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
Can we use directml for us AMD GPU peasants?
8
Is there any way to get any sort of GPU acceleration for AMD on Windows without RocM (Cuda adapter) ? I can contribute with code too. But I just want to know the feasability of this before dwelving further, as it may be a lost cause from get-go.
2023-06-03T13:41:36
https://www.reddit.com/r/LocalLLaMA/comments/13zd9sq/can_we_use_directml_for_us_amd_gpu_peasants/
shaman-warrior
self.LocalLLaMA
1970-01-01T00:00:00
0
{}
13zd9sq
false
null
t3_13zd9sq
/r/LocalLLaMA/comments/13zd9sq/can_we_use_directml_for_us_amd_gpu_peasants/
false
false
self
8
null
faldore's based-30B ggml'ed by TheBloke!
53
2023-06-03T12:40:37
https://huggingface.co/TheBloke/based-30B-GGML
Evening_Ad6637
huggingface.co
1970-01-01T00:00:00
0
{}
13zboj2
false
null
t3_13zboj2
/r/LocalLLaMA/comments/13zboj2/faldores_based30b_ggmled_by_thebloke/
false
false
https://b.thumbs.redditm…VoDnrC5_WsAE.jpg
53
{'enabled': False, 'images': [{'id': 'EbLBPWjKHOGvBmMHCP_kObILfjSS8_rJRlsGMbJs9vo', 'resolutions': [{'height': 58, 'url': 'https://external-preview.redd.it/DFSovQXVyW-qMm1-nS4xosTiubsmb6GfFJfsorkBiKM.jpg?width=108&crop=smart&auto=webp&s=3aeb56b4fd562b7d854664cd191c33dda52e17ce', 'width': 108}, {'height': 116, 'url': 'h...
Are a Matroska-style (mkv) containers on anyone's radar for these model files? Seems like providing a model along with other data like prompt templates etc. ready for applications to access would be a good idea.
17
We're all used to movies and subtitles being packaged together. Just curious if that's being looked at for these models.
2023-06-03T12:28:30
https://www.reddit.com/r/LocalLLaMA/comments/13zbdjc/are_a_matroskastyle_mkv_containers_on_anyones/
hanoian
self.LocalLLaMA
1970-01-01T00:00:00
0
{}
13zbdjc
false
null
t3_13zbdjc
/r/LocalLLaMA/comments/13zbdjc/are_a_matroskastyle_mkv_containers_on_anyones/
false
false
self
17
null
Any website that provides benchmarks for cpu /gpu or complete pc and laptops ?(mobile)
1
[deleted]
2023-06-03T10:17:16
[deleted]
2023-06-03T15:52:01
0
{}
13z8buu
false
null
t3_13z8buu
/r/LocalLLaMA/comments/13z8buu/any_website_that_provides_benchmarks_for_cpu_gpu/
false
false
default
1
null
So I just had my first interaction with Eric’s based-30b model, and wow. To be clear there’s no context/system prompt given.
115
2023-06-03T10:02:08
https://www.reddit.com/gallery/13z7zzn
sardoa11
reddit.com
1970-01-01T00:00:00
0
{}
13z7zzn
false
null
t3_13z7zzn
/r/LocalLLaMA/comments/13z7zzn/so_i_just_had_my_first_interaction_with_erics/
false
false
https://b.thumbs.redditm…xXZVRqPqYWIE.jpg
115
null
converting llama pth with llama.cpp fails
1
[removed]
2023-06-03T08:42:03
https://www.reddit.com/r/LocalLLaMA/comments/13z683e/converting_llama_pth_with_llamacpp_fails/
wsebos
self.LocalLLaMA
1970-01-01T00:00:00
0
{}
13z683e
false
null
t3_13z683e
/r/LocalLLaMA/comments/13z683e/converting_llama_pth_with_llamacpp_fails/
false
false
default
1
null
Wild training loss when finetuning Falcon-7B
4
I am doing a finetuning of Falcon-7B on the instructions data set in the Polish language. The training loss got very spikey after 200 steps. Is that a desired behaviour? https://preview.redd.it/8l7lrn1plr3b1.png?width=2710&format=png&auto=webp&s=db0483e75a8a3a2b0a649ee89883dc93071ef233
2023-06-03T08:39:04
https://www.reddit.com/r/LocalLLaMA/comments/13z65vu/wild_training_loss_when_finetuning_falcon7b/
simonsaysindy
self.LocalLLaMA
1970-01-01T00:00:00
0
{}
13z65vu
false
null
t3_13z65vu
/r/LocalLLaMA/comments/13z65vu/wild_training_loss_when_finetuning_falcon7b/
false
false
https://b.thumbs.redditm…XYUc2bETvriQ.jpg
4
null
Speed of LLaMa CPU-based Inference Across Select System Configurations
1
2023-06-03T07:10:54
https://clulece.github.io/llamma-cpu-based-performance/
clulece
clulece.github.io
1970-01-01T00:00:00
0
{}
13z4bm7
false
null
t3_13z4bm7
/r/LocalLLaMA/comments/13z4bm7/speed_of_llama_cpubased_inference_across_select/
false
false
default
1
null
WizardLM-Uncensored-Falcon-40b
187
[https://huggingface.co/ehartford/WizardLM-Uncensored-Falcon-40b](https://huggingface.co/ehartford/WizardLM-Uncensored-Falcon-40b) It's awesome. Do no harm. In testing this and other uncensored models, I noticed the foundational model itself has opinions. That led me to build [based](https://www.reddit.com/r/LocalL...
2023-06-03T07:05:48
https://www.reddit.com/r/LocalLLaMA/comments/13z47kv/wizardlmuncensoredfalcon40b/
faldore
self.LocalLLaMA
1970-01-01T00:00:00
0
{}
13z47kv
false
null
t3_13z47kv
/r/LocalLLaMA/comments/13z47kv/wizardlmuncensoredfalcon40b/
false
false
self
187
{'enabled': False, 'images': [{'id': 'ORAxIBZ_3yhL4LlEHeC4tv_tn6yS2pUHFkWblnoy7ok', 'resolutions': [{'height': 58, 'url': 'https://external-preview.redd.it/9sOLKFuTAS59zsRyy2HS_f2Yv6XlHKn6gcB8ItWYRFY.jpg?width=108&crop=smart&auto=webp&s=36b8685e32c95380b6c5978595eeb6e8088a112b', 'width': 108}, {'height': 116, 'url': 'h...
The AI will make You an Anime in Real Time
1
[removed]
2023-06-03T06:48:38
https://v.redd.it/h2yqxr9c2r3b1
adesigne
v.redd.it
1970-01-01T00:00:00
0
{}
13z3u33
false
{'reddit_video': {'bitrate_kbps': 800, 'dash_url': 'https://v.redd.it/h2yqxr9c2r3b1/DASHPlaylist.mpd?a=1695300114%2CZDg4MWQ2MTAxZWRjNjNhMmM2NDA3Y2YyNDFhYzlkOTE4MGVhNmYxZTMxNmQ1NmYzMjdhNGMyZWQ2YjA0OWJlZA%3D%3D&v=1&f=sd', 'duration': 36, 'fallback_url': 'https://v.redd.it/h2yqxr9c2r3b1/DASH_360.mp4?source=fallback', 'hei...
t3_13z3u33
/r/LocalLLaMA/comments/13z3u33/the_ai_will_make_you_an_anime_in_real_time/
false
false
default
1
null
based-30b
148
Today I released based-30b. [https://erichartford.com/based-30b](https://erichartford.com/based-30b) [https://huggingface.co/ehartford/based-30b](https://huggingface.co/ehartford/based-30b) It's a bit difficult to explain this model. It's a window into the mind of the foundational model. A minimal dataset inspir...
2023-06-03T05:55:27
https://www.reddit.com/r/LocalLLaMA/comments/13z2nim/based30b/
faldore
self.LocalLLaMA
1970-01-01T00:00:00
0
{}
13z2nim
false
null
t3_13z2nim
/r/LocalLLaMA/comments/13z2nim/based30b/
false
false
self
148
{'enabled': False, 'images': [{'id': 'lNiLqLI9dgIkz4KVVl94-x4cbPilcjvDR324LmSB-TU', 'resolutions': [{'height': 56, 'url': 'https://external-preview.redd.it/4WQl-CBHHNvabZAceS460v6Xlqny15syzJzsLUObSs0.jpg?width=108&crop=smart&auto=webp&s=9755868df57ad87b537c145c5cef6396bd94cc69', 'width': 108}, {'height': 113, 'url': 'h...
‎Found a new iOS app that supports Oobabooga's TextGen WebUI API
11
[deleted]
2023-06-03T05:44:22
[deleted]
1970-01-01T00:00:00
0
{}
13z2epc
false
null
t3_13z2epc
/r/LocalLLaMA/comments/13z2epc/found_a_new_ios_app_that_supports_oobaboogas/
false
false
default
11
null
‎Found a new iOS app that can support Oobabooga's TextGen WebUI API
1
[deleted]
2023-06-03T05:29:16
[deleted]
1970-01-01T00:00:00
0
{}
13z22ts
false
null
t3_13z22ts
/r/LocalLLaMA/comments/13z22ts/found_a_new_ios_app_that_can_support_oobaboogas/
false
false
default
1
null
Nous-Hermes-13B
2
[removed]
2023-06-03T04:53:43
https://www.reddit.com/r/LocalLLaMA/comments/13z19qm/noushermes13b/
ArcadesOfAntiquity
self.LocalLLaMA
1970-01-01T00:00:00
0
{}
13z19qm
false
null
t3_13z19qm
/r/LocalLLaMA/comments/13z19qm/noushermes13b/
false
false
default
2
null
Beginner using llama.cpp. Does it only support GGML models?
1
[removed]
2023-06-03T04:40:27
https://www.reddit.com/r/LocalLLaMA/comments/13z0ytd/beginner_using_llamacpp_does_it_only_support_ggml/
Tasty-Lobster-8915
self.LocalLLaMA
1970-01-01T00:00:00
0
{}
13z0ytd
false
null
t3_13z0ytd
/r/LocalLLaMA/comments/13z0ytd/beginner_using_llamacpp_does_it_only_support_ggml/
false
false
default
1
null
can the oogabooga webui allow response editing like kobold?
3
i am enjoying running the 30b wizard 4bit and some of the responses it gives me are ALMOST quite good, for story generation. however i can't figure out how to "fix" the ai response so that it takes it into consideration for further responses. for example in kobold. ​ me: Write me a short story about a dancing...
2023-06-03T04:34:18
https://www.reddit.com/r/LocalLLaMA/comments/13z0tur/can_the_oogabooga_webui_allow_response_editing/
DominicanGreg
self.LocalLLaMA
1970-01-01T00:00:00
0
{}
13z0tur
false
null
t3_13z0tur
/r/LocalLLaMA/comments/13z0tur/can_the_oogabooga_webui_allow_response_editing/
false
false
self
3
null
Announcing Nous-Hermes-13b (info link in thread)
49
2023-06-03T04:21:35
https://huggingface.co/NousResearch/Nous-Hermes-13b
chakalakasp
huggingface.co
1970-01-01T00:00:00
0
{}
13z0juh
false
null
t3_13z0juh
/r/LocalLLaMA/comments/13z0juh/announcing_noushermes13b_info_link_in_thread/
false
false
https://b.thumbs.redditm…K467PnSIhNVM.jpg
49
{'enabled': False, 'images': [{'id': 'm_Ti0xgpY5STPy0z2rsutViLUnBplpRg6eu-ltLudx8', 'resolutions': [{'height': 58, 'url': 'https://external-preview.redd.it/nVDU3mR8rdRvvWg4JxHTi70Fz8bZgTOn2Y_v8msiVUY.jpg?width=108&crop=smart&auto=webp&s=f410531c5f2e3fba9616514288f67c4611681e93', 'width': 108}, {'height': 116, 'url': 'h...
30b with 16gb of RAM?
11
[removed]
2023-06-03T03:31:13
https://www.reddit.com/r/LocalLLaMA/comments/13yzdjp/30b_with_16gb_of_ram/
Covid-Plannedemic
self.LocalLLaMA
1970-01-01T00:00:00
0
{}
13yzdjp
false
null
t3_13yzdjp
/r/LocalLLaMA/comments/13yzdjp/30b_with_16gb_of_ram/
false
false
default
11
null
Paid dev gig: develop a basic LLM PEFT finetuning utility
8
I've been closely following the progress on locally hostable LLMs and PEFT, especially recent step-change developments like QLORA. But I only have very basic programming skills so things like custom finetuning is currently a bit beyond my skill level to orchestrate efficiently, though I have many ideas I want to try ou...
2023-06-03T02:42:10
https://www.reddit.com/r/LocalLLaMA/comments/13yy6co/paid_dev_gig_develop_a_basic_llm_peft_finetuning/
madmax_br5
self.LocalLLaMA
1970-01-01T00:00:00
0
{}
13yy6co
false
null
t3_13yy6co
/r/LocalLLaMA/comments/13yy6co/paid_dev_gig_develop_a_basic_llm_peft_finetuning/
false
false
self
8
null
OpenLlama will be released on Monday!
187
2023-06-03T02:17:32
https://github.com/openlm-research/open_llama/issues/36
pokeuser61
github.com
1970-01-01T00:00:00
0
{}
13yxj9b
false
null
t3_13yxj9b
/r/LocalLLaMA/comments/13yxj9b/openllama_will_be_released_on_monday/
false
false
https://b.thumbs.redditm…yHLneHmxnvkY.jpg
187
{'enabled': False, 'images': [{'id': 'TD_Kuk7E7EbCcto1K3q7RSdRgIrw8gmbHKMgRYfgC6Y', 'resolutions': [{'height': 54, 'url': 'https://external-preview.redd.it/E-uW-DwIqoL82K79b506qercIeG-iaDq5iKb_7iCuyY.jpg?width=108&crop=smart&auto=webp&s=2da4f4c3ecb2c415922d527fdca4529fdf216945', 'width': 108}, {'height': 108, 'url': 'h...
Issues installing vicuna and alpaca. Nothing happens when i run the .bat file
1
[removed]
2023-06-03T01:17:33
https://www.reddit.com/r/LocalLLaMA/comments/13yvyj7/issues_installing_vicuna_and_alpaca_nothing/
East-Mirror-8088
self.LocalLLaMA
1970-01-01T00:00:00
0
{}
13yvyj7
false
null
t3_13yvyj7
/r/LocalLLaMA/comments/13yvyj7/issues_installing_vicuna_and_alpaca_nothing/
false
false
default
1
null
LLM to mimic artist style in low-resource language
4
I'm working on a project to see how feasible it is to finetune LLMs on data of figures whose is in (comparatively) low-resource languages (like Urdu), and have this model function as a chatbot. All the recent approaches with PEFT and QLoRA and 8-bit optimizers and stuff are insane and this seems more doable than ever b...
2023-06-02T22:59:40
https://www.reddit.com/r/LocalLLaMA/comments/13yskxu/llm_to_mimic_artist_style_in_lowresource_language/
bataslipper
self.LocalLLaMA
1970-01-01T00:00:00
0
{}
13yskxu
false
null
t3_13yskxu
/r/LocalLLaMA/comments/13yskxu/llm_to_mimic_artist_style_in_lowresource_language/
false
false
self
4
null
How to run Guanaco 65B with llama.cpp?
1
[deleted]
2023-06-02T22:46:15
[deleted]
1970-01-01T00:00:00
0
{}
13ys75a
false
null
t3_13ys75a
/r/LocalLLaMA/comments/13ys75a/how_to_run_guanaco_65b_with_llamacpp/
false
false
default
1
null
C Transformers: Python bindings for GGML models
1
[removed]
2023-06-02T22:29:44
https://www.reddit.com/r/LocalLLaMA/comments/13yrq53/c_transformers_python_bindings_for_ggml_models/
Ravindra-Marella
self.LocalLLaMA
1970-01-01T00:00:00
0
{}
13yrq53
false
null
t3_13yrq53
/r/LocalLLaMA/comments/13yrq53/c_transformers_python_bindings_for_ggml_models/
false
false
default
1
null
Is anybody running this on Runpod instead of their pc?
1
Looking for a tutorial on how to run it on Runpod anyone have one?
2023-06-02T22:11:07
https://www.reddit.com/r/LocalLLaMA/comments/13yr6np/is_anybody_running_this_on_runpod_instead_of/
ricketpipe
self.LocalLLaMA
1970-01-01T00:00:00
0
{}
13yr6np
false
null
t3_13yr6np
/r/LocalLLaMA/comments/13yr6np/is_anybody_running_this_on_runpod_instead_of/
false
false
self
1
null
Falcon OpenAssistant?👀
16
https://huggingface.co/OpenAssistant/falcon-40b-sft-top1-560 It's too late for me but I will test this out tomorrow. I have high hopes for this model. And the ones that will follow. It's fully open source and the dataset is actually good. Idk what they trained flacon 40b instruct on. But it was dogshit. Edit: Sample...
2023-06-02T21:56:35
https://www.reddit.com/r/LocalLLaMA/comments/13yqr4n/falcon_openassistant/
NeatManagement3
self.LocalLLaMA
2023-06-03T06:52:33
0
{}
13yqr4n
false
null
t3_13yqr4n
/r/LocalLLaMA/comments/13yqr4n/falcon_openassistant/
false
false
self
16
{'enabled': False, 'images': [{'id': 'XZHgrkxmT3BbfwoNENzcky0LC_hx5L_ZV6vbCAuGNS4', 'resolutions': [{'height': 58, 'url': 'https://external-preview.redd.it/WO_-pYnWYruCRoQkBk4IjWdE944h9FSsRsu65O4-9mI.jpg?width=108&crop=smart&auto=webp&s=3d221c39d8180eb851b73f36cfcd3f9bafe8c513', 'width': 108}, {'height': 116, 'url': 'h...
Why is linebreak not in LLaMA tokenizer vocabulary?
1
[deleted]
2023-06-02T21:56:21
[deleted]
1970-01-01T00:00:00
0
{}
13yqqww
false
null
t3_13yqqww
/r/LocalLLaMA/comments/13yqqww/why_is_linebreak_not_in_llama_tokenizer_vocabulary/
false
false
default
1
null
Dedicated server build help/questions
6
Hi, I'd like to build myself a dedicated server exclusively for running LLMs. If you've done this at all, link to PCPartPicker or any ould be highly appreciated. I've built my own PC, but never built a server before, idk if r/buildapc would be more appropriate for this post or not. I'm hoping to be able to run curren...
2023-06-02T21:35:05
https://www.reddit.com/r/LocalLLaMA/comments/13yq3io/dedicated_server_build_helpquestions/
Stupid_and_confused
self.LocalLLaMA
1970-01-01T00:00:00
0
{}
13yq3io
false
null
t3_13yq3io
/r/LocalLLaMA/comments/13yq3io/dedicated_server_build_helpquestions/
false
false
self
6
null
Q: Best step-by-step guides to finetuning MPT / Falcon models
13
I've found u/faldore's post on [finetuning WizardLM](https://erichartford.com/uncensored-models#heading-lets-get-down-to-business-uncensoring-wizardlm) on Llama very helpful. I'm curious if there are other step-by-step best practice guides / scripts / discords out there for finetuning Falcon or MPT? Is [Llama-X's tr...
2023-06-02T20:42:38
https://www.reddit.com/r/LocalLLaMA/comments/13yohs2/q_best_stepbystep_guides_to_finetuning_mpt_falcon/
peakfish
self.LocalLLaMA
1970-01-01T00:00:00
0
{}
13yohs2
false
null
t3_13yohs2
/r/LocalLLaMA/comments/13yohs2/q_best_stepbystep_guides_to_finetuning_mpt_falcon/
false
false
self
13
{'enabled': False, 'images': [{'id': 'WFmw_IqbCMxC5TS9tSA47Pd_31AlpxTaJyAIcZxVjpo', 'resolutions': [{'height': 56, 'url': 'https://external-preview.redd.it/r8blyjeT-tQk_JBraLsXAWI69FKM0k851z0NB4nowI8.jpg?width=108&crop=smart&auto=webp&s=673e0261a4ce3e2d0a2ce43c3a573218551c26e8', 'width': 108}, {'height': 113, 'url': 'h...
GPU Problem running manticore 13b on koboldcpp
1
[removed]
2023-06-02T20:32:18
[deleted]
1970-01-01T00:00:00
0
{}
13yo6q2
false
null
t3_13yo6q2
/r/LocalLLaMA/comments/13yo6q2/gpu_problem_running_manticore_13b_on_koboldcpp/
false
false
default
1
null
Repos and tutorials for a full finetune (not LoRA)
8
Hi again, looking to learn more about the full finetunning process and can't seem to get the right point. I have experimented with LoRA finetunning and although great i'm trying to compare and constract the differences between the two beyond what a few whispers say here and there. Any repos documentations on how to do ...
2023-06-02T19:42:52
https://www.reddit.com/r/LocalLLaMA/comments/13ymrdh/repos_and_tutorials_for_a_full_finetune_not_lora/
orangeatom
self.LocalLLaMA
1970-01-01T00:00:00
0
{}
13ymrdh
false
null
t3_13ymrdh
/r/LocalLLaMA/comments/13ymrdh/repos_and_tutorials_for_a_full_finetune_not_lora/
false
false
self
8
null
The Curse of Recursion: Training on Generated Data Makes Models Forget
41
[https://huggingface.co/papers/2305.17493](https://huggingface.co/papers/2305.17493) ​ \> What will happen to GPT-{n} once LLMs contribute much of the language found online? We find that use of model-generated content in training causes irreversible defects in the resulting models, where tails of the original ...
2023-06-02T19:40:20
https://www.reddit.com/r/LocalLLaMA/comments/13ymov8/the_curse_of_recursion_training_on_generated_data/
AutomataManifold
self.LocalLLaMA
1970-01-01T00:00:00
0
{}
13ymov8
false
null
t3_13ymov8
/r/LocalLLaMA/comments/13ymov8/the_curse_of_recursion_training_on_generated_data/
false
false
self
41
{'enabled': False, 'images': [{'id': 'yS-II-gkr832EGDXHL6d0I532Ke7FNxRNlN2uQjsQ4w', 'resolutions': [{'height': 58, 'url': 'https://external-preview.redd.it/EDd9me0Ws0OoWHGGF9KcAyljEEx1s0Ial6Nn6nuPEbA.jpg?width=108&crop=smart&auto=webp&s=e5b70c023ca473415222020d568617d36bfccc89', 'width': 108}, {'height': 116, 'url': 'h...
Whisper.cpp
2
[removed]
2023-06-02T18:15:33
https://www.reddit.com/r/LocalLLaMA/comments/13yk6r4/whispercpp/
_omid_
self.LocalLLaMA
2023-06-02T18:31:11
0
{}
13yk6r4
false
null
t3_13yk6r4
/r/LocalLLaMA/comments/13yk6r4/whispercpp/
false
false
default
2
null
A helpful comparison I found
1
2023-06-02T18:12:47
https://www.salkantaytrekmachu.com/en/travel-blog/llama-vs-alpaca-vs-vicuna-and-guanaco
Mediocre_Comment_368
salkantaytrekmachu.com
1970-01-01T00:00:00
0
{}
13yk442
false
null
t3_13yk442
/r/LocalLLaMA/comments/13yk442/a_helpful_comparison_i_found/
false
false
default
1
null
Favorite models and prompts for making Stable Diffusion prompts?
6
I have been experimenting with WizardLM 30B (but I run out of VRAM a lot due to context window) and 13B but the results trying to create a character that can interpret instructions for making Stable Diffusion prompts. So far I've been trying variations of, """ Pretend you are an expert on generating prompts for AI t...
2023-06-02T17:53:19
https://www.reddit.com/r/LocalLLaMA/comments/13yjlw5/favorite_models_and_prompts_for_making_stable/
EarthquakeBass
self.LocalLLaMA
1970-01-01T00:00:00
0
{}
13yjlw5
false
null
t3_13yjlw5
/r/LocalLLaMA/comments/13yjlw5/favorite_models_and_prompts_for_making_stable/
false
false
self
6
null
Is there an api for hugging face LLMs
3
Hey there, i don't know if this is the appropriate subreddit to post. I'm new to this whole open source LLMs field, and i was wondering if hugging face or any other platform offers an api to use the LLMs hosted there like the openai api. Cuz i don't even remotely have the necessary hardware to install it locally. And i...
2023-06-02T17:07:15
https://www.reddit.com/r/LocalLLaMA/comments/13yieyt/is_there_an_api_for_hugging_face_llms/
dude_dz
self.LocalLLaMA
1970-01-01T00:00:00
0
{}
13yieyt
false
null
t3_13yieyt
/r/LocalLLaMA/comments/13yieyt/is_there_an_api_for_hugging_face_llms/
false
false
self
3
null
Implement Generative Agent with Local LLM, Guidance, and Langchain (Full Features)
77
The source code: [https://github.com/QuangBK/generativeAgent\_LLM](https://github.com/QuangBK/generativeAgent_LLM) After making a ReAct agent work well with Guidance, I decided to implement Generative Agent from the "Generative Agents: Interactive Simulacra of Human Behavior" paper. I found some implementations on Gi...
2023-06-02T16:07:58
https://www.reddit.com/r/LocalLLaMA/comments/13ygukg/implement_generative_agent_with_local_llm/
Unhappy-Reaction2054
self.LocalLLaMA
1970-01-01T00:00:00
0
{}
13ygukg
false
null
t3_13ygukg
/r/LocalLLaMA/comments/13ygukg/implement_generative_agent_with_local_llm/
false
false
self
77
{'enabled': False, 'images': [{'id': '413Uzj91iJYORaUfYOPQAylLeg-hQlrcGMV6fwEwttM', 'resolutions': [{'height': 54, 'url': 'https://external-preview.redd.it/CfCNr8TlZMF7Hl-9sOdZ1dsHpuCLlgwGyIUC03EAuvQ.jpg?width=108&crop=smart&auto=webp&s=fbe3bf9d09acea66aa671d3cf7076bb01072ebf6', 'width': 108}, {'height': 108, 'url': 'h...
Anybody tried Lion: Adversarial Distillation of Closed-Source Large Language Model?
11
Accidentally found the Lion model. [https://github.com/YJiangcm/Lion](https://github.com/YJiangcm/Lion) [https://huggingface.co/YuxinJiang/Lion](https://huggingface.co/YuxinJiang/Lion) [https://b79eaa18f7e179e9.gradio.app/](https://b79eaa18f7e179e9.gradio.app/) Bold claims on the github: ​ https://previe...
2023-06-02T15:54:41
https://www.reddit.com/r/LocalLLaMA/comments/13ygi0f/anybody_tried_lion_adversarial_distillation_of/
eggandbacon_0056
self.LocalLLaMA
1970-01-01T00:00:00
0
{}
13ygi0f
false
null
t3_13ygi0f
/r/LocalLLaMA/comments/13ygi0f/anybody_tried_lion_adversarial_distillation_of/
false
false
https://a.thumbs.redditm…2hSOrn1bbCH4.jpg
11
{'enabled': False, 'images': [{'id': 'aSiaUZ6u56xhUIX5sMo0Ofvm-4sQWSJuXQFc--hE_DI', 'resolutions': [{'height': 54, 'url': 'https://external-preview.redd.it/TKE3NazUGT6hcal80aKeiXUGv6S53bXx_YE8zdn2tsw.jpg?width=108&crop=smart&auto=webp&s=422c98a994eab6af15bcb5684bb0ed4a8e45a5c5', 'width': 108}, {'height': 108, 'url': 'h...
What kind of results are you seeing with semantic search? Any model recommendations?
7
I've set up the Langchain similarity\_search example with my own text, and I've tried a few different models including wizard-vicuna-13B.ggmlv3.q4\_0.bin. The results are terrible/unusable - it's unable to provide meaningful similarity scores for simple documents (3 sentences about a specific topic). I see there are ...
2023-06-02T15:33:13
https://www.reddit.com/r/LocalLLaMA/comments/13yfxzk/what_kind_of_results_are_you_seeing_with_semantic/
rhinomansufferer
self.LocalLLaMA
2023-06-02T15:56:10
0
{}
13yfxzk
false
null
t3_13yfxzk
/r/LocalLLaMA/comments/13yfxzk/what_kind_of_results_are_you_seeing_with_semantic/
false
false
self
7
{'enabled': False, 'images': [{'id': 'JkuGKvIKQ-R8TvHZovrrI6-YNuELMZyo6OdE5W_o7_w', 'resolutions': [{'height': 54, 'url': 'https://external-preview.redd.it/896cbqV6KZ-AwFxyL8fkoGH5rLzc2tX0K-Vm4IpUIIA.jpg?width=108&crop=smart&auto=webp&s=bc301aa3e4b0d6f5ca2ac9e5ec24a931f5cc4eb4', 'width': 108}, {'height': 108, 'url': 'h...
Incorporating llama into an app [early development insight]
21
2023-06-02T15:12:11
https://v.redd.it/typ10qu8fm3b1
frapastique
v.redd.it
1970-01-01T00:00:00
0
{}
13yfehx
false
{'reddit_video': {'bitrate_kbps': 4800, 'dash_url': 'https://v.redd.it/typ10qu8fm3b1/DASHPlaylist.mpd?a=1695281603%2CNzMwYzFkYzFhZGVjMDgxY2QxYTYwMmNmMzAwNWYxOTE0NzYyZjViZWM3MDA3YWU1NTA3NWNhMTMwOTkyNmZlNg%3D%3D&v=1&f=sd', 'duration': 43, 'fallback_url': 'https://v.redd.it/typ10qu8fm3b1/DASH_1080.mp4?source=fallback', 'h...
t3_13yfehx
/r/LocalLLaMA/comments/13yfehx/incorporating_llama_into_an_app_early_development/
false
false
https://b.thumbs.redditm…VcOg5LZwvH7A.jpg
21
{'enabled': False, 'images': [{'id': 'dPxtyGfKWXjETW--lejpfdIs6pziQApLyeueOKmWDac', 'resolutions': [{'height': 216, 'url': 'https://external-preview.redd.it/vWL_mXeVZvIS1R3AjE7IAo6VtdnqXss7xpPHtqkSt2o.png?width=108&crop=smart&format=pjpg&auto=webp&s=3f4a03bfe57921b3a28ebd8e18407303576a3fa1', 'width': 108}, {'height': 4...
Manticore-13B-Chat-Pyg-Guanaco-GGML-q4_0 - America's Next Top Model!
92
No but seriously, wtf? Can you guys try this: https://huggingface.co/mindrage/Manticore-13B-Chat-Pyg-Guanaco-GGML-q4_0 How did this 13b, and not even q8_0, beat most 30b's in my spreadsheet? https://docs.google.com/spreadsheets/d/1NgHDxbVWJFolq8bLvLkuPWKC7i_R6I6W/edit#gid=2011456595 My test settings: Kobold 1.27...
2023-06-02T15:08:12
https://www.reddit.com/r/LocalLLaMA/comments/13yfask/manticore13bchatpygguanacoggmlq4_0_americas_next/
YearZero
self.LocalLLaMA
2023-06-02T15:20:32
0
{}
13yfask
false
null
t3_13yfask
/r/LocalLLaMA/comments/13yfask/manticore13bchatpygguanacoggmlq4_0_americas_next/
false
false
self
92
{'enabled': False, 'images': [{'id': 'lEm-tjB8J9gt1qmj9MgEacXbDjsDUlJEvPwFaDXdAbA', 'resolutions': [{'height': 58, 'url': 'https://external-preview.redd.it/yFcPdI7ifPfEiuv0bg0sDV3LWDaaxq7RaFXcEj-4Y1k.jpg?width=108&crop=smart&auto=webp&s=33f4f12ee3c140a15e0c49eab0f1822267743fc0', 'width': 108}, {'height': 116, 'url': 'h...
Which models do you recommend for an AI school assistant in EU?
6
Hi, I'm teacher in an european school. Currently my task is to research and prototype an AI learning assistant which walks students individually through a curriculum module for learning HTML. Are there any go-to models or service providers around yet? I see there are many OSS LLMs like llama and such, and there a...
2023-06-02T14:48:42
https://www.reddit.com/r/LocalLLaMA/comments/13yesx9/which_models_do_you_recommend_for_an_ai_school/
the_embassy_official
self.LocalLLaMA
1970-01-01T00:00:00
0
{}
13yesx9
false
null
t3_13yesx9
/r/LocalLLaMA/comments/13yesx9/which_models_do_you_recommend_for_an_ai_school/
false
false
self
6
null
New quantization method AWQ outperforms GPTQ in 4-bit and 3-bit with 1.45x speedup and works with multimodal LLMs
334
Paper: [https://arxiv.org/abs/2306.00978](https://arxiv.org/abs/2306.00978) GitHub: [https://github.com/mit-han-lab/llm-awq](https://github.com/mit-han-lab/llm-awq) Some excerpts: >In this paper, we propose Activation-aware Weight Quantization (AWQ), a hardware-friendly low-bit weight-only quantization method for LL...
2023-06-02T14:35:32
https://www.reddit.com/r/LocalLLaMA/comments/13yehfn/new_quantization_method_awq_outperforms_gptq_in/
Spiritual-Roll3062
self.LocalLLaMA
1970-01-01T00:00:00
0
{}
13yehfn
false
null
t3_13yehfn
/r/LocalLLaMA/comments/13yehfn/new_quantization_method_awq_outperforms_gptq_in/
false
false
https://a.thumbs.redditm…V14JREnmlfY4.jpg
334
{'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...
LLaMA for language translation? Or alternatives?
11
What is the best open LLM out there for language translation? Specifically: English to: Chinese, Japanese, German, French, Spanish, Arabic ... (most popular languages) GPT 3.5 performs well on all of these. ChatGPT3.5 is quite good but unfortunately it's not open-source. :( Is there any alternative or list of othe...
2023-06-02T14:32:53
https://www.reddit.com/r/LocalLLaMA/comments/13yef4q/llama_for_language_translation_or_alternatives/
22_YEAR_OLD_LOOMER
self.LocalLLaMA
2023-06-02T15:29:02
0
{}
13yef4q
false
null
t3_13yef4q
/r/LocalLLaMA/comments/13yef4q/llama_for_language_translation_or_alternatives/
false
false
self
11
null
Training BERT from scratch on an 8GB 3060
20
2023-06-02T14:22:29
https://sidsite.com/posts/bert-from-scratch/
kryptkpr
sidsite.com
1970-01-01T00:00:00
0
{}
13ye620
false
null
t3_13ye620
/r/LocalLLaMA/comments/13ye620/training_bert_from_scratch_on_an_8gb_3060/
false
false
default
20
null
Is it possible , PrivateGPT ?
0
[removed]
2023-06-02T13:31:52
https://www.reddit.com/r/LocalLLaMA/comments/13ycwrw/is_it_possible_privategpt/
Curious-Ninja150627
self.LocalLLaMA
1970-01-01T00:00:00
0
{}
13ycwrw
false
null
t3_13ycwrw
/r/LocalLLaMA/comments/13ycwrw/is_it_possible_privategpt/
false
false
default
0
null
Guanaco-65B, How to cool passive A40?
4
I recently acquired an NVIDIA A40 to be able to run larger models. Does anyone have a suggestion on how to cool these cards? I have it sitting in a mid-tower (ATX) case vertically aligned. Any ideas? ​ https://preview.redd.it/73hg4mruwl3b1.png?width=2304&format=png&auto=webp&s=3be48b998d314349a25aa04efceaf068d...
2023-06-02T13:29:25
https://www.reddit.com/r/LocalLLaMA/comments/13ycufo/guanaco65b_how_to_cool_passive_a40/
muchCode
self.LocalLLaMA
1970-01-01T00:00:00
0
{}
13ycufo
false
null
t3_13ycufo
/r/LocalLLaMA/comments/13ycufo/guanaco65b_how_to_cool_passive_a40/
false
false
https://b.thumbs.redditm…UDCDMcIPZ4MI.jpg
4
null
Best CPU Based Models & GPU recommendation
10
Hello wonderful community, things indeed are changing daily. I am trying to connect the dots. **Let's say you have:** **CPU**: 12 x Core **RAM**: 64GB **GPU**: 🥔 Nvidia Quatro 4GB * How can we know which model supports **CPU** only rendering? * Which one does it best? * How do know how much **RAM** model needs?...
2023-06-02T07:29:07
https://www.reddit.com/r/LocalLLaMA/comments/13y5yrg/best_cpu_based_models_gpu_recommendation/
polytect
self.LocalLLaMA
1970-01-01T00:00:00
0
{}
13y5yrg
false
null
t3_13y5yrg
/r/LocalLLaMA/comments/13y5yrg/best_cpu_based_models_gpu_recommendation/
false
false
self
10
null
Seeking Advice for a New Machine Optimized for LLMs (Large Language Models), Max Budget €3,000
16
Hey fellow Redditors! I’m seeking some guidance on purchasing a new machine optimized for working with large language models (LLMs). As an avid user of language models and AI technologies, I’ve outgrown my current setup and want to invest in a more powerful and efficient system. With a maximum budget of €3,000, I’m l...
2023-06-02T07:00:16
https://www.reddit.com/r/LocalLLaMA/comments/13y5i32/seeking_advice_for_a_new_machine_optimized_for/
_omid_
self.LocalLLaMA
1970-01-01T00:00:00
0
{}
13y5i32
false
null
t3_13y5i32
/r/LocalLLaMA/comments/13y5i32/seeking_advice_for_a_new_machine_optimized_for/
false
false
self
16
null
Actually good git repo chat?
9
[deleted]
2023-06-02T06:57:23
[deleted]
1970-01-01T00:00:00
0
{}
13y5gdz
false
null
t3_13y5gdz
/r/LocalLLaMA/comments/13y5gdz/actually_good_git_repo_chat/
false
false
default
9
null
Need Help GUYS, Private GPT?
0
[removed]
2023-06-02T06:34:47
https://www.reddit.com/r/LocalLLaMA/comments/13y53iy/need_help_guys_private_gpt/
Curious-Ninja150627
self.LocalLLaMA
1970-01-01T00:00:00
0
{}
13y53iy
false
null
t3_13y53iy
/r/LocalLLaMA/comments/13y53iy/need_help_guys_private_gpt/
false
false
default
0
null
MLC LLM invented a new GPU: GeForce® RTX™ 2060
1
2023-06-02T05:39:43
https://i.redd.it/jok6x4n4lj3b1.png
cesiumdragon
i.redd.it
1970-01-01T00:00:00
0
{}
13y46n7
false
null
t3_13y46n7
/r/LocalLLaMA/comments/13y46n7/mlc_llm_invented_a_new_gpu_geforce_rtxγäó_2060/
false
false
default
1
null
Blockwise Parallel Transformer for Long Context Large Models
42
[https://www.reddit.com/r/MachineLearning/comments/13xyvgt/r\_blockwise\_parallel\_transformer\_for\_long\_context/](https://www.reddit.com/r/MachineLearning/comments/13xyvgt/r_blockwise_parallel_transformer_for_long_context/) TLDR: Now it's possible to train models with up to 4x context length (compared to memory-eff...
2023-06-02T03:04:24
https://www.reddit.com/r/LocalLLaMA/comments/13y1dvr/blockwise_parallel_transformer_for_long_context/
IxinDow
self.LocalLLaMA
1970-01-01T00:00:00
0
{}
13y1dvr
false
null
t3_13y1dvr
/r/LocalLLaMA/comments/13y1dvr/blockwise_parallel_transformer_for_long_context/
false
false
https://b.thumbs.redditm…WQxcPnWtez0Y.jpg
42
null
Please help, low end desktop setup config optimization with simple installer | webui
3
Hey guys this is my first post here, I seriously appreciate any and all help you may be able to provide. My specs are quite dated:4GB GTX 970, 16GB DDr4 RAM, i5 6600 I've been wanting to dive in for a bit and now here I am. I used the simple installer tool found in this sub's wiki, and when prompted I selected to ...
2023-06-02T02:33:42
https://www.reddit.com/r/LocalLLaMA/comments/13y0ru8/please_help_low_end_desktop_setup_config/
JakeGrudge
self.LocalLLaMA
1970-01-01T00:00:00
0
{}
13y0ru8
false
null
t3_13y0ru8
/r/LocalLLaMA/comments/13y0ru8/please_help_low_end_desktop_setup_config/
false
false
self
3
null
Introducing Basaran: self-hosted open-source alternative to the OpenAI text completion API
92
Hi [r/LocalLLaMA/](https://www.reddit.com/r/LocalLLaMA/)! I made an OpenAI-compatible streaming API (and playground) for your 🤗 Transformers-based text generation models, including LLaMA and variants built upon it! GitHub: [https://github.com/hyperonym/basaran](https://github.com/hyperonym/basaran) https://i.redd.i...
2023-06-02T02:06:25
https://www.reddit.com/r/LocalLLaMA/comments/13y07tr/introducing_basaran_selfhosted_opensource/
peakji
self.LocalLLaMA
1970-01-01T00:00:00
0
{}
13y07tr
false
null
t3_13y07tr
/r/LocalLLaMA/comments/13y07tr/introducing_basaran_selfhosted_opensource/
false
false
https://b.thumbs.redditm…EJl9Onuz_j0k.jpg
92
{'enabled': False, 'images': [{'id': 'ULhu-hhgGrIZ4_s0EyxKMLeQyzdIZzAbZqxRGaRTiZw', 'resolutions': [{'height': 54, 'url': 'https://external-preview.redd.it/tSKPJVWaBxLL-Q8W_54xTZIYUTbA5h92lyN5vWzJJ44.jpg?width=108&crop=smart&auto=webp&s=c4dd62da316fd6acb6540b47413c934b4d4b4410', 'width': 108}, {'height': 108, 'url': 'h...
Best Confguration & Settings for my low end setup? using text generation webui tool
1
[removed]
2023-06-02T01:42:12
https://www.reddit.com/r/LocalLLaMA/comments/13xzpy6/best_confguration_settings_for_my_low_end_setup/
Sad-Reflection-7995
self.LocalLLaMA
1970-01-01T00:00:00
0
{}
13xzpy6
false
null
t3_13xzpy6
/r/LocalLLaMA/comments/13xzpy6/best_confguration_settings_for_my_low_end_setup/
false
false
default
1
null
Found an iOS app for TestFlight that allows you to run LLMs locally
12
From the download page: “Vicuna-7B takes 4GB of RAM and RedPajama-3B takes 2.2GB to run. Considering the iOS and other running applications, we will need a recent iPhone with 6GB for Vicuna-7B or 4GB for RedPajama-3B to run the app. The application is only tested on iPhone 14 Pro Max, iPhone 14 Pro and iPhone 12 Pro.”
2023-06-02T01:39:48
https://mlc.ai/mlc-llm/#iphone
HemisphereGuide
mlc.ai
1970-01-01T00:00:00
0
{}
13xzo5i
false
null
t3_13xzo5i
/r/LocalLLaMA/comments/13xzo5i/found_an_ios_app_for_testflight_that_allows_you/
false
false
default
12
null
The Best 8GB Macbook Pro Setup?
0
[removed]
2023-06-02T00:45:29
https://www.reddit.com/r/LocalLLaMA/comments/13xyj7e/the_best_8gb_macbook_pro_setup/
TechnologicalFreedom
self.LocalLLaMA
1970-01-01T00:00:00
0
{}
13xyj7e
false
null
t3_13xyj7e
/r/LocalLLaMA/comments/13xyj7e/the_best_8gb_macbook_pro_setup/
false
false
default
0
null
What is the SOTA instruct model for code generation?
1
I'm looking for the most coherent model that will take a description of a function or component and spit it out (EX, Make a react component that opens a dialog, which has two named text boxes) rather than githubpilot/ghostwiter autocomplete style code gen. Ty in advance lol P
2023-06-01T23:02:03
https://www.reddit.com/r/LocalLLaMA/comments/13xw7np/what_is_the_sota_instruct_model_for_code/
FreezeproofViola
self.LocalLLaMA
1970-01-01T00:00:00
0
{}
13xw7np
false
null
t3_13xw7np
/r/LocalLLaMA/comments/13xw7np/what_is_the_sota_instruct_model_for_code/
false
false
self
1
null
Best architecture for Running 13B Parameter Models
4
I've been experimenting with some 13B models + I'm trying to get the fastest performance out of it. So far, have been using EC2 (g4dn.2xlarge) to run some GPTQ models. Anyone experimented with scaling up GPU power on these models before? Wondering if it's worth investing in a better machine.
2023-06-01T22:58:48
https://www.reddit.com/r/LocalLLaMA/comments/13xw4k4/best_architecture_for_running_13b_parameter_models/
robopika
self.LocalLLaMA
1970-01-01T00:00:00
0
{}
13xw4k4
false
null
t3_13xw4k4
/r/LocalLLaMA/comments/13xw4k4/best_architecture_for_running_13b_parameter_models/
false
false
self
4
null
What did I do wrong?(galactica 125m)
1
2023-06-01T22:54:32
https://i.redd.it/p3fxwwktkh3b1.jpg
bot-333
i.redd.it
1970-01-01T00:00:00
0
{}
13xw12b
false
null
t3_13xw12b
/r/LocalLLaMA/comments/13xw12b/what_did_i_do_wronggalactica_125m/
false
false
default
1
null
Celebrating LocalLLama: Embracing Enthusiasm while Learning from Crypto's Lessons
0
[removed]
2023-06-01T22:42:40
[deleted]
1970-01-01T00:00:00
0
{}
13xvqzj
false
null
t3_13xvqzj
/r/LocalLLaMA/comments/13xvqzj/celebrating_localllama_embracing_enthusiasm_while/
false
false
default
0
null
News or Blog Article Build?
1
I enjoy writing but generating content every day becomes monotonous and is its own kind of horrible grind. If i can get my 4090 to write a few basic articles for me every couple days and then i give them a quick edit, that would be an awesome workflow improvement for me! Any local LLaMAers out there who are happy wit...
2023-06-01T22:38:10
https://www.reddit.com/r/LocalLLaMA/comments/13xvn1y/news_or_blog_article_build/
frostpen
self.LocalLLaMA
1970-01-01T00:00:00
0
{}
13xvn1y
false
null
t3_13xvn1y
/r/LocalLLaMA/comments/13xvn1y/news_or_blog_article_build/
false
false
self
1
null
A guy created a 3D game model of himself with AIs
8
[removed]
2023-06-01T20:58:38
https://v.redd.it/z8tejby50h3b1
adesigne
v.redd.it
1970-01-01T00:00:00
0
{}
13xt63e
false
{'reddit_video': {'bitrate_kbps': 4800, 'dash_url': 'https://v.redd.it/z8tejby50h3b1/DASHPlaylist.mpd?a=1695262629%2COWI3Yzc1NjdlZmRkODFlYWQ4NGM1OWE4NGZiMTg5NjQxODc5MTkzYjlhZmI1ZjY4MTMxNzQ4YTQ3MWNkZTdiZA%3D%3D&v=1&f=sd', 'duration': 57, 'fallback_url': 'https://v.redd.it/z8tejby50h3b1/DASH_1080.mp4?source=fallback', 'h...
t3_13xt63e
/r/LocalLLaMA/comments/13xt63e/a_guy_created_a_3d_game_model_of_himself_with_ais/
false
false
default
8
null
Best model to transform data?
10
[deleted]
2023-06-01T20:34:18
[deleted]
2023-06-21T11:43:02
0
{}
13xsk4q
false
null
t3_13xsk4q
/r/LocalLLaMA/comments/13xsk4q/best_model_to_transform_data/
false
false
default
10
null
Commercial Opensource LLM
4
Hello [Disclaimer: i am sorry if this question was answered before and i'm violating the Rules of this subreddit. Please direct me to the place where i can find some answers before banning me.] I am trying to find the best (or Just a couple of capable) Opensource LLM's available for Commercial Use. Do you have any...
2023-06-01T20:29:56
https://www.reddit.com/r/LocalLLaMA/comments/13xsfz0/commercial_opensource_llm/
schmul02
self.LocalLLaMA
1970-01-01T00:00:00
0
{}
13xsfz0
false
null
t3_13xsfz0
/r/LocalLLaMA/comments/13xsfz0/commercial_opensource_llm/
false
false
self
4
null
Script to convert Falcon to ggml
1
[removed]
2023-06-01T19:37:06
https://www.reddit.com/r/LocalLLaMA/comments/13xr2ul/script_to_convert_falcon_to_ggml/
Yo-Momma-Loves-AI
self.LocalLLaMA
1970-01-01T00:00:00
0
{}
13xr2ul
false
null
t3_13xr2ul
/r/LocalLLaMA/comments/13xr2ul/script_to_convert_falcon_to_ggml/
false
false
default
1
null
Chat with your data locally and privately on CPU with LocalDocs: GPT4All's first plugin!
78
2023-06-01T17:52:09
https://twitter.com/nomic_ai/status/1664316537736511500
NomicAI
twitter.com
1970-01-01T00:00:00
0
{}
13xod69
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 now have plugins! 💥<br><br>GPT4All LocalDocs allows you chat with your private data!<br><br>- Drag and drop files in...
t3_13xod69
/r/LocalLLaMA/comments/13xod69/chat_with_your_data_locally_and_privately_on_cpu/
false
false
https://b.thumbs.redditm…QqE9H7IwCARg.jpg
78
{'enabled': False, 'images': [{'id': 'W69-zhaSfq2z-P9ItUZjFVRDaoMYsC2N00hrJK0Nubk', 'resolutions': [{'height': 64, 'url': 'https://external-preview.redd.it/R495KtLsDZ9RC_ZlhtDsnFrKyHr0NXpIeDCjyEFGoxc.jpg?width=108&crop=smart&auto=webp&s=5b2efb766869ed6fcb3c99de88aef9b0f1344678', 'width': 108}], 'source': {'height': 83,...
LLaMa-Adapter Multimodal supporting text, image, audio, and video inputs
15
2023-06-01T17:48:56
https://twitter.com/lupantech/status/1664316926003396608
_wsgeorge
twitter.com
1970-01-01T00:00:00
0
{}
13xoa3b
false
{'oembed': {'author_name': 'Pan Lu', 'author_url': 'https://twitter.com/lupantech', 'cache_age': 3153600000, 'height': None, 'html': '<blockquote class="twitter-video"><p lang="en" dir="ltr">🔥Thrilled to release LLaMa-Adapter Multimodal!<br><br>🎯Now supporting text, image, audio, and video inputs powered by <a href="...
t3_13xoa3b
/r/LocalLLaMA/comments/13xoa3b/llamaadapter_multimodal_supporting_text_image/
false
false
https://b.thumbs.redditm…9Twa9Xl2_g1I.jpg
15
{'enabled': False, 'images': [{'id': 'dk66zFAtNBHp78ITQwPwv6nwBc7KeFVG3UtDHGq-0IQ', 'resolutions': [{'height': 60, 'url': 'https://external-preview.redd.it/nvQ830q-6IYMc42YNjZjou-kf2YY-YR-Ifq4fqT1Sdo.jpg?width=108&crop=smart&auto=webp&s=de9e6648418d01e7760ce52fc377a85978df13a0', 'width': 108}], 'source': {'height': 78,...
Is there a model I can run on my M1 Mac?
1
[removed]
2023-06-01T17:11:57
https://www.reddit.com/r/LocalLLaMA/comments/13xnbje/is_there_a_model_i_can_run_on_my_m1_mac/
renegadellama
self.LocalLLaMA
1970-01-01T00:00:00
0
{}
13xnbje
false
null
t3_13xnbje
/r/LocalLLaMA/comments/13xnbje/is_there_a_model_i_can_run_on_my_m1_mac/
false
false
default
1
null
NVIDIA’s new AI model ‘NEURALANGELO’ reconstructs 3D scenes from 2D videos.
66
[removed]
2023-06-01T17:05:41
https://v.redd.it/f9ih2ipluf3b1
adesigne
v.redd.it
1970-01-01T00:00:00
0
{}
13xn5h5
false
{'reddit_video': {'bitrate_kbps': 2400, 'dash_url': 'https://v.redd.it/f9ih2ipluf3b1/DASHPlaylist.mpd?a=1695255560%2CYWEzMjA5NjE4MjFkYTBkZWJmOGI2YmFmYzA3ZDNiNWZkNThiNGYzOTdhZTcxMDRlMjBiMzhmMzUwZTc0NTczMQ%3D%3D&v=1&f=sd', 'duration': 57, 'fallback_url': 'https://v.redd.it/f9ih2ipluf3b1/DASH_720.mp4?source=fallback', 'he...
t3_13xn5h5
/r/LocalLLaMA/comments/13xn5h5/nvidias_new_ai_model_neuralangelo_reconstructs_3d/
false
false
default
66
null
Seeking an experienced oobabooga user to get Falcon 40B running inside Oobabooga. Offering 96 hours of 48GB GPU time.
38
I have a server with 48GB of VRAM (a Quadro RTX 8000) and 128GB of RAM. I have tried and failed to get Falcon 40B working at all, either inside Ooba or not inside Ooba. I am seeking an experienced user to help me get Falcon 40B going inside Oobabooga, and produce a HOWTO stating how this was done. (This HOWTO will ge...
2023-06-01T17:03:20
https://www.reddit.com/r/LocalLLaMA/comments/13xn37k/seeking_an_experienced_oobabooga_user_to_get/
AlpsAficionado
self.LocalLLaMA
1970-01-01T00:00:00
0
{}
13xn37k
false
null
t3_13xn37k
/r/LocalLLaMA/comments/13xn37k/seeking_an_experienced_oobabooga_user_to_get/
false
false
self
38
null
Help getting a model which can come up with a simple filename
2
I am trying to scan PDF files then use Tesseract OCR to annotate the text and ask my local model to come up with a file name to organize bills. I have tried text-generation-webui with WizardLM 30B, Wizard Vicuna 30B, 13B and a few others using prompts such as "Given the following scanned text, reply with a filename su...
2023-06-01T16:59:03
https://www.reddit.com/r/LocalLLaMA/comments/13xmynf/help_getting_a_model_which_can_come_up_with_a/
superlinux
self.LocalLLaMA
1970-01-01T00:00:00
0
{}
13xmynf
false
null
t3_13xmynf
/r/LocalLLaMA/comments/13xmynf/help_getting_a_model_which_can_come_up_with_a/
false
false
self
2
null
Fine-tune the WizardLM 13B using chat history from ChatGPT with QLoRa
59
The results is kind of interesting, Most of my conversations with ChatGPT are coding related. Somehow, the fine-tuned model appears to have improved its logic and reasoning capabilities. I suspect that OpenAI has a large user base of developers. so, they have trained their model based on these conversations maybe that ...
2023-06-01T16:39:26
https://www.reddit.com/r/LocalLLaMA/comments/13xmfu0/finetune_the_wizardlm_13b_using_chat_history_from/
mzbacd
self.LocalLLaMA
2023-06-01T16:42:29
0
{}
13xmfu0
false
null
t3_13xmfu0
/r/LocalLLaMA/comments/13xmfu0/finetune_the_wizardlm_13b_using_chat_history_from/
false
false
self
59
{'enabled': False, 'images': [{'id': 'SYNNBiAXntrxl-ahkf9pFqLRUEFcidOyFZXOT6tYoCA', 'resolutions': [{'height': 54, 'url': 'https://external-preview.redd.it/EPykmoFPi2B0aiVNfaVrPam_XJo7e9X2br6flzkxVQQ.jpg?width=108&crop=smart&auto=webp&s=7ed178e92f0973fef9412aaee3258166989ab6d0', 'width': 108}, {'height': 108, 'url': 'h...
Fine-tune the WizardLM 13B using chat history from ChatGPT using QLoRa.
1
[deleted]
2023-06-01T16:38:00
[deleted]
1970-01-01T00:00:00
0
{}
13xmeev
false
null
t3_13xmeev
/r/LocalLLaMA/comments/13xmeev/finetune_the_wizardlm_13b_using_chat_history_from/
false
false
default
1
null
WizardLM-Uncensored-Falcon-7b
240
Today I released WizardLM-Uncensored-Falcon-7b [https://huggingface.co/ehartford/WizardLM-Uncensored-Falcon-7b](https://huggingface.co/ehartford/WizardLM-Uncensored-Falcon-7b) This took 8 hours to train on 4x A100, using WizardLM's original training script (which, surprisingly, worked just fine with Falcon, good job...
2023-06-01T16:35:08
https://www.reddit.com/r/LocalLLaMA/comments/13xmbkz/wizardlmuncensoredfalcon7b/
faldore
self.LocalLLaMA
1970-01-01T00:00:00
1
{'gid_2': 1}
13xmbkz
false
null
t3_13xmbkz
/r/LocalLLaMA/comments/13xmbkz/wizardlmuncensoredfalcon7b/
false
false
self
240
{'enabled': False, 'images': [{'id': '4yRErc-M_g6To-KQcI-i394Ooa1yRZTnS0GKtDlUcWo', 'resolutions': [{'height': 58, 'url': 'https://external-preview.redd.it/JPAxbBc1Qj2ceO_RkD7ykCmD9Hm0SqeP_Nl7tBfHCeo.jpg?width=108&crop=smart&auto=webp&s=8bdb18a51b88df23c46cdcd97f8c59622aaf595e', 'width': 108}, {'height': 116, 'url': 'h...
I am simply blown away with some of the stuff this thing writes.
39
It just hit me up with the: " It felt like all hope was lost just minutes earlier - yet here they were, back where everything began. And this time, nothing would stop them from reaching their goal. Nothing except maybe death itself. But even then, what did death matter? Death wasn't something anyone could avoid foreve...
2023-06-01T16:21:01
https://www.reddit.com/r/LocalLLaMA/comments/13xlxx2/i_am_simply_blown_away_with_some_of_the_stuff/
ansmo
self.LocalLLaMA
1970-01-01T00:00:00
0
{}
13xlxx2
false
null
t3_13xlxx2
/r/LocalLLaMA/comments/13xlxx2/i_am_simply_blown_away_with_some_of_the_stuff/
false
false
self
39
null
Dalaï -> Alpaca/llama
1
[removed]
2023-06-01T16:07:57
https://www.reddit.com/r/LocalLLaMA/comments/13xll7s/dalaï_alpacallama/
RatioAltruistic9324
self.LocalLLaMA
1970-01-01T00:00:00
0
{}
13xll7s
false
null
t3_13xll7s
/r/LocalLLaMA/comments/13xll7s/dalaï_alpacallama/
false
false
default
1
null
How is gpt-3.5/gpt-4 so fast?
12
If my 3090 can get around 11/12 tokens on a 33B model with all the possible optimizations and math magic, how does openAI run a 175B model such that it gives basically instant replies? Assuming they are using the latest and greatest (H100), it would need to be thousands of times faster than a 3090, which it isn't. Wha...
2023-06-01T14:25:31
https://www.reddit.com/r/LocalLLaMA/comments/13xiyux/how_is_gpt35gpt4_so_fast/
HideLord
self.LocalLLaMA
1970-01-01T00:00:00
0
{}
13xiyux
false
null
t3_13xiyux
/r/LocalLLaMA/comments/13xiyux/how_is_gpt35gpt4_so_fast/
false
false
self
12
null
How can I increase the speed of the token generation process?
4
Suppose I have a very large graphics card. How can I increase the speed of the token generation process by 10 times? Are there any methods available to parallelize the process?
2023-06-01T13:19:16
https://www.reddit.com/r/LocalLLaMA/comments/13xher4/how_can_i_increase_the_speed_of_the_token/
GooD404
self.LocalLLaMA
1970-01-01T00:00:00
0
{}
13xher4
false
null
t3_13xher4
/r/LocalLLaMA/comments/13xher4/how_can_i_increase_the_speed_of_the_token/
false
false
self
4
null
Running a local model on Mac
2
[removed]
2023-06-01T13:10:32
https://www.reddit.com/r/LocalLLaMA/comments/13xh7n3/running_a_local_model_on_mac/
haragoshi
self.LocalLLaMA
1970-01-01T00:00:00
0
{}
13xh7n3
false
null
t3_13xh7n3
/r/LocalLLaMA/comments/13xh7n3/running_a_local_model_on_mac/
false
false
default
2
null
Creating a website for "What can I run with my specs"?
406
After seeing the plethora of "What can I run with X" posts in various subs, I started thinking we need to build a website that allows the community to upload their specs, the models they run etc..and then let people put in their system specs to get a list of what models they can run. I figure something like this must ...
2023-06-01T13:00:25
https://www.reddit.com/r/LocalLLaMA/comments/13xgyyw/creating_a_website_for_what_can_i_run_with_my/
SigmaSixShooter
self.LocalLLaMA
1970-01-01T00:00:00
1
{'gid_2': 1}
13xgyyw
false
null
t3_13xgyyw
/r/LocalLLaMA/comments/13xgyyw/creating_a_website_for_what_can_i_run_with_my/
false
false
self
406
{'enabled': False, 'images': [{'id': 'vVKQ5cZRVsBKLvYi3h5K9S4hPIjY_YtWJEKJyLiIoMw', 'resolutions': [{'height': 104, 'url': 'https://external-preview.redd.it/lRdzQ_CRnYUsFE6KFq7Ujjep5SIvB8eS1hyOOucowRc.png?width=108&crop=smart&auto=webp&s=bc2a91d5fe0d45f4161d1a3b0d425d7f43c7f03b', 'width': 108}, {'height': 208, 'url': '...
How can I get a model to be able to answer questions with information from my local files?
10
Are there any projects or guides that concern themselves with this use case?
2023-06-01T12:40:40
https://www.reddit.com/r/LocalLLaMA/comments/13xgjpx/how_can_i_get_a_model_to_be_able_to_answer/
LFS2y6eSkmsbSX
self.LocalLLaMA
1970-01-01T00:00:00
0
{}
13xgjpx
false
null
t3_13xgjpx
/r/LocalLLaMA/comments/13xgjpx/how_can_i_get_a_model_to_be_able_to_answer/
false
false
self
10
null
Getting rid of </s> and similars?
0
[removed]
2023-06-01T12:39:49
https://www.reddit.com/r/LocalLLaMA/comments/13xgj07/getting_rid_of_s_and_similars/
elektroB
self.LocalLLaMA
1970-01-01T00:00:00
0
{}
13xgj07
false
null
t3_13xgj07
/r/LocalLLaMA/comments/13xgj07/getting_rid_of_s_and_similars/
false
false
default
0
null
Help wanted: understanding terrible llama.cpp w/ CUDA inference speed (less then 1token/minute) on powerful machine (A6000)
4
EDIT: Solved! Solution in top level reply below Hi all, I've been searching all over for help w/ this. I'm sorry if this is the wrong place. I'm willing to pay for whoever can help me. My goal is to reach token generation speed of 10+/second w/ a model of 30B params. I've tried to follow the `llama.cpp` readme inst...
2023-06-01T11:15:50
https://www.reddit.com/r/LocalLLaMA/comments/13xetjq/help_wanted_understanding_terrible_llamacpp_w/
Breserk
self.LocalLLaMA
2023-06-01T12:26:45
0
{}
13xetjq
false
null
t3_13xetjq
/r/LocalLLaMA/comments/13xetjq/help_wanted_understanding_terrible_llamacpp_w/
false
false
self
4
null
How can I create funnier stories? harry potter fan fiction
1
Hello. Can someone please tell me how to generate funnier stories? This story isn't funny. thanks Perhaps changing the temperature? model? the prompt? etc? to what values? thanks dewi@dewiserver:~$ cat /home/dewi/tmp/text_llm/2023-06-01_09-22-48 ++ cat text12.txt + /home/dewi/code/llama.c...
2023-06-01T10:38:05
https://www.reddit.com/r/LocalLLaMA/comments/13xe4el/how_can_i_create_funnier_stories_harry_potter_fan/
dewijones92
self.LocalLLaMA
1970-01-01T00:00:00
0
{}
13xe4el
false
null
t3_13xe4el
/r/LocalLLaMA/comments/13xe4el/how_can_i_create_funnier_stories_harry_potter_fan/
false
false
self
1
null
How good is Guanaco 33B model really?
25
I'm confused because the Guanaco models are being praised as being really good on YT. However, it's not even listed on the Open LLM Leaderboard. So how good can it really be? Am I missing something? p.s. I do have the 13B and 33B Guanaco models running locally on my machine and they were OK but I feel like other m...
2023-06-01T09:37:57
https://www.reddit.com/r/LocalLLaMA/comments/13xd3e4/how_good_is_guanaco_33b_model_really/
Cruzifer07
self.LocalLLaMA
1970-01-01T00:00:00
0
{}
13xd3e4
false
null
t3_13xd3e4
/r/LocalLLaMA/comments/13xd3e4/how_good_is_guanaco_33b_model_really/
false
false
self
25
null
Am on my last $4.20 of RunPod credits so decided to spin up Guanaco 65B on a single A6000 for y'all to play around with and for me to see how much traffic it can handle haha
33
**EDIT:** Thanks for trying it out everyone! Looks like my RunPod credits ran out a while back so unfortunately Llama will just error out now :( May host another model in the future! Pulled this Next.js app together in about 90 minutes with the help of our almighty Lord and savior GPT-4: [https://askllama.vercel.app/]...
2023-06-01T09:10:00
https://www.reddit.com/r/LocalLLaMA/comments/13xcn3p/am_on_my_last_420_of_runpod_credits_so_decided_to/
itsmnjn
self.LocalLLaMA
2023-06-01T18:17:41
0
{}
13xcn3p
false
null
t3_13xcn3p
/r/LocalLLaMA/comments/13xcn3p/am_on_my_last_420_of_runpod_credits_so_decided_to/
false
false
self
33
null
Interactive Generation of (Arbitrarily) Long Text?
1
[removed]
2023-06-01T08:02:17
[deleted]
1970-01-01T00:00:00
0
{}
13xbkzl
false
null
t3_13xbkzl
/r/LocalLLaMA/comments/13xbkzl/interactive_generation_of_arbitrarily_long_text/
false
false
default
1
null
How to deploy 7B model to mobile app?
2
Any suggestion to make it run locally in mobile? Using GPT API seems to be quite costly.
2023-06-01T07:48:45
https://www.reddit.com/r/LocalLLaMA/comments/13xbd9i/how_to_deploy_7b_model_to_mobile_app/
direwulf33
self.LocalLLaMA
1970-01-01T00:00:00
0
{}
13xbd9i
false
null
t3_13xbd9i
/r/LocalLLaMA/comments/13xbd9i/how_to_deploy_7b_model_to_mobile_app/
false
false
self
2
null
What if you trained language models on word problems?
1
A lot of you have seen questions like this one posed to LLMs and answered incorrectly: “Sally has three apples and takes a bite from a banana. How many apples does she have?” Well, what if we trained LLMs on a large corpus of such questions and their correct answers? Would it improve their overall intelligence or wo...
2023-06-01T07:29:31
https://www.reddit.com/r/LocalLLaMA/comments/13xb2n4/what_if_you_trained_language_models_on_word/
Basic_Description_56
self.LocalLLaMA
1970-01-01T00:00:00
0
{}
13xb2n4
false
null
t3_13xb2n4
/r/LocalLLaMA/comments/13xb2n4/what_if_you_trained_language_models_on_word/
false
false
self
1
null
How to use AMD GPU?
3
Hello, I'm trying to install some LMs on my local PC and have an AMD gpu. Can you please help me to make them use my GPU? I don't understand how to proceed. Thank you.
2023-06-01T06:41:51
https://www.reddit.com/r/LocalLLaMA/comments/13xabwa/how_to_use_amd_gpu/
FireTriad
self.LocalLLaMA
1970-01-01T00:00:00
0
{}
13xabwa
false
null
t3_13xabwa
/r/LocalLLaMA/comments/13xabwa/how_to_use_amd_gpu/
false
false
self
3
null
I'm currently running falcon-40b-instruct. Comment anything you want to ask it, and I'll tell you its response.
106
Running TheBloke's QPTQ mode on an A100 40GB on Runpod. Note that it gives very ChatGPT like answers, often starting with "As an AI language model". Not too surprising given the dataset it was trained on. I'll be running it for the next few hours and want to test its limits and capabilities.
2023-06-01T05:09:19
https://www.reddit.com/r/LocalLLaMA/comments/13x8tlm/im_currently_running_falcon40binstruct_comment/
sardoa11
self.LocalLLaMA
1970-01-01T00:00:00
0
{}
13x8tlm
false
null
t3_13x8tlm
/r/LocalLLaMA/comments/13x8tlm/im_currently_running_falcon40binstruct_comment/
false
false
self
106
null
Fine tuning LLMs?
13
Hi, I am new to ML and LLMs. I am just wondering how do we fine tune an LLM just to do a single NLP task such as multi label text classification of let's say....500k labels? Thank you Reddit
2023-06-01T03:34:35
https://www.reddit.com/r/LocalLLaMA/comments/13x733v/fine_tuning_llms/
ReversingEntropy
self.LocalLLaMA
1970-01-01T00:00:00
0
{}
13x733v
false
null
t3_13x733v
/r/LocalLLaMA/comments/13x733v/fine_tuning_llms/
false
false
self
13
null
Vicuna claims there's a lmsys-models python library and you can import Vicuna from there
0
[removed]
2023-06-01T03:19:08
[deleted]
1970-01-01T00:00:00
0
{}
13x6sg4
false
null
t3_13x6sg4
/r/LocalLLaMA/comments/13x6sg4/vicuna_claims_theres_a_lmsysmodels_python_library/
false
false
default
0
null
Quantize Embbeding models (Encoders)
1
[removed]
2023-06-01T02:56:19
https://www.reddit.com/r/LocalLLaMA/comments/13x6c7u/quantize_embbeding_models_encoders/
BecomeAllan
self.LocalLLaMA
1970-01-01T00:00:00
0
{}
13x6c7u
false
null
t3_13x6c7u
/r/LocalLLaMA/comments/13x6c7u/quantize_embbeding_models_encoders/
false
false
default
1
null
Why Falcon going Apache 2.0 is a BIG deal for all of us.
121
Falcon 40B is SOTA, going Commercial-use friendly is going to get it a lot of attention in the open source community. Why does this matter? Cause Meta is benefiting heavily from all the innovation on the space with LLaMa and something like this will mean less people will focus on their model and contribute to Falcon ...
2023-06-01T00:53:46
https://www.reddit.com/r/LocalLLaMA/comments/13x3q26/why_falcon_going_apache_20_is_a_big_deal_for_all/
EcstaticVenom
self.LocalLLaMA
1970-01-01T00:00:00
0
{}
13x3q26
false
null
t3_13x3q26
/r/LocalLLaMA/comments/13x3q26/why_falcon_going_apache_20_is_a_big_deal_for_all/
false
false
self
121
null
Experience running 13B q4/5 models on M1 with 16gig RAM is poor
1
[removed]
2023-06-01T00:47:00
https://www.reddit.com/r/LocalLLaMA/comments/13x3kn5/experience_running_13b_q45_models_on_m1_with/
_wsgeorge
self.LocalLLaMA
1970-01-01T00:00:00
0
{}
13x3kn5
false
null
t3_13x3kn5
/r/LocalLLaMA/comments/13x3kn5/experience_running_13b_q45_models_on_m1_with/
false
false
default
1
null
Sharing LLMLounge: Subreddit to talk about all things LLM outside the OpenAI/Meta sphere
2
[removed]
2023-05-31T23:47:50
https://www.reddit.com/r/LocalLLaMA/comments/13x273l/sharing_llmlounge_subreddit_to_talk_about_all/
EcstaticVenom
self.LocalLLaMA
1970-01-01T00:00:00
0
{}
13x273l
false
null
t3_13x273l
/r/LocalLLaMA/comments/13x273l/sharing_llmlounge_subreddit_to_talk_about_all/
false
false
default
2
null
Using base models directly
10
I've been working on a project to enforce syntax constraints on LLM generations: [https://github.com/IsaacRe/Syntactically-Constrained-Sampling](https://github.com/IsaacRe/Syntactically-Constrained-Sampling) I was playing around with constraining original (non IFT) Llama-7B to produce output following a specific JSO...
2023-05-31T23:36:24
https://www.reddit.com/r/LocalLLaMA/comments/13x1xb5/using_base_models_directly/
isaacrehg
self.LocalLLaMA
1970-01-01T00:00:00
0
{}
13x1xb5
false
null
t3_13x1xb5
/r/LocalLLaMA/comments/13x1xb5/using_base_models_directly/
false
false
self
10
{'enabled': False, 'images': [{'id': '_r1TtGkbYPpDBcAakTPFY9-wwEoYtF6QgbG1XeqLgFI', 'resolutions': [{'height': 54, 'url': 'https://external-preview.redd.it/urG44lP1SF-0A4A6Bmm5RupvhgFgtvdU9Qnyb-sytlY.jpg?width=108&crop=smart&auto=webp&s=a7a82433428ceaa1ec5df0477d23172752e55a20', 'width': 108}, {'height': 108, 'url': 'h...