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 ⌀ |
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
Paper with dataset: Let’s Verify Step by Step | 30 | 2023-05-31T23:31:46 | https://twitter.com/_akhaliq/status/1663981726647894027 | ninjasaid13 | twitter.com | 1970-01-01T00:00:00 | 0 | {} | 13x1tb3 | false | {'oembed': {'author_name': 'AK', 'author_url': 'https://twitter.com/_akhaliq', 'cache_age': 3153600000, 'height': None, 'html': '<blockquote class="twitter-video"><p lang="en" dir="ltr">Open AI releases paper + dataset<br><br>Let’s Verify Step by Step<br><br>trained a model to achieve a new state-of-the-art in mathemat... | t3_13x1tb3 | /r/LocalLLaMA/comments/13x1tb3/paper_with_dataset_lets_verify_step_by_step/ | false | false | 30 | {'enabled': False, 'images': [{'id': 'UO2NDUz6VO_0ZzZlnukTQKJ0IlrpPsKILmmg8vffv5Y', 'resolutions': [{'height': 94, 'url': 'https://external-preview.redd.it/S7BzeQ19Nj-B80F4tmJwbyVZhd4bccgsjFmyFQQjJsc.jpg?width=108&crop=smart&auto=webp&s=bdb74b9e9da16db7e8083a76e3b1daafc68de97e', 'width': 108}], 'source': {'height': 123... | ||
Gozfarb shareGPT dataset? | 3 | Is there a copy of the HF Gozfarb shareGPT dataset available anywhere? A lot of important fine-tuning repositories rely on it, and I wanted to try fine-tuning it myself. It looks like the whole account is gone.
​
Thank you! | 2023-05-31T22:38:29 | https://www.reddit.com/r/LocalLLaMA/comments/13x0ht9/gozfarb_sharegpt_dataset/ | ProfessionalHand9945 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 13x0ht9 | false | null | t3_13x0ht9 | /r/LocalLLaMA/comments/13x0ht9/gozfarb_sharegpt_dataset/ | false | false | self | 3 | null |
CUDA out of memory error | 0 | [removed] | 2023-05-31T21:33:06 | https://www.reddit.com/r/LocalLLaMA/comments/13wysff/cuda_out_of_memory_error/ | franco84732 | self.LocalLLaMA | 2023-05-31T21:40:40 | 0 | {} | 13wysff | false | null | t3_13wysff | /r/LocalLLaMA/comments/13wysff/cuda_out_of_memory_error/ | false | false | default | 0 | null |
Hi, just a question on resizable bar... | 1 | [removed] | 2023-05-31T21:06:36 | https://www.reddit.com/r/LocalLLaMA/comments/13wy2p9/hi_just_a_question_on_resizable_bar/ | Ferrero__64 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 13wy2p9 | false | null | t3_13wy2p9 | /r/LocalLLaMA/comments/13wy2p9/hi_just_a_question_on_resizable_bar/ | false | false | default | 1 | null |
How to load guanaco-33b on both cpu and gpu so it doesn't give me OOM error ? | 1 | [removed] | 2023-05-31T20:52:43 | https://www.reddit.com/r/LocalLLaMA/comments/13wxp75/how_to_load_guanaco33b_on_both_cpu_and_gpu_so_it/ | [deleted] | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 13wxp75 | false | null | t3_13wxp75 | /r/LocalLLaMA/comments/13wxp75/how_to_load_guanaco33b_on_both_cpu_and_gpu_so_it/ | false | false | default | 1 | null |
Meta experiments with quantization aware training for LLMs, allowing for 4-bit quantization better than GPTQ and with reduced memory requirements. | 90 | Paper: [https://arxiv.org/abs/2305.17888](https://arxiv.org/abs/2305.17888)
Some excerpts:
>As a result, we are able to distill the 7B, 13B and 30B LLaMA models with weights and KV cache quantized down to 4-bits. In this regard, our approach exhibits significant enhancements in quality compared to post-training quant... | 2023-05-31T20:31:01 | https://www.reddit.com/r/LocalLLaMA/comments/13wx4q0/meta_experiments_with_quantization_aware_training/ | FrequentVariety4414 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 13wx4q0 | false | null | t3_13wx4q0 | /r/LocalLLaMA/comments/13wx4q0/meta_experiments_with_quantization_aware_training/ | false | false | 90 | {'enabled': False, 'images': [{'id': 'q3evP6JeDpAC2MdSQHWYxnCYTqbJkElIQsLFqVSdkss', 'resolutions': [{'height': 63, 'url': 'https://external-preview.redd.it/0HhwdU6MKIAKjL9Y8-B_iH374a3NiPTy0ib8lmloRzA.jpg?width=108&crop=smart&auto=webp&s=2711d572cfc6c713893cf24e8c4a7344d5ad8a4c', 'width': 108}, {'height': 126, 'url': 'h... | |
Thoughts on llama.cpp CPU usage? | 15 | 2023-05-31T20:26:55 | involviert | i.redd.it | 1970-01-01T00:00:00 | 0 | {} | 13wx0ws | false | null | t3_13wx0ws | /r/LocalLLaMA/comments/13wx0ws/thoughts_on_llamacpp_cpu_usage/ | false | false | 15 | {'enabled': True, 'images': [{'id': 's6focp9-t17jTPqhwUgPd8W3HydNpv65QyL2bHT0kcI', 'resolutions': [{'height': 35, 'url': 'https://preview.redd.it/t40qqse7o93b1.png?width=108&crop=smart&auto=webp&s=4ba792ad022ef437a35555fc5a69b681c08e4269', 'width': 108}, {'height': 71, 'url': 'https://preview.redd.it/t40qqse7o93b1.png?... | |||
best LLM my computer can handle? | 1 | [removed] | 2023-05-31T20:11:17 | [deleted] | 1970-01-01T00:00:00 | 0 | {} | 13wwml4 | false | null | t3_13wwml4 | /r/LocalLLaMA/comments/13wwml4/best_llm_my_computer_can_handle/ | false | false | default | 1 | null | ||
Comparing the Applications of Uncensored LLM Models to Public Models | 0 | [removed] | 2023-05-31T20:00:08 | [deleted] | 1970-01-01T00:00:00 | 0 | {} | 13wwc4h | false | null | t3_13wwc4h | /r/LocalLLaMA/comments/13wwc4h/comparing_the_applications_of_uncensored_llm/ | false | false | default | 0 | null | ||
OpenLlama finetuning and inference on intel dgpus | 2 | [removed] | 2023-05-31T19:35:49 | https://www.reddit.com/r/LocalLLaMA/comments/13wvpxc/openllama_finetuning_and_inference_on_intel_dgpus/ | unrahul | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 13wvpxc | false | null | t3_13wvpxc | /r/LocalLLaMA/comments/13wvpxc/openllama_finetuning_and_inference_on_intel_dgpus/ | false | false | default | 2 | null |
LLM Score v2 - Modern Models Tested by Human | 77 | Hey folks!
I'd like to share some numbers of **Gotzmann LLM Score** after two-week-long marathon testing all popular GGML models available here, including fresh hot **Hippogriff** and **Samantha** :)
The V2 questions were fixed for better and there finally good scores for those who'd like to use instruct models for r... | 2023-05-31T19:22:07 | https://www.reddit.com/r/LocalLLaMA/comments/13wvd0j/llm_score_v2_modern_models_tested_by_human/ | Gatzuma | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 13wvd0j | false | null | t3_13wvd0j | /r/LocalLLaMA/comments/13wvd0j/llm_score_v2_modern_models_tested_by_human/ | false | false | 77 | {'enabled': False, 'images': [{'id': 'XU0ZoS-2FKOHVF5eYKmADD890q6sOEOpCLirBhmc-mM', 'resolutions': [{'height': 56, 'url': 'https://external-preview.redd.it/n4gC1GYp19UK7iBIoabYr-WOB2v1WjVOF_nHciFemFY.jpg?width=108&crop=smart&auto=webp&s=d35b0af110726adf73a8a8a1430c43e3a20e9600', 'width': 108}, {'height': 113, 'url': 'h... | |
Getting Falcon 40B to work? | 12 | Has anyone here actually gotten Falcon 40B to work?
I've tried running it in Oobabooga; I get errors.
I've tried running the example code from the Falcon 40B repo; it doesn't produce any output either.
Does anyone at all have a working HOWTO for running Falcon 40B, ideally in Oobabooga? | 2023-05-31T19:01:17 | https://www.reddit.com/r/LocalLLaMA/comments/13wutj4/getting_falcon_40b_to_work/ | AlpsAficionado | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 13wutj4 | false | null | t3_13wutj4 | /r/LocalLLaMA/comments/13wutj4/getting_falcon_40b_to_work/ | false | false | self | 12 | null |
How should I choose between 4/8-bit model? | 1 | [removed] | 2023-05-31T18:40:57 | [deleted] | 1970-01-01T00:00:00 | 0 | {} | 13wuazp | false | null | t3_13wuazp | /r/LocalLLaMA/comments/13wuazp/how_should_i_choose_between_48bit_model/ | false | false | default | 1 | null | ||
hippogriff-30b King of good roleplay for me - Listens to "Tool" | 3 | [removed] | 2023-05-31T18:23:26 | [deleted] | 1970-01-01T00:00:00 | 0 | {} | 13wtv8z | false | null | t3_13wtv8z | /r/LocalLLaMA/comments/13wtv8z/hippogriff30b_king_of_good_roleplay_for_me/ | false | false | default | 3 | null | ||
Can't load a 30B GPTQ model on 20Gb of VRAM (split on two GPUs) | 7 | Hey there!
I'm new to this so I'm quite lost on how I could run a 30B model.
-
I got an RTX4070 today with 12Gb of VRAM and kept my old donkey the GTX1070 with its 8Gb. I also have 48Gb of RAM.
Now I've read that 30B models could load with 20Gb of VRAM but with the oobabooga UI I get this message :
RuntimeEr... | 2023-05-31T18:18:34 | https://www.reddit.com/r/LocalLLaMA/comments/13wtqx2/cant_load_a_30b_gptq_model_on_20gb_of_vram_split/ | Extraltodeus | self.LocalLLaMA | 2023-06-01T00:37:41 | 0 | {} | 13wtqx2 | false | null | t3_13wtqx2 | /r/LocalLLaMA/comments/13wtqx2/cant_load_a_30b_gptq_model_on_20gb_of_vram_split/ | false | false | self | 7 | {'enabled': False, 'images': [{'id': 'FMRmpeVBrEzhPPzjaS62Anb7KWA2xvPB_u3njHDRojg', 'resolutions': [{'height': 54, 'url': 'https://external-preview.redd.it/7KLmwRanGFDIoac5i936S1SBBwuxKfYQUDFDSpDrpns.jpg?width=108&crop=smart&auto=webp&s=218ff1c36305c08dadeb33b5ef349b0d4bfcb493', 'width': 108}, {'height': 108, 'url': 'h... |
LLM-As-Chatbot: Local, Open Source Instruction Following Models | 5 | From the [github repo](https://github.com/deep-diver/LLM-As-Chatbot):
>The purpose of this repository is to let people to use lots of open sourced instruction-following fine-tuned LLM models as a Chatbot service.
LLM-As-Chatbot is a local service for using instruction-tuned models. I'm excited to see what this enable... | 2023-05-31T18:18:00 | https://www.reddit.com/r/LocalLLaMA/comments/13wtqg9/llmaschatbot_local_open_source_instruction/ | triptoplane | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 13wtqg9 | false | null | t3_13wtqg9 | /r/LocalLLaMA/comments/13wtqg9/llmaschatbot_local_open_source_instruction/ | false | false | self | 5 | {'enabled': False, 'images': [{'id': 'h9GWZbwbHZ7OipB6De1T-nY-AcxsSqnSHcP52T7NZUM', 'resolutions': [{'height': 54, 'url': 'https://external-preview.redd.it/s_qIHTp2VU-Hnu8ZPCYIid51JnLH_bK8FxfZHdAhKe0.jpg?width=108&crop=smart&auto=webp&s=dac85da949c29972840e257ab243e96c9b02b3ec', 'width': 108}, {'height': 108, 'url': 'h... |
Local Large Language Models – beginners guide | 1 | 2023-05-31T18:03:15 | https://int8.io/local-large-language-models-beginners-guide/ | zibenmoka | int8.io | 1970-01-01T00:00:00 | 0 | {} | 13wtdhs | false | null | t3_13wtdhs | /r/LocalLLaMA/comments/13wtdhs/local_large_language_models_beginners_guide/ | false | false | default | 1 | null | |
Persistent cloud computing setup to run different LLM models. | 4 | Hi All,
in my limited free time, i experiment a bit with self hosted large language models just to try to keep up with what is possible. With the current speed of development, i am having a hard time to keep up. I guess that i am not alone with this. :-)
Anyway, what i am actually interested in is if some of you ar... | 2023-05-31T17:42:13 | https://www.reddit.com/r/LocalLLaMA/comments/13wsufp/persistent_cloud_computing_setup_to_run_different/ | Xardas1987 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 13wsufp | false | null | t3_13wsufp | /r/LocalLLaMA/comments/13wsufp/persistent_cloud_computing_setup_to_run_different/ | false | false | self | 4 | null |
LlamaCPP and LangChain Agent Quality | 25 | I've tried many models ranging from 7B to 30B in `langchain` and found that none can perform tasks. ChatGPT seems to be the only zero shot agent capable of producing the correct `Action, Action Input, Observation` loop.
For the models I modified the prompts with the ones in oobabooga for instructions. So they are like... | 2023-05-31T17:26:24 | https://www.reddit.com/r/LocalLLaMA/comments/13wsg64/llamacpp_and_langchain_agent_quality/ | IWantToBeAWebDev | self.LocalLLaMA | 2023-05-31T17:38:54 | 0 | {} | 13wsg64 | false | null | t3_13wsg64 | /r/LocalLLaMA/comments/13wsg64/llamacpp_and_langchain_agent_quality/ | false | false | self | 25 | null |
Completely lost regarding training LLaMA model | 9 | Hi, I need help training a LLaMA-model. I'm a bit lost and have no idea where to even begin.
I want to train a 7B-model on my own text. Preferably the openLLaMA-7B one as that can be used commercially. I have structured my dataset like this:
>Title of the subject
>
>Textblock
I want my model not to be a traditio... | 2023-05-31T17:12:59 | https://www.reddit.com/r/LocalLLaMA/comments/13ws492/completely_lost_regarding_training_llama_model/ | Xeruthos | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 13ws492 | false | null | t3_13ws492 | /r/LocalLLaMA/comments/13ws492/completely_lost_regarding_training_llama_model/ | false | false | self | 9 | null |
How much of an upgrade for 30b models would downgrading from a 3060TI 8GB VRAM to a 3060 12GB VRAM be? | 3 | [deleted] | 2023-05-31T16:55:30 | [deleted] | 1970-01-01T00:00:00 | 0 | {} | 13wrn8m | false | null | t3_13wrn8m | /r/LocalLLaMA/comments/13wrn8m/how_much_of_an_upgrade_for_30b_models_would/ | false | false | default | 3 | null | ||
Inspired by a recent post on this r/ I decided to play with parameters to get weird results... I think this is success (model: guanaco-13B-GGML 5_0) | 18 | 2023-05-31T16:51:02 | https://www.reddit.com/gallery/13wrj16 | Famberlight | reddit.com | 1970-01-01T00:00:00 | 0 | {} | 13wrj16 | false | null | t3_13wrj16 | /r/LocalLLaMA/comments/13wrj16/inspired_by_a_recent_post_on_this_r_i_decided_to/ | false | false | 18 | null | ||
Online Services to run LLMs? | 1 | [removed] | 2023-05-31T16:49:44 | https://www.reddit.com/r/LocalLLaMA/comments/13wrhrn/online_services_to_run_llms/ | pelatho | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 13wrhrn | false | null | t3_13wrhrn | /r/LocalLLaMA/comments/13wrhrn/online_services_to_run_llms/ | false | false | default | 1 | null |
Any non-LLama models under 20B (commercially licensable) that are not really bad? | 2 | [removed] | 2023-05-31T16:42:03 | [deleted] | 1970-01-01T00:00:00 | 0 | {} | 13wragb | false | null | t3_13wragb | /r/LocalLLaMA/comments/13wragb/any_nonllama_models_under_20b_commercially/ | false | false | default | 2 | null | ||
Integrating LLMs into existing RPG games | 20 | AFAIK, Infinite Engine/Fallout/Daggerfal were completely reverse engineered, so it should be just a matter of processing the hardcoded character dialogues with LLM to produce a character sheet, and then just use it to generate dynamic dialogue coupled with action tokens. It is also possible to make LLM act as a dungeon... | 2023-05-31T15:29:50 | https://www.reddit.com/r/LocalLLaMA/comments/13wpd7w/integrating_llms_into_existing_rpg_games/ | NancyAurum | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 13wpd7w | false | null | t3_13wpd7w | /r/LocalLLaMA/comments/13wpd7w/integrating_llms_into_existing_rpg_games/ | false | false | self | 20 | null |
Guanaco 33B coding | 27 | I recently tested Guanaco 33B with internet access (EdgeGPT, settings: 'always search' checked) and I am surprised with the results for code generation.
I compared code generation with ChatGPT(not paid version), Bing, Phind.com on same prompts and on all it generates better coding.
I changed the instruction templat... | 2023-05-31T15:27:36 | https://www.reddit.com/r/LocalLLaMA/comments/13wpb6q/guanaco_33b_coding/ | kexibis | self.LocalLLaMA | 2023-05-31T15:49:03 | 0 | {} | 13wpb6q | false | null | t3_13wpb6q | /r/LocalLLaMA/comments/13wpb6q/guanaco_33b_coding/ | false | false | self | 27 | null |
Combining LLMs with Instant Generation Descriptive GUIs for Interactive Text Input | 5 |
I wanted to discuss an interesting concept that I've been contemplating recently: the combination of Large Language Models (LLMs) like OpenAI's GPT series with Instant Generation Descriptive Graphical User Interfaces (GUIs) to facilitate more interactive text input.
We're all familiar with traditional text input me... | 2023-05-31T15:23:06 | https://www.reddit.com/r/LocalLLaMA/comments/13wp727/combining_llms_with_instant_generation/ | Periplokos | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 13wp727 | false | null | t3_13wp727 | /r/LocalLLaMA/comments/13wp727/combining_llms_with_instant_generation/ | false | false | self | 5 | null |
Dataset prep/cleaning | 3 | I’m seeing pretty decent results training LoRA’s over the documentation and user manuals of a complicated software system. I manually crafted and cleaned this dataset by hand (a real pita) then trained via raw text option in webui.
Now I’d like to do the same for the source code just to see what the LLM learns. I sup... | 2023-05-31T15:21:38 | https://www.reddit.com/r/LocalLLaMA/comments/13wp5qc/dataset_prepcleaning/ | ki7a | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 13wp5qc | false | null | t3_13wp5qc | /r/LocalLLaMA/comments/13wp5qc/dataset_prepcleaning/ | false | false | self | 3 | null |
I think custom datasets and LoRA training will define the future of LLM competency | 70 | With things like [Landmark Attention,](https://github.com/epfml/landmark-attention) we could have near-infinite context without running into memory issues. Landmark Attention breaks the context into 50 token chunks and makes a new token to represent that chunk, essentially compressing the context 50x. It's able to pull... | 2023-05-31T15:18:28 | https://www.reddit.com/r/LocalLLaMA/comments/13wp2ni/i_think_custom_datasets_and_lora_training_will/ | NeverEndingToast | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 13wp2ni | false | null | t3_13wp2ni | /r/LocalLLaMA/comments/13wp2ni/i_think_custom_datasets_and_lora_training_will/ | false | false | self | 70 | {'enabled': False, 'images': [{'id': '9AlTfytK8JKMoaR1DoQd2gvztH9ezp_V0W7Po5AIfqU', 'resolutions': [{'height': 54, 'url': 'https://external-preview.redd.it/J6Q841wYA31K6gamo0qaVz9gbd_3SeNafLfohDlcFN0.jpg?width=108&crop=smart&auto=webp&s=2f1cef133667bae4b4213dd00b1cd8e2a8cbd0ae', 'width': 108}, {'height': 108, 'url': 'h... |
Falcon40B has waived royalties on its use for commercial and research purposes | 354 | 2023-05-31T14:51:50 | https://twitter.com/TIIuae/status/1663911042559234051?s=20 | hackerllama | twitter.com | 1970-01-01T00:00:00 | 0 | {} | 13wodey | false | {'oembed': {'author_name': 'Technology Innovation Institute', 'author_url': 'https://twitter.com/TIIuae', 'cache_age': 3153600000, 'height': None, 'html': '<blockquote class="twitter-video"><p lang="en" dir="ltr">UAE's Falcon 40B,\xa0the world's top ranked open-source AI model from the Technology Innovation Ins... | t3_13wodey | /r/LocalLLaMA/comments/13wodey/falcon40b_has_waived_royalties_on_its_use_for/ | false | false | 354 | {'enabled': False, 'images': [{'id': 'T1VBjYNi-z2BPIjFQEgNPu8OUHu28n8ENpivlN_1Ivs', 'resolutions': [{'height': 108, 'url': 'https://external-preview.redd.it/637cUHKm0dDFQxduekMskbWVxA8bP7NayNfrwH5xi7I.jpg?width=108&crop=smart&auto=webp&s=2c8b1abff2faa322a50a8644d5e6ee1fb9aaa094', 'width': 108}], 'source': {'height': 14... | ||
Training a 13B LLaMA on information from documents. | 6 | Hello. I am running Meta’s 13B LLaMA in 4bit using ooba UI. I am mainly using the chat function, and was wondering if it is possible to train it on some documents that I have, so that it can help me and my colleagues troubleshoot system errors.
As a larger context, I have about 5 documents for a “system”. Those docume... | 2023-05-31T14:37:53 | https://www.reddit.com/r/LocalLLaMA/comments/13wo0ut/training_a_13b_llama_on_information_from_documents/ | reverrover16 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 13wo0ut | false | null | t3_13wo0ut | /r/LocalLLaMA/comments/13wo0ut/training_a_13b_llama_on_information_from_documents/ | false | false | self | 6 | null |
What’s the best local LLM for low to medium end machines? | 37 | I have a laptop with a 1650 ti, 16 gigs of RAM, and an i5-10th gen. I am looking for a good local LLM that I can use for coding, and just normal conversations. I want it to be able to run smooth enough on my computer but actually be good as well. I also would prefer if it had plugins that could read files. | 2023-05-31T14:30:54 | https://www.reddit.com/r/LocalLLaMA/comments/13wnuuo/whats_the_best_local_llm_for_low_to_medium_end/ | SimRacer101 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 13wnuuo | false | null | t3_13wnuuo | /r/LocalLLaMA/comments/13wnuuo/whats_the_best_local_llm_for_low_to_medium_end/ | false | false | self | 37 | null |
Would I be able to QLora finetune 65b models with 2 3090s and NVLink? | 6 | Basically the title. I wanted to know If I purchased a 3090 and NVLink if I would be able to finetune the 65b model. If I can't, I guess I would have to run it on huggingface | 2023-05-31T13:53:44 | https://www.reddit.com/r/LocalLLaMA/comments/13wmyb3/would_i_be_able_to_qlora_finetune_65b_models_with/ | MrBeforeMyTime | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 13wmyb3 | false | null | t3_13wmyb3 | /r/LocalLLaMA/comments/13wmyb3/would_i_be_able_to_qlora_finetune_65b_models_with/ | false | false | self | 6 | null |
Mixing 3090ti and p40 for gpu 65b | 4 | Hi all, I have a 3090ti, 3950x, and 64 gb of vram. Obviously I'm only able to run 65b models on the cpu/ram (I can't compile the latest llama.ccp to enable gpu offloading for ggml due to a weird but but that's unrelated to this post.)
I was wondering if adding a used tesla p40 and splitting the model across the vram u... | 2023-05-31T13:23:47 | https://www.reddit.com/r/LocalLLaMA/comments/13wm849/mixing_3090ti_and_p40_for_gpu_65b/ | TheSilentFire | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 13wm849 | false | null | t3_13wm849 | /r/LocalLLaMA/comments/13wm849/mixing_3090ti_and_p40_for_gpu_65b/ | false | false | self | 4 | null |
LLM for information extraction | 13 | Hi,
I'm trying to use the LLama family to extract information from unstructured text and to return it in JSON format. The tasks are e.g. to return the date a letter was written (the date is mentioned in the text). While ChatGPT answers the question immediately and correctly, all my Llama/vicuna/alpaca attempts fail (I... | 2023-05-31T13:15:34 | https://www.reddit.com/r/LocalLLaMA/comments/13wm0z6/llm_for_information_extraction/ | Bradymodion | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 13wm0z6 | false | null | t3_13wm0z6 | /r/LocalLLaMA/comments/13wm0z6/llm_for_information_extraction/ | false | false | self | 13 | null |
Help needed with installing quant_cuda for the WebUI | 1 | [removed] | 2023-05-31T12:53:56 | https://www.reddit.com/r/LocalLLaMA/comments/13wlhwo/help_needed_with_installing_quant_cuda_for_the/ | QUAZARD3141 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 13wlhwo | false | null | t3_13wlhwo | /r/LocalLLaMA/comments/13wlhwo/help_needed_with_installing_quant_cuda_for_the/ | false | false | default | 1 | null |
Can finetuning an LLM add new knowledge or just teach it response patterns? | 13 | Hi all, I have a question regarding fine-tuning of LLMs. I wanted to add some new content/knowledge to an LLM by fine-tuning it, but through some searches, I found some mentions that fine-tuning an LLM does not give it new knowledge but trains it for a specific response pattern ([Link](https://community.openai.com/t/fi... | 2023-05-31T10:41:58 | https://www.reddit.com/r/LocalLLaMA/comments/13wimi0/can_finetuning_an_llm_add_new_knowledge_or_just/ | bafil596 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 13wimi0 | false | null | t3_13wimi0 | /r/LocalLLaMA/comments/13wimi0/can_finetuning_an_llm_add_new_knowledge_or_just/ | false | false | self | 13 | {'enabled': False, 'images': [{'id': 'BxNvUeMFd6obe78ihkAJrzGJFpOkQpmEJ7BbVi_larY', 'resolutions': [{'height': 60, 'url': 'https://external-preview.redd.it/2J07IKccOEu528Dr2WlyssuQYfjax6yT553dEfNzT00.jpg?width=108&crop=smart&auto=webp&s=93162f369263d5c2a9e1768260a77dbe05103f3e', 'width': 108}, {'height': 121, 'url': 'h... |
OpenAccess AI Collective's Hippogriff 30B Chat | 87 | Another great new model from [OpenAccess AI Collective](https://huggingface.co/openaccess-ai-collective) and /u/winglian
# Hippogriff 30B Chat
Hippogriff 30B Chat is an experiment that builds on Manticore with new datasets, while removing a few more instruction and chat datasets. It also includes a de-duped subset of... | 2023-05-31T10:36:14 | https://www.reddit.com/r/LocalLLaMA/comments/13wiin0/openaccess_ai_collectives_hippogriff_30b_chat/ | The-Bloke | self.LocalLLaMA | 2023-05-31T12:39:44 | 0 | {} | 13wiin0 | false | null | t3_13wiin0 | /r/LocalLLaMA/comments/13wiin0/openaccess_ai_collectives_hippogriff_30b_chat/ | false | false | self | 87 | {'enabled': False, 'images': [{'id': '6atkc6f2ftM9kyUXaG-h4RD1n166r6NsA0DiHOpeJaY', 'resolutions': [{'height': 58, 'url': 'https://external-preview.redd.it/tjMJ3TzMxZjUJYie29xcIAkyylOATgiaCwaQO2duXLU.jpg?width=108&crop=smart&auto=webp&s=86584819f161b7d61d55d078b6fd3313c0ed67df', 'width': 108}, {'height': 116, 'url': 'h... |
New model: RWKV-4-Raven-7B-v12-Eng49%-Chn49%-Jpn1%-Other1%-20230530-ctx8192.pth | 34 | 2023-05-31T10:29:55 | https://huggingface.co/BlinkDL/rwkv-4-raven/blob/main/RWKV-4-Raven-7B-v12-Eng49%25-Chn49%25-Jpn1%25-Other1%25-20230530-ctx8192.pth | Balance- | huggingface.co | 1970-01-01T00:00:00 | 0 | {} | 13wie45 | false | null | t3_13wie45 | /r/LocalLLaMA/comments/13wie45/new_model/ | false | false | 34 | {'enabled': False, 'images': [{'id': '3HjrW-l8WZHB406ZEXOb2zG68k9U687DZ8bOgw_-CoQ', 'resolutions': [{'height': 58, 'url': 'https://external-preview.redd.it/TCLHAYQVnNMv1bzAnQTSAHuMnq75fQsEzsLQeAC45_8.jpg?width=108&crop=smart&auto=webp&s=d93692813a3b9f071865edd0279f9dec8bb3f1f1', 'width': 108}, {'height': 116, 'url': 'h... | ||
What is the objective for the supervised fine-tuning stage of instruction-following models? | 1 | 2023-05-31T10:06:24 | https://www.reddit.com/r/deeplearning/comments/13whxjk/what_is_the_objective_for_the_supervised/ | BlueHemp | reddit.com | 1970-01-01T00:00:00 | 0 | {} | 13whzaq | false | null | t3_13whzaq | /r/LocalLLaMA/comments/13whzaq/what_is_the_objective_for_the_supervised/ | false | false | default | 1 | null | |
Help for a complete noob | 1 | [removed] | 2023-05-31T10:03:56 | https://www.reddit.com/r/LocalLLaMA/comments/13whxqg/help_for_a_complete_noob/ | Leavetheporkbehind | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 13whxqg | false | null | t3_13whxqg | /r/LocalLLaMA/comments/13whxqg/help_for_a_complete_noob/ | false | false | default | 1 | null |
Lora batch job merging thought | 2 | Memory and context are the stand out limitations for me and LLMs. Just had a thought and was wondering if anyone is aware of anyone trying this approach. Run a local model for an internal use at a company and log all chat dialog, then at the end of the day take that log and use it to train a Lora in an overnight batch... | 2023-05-31T09:36:47 | https://www.reddit.com/r/LocalLLaMA/comments/13whgzn/lora_batch_job_merging_thought/ | TaiMaiShu-71 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 13whgzn | false | null | t3_13whgzn | /r/LocalLLaMA/comments/13whgzn/lora_batch_job_merging_thought/ | false | false | self | 2 | null |
Method to block possible internet traffic from LLaMA on MacOS | 0 | **So in an abundance of paranoid caution I wanted to really make sure that my Vicuna/textgenerationwebui setup could not access the internet, as I really don't want confidential material uploaded.**
**I did the following, in case it's useful to anyone else OR if I've been stupid somehow and it's not actually working ... | 2023-05-31T09:13:50 | https://www.reddit.com/r/LocalLLaMA/comments/13wh2yu/method_to_block_possible_internet_traffic_from/ | spoilingba | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 13wh2yu | false | null | t3_13wh2yu | /r/LocalLLaMA/comments/13wh2yu/method_to_block_possible_internet_traffic_from/ | false | false | self | 0 | null |
OpenAssistant's RLHF Models | 13 | OpenAssistant releases RLHF tuned version. Curious to see how this compares to the StableVicuna.
[https://huggingface.co/OpenAssistant/oasst-rlhf-2-llama-30b-7k-steps-xor](https://huggingface.co/OpenAssistant/oasst-rlhf-2-llama-30b-7k-steps-xor)
Tagging u/The-Bloke in the hopes of getting quantised GGML weights :) Th... | 2023-05-31T07:46:23 | https://www.reddit.com/r/LocalLLaMA/comments/13wfn56/openassistants_rlhf_models/ | sneruz | self.LocalLLaMA | 2023-05-31T12:08:22 | 0 | {} | 13wfn56 | false | null | t3_13wfn56 | /r/LocalLLaMA/comments/13wfn56/openassistants_rlhf_models/ | false | false | self | 13 | {'enabled': False, 'images': [{'id': '578mpVwWF25m5vOABma33i38LCAywh4p3qragThHgh8', 'resolutions': [{'height': 58, 'url': 'https://external-preview.redd.it/Q4diQydPsktvjujZNEiPMD2xvDQv0tr2KPVRSPaIZxg.jpg?width=108&crop=smart&auto=webp&s=b24867e2302ce1e54245f8ce49abf40ce21a28b3', 'width': 108}, {'height': 116, 'url': 'h... |
AutoCompleter: auto complete any text inside any application | 1 | [removed] | 2023-05-31T07:17:27 | https://www.reddit.com/r/LocalLLaMA/comments/13wf6g8/autocompleter_auto_complete_any_text_inside_any/ | Kitchen-Monitor-6924 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 13wf6g8 | false | null | t3_13wf6g8 | /r/LocalLLaMA/comments/13wf6g8/autocompleter_auto_complete_any_text_inside_any/ | false | false | default | 1 | null |
AutoCompleter: Auto Complete anything using a ggml model | 1 | [removed] | 2023-05-31T05:58:15 | [deleted] | 1970-01-01T00:00:00 | 0 | {} | 13wdvnz | false | null | t3_13wdvnz | /r/LocalLLaMA/comments/13wdvnz/autocompleter_auto_complete_anything_using_a_ggml/ | false | false | default | 1 | null | ||
(Code Released) Landmark Attention: Random-Access Infinite Context Length for Transformers | 150 | Code for Landmark Attention is now released and it should be possible to finetune existing LLaMA models using this method.
[https://github.com/epfml/landmark-attention](https://github.com/epfml/landmark-attention)
More info
[https://www.reddit.com/r/MachineLearning/comments/13srbl7/landmark\_attention\_randomaccess... | 2023-05-31T03:35:17 | https://www.reddit.com/r/LocalLLaMA/comments/13wb59a/code_released_landmark_attention_randomaccess/ | IxinDow | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 13wb59a | false | null | t3_13wb59a | /r/LocalLLaMA/comments/13wb59a/code_released_landmark_attention_randomaccess/ | false | false | self | 150 | {'enabled': False, 'images': [{'id': '9AlTfytK8JKMoaR1DoQd2gvztH9ezp_V0W7Po5AIfqU', 'resolutions': [{'height': 54, 'url': 'https://external-preview.redd.it/J6Q841wYA31K6gamo0qaVz9gbd_3SeNafLfohDlcFN0.jpg?width=108&crop=smart&auto=webp&s=2f1cef133667bae4b4213dd00b1cd8e2a8cbd0ae', 'width': 108}, {'height': 108, 'url': 'h... |
Fine-Tuning Language Models with Just Forward Passes | 27 | [https://arxiv.org/abs/2305.17333](https://arxiv.org/abs/2305.17333)
TL;DR: MeZO allows for fine-tuning a model with the same amount of VRAM as needed for inference. Can be used for either a full fine tune or a LoRA. Potentially can be combined with other memory-efficient strategies, but they haven't tried it with qua... | 2023-05-31T03:22:24 | https://www.reddit.com/r/LocalLLaMA/comments/13wavpf/finetuning_language_models_with_just_forward/ | AutomataManifold | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 13wavpf | false | null | t3_13wavpf | /r/LocalLLaMA/comments/13wavpf/finetuning_language_models_with_just_forward/ | false | false | self | 27 | {'enabled': False, 'images': [{'id': 'q3evP6JeDpAC2MdSQHWYxnCYTqbJkElIQsLFqVSdkss', 'resolutions': [{'height': 63, 'url': 'https://external-preview.redd.it/0HhwdU6MKIAKjL9Y8-B_iH374a3NiPTy0ib8lmloRzA.jpg?width=108&crop=smart&auto=webp&s=2711d572cfc6c713893cf24e8c4a7344d5ad8a4c', 'width': 108}, {'height': 126, 'url': 'h... |
Where can I keep on top of LLM developments? | 27 | I'm currently attempting to broaden my knowledge of AI and ML, particularly in relation to large language models. My understanding so far is that a significant limitation of these models is their restricted context window, which appears to hinder their ability to maintain continuity of information and reason effectivel... | 2023-05-31T02:43:22 | https://www.reddit.com/r/LocalLLaMA/comments/13wa1of/where_can_i_keep_on_top_of_llm_developments/ | banderamobile | self.LocalLLaMA | 2023-05-31T03:48:38 | 0 | {} | 13wa1of | false | null | t3_13wa1of | /r/LocalLLaMA/comments/13wa1of/where_can_i_keep_on_top_of_llm_developments/ | false | false | self | 27 | null |
Chinese-Alpaca-Plus-13B-GPTQ | 4 | I'd like to share with you today the [**Chinese-Alpaca-Plus-13B-GPTQ**](https://huggingface.co/rabitt/Chinese-Alpaca-Plus-13B-GPTQ) model, which is the GPTQ format quantised 4bit models of [Yiming Cui's Chinese-LLaMA-Alpaca 13B](https://github.com/ymcui/Chinese-LLaMA-Alpaca) for GPU reference.
to use it in text-genera... | 2023-05-31T02:31:04 | https://www.reddit.com/r/LocalLLaMA/comments/13w9ry5/chinesealpacaplus13bgptq/ | ttimasdf | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 13w9ry5 | false | null | t3_13w9ry5 | /r/LocalLLaMA/comments/13w9ry5/chinesealpacaplus13bgptq/ | false | false | self | 4 | {'enabled': False, 'images': [{'id': 'X4rmX94b0pa0Swfzq-37wJrtt_jnnNUgkrwXRsN0lyI', 'resolutions': [{'height': 58, 'url': 'https://external-preview.redd.it/H6mkA79_5kvDe6H0yIuYLV5dss5HyIh8_LhVBcclszA.jpg?width=108&crop=smart&auto=webp&s=d0272c240e8ab71d826533a0c17f599316ef6214', 'width': 108}, {'height': 116, 'url': 'h... |
Using the right prompt format makes responses so much better | 74 | 2023-05-31T01:28:40 | https://www.reddit.com/gallery/13w8ecu | Creative-Rest-2112 | reddit.com | 1970-01-01T00:00:00 | 0 | {} | 13w8ecu | false | null | t3_13w8ecu | /r/LocalLLaMA/comments/13w8ecu/using_the_right_prompt_format_makes_responses_so/ | false | false | default | 74 | null | |
Using the right prompt format makes a huge difference | 1 | [removed] | 2023-05-31T01:03:32 | [deleted] | 1970-01-01T00:00:00 | 0 | {} | 13w7ukj | false | null | t3_13w7ukj | /r/LocalLLaMA/comments/13w7ukj/using_the_right_prompt_format_makes_a_huge/ | false | false | default | 1 | null | ||
Llama weight license- any updates from Meta? | 6 | Has anyone heard any updates if meta is considering changing the llama weights license? I am desperate for a commercial model that isn’t closedAI and I’m getting backed into a corner not being able to use llama commercially. I’ve been scouring twitter and other places but haven’t seen anything new for a few weeks. | 2023-05-30T23:48:23 | https://www.reddit.com/r/LocalLLaMA/comments/13w64t8/llama_weight_license_any_updates_from_meta/ | big_ol_tender | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 13w64t8 | false | null | t3_13w64t8 | /r/LocalLLaMA/comments/13w64t8/llama_weight_license_any_updates_from_meta/ | false | false | self | 6 | null |
Which uncensored model to use to remove calendar events from message text? | 1 | I need a model which can consistently remove any references to calendar events like Christmas, Halloween, Valentine’s Day, etc. as well as any reference to day or month like Sunday, Monday or February etc. I tried the 30B Wizard uncensored but it didn’t do a good job compared to GPT3.5. It kept the same message without... | 2023-05-30T23:44:11 | https://www.reddit.com/r/LocalLLaMA/comments/13w61b4/which_uncensored_model_to_use_to_remove_calendar/ | RepresentativeOdd276 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 13w61b4 | false | null | t3_13w61b4 | /r/LocalLLaMA/comments/13w61b4/which_uncensored_model_to_use_to_remove_calendar/ | false | false | self | 1 | null |
Increasing speed for webui/Wizard-Vicuna-13B with my Mac Pro M1 16gb setup? | 7 | Hey! So after a lot of time spent getting it to actually work, I've finally got my offline llama setup on a Macbook with an Apple M1 Pro (model number mk193b/a, 10 cores (8 performance 2 efficiency), 16 GB LPDDR5 RAM).
I'm definitely running ARM64 python also.
It's still running quite slowly even for simple questions... | 2023-05-30T23:05:16 | https://www.reddit.com/r/LocalLLaMA/comments/13w53k3/increasing_speed_for_webuiwizardvicuna13b_with_my/ | spoilingba | self.LocalLLaMA | 2023-05-31T08:43:28 | 0 | {} | 13w53k3 | false | null | t3_13w53k3 | /r/LocalLLaMA/comments/13w53k3/increasing_speed_for_webuiwizardvicuna13b_with_my/ | false | false | self | 7 | null |
Cheapest GPU VPS for 24/7 hosting | 4 | I found runpod.io a very interesting provider for cloud GPU with fair on-demand pricing, especially for training and testing. But for production deployment I am looking for a VPS that I can rent on monthly basis to run 24/7 and which is therefore cheaper (per month). Are there providers you can recommend? | 2023-05-30T22:15:43 | https://www.reddit.com/r/LocalLLaMA/comments/13w3w74/cheapest_gpu_vps_for_247_hosting/ | Koliham | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 13w3w74 | false | null | t3_13w3w74 | /r/LocalLLaMA/comments/13w3w74/cheapest_gpu_vps_for_247_hosting/ | false | false | self | 4 | null |
problem installing llama.cpp on a scientific linux cluster | 1 | [removed] | 2023-05-30T21:46:59 | https://www.reddit.com/r/LocalLLaMA/comments/13w35zr/problem_installing_llamacpp_on_a_scientific_linux/ | Bozo32 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 13w35zr | false | null | t3_13w35zr | /r/LocalLLaMA/comments/13w35zr/problem_installing_llamacpp_on_a_scientific_linux/ | false | false | default | 1 | null |
Link with js script | 1 | [removed] | 2023-05-30T21:46:37 | https://www.reddit.com/r/LocalLLaMA/comments/13w35o8/link_with_js_script/ | Interesting_Ad_1603 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 13w35o8 | false | null | t3_13w35o8 | /r/LocalLLaMA/comments/13w35o8/link_with_js_script/ | false | false | default | 1 | null |
GPU card suggestions | 4 | I'm new here and am completely lost when it comes to video cards. Unfortunately I'm not a gamer so I have no clue on them but I am interested in running these models. I would say I'm more of a hobbyist looking more likely at running smaller models with budget under $700.
Can someone recommend some video cards to buy?... | 2023-05-30T20:48:36 | https://www.reddit.com/r/LocalLLaMA/comments/13w1nxv/gpu_card_suggestions/ | ctbitcoin | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 13w1nxv | false | null | t3_13w1nxv | /r/LocalLLaMA/comments/13w1nxv/gpu_card_suggestions/ | false | false | self | 4 | null |
if the average human typing speed is around the 1 token/s mark, why it feel so slow to interact with LLMs running on cpu? | 25 | human beings fall between the 40 to 70 words per minute in typing benchmarks, which translates to roughly 1 token/s. Many people have shared their experience about running LLMs on cpu/ram with comparable response times, why do we consider such speed slow if it's kinda the same as chatting with other person? | 2023-05-30T20:11:58 | https://www.reddit.com/r/LocalLLaMA/comments/13w0qcp/if_the_average_human_typing_speed_is_around_the_1/ | Caffdy | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 13w0qcp | false | null | t3_13w0qcp | /r/LocalLLaMA/comments/13w0qcp/if_the_average_human_typing_speed_is_around_the_1/ | false | false | self | 25 | null |
Llama Chatbot for Telegram | 1 | [removed] | 2023-05-30T19:41:34 | https://github.com/aneeshjoy/llama-telegram-bot | [deleted] | github.com | 1970-01-01T00:00:00 | 0 | {} | 13vzxyg | false | null | t3_13vzxyg | /r/LocalLLaMA/comments/13vzxyg/llama_chatbot_for_telegram/ | false | false | default | 1 | null |
LLM Lobotomy - predictions? | 19 | I'm wondering if anyone has ever tried effectively giving an LLM a 'lobotomy' by gradually corrupting it's weights while using it?
Seems like an interesting thing to try. Firstly you'd run the original model, give it some prompts, record the outputs.
Then you'd randomly (or perhaps not randomly), change the values of... | 2023-05-30T17:51:20 | https://www.reddit.com/r/LocalLLaMA/comments/13vx1e5/llm_lobotomy_predictions/ | ozzeruk82 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 13vx1e5 | false | null | t3_13vx1e5 | /r/LocalLLaMA/comments/13vx1e5/llm_lobotomy_predictions/ | false | false | self | 19 | null |
AutoCompleter: Auto Complete anything using a ggml model | 1 | [removed] | 2023-05-30T17:48:30 | [deleted] | 1970-01-01T00:00:00 | 0 | {} | 13vwysi | false | null | t3_13vwysi | /r/LocalLLaMA/comments/13vwysi/autocompleter_auto_complete_anything_using_a_ggml/ | false | false | default | 1 | null | ||
Can you download your Huggingface chats? | 1 | [removed] | 2023-05-30T17:22:31 | https://www.reddit.com/r/LocalLLaMA/comments/13vwaud/can_you_download_your_huggingface_chats/ | spmmora | self.LocalLLaMA | 2023-06-02T11:33:21 | 0 | {} | 13vwaud | false | null | t3_13vwaud | /r/LocalLLaMA/comments/13vwaud/can_you_download_your_huggingface_chats/ | false | false | default | 1 | null |
Long load time using from_pretrained? | 2 | Loading a 6B model (gpt-j) onto GPU using from\_pretrained is taking over an hour. I have the model files cached and use\_local\_files set to True. Can't find anyone else with this issue. Here's the full call:
``AutoModelForCausalLM.from_pretrained(config.base_model_name_or_path,
... | 2023-05-30T17:13:28 | https://www.reddit.com/r/LocalLLaMA/comments/13vw2eh/long_load_time_using_from_pretrained/ | ThineGame | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 13vw2eh | false | null | t3_13vw2eh | /r/LocalLLaMA/comments/13vw2eh/long_load_time_using_from_pretrained/ | false | false | self | 2 | null |
temperature=1000.0 and top_p=0.1 is hilarious | 262 | I find this behavior surprising and enlightening. Having top\_p small enough keeps it mostly coherent while making it have a really difficult time speaking properly.
​
>I have 2 cows, and one of 'm died cuzz the farmer was mean and didn t let 'er drink any wate. I m so pist! But now i only haz the other, an i... | 2023-05-30T16:42:24 | https://www.reddit.com/r/LocalLLaMA/comments/13vv941/temperature10000_and_top_p01_is_hilarious/ | phree_radical | self.LocalLLaMA | 2023-05-30T16:46:11 | 1 | {'gid_2': 1} | 13vv941 | false | null | t3_13vv941 | /r/LocalLLaMA/comments/13vv941/temperature10000_and_top_p01_is_hilarious/ | false | false | self | 262 | null |
What runs ChatGPT? Inside Microsoft's AI supercomputer | 8 | What runs ChatGPT? Inside Microsoft's AI supercomputer: [https://youtu.be/Rk3nTUfRZmo](https://youtu.be/Rk3nTUfRZmo)
​
How much better is the 530B model, compared to 170B GPT3? | 2023-05-30T16:06:21 | https://www.reddit.com/r/LocalLLaMA/comments/13vubnr/what_runs_chatgpt_inside_microsofts_ai/ | NancyAurum | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 13vubnr | false | null | t3_13vubnr | /r/LocalLLaMA/comments/13vubnr/what_runs_chatgpt_inside_microsofts_ai/ | false | false | self | 8 | {'enabled': False, 'images': [{'id': 'qypuv7qgWWhlaEITLML1HTEM2xyJxc90FtPYgwoqn0s', 'resolutions': [{'height': 81, 'url': 'https://external-preview.redd.it/X6bFFFNabiMERs8LOF8geqm6C-5l3Qe8GJF335w_Skk.jpg?width=108&crop=smart&auto=webp&s=4e8ee2efc8ef386f46c637225f3618f16e5559fb', 'width': 108}, {'height': 162, 'url': 'h... |
Understanding frequency penalty, presence penalty, repetition penalty | 1 | [removed] | 2023-05-30T15:50:49 | [deleted] | 1970-01-01T00:00:00 | 0 | {} | 13vtx2j | false | null | t3_13vtx2j | /r/LocalLLaMA/comments/13vtx2j/understanding_frequency_penalty_presence_penalty/ | false | false | default | 1 | null | ||
ARKANE INDUSTRIES BASILISK FRAMEWORK | 0 | [removed] | 2023-05-30T13:24:32 | https://www.reddit.com/gallery/13vq96s | 0xPICNIK | reddit.com | 1970-01-01T00:00:00 | 0 | {} | 13vq96s | false | null | t3_13vq96s | /r/LocalLLaMA/comments/13vq96s/arkane_industries_basilisk_framework/ | false | false | default | 0 | null |
Any Local LLMs trained specifically to handle langchain? | 28 | It seems so obvious that I can't believe I don't see people dropping better versions of langchain agent trained models every day.
Local models aren't as strong in their general reasoning skills and in my attempts to use some of the more commonly well regarded local models like snoozy, they just can't handle the long ... | 2023-05-30T13:14:43 | https://www.reddit.com/r/LocalLLaMA/comments/13vq0uj/any_local_llms_trained_specifically_to_handle/ | gentlecucumber | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 13vq0uj | false | null | t3_13vq0uj | /r/LocalLLaMA/comments/13vq0uj/any_local_llms_trained_specifically_to_handle/ | false | false | self | 28 | null |
What can I do with 10GB of VRAM? | 3 | The idea of being able to run a LLM locally seems almost too good to be true so I'd like to try it out but as far as I know this requires a lot of RAM and VRAM. RAM isn't much of an issue as I have 32GB, but the 10GB of VRAM in my 3080 seems to be pushing the bare minimum of VRAM needed. I've thought of selling my 3080... | 2023-05-30T13:09:58 | https://www.reddit.com/r/LocalLLaMA/comments/13vpws1/what_can_i_do_with_10gb_of_vram/ | yungfishstick | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 13vpws1 | false | null | t3_13vpws1 | /r/LocalLLaMA/comments/13vpws1/what_can_i_do_with_10gb_of_vram/ | false | false | self | 3 | null |
Can we have tracker for every module release or announce here ? | 0 | [removed] | 2023-05-30T13:02:16 | [deleted] | 2023-06-26T12:15:29 | 0 | {} | 13vpq1u | false | null | t3_13vpq1u | /r/LocalLLaMA/comments/13vpq1u/can_we_have_tracker_for_every_module_release_or/ | false | false | default | 0 | null | ||
I want to translate natural language into commands for a robot, is a local LLaMa the place to start? | 14 | I want to speak to a robot using conversational speech and have that translated into actions. I like the idea of using a local AI to do that but I am wondering whether I need something as general as a LLaMa. I did see a [post](https://towardsdatascience.com/control-web-apps-via-natural-language-by-casting-speech-to-com... | 2023-05-30T12:46:13 | https://www.reddit.com/r/LocalLLaMA/comments/13vpc5k/i_want_to_translate_natural_language_into/ | iChinguChing | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 13vpc5k | false | null | t3_13vpc5k | /r/LocalLLaMA/comments/13vpc5k/i_want_to_translate_natural_language_into/ | false | false | self | 14 | {'enabled': False, 'images': [{'id': '07_FXwbB_oj_jdjPer6HfK8b5htgnPF9IhCYPQ5lO3c', 'resolutions': [{'height': 58, 'url': 'https://external-preview.redd.it/FsIIy_NoZkpDtaBSFsZf_sOUMa2g6UP3Iu5WkBxuEyk.jpg?width=108&crop=smart&auto=webp&s=36f4288e0cf6f39222172e2664bb38bebac39273', 'width': 108}, {'height': 116, 'url': 'h... |
[P] Fine-tuning LLaMA on TheVault by AI4Code | 10 | Hey everyone, I'm looking for suggestions and things to keep in mind while I do this.
I essentially want to fine-tune LLaMA on a dataset that's geared towards code generation. After a bit of research I found [TheVault](https://github.com/FSoft-AI4Code/TheVault) which seems good enough for the job (let me know if ther... | 2023-05-30T11:26:25 | https://www.reddit.com/r/LocalLLaMA/comments/13vnngo/p_finetuning_llama_on_thevault_by_ai4code/ | 04RR | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 13vnngo | false | null | t3_13vnngo | /r/LocalLLaMA/comments/13vnngo/p_finetuning_llama_on_thevault_by_ai4code/ | false | false | self | 10 | {'enabled': False, 'images': [{'id': 'LbDf92FJ1Tb60TgiYvBvIiV_muINezCCLBCEmDpJyvQ', 'resolutions': [{'height': 54, 'url': 'https://external-preview.redd.it/UEOqLWQy4uYWJrEV6fpFTetElJ5uGPNVRkUDKr3N1tI.jpg?width=108&crop=smart&auto=webp&s=a34b8e44de682c546f39684783cc7bd7a077a98e', 'width': 108}, {'height': 108, 'url': 'h... |
Can an RTX 3090 run a 30B 4bit model with webui and windows desktop at the same time? | 2 | [deleted] | 2023-05-30T10:10:52 | [deleted] | 1970-01-01T00:00:00 | 0 | {} | 13vm7tx | false | null | t3_13vm7tx | /r/LocalLLaMA/comments/13vm7tx/can_an_rtx_3090_run_a_30b_4bit_model_with_webui/ | false | false | default | 2 | null | ||
Looking for a pre trained food recognition model | 0 | [removed] | 2023-05-30T09:06:47 | https://www.reddit.com/r/LocalLLaMA/comments/13vl4ru/looking_for_a_pre_trained_food_recognition_model/ | Excellent-Pea3508 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 13vl4ru | false | null | t3_13vl4ru | /r/LocalLLaMA/comments/13vl4ru/looking_for_a_pre_trained_food_recognition_model/ | false | false | default | 0 | null |
samantha-falcon-7b | 43 | I've released a Samantha finetune of falcon-7b.
[**https://huggingface.co/ehartford/samantha-falcon-7b**](https://huggingface.co/ehartford/samantha-falcon-7b)
should make falcon more fun to talk to. 40b is coming too.
In case you haven't met her:
[https://erichartford.com/meet-samantha](https://erichartford.com/me... | 2023-05-30T06:50:12 | https://www.reddit.com/r/LocalLLaMA/comments/13vivij/samanthafalcon7b/ | faldore | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 13vivij | false | null | t3_13vivij | /r/LocalLLaMA/comments/13vivij/samanthafalcon7b/ | false | false | self | 43 | {'enabled': False, 'images': [{'id': 'EbCiWIN49sd0THriZeJyHZ7VKvytwjy5Nobqky9_rMw', 'resolutions': [{'height': 58, 'url': 'https://external-preview.redd.it/_86VQ1oE4CPv33SjOtLsfTrlhEbz_XCKYKwzf0BjZWk.jpg?width=108&crop=smart&auto=webp&s=9f4276960aca828176d4b8ca1589aa9dc9ebc3fa', 'width': 108}, {'height': 116, 'url': 'h... |
LLama + llama-index | 0 | [removed] | 2023-05-30T06:28:26 | https://www.reddit.com/r/LocalLLaMA/comments/13viiuv/llama_llamaindex/ | Reasonable-Put-1853 | self.LocalLLaMA | 2023-05-30T06:39:11 | 0 | {} | 13viiuv | false | null | t3_13viiuv | /r/LocalLLaMA/comments/13viiuv/llama_llamaindex/ | false | false | default | 0 | null |
TheBloke is on an absolute tear over on HuggingFace | 1 | [removed] | 2023-05-30T06:01:16 | https://www.reddit.com/r/LocalLLaMA/comments/13vi2ow/thebloke_is_on_an_absolute_tear_over_on/ | natufian | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 13vi2ow | false | null | t3_13vi2ow | /r/LocalLLaMA/comments/13vi2ow/thebloke_is_on_an_absolute_tear_over_on/ | false | false | default | 1 | null |
Wizard-Vicuna-30B-Uncensored | 336 | I just released Wizard-Vicuna-30B-Uncensored
[https://huggingface.co/ehartford/Wizard-Vicuna-30B-Uncensored](https://huggingface.co/ehartford/Wizard-Vicuna-30B-Uncensored)
It's what you'd expect, although I found the larger models seem to be more resistant than the smaller ones.
Disclaimers:
An uncensored model has... | 2023-05-30T05:54:14 | https://www.reddit.com/r/LocalLLaMA/comments/13vhyen/wizardvicuna30buncensored/ | faldore | self.LocalLLaMA | 2023-05-30T05:57:44 | 0 | {} | 13vhyen | false | null | t3_13vhyen | /r/LocalLLaMA/comments/13vhyen/wizardvicuna30buncensored/ | false | false | self | 336 | {'enabled': False, 'images': [{'id': 'iykKO3N7SpXuBtTikcYk9qHwPIi8eRAcC-Ft--EB2mw', 'resolutions': [{'height': 58, 'url': 'https://external-preview.redd.it/FEF7RlKudVYdZKaoxORTg_GkQRI27jrV5SdtMq9v20c.jpg?width=108&crop=smart&auto=webp&s=b779898997e5e5a921c2a16565cb3f8dabe05c30', 'width': 108}, {'height': 116, 'url': 'h... |
Worth it on my AMD based laptop? | 1 | Hey everyone.
Im seeing pretty much all intel/nvidia support for everything. I already planned to buy a new pc in the fall, but I'd like to learn how to operate them in the mean time, even if it is just a 7b model. Having a local model to go over all of my research docs and aid me in writing sounds like a dream. I don... | 2023-05-30T05:53:25 | https://www.reddit.com/r/LocalLLaMA/comments/13vhxy0/worth_it_on_my_amd_based_laptop/ | The_Dayne | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 13vhxy0 | false | null | t3_13vhxy0 | /r/LocalLLaMA/comments/13vhxy0/worth_it_on_my_amd_based_laptop/ | false | false | self | 1 | null |
Best web UI and cloud GPU to run 30b LLaMA models? | 3 | As it’s not possible for my hardware to run anything more than a quantised 13b model, I’m looking for alternative solutions that maybe others have been using.
I loved the idea of the Hugging Face web-ui as it’s stupid easy since that’s where the models are hosted, but quickly found out the LLaMA models aren’t suppo... | 2023-05-30T05:32:53 | https://www.reddit.com/r/LocalLLaMA/comments/13vhlqg/best_web_ui_and_cloud_gpu_to_run_30b_llama_models/ | sardoa11 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 13vhlqg | false | null | t3_13vhlqg | /r/LocalLLaMA/comments/13vhlqg/best_web_ui_and_cloud_gpu_to_run_30b_llama_models/ | false | false | self | 3 | null |
Introducing LocalGPT: Offline ChatBOT for your FILES with GPU - Vicuna | 149 | Introducing LocalGPT: [https://github.com/PromtEngineer/localGPT](https://github.com/PromtEngineer/localGPT)
This project will enable you to chat with your files using an LLM. Run it offline locally without internet access. Completely private and you don't share your data with anyone. It takes inspiration from the pri... | 2023-05-30T05:21:23 | https://www.reddit.com/r/LocalLLaMA/comments/13vhev0/introducing_localgpt_offline_chatbot_for_your/ | satmarz | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 13vhev0 | false | null | t3_13vhev0 | /r/LocalLLaMA/comments/13vhev0/introducing_localgpt_offline_chatbot_for_your/ | false | false | self | 149 | {'enabled': False, 'images': [{'id': 'k9UvaWdiVD4hOv1vETarT9Ls9F-dIr24qSsAyOL1eOU', 'resolutions': [{'height': 54, 'url': 'https://external-preview.redd.it/8gUl3q1djrE7uaEHsNuEr6fSSSaqdC37nQec4bTYSnQ.jpg?width=108&crop=smart&auto=webp&s=82080fe11385d96a09bfc1921d71f6850ca6380f', 'width': 108}, {'height': 108, 'url': 'h... |
How many iterations do fine-trained models usually need/use using LoRA/QLoRA? | 10 | [deleted] | 2023-05-30T04:30:13 | [deleted] | 1970-01-01T00:00:00 | 0 | {} | 13vggwg | false | null | t3_13vggwg | /r/LocalLLaMA/comments/13vggwg/how_many_iterations_do_finetrained_models_usually/ | false | false | default | 10 | null | ||
PrivateGPT - Asking itself questions and answering? | 2 | When I ask a question on PrivateGPT, it answers, but spirals and starts asking random questions and answering them by itself. In the example below, I only asked it the first question but it spiralled into the other questions and gave answers. Any idea how to fix this?
Using the Koala 13B, but similar results with GPT... | 2023-05-30T04:07:58 | https://www.reddit.com/r/LocalLLaMA/comments/13vg1gt/privategpt_asking_itself_questions_and_answering/ | masterblaster269 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 13vg1gt | false | null | t3_13vg1gt | /r/LocalLLaMA/comments/13vg1gt/privategpt_asking_itself_questions_and_answering/ | false | false | 2 | null | |
Good ggml model for coding? | 6 | Hi all, anyone have a recommendation for a ggml model fine tuned for code?
Edit: not too concerned on language, python preferred but most languages would be fine. | 2023-05-30T03:55:16 | https://www.reddit.com/r/LocalLLaMA/comments/13vfrnj/good_ggml_model_for_coding/ | Equal_Station2752 | self.LocalLLaMA | 2023-05-30T04:10:41 | 0 | {} | 13vfrnj | false | null | t3_13vfrnj | /r/LocalLLaMA/comments/13vfrnj/good_ggml_model_for_coding/ | false | false | self | 6 | null |
Seeking Opinions on e5-large-v2 and instructor-xl Embedding Models for Multilingual Applications | 12 | Hi Reddit Community,
I hope you're all doing well. I've been recently exploring the realm of embedding models for a multilingual project I am working on, and I've narrowed my options down to two models: e5-large-v2 and instructor-xl.
Each of them appears promising, with their own unique features and capabilities. But... | 2023-05-30T02:36:24 | https://www.reddit.com/r/LocalLLaMA/comments/13ve2wd/seeking_opinions_on_e5largev2_and_instructorxl/ | Reality-Sufficient | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 13ve2wd | false | null | t3_13ve2wd | /r/LocalLLaMA/comments/13ve2wd/seeking_opinions_on_e5largev2_and_instructorxl/ | false | false | self | 12 | null |
Uncensored model for 4Gb vram | 2 | [removed] | 2023-05-30T02:25:04 | https://www.reddit.com/r/LocalLLaMA/comments/13vdu02/uncensored_model_for_4gb_vram/ | cyberv1k1n9 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 13vdu02 | false | null | t3_13vdu02 | /r/LocalLLaMA/comments/13vdu02/uncensored_model_for_4gb_vram/ | false | false | default | 2 | null |
Mod team and contributors | 29 | This small community of local language model enthusiasts has grown quickly! Thank you everyone for being part of what makes this subreddit great.
r/LocalLLaMA is looking for two things:
* One or two moderators to help with keeping the subreddit high quality and maintaining the wiki pages. If you're interested in help... | 2023-05-30T02:14:54 | https://www.reddit.com/r/LocalLLaMA/comments/13vdlzr/mod_team_and_contributors/ | Technical_Leather949 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 13vdlzr | true | null | t3_13vdlzr | /r/LocalLLaMA/comments/13vdlzr/mod_team_and_contributors/ | false | false | self | 29 | null |
Guanaco 7B llama.cpp newline issue | 6 | So, I've been using Guanaco 7B q5\_1 with llama.cpp and think it's \*awesome\*. With the "precise chat" settings, it's easily the best 7B model available, punches well above it's weight, and acts like a 13B in a lot of ways. There's just one glaring problem that, realistically, is more of a minor annoyance than anythin... | 2023-05-30T00:47:23 | https://www.reddit.com/r/LocalLLaMA/comments/13vbr0e/guanaco_7b_llamacpp_newline_issue/ | AI-Pon3 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 13vbr0e | false | null | t3_13vbr0e | /r/LocalLLaMA/comments/13vbr0e/guanaco_7b_llamacpp_newline_issue/ | false | false | self | 6 | null |
Cheap/Free GPU Cloud services? | 1 | [removed] | 2023-05-30T00:25:08 | https://www.reddit.com/r/LocalLLaMA/comments/13vb9ia/cheapfree_gpu_cloud_services/ | Huge-Usual-3787 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 13vb9ia | false | null | t3_13vb9ia | /r/LocalLLaMA/comments/13vb9ia/cheapfree_gpu_cloud_services/ | false | false | default | 1 | null |
Cross pollination of ideas from Stable Diffusion: Textual Inversions | 50 | I've had this idea rattling around in my mind for a while and need to get it out. I was amazed to hear from the creator of LORA that they designed LORA for LLMs, but they ended up being quite suited for Stable Diffusion. This got me wondering - is there anything currently in Stable Diffusion that is able to be applied ... | 2023-05-29T21:37:35 | https://www.reddit.com/r/LocalLLaMA/comments/13v7ctt/cross_pollination_of_ideas_from_stable_diffusion/ | revolved | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 13v7ctt | false | null | t3_13v7ctt | /r/LocalLLaMA/comments/13v7ctt/cross_pollination_of_ideas_from_stable_diffusion/ | false | false | self | 50 | {'enabled': False, 'images': [{'id': 'HFF1ModH9rb79ohJok8TB5o2V72dPF1koNi65mLF9Fk', 'resolutions': [{'height': 81, 'url': 'https://external-preview.redd.it/sibHwFD7dMBm0hOMe3NBTV_nktx-n497RV-fu7k8hXI.jpg?width=108&crop=smart&auto=webp&s=afbdc7fb6a6e30e19c8e39a9b5e4f4f3f0f3841e', 'width': 108}, {'height': 162, 'url': 'h... |
llamacpp memory use on a m1 using oobabooga | 1 | [removed] | 2023-05-29T21:32:00 | https://www.reddit.com/r/LocalLLaMA/comments/13v77yw/llamacpp_memory_use_on_a_m1_using_oobabooga/ | Bozo32 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 13v77yw | false | null | t3_13v77yw | /r/LocalLLaMA/comments/13v77yw/llamacpp_memory_use_on_a_m1_using_oobabooga/ | false | false | default | 1 | null |
TIL Sharding a model into smaller chunks may make it possible to load in Free Colab instances without running out of memory | 24 | I recently came across this [huggingface article](https://huggingface.co/blog/4bit-transformers-bitsandbytes) where there was a notebook claiming that they you can load GPT-NeoX-20B in a Free Colab instance which I found hard to believe because I was unable to load models as small as GPT-Neo-2.7B and StableLM 3B on a F... | 2023-05-29T21:12:58 | https://www.reddit.com/r/LocalLLaMA/comments/13v6qvh/til_sharding_a_model_into_smaller_chunks_may_make/ | ragnarkar | self.LocalLLaMA | 2023-05-30T13:06:07 | 0 | {} | 13v6qvh | false | null | t3_13v6qvh | /r/LocalLLaMA/comments/13v6qvh/til_sharding_a_model_into_smaller_chunks_may_make/ | false | false | self | 24 | {'enabled': False, 'images': [{'id': '5ors3IzSd91LDWo2yC2yuTxbj5satwsZQHIPrP5aNIo', 'resolutions': [{'height': 54, 'url': 'https://external-preview.redd.it/AdT_mjn1LNVLlYzaUOGIw8eCMBkcVhUwUipuiEi6w-s.jpg?width=108&crop=smart&auto=webp&s=ffc336c656133c8a8bd641e31b75fb1aa11f8621', 'width': 108}, {'height': 108, 'url': 'h... |
Bitsandbytes giving you a cuda error on windows? Don't worry, some guy already compiled it for you. | 14 | I don't know what bitsandbytes is or what it does or why it won't just compile for me out of the box. Alls I know is it gives me errors and makes me sad. In an effort to prevent more tears, here's what I learned: I found some post somewhere that said to pip install this git repository and I did and then bitsandbytes ... | 2023-05-29T20:13:35 | https://www.reddit.com/r/LocalLLaMA/comments/13v57sf/bitsandbytes_giving_you_a_cuda_error_on_windows/ | UnoriginalScreenName | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 13v57sf | false | null | t3_13v57sf | /r/LocalLLaMA/comments/13v57sf/bitsandbytes_giving_you_a_cuda_error_on_windows/ | false | false | self | 14 | {'enabled': False, 'images': [{'id': 'BSXsiBdAOCkfF5-JmoMvq9Q6TWfza3b-1kk_0wUeqQ4', 'resolutions': [{'height': 54, 'url': 'https://external-preview.redd.it/wMixadyzI2jh_z0lVuqQo0K21YoBuWKhyaWGxPqq6MM.jpg?width=108&crop=smart&auto=webp&s=8b176a9209c9411f21d188fd88d66ab729a03525', 'width': 108}, {'height': 108, 'url': 'h... |
Server help (again) | 2 | [removed] | 2023-05-29T19:52:34 | https://www.reddit.com/r/LocalLLaMA/comments/13v4ohm/server_help_again/ | Emergency-Seaweed-73 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 13v4ohm | false | null | t3_13v4ohm | /r/LocalLLaMA/comments/13v4ohm/server_help_again/ | false | false | default | 2 | null |
Is there a GUI for llama.cpp that I can use my CuBlas enabled binary with? | 1 | [removed] | 2023-05-29T19:29:49 | https://www.reddit.com/r/LocalLLaMA/comments/13v4425/is_there_a_gui_for_llamacpp_that_i_can_use_my/ | APUsilicon | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 13v4425 | false | null | t3_13v4425 | /r/LocalLLaMA/comments/13v4425/is_there_a_gui_for_llamacpp_that_i_can_use_my/ | false | false | default | 1 | null |
Model answering itself? | 0 | [removed] | 2023-05-29T19:23:50 | https://www.reddit.com/r/LocalLLaMA/comments/13v3yqa/model_answering_itself/ | butidontwanto | self.LocalLLaMA | 2023-05-29T19:30:10 | 0 | {} | 13v3yqa | false | null | t3_13v3yqa | /r/LocalLLaMA/comments/13v3yqa/model_answering_itself/ | false | false | default | 0 | null |
Multiple cheap gpus or a single expensive one? | 13 | So i have about $500-600 and already a good server 128-256gb ddr3 and 24 xeon e5-2698 V2 cores so there i don't need an upgrade i think but i dont have a GPU in it yet and i am wondering would it be better to get more ram and getting older server GPUs or something like a single 3090? Also does AMD vs Nvidia matter seei... | 2023-05-29T18:58:17 | https://www.reddit.com/r/LocalLLaMA/comments/13v3b6q/multiple_cheap_gpus_or_a_single_expensive_one/ | gpu_melter | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 13v3b6q | false | null | t3_13v3b6q | /r/LocalLLaMA/comments/13v3b6q/multiple_cheap_gpus_or_a_single_expensive_one/ | false | false | self | 13 | null |
Kobold on runpod? | 2 | [removed] | 2023-05-29T18:34:59 | https://www.reddit.com/r/LocalLLaMA/comments/13v2qry/kobold_on_runpod/ | chakalakasp | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 13v2qry | false | null | t3_13v2qry | /r/LocalLLaMA/comments/13v2qry/kobold_on_runpod/ | false | false | default | 2 | null |
Subsets and Splits
No community queries yet
The top public SQL queries from the community will appear here once available.