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
Whats the best way to run LLaMA on a M1 Max? Best Model?
6
Ive been using a couple but ive been kind of randomly using them. And im not sure im using the best method to run them. Anyone want to share their experience on m1 ?
2023-06-22T04:04:38
https://www.reddit.com/r/LocalLLaMA/comments/14fsu1c/whats_the_best_way_to_run_llama_on_a_m1_max_best/
MumeiNoName
self.LocalLLaMA
1970-01-01T00:00:00
0
{}
14fsu1c
false
null
t3_14fsu1c
/r/LocalLLaMA/comments/14fsu1c/whats_the_best_way_to_run_llama_on_a_m1_max_best/
false
false
self
6
null
New subreddit for AI prompt requests
2
[removed]
2023-06-22T03:37:09
https://www.reddit.com/r/LocalLLaMA/comments/14fsaaq/new_subreddit_for_ai_prompt_requests/
No-Transition3372
self.LocalLLaMA
1970-01-01T00:00:00
0
{}
14fsaaq
false
null
t3_14fsaaq
/r/LocalLLaMA/comments/14fsaaq/new_subreddit_for_ai_prompt_requests/
false
false
default
2
null
What models are GPT4All-J compatible?
7
[removed]
2023-06-22T03:02:25
https://www.reddit.com/r/LocalLLaMA/comments/14frl6s/what_models_are_gpt4allj_compatible/
card_chase
self.LocalLLaMA
1970-01-01T00:00:00
0
{}
14frl6s
false
null
t3_14frl6s
/r/LocalLLaMA/comments/14frl6s/what_models_are_gpt4allj_compatible/
false
false
default
7
null
How to Use Langchain with Exllama?
9
Is that possible to use Langchain with Exllama? I'd appreciate any code snippet.
2023-06-22T02:06:45
https://www.reddit.com/r/LocalLLaMA/comments/14fqfdu/how_to_use_langchain_with_exllama/
jl303
self.LocalLLaMA
1970-01-01T00:00:00
0
{}
14fqfdu
false
null
t3_14fqfdu
/r/LocalLLaMA/comments/14fqfdu/how_to_use_langchain_with_exllama/
false
false
self
9
null
Automatic Stock Analysis - Scraping Twitter + GPT4 (or llama)
1
2023-06-22T01:51:40
https://www.linkedin.com/posts/kristintynski_gpt4-gpt4-gpt35turbo16k-activity-7077372458848145408-xcx7?utm_source=share&utm_medium=member_desktop
transtwin
linkedin.com
1970-01-01T00:00:00
0
{}
14fq3w0
false
null
t3_14fq3w0
/r/LocalLLaMA/comments/14fq3w0/automatic_stock_analysis_scraping_twitter_gpt4_or/
false
false
default
1
null
Yet another fun test (astronomy)
6
All models were run with ooba/llama-precise + default model-specific instruct prompt that ooba chose. The data part is from Wolfram. Prompt: >Which planets can I see tonight from Honolulu on 2023-03-25 at precisely 9:00pm UTC-10? Use the data below to answer. > >planet | altitude | azimuth > >Mercury | -23° 5...
2023-06-22T00:47:36
https://www.reddit.com/r/LocalLLaMA/comments/14foqxx/yet_another_fun_test_astronomy/
Mizstik
self.LocalLLaMA
1970-01-01T00:00:00
0
{}
14foqxx
false
null
t3_14foqxx
/r/LocalLLaMA/comments/14foqxx/yet_another_fun_test_astronomy/
false
false
self
6
null
Prompt engineering: What are some good prompts you have found to make the chatbot emulate personalities?
16
I’m trying to test different LLMs on who can emulate personalities most accurately and was wondering if anyone has good ideas of how to compose the prompt so that the LLMs behaves the way we expect. The personality will be given as a description within the prompt context/token itself so we’re not trying to emulate any ...
2023-06-21T22:43:37
https://www.reddit.com/r/LocalLLaMA/comments/14flwpw/prompt_engineering_what_are_some_good_prompts_you/
RepresentativeOdd276
self.LocalLLaMA
1970-01-01T00:00:00
0
{}
14flwpw
false
null
t3_14flwpw
/r/LocalLLaMA/comments/14flwpw/prompt_engineering_what_are_some_good_prompts_you/
false
false
self
16
null
Bright Eye: free mobile AI app to generate art and text.(GPT-4 powered)
0
[removed]
2023-06-21T22:21:32
https://www.reddit.com/r/LocalLLaMA/comments/14flddm/bright_eye_free_mobile_ai_app_to_generate_art_and/
Psychological_Ad4766
self.LocalLLaMA
1970-01-01T00:00:00
0
{}
14flddm
false
null
t3_14flddm
/r/LocalLLaMA/comments/14flddm/bright_eye_free_mobile_ai_app_to_generate_art_and/
false
false
default
0
null
Finetune bug with Llama 13, 30 and 65B
6
Hey all! I am trying to finetune the Llama models using the stanford alpaca repo. I can successfully finetune a 7B model, but all of the larger models have a strange issue where the initial loss is massive (1e5) and immediately drops to 0.0 for the rest of the finetune process. The model that I get at the end of the ...
2023-06-21T22:19:39
https://www.reddit.com/r/LocalLLaMA/comments/14flbky/finetune_bug_with_llama_13_30_and_65b/
Svvance
self.LocalLLaMA
1970-01-01T00:00:00
0
{}
14flbky
false
null
t3_14flbky
/r/LocalLLaMA/comments/14flbky/finetune_bug_with_llama_13_30_and_65b/
false
false
self
6
null
Hearing Scheduled for Tomorrow with CEO of HuggingFace - Artificial Intelligence: Advancing Innovation Towards the National Interest
1
[deleted]
2023-06-21T22:19:01
[deleted]
1970-01-01T00:00:00
0
{}
14flazk
false
null
t3_14flazk
/r/LocalLLaMA/comments/14flazk/hearing_scheduled_for_tomorrow_with_ceo_of/
false
false
default
1
null
Hearing Scheduled for Tomorrow with Hugging Face CEO - Artificial Intelligence: Advancing Innovation Towards the National Interest
57
[Stream it here June 22, 2023 10:00AM EST](https://www.youtube.com/live/7s_Wv5VklVA) [Artificial Intelligence: Advancing Innovation Towards the National Interest](https://science.house.gov/hearings?ID=441AF8AB-7065-45C8-81E0-F386158D625C) [Hearing Charter \[PDF\]](https://republicans-science.house.gov/_cache/files/f/...
2023-06-21T22:06:15
https://www.reddit.com/r/LocalLLaMA/comments/14fkzcj/hearing_scheduled_for_tomorrow_with_hugging_face/
Basic_Description_56
self.LocalLLaMA
2023-06-22T05:09:50
0
{}
14fkzcj
false
null
t3_14fkzcj
/r/LocalLLaMA/comments/14fkzcj/hearing_scheduled_for_tomorrow_with_hugging_face/
false
false
https://b.thumbs.redditm…UXWNf--2r7WE.jpg
57
{'enabled': False, 'images': [{'id': 'qAQ0onF1XqFRiBxHoF5saS8LpmACVTHzxE9cK3sUNhg', 'resolutions': [{'height': 60, 'url': 'https://external-preview.redd.it/LisAhqObgoc8MwcSz5KXOWBRW66ZQFIsvFs3HA5XiJQ.jpg?width=108&crop=smart&auto=webp&s=91d426842e7a66f7718ba0a392614ce8d1bb4b04', 'width': 108}, {'height': 121, 'url': 'h...
Any arch Linux users with AMD GPU?
10
Hi, I'm trying to get a LLM run under arch Linux with a AMD GPU? But for now without success. Anybody here who can help? Tried oobabooga but I was not able to get it to run with rocm. How is your experience so far?
2023-06-21T21:47:47
https://www.reddit.com/r/LocalLLaMA/comments/14fkibn/any_arch_linux_users_with_amd_gpu/
RudeboyRudolfo
self.LocalLLaMA
1970-01-01T00:00:00
0
{}
14fkibn
false
null
t3_14fkibn
/r/LocalLLaMA/comments/14fkibn/any_arch_linux_users_with_amd_gpu/
false
false
self
10
null
Any arch Linux users here with and GPU?
1
[deleted]
2023-06-21T21:43:58
[deleted]
1970-01-01T00:00:00
0
{}
14fkemo
false
null
t3_14fkemo
/r/LocalLLaMA/comments/14fkemo/any_arch_linux_users_here_with_and_gpu/
false
false
default
1
null
How to download models from HF from terminal without git LFS or sudo
0
[deleted]
2023-06-21T20:30:47
[deleted]
1970-01-01T00:00:00
0
{}
14fiht1
false
null
t3_14fiht1
/r/LocalLLaMA/comments/14fiht1/how_to_download_models_from_hf_from_terminal/
false
false
default
0
null
A simple way to "Extending Context to 8K"?!
161
2023-06-21T19:14:58
https://kaiokendev.github.io/til#extending-context-to-8k
pseudonerv
kaiokendev.github.io
1970-01-01T00:00:00
0
{}
14fgjqj
false
null
t3_14fgjqj
/r/LocalLLaMA/comments/14fgjqj/a_simple_way_to_extending_context_to_8k/
false
false
default
161
null
Offering a stipend for researchers to train open-source fine-tuned models
23
[removed]
2023-06-21T18:56:39
https://www.reddit.com/r/LocalLLaMA/comments/14fg430/offering_a_stipend_for_researchers_to_train/
newy66
self.LocalLLaMA
2023-06-21T19:19:09
0
{}
14fg430
true
null
t3_14fg430
/r/LocalLLaMA/comments/14fg430/offering_a_stipend_for_researchers_to_train/
false
false
default
23
null
Transformers samplers added to exllama on oobabooga text-gen-webui, so all the samplers of GPTQ-for-LLaMA now works in exllama!
38
2023-06-21T18:46:18
https://github.com/oobabooga/text-generation-webui/commit/580c1ee7483e9934b7884ff0071c1784060ba6eb
panchovix
github.com
1970-01-01T00:00:00
0
{}
14ffvcn
false
null
t3_14ffvcn
/r/LocalLLaMA/comments/14ffvcn/transformers_samplers_added_to_exllama_on/
false
false
https://b.thumbs.redditm…9KPrlwoZM5Bk.jpg
38
{'enabled': False, 'images': [{'id': 'A0zS9fWyOdGCf-jPZS_FPiAT_xwyux6C0Vz2GrqP4ik', 'resolutions': [{'height': 54, 'url': 'https://external-preview.redd.it/tSUXidxTjZE9W3lEEaRxSJNwZDu_azfGUBErg6Rr2ow.jpg?width=108&crop=smart&auto=webp&s=af17d16e6e029ee27991152f543a05d71bdcb2ed', 'width': 108}, {'height': 108, 'url': 'h...
Training LLaMA with Unstructured Data
5
I'm new to these topics, and I couldn't find much information about training the LLaMA models with documents. For example, is it possible to fine-tune Guanaco models with documents? How can I train these models with unstructured data?
2023-06-21T18:02:40
https://www.reddit.com/r/LocalLLaMA/comments/14fesbj/training_llama_with_unstructured_data/
ARBasaran
self.LocalLLaMA
1970-01-01T00:00:00
0
{}
14fesbj
false
null
t3_14fesbj
/r/LocalLLaMA/comments/14fesbj/training_llama_with_unstructured_data/
false
false
self
5
null
Local rig configuration for llama and LLM
6
[removed]
2023-06-21T16:37:11
https://www.reddit.com/r/LocalLLaMA/comments/14fcko5/local_rig_configuration_for_llama_and_llm/
hehsbbslwh142538
self.LocalLLaMA
1970-01-01T00:00:00
0
{}
14fcko5
false
null
t3_14fcko5
/r/LocalLLaMA/comments/14fcko5/local_rig_configuration_for_llama_and_llm/
false
false
default
6
null
Using LLM to create dataset
1
[removed]
2023-06-21T16:36:44
https://www.reddit.com/r/LocalLLaMA/comments/14fck9r/using_llm_to_create_dataset/
gptzerozero
self.LocalLLaMA
1970-01-01T00:00:00
0
{}
14fck9r
false
null
t3_14fck9r
/r/LocalLLaMA/comments/14fck9r/using_llm_to_create_dataset/
false
false
default
1
null
Starting out with local llm
1
[removed]
2023-06-21T15:59:27
https://www.reddit.com/r/LocalLLaMA/comments/14fbkve/starting_out_with_local_llm/
haywirehax
self.LocalLLaMA
1970-01-01T00:00:00
0
{}
14fbkve
false
null
t3_14fbkve
/r/LocalLLaMA/comments/14fbkve/starting_out_with_local_llm/
false
false
default
1
null
Local vicuna AI for low end pc?
1
[removed]
2023-06-21T15:56:31
https://www.reddit.com/r/LocalLLaMA/comments/14fbi79/local_vicuna_ai_for_low_end_pc/
AdamsText
self.LocalLLaMA
1970-01-01T00:00:00
0
{}
14fbi79
false
null
t3_14fbi79
/r/LocalLLaMA/comments/14fbi79/local_vicuna_ai_for_low_end_pc/
false
false
default
1
null
Train a local LLM on my files for use as a general-purpose chatbot
4
**tl;dr: I'm a noob and want to have a chatbot answer questions about my personal data. Pls help.** **edit: I searched the subreddit with some new words and was pointed to LoRA training which seems like the starting point, so this might be moot. Please point me to any new resources from there! :)** Hi Reddit. I need...
2023-06-21T15:54:21
https://www.reddit.com/r/LocalLLaMA/comments/14fbg4p/train_a_local_llm_on_my_files_for_use_as_a/
Creative_Addition_29
self.LocalLLaMA
2023-06-21T16:02:03
0
{}
14fbg4p
false
null
t3_14fbg4p
/r/LocalLLaMA/comments/14fbg4p/train_a_local_llm_on_my_files_for_use_as_a/
false
false
self
4
null
Best LLM for Note and Fact generation
2
[removed]
2023-06-21T15:53:49
[deleted]
1970-01-01T00:00:00
0
{}
14fbfnf
false
null
t3_14fbfnf
/r/LocalLLaMA/comments/14fbfnf/best_llm_for_note_and_fact_generation/
false
false
default
2
null
Last Nvidia Drivers let you use the shared memory of your GPU with EXLlama
80
My graphics card is an Nvidia RTX 4070 with 12 gigabytes of video memory. I recently upgraded my PC with an additional 32 gigabytes of system RAM, bringing the total to 48 gigabytes. I tried loading a 33b model(Guanaco is great), with these two options: llama.cpp using a GGML model, or EXLlama using a GPTQ version. T...
2023-06-21T15:46:53
https://www.reddit.com/r/LocalLLaMA/comments/14fb9c0/last_nvidia_drivers_let_you_use_the_shared_memory/
alexthai7
self.LocalLLaMA
2023-06-21T16:18:01
0
{}
14fb9c0
false
null
t3_14fb9c0
/r/LocalLLaMA/comments/14fb9c0/last_nvidia_drivers_let_you_use_the_shared_memory/
false
false
self
80
null
Building koboldcpp_CUDA on Linux
20
I've successfully managed to run Koboldcpp CUDA edition on Ubuntu! It's not something you can easily find through a direct search, but with some indirect hints, I figured it out. On the Koboldcpp GitHub repository, there are no instructions on how to build the CuBlas version, which is crucial for utilizing Nvidia's CU...
2023-06-21T15:35:54
https://www.reddit.com/r/LocalLLaMA/comments/14faz1d/building_koboldcpp_cuda_on_linux/
Current-Voice2755
self.LocalLLaMA
1970-01-01T00:00:00
0
{}
14faz1d
false
null
t3_14faz1d
/r/LocalLLaMA/comments/14faz1d/building_koboldcpp_cuda_on_linux/
false
false
self
20
{'enabled': False, 'images': [{'id': 'a1QWRPDvXA-AUqmcv2cSMMAcJ1DAQeFgdSV9fAki7Y0', 'resolutions': [{'height': 54, 'url': 'https://external-preview.redd.it/bGVoIjHELN4vIvAEED21I5-DTSMs5VW2272JrDjd6so.jpg?width=108&crop=smart&auto=webp&s=ebb5cac99e579df42039abe960e8a6dc934a7f0b', 'width': 108}, {'height': 108, 'url': 'h...
Which are the best LLMs that can explain code?
23
Given a piece of code, I am looking for open-source LLMs that can explain what the code does in layman terms. Brownie points if it can additionally detect syntactic bugs in the code (i.e., the code will produce compile-time error if it is run). And super gigantic brownie points if it can detect semantic bugs in the cod...
2023-06-21T15:18:26
https://www.reddit.com/r/LocalLLaMA/comments/14faiqr/which_are_the_best_llms_that_can_explain_code/
ResearcherNo4728
self.LocalLLaMA
2023-06-21T15:24:01
0
{}
14faiqr
false
null
t3_14faiqr
/r/LocalLLaMA/comments/14faiqr/which_are_the_best_llms_that_can_explain_code/
false
false
self
23
null
Opinions on 33b vs 65b models and PC suggestions please.
7
Sat wondering about which option to do about my current pc (5950x 128gig ram, 4070/4090) I sold a 3090 and stupidly bought a 4090 a few months back. Currently mostly use the 4070 to game on and 4090 to run 33b models (since cheaper on uk electric) but I'm pondering if I should sell the 4090 and maybe get 2 3090s with t...
2023-06-21T14:22:02
https://www.reddit.com/r/LocalLLaMA/comments/14f92zp/opinions_on_33b_vs_65b_models_and_pc_suggestions/
fluffywuffie90210
self.LocalLLaMA
1970-01-01T00:00:00
0
{}
14f92zp
false
null
t3_14f92zp
/r/LocalLLaMA/comments/14f92zp/opinions_on_33b_vs_65b_models_and_pc_suggestions/
false
false
self
7
null
A reminder of why we need "local" LLM: Over 100,000 compromised ChatGPT accounts found for sale on dark web
1
2023-06-21T14:13:07
https://www.theregister.com/2023/06/20/stolen_chatgpt_accounts/
kryptkpr
theregister.com
1970-01-01T00:00:00
0
{}
14f8v68
false
null
t3_14f8v68
/r/LocalLLaMA/comments/14f8v68/a_reminder_of_why_we_need_local_llm_over_100000/
false
false
default
1
null
Seeking Guidance on Open-Source LLM Deployment & Fine-Tuning
0
[removed]
2023-06-21T14:09:19
https://www.reddit.com/r/LocalLLaMA/comments/14f8rns/seeking_guidance_on_opensource_llm_deployment/
TobyWonKenobi
self.LocalLLaMA
2023-06-21T14:13:52
0
{}
14f8rns
false
null
t3_14f8rns
/r/LocalLLaMA/comments/14f8rns/seeking_guidance_on_opensource_llm_deployment/
false
false
default
0
null
create the best coder open-source in the world?
61
Alright. It's time for some action! [https://arxiv.org/abs/2306.11644](https://arxiv.org/abs/2306.11644) ​ Microsoft showed us you can train smaller llms, so small as 1.3B tokens that beat 3.5 GPT which in my opinion is quite good at coding if you are specific enough on single languages. This means you can...
2023-06-21T12:09:47
https://www.reddit.com/r/LocalLLaMA/comments/14f5zr7/create_the_best_coder_opensource_in_the_world/
shaman-warrior
self.LocalLLaMA
1970-01-01T00:00:00
0
{}
14f5zr7
false
null
t3_14f5zr7
/r/LocalLLaMA/comments/14f5zr7/create_the_best_coder_opensource_in_the_world/
false
false
self
61
{'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...
Q: Simple prompts to test model's core reasoning ability?
10
I've seen some people use basic arithmetic questions. I'd love to collect such questions so that we can compare models easily. Ideally that can surface the known gaps between open source models and ChatGPT 3.5 / 4 models.
2023-06-21T07:54:37
https://www.reddit.com/r/LocalLLaMA/comments/14f17ix/q_simple_prompts_to_test_models_core_reasoning/
kkimdev
self.LocalLLaMA
1970-01-01T00:00:00
0
{}
14f17ix
false
null
t3_14f17ix
/r/LocalLLaMA/comments/14f17ix/q_simple_prompts_to_test_models_core_reasoning/
false
false
self
10
null
What is the significance of n_ctx ?
3
I would like to know what is the significance of \`n\_ctx\`. I know that i represents the maximum number of tokens that the input sequence can be. But it is given as a parameter which can be set while initializing the model, so that makes me think, if I need to process a longer prompt I will just change it. Ha...
2023-06-21T06:29:11
https://www.reddit.com/r/LocalLLaMA/comments/14eznwk/what_is_the_significance_of_n_ctx/
dhirajsuvarna
self.LocalLLaMA
1970-01-01T00:00:00
0
{}
14eznwk
false
null
t3_14eznwk
/r/LocalLLaMA/comments/14eznwk/what_is_the_significance_of_n_ctx/
false
false
self
3
null
Is it possible to do personal RLHF?
4
I have been using the chatbot example from exllama with LLaMA 65B, with various modified prompts. It's a lot of fun. A difficulty is that there's personality instability from run to run. That's not all bad, since it's a fun game to try to guide the bot in interesting directions. But deliberately guiding the bot (even ...
2023-06-21T06:09:09
https://www.reddit.com/r/LocalLLaMA/comments/14ezam7/is_it_possible_to_do_personal_rlhf/
hold_my_fish
self.LocalLLaMA
1970-01-01T00:00:00
0
{}
14ezam7
false
null
t3_14ezam7
/r/LocalLLaMA/comments/14ezam7/is_it_possible_to_do_personal_rlhf/
false
false
self
4
null
Microsoft makes new 1.3B coding LLM that outperforms all models on MBPP except GPT-4, reaches third place on HumanEval above GPT-3.5, and shows emergent properties
433
Textbooks Are All You Need Paper: [https://arxiv.org/abs/2306.11644](https://arxiv.org/abs/2306.11644) Excerpts: >In this work, following the footsteps of Eldan and Li, we explore the improvement that can be obtained along a different axis: the *quality* of the data. We demonstrate the power of high quality data in ...
2023-06-21T06:03:24
https://www.reddit.com/r/LocalLLaMA/comments/14ez6qf/microsoft_makes_new_13b_coding_llm_that/
llamaShill
self.LocalLLaMA
1970-01-01T00:00:00
0
{}
14ez6qf
false
null
t3_14ez6qf
/r/LocalLLaMA/comments/14ez6qf/microsoft_makes_new_13b_coding_llm_that/
false
false
self
433
{'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...
Is anyone using local LLMs for their business?
1
[removed]
2023-06-21T05:13:00
https://www.reddit.com/r/LocalLLaMA/comments/14ey89g/is_anyone_using_local_llms_for_their_business/
Aggressive-Snow-835
self.LocalLLaMA
1970-01-01T00:00:00
0
{}
14ey89g
false
null
t3_14ey89g
/r/LocalLLaMA/comments/14ey89g/is_anyone_using_local_llms_for_their_business/
false
false
default
1
null
Llama-cpp-python is slower than llama.cpp by more than 25%. Let's get it resolved
36
Llama.cpp is not just 1 or 2 percent faster; it's a whopping 28% faster than llama-cpp-python: 30.9s vs 39.5s. I came across this issue two days ago and spent half a day conducting thorough tests and creating a detailed bug report for llama-cpp-python. But it seems like nobody cares about it at all. So, I decided to ...
2023-06-21T02:56:50
https://www.reddit.com/r/LocalLLaMA/comments/14evg0g/llamacpppython_is_slower_than_llamacpp_by_more/
Big_Communication353
self.LocalLLaMA
2023-06-21T03:02:09
0
{}
14evg0g
false
null
t3_14evg0g
/r/LocalLLaMA/comments/14evg0g/llamacpppython_is_slower_than_llamacpp_by_more/
false
false
self
36
{'enabled': False, 'images': [{'id': '2A6pPlrffR6nIlGIdi_x08hRw9_DuJi2nOx4BRixmXQ', 'resolutions': [{'height': 54, 'url': 'https://external-preview.redd.it/_tX2_Lh-xKbyrTuxCsXYgxOkiEw2GgYL_xysvnkdvIE.jpg?width=108&crop=smart&auto=webp&s=4c36a62d0befa4dd32cce4c8636a5ba3180b4f9d', 'width': 108}, {'height': 108, 'url': 'h...
Best ggml model for instruction following?
2
[removed]
2023-06-21T02:56:49
https://www.reddit.com/r/LocalLLaMA/comments/14evg01/best_ggml_model_for_instruction_following/
eyerfing
self.LocalLLaMA
1970-01-01T00:00:00
0
{}
14evg01
false
null
t3_14evg01
/r/LocalLLaMA/comments/14evg01/best_ggml_model_for_instruction_following/
false
false
default
2
null
Best bet for parseable output?
3
Would like it if I could get output in consistent JSON or something somehow so I could do specific stuff with it. Any models better or worse for this than other? Any prompt tricks? I’ve only experimented a tiny bit so far mostly with Wizard 13b
2023-06-21T01:35:58
https://www.reddit.com/r/LocalLLaMA/comments/14etov8/best_bet_for_parseable_output/
EarthquakeBass
self.LocalLLaMA
1970-01-01T00:00:00
0
{}
14etov8
false
null
t3_14etov8
/r/LocalLLaMA/comments/14etov8/best_bet_for_parseable_output/
false
false
self
3
null
How to dive deeper into LLMs?
12
Hi there! I am from a computer-vision background as LLM is gaining much hype, I am diving deeper into the NLP field as well. I have gone through language models such as BERT and GPT as a lot of resources were available for them. Now I want to dive deeper into large llm. Can you guys provide any roadmap, resources, or A...
2023-06-21T01:23:59
https://www.reddit.com/r/LocalLLaMA/comments/14etfd1/how_to_dive_deeper_into_llms/
rajanghimire534
self.LocalLLaMA
1970-01-01T00:00:00
0
{}
14etfd1
false
null
t3_14etfd1
/r/LocalLLaMA/comments/14etfd1/how_to_dive_deeper_into_llms/
false
false
self
12
null
Models produce incoherent statements
1
[removed]
2023-06-21T00:57:43
https://www.reddit.com/r/LocalLLaMA/comments/14esz3l/models_produce_incoherent_statements/
SpareSink5530
self.LocalLLaMA
1970-01-01T00:00:00
0
{}
14esz3l
false
null
t3_14esz3l
/r/LocalLLaMA/comments/14esz3l/models_produce_incoherent_statements/
false
false
default
1
null
What is the fastest way to do inference with a 3/4 bit quantized 13b vicuna model?
7
Right now, as far as I've read, the fastest with a gpu is exllama, outperforming everything else. However, I haven't heard anything about how it compares with both llama.cpp gpu inference (wich was merged very recently) and other quantization methods (squeezeLLM is one that stands out a lot). What's the fastest for inf...
2023-06-21T00:38:57
https://www.reddit.com/r/LocalLLaMA/comments/14eskrb/what_is_the_fastest_way_to_do_inference_with_a_34/
KillerX629
self.LocalLLaMA
1970-01-01T00:00:00
0
{}
14eskrb
false
null
t3_14eskrb
/r/LocalLLaMA/comments/14eskrb/what_is_the_fastest_way_to_do_inference_with_a_34/
false
false
self
7
null
Question: Does using, for example, Wizard-Vicuna-7B-Uncensored, make it learn over time in it's local instance ?
2
I am really impressed by the performance of the 8-bit Wizard-Vicuna-7B-Uncensored 1.0, and now i would like to use it for work as it's basically doing the same as ChatGPT for my scripting needs, but one thing i find important to know even though i cant seem to find an answer ; - Does the LLaMa learn over time from the...
2023-06-21T00:22:36
https://www.reddit.com/r/LocalLLaMA/comments/14es7dj/question_does_using_for_example/
[deleted]
self.LocalLLaMA
1970-01-01T00:00:00
0
{}
14es7dj
false
null
t3_14es7dj
/r/LocalLLaMA/comments/14es7dj/question_does_using_for_example/
false
false
self
2
null
vLLM: 24x faster LLM serving than HuggingFace Transformers
2
2023-06-20T22:06:32
https://vllm.ai/
iwaswrongonce
vllm.ai
1970-01-01T00:00:00
0
{}
14eouux
false
null
t3_14eouux
/r/LocalLLaMA/comments/14eouux/vllm_24x_faster_llm_serving_than_huggingface/
false
false
default
2
null
[Rumor] Potential GPT-4 architecture description
223
[Source](https://twitter.com/soumithchintala/status/1671267150101721090?s=46&t=dUCVh9akIWxxNUIkrDJwJg)
2023-06-20T21:52:11
https://i.redd.it/66mu2t61v87b1.jpg
Shir_man
i.redd.it
1970-01-01T00:00:00
0
{}
14eoh4f
false
null
t3_14eoh4f
/r/LocalLLaMA/comments/14eoh4f/rumor_potential_gpt4_architecture_description/
false
false
https://b.thumbs.redditm…pHc4nQg7iKyU.jpg
223
{'enabled': True, 'images': [{'id': 'NDr8aoAANKipaJwWs-HJ-EKKOoqT2zpqehOVsUyVWQ8', 'resolutions': [{'height': 184, 'url': 'https://preview.redd.it/66mu2t61v87b1.jpg?width=108&crop=smart&auto=webp&s=86d1a1bd185d9f206c1cef4e2c79981f6bd843fc', 'width': 108}, {'height': 369, 'url': 'https://preview.redd.it/66mu2t61v87b1.jp...
Newb runs into compute bottlenecks
0
[deleted]
2023-06-20T21:48:59
[deleted]
1970-01-01T00:00:00
0
{}
14eodyj
false
null
t3_14eodyj
/r/LocalLLaMA/comments/14eodyj/newb_runs_into_compute_bottlenecks/
false
false
default
0
null
Falcoder 7B - Falcon Finetuned with CodeAlpaca w/QLoRA and PEFT
16
NOT My Model ​ Falcon-7b fine-tuned on the CodeAlpaca 20k instructions dataset by using the method QLoRA with PEFT library CodeAlpaca\_20K: contains 20K instruction-following data used for fine-tuning the Code Alpaca model. [https://huggingface.co/mrm8488/falcoder-7b](https://huggingface.co/mrm8488/falcod...
2023-06-20T20:50:32
https://www.reddit.com/r/LocalLLaMA/comments/14emsoi/falcoder_7b_falcon_finetuned_with_codealpaca/
ChobPT
self.LocalLLaMA
1970-01-01T00:00:00
0
{}
14emsoi
false
null
t3_14emsoi
/r/LocalLLaMA/comments/14emsoi/falcoder_7b_falcon_finetuned_with_codealpaca/
false
false
self
16
{'enabled': False, 'images': [{'id': 'kckByvNI7xP1OTFxNupfAgvrJXZ0fbzbK3KHxeMbvbI', 'resolutions': [{'height': 108, 'url': 'https://external-preview.redd.it/frxywgHviuEwBJBs1IC_M_vc55iHXsOI7ntVnbQs2rM.jpg?width=108&crop=smart&auto=webp&s=92210f7206a60246c0bc8be4ae600a7250f4c469', 'width': 108}, {'height': 216, 'url': '...
Preset Arena experiment: last 48 hours. Please vote!
29
A few days ago I posted [Preset Arena: 17,205 comparisons between 241 different presets.](https://www.reddit.com/r/LocalLLaMA/comments/14adfw2/preset_arena_17205_comparisons_between_241/) Since then, **5619** votes have been obtained. THANK YOU to everyone who voted! I think that 17,205 comparisons may have been too ...
2023-06-20T20:48:54
https://www.reddit.com/r/LocalLLaMA/comments/14emr26/preset_arena_experiment_last_48_hours_please_vote/
oobabooga4
self.LocalLLaMA
2023-06-20T20:53:28
0
{}
14emr26
false
null
t3_14emr26
/r/LocalLLaMA/comments/14emr26/preset_arena_experiment_last_48_hours_please_vote/
false
false
self
29
null
HELP! Unable to run HF Inference API for my finetuned falcon-7b model.
1
[removed]
2023-06-20T20:37:05
https://www.reddit.com/r/LocalLLaMA/comments/14emff6/help_unable_to_run_hf_inference_api_for_my/
medmac01
self.LocalLLaMA
1970-01-01T00:00:00
0
{}
14emff6
false
null
t3_14emff6
/r/LocalLLaMA/comments/14emff6/help_unable_to_run_hf_inference_api_for_my/
false
false
default
1
null
Are there any good GUIs for llama.cpp GGML?
1
[removed]
2023-06-20T20:29:04
https://www.reddit.com/r/LocalLLaMA/comments/14em7fn/are_there_any_good_guis_for_llamacpp_ggml/
Virtamancer
self.LocalLLaMA
1970-01-01T00:00:00
0
{}
14em7fn
false
null
t3_14em7fn
/r/LocalLLaMA/comments/14em7fn/are_there_any_good_guis_for_llamacpp_ggml/
false
false
default
1
null
Just released - vLLM inference library that accelerates HF Transformers by 24x
94
vLLM is an open-source LLM inference and serving library that accelerates HuggingFace Transformers by 24x and powers Vicuna and Chatbot Arena. Github: [https://github.com/vllm-project/vllm](https://github.com/vllm-project/vllm)Blog post: [https://vllm.ai](https://t.co/M7g6pa8rHj) * Edit - it wasn't "just released"...
2023-06-20T20:28:38
https://www.reddit.com/r/LocalLLaMA/comments/14em713/just_released_vllm_inference_library_that/
yanjb
self.LocalLLaMA
2023-06-20T21:14:45
0
{}
14em713
false
null
t3_14em713
/r/LocalLLaMA/comments/14em713/just_released_vllm_inference_library_that/
false
false
https://b.thumbs.redditm…bt7OoVbz6q3Y.jpg
94
{'enabled': False, 'images': [{'id': 'DYs7CkN9PGgRHPUogaL4fxcBexAw6r6seHmUbQMmyv8', 'resolutions': [{'height': 54, 'url': 'https://external-preview.redd.it/60fMZ9sfWGJnltAGF_Gi7alsRI5ZOGDt0tl871iLwNY.jpg?width=108&crop=smart&auto=webp&s=dd760df847a7e0e0e0b4b9205e8fb93196f3fc5d', 'width': 108}, {'height': 108, 'url': 'h...
George Hotz questions GGML & Quantization in general without better testing (Latent Space Podcast)(29:07)
3
2023-06-20T20:00:38
https://www.latent.space/p/geohot
jimmy6dof
latent.space
1970-01-01T00:00:00
0
{}
14eleza
false
null
t3_14eleza
/r/LocalLLaMA/comments/14eleza/george_hotz_questions_ggml_quantization_in/
false
false
https://a.thumbs.redditm…1Ac6gPIS6b-0.jpg
3
{'enabled': False, 'images': [{'id': 'pkzIN84fxa_C8ZMFCGKm0A627gqydXLQchUXyHRfYFs', 'resolutions': [{'height': 60, 'url': 'https://external-preview.redd.it/43Cow787MPCXmqnWhBPg03qsonjcQchSgg0uUY9ME_M.jpg?width=108&crop=smart&auto=webp&s=3445ffb4927134f3b80b90aef452c3f15652f229', 'width': 108}, {'height': 121, 'url': 'h...
Error when attempting inference with LoRA applied (see comments)
1
2023-06-20T18:47:19
https://i.redd.it/u3x41ruzx77b1.png
yuicebox
i.redd.it
1970-01-01T00:00:00
0
{}
14ejg6r
false
null
t3_14ejg6r
/r/LocalLLaMA/comments/14ejg6r/error_when_attempting_inference_with_lora_applied/
false
false
default
1
null
What is the best 7b LLM
10
With all these fine-tuned models floating around it's getting harder to pick the best model for projects. Any idea which 7b LLM has the best eval scores on ARC, HellaSwag, MMLU or TruthfulQA. I took a look at [HF leaderboard](https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard) but this doesn't include a...
2023-06-20T18:36:36
https://www.reddit.com/r/LocalLLaMA/comments/14ej5sn/what_is_the_best_7b_llm/
04RR
self.LocalLLaMA
1970-01-01T00:00:00
0
{}
14ej5sn
false
null
t3_14ej5sn
/r/LocalLLaMA/comments/14ej5sn/what_is_the_best_7b_llm/
false
false
self
10
{'enabled': False, 'images': [{'id': 'EN0-abblERL52DxeoNzcxdkhvXEwLdZMJTS58Umjs64', 'resolutions': [{'height': 58, 'url': 'https://external-preview.redd.it/pnEIDVgN3O3UZSEZF8G101Cpm5FLu9i3k_abBlep_2c.jpg?width=108&crop=smart&auto=webp&s=6fbb309f983333cbaf528bd40f8d6ffb39877704', 'width': 108}, {'height': 116, 'url': 'h...
LLaMA Equivalent Music LM
1
[removed]
2023-06-20T17:10:34
https://www.reddit.com/r/LocalLLaMA/comments/14egv3g/llama_equivalent_music_lm/
somethedaring
self.LocalLLaMA
1970-01-01T00:00:00
0
{}
14egv3g
false
null
t3_14egv3g
/r/LocalLLaMA/comments/14egv3g/llama_equivalent_music_lm/
false
false
default
1
null
GPT4All now supports Replit model on Apple Silicon (23 tok/sec)!
31
2023-06-20T17:04:42
https://twitter.com/nomic_ai/status/1671166514903543808
NomicAI
twitter.com
1970-01-01T00:00:00
0
{}
14egpd4
false
{'oembed': {'author_name': 'Nomic AI', 'author_url': 'https://twitter.com/nomic_ai', 'cache_age': 3153600000, 'height': None, 'html': '<blockquote class="twitter-video"><p lang="en" dir="ltr">Local LLMs in GPT4All are now 2x faster on Apple Silicone ⚡\uf8ff<br>- Supports all LLaMa models<br>- Exclusive support of the R...
t3_14egpd4
/r/LocalLLaMA/comments/14egpd4/gpt4all_now_supports_replit_model_on_apple/
false
false
https://b.thumbs.redditm…2tNgeyMVZRBE.jpg
31
{'enabled': False, 'images': [{'id': '874e-Hu7RjLoZ2m3gpd5U5gKCYJcGu9LrwjsXGIwn7k', 'resolutions': [{'height': 62, 'url': 'https://external-preview.redd.it/BYReTCn6vlaPLR9-3bt5pdrSPiljLX3ATqnroGudgLU.jpg?width=108&crop=smart&auto=webp&s=969cae5340b7acf50e64cea61a547b28ecf02cc7', 'width': 108}], 'source': {'height': 81,...
I think I need some help setting things up for local usage...
147
2023-06-20T16:29:48
https://i.redd.it/b7szgt2h977b1.png
isoceans
i.redd.it
1970-01-01T00:00:00
0
{}
14efqn6
false
null
t3_14efqn6
/r/LocalLLaMA/comments/14efqn6/i_think_i_need_some_help_setting_things_up_for/
false
false
https://a.thumbs.redditm…sgenfo4uH1S8.jpg
147
{'enabled': True, 'images': [{'id': 'w21ZLyYH4aEydC18Nb8CKILufe6muisPyQQExtAhqOQ', 'resolutions': [{'height': 61, 'url': 'https://preview.redd.it/b7szgt2h977b1.png?width=108&crop=smart&auto=webp&s=a28967fa4beddb4a8b61b43bb4fd23177fbd3e64', 'width': 108}, {'height': 122, 'url': 'https://preview.redd.it/b7szgt2h977b1.png...
PostgresML adds GPTQ & GGML quantized LLM support for Huggingface Transformers
9
2023-06-20T16:12:45
https://postgresml.org/blog/announcing-gptq-and-ggml-quantized-llm-support-for-huggingface-transformers
something_cleverer
postgresml.org
1970-01-01T00:00:00
0
{}
14efaze
false
null
t3_14efaze
/r/LocalLLaMA/comments/14efaze/postgresml_adds_gptq_ggml_quantized_llm_support/
false
false
default
9
null
New AI 'influencers' every other day
1
2023-06-20T15:32:07
https://i.redd.it/5srg1ti4z67b1.png
liamsagely
i.redd.it
1970-01-01T00:00:00
0
{}
14ee9e1
false
null
t3_14ee9e1
/r/LocalLLaMA/comments/14ee9e1/new_ai_influencers_every_other_day/
false
false
default
1
null
Keeping my LLM on topic when passing context?
10
I am currently attempting to pass some context to the GPT4All-13B-Snoozy model in order to answer a question. The problem is that sometimes, the context string I am passing may contain additional irrelevant information in addition to the information needed to answer the given question. This works fine, except for that...
2023-06-20T15:17:37
https://www.reddit.com/r/LocalLLaMA/comments/14edvw4/keeping_my_llm_on_topic_when_passing_context/
kotschi1997
self.LocalLLaMA
1970-01-01T00:00:00
0
{}
14edvw4
false
null
t3_14edvw4
/r/LocalLLaMA/comments/14edvw4/keeping_my_llm_on_topic_when_passing_context/
false
false
self
10
null
Inference of fine-tuned 8bit model from code
1
[removed]
2023-06-20T15:02:28
https://www.reddit.com/r/LocalLLaMA/comments/14edigf/inference_of_finetuned_8bit_model_from_code/
Old_Speech_5665
self.LocalLLaMA
1970-01-01T00:00:00
0
{}
14edigf
false
null
t3_14edigf
/r/LocalLLaMA/comments/14edigf/inference_of_finetuned_8bit_model_from_code/
false
false
default
1
null
Does local LLaMA's use SLI for increased VRAM?
3
This may be a dumb question, but I have a 1080 Ti currently, and was thinking about picking up 3 more for cheap (about $500), which would give me 44GB of VRAM in total... Would this be utilized with setup?
2023-06-20T13:46:19
https://www.reddit.com/r/LocalLLaMA/comments/14ebleu/does_local_llamas_use_sli_for_increased_vram/
iamthewhatt
self.LocalLLaMA
1970-01-01T00:00:00
0
{}
14ebleu
false
null
t3_14ebleu
/r/LocalLLaMA/comments/14ebleu/does_local_llamas_use_sli_for_increased_vram/
false
false
self
3
null
First 13B open instruct open llama
32
https://huggingface.co/VMware/open-llama-13b-open-instruct Not sure about you guys but this is huge. First fully open source, commercially usable 13b model. I think it actually performs quite well. Write in the comments your experience. Edit : The link points to a merged LoRA model btw. Thanks for pointing that out u...
2023-06-20T12:58:49
https://www.reddit.com/r/LocalLLaMA/comments/14eahjk/first_13b_open_instruct_open_llama/
NeatManagement3
self.LocalLLaMA
2023-06-20T13:39:15
0
{}
14eahjk
false
null
t3_14eahjk
/r/LocalLLaMA/comments/14eahjk/first_13b_open_instruct_open_llama/
false
false
self
32
{'enabled': False, 'images': [{'id': 'LW_qIW9esjcRqthCWBRqjAO9CO-86W08ZFYUlMXYxdY', 'resolutions': [{'height': 58, 'url': 'https://external-preview.redd.it/vb4kyG-O9YeNfer9fFYp1A1CS3FS9hoU8EsKLDIMok4.jpg?width=108&crop=smart&auto=webp&s=df2b3715e10c9015a7fd4080bdb2f7c8e1dd6862', 'width': 108}, {'height': 116, 'url': 'h...
Sometimes Kobold doesn't show output in real time and waits until it's finished generating the text. Why?
1
[deleted]
2023-06-20T12:23:29
[deleted]
1970-01-01T00:00:00
0
{}
14e9pts
false
null
t3_14e9pts
/r/LocalLLaMA/comments/14e9pts/sometimes_kobold_doesnt_show_output_in_real_time/
false
false
default
1
null
I've come to rely on LLMs for emotional support and good advice
191
2023-06-20T11:55:46
https://i.redd.it/d43p14vgw57b1.png
veli_joza
i.redd.it
1970-01-01T00:00:00
0
{}
14e94oe
false
null
t3_14e94oe
/r/LocalLLaMA/comments/14e94oe/ive_come_to_rely_on_llms_for_emotional_support/
false
false
https://b.thumbs.redditm…UBPK0mLJcKFA.jpg
191
{'enabled': True, 'images': [{'id': 'Do4MraDRd5UikR_L8WTAKHD_jsuk6mEBhiWGgrX0X70', 'resolutions': [{'height': 115, 'url': 'https://preview.redd.it/d43p14vgw57b1.png?width=108&crop=smart&auto=webp&s=58a843dd89bc3fd6142231c75b82b9f71f090fc4', 'width': 108}, {'height': 231, 'url': 'https://preview.redd.it/d43p14vgw57b1.pn...
Does anyone know how to remove this body of text from my outputs?
4
Hello! I'm new to LLMs and LLaMA in general, and even newer to this subreddit so I apologise if my question is easily fixable. I've been messing around with an application called 'GPT4All' and I'm sure a few of you have heard of it. In case you haven't, it's a program/application that allows people to have a local AI...
2023-06-20T11:18:34
https://www.reddit.com/r/LocalLLaMA/comments/14e8duf/does_anyone_know_how_to_remove_this_body_of_text/
Cold_Masterpiece_147
self.LocalLLaMA
1970-01-01T00:00:00
0
{}
14e8duf
false
null
t3_14e8duf
/r/LocalLLaMA/comments/14e8duf/does_anyone_know_how_to_remove_this_body_of_text/
false
false
https://b.thumbs.redditm…Yh02RrYmWqxg.jpg
4
null
Discussion about Hadware Requirements for local LlaMa
4
Hello, I want to buy a computer to run local LLaMa models. I have read the recommendations regarding the hardware in the Wiki of this Reddit. My Question is, however, how good are these models running with the recommended hardware requirements? Is it as fast as ChatGPT generating responses? Or does it take like 1-5 M...
2023-06-20T10:56:17
https://www.reddit.com/r/LocalLLaMA/comments/14e7xf1/discussion_about_hadware_requirements_for_local/
Plane_Discussion_924
self.LocalLLaMA
1970-01-01T00:00:00
0
{}
14e7xf1
false
null
t3_14e7xf1
/r/LocalLLaMA/comments/14e7xf1/discussion_about_hadware_requirements_for_local/
false
false
self
4
null
Build, Train, and Deploy LLM Agents with Agent M
0
[removed]
2023-06-20T10:40:37
https://www.reddit.com/r/LocalLLaMA/comments/14e7n3u/build_train_and_deploy_llm_agents_with_agent_m/
Floatbot_Inc
self.LocalLLaMA
1970-01-01T00:00:00
0
{}
14e7n3u
false
null
t3_14e7n3u
/r/LocalLLaMA/comments/14e7n3u/build_train_and_deploy_llm_agents_with_agent_m/
false
false
default
0
null
Build, Train and Deploy LLM Agents with Agent M
0
2023-06-20T10:37:04
https://i.redd.it/clf1d00ki57b1.jpg
Floatbot_Inc
i.redd.it
1970-01-01T00:00:00
0
{}
14e7kqy
false
null
t3_14e7kqy
/r/LocalLLaMA/comments/14e7kqy/build_train_and_deploy_llm_agents_with_agent_m/
false
false
default
0
null
What Type of Research Can Bring Value to the Community?
21
Hi guys, Im a researcher scoping (and struggling) for ideas on what could bring value to the community and field in general. I've been looking into creating new evaluation methods or ways in which one can evaluate the performance of LLMs more objectively - and several ideas into ethics and biases, but not sure whi...
2023-06-20T10:23:48
https://www.reddit.com/r/LocalLLaMA/comments/14e7buc/what_type_of_research_can_bring_value_to_the/
XhoniShollaj
self.LocalLLaMA
1970-01-01T00:00:00
0
{}
14e7buc
false
null
t3_14e7buc
/r/LocalLLaMA/comments/14e7buc/what_type_of_research_can_bring_value_to_the/
false
false
self
21
null
What Model should I use?
4
I’m working on a bot that uses an LLM to take on a personality of an insulting, pompous Space pirate AI. So far I can’t find an LLM that can do chatting well. It keeps asking if I need any help. I just want to chat and follow the prompt. Edit: I’m using the Oobabooga API for the not silly tavern or the webui.
2023-06-20T10:18:02
https://www.reddit.com/r/LocalLLaMA/comments/14e77xi/what_model_should_i_use/
PhraseOk8758
self.LocalLLaMA
2023-06-20T10:22:36
0
{}
14e77xi
false
null
t3_14e77xi
/r/LocalLLaMA/comments/14e77xi/what_model_should_i_use/
false
false
self
4
null
Discussion about optimal Hardware-Requirements
0
[deleted]
2023-06-20T10:06:27
[deleted]
1970-01-01T00:00:00
0
{}
14e70bi
false
null
t3_14e70bi
/r/LocalLLaMA/comments/14e70bi/discussion_about_optimal_hardwarerequirements/
false
false
default
0
null
Visual Studio Code extension for WizardCoder
81
I just built the Quick Extension for WizardCoder so I can try it out in a real coding environment. I also have access to GitHub Copilot chat. I have to say that WizardCoder is quite good. PS: extension :[https://marketplace.visualstudio.com/items?itemName=mzbac.wizardcoder-vsc&ssr=false#overview](https://marketpl...
2023-06-20T09:04:34
https://www.reddit.com/r/LocalLLaMA/comments/14e5vwi/visual_studio_code_extension_for_wizardcoder/
mzbacd
self.LocalLLaMA
1970-01-01T00:00:00
0
{}
14e5vwi
false
null
t3_14e5vwi
/r/LocalLLaMA/comments/14e5vwi/visual_studio_code_extension_for_wizardcoder/
false
false
self
81
{'enabled': False, 'images': [{'id': '0X9djfd_bWdlhM07dSftS7otpejs3cdKDPe1jQJUgj0', 'resolutions': [{'height': 108, 'url': 'https://external-preview.redd.it/7z8TdtSd4Oaij01D_-bwaiL9CJ8THjhrUfJQjAqU9yc.jpg?width=108&crop=smart&auto=webp&s=aa64a99f2e0981debb75f458f19bb532977b67ae', 'width': 108}, {'height': 216, 'url': '...
WizardLM-13B-V1.0-Uncensored
203
Following up on [https://www.reddit.com/r/LocalLLaMA/comments/14ckrd6](https://www.reddit.com/r/LocalLLaMA/comments/14ckrd6) Today I released WizardLM-13B-V1.0-Uncensored [https://huggingface.co/ehartford/WizardLM-13B-V1.0-Uncensored](https://huggingface.co/ehartford/WizardLM-13B-V1.0-Uncensored) Based on the [Wizar...
2023-06-20T08:03:24
https://www.reddit.com/r/LocalLLaMA/comments/14e4sw8/wizardlm13bv10uncensored/
faldore
self.LocalLLaMA
1970-01-01T00:00:00
1
{'gid_2': 1}
14e4sw8
false
null
t3_14e4sw8
/r/LocalLLaMA/comments/14e4sw8/wizardlm13bv10uncensored/
false
false
self
203
{'enabled': False, 'images': [{'id': '_K7qWtA4Mm1G0sMWCNN7AsiduSrbTwTCBzLbjFUqJpY', 'resolutions': [{'height': 58, 'url': 'https://external-preview.redd.it/wnwk-Px3Wy0EFWih4C-1t6kgGAA0uxezHnl5eO8GD1c.jpg?width=108&crop=smart&auto=webp&s=5f4b7b7002f99e0fd7ba9816582ebab7510b9467', 'width': 108}, {'height': 116, 'url': 'h...
Recursion of Thought: A Divide-and-Conquer Approach to Multi-Context Reasoning with Language Models
45
>Generating intermediate steps, or Chain of Thought (CoT), is an effective way to significantly improve language models' (LM) multi-step reasoning capability. However, the CoT lengths can grow rapidly with the problem complexity, easily exceeding the maximum context size. Instead of increasing the context limit, which ...
2023-06-20T07:53:23
https://www.reddit.com/r/LocalLLaMA/comments/14e4mg6/recursion_of_thought_a_divideandconquer_approach/
Balance-
self.LocalLLaMA
1970-01-01T00:00:00
0
{}
14e4mg6
false
null
t3_14e4mg6
/r/LocalLLaMA/comments/14e4mg6/recursion_of_thought_a_divideandconquer_approach/
false
false
https://b.thumbs.redditm…gZ1dnJQ3UThA.jpg
45
{'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...
How do I run Stable Diffusion and LLMs from my PC on my mobile device? Offline and private ways?
3
Posting here after a recommendation from r/selfhosted . Currently I'm on Windows 10 but I'm switching to Pop!\_Os in the next few days. And I have a Samsung Galaxy Tab E 9.6' with an Android 4.4.4 custom rom, though I can switch to a 7.1.2 custom rom if needed, and root it too. If I have a long usb cable, is that...
2023-06-20T07:34:35
https://www.reddit.com/r/LocalLLaMA/comments/14e4arx/how_do_i_run_stable_diffusion_and_llms_from_my_pc/
ThrowawayProgress99
self.LocalLLaMA
2023-06-26T23:34:32
0
{}
14e4arx
false
null
t3_14e4arx
/r/LocalLLaMA/comments/14e4arx/how_do_i_run_stable_diffusion_and_llms_from_my_pc/
false
false
self
3
{'enabled': False, 'images': [{'id': 'nfayPavSUB5ngYv6-19UHNBThsXfcLIDQl4HkEe3Cv0', 'resolutions': [{'height': 108, 'url': 'https://external-preview.redd.it/QgPvRTknlY3rMNDqH1k4I37XGiq9tZF_FsygC_Xht4o.jpg?width=108&crop=smart&auto=webp&s=b1c8a90e5690a7186afdb269ad05279551994d09', 'width': 108}, {'height': 216, 'url': '...
PirvateGPT: Error loading source documents?
1
[removed]
2023-06-20T07:29:58
https://www.reddit.com/r/LocalLLaMA/comments/14e47y0/pirvategpt_error_loading_source_documents/
card_chase
self.LocalLLaMA
1970-01-01T00:00:00
0
{}
14e47y0
false
null
t3_14e47y0
/r/LocalLLaMA/comments/14e47y0/pirvategpt_error_loading_source_documents/
false
false
default
1
null
Best free open-source LLM to use for the recommendation task
1
[removed]
2023-06-20T06:56:56
https://www.reddit.com/r/LocalLLaMA/comments/14e3muo/best_free_opensource_llm_to_use_for_the/
lahaine93
self.LocalLLaMA
1970-01-01T00:00:00
0
{}
14e3muo
false
null
t3_14e3muo
/r/LocalLLaMA/comments/14e3muo/best_free_opensource_llm_to_use_for_the/
false
false
default
1
null
Unstructured text to graphDB
1
[removed]
2023-06-20T06:17:22
https://www.reddit.com/r/LocalLLaMA/comments/14e2wq3/unstructured_text_to_graphdb/
Raise_Fickle
self.LocalLLaMA
1970-01-01T00:00:00
0
{}
14e2wq3
false
null
t3_14e2wq3
/r/LocalLLaMA/comments/14e2wq3/unstructured_text_to_graphdb/
false
false
default
1
null
Creating an Org Knowledge Management System
10
Hi All, Kinda new to this space yet tried a few models. I would like to get direction on how to create a personalized knowledge management system that allows users to type and get answers. I want to train this model with organizational data and keep it privately hosted. Happy to create department-wise models if...
2023-06-20T02:33:58
https://www.reddit.com/r/LocalLLaMA/comments/14dyimz/creating_an_org_knowledge_management_system/
SpongeBob_000
self.LocalLLaMA
1970-01-01T00:00:00
0
{}
14dyimz
false
null
t3_14dyimz
/r/LocalLLaMA/comments/14dyimz/creating_an_org_knowledge_management_system/
false
false
self
10
null
Making a LoRA for WizardLM
0
[deleted]
2023-06-20T02:20:01
[deleted]
1970-01-01T00:00:00
0
{}
14dy795
false
null
t3_14dy795
/r/LocalLLaMA/comments/14dy795/making_a_lora_for_wizardlm/
false
false
default
0
null
Try the new RWKV world 7B, it's incredible.
32
[deleted]
2023-06-20T02:19:13
[deleted]
1970-01-01T00:00:00
0
{}
14dy6of
false
null
t3_14dy6of
/r/LocalLLaMA/comments/14dy6of/try_the_new_rwkv_world_7b_its_incredible/
false
false
default
32
null
Alternative C# bindings in development, anyone interested?
12
**Edit: The bulk of the code can be found in this subdirectory.** **https://github.com/MrJackSpade/Chie/tree/main/LLamaSharp/LLama** Was just wondering if there's anyone who wants to contribute to a chunk of a project I'm working on. I wasn't particularly satisfied with the state of the current LlamaSharp project, s...
2023-06-20T02:10:18
https://www.reddit.com/r/LocalLLaMA/comments/14dxznf/alternative_c_bindings_in_development_anyone/
mrjackspade
self.LocalLLaMA
2023-06-20T17:49:53
0
{}
14dxznf
false
null
t3_14dxznf
/r/LocalLLaMA/comments/14dxznf/alternative_c_bindings_in_development_anyone/
false
false
self
12
{'enabled': False, 'images': [{'id': '7F21HkIZ7kiK1HC_9WGRzzNC45LauG9S2AgOqNfW6uw', 'resolutions': [{'height': 54, 'url': 'https://external-preview.redd.it/W8FMnClGeDLG9F8KU-brXD81et0g0p4upXHNFxEA2fc.jpg?width=108&crop=smart&auto=webp&s=415758c5775304ae97cc5c64096e4bce799a3ed9', 'width': 108}, {'height': 108, 'url': 'h...
Anyboty Client - Alpha 0.1.1 Release - GGMLv3 Compatible Easy to Use Client
10
2023-06-20T00:55:51
https://anyboty.itch.io/anyboty
Pathos14489
anyboty.itch.io
1970-01-01T00:00:00
0
{}
14dwcft
false
null
t3_14dwcft
/r/LocalLLaMA/comments/14dwcft/anyboty_client_alpha_011_release_ggmlv3/
false
false
https://b.thumbs.redditm…bjZ1YB1fk3sU.jpg
10
{'enabled': False, 'images': [{'id': '7aKyCAIq4SAnFwxYHDpdcXu8UleY-vwKVX4Jat_6qLo', 'resolutions': [{'height': 85, 'url': 'https://external-preview.redd.it/2EJ_h26BboK-gACvjoOjMgFP9jEDNijqh8i2nIUUXB4.jpg?width=108&crop=smart&auto=webp&s=712fb68d4db7b695d2a8b5bd76b9e9cde7ff9f17', 'width': 108}, {'height': 171, 'url': 'h...
Finetuned LLM not getting better performance
3
I have been trying hard to get Vicuna 7B to be a better assistant by finetuning it on my own documents, but results so far have been weak. It doesn't seem like next word prediction on a new high quality corpus is enough for it to leverage the knowledge on a chat bot format. Has anyone faced this same problem? We could ...
2023-06-20T00:23:42
https://www.reddit.com/r/LocalLLaMA/comments/14dvmkr/finetuned_llm_not_getting_better_performance/
kreuzguy
self.LocalLLaMA
1970-01-01T00:00:00
0
{}
14dvmkr
false
null
t3_14dvmkr
/r/LocalLLaMA/comments/14dvmkr/finetuned_llm_not_getting_better_performance/
false
false
self
3
null
Better/Good Uncensored 30B/65B model for RP?
6
Hi there! Wondering which models are being used for RP that works good, while also being uncensored. 30B there seems to be a lot, but at 65B there's airoboros, guanaco, robin, alpaca-vicunlocked, but I'm not sure if there's more. There seems to be very few of them. For 30B, I know those same models I mentioned that a...
2023-06-20T00:21:53
https://www.reddit.com/r/LocalLLaMA/comments/14dvl34/bettergood_uncensored_30b65b_model_for_rp/
panchovix
self.LocalLLaMA
1970-01-01T00:00:00
0
{}
14dvl34
false
null
t3_14dvl34
/r/LocalLLaMA/comments/14dvl34/bettergood_uncensored_30b65b_model_for_rp/
false
false
self
6
null
QLoRA Dataset
1
[removed]
2023-06-19T23:18:18
[deleted]
2023-06-19T23:23:11
0
{}
14du2vv
false
null
t3_14du2vv
/r/LocalLLaMA/comments/14du2vv/qlora_dataset/
false
false
default
1
null
Any tips for having models adhere to chat formatting (ie speech in quotes and actions in asterisks) when using KoboldAI with SillyTavern?
6
I’ve been using Sillytavern with koboldAI running via runpod, and am just wondering if there are any settings or improved prompts I can adjust in ST to improve character’s adherence to the “chat formatting” in their replies. I’ve been using 4bit Airoboros 33B and VidUnlocked 30b and really like the content of the resu...
2023-06-19T23:09:06
https://www.reddit.com/r/LocalLLaMA/comments/14dtv5r/any_tips_for_having_models_adhere_to_chat/
BangkokPadang
self.LocalLLaMA
1970-01-01T00:00:00
0
{}
14dtv5r
false
null
t3_14dtv5r
/r/LocalLLaMA/comments/14dtv5r/any_tips_for_having_models_adhere_to_chat/
false
false
self
6
null
What are the current best uncensored models?
44
\[Bottom text\]
2023-06-19T23:03:51
https://www.reddit.com/r/LocalLLaMA/comments/14dtqw2/what_are_the_current_best_uncensored_models/
TheZorro_Sama
self.LocalLLaMA
1970-01-01T00:00:00
0
{}
14dtqw2
false
null
t3_14dtqw2
/r/LocalLLaMA/comments/14dtqw2/what_are_the_current_best_uncensored_models/
false
false
self
44
null
Conda environment is empty. Press any key to continue . . . "Press key" The windows closes and nothing happens.
1
[removed]
2023-06-19T22:55:56
https://www.reddit.com/r/LocalLLaMA/comments/14dtjq0/conda_environment_is_empty_press_any_key_to/
Vanilla_Vampi
self.LocalLLaMA
1970-01-01T00:00:00
0
{}
14dtjq0
false
null
t3_14dtjq0
/r/LocalLLaMA/comments/14dtjq0/conda_environment_is_empty_press_any_key_to/
false
false
default
1
null
Tutorial - train your own llama.cpp mini-ggml-model from scratch!
156
2023-06-19T22:26:44
https://asciinema.org/a/592303
Evening_Ad6637
asciinema.org
1970-01-01T00:00:00
0
{}
14dstqm
false
null
t3_14dstqm
/r/LocalLLaMA/comments/14dstqm/tutorial_train_your_own_llamacpp_miniggmlmodel/
false
false
https://a.thumbs.redditm…U_c7Id94NU58.jpg
156
{'enabled': False, 'images': [{'id': '1AWydW3gz9Q0_fQz7g4w5Al-pPtgsEMV3SO7mCTxX4c', 'resolutions': [{'height': 71, 'url': 'https://external-preview.redd.it/yS_hQbNoxSkIXCNqZVPaNeUVdG-auQ3TxPwcLKmlrOg.jpg?width=108&crop=smart&auto=webp&s=82435af198450db42a7f193b133cedaeca62cbc8', 'width': 108}, {'height': 143, 'url': 'h...
llama.cpp - Training your own mini ggml model from scratch works!
1
[deleted]
2023-06-19T22:24:15
[deleted]
1970-01-01T00:00:00
0
{}
14dsrer
false
null
t3_14dsrer
/r/LocalLLaMA/comments/14dsrer/llamacpp_training_your_own_mini_ggml_model_from/
false
false
default
1
null
Adapter merge for Flacon 40b instruct model (loaded in 8bit)
2
Is it possible to merge a finetuned adapter on falcon 40b loaded in ( 8 bit ) mode?
2023-06-19T22:19:30
https://www.reddit.com/r/LocalLLaMA/comments/14dsmvy/adapter_merge_for_flacon_40b_instruct_model/
unoshow
self.LocalLLaMA
1970-01-01T00:00:00
0
{}
14dsmvy
false
null
t3_14dsmvy
/r/LocalLLaMA/comments/14dsmvy/adapter_merge_for_flacon_40b_instruct_model/
false
false
self
2
null
Best LLM for legal analysis
4
I'm working on a community project to use (privacy-cleansed) legal data to fine-tune a model, with the end-goal of making the law more accessible to the public. Between us we've a decent range of tech skills, and a benefactor is providing a limited budget (a few thousand to get to launch). We're thinking of building in...
2023-06-19T21:42:54
https://www.reddit.com/r/LocalLLaMA/comments/14drnvd/best_llm_for_legal_analysis/
edinburgh1975
self.LocalLLaMA
1970-01-01T00:00:00
0
{}
14drnvd
false
null
t3_14drnvd
/r/LocalLLaMA/comments/14drnvd/best_llm_for_legal_analysis/
false
false
self
4
null
Complete noob that's been lurking for weeks but still lost: billion questions. Tutorial links or direct answers are both appreciated.
3
Pretty much the title - I have no clue wtf I'm doing, other than that I'm going to have to use that thing that one person made, that splits the model's vram usage across multiple GPUs, with more of the processing still having to run on a single GPU (thus, the thought to use a 3090 for that "main" card, with P40s as the...
2023-06-19T20:37:17
https://www.reddit.com/r/LocalLLaMA/comments/14dpxj1/complete_noob_thats_been_lurking_for_weeks_but/
CanineAssBandit
self.LocalLLaMA
1970-01-01T00:00:00
0
{}
14dpxj1
false
null
t3_14dpxj1
/r/LocalLLaMA/comments/14dpxj1/complete_noob_thats_been_lurking_for_weeks_but/
false
false
self
3
{'enabled': False, 'images': [{'id': 'veE04iaMbgI4yLvLGj2IZNV7UQfnq3n_7BmxP28dCd8', 'resolutions': [{'height': 54, 'url': 'https://external-preview.redd.it/BGOGS7KdVHomyGu2FIFx85nsQDLp_fpWWBKXxvtudf4.jpg?width=108&crop=smart&auto=webp&s=0e594332595e82a5118e08d35a2cd140c18d7571', 'width': 108}, {'height': 108, 'url': 'h...
Loading large models over more than one GPU -- neither auto-devices nor manually assigning memory seems to do its job in oobabooga
4
[removed]
2023-06-19T20:30:16
https://www.reddit.com/r/LocalLLaMA/comments/14dpqrb/loading_large_models_over_more_than_one_gpu/
tenmileswide
self.LocalLLaMA
1970-01-01T00:00:00
0
{}
14dpqrb
false
null
t3_14dpqrb
/r/LocalLLaMA/comments/14dpqrb/loading_large_models_over_more_than_one_gpu/
false
false
default
4
null
Proof of Concept: Local LLM to execute terminal comands (Here GPT-2)
37
I have written a very simple script as a proof of concept that shows the possibilities of local llms that could do work for you (even a small gpt-2 is possible). Here is an asciinema record: [ai2-shell](https://asciinema.org/a/592283) --- Just for demonstration purpose I wanted something fast, so here I used gpt-2...
2023-06-19T20:17:40
https://www.reddit.com/r/LocalLLaMA/comments/14dpf44/proof_of_concept_local_llm_to_execute_terminal/
Evening_Ad6637
self.LocalLLaMA
2023-06-20T00:14:52
0
{}
14dpf44
false
null
t3_14dpf44
/r/LocalLLaMA/comments/14dpf44/proof_of_concept_local_llm_to_execute_terminal/
false
false
self
37
{'enabled': False, 'images': [{'id': 'Lbi610UzLW-T4V3g8HL0qtAV94Hkml7JQXOWxktu6aE', 'resolutions': [{'height': 73, 'url': 'https://external-preview.redd.it/r4gQ-EIuvZdiYin01mW2La2hgWviuHKvrMwfoIMy0TM.jpg?width=108&crop=smart&auto=webp&s=0756a8326bfd71052248f788462fa4b49c1bc328', 'width': 108}, {'height': 146, 'url': 'h...
I'm new at the party. Can I make something with a GeForce GTX 1050 ti? Or is that too bad?
1
[removed]
2023-06-19T19:59:44
https://www.reddit.com/r/LocalLLaMA/comments/14doxz0/im_new_at_the_party_can_i_make_something_with_a/
thiagosanches
self.LocalLLaMA
2023-06-19T20:15:42
0
{}
14doxz0
false
null
t3_14doxz0
/r/LocalLLaMA/comments/14doxz0/im_new_at_the_party_can_i_make_something_with_a/
false
false
default
1
null
Text Generation Web UI for Chatbots (Model and Parameter Discussion)
2
So I just recently set up Oobabooga's [Text Generation Web UI](https://github.com/oobabooga/text-generation-webui) (TGWUI) and was playing around with different models and character creations within the UI. I just followed the basic example character profile that is provided to create a new character to chat with (not ...
2023-06-19T18:46:27
https://www.reddit.com/r/LocalLLaMA/comments/14dmyh9/text_generation_web_ui_for_chatbots_model_and/
psi-love
self.LocalLLaMA
1970-01-01T00:00:00
0
{}
14dmyh9
false
null
t3_14dmyh9
/r/LocalLLaMA/comments/14dmyh9/text_generation_web_ui_for_chatbots_model_and/
false
false
self
2
{'enabled': False, 'images': [{'id': '7UgRrSr917wz5Gsb3o0qEv_Yb5qwB1G4LtQ1PA31Xrg', 'resolutions': [{'height': 54, 'url': 'https://external-preview.redd.it/5yu8f94i8qqa8nDxytOB-UYUFPeMP9Vw3f1_92hfQYo.jpg?width=108&crop=smart&auto=webp&s=4a6b19d5c613e82c4afceb537d2c122a0ae9dd17', 'width': 108}, {'height': 108, 'url': 'h...
Why don't evaluation benchmarks use a proper prompt formatting?
14
I recently delved into the evaluation process of models on the [Open LLM leaderboard](https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard), and something caught my attention. If you look into, e.g., [Vicuna training code](https://github.com/lm-sys/FastChat/blob/main/fastchat/train/train.py#L96), you may n...
2023-06-19T17:58:24
https://www.reddit.com/r/LocalLLaMA/comments/14dlo95/why_dont_evaluation_benchmarks_use_a_proper/
pilot7747
self.LocalLLaMA
2023-06-19T18:09:40
0
{}
14dlo95
false
null
t3_14dlo95
/r/LocalLLaMA/comments/14dlo95/why_dont_evaluation_benchmarks_use_a_proper/
false
false
self
14
{'enabled': False, 'images': [{'id': 'EN0-abblERL52DxeoNzcxdkhvXEwLdZMJTS58Umjs64', 'resolutions': [{'height': 58, 'url': 'https://external-preview.redd.it/pnEIDVgN3O3UZSEZF8G101Cpm5FLu9i3k_abBlep_2c.jpg?width=108&crop=smart&auto=webp&s=6fbb309f983333cbaf528bd40f8d6ffb39877704', 'width': 108}, {'height': 116, 'url': 'h...