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 ⌀ |
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
Question about fine-tuning LLaMA-65B | 10 | How many 80GB A100s or H100s are required to fine-tune LLaMA-65B? I assume the VRAM requirements would be pretty much double what is required to fine-tune LLaMA-33B, but I'm not certain as I haven't fine-tuned any models before. | 2023-05-22T03:14:50 | https://www.reddit.com/r/LocalLLaMA/comments/13oeu66/question_about_finetuning_llama65b/ | Adventurous_Jelly276 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 13oeu66 | false | null | t3_13oeu66 | /r/LocalLLaMA/comments/13oeu66/question_about_finetuning_llama65b/ | false | false | self | 10 | null |
Any idea Vicuna 13B 4bit model output random content? | 2 | [removed] | 2023-05-22T02:09:55 | https://www.reddit.com/r/LocalLLaMA/comments/13oder5/any_idea_vicuna_13b_4bit_model_output_random/ | direwulf33 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 13oder5 | false | null | t3_13oder5 | /r/LocalLLaMA/comments/13oder5/any_idea_vicuna_13b_4bit_model_output_random/ | false | false | default | 2 | null |
Is there a subreddit for people interested in actually using a local LLM productively? | 1 | [removed] | 2023-05-21T21:56:07 | https://www.reddit.com/r/LocalLLaMA/comments/13o7lr6/is_there_a_subreddit_for_people_interested_in/ | Careful_Fee_642 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 13o7lr6 | false | null | t3_13o7lr6 | /r/LocalLLaMA/comments/13o7lr6/is_there_a_subreddit_for_people_interested_in/ | false | false | default | 1 | null |
airoboros-13b -- 98% against gpt-3.5 | 214 | [deleted] | 2023-05-21T21:15:31 | [deleted] | 2023-05-21T21:18:44 | 0 | {} | 13o6kp8 | false | null | t3_13o6kp8 | /r/LocalLLaMA/comments/13o6kp8/airoboros13b_98_against_gpt35/ | false | false | default | 214 | null | ||
airobors-13b - 98% eval vs gpt-3.5-turbo | 1 | [deleted] | 2023-05-21T21:12:52 | [deleted] | 1970-01-01T00:00:00 | 0 | {} | 13o6icr | false | null | t3_13o6icr | /r/LocalLLaMA/comments/13o6icr/airobors13b_98_eval_vs_gpt35turbo/ | false | false | default | 1 | null | ||
How fast will an RK3588s with a 6 TOPS NPU run LLaMa models? | 1 | [removed] | 2023-05-21T18:36:48 | https://www.reddit.com/r/LocalLLaMA/comments/13o2mem/how_fast_will_an_rk3588s_with_a_6_tops_npu_run/ | JeffersonTerrerfield | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 13o2mem | false | null | t3_13o2mem | /r/LocalLLaMA/comments/13o2mem/how_fast_will_an_rk3588s_with_a_6_tops_npu_run/ | false | false | default | 1 | null |
Which Open LLMs can I run with RTX 3070ti locally?? | 1 | [removed] | 2023-05-21T17:22:35 | https://www.reddit.com/r/LocalLLaMA/comments/13o0qd9/which_open_llms_can_i_run_with_rtx_3070ti_locally/ | Hot_Adhesiveness_259 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 13o0qd9 | false | null | t3_13o0qd9 | /r/LocalLLaMA/comments/13o0qd9/which_open_llms_can_i_run_with_rtx_3070ti_locally/ | false | false | default | 1 | null |
llama.cpp running extremely slow via GPT4ALL | 2 | Hi all,
I compiled llama.cpp to use with GPT4ALL and is providing good output and I am happy with the results. However unfortunately for a simple matching question with perhaps 30 tokens, the output is taking 60 seconds. Output really only needs to be 3 tokens maximum but is never more than 10. I used the standard [GP... | 2023-05-21T14:21:39 | https://www.reddit.com/r/LocalLLaMA/comments/13nwb60/llamacpp_running_extremely_slow_via_gpt4all/ | EmbarrassedSleep6981 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 13nwb60 | false | null | t3_13nwb60 | /r/LocalLLaMA/comments/13nwb60/llamacpp_running_extremely_slow_via_gpt4all/ | false | false | self | 2 | {'enabled': False, 'images': [{'id': 'bgEVd_LAkjXY8gB-hohtJcoyOi6Hbzz3BRZs7CeIBug', 'resolutions': [{'height': 54, 'url': 'https://external-preview.redd.it/U_sGAtJE52N3O_bKSZMxffGChehdpYhDUK3m5FfHV34.jpg?width=108&crop=smart&auto=webp&s=c9ade8df62f42df46111a920f5aed6b39337dc11', 'width': 108}, {'height': 108, 'url': 'h... |
KoboldCpp updated to v1.24, supports new GGJT v3 quantizations while still maintaining full backwards compatibility. | 101 | - Added support for the new GGJT v3 (q4_0, q4_1 and q8_0) quantization format changes.
- Still retains backwards compatibility with every single historical GGML format (GGML, GGHF, GGJT v1,2,3 + all other formats from supported architectures).
- Supports GGML models for LLAMA, RWKV, GPT-2, GPT-J and GPT-NeoX
- Supports... | 2023-05-21T12:25:24 | https://www.reddit.com/r/LocalLLaMA/comments/13nrp0r/koboldcpp_updated_to_v124_supports_new_ggjt_v3/ | HadesThrowaway | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 13nrp0r | false | null | t3_13nrp0r | /r/LocalLLaMA/comments/13nrp0r/koboldcpp_updated_to_v124_supports_new_ggjt_v3/ | false | false | self | 101 | {'enabled': False, 'images': [{'id': 'Cv2Fvh0FKLhQk-IG0MAQC7avJtRIUrN39qstdvEmMIE', 'resolutions': [{'height': 102, 'url': 'https://external-preview.redd.it/mq20r6Fq4HWxfY3jCxdgz33uLlRCaqUtFnPp8nr1Lis.png?width=108&crop=smart&auto=webp&s=de24083f6f5b6c336aca77ede36252544a7ccc08', 'width': 108}, {'height': 204, 'url': '... |
chart of gpu performance on llms | 1 | [removed] | 2023-05-21T08:55:21 | https://www.reddit.com/r/LocalLLaMA/comments/13nnqtz/chart_of_gpu_performance_on_llms/ | Kurdiwari | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 13nnqtz | false | null | t3_13nnqtz | /r/LocalLLaMA/comments/13nnqtz/chart_of_gpu_performance_on_llms/ | false | false | default | 1 | null |
Help can't get reply from MetalX Alpasta 30b 4bit | 1 | [removed] | 2023-05-21T08:16:36 | [deleted] | 1970-01-01T00:00:00 | 0 | {} | 13nn1xl | false | null | t3_13nn1xl | /r/LocalLLaMA/comments/13nn1xl/help_cant_get_reply_from_metalx_alpasta_30b_4bit/ | false | false | default | 1 | null | ||
Models are repeating text several times? | 5 | For some reason with several models, if I submit a prompt I get an answer repeated over and over, rather than just generating it once. For example, the below code...
`from langchain.llms import HuggingFacePipeline`
`import torch`
`from transformers import AutoTokenizer, AutoModelForCausalLM, pipeline`
`model_id = '... | 2023-05-21T07:32:36 | https://www.reddit.com/r/LocalLLaMA/comments/13nm96l/models_are_repeating_text_several_times/ | TheNomadicAspie | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 13nm96l | false | null | t3_13nm96l | /r/LocalLLaMA/comments/13nm96l/models_are_repeating_text_several_times/ | false | false | self | 5 | null |
Is the Nvidia K80 with 24GB usable for LLMs? | 11 | Whilst looking for used P40s, I came across some VERY cheap K80s (whatever they are).
Are they usable for running LLMs?
(I don't care about the speed too much .. but the 24GB could be useful) | 2023-05-21T07:27:26 | https://www.reddit.com/r/LocalLLaMA/comments/13nm5ox/is_the_nvidia_k80_with_24gb_usable_for_llms/ | MrEloi | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 13nm5ox | false | null | t3_13nm5ox | /r/LocalLLaMA/comments/13nm5ox/is_the_nvidia_k80_with_24gb_usable_for_llms/ | false | false | self | 11 | null |
Help with getting started implementing long-term memory on local model? | 9 | I've been learning everything I can about this stuff, but am having trouble finding actual examples of code to alter and learn from, most of the information I can find is more theoretical, so I'm hoping maybe someone could point me in the right direction.
I upgraded my graphics card to a 3060 so I can run the dolly 2.... | 2023-05-21T07:06:48 | https://www.reddit.com/r/LocalLLaMA/comments/13nlrzp/help_with_getting_started_implementing_longterm/ | TheNomadicAspie | self.LocalLLaMA | 2023-05-21T07:11:28 | 0 | {} | 13nlrzp | false | null | t3_13nlrzp | /r/LocalLLaMA/comments/13nlrzp/help_with_getting_started_implementing_longterm/ | false | false | self | 9 | {'enabled': False, 'images': [{'id': 'OgFzGCIRw1ZxjMOSkfV1OiH-_nQiZl8rzSonmOAuhGs', 'resolutions': [{'height': 108, 'url': 'https://external-preview.redd.it/-WiKXADWH5lgU4gQv5fcDAQ9QKNBZTJ-D83BykIL2HA.jpg?width=108&crop=smart&auto=webp&s=df9c6a296446d05d873c629a30253398c4d29c1b', 'width': 108}], 'source': {'height': 15... |
How do I get Local LLM to analyze an whole excel or CSV? | 13 | I am trying to tinker with the idea of ingesting a csv with multiple rows, with numeric and categorical feature, and then extract insights from that document.
Expectation - Local LLM will go through the excel sheet, identify few patterns, and provide some key insights
Right now, I went through various local versions... | 2023-05-21T06:44:49 | https://www.reddit.com/r/LocalLLaMA/comments/13nld5x/how_do_i_get_local_llm_to_analyze_an_whole_excel/ | DesmonMiles07 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 13nld5x | false | null | t3_13nld5x | /r/LocalLLaMA/comments/13nld5x/how_do_i_get_local_llm_to_analyze_an_whole_excel/ | false | false | self | 13 | null |
Server. Build/questions. | 3 |
Hey guys I have a few questions, I'd like to build a server with a few gpus in it so me and a couple guys can use it remotely. Is that possible and how would I set it up?
Second question, if I'm going for vram on a budget, could I just use some Nvidia tesla k80's looks like they have 24gb gddr5? Cost 150$. If you hav... | 2023-05-21T06:28:55 | https://www.reddit.com/r/LocalLLaMA/comments/13nl2o0/server_buildquestions/ | Emergency-Seaweed-73 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 13nl2o0 | false | null | t3_13nl2o0 | /r/LocalLLaMA/comments/13nl2o0/server_buildquestions/ | false | false | self | 3 | null |
Llama.cpp master-fab49c6 Issues | 2 | [removed] | 2023-05-21T05:30:02 | https://www.reddit.com/r/LocalLLaMA/comments/13njzj7/llamacpp_masterfab49c6_issues/ | mrjackspade | self.LocalLLaMA | 2023-05-21T06:52:07 | 0 | {} | 13njzj7 | false | null | t3_13njzj7 | /r/LocalLLaMA/comments/13njzj7/llamacpp_masterfab49c6_issues/ | false | false | default | 2 | null |
What coding llm is the best? | 75 | So besides GPT4, I have found Codeium to be the best imo. Phind is good for a search engine/code engine. However, I have seen interesting tests with Starcoder. Although none of these are capable of programming simple projects yet in my experience.
​
What has your experience been? Thank you. | 2023-05-21T04:49:07 | https://www.reddit.com/r/LocalLLaMA/comments/13nj7g8/what_coding_llm_is_the_best/ | ArmoredBattalion | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 13nj7g8 | false | null | t3_13nj7g8 | /r/LocalLLaMA/comments/13nj7g8/what_coding_llm_is_the_best/ | false | false | self | 75 | null |
Following u/faldore's amazing work, I'd like to create an uncensored version of the Alpacino30b model, and am seeking sponsors to help cover the compute costs. | 35 | [removed] | 2023-05-21T03:43:24 | https://www.reddit.com/r/LocalLLaMA/comments/13nhwsh/following_ufaldores_amazing_work_id_like_to/ | sardoa11 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 13nhwsh | false | null | t3_13nhwsh | /r/LocalLLaMA/comments/13nhwsh/following_ufaldores_amazing_work_id_like_to/ | false | false | default | 35 | null |
r/PygmalionAI/ sub is being disowned and being take over by Rouge mod we currently move to r/Pygmalion_ai/ | 1 | [removed] | 2023-05-21T03:40:10 | https://www.reddit.com/r/LocalLLaMA/comments/13nhudv/rpygmalionai_sub_is_being_disowned_and_being_take/ | Merchant_Lawrence | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 13nhudv | false | null | t3_13nhudv | /r/LocalLLaMA/comments/13nhudv/rpygmalionai_sub_is_being_disowned_and_being_take/ | false | false | default | 1 | null |
I want to share with you my easy peasy llamacpp script | 27 | 2023-05-21T03:39:30 | https://asciinema.org/a/586215 | Evening_Ad6637 | asciinema.org | 1970-01-01T00:00:00 | 0 | {} | 13nhtw0 | false | null | t3_13nhtw0 | /r/LocalLLaMA/comments/13nhtw0/i_want_to_share_with_you_my_easy_peasy_llamacpp/ | false | false | 27 | {'enabled': False, 'images': [{'id': 'sEnAY_QXHB893PK3xk6ClewTprQOoXmv7BOCm8Oh-RU', 'resolutions': [{'height': 79, 'url': 'https://external-preview.redd.it/gvGe7sDDVEl3i9MrkEgqUOIJ2Uxyn3PTLHDK5qfY96E.jpg?width=108&crop=smart&auto=webp&s=dd3ba7c980bf22b45c2d42823eccf61ec50c910b', 'width': 108}, {'height': 159, 'url': 'h... | ||
Error with no groupsize | 1 | If I try to run in ooba a gptq model made with no groupsize like VicUnlocked-30B-LoRA-GPTQ, I get this error:
>NO\_GROUP: tl.constexpr, BLOCK\_SIZE\_M: tl.constexpr, BLOCK\_SIZE\_N: tl.constexpr, BLOCK\_SIZE\_K: tl.constexpr, GROUP\_SIZE\_M: tl.constexpr):“”"Compute the matrix multiplication C = A x B.A is of shape (M... | 2023-05-21T03:16:54 | https://www.reddit.com/r/LocalLLaMA/comments/13nhdng/error_with_no_groupsize/ | RabbitEater2 | self.LocalLLaMA | 2023-05-21T03:20:31 | 0 | {} | 13nhdng | false | null | t3_13nhdng | /r/LocalLLaMA/comments/13nhdng/error_with_no_groupsize/ | false | false | 1 | null | |
In July, the GeForce RTX 4060 Ti (16GB) arrives in stores, starting at $499 | 39 | This seems like a slow card for gamers compared to other options, but a good value for language models due to price and 16 GB VRAM? | 2023-05-21T01:24:49 | https://www.nvidia.com/en-us/geforce/news/geforce-rtx-4060-4060ti/ | ThePseudoMcCoy | nvidia.com | 1970-01-01T00:00:00 | 0 | {} | 13nf0mw | false | null | t3_13nf0mw | /r/LocalLLaMA/comments/13nf0mw/in_july_the_geforce_rtx_4060_ti_16gb_arrives_in/ | false | false | 39 | {'enabled': False, 'images': [{'id': 'c5hFdn7sJoD-8ROp9zMR2A6pfZmGcUQsIr1CDmLSbOU', 'resolutions': [{'height': 56, 'url': 'https://external-preview.redd.it/CxjooKgLJZlMBaTAWdIYeZD08aY2JRT2zXsUa6e22Nk.jpg?width=108&crop=smart&auto=webp&s=7fdc802fa250f3ba72ccff76e15013d09210af70', 'width': 108}, {'height': 113, 'url': 'h... | |
Weird Dual GPU setup in Ooba | 3 | I recently got a 2nd video card with more VRAM (a6000 48gb) to try and load some bigger models, however I am trying to do a weird setup — I am trying to load 0mb into my first card and have the entire model loaded into my 2nd card (as I don’t want to slow things down inferencing across both cards if it will all fit int... | 2023-05-21T00:03:39 | https://www.reddit.com/r/LocalLLaMA/comments/13nd96e/weird_dual_gpu_setup_in_ooba/ | disarmyouwitha | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 13nd96e | false | null | t3_13nd96e | /r/LocalLLaMA/comments/13nd96e/weird_dual_gpu_setup_in_ooba/ | false | false | self | 3 | null |
Powerpointer - Generate entire powerpoints using local large language models | 66 | Hello community
I created a powerpoint generator which can generate diverse, good looking powerpoints using models like Vicuna or Alpaca. It uses text-generation-webui --api as a backend, so you can use text-generation-webui and the generator at the same time.
You can select between 7 powerpoint designs and it also... | 2023-05-20T22:42:24 | https://www.reddit.com/r/LocalLLaMA/comments/13nbfvz/powerpointer_generate_entire_powerpoints_using/ | zBlackVision11 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 13nbfvz | false | null | t3_13nbfvz | /r/LocalLLaMA/comments/13nbfvz/powerpointer_generate_entire_powerpoints_using/ | false | false | self | 66 | {'enabled': False, 'images': [{'id': 'pdGxjYtEWUuyNxeS-Pa-skIbwqcKhZ-Vh3KV8j4saeo', 'resolutions': [{'height': 54, 'url': 'https://external-preview.redd.it/5kQP8mDp0ujioqEPiw1VoXsFdaY5FsVn5wYmpete8u0.jpg?width=108&crop=smart&auto=webp&s=d482271b3b69892d052f7b2a25fc4dfffbb727a3', 'width': 108}, {'height': 108, 'url': 'h... |
Need Assistance Running the starcoder-GPTQ-4bit-128g Model with missing config.json in text-generation-webui | 7 | Hello LocalLLaMA community,
I've been trying to load the [starcoder-GPTQ-4bit-128g model](https://huggingface.co/mayank31398/starcoder-GPTQ-4bit-128g) into the [text-generation-webui by oobabooga](https://github.com/oobabooga/text-generation-webui) but have run into some difficulties due to missing files. Specifically... | 2023-05-20T22:10:20 | https://www.reddit.com/r/LocalLLaMA/comments/13naoyg/need_assistance_running_the_starcodergptq4bit128g/ | LaCipe | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 13naoyg | false | null | t3_13naoyg | /r/LocalLLaMA/comments/13naoyg/need_assistance_running_the_starcodergptq4bit128g/ | false | false | self | 7 | {'enabled': False, 'images': [{'id': 'fg9qOeYrOPWrI8Sr0baIRR_z7q7sym25M66JFFcrTAg', 'resolutions': [{'height': 58, 'url': 'https://external-preview.redd.it/XLddIZQFNFNrgKu2alX2VHzkxhMdl1MtB4EOsXn_bik.jpg?width=108&crop=smart&auto=webp&s=b523133e0a3b86ea433e83f4780fd2f724ecbe64', 'width': 108}, {'height': 116, 'url': 'h... |
Best model for game "AI agent"? | 11 | Hi,
So basically I'm looking for a model suitable to be used as an AI agent back-end.
What I expect from it is to be really good at following instructions (and also not too restrictive when it comes to violence).
I was trying out requests like this:
*Player is doing X, saying Y, you are this NPC XY, your possible a... | 2023-05-20T22:00:50 | https://www.reddit.com/r/LocalLLaMA/comments/13naggc/best_model_for_game_ai_agent/ | kamtar | self.LocalLLaMA | 2023-05-20T22:04:48 | 0 | {} | 13naggc | false | null | t3_13naggc | /r/LocalLLaMA/comments/13naggc/best_model_for_game_ai_agent/ | false | false | self | 11 | null |
Which file formats should I use if I have a GPU | 5 | I understand that there are different models. I know of three interfaces: gpt4all, llama.ccp and oogabooga. I don't understand file formats. The latest Manticore releases comes in different formats. What combo of interface/format should I use for a 3080? | 2023-05-20T21:45:54 | https://www.reddit.com/r/LocalLLaMA/comments/13na3a5/which_file_formats_should_i_use_if_i_have_a_gpu/ | infohawk | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 13na3a5 | false | null | t3_13na3a5 | /r/LocalLLaMA/comments/13na3a5/which_file_formats_should_i_use_if_i_have_a_gpu/ | false | false | self | 5 | null |
Combining weights (fine tunes of the same base) | 3 | [deleted] | 2023-05-20T21:35:21 | [deleted] | 2023-06-23T07:06:10 | 0 | {} | 13n9u58 | false | null | t3_13n9u58 | /r/LocalLLaMA/comments/13n9u58/combining_weights_fine_tunes_of_the_same_base/ | false | false | default | 3 | null | ||
My results using a Tesla P40 | 101 | TL;DR at bottom
So like many of you, I feel down the AI text gen rabbit hole. My wife has been severely addicted to all things chat AI, so it was only natural. Our previous server was running a 3500 core i-5 from over a decade ago, so we figured this would be the best time to upgrade. We got a P40 as well for gits ... | 2023-05-20T20:47:26 | https://www.reddit.com/r/LocalLLaMA/comments/13n8bqh/my_results_using_a_tesla_p40/ | AsheramL | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 13n8bqh | false | null | t3_13n8bqh | /r/LocalLLaMA/comments/13n8bqh/my_results_using_a_tesla_p40/ | false | false | self | 101 | null |
Running a small model on a phone? | 8 | Anyone have any luck running a small model on a phone. I seen the llama.cpp repo an it has a section to get a model running on android.
thanks for tha downvotes much appreciated.
​ | 2023-05-20T20:12:27 | https://www.reddit.com/r/LocalLLaMA/comments/13n6c3z/running_a_small_model_on_a_phone/ | ScoobySnackzz12 | self.LocalLLaMA | 2023-05-21T13:24:58 | 0 | {} | 13n6c3z | false | null | t3_13n6c3z | /r/LocalLLaMA/comments/13n6c3z/running_a_small_model_on_a_phone/ | false | false | self | 8 | null |
Why can't we use edge TPUs (like coral AI) with inferencing? | 5 | I ask this from extreme amounts of ignorance, if we can load a full model into system ram, what's stopping the TPU from participating in calculations?
Or is it just that GPU ram is that much faster than system ram and that's the real reason they're better than CPUs? | 2023-05-20T20:07:18 | https://www.reddit.com/r/LocalLLaMA/comments/13n613w/why_cant_we_use_edge_tpus_like_coral_ai_with/ | noneabove1182 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 13n613w | false | null | t3_13n613w | /r/LocalLLaMA/comments/13n613w/why_cant_we_use_edge_tpus_like_coral_ai_with/ | false | false | self | 5 | null |
Is there such a thing as local Llamas integrated into VSCode? | 17 | Hi, I’m wondering if someone already created a plug-in for using these models directly from VSCode?
It should be pretty trivial to connect a VSCode plugin to the text-generation-web-ui API, and it could be interesting when used with models that can generate code.
If there’s not one already, I’d look into building it,... | 2023-05-20T19:15:41 | https://www.reddit.com/r/LocalLLaMA/comments/13n3ikw/is_there_such_a_thing_as_local_llamas_integrated/ | rustedbits | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 13n3ikw | false | null | t3_13n3ikw | /r/LocalLLaMA/comments/13n3ikw/is_there_such_a_thing_as_local_llamas_integrated/ | false | false | self | 17 | null |
Tired of errors | 2 | I have spent the whole day trying to work with a LlaMa model and have tried different versions of different models. I have also tried different version of the library to no avail. I keep getting the following error:
error loading model: unknown (magic, version) combination: 67676a74, 00000003; is this really a GGML fi... | 2023-05-20T17:49:11 | https://www.reddit.com/r/LocalLLaMA/comments/13n1cwg/tired_of_errors/ | Horcruxno13 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 13n1cwg | false | null | t3_13n1cwg | /r/LocalLLaMA/comments/13n1cwg/tired_of_errors/ | false | false | self | 2 | null |
Install Ooba textgen + llama.cpp with GPU support on Windows via WSL2 | 11 | 2023-05-20T17:45:03 | https://pastebin.com/GwSysUxj | _underlines_ | pastebin.com | 1970-01-01T00:00:00 | 0 | {} | 13n19cu | false | null | t3_13n19cu | /r/LocalLLaMA/comments/13n19cu/install_ooba_textgen_llamacpp_with_gpu_support_on/ | false | false | 11 | {'enabled': False, 'images': [{'id': 'OgFzGCIRw1ZxjMOSkfV1OiH-_nQiZl8rzSonmOAuhGs', 'resolutions': [{'height': 108, 'url': 'https://external-preview.redd.it/-WiKXADWH5lgU4gQv5fcDAQ9QKNBZTJ-D83BykIL2HA.jpg?width=108&crop=smart&auto=webp&s=df9c6a296446d05d873c629a30253398c4d29c1b', 'width': 108}], 'source': {'height': 15... | ||
Issues running oobabooga_windows after reinstall | 3 | [removed] | 2023-05-20T17:42:30 | [deleted] | 2023-05-20T18:09:55 | 0 | {} | 13n175h | false | null | t3_13n175h | /r/LocalLLaMA/comments/13n175h/issues_running_oobabooga_windows_after_reinstall/ | false | false | default | 3 | null | ||
Why do sometimes the generation of and answer become super slow? It's pretty consistent but sometimes It Just slows down randomly. What can be the issue? | 2 | 2023-05-20T17:24:58 | DarkMamm | i.imgur.com | 1970-01-01T00:00:00 | 0 | {} | 13n0sfu | false | null | t3_13n0sfu | /r/LocalLLaMA/comments/13n0sfu/why_do_sometimes_the_generation_of_and_answer/ | false | false | 2 | {'enabled': True, 'images': [{'id': 'i43IcbXpRSBIeaubyURCgWKMeNijEnBbwovsWaT0pBY', 'resolutions': [{'height': 81, 'url': 'https://external-preview.redd.it/UUijalk3-gWq561GeisZ5OW98-z-EBKAEJYRYd-tiys.jpg?width=108&crop=smart&auto=webp&s=7130d72105f5c32e6df488847fca7f583c508b38', 'width': 108}, {'height': 162, 'url': 'ht... | |||
Todd Lora horning up models. | 34 | I've been working on a LoRA using the dataset from the Todd Proxy (I think) dump from 4chan. This time trained on a 13b llama at 128 rank for 1 epoch. Works on llama derived 13bs. The goal is to de-censor models and make them write longer.
This run took 12 or so hours. There are 50k+ unique prompts in the dataset. I r... | 2023-05-20T16:13:56 | https://www.reddit.com/r/LocalLLaMA/comments/13mz27l/todd_lora_horning_up_models/ | a_beautiful_rhind | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 13mz27l | false | null | t3_13mz27l | /r/LocalLLaMA/comments/13mz27l/todd_lora_horning_up_models/ | false | false | self | 34 | {'enabled': False, 'images': [{'id': 'UVTttE2p7GzqDHO34XkKrnF4dV0HPW2BiXUCkfJMtiw', 'resolutions': [{'height': 46, 'url': 'https://external-preview.redd.it/ifMhJ82lD5gYaz0Uab43MOZPV7i8JVXp3l4T9EfyfcQ.jpg?width=108&crop=smart&auto=webp&s=81e5cb52a3d32b84fb88a159f6e69c44f6ed20cb', 'width': 108}, {'height': 93, 'url': 'ht... |
You can now relive the infamous "I'm sorry, Dave, I'm afraid I can't do that" scene | 21 | 2023-05-20T16:11:17 | https://www.reddit.com/gallery/13myzvb | belladorexxx | reddit.com | 1970-01-01T00:00:00 | 0 | {} | 13myzvb | false | null | t3_13myzvb | /r/LocalLLaMA/comments/13myzvb/you_can_now_relive_the_infamous_im_sorry_dave_im/ | false | false | 21 | null | ||
Looking for a way to simulate chaotic thought process | 6 | I'd like to simulate random thought process.
For example, if I ask "give me a random word", the answer I get is often pretty deterministic and limited to a narrow range of answers, even when playing with temperature, top\_p and top\_k which also have the side effect or missing the instruction's point completely if out... | 2023-05-20T15:51:27 | https://www.reddit.com/r/LocalLLaMA/comments/13myhno/looking_for_a_way_to_simulate_chaotic_thought/ | Thireus | self.LocalLLaMA | 2023-05-20T15:54:44 | 0 | {} | 13myhno | false | null | t3_13myhno | /r/LocalLLaMA/comments/13myhno/looking_for_a_way_to_simulate_chaotic_thought/ | false | false | self | 6 | null |
13B 4bit or 7B 8bits | 23 |
Hello, I was just wondering what would be the best in terms of speed or quality and what is for you the best compromise for the ehartford's Wizard Uncensored.
I use a ryzen 7600x, 16GB ddr4 3200 ram and a 8gb 3060ti | 2023-05-20T15:20:39 | https://www.reddit.com/r/LocalLLaMA/comments/13mxq66/13b_4bit_or_7b_8bits/ | PapyplO | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 13mxq66 | false | null | t3_13mxq66 | /r/LocalLLaMA/comments/13mxq66/13b_4bit_or_7b_8bits/ | false | false | self | 23 | null |
Devs and local LLM users | 1 | [removed] | 2023-05-20T15:17:33 | https://www.reddit.com/r/LocalLLaMA/comments/13mxnbq/devs_and_local_llm_users/ | drbh_ | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 13mxnbq | false | null | t3_13mxnbq | /r/LocalLLaMA/comments/13mxnbq/devs_and_local_llm_users/ | false | false | default | 1 | null |
Problems with ouput in the Text generation web UI | 1 | Hi,
I just installed the 4-bit LLaMa following this article:
[https://www.reddit.com/r/LocalLLaMA/comments/11o6o3f/how\_to\_install\_llama\_8bit\_and\_4bit/](https://www.reddit.com/r/LocalLLaMA/comments/11o6o3f/how_to_install_llama_8bit_and_4bit/)
After that, I downloaded the WizardLM-7B-uncensored-GPTQ model over ... | 2023-05-20T15:11:49 | https://www.reddit.com/r/LocalLLaMA/comments/13mxhxx/problems_with_ouput_in_the_text_generation_web_ui/ | Liparu | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 13mxhxx | false | null | t3_13mxhxx | /r/LocalLLaMA/comments/13mxhxx/problems_with_ouput_in_the_text_generation_web_ui/ | false | false | self | 1 | {'enabled': False, 'images': [{'id': 'VeQ7J7AHAfqAyuWDlt6KtqZAD2MPOHJxpZV7LzS8g9k', 'resolutions': [{'height': 58, 'url': 'https://external-preview.redd.it/ttp7PNmuZ-Sf15wnMLyeV0CqNYgpdylensMpV1pjvm4.jpg?width=108&crop=smart&auto=webp&s=3162912114c90470ebbdaaddbe50c701814f7db0', 'width': 108}, {'height': 116, 'url': 'h... |
LambdaLabs offering free compute for 30 days to train open models | 170 | 2023-05-20T14:56:30 | https://twitter.com/boborado/status/1659608452849897472?t=nweVmAjfSfklvHmoSr2txw&s=19 | 404underConstruction | twitter.com | 1970-01-01T00:00:00 | 0 | {} | 13mwupt | false | {'oembed': {'author_name': 'Robert Brooks IV', 'author_url': 'https://twitter.com/boborado', 'cache_age': 3153600000, 'height': None, 'html': '<blockquote class="twitter-video"><p lang="en" dir="ltr">I have 248 H100 SXM5s networked with 3200 Gbps Infiniband just sitting in front of me. Ready to go. <br><br>Who wants to... | t3_13mwupt | /r/LocalLLaMA/comments/13mwupt/lambdalabs_offering_free_compute_for_30_days_to/ | false | false | 170 | {'enabled': False, 'images': [{'id': 'Cw_4zUBGQYHysV7uArqTHfHBc9N8xecsov7KHph4RwQ', 'resolutions': [{'height': 108, 'url': 'https://external-preview.redd.it/he9R5AapkwWVGhk_MNyrLz0OvCJvG5SlKiC9OMprc98.jpg?width=108&crop=smart&auto=webp&s=705cb69d98de9220411d90ba5aed2da18f3d61d4', 'width': 108}], 'source': {'height': 14... | ||
Seeking Guidance on Leveraging Local Models and Optimizing GPU Utilization in containerized packages | 6 | Hello locallamas,
I'm reaching out to share my current experiences and solicit some advice from our collective wisdom. My background includes working as a DevOps Engineer and Cloud Engineer, currently pursuing a degree in InfoSec, and I have a keen interest in LLM. My journey with GPT models started in July '21 and I'... | 2023-05-20T14:53:14 | https://www.reddit.com/r/LocalLLaMA/comments/13mwnc1/seeking_guidance_on_leveraging_local_models_and/ | 2good4hisowngood | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 13mwnc1 | false | null | t3_13mwnc1 | /r/LocalLLaMA/comments/13mwnc1/seeking_guidance_on_leveraging_local_models_and/ | false | false | self | 6 | {'enabled': False, 'images': [{'id': 'jfeVG47nZdEkz9kXfW1CcS-Sy8l4DXGb9JErx6bLKfU', 'resolutions': [{'height': 58, 'url': 'https://external-preview.redd.it/Bixm6H31yqw0RCcD8LB0e8eIdtJeMUaF4N5ZipM_BQY.jpg?width=108&crop=smart&auto=webp&s=abf38332c5c00a919af5be75653a93473aa2e5fa', 'width': 108}, {'height': 116, 'url': 'h... |
Information v Reasoning | 2 | Just wondering : can we build models which are great at Reasoning, but with not too much Data?
Or do we need a large model to achieve both? | 2023-05-20T14:38:01 | https://www.reddit.com/r/LocalLLaMA/comments/13mvowi/information_v_reasoning/ | MrEloi | self.LocalLLaMA | 2023-05-20T14:48:03 | 0 | {} | 13mvowi | false | null | t3_13mvowi | /r/LocalLLaMA/comments/13mvowi/information_v_reasoning/ | false | false | self | 2 | null |
Which is the best option only for make questions to documents? | 2 | Hello dear, I wanted to ask you about what would be the most "lightweight" option when processing a text, a pdf or any content to generate an answer, even a basic one, based on questions? With lightweight I mean a model perhaps adjusted to ask only questions without consuming too many computer resources something simil... | 2023-05-20T14:35:44 | https://www.reddit.com/r/LocalLLaMA/comments/13mvjn2/which_is_the_best_option_only_for_make_questions/ | hwpoison | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 13mvjn2 | false | null | t3_13mvjn2 | /r/LocalLLaMA/comments/13mvjn2/which_is_the_best_option_only_for_make_questions/ | false | false | self | 2 | null |
Is this a good AI PC build? (RTX 4090, Ryzen 9 5950X, 32 GB RAM) | 13 | Hey everyone,
I found a [prebuilt PC on Amazon](https://www.amazon.de/-/en/gp/product/B0BLD176XL/ref=ox_sc_act_title_1?smid=AOHI1X68KO3E5&th=1) that caught my attention. I'm interested in running AI apps like Whisper, Vicuna, and Stable Diffusion on it. The GPU, an RTX 4090, looks great, but I'm unsure if the CPU is p... | 2023-05-20T12:35:59 | https://www.reddit.com/r/LocalLLaMA/comments/13mqtrf/is_this_a_good_ai_pc_build_rtx_4090_ryzen_9_5950x/ | Prince-of-Privacy | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 13mqtrf | false | null | t3_13mqtrf | /r/LocalLLaMA/comments/13mqtrf/is_this_a_good_ai_pc_build_rtx_4090_ryzen_9_5950x/ | false | false | self | 13 | null |
Will we always need to load entire models into RAM, or is it technically possible to only load part at a time? For both llama.cpp and PEFT DeepSpeed/FSDP | 11 | While llama.cpp and PEFT both have support for splitting tasks between CPU and GPU (splitting the model up between VRAM and RAM), as far as I know the model still has to be fully loaded into system RAM to do this. In the (near?) future, will it be possible to load only part of a model into RAM at a time as part of thi... | 2023-05-20T11:40:47 | https://www.reddit.com/r/LocalLLaMA/comments/13mpnaw/will_we_always_need_to_load_entire_models_into/ | SoylentMithril | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 13mpnaw | false | null | t3_13mpnaw | /r/LocalLLaMA/comments/13mpnaw/will_we_always_need_to_load_entire_models_into/ | false | false | self | 11 | null |
Models I can Run On Mac M1? | 1 | [removed] | 2023-05-20T10:50:45 | https://www.reddit.com/r/LocalLLaMA/comments/13monv5/models_i_can_run_on_mac_m1/ | buxrmp | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 13monv5 | false | null | t3_13monv5 | /r/LocalLLaMA/comments/13monv5/models_i_can_run_on_mac_m1/ | false | false | default | 1 | null |
Does anybody know ggml bin models that can speak Albanian, Macedonian, Bulgarian, Greek, Latvian, Estonian, Hungarian, Lithuanian, Swedish, Slovenian, Norwegian, Dutch? | 13 | I am interested in learning foreign languages and try to find suitable llama models. | 2023-05-20T10:13:07 | https://www.reddit.com/r/LocalLLaMA/comments/13mnzcz/does_anybody_know_ggml_bin_models_that_can_speak/ | Languages_Learner | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 13mnzcz | false | null | t3_13mnzcz | /r/LocalLLaMA/comments/13mnzcz/does_anybody_know_ggml_bin_models_that_can_speak/ | false | false | self | 13 | null |
WizardLM: Overview of the Evol-Instruct Method in a Short Video | 1 | [removed] | 2023-05-20T08:40:20 | https://www.reddit.com/r/LocalLLaMA/comments/13mmdgo/wizardlm_overview_of_the_evolinstruct_method_in_a/ | TrimTasker | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 13mmdgo | false | null | t3_13mmdgo | /r/LocalLLaMA/comments/13mmdgo/wizardlm_overview_of_the_evolinstruct_method_in_a/ | false | false | default | 1 | null |
LLama with internet access? | 14 | Hello,
I was researching this, but I can't quite figure it out, so I am wondering here: what are good pointers and such if I want to make a LLaMa-based chatbot with internet access?
I want to make a programming-specific assistant for writing scripts on command, and internet access would be vital to have all res... | 2023-05-20T07:28:18 | https://www.reddit.com/r/LocalLLaMA/comments/13ml4hq/llama_with_internet_access/ | MatchTerm69 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 13ml4hq | false | null | t3_13ml4hq | /r/LocalLLaMA/comments/13ml4hq/llama_with_internet_access/ | false | false | self | 14 | null |
Which models can you run at reasonable speeds on a laptop with 32 gb ram and a 3070? | 2 | I am a noob when it comes to LLMs I have tried some of the 13b models but inference is slow. Should I stick to 7b only? I tried have both bin and ggml models in oobabooga textgen with llama extension - gpt4xvicuna 4bit | 2023-05-20T06:57:22 | https://www.reddit.com/r/LocalLLaMA/comments/13mkkp5/which_models_can_you_run_at_reasonable_speeds_on/ | hihajab | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 13mkkp5 | false | null | t3_13mkkp5 | /r/LocalLLaMA/comments/13mkkp5/which_models_can_you_run_at_reasonable_speeds_on/ | false | false | self | 2 | null |
GLM-130B | 6 | The [https://github.com/THUDM/GLM-130B](https://github.com/THUDM/GLM-130B) model is trained on The Pile and can run on 4x3090 when quantized to INT4. I'm wondering if anyone knows if this model could (or has) been quantized using GPTQ, which gives some impressive performance gains over traditional quantization, and I'... | 2023-05-20T06:10:33 | https://www.reddit.com/r/LocalLLaMA/comments/13mjr7m/glm130b/ | tronathan | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 13mjr7m | false | null | t3_13mjr7m | /r/LocalLLaMA/comments/13mjr7m/glm130b/ | false | false | self | 6 | {'enabled': False, 'images': [{'id': '6Ie7e7foB4I5D5_FI7bjwwibKegZVK0-ck0nj9sW30E', 'resolutions': [{'height': 54, 'url': 'https://external-preview.redd.it/Q6iJ_TXNilZS4C-UlAS_xJgZUkipISpwpN0LzdQ9xoQ.jpg?width=108&crop=smart&auto=webp&s=914f410fd87e84c888df0f03e1205ae706c0a350', 'width': 108}, {'height': 108, 'url': 'h... |
Which model is the best for you? | 59 | New models are coming up almost every day & there are multiple places to compare models but they can't catch up with the speed as new models are created/improved.
So I create this thread for us to share our own experiences with models and share our personal opinions on what's the best for you, probably with a brief ex... | 2023-05-20T04:24:28 | https://www.reddit.com/r/LocalLLaMA/comments/13mhrqr/which_model_is_the_best_for_you/ | MichaelBui2812 | self.LocalLLaMA | 2023-05-20T06:09:19 | 0 | {} | 13mhrqr | false | null | t3_13mhrqr | /r/LocalLLaMA/comments/13mhrqr/which_model_is_the_best_for_you/ | false | false | self | 59 | null |
Running GPTQ model in Mac M1 2020? | 3 | Does anyone know if oobabooga (or llamacpp) has support for Mac M1 GPU to run the GPTQ model?
I tried following the instruction on [https://github.com/oobabooga/text-generation-webui/](https://github.com/oobabooga/text-generation-webui/) but I'm stuck at step `4. Install GPTQ-for-LLaMa and the monkey patch` when tryin... | 2023-05-20T03:20:41 | https://www.reddit.com/r/LocalLLaMA/comments/13mghl4/running_gptq_model_in_mac_m1_2020/ | MichaelBui2812 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 13mghl4 | false | null | t3_13mghl4 | /r/LocalLLaMA/comments/13mghl4/running_gptq_model_in_mac_m1_2020/ | false | false | self | 3 | {'enabled': False, 'images': [{'id': '_G-gSKJ6d76MYZo4vSvWdNh2at8JMNuyKQyW1pu20nA', 'resolutions': [{'height': 54, 'url': 'https://external-preview.redd.it/lFvMmISP8EAHICub_OWPEy11AbxgUX1RRM1JTh0yZ4w.jpg?width=108&crop=smart&auto=webp&s=76388a0ba09ee376b6607adcf5a46d0fb1a52936', 'width': 108}, {'height': 108, 'url': 'h... |
Offline llama | 71 | As you can see in the video, the PDF chatbot is working without internet. No OpenAI, no third party period. This is just one use case. I just wanted to put this feeler out there to see if anyone would be interested in this. If enough people are into it, I'll put the repo up on my github. Special thanks to u/The-Bloke a... | 2023-05-20T02:10:54 | https://www.reddit.com/r/LocalLLaMA/comments/13mf0bi/offline_llama/ | Jl_btdipsbro | self.LocalLLaMA | 2023-05-20T20:36:45 | 1 | {'gid_2': 1} | 13mf0bi | false | null | t3_13mf0bi | /r/LocalLLaMA/comments/13mf0bi/offline_llama/ | false | false | self | 71 | {'enabled': False, 'images': [{'id': 'kYiVOqUp5QqzFz2zdykgGVlDJrWLZ-60SRLc-25uGe0', 'resolutions': [{'height': 54, 'url': 'https://external-preview.redd.it/MX_8-a2o33x5NQXxKsQ3hUVrKZOajb3bkBW1jOM4SoI.jpg?width=108&crop=smart&auto=webp&s=211b2e62ef0d8eff45e402562b898c342838dbda', 'width': 108}, {'height': 108, 'url': 'h... |
Another new llama.cpp / GGML breaking change, affecting q4_0, q4_1 and q8_0 models. | 273 | Today llama.cpp committed another breaking GGML change: [https://github.com/ggerganov/llama.cpp/pull/1508](https://github.com/ggerganov/llama.cpp/pull/1508)
The good news is that this change brings slightly smaller file sizes (e.g 3.5GB instead of 4.0GB for 7B q4\_0, and 6.8GB vs 7.6GB for 13B q4\_0), and slightly fas... | 2023-05-20T00:50:33 | https://www.reddit.com/r/LocalLLaMA/comments/13md90j/another_new_llamacpp_ggml_breaking_change/ | The-Bloke | self.LocalLLaMA | 2023-05-20T14:53:57 | 0 | {} | 13md90j | false | null | t3_13md90j | /r/LocalLLaMA/comments/13md90j/another_new_llamacpp_ggml_breaking_change/ | false | false | self | 273 | {'enabled': False, 'images': [{'id': 'Fig9lAX5oTT6fjkgXnpKxVBgjOI3XTZhakodXjXzO8w', 'resolutions': [{'height': 54, 'url': 'https://external-preview.redd.it/hFotlrzJp6k0QqVntsE-7RbOiFBE3VpV_I7TC_2aBWc.jpg?width=108&crop=smart&auto=webp&s=19189c02435c7662523784bf3867293ec94c1e14', 'width': 108}, {'height': 108, 'url': 'h... |
Who is training their own models? | 6 | Many of the models out there are not for commercial use. Who out there are training models for commercial purposes from scratch? | 2023-05-19T23:34:15 | https://www.reddit.com/r/LocalLLaMA/comments/13mbh7s/who_is_training_their_own_models/ | jsfour | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 13mbh7s | false | null | t3_13mbh7s | /r/LocalLLaMA/comments/13mbh7s/who_is_training_their_own_models/ | false | false | self | 6 | null |
GramaLLama LORA - my first grammar Editor attempt | 18 | This 4-bit GPTQ LORA is my entry on a journey in creating a grammar "editor" aka a model to edit a text for grammar and English fluency.
The main requirement is that it doesn't try to change the style (doesn't start replacing words for no reason as many LLM would if given the task - including ChatGPT) and stays on foc... | 2023-05-19T23:25:36 | https://www.reddit.com/r/LocalLLaMA/comments/13mb9kq/gramallama_lora_my_first_grammar_editor_attempt/ | FPham | self.LocalLLaMA | 2023-05-20T07:38:19 | 0 | {} | 13mb9kq | false | null | t3_13mb9kq | /r/LocalLLaMA/comments/13mb9kq/gramallama_lora_my_first_grammar_editor_attempt/ | false | false | 18 | {'enabled': False, 'images': [{'id': '9ZlrsVubp-s5hQNFaYATOA4IkPMi8GslT4Qul8AwlZo', 'resolutions': [{'height': 58, 'url': 'https://external-preview.redd.it/DVVnDyZ-lj3PadUL5ND7VesjxxqgOf2d2QtfqQ8UHYk.jpg?width=108&crop=smart&auto=webp&s=8cab8ecd4b84824376e37cc52aa131a7bc9be44c', 'width': 108}, {'height': 116, 'url': 'h... | |
Hi community, I created a fork of microsoft's guidance and added llama-cpp-python support! | 39 | As I said in the title, I forked guidance and added llama-cpp-python support.
Here is the result of the RPG Character example with Manticore-13B:
The following is a character profile for an RPG game in JSON format.
\`\`\`json
{
"id": "e1f491f7-7ab8-4dac-8c20-c92b5e7d883d",
"description": "A quick and nimble fight... | 2023-05-19T22:52:53 | https://www.reddit.com/r/LocalLLaMA/comments/13magac/hi_community_i_created_a_fork_of_microsofts/ | FlowerPotTeaTime | self.LocalLLaMA | 2023-05-27T10:08:49 | 0 | {} | 13magac | false | null | t3_13magac | /r/LocalLLaMA/comments/13magac/hi_community_i_created_a_fork_of_microsofts/ | false | false | self | 39 | {'enabled': False, 'images': [{'id': 'IOx2rhFfqQomnY3YLw-ai67TUPNEeVr2tFf4MBeFkIM', 'resolutions': [{'height': 54, 'url': 'https://external-preview.redd.it/Dqcm95DKzVQuvhsa0DSznyZUrhnN6NjtOv70SYdICE4.jpg?width=108&crop=smart&auto=webp&s=77e3e92bf1bbd1a45957a6bc993486ddc2df99fd', 'width': 108}, {'height': 108, 'url': 'h... |
How to fix error: CUDA out of memory? | 1 | [removed] | 2023-05-19T22:17:12 | https://www.reddit.com/r/LocalLLaMA/comments/13m9jn4/how_to_fix_error_cuda_out_of_memory/ | realsupermain | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 13m9jn4 | false | null | t3_13m9jn4 | /r/LocalLLaMA/comments/13m9jn4/how_to_fix_error_cuda_out_of_memory/ | false | false | default | 1 | null |
Finally got a model running on my XTX, using llama.cpp | 60 | Not seen many people running on AMD hardware, so I figured I would try out this [llama.cpp OpenCL pull request](https://github.com/ggerganov/llama.cpp/pull/1459) on my Ubuntu 7900 XTX machine and document what I did to get it running.
I am seeing extremely good speeds compared to CPU (as one would hope). I tried `TheB... | 2023-05-19T21:39:43 | https://www.reddit.com/r/LocalLLaMA/comments/13m8li2/finally_got_a_model_running_on_my_xtx_using/ | TeakTop | self.LocalLLaMA | 2023-05-23T05:37:46 | 0 | {} | 13m8li2 | false | null | t3_13m8li2 | /r/LocalLLaMA/comments/13m8li2/finally_got_a_model_running_on_my_xtx_using/ | false | false | self | 60 | {'enabled': False, 'images': [{'id': '1_Vo1m7FsR1o8NrUw_sL_GaendLM5RTK4HdbByGKeRo', 'resolutions': [{'height': 54, 'url': 'https://external-preview.redd.it/kCAga5qlCW9WpV14m-1KClwSzc5s09EG5mOg2FdzPLk.jpg?width=108&crop=smart&auto=webp&s=a969b2652ea90b3ca892393673bc33211d2d8b87', 'width': 108}, {'height': 108, 'url': 'h... |
I need to train a LORA for my LLM project | 3 | So I’m working on a project that utilizes a LLM not sure which one yet but the main thing is I need to input a bunch of information to both give it a personality but more importantly I need to to be able to answer specific questions that are answered in the training documents. They also need to be answered basically ve... | 2023-05-19T21:30:34 | https://www.reddit.com/r/LocalLLaMA/comments/13m8d8w/i_need_to_train_a_lora_for_my_llm_project/ | opi098514 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 13m8d8w | false | null | t3_13m8d8w | /r/LocalLLaMA/comments/13m8d8w/i_need_to_train_a_lora_for_my_llm_project/ | false | false | self | 3 | null |
Any Discord groups for Local LLama? | 1 | [removed] | 2023-05-19T18:57:06 | https://www.reddit.com/r/LocalLLaMA/comments/13m4fh6/any_discord_groups_for_local_llama/ | NeverEndingToast | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 13m4fh6 | false | null | t3_13m4fh6 | /r/LocalLLaMA/comments/13m4fh6/any_discord_groups_for_local_llama/ | false | false | default | 1 | null |
Getting rid of </s> | 4 | Hi there!
Can somebody tell me why a few models end their replys with "</s>" and how I can stop it?
For example I tried this with Manticore-13B.ggmlv2.q5\_1.bin.
Started it with:
main -m models\Manticore-13B.ggmlv2.q5_1.bin --interactive-first --reverse-prompt "user:" --in-suffix "AI:" --color -c 2048 --temp 0.... | 2023-05-19T18:45:43 | https://www.reddit.com/r/LocalLLaMA/comments/13m44w6/getting_rid_of_s/ | honuvo | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 13m44w6 | false | null | t3_13m44w6 | /r/LocalLLaMA/comments/13m44w6/getting_rid_of_s/ | false | false | self | 4 | null |
Windows Batch File for running different models with Llama.cpp | 11 | In case some of you are not using the python web ui.
Here is a batch file that I use to test/run different models. Maybe it's helpful to those of you who run windows. The main batch file will call another batch file tailored to the specific model. I find it easier to test with than the python web UI.
Here is batch ... | 2023-05-19T18:37:10 | https://www.reddit.com/r/LocalLLaMA/comments/13m3wnd/windows_batch_file_for_running_different_models/ | ccss2 | self.LocalLLaMA | 2023-05-19T18:41:58 | 0 | {} | 13m3wnd | false | null | t3_13m3wnd | /r/LocalLLaMA/comments/13m3wnd/windows_batch_file_for_running_different_models/ | false | false | 11 | null | |
(HELP) Token Issue on Generation | 1 | Hello everyone,
I was wondering if I could get some help, I'm currently using this colab notebook ([https://colab.research.google.com/github/zetavg/LLaMA-LoRA-Tuner/blob/main/LLaMA\_LoRA.ipynb#scrollTo=iLygNTcHk0N8](https://colab.research.google.com/github/zetavg/LLaMA-LoRA-Tuner/blob/main/LLaMA_LoRA.ipynb#scrollTo=iL... | 2023-05-19T18:20:59 | https://www.reddit.com/r/LocalLLaMA/comments/13m3h0d/help_token_issue_on_generation/ | pkkvu | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 13m3h0d | false | null | t3_13m3h0d | /r/LocalLLaMA/comments/13m3h0d/help_token_issue_on_generation/ | false | false | 1 | {'enabled': False, 'images': [{'id': 'nkhh65ujo5BznFJFojoMPaKjGuLSpPj6KGhRov-ykOg', 'resolutions': [{'height': 108, 'url': 'https://external-preview.redd.it/MrcDZx2izDY9ERwgWmMS-Hm2M3GEKZgeYLDszSh-KrQ.jpg?width=108&crop=smart&auto=webp&s=4b647239f77bf713f4a6209cfa4867351c055fd9', 'width': 108}, {'height': 216, 'url': '... | |
Question: Hardware development for large transformer models.... ?? | 7 | With very large models in the 10-100 multi billion range, is there anybody who developing hardware that can run tem on a single chip?
It seems like NPU, GPU and TPU architectures may be too general purpose. The math for running these models seems to be very limited, and could probably be embedded with the memory chip... | 2023-05-19T17:00:27 | https://www.reddit.com/r/LocalLLaMA/comments/13m1b06/question_hardware_development_for_large/ | BackwardGoose | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 13m1b06 | false | null | t3_13m1b06 | /r/LocalLLaMA/comments/13m1b06/question_hardware_development_for_large/ | false | false | self | 7 | null |
Has anyone mixed a P40 with a 3090/4090 just to add more GPU memory? | 26 | This question is mainly aimed at inferencing: I know the P40's are much slower, but has anyone added one just for the added memory to run larger models? Since only one GPU processor seems to be used at a time during inference and gaming won't really use the second card, it feels wasteful to spend $800 on another 3090 j... | 2023-05-19T16:58:10 | https://www.reddit.com/r/LocalLLaMA/comments/13m18nk/has_anyone_mixed_a_p40_with_a_30904090_just_to/ | LetMeGuessYourAlts | self.LocalLLaMA | 2023-05-19T17:04:17 | 0 | {} | 13m18nk | false | null | t3_13m18nk | /r/LocalLLaMA/comments/13m18nk/has_anyone_mixed_a_p40_with_a_30904090_just_to/ | false | false | self | 26 | null |
Why can't LLaMA based models edit/rewrite? Maybe need a specific prompt? | 14 | You can ask Chat GPT or Bard to edit or rewrite the following to make it whatever.
However, all the LLaMA based models I tried, it just outputs what might come after the writing instead of rewriting it.
Does anyone have a specific prompt that I can use for edit/rewrite purpose?
Thanks! | 2023-05-19T16:57:59 | https://www.reddit.com/r/LocalLLaMA/comments/13m18i0/why_cant_llama_based_models_editrewrite_maybe/ | jl303 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 13m18i0 | false | null | t3_13m18i0 | /r/LocalLLaMA/comments/13m18i0/why_cant_llama_based_models_editrewrite_maybe/ | false | false | self | 14 | null |
As a large language model... | 151 | 2023-05-19T16:42:11 | https://imgur.com/gallery/Mz5N5ug | SlowMovingTarget | imgur.com | 1970-01-01T00:00:00 | 0 | {} | 13m0tjd | false | {'oembed': {'author_name': '', 'description': 'Discover topics like ai, hal9000, and the magic of the internet at Imgur, a community powered entertainment destination. Lift your spirits with funny jokes, trending memes, entertaining gifs, inspiring stories, viral videos, and so much more from users like kytayn.', 'heig... | t3_13m0tjd | /r/LocalLLaMA/comments/13m0tjd/as_a_large_language_model/ | false | false | 151 | {'enabled': False, 'images': [{'id': 'RypgvR0cosSRy5kKNRUFcUr2QiGLWa_CZmmHXbLySUs', 'resolutions': [{'height': 67, 'url': 'https://external-preview.redd.it/MTnkf11SmZ25kTBLVCGpzlM3_qGTlY9bxmvry-tidig.jpg?width=108&crop=smart&auto=webp&s=1a84f4d7eaa52522cb8c13d5d032cdd44acb0338', 'width': 108}, {'height': 135, 'url': 'h... | ||
Possible to run a 30B quantized model on 10GB VRAM + 32GB RAM | 11 | I just read a post about a modification that lets you share model loading between video card and RAM+CPU, I think it’s GGML but not sure. Does this mean I could (slowly) run a 30B model quantized? I have a Ryzen 5600x by the way, if that matters. | 2023-05-19T16:25:09 | https://www.reddit.com/r/LocalLLaMA/comments/13m0cv6/possible_to_run_a_30b_quantized_model_on_10gb/ | maxiedaniels | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 13m0cv6 | false | null | t3_13m0cv6 | /r/LocalLLaMA/comments/13m0cv6/possible_to_run_a_30b_quantized_model_on_10gb/ | false | false | self | 11 | null |
Hyena Hierarchy: Towards Larger Convolutional Language Models | 43 | Those of you following everything closely has anyone come across open source projects attempting to leverage the recent Hyena development. My understanding is it is likely a huge breakthrough in efficiency for LLMs and should allow models to run on significantly smaller hardware and memory requirements. | 2023-05-19T15:59:56 | https://hazyresearch.stanford.edu/blog/2023-03-07-hyena | alchemist1e9 | hazyresearch.stanford.edu | 1970-01-01T00:00:00 | 0 | {} | 13lznoc | false | null | t3_13lznoc | /r/LocalLLaMA/comments/13lznoc/hyena_hierarchy_towards_larger_convolutional/ | false | false | 43 | {'enabled': False, 'images': [{'id': '-WHgGLJANkDpubg8JwSLJ_kMgGHdyAiWnD4mQMVCLm0', 'resolutions': [{'height': 108, 'url': 'https://external-preview.redd.it/yIFZCOsTxmZV5L1s0iCvqnvaDHMoCFUEEEsPkVLz1sA.jpg?width=108&crop=smart&auto=webp&s=fd10df8933b1c9751ea7d0fcf20f1e54587a02ce', 'width': 108}, {'height': 216, 'url': '... | |
ERROR: Failed building wheel for llama-cpp-python | 1 | [removed] | 2023-05-19T15:43:08 | https://www.reddit.com/r/LocalLLaMA/comments/13lz70j/error_failed_building_wheel_for_llamacpppython/ | Accomplished-Jury-87 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 13lz70j | false | null | t3_13lz70j | /r/LocalLLaMA/comments/13lz70j/error_failed_building_wheel_for_llamacpppython/ | false | false | default | 1 | null |
Let's talk about prompt styles and their documentation? | 36 | I wanted to discuss this because it seems quite important to use the models. Maybe I just don't get it, but to me it seems models don't always come with clear instructions how the model should be used. It may seem sufficient but when you dive in deeper this is not a topic that should have *any* uncertainty, given how m... | 2023-05-19T14:23:11 | https://www.reddit.com/r/LocalLLaMA/comments/13lwwux/lets_talk_about_prompt_styles_and_their/ | involviert | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 13lwwux | false | null | t3_13lwwux | /r/LocalLLaMA/comments/13lwwux/lets_talk_about_prompt_styles_and_their/ | false | false | self | 36 | null |
Full fine-tunes of PyTorch models? | 3 | What tools are folks using to do full fine-tunes (rather than LoRA + merges) of Llama or Vicuna model these days? I can find a lot of easy ones for LoRA+merge (text-generation-webui, [https://github.com/tloen/alpaca-lora](https://github.com/tloen/alpaca-lora)), but haven't found ones for a full fine-tune. | 2023-05-19T14:13:40 | https://www.reddit.com/r/LocalLLaMA/comments/13lwmva/full_finetunes_of_pytorch_models/ | Fun_Tangerine_1086 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 13lwmva | false | null | t3_13lwmva | /r/LocalLLaMA/comments/13lwmva/full_finetunes_of_pytorch_models/ | false | false | self | 3 | {'enabled': False, 'images': [{'id': 'UYKFmPP2-DbydEGwkKwhmsl0pQLnyYpsjH81jBvoAiE', 'resolutions': [{'height': 54, 'url': 'https://external-preview.redd.it/e1PIDIPluZiwhzcHre12fX8Sn4HFxRl4QyZRNw0sDTs.jpg?width=108&crop=smart&auto=webp&s=26736a3bfdaecde95315f2b2f406eb18e314a438', 'width': 108}, {'height': 108, 'url': 'h... |
WizardVIcunaAlpacaOasstMegaKoalaGpt4Lora was released | 3 | [removed] | 2023-05-19T14:09:16 | https://huggingface.co/nikitastaf1996/WizardVIcunaAlpacaOasstMegaKoalaGpt4Lora | nikitastaf1996 | huggingface.co | 1970-01-01T00:00:00 | 0 | {} | 13lwiex | false | null | t3_13lwiex | /r/LocalLLaMA/comments/13lwiex/wizardvicunaalpacaoasstmegakoalagpt4lora_was/ | false | false | default | 3 | null |
Run MPT-7B-Instruct on Google Colab? | 7 | I wanted to know has anyone tried to run MPT-7B-Instruct on Google Colab?
If so can they please share the code? I am running into the tried to allocate more RAM error
If in any other platform (eg. Kaggle) then how? | 2023-05-19T13:48:58 | https://www.reddit.com/r/LocalLLaMA/comments/13lvzkc/run_mpt7binstruct_on_google_colab/ | AdRealistic03 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 13lvzkc | false | null | t3_13lvzkc | /r/LocalLLaMA/comments/13lvzkc/run_mpt7binstruct_on_google_colab/ | false | false | self | 7 | null |
Training Vicuna based on custom text/web pages | 20 | Hello,
I currently use Vicuna 13B (created delta based on llama). It works well. However, I am interested in training the model / feeding it with custom texts (own private documents). What do you think the best way is to do it? I currently have Oobabooga.
I am a bit new to it, so not sure how to start (a tutorial w... | 2023-05-19T12:26:47 | https://www.reddit.com/r/LocalLLaMA/comments/13lu13k/training_vicuna_based_on_custom_textweb_pages/ | guyromb | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 13lu13k | false | null | t3_13lu13k | /r/LocalLLaMA/comments/13lu13k/training_vicuna_based_on_custom_textweb_pages/ | false | false | self | 20 | null |
Seeking clarification about LLM's, Tools, etc.. for developers. | 20 | As android developer (professionally working 4years\~) and "AI" enthusiast, for long time i wanted to study ML/BigData to enter this world but was held back difficulty a steep learning curve.
Been lurking and using (basic stuff) stabledifussion (A1111) since august, and LLM's since about march, without python and ML l... | 2023-05-19T11:30:49 | https://www.reddit.com/r/LocalLLaMA/comments/13lssoi/seeking_clarification_about_llms_tools_etc_for/ | Clicker7 | self.LocalLLaMA | 2023-05-21T11:02:07 | 0 | {} | 13lssoi | false | null | t3_13lssoi | /r/LocalLLaMA/comments/13lssoi/seeking_clarification_about_llms_tools_etc_for/ | false | false | self | 20 | null |
Get my GPU involved? | 0 | I'm using koboldcpp-1.23.1 To run GGML models, and my GPU is never involved. Ryzen 7 5700U. Is this something I can fix? Am I doing something obviously wrong? | 2023-05-19T11:25:28 | https://www.reddit.com/r/LocalLLaMA/comments/13lsopu/get_my_gpu_involved/ | Innomen | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 13lsopu | false | null | t3_13lsopu | /r/LocalLLaMA/comments/13lsopu/get_my_gpu_involved/ | false | false | self | 0 | null |
Can you use LoRA unsupervised? | 1 | I’d now like to add a ‘concept’ or a set of information from a Knowledge Base to an instruct-tuned model. I could set up a series of prompts, but ultimately I don’t want it to reproduce the information, I want the model to understand it and use it creatively.
Is there a way to use LoRA to teach it a concept in an unsu... | 2023-05-19T11:08:02 | https://www.reddit.com/r/LocalLLaMA/comments/13lsbzj/can_you_use_lora_unsupervised/ | amemingfullife | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 13lsbzj | false | null | t3_13lsbzj | /r/LocalLLaMA/comments/13lsbzj/can_you_use_lora_unsupervised/ | false | false | self | 1 | null |
q4_0, q5_1? | 3 | New learner here! What do these mean in the context of models? I see them all over the place, but I've never seen any explanation.
EDIT: Thanks a lot everybody, now I understand! | 2023-05-19T09:51:33 | https://www.reddit.com/r/LocalLLaMA/comments/13lqua2/q4_0_q5_1/ | qwerty44279 | self.LocalLLaMA | 2023-05-19T13:24:31 | 0 | {} | 13lqua2 | false | null | t3_13lqua2 | /r/LocalLLaMA/comments/13lqua2/q4_0_q5_1/ | false | false | self | 3 | null |
Using iGPU for llama models? | 0 | [deleted] | 2023-05-19T08:35:33 | [deleted] | 2023-05-19T08:52:26 | 0 | {} | 13lpgdf | false | null | t3_13lpgdf | /r/LocalLLaMA/comments/13lpgdf/using_igpu_for_llama_models/ | false | false | default | 0 | null | ||
If you previously had bad results with Stable Vicuna outside of ooba, fix the special_tokens_map... | 19 | https://huggingface.co/CarperAI/stable-vicuna-13b-delta/blob/main/special_tokens_map.json
I'm not sure how this could've happened or if it could indicate some other issue, but bos_token is wrong at least
```
{
"bos_token": "</s>",
"eos_token": "</s>",
"pad_token": "[PAD]",
"unk_token": "</s>"
}
```
should be
... | 2023-05-19T08:06:17 | https://www.reddit.com/r/LocalLLaMA/comments/13lowzm/if_you_previously_had_bad_results_with_stable/ | phree_radical | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 13lowzm | false | null | t3_13lowzm | /r/LocalLLaMA/comments/13lowzm/if_you_previously_had_bad_results_with_stable/ | false | false | self | 19 | {'enabled': False, 'images': [{'id': '0CCfFmTZ60XSoL0dJ_ynCVdsBH-fmk8Xc8-W9nJPLRo', 'resolutions': [{'height': 58, 'url': 'https://external-preview.redd.it/1bUrRYhOdPoMUs38gJ3ZHAcizt_RdcA33DfakExdQj8.jpg?width=108&crop=smart&auto=webp&s=b3dcbf82fa79313c69c0fd1509879605b7de7e6b', 'width': 108}, {'height': 116, 'url': 'h... |
Where's my new model? | 7 | 2023-05-19T07:27:18 | ArmoredBattalion | i.redd.it | 1970-01-01T00:00:00 | 0 | {} | 13lo7gx | false | null | t3_13lo7gx | /r/LocalLLaMA/comments/13lo7gx/wheres_my_new_model/ | true | false | nsfw | 7 | {'enabled': True, 'images': [{'id': 'AAZlZI3So2meQRXQDIIjG0StU43Z70qqGwPFKZd0wvI', 'resolutions': [{'height': 144, 'url': 'https://preview.redd.it/yq5feiiwpq0b1.jpg?width=108&crop=smart&auto=webp&s=45722aac1aa128a8da490930ecdc8525d54fa950', 'width': 108}, {'height': 288, 'url': 'https://preview.redd.it/yq5feiiwpq0b1.jp... | ||
Looking to selfhost Llama on remote server, could use some help | 3 | My Goal: run 30b GPTQ Openassistant on a remote server with api access.
Link to model: [https://huggingface.co/TheBloke/OpenAssistant-SFT-7-Llama-30B-GPTQ](https://huggingface.co/TheBloke/OpenAssistant-SFT-7-Llama-30B-GPTQ)
My progess: Docker container running text-gen-webui with --public-api flag on to use it as... | 2023-05-19T07:00:55 | https://www.reddit.com/r/LocalLLaMA/comments/13lnpgt/looking_to_selfhost_llama_on_remote_server_could/ | jules241 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 13lnpgt | false | null | t3_13lnpgt | /r/LocalLLaMA/comments/13lnpgt/looking_to_selfhost_llama_on_remote_server_could/ | false | false | self | 3 | {'enabled': False, 'images': [{'id': '0_MVpXePzAudCyIn3uCjoPJqV69xuDEEw1P6fohf8tE', 'resolutions': [{'height': 58, 'url': 'https://external-preview.redd.it/bC3KWSlhdErNo61Ej7icWH7guz2c0GuhkKI0RvumXoE.jpg?width=108&crop=smart&auto=webp&s=3ed6d1099b03f9a3b3beddf35162b07d2c0ae313', 'width': 108}, {'height': 116, 'url': 'h... |
4060 Ti 16GB in July or 3060 12GB now? | 12 | Is the extra 4GB of VRAM worth the wait and the price difference (~100$)? As far as I know both can only run 13B 4bit models. | 2023-05-19T05:56:01 | https://www.reddit.com/r/LocalLLaMA/comments/13lmjjc/4060_ti_16gb_in_july_or_3060_12gb_now/ | regunakyle | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 13lmjjc | false | null | t3_13lmjjc | /r/LocalLLaMA/comments/13lmjjc/4060_ti_16gb_in_july_or_3060_12gb_now/ | false | false | self | 12 | null |
Local model response time? | 0 | How long is a response from a locally downloaded model expected to take. I'm running wizard-mega-13B.ggml.q5\_1.bin from disk and it takes as long as 2 minutes to get a response. | 2023-05-19T02:31:46 | https://www.reddit.com/r/LocalLLaMA/comments/13liju9/local_model_response_time/ | Jl_btdipsbro | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 13liju9 | false | null | t3_13liju9 | /r/LocalLLaMA/comments/13liju9/local_model_response_time/ | false | false | self | 0 | null |
Is there a place for stupid questions? | 3 | [deleted] | 2023-05-19T01:17:57 | [deleted] | 1970-01-01T00:00:00 | 0 | {} | 13lgwog | false | null | t3_13lgwog | /r/LocalLLaMA/comments/13lgwog/is_there_a_place_for_stupid_questions/ | false | false | default | 3 | null | ||
What is the smallest ggml model available? | 52 | I'm a bit obsessed with the idea that we can have an LLM “demoscene” but with small models, and I already tried a few 1B fresh models, but I want to go even smaller. Have anyone seen ggml models less than 1B? I want to evaluate their performance. | 2023-05-18T22:57:47 | https://www.reddit.com/r/LocalLLaMA/comments/13ldnlw/what_is_the_smallest_ggml_model_available/ | Shir_man | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 13ldnlw | false | null | t3_13ldnlw | /r/LocalLLaMA/comments/13ldnlw/what_is_the_smallest_ggml_model_available/ | false | false | self | 52 | null |
Equipment needed to run Dolly 2.0 3b model? | 1 | I'm trying to build a very simple chat bot for a business that needs to be able to understand and talk about a few hundred lines of data. It doesn't need to know about any external data, and would even be preferable not to, but it would be great if I can fine tune the model to learn information fed to it from the user.... | 2023-05-18T22:04:40 | https://www.reddit.com/r/LocalLLaMA/comments/13lccm4/equipment_needed_to_run_dolly_20_3b_model/ | TheNomadicAspie | self.LocalLLaMA | 2023-05-18T22:09:02 | 0 | {} | 13lccm4 | false | null | t3_13lccm4 | /r/LocalLLaMA/comments/13lccm4/equipment_needed_to_run_dolly_20_3b_model/ | false | false | self | 1 | null |
Manticore 13B - updated model from OpenAccess AI Collective | 120 | # OpenAccess AI Collective have just released Manticore 13B
An updated version of Wizard Mega 13B
Available for instant demo on a GGML-powered space at:
[https://huggingface.co/spaces/openaccess-ai-collective/manticore-ggml](https://huggingface.co/spaces/openaccess-ai-collective/manticore-ggml)
Available for local... | 2023-05-18T21:49:01 | https://www.reddit.com/r/LocalLLaMA/comments/13lbyiw/manticore_13b_updated_model_from_openaccess_ai/ | The-Bloke | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 13lbyiw | false | null | t3_13lbyiw | /r/LocalLLaMA/comments/13lbyiw/manticore_13b_updated_model_from_openaccess_ai/ | false | false | self | 120 | {'enabled': False, 'images': [{'id': '_CArfIRMSglzqoNebT4bvXRqZjSX6dMbq8siIyBeSlQ', 'resolutions': [{'height': 58, 'url': 'https://external-preview.redd.it/T2ckplnJRCJt6Sx0qCx7mRAsqA-IsyuVVEbcMhHmrJw.jpg?width=108&crop=smart&auto=webp&s=14116147869d4de3e20df891cd959520caa7e65c', 'width': 108}, {'height': 116, 'url': 'h... |
Possibility of deploying local LLM on 7 yr old laptop | 9 | Hi,
I have 7 yr old Thinkpad P50 laptop with following specs:
• Processor: Intel Core i7-6820HQ processor (8MB Cache, Up to 3.6 Ghz)
• Operating System: Windows 10 Pro 64/Ubuntu 18
• Display: 15.6 FHD(1920x1080) IPS Non-Touch
• Memory: 64GB(16x4) DDR4 2133MHz SoDIMM
• Graphic Card: NVIDIA Quadro M1000M 2GB
• Base: P5... | 2023-05-18T21:02:24 | https://www.reddit.com/r/LocalLLaMA/comments/13lasa6/possibility_of_deploying_local_llm_on_7_yr_old/ | mindseye73 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 13lasa6 | false | null | t3_13lasa6 | /r/LocalLLaMA/comments/13lasa6/possibility_of_deploying_local_llm_on_7_yr_old/ | false | false | self | 9 | null |
Pygmalion has released the new Pygmalion 13B and Metharme 13B! These are LLaMA based models for chat and instruction. | 185 | [removed] | 2023-05-18T20:57:07 | https://www.reddit.com/r/LocalLLaMA/comments/13lan4q/pygmalion_has_released_the_new_pygmalion_13b_and/ | Creative-Rest-2112 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 13lan4q | false | null | t3_13lan4q | /r/LocalLLaMA/comments/13lan4q/pygmalion_has_released_the_new_pygmalion_13b_and/ | false | false | default | 185 | null |
How to use MetaIX/GPT4-X-Alpasta-30b-4bit with oobabooga ? | 2 | [removed] | 2023-05-18T19:48:46 | https://www.reddit.com/r/LocalLLaMA/comments/13l8vni/how_to_use_metaixgpt4xalpasta30b4bit_with/ | karljoaquin | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 13l8vni | false | null | t3_13l8vni | /r/LocalLLaMA/comments/13l8vni/how_to_use_metaixgpt4xalpasta30b4bit_with/ | false | false | default | 2 | null |
Help with Random Characters and Words on Output | 1 | [deleted] | 2023-05-18T18:55:33 | [deleted] | 1970-01-01T00:00:00 | 0 | {} | 13l7hk8 | false | null | t3_13l7hk8 | /r/LocalLLaMA/comments/13l7hk8/help_with_random_characters_and_words_on_output/ | false | false | default | 1 | null | ||
Introducing TokenHawk: Local Llama Inference in WebGPU | 44 | 2023-05-18T17:20:36 | https://github.com/kayvr/token-hawk | kayvr | github.com | 1970-01-01T00:00:00 | 0 | {} | 13l4z2e | false | null | t3_13l4z2e | /r/LocalLLaMA/comments/13l4z2e/introducing_tokenhawk_local_llama_inference_in/ | false | false | 44 | {'enabled': False, 'images': [{'id': '8CZtAnMJkXfTRQHPKKSrVsh6Mmb5cAAzsVRnNi9Zs38', 'resolutions': [{'height': 54, 'url': 'https://external-preview.redd.it/S3ftbHh44BeTjBgKAp9PeJHQCHJP2VKYrsBGRGYccQk.jpg?width=108&crop=smart&auto=webp&s=ccdcccd54e15125e5a437d711585fb0dba3d707d', 'width': 108}, {'height': 108, 'url': 'h... |
Subsets and Splits
No community queries yet
The top public SQL queries from the community will appear here once available.