'yMsdfUqfFv7dFNg0ReEhZzcirvCvsWB959JMovm7B1I', 'resolutions': [{'height': 54, 'url': 'https://external-preview.redd.it/TEHkKVSCqdgtryQva6mH7jUP02MDIJ62eWBmRCU-X4M.jpg?width=108&crop=smart&auto=webp&s=f62093d698608d2118287bddeadda1dccf4faa96', 'width': 108}, {'height': 108, 'url': 'h... |
How do you keep up to date with all the innovations and frameworks? | 1 | [removed] | 2023-10-16T06:28:51 | https://www.reddit.com/r/LocalLLaMA/comments/178zjok/how_do_you_keep_up_to_date_with_all_the/ | HorrorNo8851 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 178zjok | false | null | t3_178zjok | /r/LocalLLaMA/comments/178zjok/how_do_you_keep_up_to_date_with_all_the/ | false | false | self | 1 | null |
Plot_BOT V3 13b GPTQ - a FULLY UNCENSORED plot crafting and writing assistant | 30 | One of those many weird models from my kitchen. It can generate complex and convoluted plots and plot outlines and everything related to it, while following instructions.
PlotBot V3 is not replacement for PlotBot V2 - it's uses different "wide window" training.
[https://huggingface.co/FPHam/Plot\_BOT\_V3\_13b\_GPTQ](... | 2023-10-16T06:25:44 | https://www.reddit.com/r/LocalLLaMA/comments/178zi8w/plot_bot_v3_13b_gptq_a_fully_uncensored_plot/ | FPham | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 178zi8w | false | null | t3_178zi8w | /r/LocalLLaMA/comments/178zi8w/plot_bot_v3_13b_gptq_a_fully_uncensored_plot/ | false | false | 30 | {'enabled': False, 'images': [{'id': 'GbfoXG7QPFPjGmNBVbOajyZ1Iik0OSiIo9_DCCMXYWM', 'resolutions': [{'height': 58, 'url': 'https://external-preview.redd.it/OzGNWsyqSCGB5byW6qDgs-RIffQqqBa-xVZJg_OP6H8.jpg?width=108&crop=smart&auto=webp&s=d56c20f6bc4127514b034a222b8d79b864a8aa79', 'width': 108}, {'height': 116, 'url': 'h... | |
FOMO Saver | 1 | [removed] | 2023-10-16T06:25:39 | https://www.reddit.com/r/LocalLLaMA/comments/178zi75/fomo_saver/ | HorrorNo8851 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 178zi75 | false | null | t3_178zi75 | /r/LocalLLaMA/comments/178zi75/fomo_saver/ | false | false | self | 1 | {'enabled': False, 'images': [{'id': 'Sh9Zg-lps9gGX4zFrCupyku8O5tKblcB0xRYcE57nx4', 'resolutions': [{'height': 54, 'url': 'https://external-preview.redd.it/2ZDWpbqV4DhZgQVSXpLbctYjTeuxWnE8SIhU5I4VfQc.jpg?width=108&crop=smart&auto=webp&s=bdca71579d6630c8cb3c7278f79137e2265f352b', 'width': 108}, {'height': 108, 'url': 'h... |
PromptBreeder | 2 | How exactly does this PromptBrreder work?
"The system starts with an initial set of prompts that are scored based on the model's performance on logical tasks involving those prompts.".This is from the Decoder article about Promptbreeder. Does the user give these initial prompts to the system?? | 2023-10-16T06:01:36 | https://www.reddit.com/r/LocalLLaMA/comments/178z6a7/promptbreeder/ | hana1423 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 178z6a7 | false | null | t3_178z6a7 | /r/LocalLLaMA/comments/178z6a7/promptbreeder/ | false | false | self | 2 | null |
Code gen equivalent of MBZUAI/LaMini-Flan-T5-248M | 2 | So as the title says, I am looking for a code gen model, that is equivalent to the MBZUAI/LaMini-Flan-T5-248M model for chat. I used the Flan-T5 model for a RAG application and it worked pretty well.
​
Now I am looking for a similar model(small and fast) for simple code kind of response generations:
The model... | 2023-10-16T05:44:51 | https://www.reddit.com/r/LocalLLaMA/comments/178yxhq/code_gen_equivalent_of_mbzuailaminiflant5248m/ | IamFuckinTomato | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 178yxhq | false | null | t3_178yxhq | /r/LocalLLaMA/comments/178yxhq/code_gen_equivalent_of_mbzuailaminiflant5248m/ | false | false | self | 2 | null |
Need a scalable solution for running LLMs | 5 | Hey everyone,
Recently, I have been very interested in running my own local (or cloud) LLM and feeding it my data to create a chatbot. Of course, the nature of the provided data is sensitive, so I will be using RAG to minimize hallucinations and get factual and clear answers (Q&A).
While I am still learning, I have a... | 2023-10-16T05:14:05 | https://www.reddit.com/r/LocalLLaMA/comments/178yh5y/need_a_scalable_solution_for_running_llms/ | Ayzarrr | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 178yh5y | false | null | t3_178yh5y | /r/LocalLLaMA/comments/178yh5y/need_a_scalable_solution_for_running_llms/ | false | false | self | 5 | null |
Has anyone tried LlaVA for Document QA using RAG? | 5 | I think this could work well for unstructured data, has anyone tried it? | 2023-10-16T04:55:28 | https://www.reddit.com/r/LocalLLaMA/comments/178y6sq/has_anyone_tried_llava_for_document_qa_using_rag/ | LiquidGunay | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 178y6sq | false | null | t3_178y6sq | /r/LocalLLaMA/comments/178y6sq/has_anyone_tried_llava_for_document_qa_using_rag/ | false | false | self | 5 | null |
Is multigpu (on exl2 or llama.cpp) affected by low PCIE bandwidth? | 1 | I have a motherboard with a room for a second gpu. However, the slot only has a speed of PCIE 3 x4.
Additionally, there are other training regiments I'd use, like axolotl.
Is low speed pcie a big problem or can it be easily remidied by using something like NVlink (for a 2nd 3090)? | 2023-10-16T04:51:54 | https://www.reddit.com/r/LocalLLaMA/comments/178y4tj/is_multigpu_on_exl2_or_llamacpp_affected_by_low/ | Aaaaaaaaaeeeee | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 178y4tj | false | null | t3_178y4tj | /r/LocalLLaMA/comments/178y4tj/is_multigpu_on_exl2_or_llamacpp_affected_by_low/ | false | false | self | 1 | null |
Is it normal to have 20~t/s on 4090 with 13B model? | 26 | Currently I am using
https://huggingface.co/TheBloke/MythoMax-L2-13B-GPTQ
Setup:
CPU 13700kf
GPU 4090
RAM: 64GB
Operation System: Win10
When I am running the model on oobabooga, and uses ST as front UI, I am only getting around 20t/s, sometime around 25t/s, is it normal? Or is something wrong? | 2023-10-16T04:20:03 | https://www.reddit.com/r/LocalLLaMA/comments/178xmnm/is_it_normal_to_have_20ts_on_4090_with_13b_model/ | lasaiy | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 178xmnm | false | null | t3_178xmnm | /r/LocalLLaMA/comments/178xmnm/is_it_normal_to_have_20ts_on_4090_with_13b_model/ | false | false | self | 26 | {'enabled': False, 'images': [{'id': '7A-IlVd5L1jBDVLRBnGCjf_MrVIikjPmtx9pEVOW7R0', 'resolutions': [{'height': 58, 'url': 'https://external-preview.redd.it/k8ELwyDbiRxlHlXYqRucKqutq_AunyPCuvt71QxWAJY.jpg?width=108&crop=smart&auto=webp&s=87f41c0f6cee42e1649464b1e6b0ef1585ad5f33', 'width': 108}, {'height': 116, 'url': 'h... |
How do you get 30b/33b 8k context models to work in OobaBooga without super slowing down after a few responses using a 24GB video card? | 5 | I'm using a RTX 4090, running these @ 4096/2 with Exllama (or eXllama\_HF) and after a few replies from the AI, the responses still come, but they are unbearably slooooow. Like 1 token/s or less slow...I mean they are slow in general, but it gets maddening...
How do I prevent this? What optimization switches are you ... | 2023-10-16T03:18:28 | https://www.reddit.com/r/LocalLLaMA/comments/178wkn3/how_do_you_get_30b33b_8k_context_models_to_work/ | cleverestx | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 178wkn3 | false | null | t3_178wkn3 | /r/LocalLLaMA/comments/178wkn3/how_do_you_get_30b33b_8k_context_models_to_work/ | false | false | self | 5 | null |
A Lora Collection manager for Text WebUi | 6 | If you are like me you have 100s of Loras. this is a simple project to keep a collections of them. This is only for Ooba Text WebUI. You'll have to a bit figure it out.
https://preview.redd.it/9kvsp2dk3hub1.png?width=1156&format=png&auto=webp&s=538a150601c3fd02e0e6bd8552ff4bc10c657078 | 2023-10-16T02:10:49 | https://www.reddit.com/r/LocalLLaMA/comments/178vb89/a_lora_collection_manager_for_text_webui/ | FPham | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 178vb89 | false | null | t3_178vb89 | /r/LocalLLaMA/comments/178vb89/a_lora_collection_manager_for_text_webui/ | false | false | 6 | null | |
【Pandalyst-7B-V1.2】 Now we can plot 📈 and much more powerful ! | 18 | ## Pandalyst: A large language model for mastering data analysis using pandas
https://github.com/pipizhaoa/Pandalyst
## News
- 🔥[2023/10/15] Now we can **plot** 📈! and much more powerful! We released **Pandalyst-7B-V1.2**, which was trained on **CodeLlama-7b-Python** and it surpasses **ChatGPT-3.5 (2023/06/13)**, *... | 2023-10-16T01:50:53 | https://www.reddit.com/r/LocalLLaMA/comments/178uxtf/pandalyst7bv12_now_we_can_plot_and_much_more/ | Wise_Argument_882 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 178uxtf | false | null | t3_178uxtf | /r/LocalLLaMA/comments/178uxtf/pandalyst7bv12_now_we_can_plot_and_much_more/ | false | false | self | 18 | {'enabled': False, 'images': [{'id': 'jeWAYIWEjsOLgzqUAWhBSajLbGB0NUk7mEaaZsxK7Nc', 'resolutions': [{'height': 54, 'url': 'https://external-preview.redd.it/yK4qWPNBHagkLYo901EHrvLd0SqJ1C2-idMwdvRABfU.jpg?width=108&crop=smart&auto=webp&s=4785fe5be24aff1fc88657913bb1a3c8339b8405', 'width': 108}, {'height': 108, 'url': 'h... |
Updated: Comparison on exllamav2, of bits/bpw: 2.5,4.25,4.5,4.65, 5, 6, and 7 (airoboros-l2-70b-gpt4-1.4.1) | 38 | After some time, more exllamav2 updates, fixes, and also I can't control my impulses and got a used 3090, so now I've updated these tests, with more bpw sizes (6 and 7bpw).
Also, past time the quants had some issues in the last quant part, which is fixed now. At the same time, removed 4.75bpw since it performs basical... | 2023-10-16T01:01:15 | https://www.reddit.com/r/LocalLLaMA/comments/178tzps/updated_comparison_on_exllamav2_of_bitsbpw/ | panchovix | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 178tzps | false | null | t3_178tzps | /r/LocalLLaMA/comments/178tzps/updated_comparison_on_exllamav2_of_bitsbpw/ | false | false | self | 38 | {'enabled': False, 'images': [{'id': 'G6iQk5ypIUEwEQqGFlng2KCL3SuYnosmOyiiZflFGVA', 'resolutions': [{'height': 36, 'url': 'https://external-preview.redd.it/B3glV0pQlc4O-NgDlCajYEoFWm3JDvLAt4Aa3bobAno.jpg?width=108&crop=smart&auto=webp&s=7194335697ad06ca7339345954a94c780675fe2f', 'width': 108}, {'height': 73, 'url': 'ht... |
PSA: Make old school backups before updating your inference programs | 9 | **EDIT:** Some great alternative strategies to this post in the comments below. Ultimately, whatever path you take- the point is that sometimes these updates can break your thingy, so please be ready for that BEFORE clicking the update button. This way you'll have options available to you should you need to run a model... | 2023-10-15T23:05:31 | https://www.reddit.com/r/LocalLLaMA/comments/178rp3u/psa_make_old_school_backups_before_updating_your/ | SomeOddCodeGuy | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 178rp3u | false | null | t3_178rp3u | /r/LocalLLaMA/comments/178rp3u/psa_make_old_school_backups_before_updating_your/ | false | false | self | 9 | null |
Bing chat consensus | 1 | I think it would be good to know the aggregate of use of free LARGE LM's. I will start the comments by giving my vote choice and why I chose it, it would be insightful for us all to give our reason for using the free tools that are currently superior. Our joint wants may offer insights into future models was why this h... | 2023-10-15T22:55:37 | https://www.reddit.com/r/LocalLLaMA/comments/178rhmn/bing_chat_consensus/ | randomrealname | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 178rhmn | false | null | t3_178rhmn | /r/LocalLLaMA/comments/178rhmn/bing_chat_consensus/ | false | false | self | 1 | null |
Samantha fine-tune | 3 | Greetings. Seeking for help guys. Since the last version of Samantha mistral 7b has been relased, and the dataset of samantha has also been translated in ITA, I would like to fine tune Samantha with the translated dataset (have json and jsonl files). I am able to run the model ehartford/samantha-1.2-mistral-7b on my pc... | 2023-10-15T22:54:12 | https://www.reddit.com/r/LocalLLaMA/comments/178rgih/samantha_finetune/ | simon_cry | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 178rgih | false | null | t3_178rgih | /r/LocalLLaMA/comments/178rgih/samantha_finetune/ | false | false | self | 3 | null |
Deploying Quantized Llama 2 model to GCP cloud run | 2 | I’m looking at deploying a Llama 2 model to GCP cloud run in a container. It will run on CPUs. Has anyone done it before? Any tips or thoughts? | 2023-10-15T22:13:31 | https://www.reddit.com/r/LocalLLaMA/comments/178ql8v/deploying_quantized_llama_2_model_to_gcp_cloud_run/ | Success81 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 178ql8v | false | null | t3_178ql8v | /r/LocalLLaMA/comments/178ql8v/deploying_quantized_llama_2_model_to_gcp_cloud_run/ | false | false | self | 2 | null |
llama.cpp help: Different reverse prompt behavior between running main script directly in terminal versus running as a subprocess from Python script | 1 | Hello, I am making a Python wrapper around llama.cpp via Python's subprocess library. The documented behavior of llama.cpp when a reverse prompt is passed in but interactive mode is turned off is for the program to exit, which it does correctly, when run from the terminal with
./main -m models/70B/llama-2-70b-chat.Q5... | 2023-10-15T21:44:27 | https://www.reddit.com/r/LocalLLaMA/comments/178pyd4/llamacpp_help_different_reverse_prompt_behavior/ | eisenhorn40k | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 178pyd4 | false | null | t3_178pyd4 | /r/LocalLLaMA/comments/178pyd4/llamacpp_help_different_reverse_prompt_behavior/ | false | false | self | 1 | null |
Jon Durbin released Airoboros 3.1 | 63 | [https://huggingface.co/jondurbin/airoboros-l2-13b-3.1](https://huggingface.co/jondurbin/airoboros-l2-13b-3.1) and [https://huggingface.co/jondurbin/airoboros-m-7b-3.1](https://huggingface.co/jondurbin/airoboros-m-7b-3.1)
I've tested the Mistral one and so far, I'm very impressed. It's coherent and smart in roleplay a... | 2023-10-15T21:19:01 | https://www.reddit.com/r/LocalLLaMA/comments/178pdd0/jon_durbin_released_airoboros_31/ | dampflokfreund | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 178pdd0 | false | null | t3_178pdd0 | /r/LocalLLaMA/comments/178pdd0/jon_durbin_released_airoboros_31/ | false | false | self | 63 | {'enabled': False, 'images': [{'id': 'niyL2HjnQUkuL3GRivM5cjv1FI7mdKE8s3TSy4-rMOo', 'resolutions': [{'height': 58, 'url': 'https://external-preview.redd.it/i2ClrcB6lhy2d3R1aFQuuK0X7aXhtqzpTPdojr4NREQ.jpg?width=108&crop=smart&auto=webp&s=f246957b8671d211adbdad92d566b88a86484635', 'width': 108}, {'height': 116, 'url': 'h... |
Newbie question -- what can I do with ~200GB of RAM but no GPU? | 28 | Want to experiment with LlaMA and other models, particularly in a context somewhat like AutoGPT, where I can set the LLM off on research tasks. But the only hardware I have readily available is heavy on RAM but virtually non-existent on GPU power -- it's a rackmount server.
Any options that would work in this environm... | 2023-10-15T21:12:48 | https://www.reddit.com/r/LocalLLaMA/comments/178p879/newbie_question_what_can_i_do_with_200gb_of_ram/ | GWBrooks | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 178p879 | false | null | t3_178p879 | /r/LocalLLaMA/comments/178p879/newbie_question_what_can_i_do_with_200gb_of_ram/ | false | false | self | 28 | null |
What is the best chat/rp model that can run on 8gb of vram. (any model type) | 5 | Hello, I've been messing with some models on my gaming laptop. I was wondering what the best one for chat/rp is that I could run. | 2023-10-15T20:58:07 | https://www.reddit.com/r/LocalLLaMA/comments/178ovsm/what_is_the_best_chatrp_model_that_can_run_on_8gb/ | mjh657 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 178ovsm | false | null | t3_178ovsm | /r/LocalLLaMA/comments/178ovsm/what_is_the_best_chatrp_model_that_can_run_on_8gb/ | false | false | self | 5 | null |
NanoPhi Update, Fixed Dataset, New tasks In multitask data, working chat sampling, and Emergent Properties! | 16 | Hi, everyone, Finally got around to NanoPhi.
- As u/Dry_Long3157, the Dataset JsonL was broken, and now thats fixed, the datasets around 1.4b tokens, 3.5 million rows of text
- u/Docsoc1 mentioned https://arxiv.org/abs/2305.10429, Looking into that, see if it helps
- As people have asked, I'll be releasing training... | 2023-10-15T20:36:48 | https://www.reddit.com/r/LocalLLaMA/comments/178oext/nanophi_update_fixed_dataset_new_tasks_in/ | vatsadev | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 178oext | false | null | t3_178oext | /r/LocalLLaMA/comments/178oext/nanophi_update_fixed_dataset_new_tasks_in/ | false | false | self | 16 | {'enabled': False, 'images': [{'id': 'q3evP6JeDpAC2MdSQHWYxnCYTqbJkElIQsLFqVSdkss', 'resolutions': [{'height': 63, 'url': 'https://external-preview.redd.it/izh8gZHY4FqZ1nwtU1N_TjtohUCNuvTyMn90toXda80.jpg?width=108&crop=smart&auto=webp&s=bc9575b410002edc2df3c5b5b0355fefedc7baa8', 'width': 108}, {'height': 126, 'url': 'h... |
🐺🐦⬛ Mistral LLM Comparison/Test: Instruct, OpenOrca, Dolphin, Zephyr and more... | 232 | **Wolfram's Mistral LLM Comparison/Test: Instruct, OpenOrca, Dolphin, Zephyr and more...**
With the Mistral hype still going strong, I wanted to evaluate these promising 7B models some more. And there's also the lingering question how much quantization affects quality. Plus, there have been multiple German models rele... | 2023-10-15T19:50:25 | https://www.reddit.com/r/LocalLLaMA/comments/178nf6i/mistral_llm_comparisontest_instruct_openorca/ | WolframRavenwolf | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 178nf6i | false | null | t3_178nf6i | /r/LocalLLaMA/comments/178nf6i/mistral_llm_comparisontest_instruct_openorca/ | false | false | self | 232 | {'enabled': False, 'images': [{'id': '2g4MtoKvhQOBCmeiXB1qv1h_5M24BeeYF64zcf4-rfg', 'resolutions': [{'height': 142, 'url': 'https://external-preview.redd.it/0z4RbV35RPDd2wqL6Oyz-uwz9kKNBAH0ePojGplYP2M.jpg?width=108&crop=smart&auto=webp&s=bbe38cbb6d4f7a7e6dd7d3c8b79c4ac9ba965545', 'width': 108}, {'height': 284, 'url': '... |
Esther: My first attempt at playing with local llama as a Clojure diary app | 1 | 2023-10-15T19:08:06 | https://github.com/vortext/esther | Difficult-Support794 | github.com | 1970-01-01T00:00:00 | 0 | {} | 178mi43 | false | null | t3_178mi43 | /r/LocalLLaMA/comments/178mi43/esther_my_first_attempt_at_playing_with_local/ | false | false | 1 | {'enabled': False, 'images': [{'id': 'XsaUxVR-n4TSNquCDP_2z-1kC_d1SMtI1Ez89PINqpY', 'resolutions': [{'height': 54, 'url': 'https://external-preview.redd.it/f2WNlU3yKHCKvPtAJI5B8RdsYU-vxLAFqqeJrPBn3VE.jpg?width=108&crop=smart&auto=webp&s=5480af121bffc11dbcc63a5fba3b1980173338ae', 'width': 108}, {'height': 108, 'url': 'h... | ||
Merge a lora then AWQ | 3 | Hey everyone, I have a question regarding AWQ. I have several adapters trained and I was wondering if I can merge them to the base model and then quantize that model using AWQ? Anyone done that? Any tips? | 2023-10-15T16:41:28 | https://www.reddit.com/r/LocalLLaMA/comments/178jdg1/merge_a_lora_then_awq/ | Torkoslav | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 178jdg1 | false | null | t3_178jdg1 | /r/LocalLLaMA/comments/178jdg1/merge_a_lora_then_awq/ | false | false | self | 3 | null |
Those that have built a pc for non-professional self hosted AI/ML: Is it worth it? | 74 | Prior to all this recent cool AI / ML stuff, I had been going back and forth over building a PC for years. I'm very much a 'bang for buck' gamer and I enjoyed having a linux laptop for development and a gaming console for gaming.
Nowadays I have a solid career as a sr dev, but I feel like I'm behind the times a littl... | 2023-10-15T16:34:29 | https://www.reddit.com/r/LocalLLaMA/comments/178j7yu/those_that_have_built_a_pc_for_nonprofessional/ | alpacaMyToothbrush | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 178j7yu | false | null | t3_178j7yu | /r/LocalLLaMA/comments/178j7yu/those_that_have_built_a_pc_for_nonprofessional/ | false | false | self | 74 | null |
LLM frameworks that allow continuous batching on quantized models? | 2 | For now I know vLLM and lmdeploy
Do you know other ones to put quantized models in production and achieve high throughput? | 2023-10-15T16:26:44 | https://www.reddit.com/r/LocalLLaMA/comments/178j1vr/llm_frameworks_that_allow_continuous_batching_on/ | Exotic-Estimate8355 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 178j1vr | false | null | t3_178j1vr | /r/LocalLLaMA/comments/178j1vr/llm_frameworks_that_allow_continuous_batching_on/ | false | false | self | 2 | null |
Introducing MiniSearch - A minimalist search engine with integrated browser-based AI | 1 | 2023-10-15T16:15:13 | https://www.linkedin.com/pulse/introducing-minisearch-minimalist-search-engine-ai-victor-nogueira/ | Felladrin | linkedin.com | 1970-01-01T00:00:00 | 0 | {} | 178it0g | false | null | t3_178it0g | /r/LocalLLaMA/comments/178it0g/introducing_minisearch_a_minimalist_search_engine/ | false | false | 1 | {'enabled': False, 'images': [{'id': '8ywkLgcbx7oB0uf6C3n7NNHnf20FMR_4HaRaQEpkIls', 'resolutions': [{'height': 60, 'url': 'https://external-preview.redd.it/CJpaGghalVjP0l3X44H6RFIPc-VIj-LrJlecjSTZWhY.jpg?width=108&crop=smart&auto=webp&s=aecd34e28a22fc3e8af13e0107b3db62064fcad2', 'width': 108}, {'height': 121, 'url': 'h... | ||
What is the best 7b or 13b RP model you are currently using? | 9 | And why? | 2023-10-15T16:11:12 | https://www.reddit.com/r/LocalLLaMA/comments/178ipxe/what_is_the_best_7b_or_13b_rp_model_you_are/ | swwer | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 178ipxe | false | null | t3_178ipxe | /r/LocalLLaMA/comments/178ipxe/what_is_the_best_7b_or_13b_rp_model_you_are/ | false | false | self | 9 | null |
New Vision-Language Model: BakLLaVA-1, finetuned on Mistral 7B | 195 | 2023-10-15T15:33:52 | https://x.com/skunkworks_ai/status/1713372586225156392?s=20 | ninjasaid13 | x.com | 1970-01-01T00:00:00 | 0 | {} | 178hx93 | false | null | t3_178hx93 | /r/LocalLLaMA/comments/178hx93/new_visionlanguage_model_bakllava1_finetuned_on/ | false | false | 195 | {'enabled': False, 'images': [{'id': 'yvQxxqsrR7psusgjeWb_rrkd8g60PRHJnkXTOijJfKk', 'resolutions': [{'height': 45, 'url': 'https://external-preview.redd.it/0NW1_rDFLEmyj6PCMapjYyPHEe7qGSZoVrruoiWvXfg.jpg?width=108&crop=smart&auto=webp&s=e8c727b2b1ad54903ae814f9a80e0603d8251044', 'width': 108}, {'height': 91, 'url': 'ht... | ||
PSA: Most GGUF falcon models on HF are now broken, don't download them. | 34 | A week ago there was some change to BPE tokenization. I think it was https://github.com/ggerganov/llama.cpp/pull/3252
As a result your existing falcon GGUF will now drop this error and refuse to load.
error loading model: invalid character
llama_load_model_from_file: failed to load model
2023-10-15 10:11:... | 2023-10-15T15:19:18 | https://www.reddit.com/r/LocalLLaMA/comments/178hma9/psa_most_gguf_falcon_models_on_hf_are_now_broken/ | a_beautiful_rhind | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 178hma9 | false | null | t3_178hma9 | /r/LocalLLaMA/comments/178hma9/psa_most_gguf_falcon_models_on_hf_are_now_broken/ | false | false | self | 34 | {'enabled': False, 'images': [{'id': 'a3hmEjMBofreyOb56flC-qgpWccNCl896xNCLJvKbMk', 'resolutions': [{'height': 54, 'url': 'https://external-preview.redd.it/PKGus4j_oB3dFq3hJv4rfRCqmQivDOq_MMKJ1Tt6hHE.jpg?width=108&crop=smart&auto=webp&s=a2cff3cc7747c7e1b5ae271ec6a8167602655089', 'width': 108}, {'height': 108, 'url': 'h... |
Is possible to use llama for relation extraction tasks? | 1 | Hey guys, I am new in this llm world. I have a personal project that I need to do that. So, is it possible? If yes, can you give me some tips? | 2023-10-15T15:13:03 | https://www.reddit.com/r/LocalLLaMA/comments/178hhm2/is_possible_to_use_llama_for_relation_extraction/ | Lipao262 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 178hhm2 | false | null | t3_178hhm2 | /r/LocalLLaMA/comments/178hhm2/is_possible_to_use_llama_for_relation_extraction/ | false | false | self | 1 | null |
Making LLM aware of API documentation | 8 | I want to explore some text-to-code use cases for a specific REST API I’m working with. The API has all of its documentation online. Is there some way to make LLaMA “aware” of that documentation absent putting it in the prompt (which would be way too long)? | 2023-10-15T14:29:47 | https://www.reddit.com/r/LocalLLaMA/comments/178gktl/making_llm_aware_of_api_documentation/ | Busy-Pie-4468 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 178gktl | false | null | t3_178gktl | /r/LocalLLaMA/comments/178gktl/making_llm_aware_of_api_documentation/ | false | false | self | 8 | null |
Performance report - Inference with two RTX 4060 Ti 16Gb | 88 | \## Summary
​
This post is about my hardware setup and how it performs certain LLM tasks. The idea is to provide a baseline for how a similar platform might operate.
I was inspired by the suggestions of u/FieldProgrammable and u/Zangwuz, who mentioned that sharing performance figures from my workstation could... | 2023-10-15T14:29:42 | https://www.reddit.com/r/LocalLLaMA/comments/178gkr0/performance_report_inference_with_two_rtx_4060_ti/ | pmelendezu | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 178gkr0 | false | null | t3_178gkr0 | /r/LocalLLaMA/comments/178gkr0/performance_report_inference_with_two_rtx_4060_ti/ | false | false | 88 | {'enabled': False, 'images': [{'id': 'hJ-NOGJkmb4yVp5AV2etJH4o1-8RexqWrQ2uI23eEx0', 'resolutions': [{'height': 54, 'url': 'https://external-preview.redd.it/fDOtYa0W_Iw3uzkfhqfq7JmmZKC8Vn5Wu8OawvGMH7U.jpg?width=108&crop=smart&auto=webp&s=9d9055e393ea341d62fcca1c9f089fa277a73883', 'width': 108}, {'height': 108, 'url': 'h... | |
AVX512 on scalable Xeon | 3 | I would like to build a pure-cpu server to run really large models such as Falcon and Llama. After seeing [This Post](https://www.reddit.com/r/LocalLLaMA/comments/16vlf0d/i_am_looking_for_information_regarding_running/), I think i should to re-compile llama.cpp to enable the AVX512 support. I use Xeon Gold 6138 CPU\*2,... | 2023-10-15T14:24:02 | https://www.reddit.com/r/LocalLLaMA/comments/178ggp3/avx512_on_scalable_xeon/ | MarySmith2021 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 178ggp3 | false | null | t3_178ggp3 | /r/LocalLLaMA/comments/178ggp3/avx512_on_scalable_xeon/ | false | false | self | 3 | null |
Local LLM suggestions for low spec pc: RX 580 8GB or CPU 16 GB inference? | 4 | Hi,
I am planning to try out local LLMs. My hardware specs are:
* CPU: Ryzen 3200g
* Ram: 3200 MHz 8 GB (2x)
* GPU: RX 580 8 GB
I know its not much, and my goal isn’t running 34/70B models or anything, I just want to see how local LLMs within these specs perform.
Given my specs, do you think I would try GPU or CP... | 2023-10-15T14:18:15 | https://www.reddit.com/r/LocalLLaMA/comments/178gcif/local_llm_suggestions_for_low_spec_pc_rx_580_8gb/ | FewLifetimes_ago_21 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 178gcif | false | null | t3_178gcif | /r/LocalLLaMA/comments/178gcif/local_llm_suggestions_for_low_spec_pc_rx_580_8gb/ | false | false | self | 4 | null |
having issues with loading models in oobabooga using exllamma (errors in pic) | 1 | 2023-10-15T13:22:16 | BoostManMaG | i.redd.it | 1970-01-01T00:00:00 | 0 | {} | 178f921 | false | null | t3_178f921 | /r/LocalLLaMA/comments/178f921/having_issues_with_loading_models_in_oobabooga/ | false | false | 1 | {'enabled': True, 'images': [{'id': 'Lj96zW-YvMVCvks5KVaK7yuJKt46k-G3HsA3O1HjI44', 'resolutions': [{'height': 89, 'url': 'https://preview.redd.it/fwwvrrfhadub1.png?width=108&crop=smart&auto=webp&s=3a1c1787b00da7281f487a090223f8ee68888618', 'width': 108}, {'height': 178, 'url': 'https://preview.redd.it/fwwvrrfhadub1.png... | |||
Transformers / Llama.cpp / GGUF / GGML / GPTQ & other animals | 60 | i am a little puzzled,
1. i know that transformers is the HF framework/library to load infere and train models easily
2. and that llama.cpp is another framework/library that does the more of the same but specialized in models that runs on CPU and quanitized and run much faster
3. i understand that GGML is a file forma... | 2023-10-15T12:44:03 | https://www.reddit.com/r/LocalLLaMA/comments/178el7j/transformers_llamacpp_gguf_ggml_gptq_other_animals/ | Particular_Flower_12 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 178el7j | false | null | t3_178el7j | /r/LocalLLaMA/comments/178el7j/transformers_llamacpp_gguf_ggml_gptq_other_animals/ | false | false | self | 60 | null |
Best for multiple LoRA adapter inference | 4 | Hi guys, I want to run multiple LoRA finetuned models based on the same base model (Mistral 7b). What is the best framework for this? vLLM does not seem to support LoRA officially yet and I would want to host the model on a single L4/L40 and hotswap various adapters depending on which one I want to use. Any help would ... | 2023-10-15T12:35:45 | https://www.reddit.com/r/LocalLLaMA/comments/178egak/best_for_multiple_lora_adapter_inference/ | WillingMood2319 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 178egak | false | null | t3_178egak | /r/LocalLLaMA/comments/178egak/best_for_multiple_lora_adapter_inference/ | false | false | self | 4 | null |
Which 70B model is best for writing short stories, and will also take long queries better? | 1 | [removed] | 2023-10-15T10:41:59 | https://www.reddit.com/r/LocalLLaMA/comments/178cq79/which_70b_model_is_best_for_writing_short_stories/ | Secret_Joke_2262 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 178cq79 | false | null | t3_178cq79 | /r/LocalLLaMA/comments/178cq79/which_70b_model_is_best_for_writing_short_stories/ | false | false | default | 1 | {'enabled': False, 'images': [{'id': 'CCjtpAVlCtLDCoAHHFwRN2O1m-krrAmSo-QmVT6VCqk', 'resolutions': [{'height': 54, 'url': 'https://external-preview.redd.it/iQz_kKaVapQu1lqlw2lPbkDPGg08_pacRD3bcZDYf6E.jpg?width=108&crop=smart&auto=webp&s=dc9e34c7fef24991dc6c420a7c6860200a958d5b', 'width': 108}, {'height': 108, 'url': 'h... |
Fine tune Llama2 with Lora for foreign language | 1 | [removed] | 2023-10-15T10:26:51 | https://www.reddit.com/r/LocalLLaMA/comments/178cifz/fine_tune_llama2_with_lora_for_foreign_language/ | kostakos14 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 178cifz | false | {'oembed': {'author_name': 'Sam Witteveen', 'author_url': 'https://www.youtube.com/@samwitteveenai', 'height': 200, 'html': '<iframe width="356" height="200" src="https://www.youtube.com/embed/ThKWQcyQXF8?feature=oembed&enablejsapi=1" frameborder="0" allow="accelerometer; autoplay; clipboard-write; encrypted-media; gyr... | t3_178cifz | /r/LocalLLaMA/comments/178cifz/fine_tune_llama2_with_lora_for_foreign_language/ | false | false | 1 | {'enabled': False, 'images': [{'id': 'VDbmKyCTHTQ7qgGIBBfQXwWTaf_iS02RNahxvhWPFJM', 'resolutions': [{'height': 81, 'url': 'https://external-preview.redd.it/oolHAgC3LIYbXQdLGhdNeE8Gei36mJJfKoQeRAIz5QY.jpg?width=108&crop=smart&auto=webp&s=7e9660651fd8f39c83e123d238c1786a1f26e59f', 'width': 108}, {'height': 162, 'url': 'h... | |
LLM for audit logs | 11 | Hi all. For privacy and security reasons I would like to move out from chatgpt-3.5 and hence use local llm to feed audit logs from my services (e.g. hashicorp vault, Openstack, keystone e.t.c.) and use it to summarise logs and describe what happened. Is there a model in huggingface that I could use? If not how can I ge... | 2023-10-15T09:05:50 | https://www.reddit.com/r/LocalLLaMA/comments/178bfm8/llm_for_audit_logs/ | dimtass | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 178bfm8 | false | null | t3_178bfm8 | /r/LocalLLaMA/comments/178bfm8/llm_for_audit_logs/ | false | false | self | 11 | null |
Multi-Client model Fine-tuning: One model or individual models for each client? | 2 |
Reddit Data for LLM?
Web Browsing
Custom instructions details
User
Write me a reddit question Post where I ask if I can create a llm with data of one or more channel from reddit
ChatGPT
Title: Utilizing Reddit Channel Data for Creating a Language Model: Feasibility and Recommendations?
Body:
Hello everyone,
I'm ... | 2023-10-15T08:56:11 | https://www.reddit.com/r/LocalLLaMA/comments/178bb2x/multiclient_model_finetuning_one_model_or/ | yotobeetaylor | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 178bb2x | false | null | t3_178bb2x | /r/LocalLLaMA/comments/178bb2x/multiclient_model_finetuning_one_model_or/ | false | false | self | 2 | null |
Using local llm with reddit data | 2 | Hello everyone,
I'm venturing into the realm of Natural Language Processing (NLP) and I am intrigued by the idea of training a language model using data extracted from one or more channels on Reddit.
I'm wondering if anyone has embarked on a similar project or has insights on the feasibility of this idea? Additionall... | 2023-10-15T08:53:52 | https://www.reddit.com/r/LocalLLaMA/comments/178b9zt/using_local_llm_with_reddit_data/ | yotobeetaylor | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 178b9zt | false | null | t3_178b9zt | /r/LocalLLaMA/comments/178b9zt/using_local_llm_with_reddit_data/ | false | false | self | 2 | null |
Open llm leader board on hugging face is not loading | 11 | Is it just me or is there something wrong with the open llm leader board on hugging face ?
https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard
It shows an error on loading the page | 2023-10-15T08:43:22 | https://www.reddit.com/r/LocalLLaMA/comments/178b530/open_llm_leader_board_on_hugging_face_is_not/ | testerpce | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 178b530 | false | null | t3_178b530 | /r/LocalLLaMA/comments/178b530/open_llm_leader_board_on_hugging_face_is_not/ | false | false | self | 11 | {'enabled': False, 'images': [{'id': 'EN0-abblERL52DxeoNzcxdkhvXEwLdZMJTS58Umjs64', 'resolutions': [{'height': 58, 'url': 'https://external-preview.redd.it/tSZUq9622TYSgtzH4foFlGwz9n9ixCJUAgev8O2x8jI.jpg?width=108&crop=smart&auto=webp&s=90f4efd1c1314faf5b0cd1c5eeb8d2835fe4a3ba', 'width': 108}, {'height': 116, 'url': 'h... |
Pandalyst-7B-V1.2 !!! Now we can plot 📈 ! and much more powerful ! | 1 | [removed] | 2023-10-15T08:13:25 | https://www.reddit.com/r/LocalLLaMA/comments/178aqfc/pandalyst7bv12_now_we_can_plot_and_much_more/ | Wise_Argument_882 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 178aqfc | false | null | t3_178aqfc | /r/LocalLLaMA/comments/178aqfc/pandalyst7bv12_now_we_can_plot_and_much_more/ | false | false | self | 1 | null |
Accelerated Inferenced on CPUs with Deepsparse | 4 | MPT Sparse Finetuned on GSM8k with DeepSparse
"The MPT model runs purely on CPU courtesy of sparse software execution by DeepSparse. DeepSparse provides accelerated inference by taking advantage of the MPT model's weight sparsity to deliver tokens fast!"
https://huggingface.co/spaces/neuralmagic/sparse-mpt-7b-gsm8k
... | 2023-10-15T07:48:22 | https://www.reddit.com/r/LocalLLaMA/comments/178adx2/accelerated_inferenced_on_cpus_with_deepsparse/ | mitirki | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 178adx2 | false | null | t3_178adx2 | /r/LocalLLaMA/comments/178adx2/accelerated_inferenced_on_cpus_with_deepsparse/ | false | false | self | 4 | {'enabled': False, 'images': [{'id': '831Gswk3prsPuJCde49GC6EZD2tGTCMSRgrs6MeZUgA', 'resolutions': [{'height': 58, 'url': 'https://external-preview.redd.it/aW9FoRtOAAPrqj77rJBenDT8jiZrpZrsjAEgOX2wUXY.jpg?width=108&crop=smart&auto=webp&s=a76666d3860b141deef8603528b94bb96bbc0151', 'width': 108}, {'height': 116, 'url': 'h... |
Finetune model but retain original reasoning and language capabilities | 4 | Hi,
​
i am fine tuning using qlora the Open-Orca/Mistral-7B-OpenOrca model for specific down stream tasks like NER extraction and classification.
​
this is working well and not facing any issues with this.
​
but the fine tuned model doesn't retain original conversation abilities of openorca ... | 2023-10-15T05:43:32 | https://www.reddit.com/r/LocalLLaMA/comments/1788nfp/finetune_model_but_retain_original_reasoning_and/ | manishiitg | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 1788nfp | false | null | t3_1788nfp | /r/LocalLLaMA/comments/1788nfp/finetune_model_but_retain_original_reasoning_and/ | false | false | self | 4 | null |
Model conversion | 1 | I have downloaded a GGUF model. To load it in GPT4All, I think I have to covert it into .bin model. Could anyone possibly guide me on that stuff? Thanks in advance. | 2023-10-15T04:38:05 | https://www.reddit.com/r/LocalLLaMA/comments/1787nld/model_conversion/ | New-Contribution6302 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 1787nld | false | null | t3_1787nld | /r/LocalLLaMA/comments/1787nld/model_conversion/ | false | false | self | 1 | null |
LLava working great on LLama.cpp | 36 | Llava is now built automatically when making llama.cpp. It works as advertised. Pretty cool! I can imagine what a boon this will be to the visually impaired once it's fully integrated. | 2023-10-15T01:51:50 | https://www.reddit.com/r/LocalLLaMA/comments/1784s83/llava_working_great_on_llamacpp/ | vamsammy | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 1784s83 | false | null | t3_1784s83 | /r/LocalLLaMA/comments/1784s83/llava_working_great_on_llamacpp/ | false | false | self | 36 | null |
Using Koboldcpp to run local models. I'm getting garbage responses when running from a private browser window or from a portable browser. I switch to a standard browser and I get the expected responses. | 3 | I'm trying to chat with it and it just wants to talk about html coding. I feel like it's receiving some html code with the input when running under these circumstances. I couldn't find any information from a Google search. Is this expected behavior? | 2023-10-15T00:58:00 | https://www.reddit.com/r/LocalLLaMA/comments/1783ri9/using_koboldcpp_to_run_local_models_im_getting/ | nexusjuan | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 1783ri9 | false | null | t3_1783ri9 | /r/LocalLLaMA/comments/1783ri9/using_koboldcpp_to_run_local_models_im_getting/ | false | false | self | 3 | null |
Introducing MiniSearch - A minimalist search engine with integrated browser-based AI | 1 | [removed] | 2023-10-15T00:49:50 | https://www.reddit.com/r/LocalLLaMA/comments/1783m1z/introducing_minisearch_a_minimalist_search_engine/ | Felladrin | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 1783m1z | false | null | t3_1783m1z | /r/LocalLLaMA/comments/1783m1z/introducing_minisearch_a_minimalist_search_engine/ | false | false | self | 1 | {'enabled': False, 'images': [{'id': 'JIKvAy3erMvKYGuOFYRZZy4vVxE1MwbSKKzMTe-jySc', 'resolutions': [{'height': 54, 'url': 'https://external-preview.redd.it/XpUrIzKzLQn-utcJ36Sa94KoREJNO4rs1iYV9RZyRgE.jpg?width=108&crop=smart&auto=webp&s=d6d61bdd9851ab89aa73af3b1413861fcab5bb62', 'width': 108}, {'height': 108, 'url': 'h... |
Is lowering quality of the model worth it, if the model is bigger? | 25 | Lets pretend there is two Wildcard models, and there is two versions, 7B and 13B.
What is a difference between Wildcard-7B-Q8 and Wildcard-13B-Q2?
My computer fits 7B confidently and 13B slowly.
I like the greater quality of 13B but not the slowness of it.
I noticed that difference of speed between Q8 and Q2 is gre... | 2023-10-15T00:10:28 | https://www.reddit.com/r/LocalLLaMA/comments/1782ui1/is_lowering_quality_of_the_model_worth_it_if_the/ | AdExcellent7516 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 1782ui1 | false | null | t3_1782ui1 | /r/LocalLLaMA/comments/1782ui1/is_lowering_quality_of_the_model_worth_it_if_the/ | false | false | self | 25 | null |
Running theBloke's dolphin-2.1-mistral-7B-AWQ on gtx 1060 card? | 1 | [removed] | 2023-10-14T23:57:43 | https://www.reddit.com/r/LocalLLaMA/comments/1782l5u/running_theblokes_dolphin21mistral7bawq_on_gtx/ | blacktie_redstripes | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 1782l5u | false | null | t3_1782l5u | /r/LocalLLaMA/comments/1782l5u/running_theblokes_dolphin21mistral7bawq_on_gtx/ | false | false | self | 1 | null |
2 RTX 3060 or a 4070 | 6 | Hey guys, I am currently upgrading my PC(technically a complete overhaul) to be able to fine tune LLM (LLaMA 2) and I need help deciding if I should get 2 \* RTX 3060 12gb (24 GB in total) or RTX 4070 16 GB . I do want to explore fine tuning various models and experiment with 13B models in mean time but my main focu... | 2023-10-14T23:46:11 | https://www.reddit.com/r/LocalLLaMA/comments/1782cyd/2_rtx_3060_or_a_4070/ | vaishakgkumar | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 1782cyd | false | null | t3_1782cyd | /r/LocalLLaMA/comments/1782cyd/2_rtx_3060_or_a_4070/ | false | false | self | 6 | null |
Are there any guides to using a local llm with Autogen or Chatdev? | 12 | Litellm says they can do it, and I'm reasonably sure they can, but I'm also completely and utterly lost. I've read the documentation three times now, and I still have no clue what to do. (any time I ask them for help they just send me a link to the documentation for it)
There's nothing I've found on YouTube or Google... | 2023-10-14T22:41:04 | https://www.reddit.com/r/LocalLLaMA/comments/17811ai/are_there_any_guides_to_using_a_local_llm_with/ | SendMePicsOfCat | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 17811ai | false | null | t3_17811ai | /r/LocalLLaMA/comments/17811ai/are_there_any_guides_to_using_a_local_llm_with/ | false | false | self | 12 | null |
Heads up on 3080 series and A6800 48GB (specifically used ones) Cracked Vapor Champers | 14 | 2023-10-14T21:57:52 | https://www.tomshardware.com/news/some-rtx-3080-rtx-a6000-gpus-are-prone-to-vapor-chamber-cracks-report | Aroochacha | tomshardware.com | 1970-01-01T00:00:00 | 0 | {} | 178063x | false | null | t3_178063x | /r/LocalLLaMA/comments/178063x/heads_up_on_3080_series_and_a6800_48gb/ | false | false | 14 | {'enabled': False, 'images': [{'id': 'IE539FPEP6zEbAl-KLIBuW1fLY-ZCZfaWJl8t82ZrGc', 'resolutions': [{'height': 60, 'url': 'https://external-preview.redd.it/dGTloRh3OMs_faCoJJOLyM7YNyTEsiunG7k1lwXNEBQ.jpg?width=108&crop=smart&auto=webp&s=bfb8e31a9a612e9472f9e72617677b7f7942c9d8', 'width': 108}, {'height': 121, 'url': 'h... |
Subsets and Splits
No community queries yet
The top public SQL queries from the community will appear here once available.