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 ⌀ |
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
Best way to upgrade my pc to improve t/s | 2 | Hi all, I bought a new pc last year and after experimenting with llms for the last months I have some doubts. I can run 7b, 13b and even 20/30b model reasonably fast but the 70b (I use the q3 quantization, GGUF format) run at 1t/s using windows 11. I´m thinking about how to upgrade my pc so I can get at least 2/3 t/s... | 2023-11-16T12:35:34 | https://www.reddit.com/r/LocalLLaMA/comments/17wlttf/best_way_to_upgrade_my_pc_to_improve_ts/ | DarthByron | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 17wlttf | false | null | t3_17wlttf | /r/LocalLLaMA/comments/17wlttf/best_way_to_upgrade_my_pc_to_improve_ts/ | false | false | self | 2 | null |
Why the Need for Massive Data Sets and How Human Brains Differ in Learning? | 1 | [removed] | 2023-11-16T11:30:14 | https://www.reddit.com/r/LocalLLaMA/comments/17wkomy/why_the_need_for_massive_data_sets_and_how_human/ | One-Magician-6270 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 17wkomy | false | null | t3_17wkomy | /r/LocalLLaMA/comments/17wkomy/why_the_need_for_massive_data_sets_and_how_human/ | false | false | self | 1 | null |
2x Teslas in an OEM system | 5 | I have a Dell T7610 and I got 2x P40s for running LLMs. However, nno matter what I do, I can't get both of my P40s to work on the system. Both of them work by themselves in either PCIE slot, but when both of them are plugged in, the one on the first PCIE slot always returns an error in device manager. Does anyone have ... | 2023-11-16T10:44:12 | https://www.reddit.com/r/LocalLLaMA/comments/17wjxf6/2x_teslas_in_an_oem_system/ | ConcaveTriangle5761 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 17wjxf6 | false | null | t3_17wjxf6 | /r/LocalLLaMA/comments/17wjxf6/2x_teslas_in_an_oem_system/ | false | false | 5 | null | |
2x Teslas in an OEM system | 1 | I have a Dell T7610 and I got 2x P40s for running LLMs. However, nno matter what I do, I can't get both of my P40s to work on the system. Both of them work by themselves in either PCIE slot, but when both of them are plugged in, the one on the first PCIE slot always returns an error in device manager. Does anyone have ... | 2023-11-16T10:44:10 | https://www.reddit.com/r/LocalLLaMA/comments/17wjxdq/2x_teslas_in_an_oem_system/ | ConcaveTriangle5761 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 17wjxdq | false | null | t3_17wjxdq | /r/LocalLLaMA/comments/17wjxdq/2x_teslas_in_an_oem_system/ | false | false | self | 1 | null |
LLM Leaderboard for Hallucination | 1 | 2023-11-16T08:41:15 | https://github.com/vectara/hallucination-leaderboard | __tosh | github.com | 1970-01-01T00:00:00 | 0 | {} | 17wi5eg | false | null | t3_17wi5eg | /r/LocalLLaMA/comments/17wi5eg/llm_leaderboard_for_hallucination/ | false | false | 1 | {'enabled': False, 'images': [{'id': 'tfb3st9dN_QajSUqzLawgdt_plecUNImmfGbuuGao00', 'resolutions': [{'height': 54, 'url': 'https://external-preview.redd.it/26nr0mG19mpfwzpcsfwf59fFxHGn006huZ47DfKr0ig.jpg?width=108&crop=smart&auto=webp&s=2db7b9cdd63c7a7251568faa360bfe7dd1a7b0ed', 'width': 108}, {'height': 108, 'url': 'h... | ||
Training Drafting Model | 1 | I’ve collected a dataset of legal drafts. How can I train a model(suggestions requested) to write a draft for a given situation or prepare a counter or reply to an uploaded document or text, Add any new clauses or regenerate the whole draft for higher accuracy if needed.
For ex:
- I want to draft an employment contra... | 2023-11-16T08:03:17 | https://www.reddit.com/r/LocalLLaMA/comments/17whm7n/training_drafting_model/ | Tejasw__ | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 17whm7n | false | null | t3_17whm7n | /r/LocalLLaMA/comments/17whm7n/training_drafting_model/ | false | false | self | 1 | null |
Would automatic temperature work? | 16 | Currently we manually set the temperature and keep it the whole chat.
Wouldnt it make more sense to let the model decide a temperature itself depending on the topic? | 2023-11-16T07:11:47 | https://www.reddit.com/r/LocalLLaMA/comments/17wguaa/would_automatic_temperature_work/ | freehuntx | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 17wguaa | false | null | t3_17wguaa | /r/LocalLLaMA/comments/17wguaa/would_automatic_temperature_work/ | false | false | self | 16 | null |
How can I improve inference performance to a normal range? | 1 | [removed] | 2023-11-16T06:53:12 | https://www.reddit.com/r/LocalLLaMA/comments/17wgjjh/how_can_i_improve_inference_performance_to_a/ | Radiant-Practice-270 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 17wgjjh | false | null | t3_17wgjjh | /r/LocalLLaMA/comments/17wgjjh/how_can_i_improve_inference_performance_to_a/ | false | false | self | 1 | null |
Generalized Tree-of-Thought Capability in SynthIA Models | 54 | Here's how I managed to bootstrap generalized Tree-of-Thought capability in my AIs.
This was the secret sauce to SynthIA.
Generate your dataset with this, plus the Orca system prompts.
Open Source FTW. LFG!
​
https://preview.redd.it/45uyzynlen0c1.png?width=1744&format=png&auto=webp&s=694e69603c0656ef... | 2023-11-16T05:47:22 | https://www.reddit.com/r/LocalLLaMA/comments/17wffs4/generalized_treeofthought_capability_in_synthia/ | migtissera | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 17wffs4 | false | null | t3_17wffs4 | /r/LocalLLaMA/comments/17wffs4/generalized_treeofthought_capability_in_synthia/ | false | false | 54 | null | |
anaconda help with "pip install llama-cpp-python" | 1 |
so i'm new to python/coding and i'm using anaconda to install [text-generation-webui](https://github.com/oobabooga/text-generation-webui) with [this](https://gist.github.com/mberman84/f092a28e4151dd5cecebfc58ac1cbc0e#file-gistfile1-txt) guide and when i try to use "pip install llama-cpp-python" i get the error
" no... | 2023-11-16T03:57:30 | https://www.reddit.com/r/LocalLLaMA/comments/17wdeus/anaconda_help_with_pip_install_llamacpppython/ | AdApprehensive6837 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 17wdeus | false | null | t3_17wdeus | /r/LocalLLaMA/comments/17wdeus/anaconda_help_with_pip_install_llamacpppython/ | false | false | self | 1 | {'enabled': False, 'images': [{'id': 'rRZX3PKDm_pNgnmtRnCiHQtxU7Mjo_WMUKuYbMi4jdQ', 'resolutions': [{'height': 54, 'url': 'https://external-preview.redd.it/v65lbb4LTLgaEErzNED3IqGgQtVMfuqjIV2AS1aVvHY.jpg?width=108&crop=smart&auto=webp&s=a24c9ec23e6269eca447ab1fef043ace408bbc32', 'width': 108}, {'height': 108, 'url': 'h... |
Text-Generator-webui merge bloke files | 1 | [removed] | 2023-11-16T03:56:37 | https://www.reddit.com/r/LocalLLaMA/comments/17wde8p/textgeneratorwebui_merge_bloke_files/ | Danny_Davitoe | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 17wde8p | false | null | t3_17wde8p | /r/LocalLLaMA/comments/17wde8p/textgeneratorwebui_merge_bloke_files/ | false | false | self | 1 | null |
Getting 1 billion evaluation for LLama2 clone (Chinese start up 01.ai with Yi-34B) | 1 | Since this reddit doesnt allow cross posting I'll quote
"
You might have read news last week that the Chinese startup 01.ai behind Yi-34B has topped the LLM leaderboard in hugging face. Besides the company is now valued at 1Bil USD. Lee Kai-F has announced this model and their accomplishment on LinkedIn, and the... | 2023-11-16T02:48:03 | https://www.reddit.com/r/LocalLLaMA/comments/17wby60/getting_1_billion_evaluation_for_llama2_clone/ | Infamous_Charge2666 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 17wby60 | false | null | t3_17wby60 | /r/LocalLLaMA/comments/17wby60/getting_1_billion_evaluation_for_llama2_clone/ | false | false | self | 1 | {'enabled': False, 'images': [{'id': '_rEX1xvwdv17x6NFAWQpYFNONQ0BKA5Qw0Eo0JX0zWU', 'resolutions': [{'height': 58, 'url': 'https://external-preview.redd.it/OFWu5qxCY4R2hQfI_vzWYgK2ON5meupO-ZR0eRPmsP8.jpg?width=108&crop=smart&auto=webp&s=4bc231a80d79babe4e6cddf7b4c71dcb0aa8f8ff', 'width': 108}, {'height': 116, 'url': 'h... |
OpenAI Assistants API in an Agent Framework | 3 |
(Also posted on r/ML)
I know this is the LocalLlama forum but there has been some interest in the OpenAI Assistants API, so here goes. Also of course a similar API service could be implemented using open/local models so it’s not entirely irrelevant!
Given the OpenAI Assistants API released last week, a natural next q... | 2023-11-16T02:47:01 | https://www.reddit.com/r/LocalLLaMA/comments/17wbxg7/openai_assistants_api_in_an_agent_framework/ | SatoshiNotMe | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 17wbxg7 | false | null | t3_17wbxg7 | /r/LocalLLaMA/comments/17wbxg7/openai_assistants_api_in_an_agent_framework/ | false | false | self | 3 | {'enabled': False, 'images': [{'id': 'mCf-gvgLGIf97C4Q5Pay7BZQzUkl4WPZs5p9Ug1Hclk', 'resolutions': [{'height': 56, 'url': 'https://external-preview.redd.it/RigZZifec40luNenyE_Akjp1nwDkgYM3PY2sXKQiR9U.jpg?width=108&crop=smart&auto=webp&s=6f77c5c3077d3728cfb79ff9339119fb5fd7b59d', 'width': 108}, {'height': 113, 'url': 'h... |
Echoproof: New extension for WebUI that reduces chatbot's "OCD-like" tendencies | 44 | 2023-11-16T02:36:26 | https://github.com/ThereforeGames/echoproof | ThereforeGames | github.com | 1970-01-01T00:00:00 | 0 | {} | 17wbp86 | false | null | t3_17wbp86 | /r/LocalLLaMA/comments/17wbp86/echoproof_new_extension_for_webui_that_reduces/ | false | false | 44 | {'enabled': False, 'images': [{'id': '4INlW3mxQDcu2fg5_9LHIhc_be5GsliEUoRgg82yPkI', 'resolutions': [{'height': 54, 'url': 'https://external-preview.redd.it/8-9rlTr-AuR1piVXiAPqQl4_4aaf_7YXJMDGSASK590.jpg?width=108&crop=smart&auto=webp&s=f5d8db4f25e89bd5fbcdb86c2ac89b8f283bdbe3', 'width': 108}, {'height': 108, 'url': 'h... | ||
Completion UI? | 2 | Hey yall,
I'm currently using koboldcpp but I miss being able to use a completion interface, I know that oobabooga has a completion playground but I don't really like the way it looks, is there anyway to get a completion playground using koboldcpp? | 2023-11-16T02:26:51 | https://www.reddit.com/r/LocalLLaMA/comments/17wbhhm/completion_ui/ | ipechman | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 17wbhhm | false | null | t3_17wbhhm | /r/LocalLLaMA/comments/17wbhhm/completion_ui/ | false | false | self | 2 | null |
Oh We Were So Close, Little 7b Buddy | 64 | 2023-11-16T02:15:09 | luncheroo | i.redd.it | 1970-01-01T00:00:00 | 0 | {} | 17wb805 | false | null | t3_17wb805 | /r/LocalLLaMA/comments/17wb805/oh_we_were_so_close_little_7b_buddy/ | false | false | 64 | {'enabled': True, 'images': [{'id': 'CBuX0CXsYWiQspLQKs0f1Q-nnKLd59pc-cvmLE0Q2BQ', 'resolutions': [{'height': 51, 'url': 'https://preview.redd.it/cgskerbpcm0c1.png?width=108&crop=smart&auto=webp&s=8fbebaa2401752089bab5a8dc14393b35a84776f', 'width': 108}, {'height': 103, 'url': 'https://preview.redd.it/cgskerbpcm0c1.png... | |||
Running turboderp_Llama2-70B-exl2 on 3090 24GB was disappointing... | 1 | [removed] | 2023-11-16T02:06:35 | https://www.reddit.com/r/LocalLLaMA/comments/17wb16p/running_turboderp_llama270bexl2_on_3090_24gb_was/ | BlueMetaMind | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 17wb16p | false | null | t3_17wb16p | /r/LocalLLaMA/comments/17wb16p/running_turboderp_llama270bexl2_on_3090_24gb_was/ | false | false | 1 | null | |
OpenChat- Is there a special way to use it? | 1 | [removed] | 2023-11-16T01:34:42 | https://www.reddit.com/r/LocalLLaMA/comments/17wabor/openchat_is_there_a_special_way_to_use_it/ | consig1iere | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 17wabor | false | null | t3_17wabor | /r/LocalLLaMA/comments/17wabor/openchat_is_there_a_special_way_to_use_it/ | false | false | self | 1 | null |
Multiple Local LLMs Pipeline on M-Series Mac | 15 | ​
[Left \/ CodeBooga34B - Right \/ NousCapybara34B](https://preview.redd.it/bhl8io2psl0c1.png?width=3456&format=png&auto=webp&s=ba1d0c233c123f121c75efbf9d25d7a4834a97c0)
I've been working on a Go framework with the intent of having all of the basic dependencies for LM workflows as a hobby project to learn the ... | 2023-11-16T00:23:02 | https://www.reddit.com/r/LocalLLaMA/comments/17w8oa2/multiple_local_llms_pipeline_on_mseries_mac/ | LocoMod | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 17w8oa2 | false | null | t3_17w8oa2 | /r/LocalLLaMA/comments/17w8oa2/multiple_local_llms_pipeline_on_mseries_mac/ | false | false | 15 | null | |
is there any ongoing effort to "bake-in" vision capabilities on top of base models or fine-tunes? | 6 | have been thinking about this for a while-- does anyone know how feasible this is? Basically just applying some sort of "LoRa" on top of models to give them vision capabilities-- making then multimodal. | 2023-11-16T00:03:10 | https://www.reddit.com/r/LocalLLaMA/comments/17w87ez/is_there_any_ongoing_effort_to_bakein_vision/ | LyPreto | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 17w87ez | false | null | t3_17w87ez | /r/LocalLLaMA/comments/17w87ez/is_there_any_ongoing_effort_to_bakein_vision/ | false | false | self | 6 | null |
Strange noise/sound produced by GPU while running go-llama.cpp bindings | 1 | [removed] | 2023-11-15T23:40:29 | https://www.reddit.com/r/LocalLLaMA/comments/17w7nr7/strange_noisesound_produced_by_gpu_while_running/ | KaleidoscopeGlad2649 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 17w7nr7 | false | null | t3_17w7nr7 | /r/LocalLLaMA/comments/17w7nr7/strange_noisesound_produced_by_gpu_while_running/ | false | false | self | 1 | null |
Good 34b or 70b models for Code Analysis | 9 | Hey guys, I've been lurking around this sub for a while and this is my first question.
I wanted to know if there are any good 4k or 16k context size models which are really good at picking up patterns in code.
For example figuring out Weakneses in code, by reading the code lines and suggesting an alternate line of c... | 2023-11-15T23:24:34 | https://www.reddit.com/r/LocalLLaMA/comments/17w79vh/good_34b_or_70b_models_for_code_analysis/ | Jla1Million | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 17w79vh | false | null | t3_17w79vh | /r/LocalLLaMA/comments/17w79vh/good_34b_or_70b_models_for_code_analysis/ | false | false | self | 9 | null |
Higgsfield AI. Go chat with popular finetuned models | 27 | [https://higgsfield.ai/chat](https://higgsfield.ai/chat)
Hey LocalLLaMA, Higgsfield AI here
A few days ago, we built an easy-to-use platform for everyone in the community to finetune models. Many of you uploaded datasets, and they are waiting in the queue for training.
We received a lot of feedback, and many of you ... | 2023-11-15T23:04:51 | https://www.reddit.com/r/LocalLLaMA/comments/17w6rt7/higgsfield_ai_go_chat_with_popular_finetuned/ | RiskApprehensive9770 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 17w6rt7 | false | null | t3_17w6rt7 | /r/LocalLLaMA/comments/17w6rt7/higgsfield_ai_go_chat_with_popular_finetuned/ | false | false | self | 27 | null |
New multilingual base model from nvidia: Nemotron-3-8B | 58 | nvidia released a new 8B base model (and a few fine-tunes), albeit under a restrictive license.
[https://huggingface.co/nvidia/nemotron-3-8b-base-4k](https://huggingface.co/nvidia/nemotron-3-8b-base-4k)
Happily, they did specify enough details about their training regimen for the model to be a useful data-point.
The... | 2023-11-15T22:50:19 | https://www.reddit.com/r/LocalLLaMA/comments/17w6e93/new_multilingual_base_model_from_nvidia/ | georgejrjrjr | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 17w6e93 | false | null | t3_17w6e93 | /r/LocalLLaMA/comments/17w6e93/new_multilingual_base_model_from_nvidia/ | false | false | self | 58 | {'enabled': False, 'images': [{'id': 'HxSdSImC3aTuwENPO5MkRmgaoS5HP1Gl7tganGi4z5Y', 'resolutions': [{'height': 58, 'url': 'https://external-preview.redd.it/-WRJKluDLeXudEnnlQ_LZcslezbDFHdV8uJcCowhCOk.jpg?width=108&crop=smart&auto=webp&s=f6156122244ec46c3b0b7d197afd73b4b3c3254d', 'width': 108}, {'height': 116, 'url': 'h... |
When OpenAI takes neutering to the extreme... | 185 | 2023-11-15T22:45:36 | FPham | i.redd.it | 1970-01-01T00:00:00 | 0 | {} | 17w69ve | false | null | t3_17w69ve | /r/LocalLLaMA/comments/17w69ve/when_openai_takes_neutering_to_the_extreme/ | false | false | 185 | {'enabled': True, 'images': [{'id': '68BAlXbSbhFYMOd-6SWB0dPxfc5zW0m7jXVz4Z3096o', 'resolutions': [{'height': 39, 'url': 'https://preview.redd.it/lshzh40dbl0c1.jpg?width=108&crop=smart&auto=webp&s=afef6de2cc785f5dc4e9a1807ccd63e1c65b0340', 'width': 108}, {'height': 78, 'url': 'https://preview.redd.it/lshzh40dbl0c1.jpg?... | |||
Higgsfield AI. Go chat with popular finetuned models | 1 | Hey LocalLLaMA, Higgsfield AI here
A few days ago, we built an easy-to-use platform for everyone in the community to finetune models. Many of you uploaded datasets, and they are waiting in the queue for training.
We received a lot of feedback, and many of you reached out, wanting the opportunity to try out the models... | 2023-11-15T22:45:07 | https://www.reddit.com/r/LocalLLaMA/comments/17w69ef/higgsfield_ai_go_chat_with_popular_finetuned/ | higgsfield_ai | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 17w69ef | false | null | t3_17w69ef | /r/LocalLLaMA/comments/17w69ef/higgsfield_ai_go_chat_with_popular_finetuned/ | false | false | self | 1 | null |
Higgsfield AI. Go chat with popular finetuned models | 1 | Hey LocalLLaMA, Higgsfield AI here
A few days ago, we built an easy-to-use platform for everyone in the community to finetune models. Many of you uploaded datasets, and they are waiting in the queue for training.
We received a lot of feedback, and many of you reached out, wanting the opportunity to try out the models... | 2023-11-15T22:44:52 | https://www.reddit.com/r/LocalLLaMA/comments/17w696q/higgsfield_ai_go_chat_with_popular_finetuned/ | higgsfield_ai | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 17w696q | false | null | t3_17w696q | /r/LocalLLaMA/comments/17w696q/higgsfield_ai_go_chat_with_popular_finetuned/ | false | false | self | 1 | null |
disappointed by trainers | 9 |
Dear friends
I hope this letter finds you well and in good health. I decided to write because I greatly admire your dedication to AI training on Hugging Face, and I believe you are one of the most active and knowledgeable individuals in this field.
For about a year now, I have devoted a significant amount of my ti... | 2023-11-15T22:31:01 | https://www.reddit.com/r/LocalLLaMA/comments/17w5wfm/disappointed_by_trainers/ | Creative_Bottle_3225 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 17w5wfm | false | null | t3_17w5wfm | /r/LocalLLaMA/comments/17w5wfm/disappointed_by_trainers/ | false | false | self | 9 | null |
Commercial Licensing for Yi Models is Pending Update | 2 | ### Sources:
https://huggingface.co/01-ai/Yi-6B#news
https://huggingface.co/01-ai/Yi-6B-200K#news
https://huggingface.co/01-ai/Yi-34B#news
https://huggingface.co/01-ai/Yi-34B-200K#news
Any speculations? | 2023-11-15T22:10:05 | https://www.reddit.com/r/LocalLLaMA/comments/17w5ctx/commercial_licensing_for_yi_models_is_pending/ | harumorii | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 17w5ctx | false | null | t3_17w5ctx | /r/LocalLLaMA/comments/17w5ctx/commercial_licensing_for_yi_models_is_pending/ | false | false | self | 2 | {'enabled': False, 'images': [{'id': 'AluJz0nChz5pSaft9X7Pd-CHNT4tPFgB-sVQSgmVEI0', 'resolutions': [{'height': 58, 'url': 'https://external-preview.redd.it/aJcLhD2diqv9W-JMHJow9FjnHxb9tkQJjSWdNSpGWcw.jpg?width=108&crop=smart&auto=webp&s=9e781de98817721923dde99733f0100fe43b06c8', 'width': 108}, {'height': 116, 'url': 'h... |
Nvidia: TensorRT-LLM OpenAI Chat API Integration | 9 | TensorRT-LLM for Windows will soon be compatible with OpenAI’s popular Chat API through a new wrapper. This will enable hundreds of developer projects and applications to run locally on a PC with RTX, instead of in the cloud — so users can keep private and proprietary data on their PCs.
Youtube video about it
[https... | 2023-11-15T22:09:59 | https://www.reddit.com/r/LocalLLaMA/comments/17w5cqo/nvidia_tensorrtllm_openai_chat_api_integration/ | mudgategame | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 17w5cqo | false | null | t3_17w5cqo | /r/LocalLLaMA/comments/17w5cqo/nvidia_tensorrtllm_openai_chat_api_integration/ | false | false | self | 9 | {'enabled': False, 'images': [{'id': 'fafJgAmiFbDDL8oQB8qdtd3JRzzdcsZ-z5Lm6wrdGXs', 'resolutions': [{'height': 81, 'url': 'https://external-preview.redd.it/l3ri_sKDjOGHWdJU6dflAlV1pHwrNXzzwj79CVUXEbM.jpg?width=108&crop=smart&auto=webp&s=e6ce65be1cee4fbaa8328b3741bc372e2591398d', 'width': 108}, {'height': 162, 'url': 'h... |
Commercial Licensing for Yi Models is Pending Update | 1 | ### Sources:
https://huggingface.co/01-ai/Yi-6B#news
https://huggingface.co/01-ai/Yi-6B-200K#news
https://huggingface.co/01-ai/Yi-34B#news
https://huggingface.co/01-ai/Yi-34B-200K#news
Any speculations? | 2023-11-15T22:05:18 | https://www.reddit.com/r/LocalLLaMA/comments/17w58bs/commercial_licensing_for_yi_models_is_pending/ | harumorii | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 17w58bs | false | null | t3_17w58bs | /r/LocalLLaMA/comments/17w58bs/commercial_licensing_for_yi_models_is_pending/ | false | false | self | 1 | null |
🐺🐦⬛ LLM Format Comparison/Benchmark: 70B GGUF vs. EXL2 (and AWQ) | 169 | I posted my latest [LLM Comparison/Test](https://www.reddit.com/r/LocalLLaMA/comments/17vcr9d/llm_comparisontest_2x_34b_yi_dolphin_nous/) just yesterday, but here's another (shorter) comparison/benchmark I did while working on that - **testing different formats and quantization levels**.
My goal was to find out which ... | 2023-11-15T22:04:22 | https://www.reddit.com/r/LocalLLaMA/comments/17w57eu/llm_format_comparisonbenchmark_70b_gguf_vs_exl2/ | WolframRavenwolf | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 17w57eu | false | null | t3_17w57eu | /r/LocalLLaMA/comments/17w57eu/llm_format_comparisonbenchmark_70b_gguf_vs_exl2/ | false | false | self | 169 | {'enabled': False, 'images': [{'id': '-E3KSlSzwSX9yTQAfxQyZkhYfIhsqtQIUeirxKXifKM', 'resolutions': [{'height': 54, 'url': 'https://external-preview.redd.it/MDIFjY06JaLVQ0ibe7F1Ye9iyU4bxvrS6J5FI6HFaFg.jpg?width=108&crop=smart&auto=webp&s=fd1b174f2b9dc42b12ad1ff0974e5a85d70189e2', 'width': 108}, {'height': 108, 'url': 'h... |
Is some tiny (1GB) model available through pip install? | 4 | I was looking into Galactica the other day, and it's available as a "pip install", that on first use downloads the model (260GB download LOL) and sets up everything. I got a slight headache by looking for hours through different small models, what I need to download etc, has any other model, a really small one for my s... | 2023-11-15T21:55:26 | https://www.reddit.com/r/LocalLLaMA/comments/17w4yyh/is_some_tiny_1gb_model_available_through_pip/ | GermanK20 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 17w4yyh | false | null | t3_17w4yyh | /r/LocalLLaMA/comments/17w4yyh/is_some_tiny_1gb_model_available_through_pip/ | false | false | self | 4 | null |
Converting non-LLaMA model to Q4_K_M GGUF format? | 4 | So I tried quantising the BLOOMZ 560M model ([https://huggingface.co/bigscience/bloomz-560m](https://huggingface.co/bigscience/bloomz-560m)) to GGUF format using the [convert-hf-model-to-gguf.py](https://convert-hf-model-to-gguf.py) script in the llama.cpp GitHub repo. This worked, except this script only seems to allo... | 2023-11-15T21:54:37 | https://www.reddit.com/r/LocalLLaMA/comments/17w4y7k/converting_nonllama_model_to_q4_k_m_gguf_format/ | prman7 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 17w4y7k | false | null | t3_17w4y7k | /r/LocalLLaMA/comments/17w4y7k/converting_nonllama_model_to_q4_k_m_gguf_format/ | false | false | self | 4 | {'enabled': False, 'images': [{'id': 'pHsAgFLeU9rHpjGdPmBMokZ-EqZyRiOJ8d0LLvBSeXY', 'resolutions': [{'height': 58, 'url': 'https://external-preview.redd.it/ffDCVLYVtNqnEFm_ERohRgIht7zg7921Wxhcn9B7zBE.jpg?width=108&crop=smart&auto=webp&s=c38e21bbbcc4cfd77f1f676008845dfa7ada627c', 'width': 108}, {'height': 116, 'url': 'h... |
Microsoft announced the Maia 100 AI Accelerator Chip. It's also expanding the use of the AMD MI300 in it's datacenters. Is this the beginning of the end of CUDA dominance? | 77 | 2023-11-15T20:26:51 | https://news.microsoft.com/source/features/ai/in-house-chips-silicon-to-service-to-meet-ai-demand/ | fallingdowndizzyvr | news.microsoft.com | 1970-01-01T00:00:00 | 0 | {} | 17w2v30 | false | null | t3_17w2v30 | /r/LocalLLaMA/comments/17w2v30/microsoft_announced_the_maia_100_ai_accelerator/ | false | false | 77 | {'enabled': False, 'images': [{'id': 'RxeXInsaRe1k6xd-RQV9dUVfBTCb6yxSjWs-wFCtG3U', 'resolutions': [{'height': 56, 'url': 'https://external-preview.redd.it/po-VnWVfCe70fcgDP3ymqzKavlCl3YW8jhyGmKkwWOQ.jpg?width=108&crop=smart&auto=webp&s=6bd120b4a14ceb47e686159cb558e7bb4a0966a0', 'width': 108}, {'height': 113, 'url': 'h... | ||
LMstudio: How to bulk export text from conversations? | 1 | [removed] | 2023-11-15T20:25:58 | https://www.reddit.com/r/LocalLLaMA/comments/17w2uc2/lmstudio_how_to_bulk_export_text_from/ | innocuousAzureus | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 17w2uc2 | false | null | t3_17w2uc2 | /r/LocalLLaMA/comments/17w2uc2/lmstudio_how_to_bulk_export_text_from/ | false | false | default | 1 | null |
Does LMstudio break your privacy? | 1 | [removed] | 2023-11-15T19:58:40 | https://www.reddit.com/r/LocalLLaMA/comments/17w26xa/does_lmstudio_break_your_privacy/ | innocuousAzureus | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 17w26xa | false | null | t3_17w26xa | /r/LocalLLaMA/comments/17w26xa/does_lmstudio_break_your_privacy/ | false | false | self | 1 | null |
Visibility is important | 1 | I've been in LocalLlaMa for a while now, and one of the great things about this subreddit is that people share the results of their tests, something especially helpful in a field where something new seems to be built on an almost daily basis. However, there aren't any tools for true visibility behind the scenes of what... | 2023-11-15T19:27:54 | https://www.reddit.com/r/LocalLLaMA/comments/17w1i5p/visibility_is_important/ | Ok_Relationship_9879 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 17w1i5p | false | null | t3_17w1i5p | /r/LocalLLaMA/comments/17w1i5p/visibility_is_important/ | false | false | self | 1 | {'enabled': False, 'images': [{'id': 'mtw_vw8q5e4EJF5So7Vu-vjQ2OgMMlJs1mLy1vQlNp0', 'resolutions': [{'height': 78, 'url': 'https://external-preview.redd.it/gm8Z5HCwnl87iBXhg5z8vMBPWwsobF99FPuH-gCge3c.jpg?width=108&crop=smart&auto=webp&s=572b75ec872f632445b76c9fad18709337fc6980', 'width': 108}, {'height': 157, 'url': 'h... |
Visibility is important | 1 | I've been in LocalLlaMa for a while now, and one of the great things about this subreddit is that people share the results of their tests, something especially helpful in a field where something new seems to be built on an almost daily basis. However, there aren't any tools for true visibility behind the scenes of what... | 2023-11-15T19:27:47 | https://www.reddit.com/r/LocalLLaMA/comments/17w1i26/visibility_is_important/ | Ok_Relationship_9879 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 17w1i26 | false | null | t3_17w1i26 | /r/LocalLLaMA/comments/17w1i26/visibility_is_important/ | false | false | self | 1 | null |
Curious about knowledge files for local LLMs | 1 | Hey all,
The recent GPT builder announcement has got me really into making coding assistants. I’m trying to create knowledge files that override blind spots created during ChatGPT’s training process. For instance with Flutter null safety is a persistent and annoying issue so I’ve made instructions to force it to pay m... | 2023-11-15T18:29:48 | https://www.reddit.com/r/LocalLLaMA/comments/17w066h/curious_about_knowledge_files_for_local_llms/ | SuccotashComplete | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 17w066h | false | null | t3_17w066h | /r/LocalLLaMA/comments/17w066h/curious_about_knowledge_files_for_local_llms/ | false | false | self | 1 | null |
How to rank models by popularity | 18 | https://openrouter.ai/rankings
Apps are mostly roleplay, followed by coding assistants, games, and content marketing. They’re shown here: openrouter.ai
Feedback welcome!
Feedback welcome! | 2023-11-15T18:09:36 | stevexander | i.redd.it | 1970-01-01T00:00:00 | 0 | {} | 17vzows | false | null | t3_17vzows | /r/LocalLLaMA/comments/17vzows/how_to_rank_models_by_popularity/ | false | false | 18 | {'enabled': True, 'images': [{'id': 'eH3jgaDHan_B5TzuF2-y0K3yorF5vYhwzcruiplY8zQ', 'resolutions': [{'height': 216, 'url': 'https://preview.redd.it/90u2e2h8yj0c1.jpeg?width=108&crop=smart&auto=webp&s=1654b546894c761b7856578bd69fc4602434f53c', 'width': 108}, {'height': 432, 'url': 'https://preview.redd.it/90u2e2h8yj0c1.j... | ||
How to increase the output size of any local LLM (Mistral\LLAMA)? | 1 | [removed] | 2023-11-15T17:54:00 | https://www.reddit.com/r/LocalLLaMA/comments/17vzbly/how_to_increase_the_output_size_of_any_local_llm/ | alex_pro777 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 17vzbly | false | null | t3_17vzbly | /r/LocalLLaMA/comments/17vzbly/how_to_increase_the_output_size_of_any_local_llm/ | false | false | self | 1 | null |
Mistral 13-16B? | 15 | Hey guys,
I heard mistral is releasing a model with 2x number of parameters as the open source one before the EOY, but is this one going to be behind their own api rather than open source? Or we're they talking about 'premium models' meaning even larger params. Really need this to be open source, thanks. | 2023-11-15T17:45:58 | https://www.reddit.com/r/LocalLLaMA/comments/17vz4v2/mistral_1316b/ | enterguild | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 17vz4v2 | false | null | t3_17vz4v2 | /r/LocalLLaMA/comments/17vz4v2/mistral_1316b/ | false | false | self | 15 | null |
Suggestion for LLM which has the best understanding of language structure | 2 | I want to build a very specific application which will take a block of text and give a boolean reply if the sentence is a proper english sentence or not.
Any suggestion for any such LLM?
For example, I have had some success with GPT-4, but I want to run it locally and not use OpenAI apis as of now. | 2023-11-15T17:29:47 | https://www.reddit.com/r/LocalLLaMA/comments/17vyrj8/suggestion_for_llm_which_has_the_best/ | shinigami_inso | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 17vyrj8 | false | null | t3_17vyrj8 | /r/LocalLLaMA/comments/17vyrj8/suggestion_for_llm_which_has_the_best/ | false | false | self | 2 | null |
Mistral Premium Model just mentioned at MS Ignite | 51 | Looks like there will be a premium non-open source model for mistral, hopefully it's the 180B version and the lower param models will remain open source. | 2023-11-15T17:29:28 | https://www.reddit.com/r/LocalLLaMA/comments/17vyrao/mistral_premium_model_just_mentioned_at_ms_ignite/ | johnfiretv | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 17vyrao | false | null | t3_17vyrao | /r/LocalLLaMA/comments/17vyrao/mistral_premium_model_just_mentioned_at_ms_ignite/ | false | false | self | 51 | null |
"A Benchmark to Understand the Role of Knowledge Graphs on Large Language Model's Accuracy for Question Answering on Enterprise SQL Databases"—Putting numbers to many of our intuition that KGs are much more effective than other context inputs in RAG-like approaches | 32 | 2023-11-15T16:58:52 | https://arxiv.org/abs/2311.07509 | CodeGriot | arxiv.org | 1970-01-01T00:00:00 | 0 | {} | 17vy1bo | false | null | t3_17vy1bo | /r/LocalLLaMA/comments/17vy1bo/a_benchmark_to_understand_the_role_of_knowledge/ | false | false | 32 | {'enabled': False, 'images': [{'id': 'q3evP6JeDpAC2MdSQHWYxnCYTqbJkElIQsLFqVSdkss', 'resolutions': [{'height': 63, 'url': 'https://external-preview.redd.it/izh8gZHY4FqZ1nwtU1N_TjtohUCNuvTyMn90toXda80.jpg?width=108&crop=smart&auto=webp&s=bc9575b410002edc2df3c5b5b0355fefedc7baa8', 'width': 108}, {'height': 126, 'url': 'h... | ||
Cerebras system for fine-tuning | 1 | [removed] | 2023-11-15T16:46:17 | https://www.cerebras.net/product-cloud/ | ThenNeighborhood3723 | cerebras.net | 1970-01-01T00:00:00 | 0 | {} | 17vxrn9 | false | null | t3_17vxrn9 | /r/LocalLLaMA/comments/17vxrn9/cerebras_system_for_finetuning/ | false | false | default | 1 | null |
fastchat-t5 cheapest hosting? | 5 | I already tried to set up [fastchat-t5](https://huggingface.co/lmsys/fastchat-t5-3b-v1.0) on a digitalocean virtual server with 32 GiB and 4 vCPUs for $160/month with CPU interference. The performance was horrible. Answers took about 5 seconds for the first token and then 1 word per second.
Any ideas how to host a sm... | 2023-11-15T16:45:55 | https://www.reddit.com/r/LocalLLaMA/comments/17vxrco/fastchatt5_cheapest_hosting/ | HeronAI_com | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 17vxrco | false | null | t3_17vxrco | /r/LocalLLaMA/comments/17vxrco/fastchatt5_cheapest_hosting/ | false | false | self | 5 | {'enabled': False, 'images': [{'id': 'Eob4KxD9FNha-O7U37iX0SAjsaXoUzz1R-3lVieTQYs', 'resolutions': [{'height': 58, 'url': 'https://external-preview.redd.it/rLr3mk3gNr3DPa6OWBP7JyJ8UBLgtJWKoYIQsiuBNhM.jpg?width=108&crop=smart&auto=webp&s=bacda9661cbe5e040ee75fd99dcabafa648b3cea', 'width': 108}, {'height': 116, 'url': 'h... |
Change the writing style: Dolphin 2.2 Yi 34b | 1 | I am using the new \`TheBloke/dolphin-2\_2-yi-34b-GPTQ\`, but I am not succeeding in changing the writing style of the model. I tried adding it in the character, system prompt or user prompt (API), but the result is still the same.
Example (the end I didnt expect 😂)
https://preview.redd.it/ujzp7dp78j0c1.png?widt... | 2023-11-15T15:45:22 | https://www.reddit.com/r/LocalLLaMA/comments/17vwg3r/change_the_writing_style_dolphin_22_yi_34b/ | reddithotel | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 17vwg3r | false | null | t3_17vwg3r | /r/LocalLLaMA/comments/17vwg3r/change_the_writing_style_dolphin_22_yi_34b/ | false | false | 1 | null | |
My model won't stop repeating itself and I can't figure out why. | 1 | [removed] | 2023-11-15T14:54:11 | https://www.reddit.com/r/LocalLLaMA/comments/17vvc1c/my_model_wont_stop_repeating_itself_and_i_cant/ | Future_Might_8194 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 17vvc1c | false | null | t3_17vvc1c | /r/LocalLLaMA/comments/17vvc1c/my_model_wont_stop_repeating_itself_and_i_cant/ | false | false | 1 | null | |
Myntra's Maya Chatbot | 2 | Does anyone have any idea or suggestions on how can I make chatbot like that for my shopping website. Do suggest your idea, thanks. | 2023-11-15T13:54:00 | https://www.reddit.com/r/LocalLLaMA/comments/17vu43u/myntras_maya_chatbot/ | One-Difficulty3149 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 17vu43u | false | null | t3_17vu43u | /r/LocalLLaMA/comments/17vu43u/myntras_maya_chatbot/ | false | false | self | 2 | null |
🚀 Exciting Updates from Together AI: Breakthroughs in Inference, Custom Models, and GPU Power! | 1 | Hey LLM enthusiasts! Together AI just rolled out some incredible updates that are game changers in the world of large language models. Here’s a quick rundown:
1. **Together Inference Engine Launched**: Prepare to be blown away! This new inference engine integrates cutting-edge techniques like FlashAttention-2, Flash-D... | 2023-11-15T13:48:54 | https://www.reddit.com/r/LocalLLaMA/comments/17vu0le/exciting_updates_from_together_ai_breakthroughs/ | noioiomio | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 17vu0le | false | null | t3_17vu0le | /r/LocalLLaMA/comments/17vu0le/exciting_updates_from_together_ai_breakthroughs/ | false | false | self | 1 | {'enabled': False, 'images': [{'id': 'KEKqZLXaDuojO8066WvfNm2knPNQpREJOqDRQbP0jOE', 'resolutions': [{'height': 56, 'url': 'https://external-preview.redd.it/qjk8U15PVqk_QNAR85GDkE6bEzmE2vOAbbKeJark_ng.jpg?width=108&crop=smart&auto=webp&s=c4356a09ff651d99050d2e2f7c625136bd5cc50d', 'width': 108}, {'height': 113, 'url': 'h... |
Run uncensored Yi, dolphin-2.2-yi-34b, on your own device/ across platforms | 1 | 2023-11-15T13:10:07 | https://www.secondstate.io/articles/dolphin-2.2-yi-34b/ | smileymileycoin | secondstate.io | 1970-01-01T00:00:00 | 0 | {} | 17vtawv | false | null | t3_17vtawv | /r/LocalLLaMA/comments/17vtawv/run_uncensored_yi_dolphin22yi34b_on_your_own/ | false | false | default | 1 | null | |
FP4 quantization state not initialized. Please call .cuda() or .to(device) on the LinearFP4 layer first. | 1 | Hi guys I'm following this guide to fine tune mistral: [https://github.com/brevdev/notebooks/blob/main/mistral-finetune-own-data.ipynb](https://github.com/brevdev/notebooks/blob/main/mistral-finetune-own-data.ipynb)
Running into this error when running inference on the fine tuned model: "FP4 quantization state not ini... | 2023-11-15T11:05:21 | https://www.reddit.com/r/LocalLLaMA/comments/17vrbea/fp4_quantization_state_not_initialized_please/ | AstronomerChance5093 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 17vrbea | false | null | t3_17vrbea | /r/LocalLLaMA/comments/17vrbea/fp4_quantization_state_not_initialized_please/ | false | false | self | 1 | {'enabled': False, 'images': [{'id': 'XwTOhMx3c6iXxQHmDIPQyRunmduCYYuiPKnTNYreN-k', 'resolutions': [{'height': 54, 'url': 'https://external-preview.redd.it/wavKbGgA6AuU3xeXBugbyVDxpFWrSxpFd-ybVsZRcF0.jpg?width=108&crop=smart&auto=webp&s=f8cc26b89a67acb94e6160e999a5a5d444855b67', 'width': 108}, {'height': 108, 'url': 'h... |
How/What are people doing to help creative writing processes with local LLMs? (Setup Advice) | 6 | Hi,
So I’ve no problem setting up models, have quite a few running well!
I’ve been writing a fiction book for a while and I’m a few chapters in. I’m wondering what is the best way to provide enough context i.e, read what I’ve written so far and suggest “what would character X be feeling here” or those kinds of ques... | 2023-11-15T10:54:35 | https://www.reddit.com/r/LocalLLaMA/comments/17vr5jk/howwhat_are_people_doing_to_help_creative_writing/ | Adventurous_Cat_1559 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 17vr5jk | false | null | t3_17vr5jk | /r/LocalLLaMA/comments/17vr5jk/howwhat_are_people_doing_to_help_creative_writing/ | false | false | self | 6 | null |
What exactly is pulling 100-110W when running local LLM? | 2 | This is purely out of curiosity, but if anybody has some insights I'd love to hear it.
I am running 70B Q4 models on my M1 Max Macbook Pro (10 CPU, 32 GPU, 64 GB RAM). The lid is closed because I have an external monitor 4K attached via USB-C, so the display won't draw any power.
I am using both llama.cpp and LM Stud... | 2023-11-15T10:51:14 | https://www.reddit.com/r/LocalLLaMA/comments/17vr3uu/what_exactly_is_pulling_100110w_when_running/ | k_michael | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 17vr3uu | false | null | t3_17vr3uu | /r/LocalLLaMA/comments/17vr3uu/what_exactly_is_pulling_100110w_when_running/ | false | false | self | 2 | null |
Brand New Mistral 16k Context Size Models got released last night from NurtureAI! | 7 | In no particular order! Don't forget to use each of their specific prompts for the best generations!
AWQ, and GGUF also available.
[https://huggingface.co/NurtureAI/zephyr-7b-beta-16k](https://huggingface.co/NurtureAI/zephyr-7b-beta-16k)
[https://huggingface.co/NurtureAI/neural-chat-7b-v3-16k](https://hugging... | 2023-11-15T10:22:48 | https://www.reddit.com/r/LocalLLaMA/comments/17vqpuy/brand_new_mistral_16k_context_size_models_got/ | perlthoughts | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 17vqpuy | false | null | t3_17vqpuy | /r/LocalLLaMA/comments/17vqpuy/brand_new_mistral_16k_context_size_models_got/ | false | false | self | 7 | {'enabled': False, 'images': [{'id': 'uT9brwKBK1bSMscHxGFMv9rzfoxP2n-yLPmfmEoAeTA', 'resolutions': [{'height': 58, 'url': 'https://external-preview.redd.it/RaCibwc8VxDnT3yv7Kmi3e4Oz_ajVscY_Z0X1-kRNA0.jpg?width=108&crop=smart&auto=webp&s=8243b4a23a32756eb86ce1c9488f50aee34f34d4', 'width': 108}, {'height': 116, 'url': 'h... |
SQLCoder-34b beats GPT-4 at Text-to-SQL | 43 | Defog's SQLCoder is a state-of-the-art LLM for converting natural language questions to SQL queries.
SQLCoder-34B is a 34B parameter model that outperforms gpt-4 and gpt-4-turbo for natural language to SQL generation tasks on our [**sql-eval**](https://github.com/defog-ai/sql-eval) framework, and significantly outperf... | 2023-11-15T09:48:03 | https://www.reddit.com/r/LocalLLaMA/comments/17vq8t2/sqlcoder34b_beats_gpt4_at_texttosql/ | tail-recursion | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 17vq8t2 | false | null | t3_17vq8t2 | /r/LocalLLaMA/comments/17vq8t2/sqlcoder34b_beats_gpt4_at_texttosql/ | false | false | self | 43 | {'enabled': False, 'images': [{'id': 'XICybhI4tjOoNvT_KYBcxk2eOwBKA7W5UxzFb0kuG9Q', 'resolutions': [{'height': 54, 'url': 'https://external-preview.redd.it/t6E7Ijp2Fw2rnbC_7evWvBd-T7W1-Nzyi3kjdK4wvkU.jpg?width=108&crop=smart&auto=webp&s=a5fd145b0ec8958a02ad5494590410f1a496cb50', 'width': 108}, {'height': 108, 'url': 'h... |
Is LMStudio.ai open-sourced? | 1 | [removed] | 2023-11-15T09:36:32 | https://www.reddit.com/r/LocalLLaMA/comments/17vq3cs/is_lmstudioai_opensourced/ | homelab2946 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 17vq3cs | false | null | t3_17vq3cs | /r/LocalLLaMA/comments/17vq3cs/is_lmstudioai_opensourced/ | false | false | self | 1 | null |
Running LLM on my personal pc | 2 | So in the last few weeks i have been experimenting with LLMs on my personal laptop (as I'm rarely at home) but I'm gonna have my pc with me in a few days. When running models (MythoMax 13b, mostly Q6\_K and Q5\_K\_M GGUF) I can definitely feel my laptop not liking it. Slowdowns, crashes, service terminations and timeou... | 2023-11-15T09:17:26 | https://www.reddit.com/r/LocalLLaMA/comments/17vpu0d/running_llm_on_my_personal_pc/ | Wortkraecker | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 17vpu0d | false | null | t3_17vpu0d | /r/LocalLLaMA/comments/17vpu0d/running_llm_on_my_personal_pc/ | false | false | self | 2 | null |
How to test the accuracy of LLama-2 on the MetaQA dataset? | 1 | I found that many papers tested the accuracy of the llama2 model on the MetaQA data set in experiments. But I have two questions about the experiment：
* The golden answer in MetaQA is structured, while the output of llama2 is unstructured. How to calculate whether the answer of llama2 is correct in the experiment?
* S... | 2023-11-15T09:14:23 | https://www.reddit.com/r/LocalLLaMA/comments/17vpsk2/how_to_test_the_accuracy_of_llama2_on_the_metaqa/ | Kunmel | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 17vpsk2 | false | null | t3_17vpsk2 | /r/LocalLLaMA/comments/17vpsk2/how_to_test_the_accuracy_of_llama2_on_the_metaqa/ | false | false | self | 1 | null |
Participating in Petals/Bloom | 3 | It does need what spec? Your priority in it is defined by the size of your specs? They say that we need to host a part of the model, but what part, how much? | 2023-11-15T08:49:58 | https://www.reddit.com/r/LocalLLaMA/comments/17vpgym/participating_in_petalsbloom/ | xqoe | self.LocalLLaMA | 2023-11-15T10:31:50 | 0 | {} | 17vpgym | false | null | t3_17vpgym | /r/LocalLLaMA/comments/17vpgym/participating_in_petalsbloom/ | false | false | self | 3 | null |
Your settings are (probably) hurting your model - Why sampler settings matter | 572 | Local LLMs are wonderful, and we all know that, but something that's always bothered me is that nobody in the scene seems to want to standardize or even investigate the flaws of the current sampling methods. I've found that a bad preset can make a model **significantly worse** or *golden* depending on the settings.
It... | 2023-11-15T07:48:15 | https://www.reddit.com/r/LocalLLaMA/comments/17vonjo/your_settings_are_probably_hurting_your_model_why/ | kindacognizant | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 17vonjo | false | null | t3_17vonjo | /r/LocalLLaMA/comments/17vonjo/your_settings_are_probably_hurting_your_model_why/ | false | false | 572 | {'enabled': False, 'images': [{'id': '5I8s-R2JeMUqzEg2dVIKlp8GO7BFWvaRWYS9J0uNNn4', 'resolutions': [{'height': 54, 'url': 'https://external-preview.redd.it/L8c41s0anbAG4J0YDSwFkfHV4qqy-kLXJ2WDQ2BhskY.jpg?width=108&crop=smart&auto=webp&s=977683e90cec855721b360607a9cf1e6c7daddfd', 'width': 108}, {'height': 108, 'url': 'h... | |
Contamination of famous Large Language Model (LLM) benchmarks??? | 2 |
I've heard doubts about the leakage of benchmark data, not only from the well-known benchmarks on Hugging Face's open LLM leaderboard but also others, and have concluded that quantitative scores cannot be trusted.
This has been indirectly mentioned in some papers as well.
In practice, I found no significant diff... | 2023-11-15T05:33:49 | https://www.reddit.com/r/LocalLLaMA/comments/17vmorr/contamination_of_famous_large_language_model_llm/ | Holiday_Fly_590 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 17vmorr | false | null | t3_17vmorr | /r/LocalLLaMA/comments/17vmorr/contamination_of_famous_large_language_model_llm/ | false | false | self | 2 | null |
Is Upgrading from NVIDIA H100 to H200 Worth It? | 20 | I've been closely following the recent developments from NVIDIA, and their latest announcement has really caught my attention: the H200 with the new GH200 chip. This beast is said to pack a staggering 141 GB of RAM and offers a blazing 4.8 TB/s speed. The premiere of the H200 is slated for the second quarter of 2024, a... | 2023-11-15T04:27:04 | https://www.reddit.com/r/LocalLLaMA/comments/17vll26/is_upgrading_from_nvidia_h100_to_h200_worth_it/ | Wrong_User_Logged | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 17vll26 | false | null | t3_17vll26 | /r/LocalLLaMA/comments/17vll26/is_upgrading_from_nvidia_h100_to_h200_worth_it/ | false | false | self | 20 | null |
Guidance on QA dataset creation | 1 | I am looking to create a propiertary dataset to fine-tune a LLM model. Based on the context, the llm should extract details, such as person's name, dob, height, weight, academics etc. In certain documents, some of these details might not be present.
Question: Does mentioning a field as null, if it's not present help i... | 2023-11-15T04:18:50 | Ok_Ganache_5040 | i.redd.it | 1970-01-01T00:00:00 | 0 | {} | 17vlfzk | false | null | t3_17vlfzk | /r/LocalLLaMA/comments/17vlfzk/guidance_on_qa_dataset_creation/ | false | false | 1 | {'enabled': True, 'images': [{'id': 'wuI5FScvXMWPs7LY9Y5FQ-bzltSDqcRrPBBtQVUTin8', 'resolutions': [{'height': 54, 'url': 'https://preview.redd.it/4aht9ig0uf0c1.jpg?width=108&crop=smart&auto=webp&s=2bcba1cc053db136c9ca187d22653cb45cf984a9', 'width': 108}, {'height': 108, 'url': 'https://preview.redd.it/4aht9ig0uf0c1.jpg... | ||
Those of you with high system ram machines. How fast is your ram? How important is MT/Latency speed? | 1 | [removed] | 2023-11-15T04:12:20 | https://www.reddit.com/r/LocalLLaMA/comments/17vlc2n/those_of_you_with_high_system_ram_machines_how/ | wh33t | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 17vlc2n | false | null | t3_17vlc2n | /r/LocalLLaMA/comments/17vlc2n/those_of_you_with_high_system_ram_machines_how/ | false | false | self | 1 | null |
Web search for LLMs via the you.com API | 3 | 2023-11-15T03:54:51 | https://about.you.com/introducing-the-you-api-web-scale-search-for-llms/ | WaterdanceAC | about.you.com | 1970-01-01T00:00:00 | 0 | {} | 17vl0xt | false | null | t3_17vl0xt | /r/LocalLLaMA/comments/17vl0xt/web_search_for_llms_via_the_youcom_api/ | false | false | default | 3 | null | |
Hallucination rate and Accuracy leader board | 38 | More models to be added soon. Llama-2 does well.
LLMs were asked to summarize text. Summarization was analyzed for accuracy and hallucinations. Below are the results.
[https://twitter.com/vectara/status/1721943596692070486](https://twitter.com/vectara/status/1721943596692070486)
​
https://preview.redd.it/... | 2023-11-15T03:52:22 | https://www.reddit.com/r/LocalLLaMA/comments/17vkze4/hallucination_rate_and_accuracy_leader_board/ | Terminator857 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 17vkze4 | false | null | t3_17vkze4 | /r/LocalLLaMA/comments/17vkze4/hallucination_rate_and_accuracy_leader_board/ | false | false | 38 | {'enabled': False, 'images': [{'id': 'LTVh18yygAV8AP8hyqnB60hpOxDbP84jMZOIztThGX8', 'resolutions': [{'height': 61, 'url': 'https://external-preview.redd.it/TNHeboZb7--Qt1yJpRVITOIS4SyUtsHIIuNY5dNoOgk.jpg?width=108&crop=smart&auto=webp&s=b04f344de6b77ee203fc7d9c4b1e7fa1555bc33e', 'width': 108}, {'height': 123, 'url': 'h... | |
What are some of the things that would be cool to explore using LLVM that you run locally on GPU ? | 1 | The questions comes as, ok all this models are cool, but could there be used in an automated fashion, to do cool things with them or everyone is doing the basic ChatGPT style thing ? Could they read all notes and documend on computer and build an huge index and used that as somekind knowladge graph a base something lik... | 2023-11-15T01:37:21 | https://www.reddit.com/r/LocalLLaMA/comments/17viawx/what_are_some_of_the_things_that_would_be_cool_to/ | openroom_xyz | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 17viawx | false | null | t3_17viawx | /r/LocalLLaMA/comments/17viawx/what_are_some_of_the_things_that_would_be_cool_to/ | false | false | self | 1 | null |
Training Llama 2? | 1 | I need help, every video I find on YouTube is out of date or I just can't get it to work. I am working on a data set for shadowrun lore. Are there good viedoes or up to date how to Wiki's you people like? Or should I just hold off on llama 2 and train a llama 1 model?
I tried the build in trainer but I am not having a... | 2023-11-15T00:14:48 | https://www.reddit.com/r/LocalLLaMA/comments/17vgkno/training_llama_2/ | psdwizzard | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 17vgkno | false | null | t3_17vgkno | /r/LocalLLaMA/comments/17vgkno/training_llama_2/ | false | false | self | 1 | null |
Using LMStudio with ggml_llava-v1.5-7b | 2 | Basically I am trying to pass an image to the model and expect it to work. Unfortunately I haven't found how to pass an image using LMStudio. Any ideas? This is the model I am using. [https://huggingface.co/mys/ggml\_llava-v1.5-7b](https://huggingface.co/mys/ggml_llava-v1.5-7b) I was able to make this model work with ... | 2023-11-14T23:45:58 | https://www.reddit.com/r/LocalLLaMA/comments/17vfy1c/using_lmstudio_with_ggml_llavav157b/ | ilt1 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 17vfy1c | false | null | t3_17vfy1c | /r/LocalLLaMA/comments/17vfy1c/using_lmstudio_with_ggml_llavav157b/ | false | false | self | 2 | {'enabled': False, 'images': [{'id': 'pWxt_1VSXKiPvRwMPArhF8uexTPS3SWBzcbBPfayWF4', 'resolutions': [{'height': 58, 'url': 'https://external-preview.redd.it/g3hjFYbCGoFd1wVNf8QRy5ORlbH2pyPEWeL8FifAw-E.jpg?width=108&crop=smart&auto=webp&s=e4bbd5e19cfdd8b5e87d6c49f099e11aaf01c386', 'width': 108}, {'height': 116, 'url': 'h... |
Guidance is back 🥳 | 1 | 2023-11-14T22:24:58 | https://github.com/guidance-ai/guidance | a_fish1 | github.com | 1970-01-01T00:00:00 | 0 | {} | 17ve3sd | false | null | t3_17ve3sd | /r/LocalLLaMA/comments/17ve3sd/guidance_is_back/ | false | false | 1 | {'enabled': False, 'images': [{'id': 'hXH2T2631Dhrx_fZEhMo966YA9jDyZphpWqmttSgA4Q', 'resolutions': [{'height': 54, 'url': 'https://external-preview.redd.it/dsNlxhuKzC7mbTKvrnwTF2F-EBQoxYBzhoA6elZzr-c.jpg?width=108&crop=smart&auto=webp&s=38b8db7e9314142300d9f240d0894a9d7afdfb9a', 'width': 108}, {'height': 108, 'url': 'h... | ||
I'd like to build a remote Game Master bot for my friends for an async LLM concept I have. What open source tools can I build a custom frontend around and host on a remote server? | 7 | I've been tinkering a lot with Ooba webui and Silly Tavern, and now have ideas for a hobby project I'd like to build. I've used ST to serve remotely, but the idea of rebuilding even a portion of ST is more than I want to attempt right now. In general though, I'm wondering what tools or libraries I should consider if bu... | 2023-11-14T22:07:01 | https://www.reddit.com/r/LocalLLaMA/comments/17vdojg/id_like_to_build_a_remote_game_master_bot_for_my/ | SlateHardjaw | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 17vdojg | false | null | t3_17vdojg | /r/LocalLLaMA/comments/17vdojg/id_like_to_build_a_remote_game_master_bot_for_my/ | false | false | self | 7 | null |
Got Llama.cpp WebUI to work on Colab | 22 | I got tired of slow cpu inference as well as Text-Generation-WebUI that's getting buggier and buggier.
Here's a working example that offloads all the layers of zephyr-7b-beta.Q6_K.gguf to T4, a free GPU on Colab.
It's pretty fast! I get 28t/s.
https://colab.research.google.com/gist/chigkim/385e8d398b40c7e61755e1a256... | 2023-11-14T21:46:36 | https://www.reddit.com/r/LocalLLaMA/comments/17vd6pk/got_llamacpp_webui_to_work_on_colab/ | chibop1 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 17vd6pk | false | null | t3_17vd6pk | /r/LocalLLaMA/comments/17vd6pk/got_llamacpp_webui_to_work_on_colab/ | false | false | self | 22 | {'enabled': False, 'images': [{'id': 'nkhh65ujo5BznFJFojoMPaKjGuLSpPj6KGhRov-ykOg', 'resolutions': [{'height': 108, 'url': 'https://external-preview.redd.it/0-fRWqjlLadVXj5pfYp4_Oe3xgBWE-_rdjVSn7hlohI.jpg?width=108&crop=smart&auto=webp&s=f34d2dfdbbfa7de0f1956f186fd8430ee96a1a55', 'width': 108}, {'height': 216, 'url': '... |
Something wrong with older AMD high VRAM cards? | 2 | I've read a lot of hardware discussions here, but never a mention of cards like [AMD 102D1631200 Radeon Instinct MI60 32GB HBM2 ](https://www.ebay.com/itm/126120627827?epid=23058194614&hash=item1d5d600e73:g:Ov8AAOSw9UFimOyF&amdata=enc%3AAQAIAAAA4PKu7gj9w8icCb82LBC4Of%2BokWXTlLCdHfN7FGfhZ1VlHaVMn%2FABeW%2FmbEmZq%2BIxTCL... | 2023-11-14T21:30:06 | https://www.reddit.com/r/LocalLLaMA/comments/17vcsf9/something_wrong_with_older_amd_high_vram_cards/ | GermanK20 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 17vcsf9 | false | null | t3_17vcsf9 | /r/LocalLLaMA/comments/17vcsf9/something_wrong_with_older_amd_high_vram_cards/ | false | false | self | 2 | {'enabled': False, 'images': [{'id': 'Iqqu2a2lsAXeXhU1yDr9Dzkupz2wVbqyFdgBnccpgNo', 'resolutions': [{'height': 81, 'url': 'https://external-preview.redd.it/sgNmBKqtkvesMIeVbGgxs5F_tMnDqLNFXk3y-C3z5aM.jpg?width=108&crop=smart&auto=webp&s=0f12bb2feffb71a156d3b857e1ec177fc7edea1f', 'width': 108}, {'height': 162, 'url': 'h... |
🐺🐦⬛ LLM Comparison/Test: 2x 34B Yi (Dolphin, Nous Capybara) vs. 12x 70B, 120B, ChatGPT/GPT-4 | 342 | I'm still hard at work on my in-depth 70B model evaluations, but with the recent releases of the first Yi finetunes, I can't hold back anymore and need to post this now...
Curious about these new Yi-based 34B models, I tested and compared them to the best 70Bs. And to make such a comparison even more exciting (and pos... | 2023-11-14T21:28:43 | https://www.reddit.com/r/LocalLLaMA/comments/17vcr9d/llm_comparisontest_2x_34b_yi_dolphin_nous/ | WolframRavenwolf | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 17vcr9d | false | null | t3_17vcr9d | /r/LocalLLaMA/comments/17vcr9d/llm_comparisontest_2x_34b_yi_dolphin_nous/ | false | false | self | 342 | {'enabled': False, 'images': [{'id': 'bDW7jyCB5L7RKBwRUqrzWSn3bIb_Szu_GogYRebiCjw', 'resolutions': [{'height': 54, 'url': 'https://external-preview.redd.it/tj8OYAHtgushFKKBfbCCyLFmzL7PWZ-Wz8cbqYk-I9E.jpg?width=108&crop=smart&auto=webp&s=f076a50b0d594dc8ba3b2ee703d67664decf1cba', 'width': 108}, {'height': 108, 'url': 'h... |
Open source LLMs generally used for publishing results | 1 | What are some of the major Open source LLMs which researchers use to test their strategies on (decoding/quantization/etc.) . I have till now used LLama-2 and MPT, what would be some other good choices for this? Vicuna is a model based on Llama itself so that won't be a good choice. Any suggestions? | 2023-11-14T20:51:16 | https://www.reddit.com/r/LocalLLaMA/comments/17vbvna/open_source_llms_generally_used_for_publishing/ | charizard_me | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 17vbvna | false | null | t3_17vbvna | /r/LocalLLaMA/comments/17vbvna/open_source_llms_generally_used_for_publishing/ | false | false | self | 1 | null |
Recommendations for C# .NET-Focused Coding Assistance Models | 3 | I've been using CodeLlama for my C# .NET projects, but it hasn't met my expectations. Does anyone have experience with coding assistance models that excel specifically in C# .NET environments? I'm looking for a tool that offers advanced features like nuanced error detection and efficient refactoring suggestions, b... | 2023-11-14T20:44:22 | https://www.reddit.com/r/LocalLLaMA/comments/17vbq2k/recommendations_for_c_netfocused_coding/ | Superluis25 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 17vbq2k | false | null | t3_17vbq2k | /r/LocalLLaMA/comments/17vbq2k/recommendations_for_c_netfocused_coding/ | false | false | self | 3 | null |
Does OpenAI ToS prohibit generating datasets for open source LLMs? | 1 | 2023-11-14T20:31:57 | Divniy | i.redd.it | 1970-01-01T00:00:00 | 0 | {} | 17vbg1f | false | null | t3_17vbg1f | /r/LocalLLaMA/comments/17vbg1f/does_openai_tos_prohibit_generating_datasets_for/ | false | false | 1 | {'enabled': True, 'images': [{'id': '0c2x5MzLGM7XtMdodKzGu99XQTKfQFTlBf1j_4kbdR4', 'resolutions': [{'height': 58, 'url': 'https://preview.redd.it/1bkkrjrmhd0c1.png?width=108&crop=smart&auto=webp&s=4ddae2ac547a7ebd22589cf9ba32f585ba06bc06', 'width': 108}, {'height': 116, 'url': 'https://preview.redd.it/1bkkrjrmhd0c1.png... | |||
Polanka 7b - Polish LLM based on Mistral | 29 | Warning, this is still work in progress.
[https://huggingface.co/piotr-ai/polanka-7b-v0.1](https://huggingface.co/piotr-ai/polanka-7b-v0.1)
First version of 7b Polish LLM finetuned using custom data in Polish language.
As a base model I used uncensored [https://huggingface.co/ehartford/dolphin-2.1-mistral-7b](https:... | 2023-11-14T19:48:45 | https://www.reddit.com/r/LocalLLaMA/comments/17vajv1/polanka_7b_polish_llm_based_on_mistral/ | Significant_Focus134 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 17vajv1 | false | null | t3_17vajv1 | /r/LocalLLaMA/comments/17vajv1/polanka_7b_polish_llm_based_on_mistral/ | false | false | self | 29 | {'enabled': False, 'images': [{'id': 'yD6Vq1Jlk0VR8yh_FcgmsyG8nGT5uyB8EuVXplmjWvo', 'resolutions': [{'height': 58, 'url': 'https://external-preview.redd.it/3S1l6K55O4OuROkUaB4lccyYnNSlDSbyLtY7GOaj-gQ.jpg?width=108&crop=smart&auto=webp&s=ac4bb18979598615cdc3beb6e4317e180581aaba', 'width': 108}, {'height': 116, 'url': 'h... |
Fine tuning LLM for Text to SQL - Self consistency | 1 | Hi, I'm fine tuning Mistral with Text-SQL pairs. Given that execution accuracy is very important in this task, what are the different ways one could ensure that the model outputs executable queries that are correct in syntax and appropirately answers the question? I was looking into self consistency but generation k sa... | 2023-11-14T19:41:24 | https://www.reddit.com/r/LocalLLaMA/comments/17vadx2/fine_tuning_llm_for_text_to_sql_self_consistency/ | weedyuh | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 17vadx2 | false | null | t3_17vadx2 | /r/LocalLLaMA/comments/17vadx2/fine_tuning_llm_for_text_to_sql_self_consistency/ | false | false | self | 1 | null |
Storing LLM models on external SSD: Is the SSD speed important? Samsung T7 w/ USB 3.2 (read: 1050MB/s) vs. Fantom w/ Thunderbolt 3/4 (read: 2800MB/s) | 8 | (title) | 2023-11-14T18:58:15 | https://www.reddit.com/r/LocalLLaMA/comments/17v9eqr/storing_llm_models_on_external_ssd_is_the_ssd/ | nderstand2grow | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 17v9eqr | false | null | t3_17v9eqr | /r/LocalLLaMA/comments/17v9eqr/storing_llm_models_on_external_ssd_is_the_ssd/ | false | false | self | 8 | null |
UI w/ context free local function calling. Define 100's of plugins with 50+ included OOB in v0.1.0, integrating with tons of other AI models. All 100% local with Llama 2 7B! | 47 | 2023-11-14T18:43:22 | https://v.redd.it/6lg88jzwyc0c1 | noco-ai | v.redd.it | 1970-01-01T00:00:00 | 0 | {} | 17v92ct | false | {'reddit_video': {'bitrate_kbps': 5000, 'dash_url': 'https://v.redd.it/6lg88jzwyc0c1/DASHPlaylist.mpd?a=1702579416%2CMjdjYjRiOTQ3YjUwMDM5MmNjOWJlOWJkZjIwNWIxM2MxZWFhNmY0Y2U4ZjNkYTMzMmQ4NzNlOTU4MjYxMWFlNw%3D%3D&v=1&f=sd', 'duration': 30, 'fallback_url': 'https://v.redd.it/6lg88jzwyc0c1/DASH_1080.mp4?source=fallback', 'h... | t3_17v92ct | /r/LocalLLaMA/comments/17v92ct/ui_w_context_free_local_function_calling_define/ | false | false | 47 | {'enabled': False, 'images': [{'id': 'nMm_MedtkOekp7FMQVzpuMNXonEJzB-KdOy_s7K9wzQ', 'resolutions': [{'height': 60, 'url': 'https://external-preview.redd.it/w-eB_lK5qelEa3lVqwdzJnCQV2zKvyA0MFG0kr8G8oo.png?width=108&crop=smart&format=pjpg&auto=webp&s=8c8207c76dc9bf77ec102a25815b1a1ce0738af7', 'width': 108}, {'height': 12... | ||
Simple automation systems for spinning up cloud VMs with GPUs | 5 | Can anyone recommend a simple system designed to spin up short-lived cloud VMs with GPUs for inference? Something that can automatically spin up the VM and start services, and then turn it off when it's no longer in use?
I'd like to be able to run my own models without censorship from the inference-as-a-service provid... | 2023-11-14T18:35:51 | https://www.reddit.com/r/LocalLLaMA/comments/17v8w1s/simple_automation_systems_for_spinning_up_cloud/ | ostensiblymicah | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 17v8w1s | false | null | t3_17v8w1s | /r/LocalLLaMA/comments/17v8w1s/simple_automation_systems_for_spinning_up_cloud/ | false | false | self | 5 | null |
LLM Performance on M3 Max | 25 | 2023-11-14T18:26:03 | https://www.nonstopdev.com/llm-performance-on-m3-max/ | merryhime | nonstopdev.com | 1970-01-01T00:00:00 | 0 | {} | 17v8nv8 | false | null | t3_17v8nv8 | /r/LocalLLaMA/comments/17v8nv8/llm_performance_on_m3_max/ | false | false | 25 | {'enabled': False, 'images': [{'id': 'J0lLldtl0iKQZp-9n8iB1WriLreOvwxmkLcMRqVWuFY', 'resolutions': [{'height': 65, 'url': 'https://external-preview.redd.it/SacZ50L-iFz9kpRQnXpAYZa1bX0EjdI1H0G726BSTTk.jpg?width=108&crop=smart&auto=webp&s=dbec87e11ab7a8b94ba354001fcff23cae8a80c2', 'width': 108}, {'height': 130, 'url': 'h... | ||
DreamGen Opus 70B — Uncensored model for story telling and chat / roleplay | 90 | **TL;DR:**
- **Uncensored, Llama 2** **70B** based model for collaborative/steerable story writing and chat / role-play.
- **Hugging Face link:**
- **[dreamgen/opus-v0-70b](https://huggingface.co/dreamgen/opus-v0-70b)**
- [dreamgen/opus-v0-70b-awq](https://huggingface.co/dreamgen/opus-v0-70b-awq)
- [dreamg... | 2023-11-14T17:03:09 | https://www.reddit.com/r/LocalLLaMA/comments/17v6r0c/dreamgen_opus_70b_uncensored_model_for_story/ | DreamGenX | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 17v6r0c | false | null | t3_17v6r0c | /r/LocalLLaMA/comments/17v6r0c/dreamgen_opus_70b_uncensored_model_for_story/ | false | false | self | 90 | {'enabled': False, 'images': [{'id': 'dC_vpoKDGYBoIP7F1VzEVyZa3z2ER5QWOV0oA5p8id0', 'resolutions': [{'height': 58, 'url': 'https://external-preview.redd.it/9kMjvxeO3ngZjWPWv08aiRhe_L8qw9hFP0Qpc4yhBcc.jpg?width=108&crop=smart&auto=webp&s=27ba0597b819fd67559d55d93579818f6b2ffe44', 'width': 108}, {'height': 116, 'url': 'h... |
Training on the rephrased test set is all you need: 13B models can reach GPT-4 performance in benchmarks with no contamination detectable by traditional methods | 226 | 2023-11-14T16:55:34 | https://lmsys.org/blog/2023-11-14-llm-decontaminator/ | Covid-Plannedemic_ | lmsys.org | 1970-01-01T00:00:00 | 0 | {} | 17v6kp2 | false | null | t3_17v6kp2 | /r/LocalLLaMA/comments/17v6kp2/training_on_the_rephrased_test_set_is_all_you/ | false | false | 226 | {'enabled': False, 'images': [{'id': 'OHebbMrVXPgCOnnrdgReC7QDWkT1gC9hey8haUQ2LbQ', 'resolutions': [{'height': 97, 'url': 'https://external-preview.redd.it/FfQ4P8ptXczB32aUaEK_Hrmq-iWboz7s-uJeJXYXR6M.jpg?width=108&crop=smart&auto=webp&s=1495aa550ee54f33af42fad89ed5f192fe2d46d7', 'width': 108}, {'height': 195, 'url': 'h... | ||
Dataset format for fine-tuning Llama-2 with axolotl on conversations | 3 | Hello
I'm using axolotl for fine-tuning Llama-2 13B on conversations. One possibility is to have the dataset in the following format:
# dataset.jsonl
{"text": "### Human: This is a question### Chatbot: This is a reply### Human: What the hell are you talking about?"}
{"text": "### Human: Who's coming tonight?###... | 2023-11-14T16:19:54 | https://www.reddit.com/r/LocalLLaMA/comments/17v5s57/dataset_format_for_finetuning_llama2_with_axolotl/ | Helveticus99 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 17v5s57 | false | null | t3_17v5s57 | /r/LocalLLaMA/comments/17v5s57/dataset_format_for_finetuning_llama2_with_axolotl/ | false | false | self | 3 | null |
A fun day evaluating LLM Chat GUIs/Servers in Docker. Here's what I learned... | 26 | Today I tried a number of private (local) opensource **#GenAI** **#LLM** servers in Docker. I only run LLM servers in Docker. Without Docker I'm pretty sure my desktop would quickly become an angry bag of snakes in no time (Snakes, pythons, geddit? 🐍 😁 ). For context, I'm evaluating these LLM components to figure ou... | 2023-11-14T16:18:26 | https://www.reddit.com/r/LocalLLaMA/comments/17v5r0p/a_fun_day_evaluating_llm_chat_guisservers_in/ | benbravo73 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 17v5r0p | false | null | t3_17v5r0p | /r/LocalLLaMA/comments/17v5r0p/a_fun_day_evaluating_llm_chat_guisservers_in/ | false | false | 26 | {'enabled': False, 'images': [{'id': 'zPrgnSfSwVxQbnbhUPmrtJqHNHJL8R5btf3ZYYdAbk0', 'resolutions': [{'height': 54, 'url': 'https://external-preview.redd.it/eD5KfjHctjE0B4grTUd_PIeFhWx2m_YZwYslid3NLiY.jpg?width=108&crop=smart&auto=webp&s=ce3a553d51b120d8609fe038c719fe3102fa2400', 'width': 108}, {'height': 108, 'url': 'h... | |
How much more stupid is the 120B goliath Q3_K_M than the larger options? | 1 | I want to download the goliath model but I can only afford Q3\_K\_M. It is written that it has high quality losses. How much quality loss is there?
I heard that the larger the model, the less it suffers intellectually when it is optimized. I usually use 70B Q5\_K\_M. Can I expect that 120B Q3\_K\_M will be significant... | 2023-11-14T16:17:56 | https://www.reddit.com/r/LocalLLaMA/comments/17v5qmu/how_much_more_stupid_is_the_120b_goliath_q3_k_m/ | Secret_Joke_2262 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 17v5qmu | false | null | t3_17v5qmu | /r/LocalLLaMA/comments/17v5qmu/how_much_more_stupid_is_the_120b_goliath_q3_k_m/ | false | false | 1 | null | |
How much have chatbots like ChatGPT replaced Google or other search engines for you? | 4 | I've heard a lot of people say they use Google considerably less after they started using ChatGPT, but personally my usage of Google hasn't gone down that much. I still make lots of random searches out of curiosity, and use Perplexity to make those same searches, I'd actually say Perplexity has made me search more... | 2023-11-14T15:41:04 | https://www.reddit.com/r/LocalLLaMA/comments/17v4xm3/how_much_have_chatbots_like_chatgpt_replaced/ | TheTwelveYearOld | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 17v4xm3 | false | null | t3_17v4xm3 | /r/LocalLLaMA/comments/17v4xm3/how_much_have_chatbots_like_chatgpt_replaced/ | false | false | self | 4 | null |
Neural-chat-7b-v3-1 GGUF. New Mistral finetune | 24 | Couldn't wait for the great TheBloke to release it so I've uploaded a Q5\_K\_M GGUF of [Intel/neural-chat-7b-v3-1](https://huggingface.co/Intel/neural-chat-7b-v3-1).
From some preliminary test on [PISA sample questions](https://www.oecd.org/pisa/aboutpisa/PISA%20for%20Schools%20sample%20test%20items.pdf) it seems a... | 2023-11-14T15:39:53 | https://www.reddit.com/r/LocalLLaMA/comments/17v4woq/neuralchat7bv31_gguf_new_mistral_finetune/ | fakezeta | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 17v4woq | false | null | t3_17v4woq | /r/LocalLLaMA/comments/17v4woq/neuralchat7bv31_gguf_new_mistral_finetune/ | false | false | 24 | {'enabled': False, 'images': [{'id': 'MTHa0RFu26sELjrensnxBNo3EpGgvvXukCfilQ3uEDY', 'resolutions': [{'height': 58, 'url': 'https://external-preview.redd.it/oVzLyFlZ-FVRhjd4IQzuJpDzN-DCVuLdmZNUeFdKrrY.jpg?width=108&crop=smart&auto=webp&s=74983322bb1387297c0925d101f2cdac0e0cbc03', 'width': 108}, {'height': 116, 'url': 'h... | |
Help with Alpaca prompt formatting? | 3 | Im trying to use a new model which requires Alpaca formatting, I've only used llama2 formatted prompts before so I tried to convert my existing ones and Im having some trouble.
My llama2 prompts which work well look like this:
\`\`\`
\[INST\]
Task: Generate a JSON file containing a series of French sentences tailo... | 2023-11-14T14:46:38 | https://www.reddit.com/r/LocalLLaMA/comments/17v3rhw/help_with_alpaca_prompt_formatting/ | Adventurous_Cat_1559 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 17v3rhw | false | null | t3_17v3rhw | /r/LocalLLaMA/comments/17v3rhw/help_with_alpaca_prompt_formatting/ | false | false | self | 3 | null |
SPHINX: a new multi-modal LLM from the creators of LLaMA-Adapter | 55 | I found out about this model browsing LLaMA-Adapter repo, it was released a few days ago.
[Model page](https://huggingface.co/Alpha-VLLM/SPHINX)
[Weights (40GB)](https://huggingface.co/Alpha-VLLM/LLaMA2-Accessory/tree/main/finetune/mm/SPHINX)
[Paper](https://github.com/Alpha-VLLM/LLaMA2-Accessory/blob/main/SPHIN... | 2023-11-14T14:35:11 | https://www.reddit.com/r/LocalLLaMA/comments/17v3j52/sphinx_a_new_multimodal_llm_from_the_creators_of/ | remixer_dec | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 17v3j52 | false | null | t3_17v3j52 | /r/LocalLLaMA/comments/17v3j52/sphinx_a_new_multimodal_llm_from_the_creators_of/ | false | false | 55 | {'enabled': False, 'images': [{'id': 'ReAc29HdboIiFN92DonHNHv__71q8E3c-qXuUtP6iGo', 'resolutions': [{'height': 58, 'url': 'https://external-preview.redd.it/iXvsHEilna8zisdl2e_YlyXteHaMi2bZpneFVRLOyxs.jpg?width=108&crop=smart&auto=webp&s=b4942e5c4de4950d837a48bacc0a40305b70173a', 'width': 108}, {'height': 116, 'url': 'h... | |
Streaming LLM response in Azure ML support | 1 | [removed] | 2023-11-14T13:31:16 | https://www.reddit.com/r/LocalLLaMA/comments/17v29fo/streaming_llm_response_in_azure_ml_support/ | ianuvrat | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 17v29fo | false | null | t3_17v29fo | /r/LocalLLaMA/comments/17v29fo/streaming_llm_response_in_azure_ml_support/ | false | false | self | 1 | null |
What LLM would you suggest for a rtx 3060? | 2 | I know how to install and set it up; I tried a couple 70b parameter model... Did not go well. Which would you say is as of now the best uncensored model for my computer right now as of today? I know it changes, but you get what I mean. | 2023-11-14T12:55:55 | https://www.reddit.com/r/LocalLLaMA/comments/17v1mqd/what_llm_would_you_suggest_for_a_rtx_3060/ | Electrical_Apricot69 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 17v1mqd | false | null | t3_17v1mqd | /r/LocalLLaMA/comments/17v1mqd/what_llm_would_you_suggest_for_a_rtx_3060/ | false | false | default | 2 | null |
codellama gives really bad results, am I doing something wrong? | 8 | Is this modal just not good enough? I would think it would know the difference between python and js at the very least?
https://preview.redd.it/xf06g5dn8b0c1.png?width=1754&format=png&auto=webp&s=fd4d297400f379bd7d679d963359f550242a8de4 | 2023-11-14T12:52:27 | https://www.reddit.com/r/LocalLLaMA/comments/17v1kkt/codellama_gives_really_bad_results_am_i_doing/ | Detz | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 17v1kkt | false | null | t3_17v1kkt | /r/LocalLLaMA/comments/17v1kkt/codellama_gives_really_bad_results_am_i_doing/ | false | false | 8 | null | |
I asked GPT-4-Turbo of a proposal of replacing the Self-Attention Mechanism | 15 | Hello there,
I am not that knowledgeable in the building Process of LLM Neural Networks but I heard that one of the biggest problems of the transformers is that the Self-Attention is scaling quadratically with every consecutive token and that takes a lot of computational resources, I heard that some people tried cutti... | 2023-11-14T11:26:24 | https://www.reddit.com/r/LocalLLaMA/comments/17v08jb/i_asked_gpt4turbo_of_a_proposal_of_replacing_the/ | _lMark | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 17v08jb | false | null | t3_17v08jb | /r/LocalLLaMA/comments/17v08jb/i_asked_gpt4turbo_of_a_proposal_of_replacing_the/ | false | false | self | 15 | null |
Looking for a Less Formal Generative Model | 1 | As the title suggests, I am seeking a model, preferably around 7 billion parameters, to generate more human-like text, specifically at the level of a student. I am working on a project where I aim to produce flawless generations that challenge discriminator models in distinguishing between human-written and generat... | 2023-11-14T11:12:21 | https://www.reddit.com/r/LocalLLaMA/comments/17v017o/looking_for_a_less_formal_generative_model/ | missing-in-idleness | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 17v017o | false | null | t3_17v017o | /r/LocalLLaMA/comments/17v017o/looking_for_a_less_formal_generative_model/ | false | false | self | 1 | null |
Subsets and Splits
No community queries yet
The top public SQL queries from the community will appear here once available.