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 ⌀ |
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
Evaluating mistral-medium | 31 | I've seen very little evaluations of mistral-medium, their new model that's only available via API and that's supposedly somewhere between GPT 3 and GPT 4.
I've gotten access to it via my office, and I'll be evaluating its performance for various apps we've been working on using OpenAI's APIs so far.
Alongside that, ... | 2023-12-17T14:20:27 | https://www.reddit.com/r/LocalLLaMA/comments/18kib8y/evaluating_mistralmedium/ | Kinniken | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 18kib8y | false | null | t3_18kib8y | /r/LocalLLaMA/comments/18kib8y/evaluating_mistralmedium/ | false | false | self | 31 | null |
failed to quantize: ios_base::clear: unspecified iostream_category error - Where to go for help? | 1 | I'm trying to run llama following the instructions on [their repo](https://github.com/ggerganov/llama.cpp) on a Mac M2 Max 64GB:
Here are the instructions of their repo that I'm following, and I get stuck at step #4 (I added the numbers for better legibility). I have also not done any of the optional steps.
Prepare D... | 2023-12-17T13:42:04 | https://www.reddit.com/r/LocalLLaMA/comments/18khle8/failed_to_quantize_ios_baseclear_unspecified/ | Lanski13 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 18khle8 | false | null | t3_18khle8 | /r/LocalLLaMA/comments/18khle8/failed_to_quantize_ios_baseclear_unspecified/ | false | false | self | 1 | {'enabled': False, 'images': [{'id': 'DJPqvteONpGwVVw6LzaG6b8vlDa2rv2hETCaqe0z57s', 'resolutions': [{'height': 54, 'url': 'https://external-preview.redd.it/wyCM1fHzTa-IIqHgS1QTxdSYNXn668elDj0WmYMPf_k.jpg?width=108&crop=smart&auto=webp&s=d6fa197328d583bcae7a764b40fd1214265b6852', 'width': 108}, {'height': 108, 'url': 'h... |
Best function call return format | 9 | Lately I've been testing diferent ways to provide the LLM with its own function call output and it's interesting to see how the model responds to the diferent formats.
For example if you provide it inside the function call json with the key response seems to be the best way to make the LLM understand we're that inform... | 2023-12-17T13:15:05 | https://www.reddit.com/r/LocalLLaMA/comments/18kh45r/best_function_call_return_format/ | igna778 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 18kh45r | false | null | t3_18kh45r | /r/LocalLLaMA/comments/18kh45r/best_function_call_return_format/ | false | false | self | 9 | null |
LLM playground | 5 |
Can you tell of me good web interface LLM playground websites? The likes of chatbot arena for example. The more the better as they say. | 2023-12-17T13:12:07 | https://www.reddit.com/r/LocalLLaMA/comments/18kh2ck/llm_playground/ | OldSet0 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 18kh2ck | false | null | t3_18kh2ck | /r/LocalLLaMA/comments/18kh2ck/llm_playground/ | false | false | self | 5 | null |
FineTuning LongT5 for QA | 3 | Code for FineTuning and then it's inference of LongT5 for QA | 2023-12-17T13:06:23 | https://www.reddit.com/r/LocalLLaMA/comments/18kgysq/finetuning_longt5_for_qa/ | yashBhaskar | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 18kgysq | false | null | t3_18kgysq | /r/LocalLLaMA/comments/18kgysq/finetuning_longt5_for_qa/ | false | false | self | 3 | null |
Worth it to buy a modded 22GB 2080ti for LLMs? | 17 | I can get my hands on a 2080Ti with 22GB of VRAM instead of the original 11GB, for around $500/£400. Would you say this is worth it / the markup is fair given that unmodded variants can be had for slightly over half the price?
Right now I'm using A4000s which have been okay, but the 16GB limit is sometimes difficult t... | 2023-12-17T12:54:31 | https://www.reddit.com/r/LocalLLaMA/comments/18kgr9m/worth_it_to_buy_a_modded_22gb_2080ti_for_llms/ | define_undefine | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 18kgr9m | false | null | t3_18kgr9m | /r/LocalLLaMA/comments/18kgr9m/worth_it_to_buy_a_modded_22gb_2080ti_for_llms/ | false | false | self | 17 | null |
👋 How we created Trinity: Our experimental LLM that's #1 and #2 on the Hugging Face Leaderboard | 16 | [removed] | 2023-12-17T12:47:55 | https://www.reddit.com/r/LocalLLaMA/comments/18kgnfl/how_we_created_trinity_our_experimental_llm_thats/ | jan-ai | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 18kgnfl | false | null | t3_18kgnfl | /r/LocalLLaMA/comments/18kgnfl/how_we_created_trinity_our_experimental_llm_thats/ | false | false | self | 16 | {'enabled': False, 'images': [{'id': 'EN0-abblERL52DxeoNzcxdkhvXEwLdZMJTS58Umjs64', 'resolutions': [{'height': 58, 'url': 'https://external-preview.redd.it/tSZUq9622TYSgtzH4foFlGwz9n9ixCJUAgev8O2x8jI.jpg?width=108&crop=smart&auto=webp&s=90f4efd1c1314faf5b0cd1c5eeb8d2835fe4a3ba', 'width': 108}, {'height': 116, 'url': 'h... |
failed to quantize: ios_base::clear: unspecified iostream_category error - Where to go for help? | 1 | [removed] | 2023-12-17T12:40:52 | https://www.reddit.com/r/LocalLLaMA/comments/18kgjas/failed_to_quantize_ios_baseclear_unspecified/ | Electrical_Town_2273 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 18kgjas | false | null | t3_18kgjas | /r/LocalLLaMA/comments/18kgjas/failed_to_quantize_ios_baseclear_unspecified/ | false | false | self | 1 | {'enabled': False, 'images': [{'id': 'DJPqvteONpGwVVw6LzaG6b8vlDa2rv2hETCaqe0z57s', 'resolutions': [{'height': 54, 'url': 'https://external-preview.redd.it/wyCM1fHzTa-IIqHgS1QTxdSYNXn668elDj0WmYMPf_k.jpg?width=108&crop=smart&auto=webp&s=d6fa197328d583bcae7a764b40fd1214265b6852', 'width': 108}, {'height': 108, 'url': 'h... |
How do I update llama.cpp for android in termux | 1 | [removed] | 2023-12-17T12:10:38 | https://www.reddit.com/r/LocalLLaMA/comments/18kg212/how_do_i_update_llamacpp_for_android_in_termux/ | Alert-Estimate | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 18kg212 | false | null | t3_18kg212 | /r/LocalLLaMA/comments/18kg212/how_do_i_update_llamacpp_for_android_in_termux/ | false | false | self | 1 | null |
Hardware problem | 3 | Should I get:
1) 4060 Ti 16GB x 4 + Threadripper 5955wx on TRX40 motherboard
or
2) 3090 24GB x2 + i9 14700k on z790 motherboard
They have the same price in my country. The good thing about the first setup is 64gb vram, but less bandwidth.
My purpose is to finetune llama 2 70B locally. | 2023-12-17T12:00:44 | https://www.reddit.com/r/LocalLLaMA/comments/18kfw95/hardware_problem/ | 2047Escaper | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 18kfw95 | false | null | t3_18kfw95 | /r/LocalLLaMA/comments/18kfw95/hardware_problem/ | false | false | self | 3 | null |
SOLAR: an 11B model that beats every open model, including Mixtral, Yi-34B, Llama 2 70B, and Falcon 180B！ | 116 | [https://huggingface.co/upstage/SOLAR-10.7B-Instruct-v1.0](https://huggingface.co/upstage/SOLAR-10.7B-Instruct-v1.0) | 2023-12-17T11:22:18 | https://www.reddit.com/r/LocalLLaMA/comments/18kfbh7/solar_an_11b_model_that_beats_every_open_model/ | Own_Relationship8953 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 18kfbh7 | false | null | t3_18kfbh7 | /r/LocalLLaMA/comments/18kfbh7/solar_an_11b_model_that_beats_every_open_model/ | false | false | self | 116 | {'enabled': False, 'images': [{'id': 'eYgOzVBAuNvqoa0iO_7oesPDF4IMahqO_VDioDBGPX4', 'resolutions': [{'height': 58, 'url': 'https://external-preview.redd.it/Cq_Rk78EGQabardJnIURHUQ_utTWcUKJTxaGWN2Oazc.jpg?width=108&crop=smart&auto=webp&s=e67807fe20978ba6a4ca59164cb6a22881c5891d', 'width': 108}, {'height': 116, 'url': 'h... |
Why is there so much focus on Role Play? | 171 | Hi!
I ask this with the utmost respect. I just wonder why is there so much focus on Role play in the world of LocalLLM’s.
Whenever a new model comes out, it seems that one of the first things to be tested is the RP capabilities.
There seem to be TONS of tools developed around role playing, like silly tavern and char... | 2023-12-17T11:12:39 | https://www.reddit.com/r/LocalLLaMA/comments/18kf6es/why_is_there_so_much_focus_on_role_play/ | bullerwins | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 18kf6es | false | null | t3_18kf6es | /r/LocalLLaMA/comments/18kf6es/why_is_there_so_much_focus_on_role_play/ | false | false | self | 171 | null |
Translation Model Leaderboard | 15 | Hey guys, for one of my projects I have recently added in a translation layer before prompting my LLM for inference. It was then when I realized we didn't really have a leaderboard for translation models, a compilation of the best ones or even a real list of all the serious competitors. This is what I wanted to start h... | 2023-12-17T11:11:13 | https://www.reddit.com/r/LocalLLaMA/comments/18kf5pb/translation_model_leaderboard/ | Galaktische_Gurke | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 18kf5pb | false | null | t3_18kf5pb | /r/LocalLLaMA/comments/18kf5pb/translation_model_leaderboard/ | false | false | self | 15 | null |
How can RAG from LlamaIndex be integrated with a local llama-cpp-python API server? | 4 | I would like to use [LlamaIndex](https://www.llamaindex.ai/) to index documents and media into a vector store, and then be able to use a [chat UI](https://github.com/mckaywrigley/chatbot-ui) to query that information, entirely locally. Ideally this would be using [Llama.cpp's OpenAI API web service](https://github.com/... | 2023-12-17T08:47:05 | https://www.reddit.com/r/LocalLLaMA/comments/18kd2n8/how_can_rag_from_llamaindex_be_integrated_with_a/ | PrinceOfLeon | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 18kd2n8 | false | null | t3_18kd2n8 | /r/LocalLLaMA/comments/18kd2n8/how_can_rag_from_llamaindex_be_integrated_with_a/ | false | false | self | 4 | null |
Best Uncensored Model to run on 16GB of VRAM? | 45 | Been out of the local scene for a few months but I have a gpu with 16gb of vram whats the best ungimped model i could run at the moment? Just general stuff nothing specific. | 2023-12-17T08:22:16 | https://www.reddit.com/r/LocalLLaMA/comments/18kcqcb/best_uncensored_model_to_run_on_16gb_of_vram/ | AMDBlackScreen | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 18kcqcb | false | null | t3_18kcqcb | /r/LocalLLaMA/comments/18kcqcb/best_uncensored_model_to_run_on_16gb_of_vram/ | false | false | self | 45 | null |
LLM playground | 1 | [removed] | 2023-12-17T05:28:48 | https://www.reddit.com/r/LocalLLaMA/comments/18ka4ir/llm_playground/ | OldSet0 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 18ka4ir | false | null | t3_18ka4ir | /r/LocalLLaMA/comments/18ka4ir/llm_playground/ | false | false | self | 1 | null |
Has anyone played around with Phi-2 | 1 | They uploaded to huggingface:
[https://huggingface.co/microsoft/phi-2](https://huggingface.co/microsoft/phi-2)
Has it been evaled on the benchmarks? | 2023-12-17T05:22:53 | https://www.reddit.com/r/LocalLLaMA/comments/18ka10m/has_anyone_played_around_with_phi2/ | Honest-Debate-6863 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 18ka10m | false | null | t3_18ka10m | /r/LocalLLaMA/comments/18ka10m/has_anyone_played_around_with_phi2/ | false | false | self | 1 | {'enabled': False, 'images': [{'id': 'IC9jEjr4wqjQ7Zp6pkl3zp0k6W16A-udtoplxE4MnyY', 'resolutions': [{'height': 58, 'url': 'https://external-preview.redd.it/Bou0VApCNu-gpJZ801OxRYO9_HcS0Q7xXm8ez7FBuBI.jpg?width=108&crop=smart&auto=webp&s=0e88db6a0c39318ffd52cbcc7a8c5ebd7f2446f4', 'width': 108}, {'height': 116, 'url': 'h... |
Best local model to answer questions given some context? | 7 | Hello, I'm trying to build a local question and answering system. I stored all of my documents as a faiss index and I'm retrieving top 10 relevant embeddings for a user's question. So far this is working great. Now I'm looking for a model that can run on my 30GB RAM computer that can take those 10 embeddings and get m... | 2023-12-17T05:00:48 | https://www.reddit.com/r/LocalLLaMA/comments/18k9nth/best_local_model_to_answer_questions_given_some/ | impl66 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 18k9nth | false | null | t3_18k9nth | /r/LocalLLaMA/comments/18k9nth/best_local_model_to_answer_questions_given_some/ | false | false | self | 7 | null |
Tried to make a deez nuts joke but the model is too dumb for me to make fun of it | 2 | 2023-12-17T04:52:14 | mesayousa | i.redd.it | 1970-01-01T00:00:00 | 0 | {} | 18k9ipf | false | null | t3_18k9ipf | /r/LocalLLaMA/comments/18k9ipf/tried_to_make_a_deez_nuts_joke_but_the_model_is/ | false | false | 2 | {'enabled': True, 'images': [{'id': 'Kj-eGRuySBquQ6_gYZpzknoUdrN5l322RAiDNhF-ZHw', 'resolutions': [{'height': 216, 'url': 'https://preview.redd.it/uhc8l6d5ds6c1.jpeg?width=108&crop=smart&auto=webp&s=0117581769a4fa06862691a5fad58b92be798e8c', 'width': 108}, {'height': 432, 'url': 'https://preview.redd.it/uhc8l6d5ds6c1.j... | |||
i need a swift ui to interface with a websocket server. how do i bundle both | 1 | so id like to have my swiftui get updates from a websocket server.
but i want this websocket to be added the app bundle.
so do i just make the websocket server in swift and compile it as a binary and include and manage it from the swift code? | 2023-12-17T04:43:42 | https://www.reddit.com/r/LocalLLaMA/comments/18k9dmc/i_need_a_swift_ui_to_interface_with_a_websocket/ | herozorro | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 18k9dmc | false | null | t3_18k9dmc | /r/LocalLLaMA/comments/18k9dmc/i_need_a_swift_ui_to_interface_with_a_websocket/ | false | false | self | 1 | null |
Mixtral on an i7-7820HQ, 32GB RAM laptop is pretty decent for chatting | 20 | I installed KobaldAI and dolphin-2.5-mixtral-8x7b-gguf on an old laptop today (i7-7820HQ, 32GB RAM). The speed is like watching someone type. I normally use LLMs for brainstorming so that speed really isn’t bad at all. It’s pretty amazing to be able to run it locally on a $250 laptop! | 2023-12-17T04:37:39 | https://www.reddit.com/r/LocalLLaMA/comments/18k99x5/mixtral_on_an_i77820hq_32gb_ram_laptop_is_pretty/ | DKW0000001 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 18k99x5 | false | null | t3_18k99x5 | /r/LocalLLaMA/comments/18k99x5/mixtral_on_an_i77820hq_32gb_ram_laptop_is_pretty/ | false | false | self | 20 | null |
Can someone tell me how to use this model | 1 | [removed] | 2023-12-17T04:19:01 | https://www.reddit.com/r/LocalLLaMA/comments/18k8yga/can_someone_tell_me_how_to_use_this_model/ | throwfalseaway12 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 18k8yga | false | null | t3_18k8yga | /r/LocalLLaMA/comments/18k8yga/can_someone_tell_me_how_to_use_this_model/ | false | false | self | 1 | {'enabled': False, 'images': [{'id': 'yyc20imk2jDaMyTtiGEeH9sc5jRHFDPY1F7immamzdw', 'resolutions': [{'height': 58, 'url': 'https://external-preview.redd.it/HPTjHyuYnAZvB2MVSx1dk3P3SOuTl2C6u9czKq0fTEA.jpg?width=108&crop=smart&auto=webp&s=507c2a04086207ffd43c00f538ecb03cb0d7972d', 'width': 108}, {'height': 116, 'url': 'h... |
3080 16gb laptop + desktop gpus? | 1 | Hi, I found a good deal for laptop priced in a similar to a used 3090. I like the convenience and capability of such a device, and the fact that image training and cuda tts, and any ml github project would work hassle-free.
The bandwidth is 448.0 GB/s, which is higher than 3060 or 4060ti.
I was wondering about if I ... | 2023-12-17T04:08:30 | https://www.reddit.com/r/LocalLLaMA/comments/18k8s2n/3080_16gb_laptop_desktop_gpus/ | Aaaaaaaaaeeeee | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 18k8s2n | false | null | t3_18k8s2n | /r/LocalLLaMA/comments/18k8s2n/3080_16gb_laptop_desktop_gpus/ | false | false | self | 1 | null |
Any recommendations for using a 980ti? | 2 | Or is it just too old? Stable Diffusion works ok, but not amazing. I tried to get a 7b model to load, but it crashed my machine after a few attempts. I thought the 6gb of VRAM would at least count for something.
Anyone have experience running an LLM on this card? | 2023-12-17T04:00:15 | https://www.reddit.com/r/LocalLLaMA/comments/18k8mxr/any_recommendations_for_using_a_980ti/ | BriansRevenge | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 18k8mxr | false | null | t3_18k8mxr | /r/LocalLLaMA/comments/18k8mxr/any_recommendations_for_using_a_980ti/ | false | false | self | 2 | null |
LLM_Web_search for text-generation-webui: it's pretty awesome! | 43 | The following conversation was had using "Mistral 7B" with the **LLM\_Web\_Search** extension installed. I really like that it determines when it wants to search itself and what terms it will use!
​
>**Searcher**
>
>How can I help you today, using the internet as my guide!
>
>**You**
>
>What was th... | 2023-12-17T03:46:46 | https://www.reddit.com/r/LocalLLaMA/comments/18k8f2x/llm_web_search_for_textgenerationwebui_its_pretty/ | phr00t_ | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 18k8f2x | false | null | t3_18k8f2x | /r/LocalLLaMA/comments/18k8f2x/llm_web_search_for_textgenerationwebui_its_pretty/ | false | false | self | 43 | {'enabled': False, 'images': [{'id': 'TKom3ss809OGr1QYVHNHYAz7hr2eZAv_BugQ_JelnUg', 'resolutions': [{'height': 54, 'url': 'https://external-preview.redd.it/qe0hH-vpFe7obaLCVPBhwa2g5_vkdydxAwP5RV1TXU8.jpg?width=108&crop=smart&auto=webp&s=8fe2c4fbd31b66b407d66a269f7ae25841a3d0db', 'width': 108}, {'height': 108, 'url': 'h... |
How does speechless-llama2-hermes-orca-platypus-wizardlm-13b compare to mixtral subjectively, to anyone whose played around with both? | 1 | One might expect mixtral to have a superior knowledge domain base, but I think the other one in any domain of mixtral's base for example, would have qualities to it that subjectively have value that might be missed by mindless benchmarks.
So I'm asking the people, what is their/your subjective intuition about how eac... | 2023-12-17T03:34:35 | https://www.reddit.com/r/LocalLLaMA/comments/18k87wl/how_does/ | _______DEADPOOL____ | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 18k87wl | false | null | t3_18k87wl | /r/LocalLLaMA/comments/18k87wl/how_does/ | false | false | self | 1 | null |
GPU Recommendations | 4 | Where it starts - I have an old mining rig:
1 - 3080-TI 12GB
5 - 3060-TI 8GB
1 - 3060 12GB
But they are hooked up into a mining board that only supports PCIE-1. I'm interested in training some LLMS and in general building a machine for AI, what are your suggestions?
1. get a new board and build a new system - (che... | 2023-12-17T02:16:55 | https://www.reddit.com/r/LocalLLaMA/comments/18k6urt/gpu_recommendations/ | Second26 | self.LocalLLaMA | 2023-12-17T02:22:24 | 0 | {} | 18k6urt | false | null | t3_18k6urt | /r/LocalLLaMA/comments/18k6urt/gpu_recommendations/ | false | false | self | 4 | null |
How long before we have a consumer 32GB LLM accelerator? | 28 | Shame on AMD and Intel for not having a 32GB competitor to Nvidia. How long before they wake up and smell the coffee? Could we get one that is upgradable to 64 GB of memory? Can we get some low cost, not top speed cards with lots of memory? Is it really that hard? Have zero interest in graphics performance. Can i... | 2023-12-17T02:07:46 | https://www.reddit.com/r/LocalLLaMA/comments/18k6oy4/how_long_before_we_have_a_consumer_32gb_llm/ | danielcar | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 18k6oy4 | false | null | t3_18k6oy4 | /r/LocalLLaMA/comments/18k6oy4/how_long_before_we_have_a_consumer_32gb_llm/ | false | false | self | 28 | {'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... |
Which 'GPT-ism' in local models annoys you the most? | 104 | So there's always a ton of people complaining about how they see "As an AI language model" or something like that. However, since I don't really use AI for coding/science/homework, I've never seen this. Instead, since I'm a writer, my least favorite GPT-ism is when it tries to wrap up an entire story in a single genera... | 2023-12-17T02:05:27 | https://www.reddit.com/r/LocalLLaMA/comments/18k6nft/which_gptism_in_local_models_annoys_you_the_most/ | adumdumonreddit | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 18k6nft | false | null | t3_18k6nft | /r/LocalLLaMA/comments/18k6nft/which_gptism_in_local_models_annoys_you_the_most/ | false | false | self | 104 | null |
How to use LM Studio as a writing assistant and/or Proofreader? | 1 | How to use LM Studio as a writing assistant and/or Proofreader? | 2023-12-17T01:51:53 | https://www.reddit.com/r/LocalLLaMA/comments/18k6eaj/how_to_use_lm_studio_as_a_writing_assistant_andor/ | poet3991 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 18k6eaj | false | null | t3_18k6eaj | /r/LocalLLaMA/comments/18k6eaj/how_to_use_lm_studio_as_a_writing_assistant_andor/ | false | false | self | 1 | null |
Essential AI Tools and Libraries: A Guide to Python, Git, C++ Compile Tools, FFmpeg, CUDA, PyTorch - Amazing Resource For AI Beginners | 1 | [removed] | 2023-12-17T01:50:23 | https://www.reddit.com/r/LocalLLaMA/comments/18k6da2/essential_ai_tools_and_libraries_a_guide_to/ | CeFurkan | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 18k6da2 | false | null | t3_18k6da2 | /r/LocalLLaMA/comments/18k6da2/essential_ai_tools_and_libraries_a_guide_to/ | false | false | self | 1 | {'enabled': False, 'images': [{'id': 'dFWyXDVLReIS75Z351RIKJiqtUjmZLljhk2QyHNvgXw', 'resolutions': [{'height': 81, 'url': 'https://external-preview.redd.it/9ns5vfSrrgMV2pJYoPByHIXYjddvrU4bkmD_HgBhyE8.jpg?width=108&crop=smart&auto=webp&s=c086b62dc56d9c20b03527adfa19989bf593d39a', 'width': 108}, {'height': 162, 'url': 'h... |
Anyone else having trouble running GPTQ Mixtral models in text generation webui? | 3 | When selecting a GPT Mixtral model I'm getting these errors and they won't load. Anyone else having these problems?
C:\\text-generation-webui-main\\installer\_files\\env\\Lib\\site-packages\\gradio\\components\\dropdown.py:231: UserWarning: The value passed into gr.Dropdown() is not in the list of choices. Please upda... | 2023-12-17T01:11:28 | https://www.reddit.com/r/LocalLLaMA/comments/18k5mls/anyone_else_having_trouble_running_gptq_mixtral/ | SantaBooks | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 18k5mls | false | null | t3_18k5mls | /r/LocalLLaMA/comments/18k5mls/anyone_else_having_trouble_running_gptq_mixtral/ | false | false | self | 3 | null |
ExllamaV2 0.0.11 is released, bringing support for Mixtral models | 144 | 2023-12-17T01:05:07 | https://github.com/turboderp/exllamav2/releases/tag/v0.0.11 | AmazinglyObliviouse | github.com | 1970-01-01T00:00:00 | 0 | {} | 18k5i9s | false | null | t3_18k5i9s | /r/LocalLLaMA/comments/18k5i9s/exllamav2_0011_is_released_bringing_support_for/ | false | false | 144 | {'enabled': False, 'images': [{'id': 'zIbt4061SwYOC5uAlx2WNJ6wz99mO2Xu8iiLNcjBvNA', 'resolutions': [{'height': 54, 'url': 'https://external-preview.redd.it/Gcbsg_0BgFcEbf5t-8BGwl9lMAgSZ44JMEW5MnieKGM.jpg?width=108&crop=smart&auto=webp&s=2e0f4366491d6a8c9a591fd9e20d63111563829b', 'width': 108}, {'height': 108, 'url': 'h... | ||
Trinity 7B - a powerful 7B model for LocalAI | 16 | This model uses the SLERP method to merge the best models on 14th Dec on OpenLLM Leaderboard: LeoScorpius-7B-Chat-DPO with our latest GreenNodeLM-7B-v1olet model. It is taking the leaderboard.
Model: [Trinity-v1](https://huggingface.co/jan-hq/trinity-v1)
GGUF: [Trinity-v1-GGUF](https://huggingface.co/jan-hq/trinity-... | 2023-12-17T01:04:43 | https://www.reddit.com/r/LocalLLaMA/comments/18k5i0g/trinity_7b_a_powerful_7b_model_for_localai/ | Own_Procedure_8866 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 18k5i0g | false | null | t3_18k5i0g | /r/LocalLLaMA/comments/18k5i0g/trinity_7b_a_powerful_7b_model_for_localai/ | false | false | 16 | {'enabled': False, 'images': [{'id': 'NIYbDogY4FTN5y15JnJpSqHOV-XhzU0cTnjgKRIRZ5A', 'resolutions': [{'height': 58, 'url': 'https://external-preview.redd.it/vT6ZOubLqa_CxwWLBLlSCArZYfzF-w3b9wu5xg73WsI.jpg?width=108&crop=smart&auto=webp&s=eeb3cc6be0ed447daf2979456f3e9fcbf0bf65df', 'width': 108}, {'height': 116, 'url': 'h... | |
Most accurate model for server CPU setup? | 8 | I have a couple of older servers that I was hoping to play around with a local LLM on. I don't really care how long it takes to process and get responses, but I'd like to shoot for the best (most accurate) ones.
The server I'm thinking of using has the following specs:
- 2x2.1 Ghz * 26 cores (104 threads total)
- 1.5... | 2023-12-16T23:54:36 | https://www.reddit.com/r/LocalLLaMA/comments/18k444r/most_accurate_model_for_server_cpu_setup/ | at_physicaltherapy | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 18k444r | false | null | t3_18k444r | /r/LocalLLaMA/comments/18k444r/most_accurate_model_for_server_cpu_setup/ | false | false | self | 8 | null |
Snapdragon x1 elite maybe a "cheap" apple competitor ? | 28 | Out of interest do any of you think or hope that the new qualcomm chips might be a relatively cheap way to get in to ai for quantized 34 and potentially 70b models with 64 gb of ram and an at least decent npu ? Which supposedly can run 13b models (which i take Was meant as in un quantized) on the maschine.
I am sligh... | 2023-12-16T23:24:08 | https://www.google.com/amp/s/www.forbes.com/sites/karlfreund/2023/12/12/qualcomm-makes-its-push-for-pc-relevance-leading-with-ai/amp/ | Noxusequal | google.com | 1970-01-01T00:00:00 | 0 | {} | 18k3hm7 | false | null | t3_18k3hm7 | /r/LocalLLaMA/comments/18k3hm7/snapdragon_x1_elite_maybe_a_cheap_apple_competitor/ | false | false | 28 | {'enabled': False, 'images': [{'id': '-vMIdiFogwof_O3yHf3iS-MMtZ5tj7XHYVLDS7Q9Zts', 'resolutions': [{'height': 30, 'url': 'https://external-preview.redd.it/tpC6KW38VTGRwY98NsjRQbLRH5lBZsk-Emlnp8Eb8fM.jpg?width=108&crop=smart&auto=webp&s=9ec63ac2341834844fde9a6b2d351625be7083ba', 'width': 108}, {'height': 61, 'url': 'ht... | |
Advise on GOAL: open source projects like Azure Cognitive Search + GPT | 1 | [removed] | 2023-12-16T23:17:20 | https://www.reddit.com/r/LocalLLaMA/comments/18k3cne/advise_on_goal_open_source_projects_like_azure/ | Pretend-Word2531 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 18k3cne | false | null | t3_18k3cne | /r/LocalLLaMA/comments/18k3cne/advise_on_goal_open_source_projects_like_azure/ | false | false | self | 1 | {'enabled': False, 'images': [{'id': 'KFfJdQptaGXLhvtBUcLyLc7pCd7o2gCky5puXOS9giQ', 'resolutions': [{'height': 60, 'url': 'https://external-preview.redd.it/d97ATK0u2Re68XPT0vJD75brLE8HsO_Q8i3rfaPN6pc.jpg?width=108&crop=smart&auto=webp&s=d92d8408d9881fc0c1bbdd11ba6132d9eb00fc80', 'width': 108}, {'height': 121, 'url': 'h... |
PiVoT-MoE, 10.7B*4 RP Model | 49 | > PiVoT-MoE, is an advanced AI model specifically designed for roleplaying purposes. It has been trained using a combination of four 10.7B sized experts, each with their own specialized characteristic, all fine-tuned to bring a unique and diverse roleplaying experience.
>
>The Mixer of Experts (MoE) technique is ut... | 2023-12-16T22:37:31 | https://www.reddit.com/r/LocalLLaMA/comments/18k2jan/pivotmoe_107b4_rp_model/ | Warm_Paramedic2528 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 18k2jan | false | null | t3_18k2jan | /r/LocalLLaMA/comments/18k2jan/pivotmoe_107b4_rp_model/ | false | false | self | 49 | null |
x4 or x8 120B MoE possibly? | 12 | I would love to see someone attempt this with some of the 120B models floating around hugging face. Maybe really give gpt4 a run for its money. Given you'd need to rent quite the machine on runpod or equivalent to run it even quantized. | 2023-12-16T22:28:39 | https://www.reddit.com/r/LocalLLaMA/comments/18k2cpv/x4_or_x8_120b_moe_possibly/ | Dazzling_Ad1507 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 18k2cpv | false | null | t3_18k2cpv | /r/LocalLLaMA/comments/18k2cpv/x4_or_x8_120b_moe_possibly/ | false | false | self | 12 | null |
Most advanced LLM for a Jetson Orin Nano? | 4 | I’m looking to create a working offline chatbot (with voice input/output) and figure the Jetson Orin Nano is my best bet.
Anyone worked on a similar project before? I have some pretty cool and funny ideas I want to try building, but am wondering if any LLMs can fit on the 4 or 8gb versions of the Jetson Orin Nano + ha... | 2023-12-16T21:47:38 | https://www.reddit.com/r/LocalLLaMA/comments/18k1i2h/most_advanced_llm_for_a_jetson_orin_nano/ | fission4433 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 18k1i2h | false | null | t3_18k1i2h | /r/LocalLLaMA/comments/18k1i2h/most_advanced_llm_for_a_jetson_orin_nano/ | false | false | self | 4 | null |
Optimizing inference on Pascal GPUs | 2 | I've been running Q 5\_K\_M Mistral GGUF quants on Ooba with my Quadro P4000 (8 GB) for the past few weeks, but haven't been able to get speeds above 10 t/s. Are there any ways to eke out faster inference speeds on Pascal GPUs with Mistral or any other performant models?
​
Any tips or tricks would be appreciat... | 2023-12-16T21:35:01 | https://www.reddit.com/r/LocalLLaMA/comments/18k18tv/optimizing_inference_on_pascal_gpus/ | Aarush_Sah | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 18k18tv | false | null | t3_18k18tv | /r/LocalLLaMA/comments/18k18tv/optimizing_inference_on_pascal_gpus/ | false | false | self | 2 | null |
Anybody use mistral-7b-instruct v0.2 model? (Doesn't work well for me) | 3 | I'm using the latest v0.2 version and it's pretty bad at times. Typically the very first question I ask any model or fine tune is "How many days are in August?" Here are some terrible answers produced by the model:
* There are 31 days in August, unless it is a leap year and then there can be an additional day.
* There... | 2023-12-16T21:34:39 | https://www.reddit.com/r/LocalLLaMA/comments/18k18la/anybody_use_mistral7binstruct_v02_model_doesnt/ | gamesntech | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 18k18la | false | null | t3_18k18la | /r/LocalLLaMA/comments/18k18la/anybody_use_mistral7binstruct_v02_model_doesnt/ | false | false | self | 3 | null |
Are models getting slower with longer input? | 7 | I can load a 7B model with 8k context on my GPU, but the longer my input gets, the slower it gets. I am talking about getting three paragraphs in 4 seconds for the first response, but later waiting 1 minute for a single paragraph. When using a streaming API, it gets an acceptable token/s speed once it starts writing, b... | 2023-12-16T21:14:47 | https://www.reddit.com/r/LocalLLaMA/comments/18k0trd/are_models_getting_slower_with_longer_input/ | _allo_ | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 18k0trd | false | null | t3_18k0trd | /r/LocalLLaMA/comments/18k0trd/are_models_getting_slower_with_longer_input/ | false | false | self | 7 | null |
PSA: You can (and may want to) disable Mixtral's Sliding Window! | 61 | Was banging my head against the wall why Mixtral-8x7B-Instruct-v0.1 with 32K context wasn't able to summarize a 16K text. My prompt started with the instruction to summarize the following text, but the model simply ignored it all and hallucinated random stuff.
I first thought it was an issue with my prompt or the form... | 2023-12-16T20:55:47 | https://www.reddit.com/r/LocalLLaMA/comments/18k0fek/psa_you_can_and_may_want_to_disable_mixtrals/ | WolframRavenwolf | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 18k0fek | false | null | t3_18k0fek | /r/LocalLLaMA/comments/18k0fek/psa_you_can_and_may_want_to_disable_mixtrals/ | false | false | self | 61 | {'enabled': False, 'images': [{'id': 'xU07sACUhuScPaN8BIMV0USMZkFwSMGcorjhvoKF4K0', 'resolutions': [{'height': 58, 'url': 'https://external-preview.redd.it/FRlvpc5SALNi_rYIzAsFALIzMXE1oc-Gkb2Yh1ZWGMM.jpg?width=108&crop=smart&auto=webp&s=9ad9ea4d991fae47edd6a09b5feb6d60eca474de', 'width': 108}, {'height': 116, 'url': 'h... |
Where To Start? | 2 | I’m looking to self host a system to give it specific information and have it fetch requested information from provided documents only. I have experience in text to image but this is a little foreign. My understanding is that the foundation for what I am looking for has been developed and is available, but I’m unsure w... | 2023-12-16T20:12:46 | https://www.reddit.com/r/LocalLLaMA/comments/18jzjdb/where_to_start/ | InterestingMain5192 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 18jzjdb | false | null | t3_18jzjdb | /r/LocalLLaMA/comments/18jzjdb/where_to_start/ | false | false | self | 2 | null |
Model and fun prompts for nephew? | 9 | He’s 11 and has a 2070 super (8gb vram) and 16 gb ram. I got LM Studio with The Bloke Mistral 7b. He’s having fun having it write ridiculous stories.
What are other models / uses cases for him? Just for fun.
He’s a typical, into Fortnite/gaming kid. | 2023-12-16T20:07:10 | https://www.reddit.com/r/LocalLLaMA/comments/18jzeyp/model_and_fun_prompts_for_nephew/ | kwerky | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 18jzeyp | false | null | t3_18jzeyp | /r/LocalLLaMA/comments/18jzeyp/model_and_fun_prompts_for_nephew/ | false | false | self | 9 | null |
Conversations with friends | 1 | [removed] | 2023-12-16T19:20:26 | https://www.reddit.com/r/LocalLLaMA/comments/18jyg0a/conversations_with_friends/ | Ettaross | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 18jyg0a | false | null | t3_18jyg0a | /r/LocalLLaMA/comments/18jyg0a/conversations_with_friends/ | false | false | self | 1 | null |
The Best GPUs for Deep Learning in 2023 | 89 | 2023-12-16T19:17:55 | https://timdettmers.com/2023/01/30/which-gpu-for-deep-learning/ | semicausal | timdettmers.com | 1970-01-01T00:00:00 | 0 | {} | 18jye6i | false | null | t3_18jye6i | /r/LocalLLaMA/comments/18jye6i/the_best_gpus_for_deep_learning_in_2023/ | false | false | 89 | {'enabled': False, 'images': [{'id': 'hRzrP-m1lWiqRsPC9clNfPnRc_tCRGpGzbHrCBCO32w', 'resolutions': [{'height': 106, 'url': 'https://external-preview.redd.it/VsKEg4u26XX9vTR-l8w5GIancrmHR-u88Vw43XWdAC0.jpg?width=108&crop=smart&auto=webp&s=d3bf136e531bc2c273b80183994e8247105e2fde', 'width': 108}, {'height': 212, 'url': '... | ||
Is it possible to finetune a small LLM (7B) to interpreter a single character, without the need for a character card? | 1 | I'm curious if it would be possible to train an LLM to play and be a single character (both in chat and instruct mode) giving it all the information it needs through finetuning? | 2023-12-16T18:58:16 | https://www.reddit.com/r/LocalLLaMA/comments/18jxytd/is_it_possible_to_finetune_a_small_llm_7b_to/ | Aril_1 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 18jxytd | false | null | t3_18jxytd | /r/LocalLLaMA/comments/18jxytd/is_it_possible_to_finetune_a_small_llm_7b_to/ | false | false | self | 1 | null |
Guide to run Mixtral correctly. I see a lot of people using the wrong settings / setup which makes it go schizo or repetitive. | 152 | 2023-12-16T18:31:18 | https://rentry.org/HowtoMixtral | Different_Fix_2217 | rentry.org | 1970-01-01T00:00:00 | 0 | {} | 18jxehq | false | null | t3_18jxehq | /r/LocalLLaMA/comments/18jxehq/guide_to_run_mixtral_correctly_i_see_a_lot_of/ | false | false | 152 | {'enabled': False, 'images': [{'id': 'C-X4vFW_HFwis_-uHlyBVcfzqYrybqx0OpVjUR6hMGs', 'resolutions': [{'height': 94, 'url': 'https://external-preview.redd.it/l64Dz2MMqFrXWFChndInlSXfCPYQ1FFe4i5cbiy6cX0.jpg?width=108&crop=smart&auto=webp&s=0ef38a857d2d493f52effac01ff95da9e7780070', 'width': 108}, {'height': 189, 'url': 'h... | ||
MoE test from CasualLM, bad performance? | 1 | [deleted] | 2023-12-16T18:25:14 | https://x.com/RealJosephus/status/1735898788949287342?s=20 | ninjasaid13 | x.com | 1970-01-01T00:00:00 | 0 | {} | 18jx9w5 | false | null | t3_18jx9w5 | /r/LocalLLaMA/comments/18jx9w5/moe_test_from_casuallm_bad_performance/ | false | false | 1 | {'enabled': False, 'images': [{'id': '_me4ExZcbrMjmGGnXNrAOImbOxtbwf4ROiQeROS7RDM', 'resolutions': [{'height': 108, 'url': 'https://external-preview.redd.it/Ke1MMuVwm99NKD64TkIimoWHhGJ-MXF8QGYjrGaRA74.jpg?width=108&crop=smart&auto=webp&s=306d4ef3cbf0196743160f9780e68b1c07f91360', 'width': 108}], 'source': {'height': 20... | |
How do LLMs learn to use tools? | 11 | Anyone got any good educational resources they can share, in general or specific to Local LLMs? | 2023-12-16T18:14:05 | https://www.reddit.com/r/LocalLLaMA/comments/18jx1ci/how_do_llms_learn_to_use_tools/ | Nano_9a9o | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 18jx1ci | false | null | t3_18jx1ci | /r/LocalLLaMA/comments/18jx1ci/how_do_llms_learn_to_use_tools/ | false | false | self | 11 | null |
Is a local-LLM assistant a realistic goal at this point? | 52 | AI/LLM is crazy to wrap my head around. So many moving parts and variables to compare, and so much is moving (and search engines are getting so bad) it's hard to tell if reading posts from six months ago have any real relevance on the topic today. For reference to where I sit- I call myself a script kiddie- I can run m... | 2023-12-16T18:14:02 | https://www.reddit.com/r/LocalLLaMA/comments/18jx1bl/is_a_localllm_assistant_a_realistic_goal_at_this/ | moarmagic | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 18jx1bl | false | null | t3_18jx1bl | /r/LocalLLaMA/comments/18jx1bl/is_a_localllm_assistant_a_realistic_goal_at_this/ | false | false | self | 52 | null |
Amica 0.2 released - now has binaries for Windows, Mac, and Linux, and the ability to share and import characters | 29 | Hi,
Since the initial launch announcement a few weeks ago, [Amica](https://heyamica.com/) has received a lot of updates. I am excited to announce 0.2.0 is now ready.
https://github.com/semperai/amica/releases/tag/app-v0.2.0
# Amica 0.2.0
This release of Amica includes desktop builds for Mac, Windows, and Linux. It ... | 2023-12-16T17:40:50 | https://www.reddit.com/r/LocalLLaMA/comments/18jwbkf/amica_02_released_now_has_binaries_for_windows/ | arbiusai | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 18jwbkf | false | null | t3_18jwbkf | /r/LocalLLaMA/comments/18jwbkf/amica_02_released_now_has_binaries_for_windows/ | false | false | self | 29 | {'enabled': False, 'images': [{'id': 'xIwLQvsokSf2xQMHkQy-SiWcc8MlZg-rWn3i-ntjWpM', 'resolutions': [{'height': 48, 'url': 'https://external-preview.redd.it/YvaWFMhc7Eu1Ew_E4dyuxmaNlL4d8H5gQkJJLjntomM.jpg?width=108&crop=smart&auto=webp&s=5566a47bfb94c18f77713ad0441c5441765a50f3', 'width': 108}, {'height': 96, 'url': 'ht... |
Running models on windows with amd hardware? (7900xtx) | 1 | I can't find any resources online on how to do this. Only thing I could think of is torch-directml but have no idea how too make the models use it over the base torch module.
Any help would be hugely appreciated! | 2023-12-16T17:22:58 | https://www.reddit.com/r/LocalLLaMA/comments/18jvxlu/running_models_on_windows_with_amd_hardware/ | Matt_1F44D | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 18jvxlu | false | null | t3_18jvxlu | /r/LocalLLaMA/comments/18jvxlu/running_models_on_windows_with_amd_hardware/ | false | false | default | 1 | null |
Fantasy writing assistant model? | 6 | I've recently discovered LM Studio which allows me to quickly chat with downloaded models, and a plugin for ingesting my own fantasy novel content. I'd done well choosing an LLM and embedding model that work pretty well, but I'm wondering if anyone else has experience with this.
Some models are too dry - asking a que... | 2023-12-16T17:17:31 | https://www.reddit.com/r/LocalLLaMA/comments/18jvtfq/fantasy_writing_assistant_model/ | TheCouncilNovel | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 18jvtfq | false | null | t3_18jvtfq | /r/LocalLLaMA/comments/18jvtfq/fantasy_writing_assistant_model/ | false | false | self | 6 | null |
Newbie, searching among text intelligently | 3 | Here's my request:
​
I have tons of text (I specify that the language is German) in these piles of messages, there are parts that interest me but I can't just search for a keyword, I have to look for a context.
​
For example, I'd say to a software program: "find all the parts that contain a conversa... | 2023-12-16T16:42:36 | https://www.reddit.com/r/LocalLLaMA/comments/18jv2d3/newbie_searching_among_text_intelligently/ | soumdeal | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 18jv2d3 | false | null | t3_18jv2d3 | /r/LocalLLaMA/comments/18jv2d3/newbie_searching_among_text_intelligently/ | false | false | self | 3 | null |
Outfit anyone OSS equivalent | 1 | Is anyone working on, or knows of a model similar to outfit anyone? Working on a project that would have a ton of use for it but right now theirs is just a demo. Any solutions or ideas? | 2023-12-16T16:40:53 | https://www.reddit.com/r/LocalLLaMA/comments/18jv10m/outfit_anyone_oss_equivalent/ | How_i_met_your_bro | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 18jv10m | false | null | t3_18jv10m | /r/LocalLLaMA/comments/18jv10m/outfit_anyone_oss_equivalent/ | false | false | self | 1 | null |
Snarky AIs? | 1 | [removed] | 2023-12-16T16:36:02 | https://www.reddit.com/r/LocalLLaMA/comments/18juxfv/snarky_ais/ | Enspiredjack | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 18juxfv | false | null | t3_18juxfv | /r/LocalLLaMA/comments/18juxfv/snarky_ais/ | false | false | self | 1 | null |
very Slow speeds on 2x4090 in the last few days. | 6 | currently running a 7950x with 2x4090. just a few days ago I was getting great speeds on most LLMs I tried now I'm only getting around 1.25 tokens/s on aetheria-l2-70b.Q3. I've tried to reinstall Ooba and update Kobold, but both are slower than ever. It may be because I updated my Nvidia drivers but I'm not sure what v... | 2023-12-16T16:20:02 | https://www.reddit.com/r/LocalLLaMA/comments/18jul75/very_slow_speeds_on_2x4090_in_the_last_few_days/ | asdfgbvcxz3355 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 18jul75 | false | null | t3_18jul75 | /r/LocalLLaMA/comments/18jul75/very_slow_speeds_on_2x4090_in_the_last_few_days/ | false | false | self | 6 | null |
A new way of MOE | 1 | [removed] | 2023-12-16T16:18:07 | https://www.reddit.com/r/LocalLLaMA/comments/18jujx4/a_new_way_of_moe/ | AI_lover_9669 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 18jujx4 | false | null | t3_18jujx4 | /r/LocalLLaMA/comments/18jujx4/a_new_way_of_moe/ | false | false | self | 1 | {'enabled': False, 'images': [{'id': 'oEbTU1Y2fB-Za8R-jQULSh-lYktf0zRPYPfCqS5H1gQ', 'resolutions': [{'height': 58, 'url': 'https://external-preview.redd.it/4IrLivuY4U7nrHkhHN_rwkaFxAjb-OCY1woXiEOdkvQ.jpg?width=108&crop=smart&auto=webp&s=12175e0b9d13008ecb3b08eb85c9ed49fa2d4848', 'width': 108}, {'height': 116, 'url': 'h... |
Need help to build a RAG application on legal data - vectorDB vs Knowledge graph | 2 | I need suggestion on this space. I need precise answers to certain questions related to a legal data. Vector databases seems to be bad on this, while knowledge graphs are good. But converting legal documents into knowledge graphs is pretty difficult and approximate. How do I decide on this ? Should I use both ? Are th... | 2023-12-16T16:11:51 | https://www.reddit.com/r/LocalLLaMA/comments/18jufbx/need_help_to_build_a_rag_application_on_legal/ | maayon | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 18jufbx | false | null | t3_18jufbx | /r/LocalLLaMA/comments/18jufbx/need_help_to_build_a_rag_application_on_legal/ | false | false | self | 2 | null |
A new way of MOE??? | 1 | [removed] | 2023-12-16T16:09:29 | https://www.reddit.com/r/LocalLLaMA/comments/18judgm/a_new_way_of_moe/ | AI_lover_9669 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 18judgm | false | null | t3_18judgm | /r/LocalLLaMA/comments/18judgm/a_new_way_of_moe/ | false | false | self | 1 | {'enabled': False, 'images': [{'id': 'oEbTU1Y2fB-Za8R-jQULSh-lYktf0zRPYPfCqS5H1gQ', 'resolutions': [{'height': 58, 'url': 'https://external-preview.redd.it/4IrLivuY4U7nrHkhHN_rwkaFxAjb-OCY1woXiEOdkvQ.jpg?width=108&crop=smart&auto=webp&s=12175e0b9d13008ecb3b08eb85c9ed49fa2d4848', 'width': 108}, {'height': 116, 'url': 'h... |
What's the smallest but stil useful model you encountered | 40 | Hi, I'm interested in your opinion in the topic: what's the smallest but still usable for something model you encountered? By useful I mean for any task, from generating tags from text, sentiment analysis, to full fledged text generation, conversations, also translations would be interesting. And by small I mean below ... | 2023-12-16T15:52:41 | https://www.reddit.com/r/LocalLLaMA/comments/18ju0uw/whats_the_smallest_but_stil_useful_model_you/ | Fisent | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 18ju0uw | false | null | t3_18ju0uw | /r/LocalLLaMA/comments/18ju0uw/whats_the_smallest_but_stil_useful_model_you/ | false | false | self | 40 | null |
Mixtral can also handle number series questions | 16 | [mixtral-8x7b-instruct-v0.1.Q6\_K.gguf](https://huggingface.co/TheBloke/Mixtral-8x7B-Instruct-v0.1-GGUF/blob/main/mixtral-8x7b-instruct-v0.1.Q6_K.gguf)
\-----------------------------------------------------
In the series below, look for the degree and direction of change between the numbers. In other words, do the nu... | 2023-12-16T15:44:33 | https://www.reddit.com/r/LocalLLaMA/comments/18jtuz8/mixtral_can_also_handle_number_series_questions/ | Scary-Knowledgable | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 18jtuz8 | false | null | t3_18jtuz8 | /r/LocalLLaMA/comments/18jtuz8/mixtral_can_also_handle_number_series_questions/ | false | false | self | 16 | {'enabled': False, 'images': [{'id': 'zjNIGTMwA8_2859f_IZsUxwU-LAtGdWFd1GsZDfnEwI', 'resolutions': [{'height': 58, 'url': 'https://external-preview.redd.it/vpWBiwKwdU_Dmax7Myc3hNG1g_IFkHXHCQ0zc_Ykfac.jpg?width=108&crop=smart&auto=webp&s=7e4d40db3f52b19bf486502af3ae70ccdb9267c5', 'width': 108}, {'height': 116, 'url': 'h... |
Mixtral is great with analogies and the right prompt | 28 | ​
[mixtral-8x7b-instruct-v0.1.Q6\_K.gguf](https://huggingface.co/TheBloke/Mixtral-8x7B-Instruct-v0.1-GGUF/blob/main/mixtral-8x7b-instruct-v0.1.Q6_K.gguf)
\--------------------------------------------------
You are an expert in analogies.
​
Marathon is to race as hibernation is to
winter
bear
drea... | 2023-12-16T15:04:41 | https://www.reddit.com/r/LocalLLaMA/comments/18jt2ms/mixtral_is_great_with_analogies_and_the_right/ | Scary-Knowledgable | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 18jt2ms | false | null | t3_18jt2ms | /r/LocalLLaMA/comments/18jt2ms/mixtral_is_great_with_analogies_and_the_right/ | false | false | self | 28 | {'enabled': False, 'images': [{'id': 'zjNIGTMwA8_2859f_IZsUxwU-LAtGdWFd1GsZDfnEwI', 'resolutions': [{'height': 58, 'url': 'https://external-preview.redd.it/vpWBiwKwdU_Dmax7Myc3hNG1g_IFkHXHCQ0zc_Ykfac.jpg?width=108&crop=smart&auto=webp&s=7e4d40db3f52b19bf486502af3ae70ccdb9267c5', 'width': 108}, {'height': 116, 'url': 'h... |
[Koboldpcc + Sillytavern] Please help me find the right settings for my setup! | 1 | 2023-12-16T14:49:59 | https://www.reddit.com/gallery/18jsrye | Benjamin_swoleman | reddit.com | 1970-01-01T00:00:00 | 0 | {} | 18jsrye | false | null | t3_18jsrye | /r/LocalLLaMA/comments/18jsrye/koboldpcc_sillytavern_please_help_me_find_the/ | false | false | default | 1 | null | |
Tokens per Second Mistral 8x7B - Performance | 14 | Hey,
does anyone have data about the performance of Mistrals 8x7B on different GPUs?
Thank you! | 2023-12-16T14:41:09 | https://www.reddit.com/r/LocalLLaMA/comments/18jslmf/tokens_per_second_mistral_8x7b_performance/ | Bene0 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 18jslmf | false | null | t3_18jslmf | /r/LocalLLaMA/comments/18jslmf/tokens_per_second_mistral_8x7b_performance/ | false | false | self | 14 | null |
[Question] - Chat UI for Mistral API | 6 | Hi all,
does anyone know a good out of the box chat-ui that can be self-hosted and is interacting with the Mistral API (Mixtral 8x7B)?
I found quite a number of solutions for the chatgpt API, but would need something compatible with the Mistral APIs, as my local hardware power is unfortunately not strong enough to ru... | 2023-12-16T14:35:23 | https://www.reddit.com/r/LocalLLaMA/comments/18jshor/question_chat_ui_for_mistral_api/ | ghac101 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 18jshor | false | null | t3_18jshor | /r/LocalLLaMA/comments/18jshor/question_chat_ui_for_mistral_api/ | false | false | self | 6 | null |
How Sparse MoE(Mixtral) actually works | 1 | I've seen quite a few people ask about how exactly SMoE(for example Mixtral) works. And what an "expert" actually means and how Inference is done. This article gives a really good introduction. | 2023-12-16T14:22:22 | https://towardsdatascience.com/mixtral-8x7b-understanding-and-running-the-sparse-mixture-of-experts-0e3fc7fde818 | Eastwindy123 | towardsdatascience.com | 1970-01-01T00:00:00 | 0 | {} | 18js8k9 | false | null | t3_18js8k9 | /r/LocalLLaMA/comments/18js8k9/how_sparse_moemixtral_actually_works/ | false | false | 1 | {'enabled': False, 'images': [{'id': 'BhpvLBlwlu2U-6Osy6z6j2P-DKlYg3sSlO2ASet0558', 'resolutions': [{'height': 30, 'url': 'https://external-preview.redd.it/zzaaIXqvUYHZXZn3UdqTIrEV7iqhc964vyQ4X07N3X4.jpg?width=108&crop=smart&auto=webp&s=e965d229f33cdc4a9fdb18dd4c524275f4905150', 'width': 108}, {'height': 60, 'url': 'ht... | |
I built my own android chatting frontend for LLMs. | 27 | Project here: https://github.com/Vali-98/ChatterUI
Hey all, I'm a junior dev who has recently gotten into mobile app development and react-native. This app is a hobby project of mine and was heavily inspired by SillyTavern. Originally, it was for practicing Javascript, but I found it usable enough for casual LLM chatt... | 2023-12-16T14:19:05 | https://www.reddit.com/r/LocalLLaMA/comments/18js65y/i_built_my_own_android_chatting_frontend_for_llms/ | ----Val---- | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 18js65y | false | null | t3_18js65y | /r/LocalLLaMA/comments/18js65y/i_built_my_own_android_chatting_frontend_for_llms/ | false | false | self | 27 | {'enabled': False, 'images': [{'id': 'dpxVtuEri6rQsM9bvtDp6TifJ2xu6HU6l-qxyiWv_ug', 'resolutions': [{'height': 54, 'url': 'https://external-preview.redd.it/o6Iowk3eQoFVU0jTKM_C5JZU5DOZ1QsvGMK2pnysga0.jpg?width=108&crop=smart&auto=webp&s=951d4188a162a1a93b49edb3a34d6a0657ace564', 'width': 108}, {'height': 108, 'url': 'h... |
Unofficial Qwen 8x7b MoE - CausalLM/8x7B-MoE-test-NOT-MIXTRAL | 45 | [https://huggingface.co/CausalLM/8x7B-MoE-test-NOT-MIXTRAL](https://huggingface.co/CausalLM/8x7B-MoE-test-NOT-MIXTRAL)
>a Toolformer/Agent expert model, a multilingual translation expert model, a mathematics expert model, a visual expert model, a coding and computer expert model, and an uncensored knowledge model — to... | 2023-12-16T13:27:57 | https://www.reddit.com/r/LocalLLaMA/comments/18jr7i5/unofficial_qwen_8x7b_moe/ | No-Link-2778 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 18jr7i5 | false | null | t3_18jr7i5 | /r/LocalLLaMA/comments/18jr7i5/unofficial_qwen_8x7b_moe/ | false | false | self | 45 | {'enabled': False, 'images': [{'id': 'wGQkuonLd-lD4qCbXRcuQvjyoh9Opdp8JX3C_Cl_3dM', 'resolutions': [{'height': 58, 'url': 'https://external-preview.redd.it/GrGsEIUIZ544IM-4WtNUZwVX0KW4EdcRcANUKm5bfgY.jpg?width=108&crop=smart&auto=webp&s=bcad4af61c4dbcdf281bc760688475e8968a60a5', 'width': 108}, {'height': 116, 'url': 'h... |
I made a text-generation-webui extension that allows you to talk to multiple versions of the same character simultaneously in a single chat, in order to figure out which configuration gives the best replies | 102 | It's called Chatbot Clinic, and it's available at [https://github.com/p-e-w/chatbot_clinic](https://github.com/p-e-w/chatbot_clinic). Each character version can have its own context and generation parameters.
I've been using this for a while, and it has completely changed the way I approach writing character descripti... | 2023-12-16T13:00:10 | https://www.reddit.com/r/LocalLLaMA/comments/18jqq0m/i_made_a_textgenerationwebui_extension_that/ | -p-e-w- | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 18jqq0m | false | null | t3_18jqq0m | /r/LocalLLaMA/comments/18jqq0m/i_made_a_textgenerationwebui_extension_that/ | false | false | self | 102 | {'enabled': False, 'images': [{'id': 'itws8VFb_QOHPKAlZhJUMEY1TC2GfBmqoI792x-G1uU', 'resolutions': [{'height': 54, 'url': 'https://external-preview.redd.it/n3gZWUQwoMQcryc6UAJ6BIM9n8f7v4c1oBZbqdvUrAA.jpg?width=108&crop=smart&auto=webp&s=b851809ba6ab6aa7300e4ed0f51667780502ff75', 'width': 108}, {'height': 108, 'url': 'h... |
Looking for a local LLM with large context | 4 | Hi. Hope you have a good day and this is a right place to ask.
Long story short, I'm looking for a local LLM with a large context that can hopefully replace claude2.
Usecase:
I need to dump 40k-60k character text into it and ask an "opinion" about it, acting as a replacement of an average human. The text may be non... | 2023-12-16T12:58:34 | https://www.reddit.com/r/LocalLLaMA/comments/18jqp4c/looking_for_a_local_llm_with_large_context/ | NaN-183648 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 18jqp4c | false | null | t3_18jqp4c | /r/LocalLLaMA/comments/18jqp4c/looking_for_a_local_llm_with_large_context/ | false | false | self | 4 | null |
RuntimeError: Cannot re-initialize CUDA in forked subprocess. To use CUDA with multiprocessing, you must use the 'spawn' start method | 3 | I'm using LLAMA-2-7B-Chat AWQ on EC2 and when I'm using 3 workers with --preload it getting error and when I'm using it without --preload then it consumes the 3x memory of the model.
Following is the error what I'm getting
```
[2023-12-16 12:49:47,479] ERROR in app: Exception on /api [POST]
Traceback (most recent call... | 2023-12-16T12:54:30 | https://www.reddit.com/r/LocalLLaMA/comments/18jqmu4/runtimeerror_cannot_reinitialize_cuda_in_forked/ | Downtown-Rice-7560 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 18jqmu4 | false | null | t3_18jqmu4 | /r/LocalLLaMA/comments/18jqmu4/runtimeerror_cannot_reinitialize_cuda_in_forked/ | false | false | self | 3 | null |
Mistral with RAG try to use to much Vram if adding text files. | 1 | Hi,
​
If I use articles as below has news about fantasyfootbal , its working in 13Gb ram (I have 16GvRam)
but when I adding pdf and text (not more than 1 Mb text) its requires more memory and crashing. trying to reserve 8Gb or so .. any idea that I can efficiently use RAG with mistral7:
Code:
impor... | 2023-12-16T12:49:58 | https://www.reddit.com/r/LocalLLaMA/comments/18jqk6b/mistral_with_rag_try_to_use_to_much_vram_if/ | Total_Regular2799 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 18jqk6b | false | null | t3_18jqk6b | /r/LocalLLaMA/comments/18jqk6b/mistral_with_rag_try_to_use_to_much_vram_if/ | false | false | default | 1 | null |
How to use GPT4ALL to screen basic legal contracts | 1 | hi guys! im hoping someone can point me in the right direction...
Im trying to let GPT4ALL (i tried different models) to screen a simple legal contract.
How does this work? I get the errors as with ChatGPT-4: "im not alowed error error blablabull"
I have acces to local docs, its like GPT4ALL is still blocki... | 2023-12-16T12:43:25 | https://www.reddit.com/r/LocalLLaMA/comments/18jqgex/how_to_use_gpt4all_to_screen_basic_legal_contracts/ | alwaysonthebeach | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 18jqgex | false | null | t3_18jqgex | /r/LocalLLaMA/comments/18jqgex/how_to_use_gpt4all_to_screen_basic_legal_contracts/ | false | false | self | 1 | null |
Ilya Sutskever thinks next token prediction is enough to reach AGI and I agree | 1 | [removed] | 2023-12-16T12:35:58 | https://www.reddit.com/r/LocalLLaMA/comments/18jqc96/ilya_sutskever_thinks_next_token_prediction_is/ | enspiralart | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 18jqc96 | false | null | t3_18jqc96 | /r/LocalLLaMA/comments/18jqc96/ilya_sutskever_thinks_next_token_prediction_is/ | false | false | default | 1 | {'enabled': False, 'images': [{'id': 'oLuwzk7t70GyWvOIscDdbxL7s033khw4jiWPgTPl11Q', 'resolutions': [{'height': 81, 'url': 'https://external-preview.redd.it/tnda7AvdNng6BTuK5iqY2YFsvHBeHP1s4CEnGi2SADo.jpg?width=108&crop=smart&auto=webp&s=9480057060dd874f647d18d3af17c207f54bed7b', 'width': 108}, {'height': 162, 'url': 'h... |
Mixtral on Cpu problem | 2 | Is anybody actually able to run Mixtral on Cpu with ok speeds?
When i try it the inference in llamacpp it runs pretty okay. But the evaluation is extremely slow, going through the whole prompt at a speed similar to inference speed, meaning it takes forever to actually get the answer going.
Blas (CuBlas, Clblast) in ll... | 2023-12-16T12:35:49 | https://www.reddit.com/r/LocalLLaMA/comments/18jqc5u/mixtral_on_cpu_problem/ | paryska99 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 18jqc5u | false | null | t3_18jqc5u | /r/LocalLLaMA/comments/18jqc5u/mixtral_on_cpu_problem/ | false | false | self | 2 | null |
Techniques & datasets for validating capabilities of a language model? | 3 | I've been toying with the problem of providing an "external" memory to transformers, and have a few questions about testing & validating new transformer architectures
- Model Scale: In developing a new transformer model, what scale is ideal for demonstrating its effectiveness without directly competing with large-scal... | 2023-12-16T12:14:35 | https://www.reddit.com/r/LocalLLaMA/comments/18jq0bk/techniques_datasets_for_validating_capabilities/ | Gear5th | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 18jq0bk | false | null | t3_18jq0bk | /r/LocalLLaMA/comments/18jq0bk/techniques_datasets_for_validating_capabilities/ | false | false | self | 3 | null |
Best coding companion model today? | 31 | I am relatively new to LocalLLama's, but while playing around with Ollama + various models, I believe it doesn't make a lot of sense to use ChatGPT anymore for coding (which is what I use it for mostly).
But I am not able to figure out which models would be ideal (read at par/ better than ChatGPT?) for code completio... | 2023-12-16T11:54:42 | https://www.reddit.com/r/LocalLLaMA/comments/18jppfi/best_coding_companion_model_today/ | codevalley | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 18jppfi | false | null | t3_18jppfi | /r/LocalLLaMA/comments/18jppfi/best_coding_companion_model_today/ | false | false | self | 31 | null |
Can't implement FAISS on RAG mistral instruct.Help. | 1 | For code:
import os
import numpy as np
import faiss
import logging
from sentence\_transformers import SentenceTransformer
from llama\_index.llms import LlamaCPP
\# Set up logging
logging.basicConfig(stream=sys.stdout, level=logging.INFO)
\# Function to load and process documents
def load\_and\_... | 2023-12-16T11:20:33 | https://www.reddit.com/r/LocalLLaMA/comments/18jp7wf/cant_implement_faiss_on_rag_mistral_instructhelp/ | astrok_not | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 18jp7wf | false | null | t3_18jp7wf | /r/LocalLLaMA/comments/18jp7wf/cant_implement_faiss_on_rag_mistral_instructhelp/ | false | false | self | 1 | null |
Generating multiple tokens at once | 5 | Hi,
what always boggles my mind is that LLMs only generate one token at a time. I believe they must be capable of much more as they do not generate a random token but one that can be followed up with more to create whole texts that kind of make sense.
So I wonder if it would be possible to add multiple prediction h... | 2023-12-16T11:02:44 | https://www.reddit.com/r/LocalLLaMA/comments/18joyu2/generating_multiple_tokens_at_once/ | Schmandli | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 18joyu2 | false | null | t3_18joyu2 | /r/LocalLLaMA/comments/18joyu2/generating_multiple_tokens_at_once/ | false | false | self | 5 | null |
Is No Moat getting real? | 293 | I am referring this article from May that was supposingly leaked from a google employee
[Google "We Have No Moat, And Neither Does OpenAI" (semianalysis.com)](https://www.semianalysis.com/p/google-we-have-no-moat-and-neither)
It's December now and google tries the first time to get market share from API calls.
But a... | 2023-12-16T11:02:37 | https://www.reddit.com/r/LocalLLaMA/comments/18joyro/is_no_moat_getting_real/ | Bene0 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 18joyro | false | null | t3_18joyro | /r/LocalLLaMA/comments/18joyro/is_no_moat_getting_real/ | false | false | self | 293 | {'enabled': False, 'images': [{'id': '2e-ORlXr3q8t_t4YwQwiP0Mo0wzKQ10f6PvX1VywrKs', 'resolutions': [{'height': 52, 'url': 'https://external-preview.redd.it/Dd9F-kRfRODUzYVJwfzGw-m0UE1PIvav14lL_7C6SWs.jpg?width=108&crop=smart&auto=webp&s=f28453b0097499a073aa10d835a6060bed74dbb9', 'width': 108}, {'height': 105, 'url': 'h... |
Inference for m2m100 or other translation models. Is there something similar as vLLM | 1 | [removed] | 2023-12-16T08:47:48 | https://www.reddit.com/r/LocalLLaMA/comments/18jn42q/inference_for_m2m100_or_other_translation_models/ | Torkoslav | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 18jn42q | false | null | t3_18jn42q | /r/LocalLLaMA/comments/18jn42q/inference_for_m2m100_or_other_translation_models/ | false | false | self | 1 | null |
Stable 7B Model | 1 | What's the Most stable 7B LM that can more or less run on 4gb ram. I prefer the GGUF ones | 2023-12-16T08:43:17 | https://www.reddit.com/r/LocalLLaMA/comments/18jn1zi/stable_7b_model/ | Jsus-Sus | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 18jn1zi | false | null | t3_18jn1zi | /r/LocalLLaMA/comments/18jn1zi/stable_7b_model/ | false | false | self | 1 | null |
Autogen + mistral small/moe/mixtral | 6 | Has anyone managed to get this working? I myself would have to use the api as I have terrible hardware but it would be interesting to know.
I'm trying to get it working in vs code and have used the search bar before asking. | 2023-12-16T07:17:11 | https://www.reddit.com/r/LocalLLaMA/comments/18jlv52/autogen_mistral_smallmoemixtral/ | Unusual_Pride_6480 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 18jlv52 | false | null | t3_18jlv52 | /r/LocalLLaMA/comments/18jlv52/autogen_mistral_smallmoemixtral/ | false | false | self | 6 | null |
Phi 2 crashing on Maid (mobile) | 1 | [removed] | 2023-12-16T07:03:40 | https://www.reddit.com/r/LocalLLaMA/comments/18jlnzn/phi_2_crashing_on_maid_mobile/ | Reentry9028 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 18jlnzn | false | null | t3_18jlnzn | /r/LocalLLaMA/comments/18jlnzn/phi_2_crashing_on_maid_mobile/ | false | false | self | 1 | {'enabled': False, 'images': [{'id': 'rfNB09Gf5zkQIjjLzajs3quYIjwIaJLfjuMjxUc9kqQ', 'resolutions': [{'height': 54, 'url': 'https://external-preview.redd.it/pStBkQSkha8RsQ0qD1AZeRelFGmNgRU7m_edM51Y-iA.jpg?width=108&crop=smart&auto=webp&s=919346f7ac2e7659560e5a0a86fcd3569fc802f6', 'width': 108}, {'height': 108, 'url': 'h... |
I decided to have some fun with a LLaMa based RP AI | 2 | Please don't judge me, but I've been doing a lot of role play with AI as I feel like it's one area that AI can actually be pretty strong in. I have been trying out a variety of models using LM Studio, oobabooga,and GPT4all to get a full picture of how the models react to various things.
One of the things I've been d... | 2023-12-16T06:28:58 | https://www.reddit.com/r/LocalLLaMA/comments/18jl4px/i_decided_to_have_some_fun_with_a_llama_based_rp/ | Cool-Hornet4434 | self.LocalLLaMA | 2023-12-16T06:32:41 | 0 | {} | 18jl4px | false | null | t3_18jl4px | /r/LocalLLaMA/comments/18jl4px/i_decided_to_have_some_fun_with_a_llama_based_rp/ | false | false | self | 2 | null |
how can i access an install of ollama with datasette llm? | 1 | I'm running [Ollama](https://github.com/jmorganca/ollama)
accessible with a POST to http://localhost:11434/api/chat
how can I access it through [llm datasette](https://llm.datasette.io/en/stable/other-models.html#openai-compatible-models)? | 2023-12-16T06:00:03 | https://www.reddit.com/r/LocalLLaMA/comments/18jkonj/how_can_i_access_an_install_of_ollama_with/ | 202-456-1414 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 18jkonj | false | null | t3_18jkonj | /r/LocalLLaMA/comments/18jkonj/how_can_i_access_an_install_of_ollama_with/ | false | false | self | 1 | null |
T7610 Dual P40 Inference | 10 | Just wanted to share my journey building an AI-focused system using Tesla P40s. I read [this post](https://www.reddit.com/r/LocalLLaMA/comments/13n8bqh/my_results_using_a_tesla_p40) a while ago and was intrigued, and found a lot of 2 P40s at $250 on ebay. I ended up putting them into my workstation:
**Original System ... | 2023-12-16T05:26:32 | https://www.reddit.com/r/LocalLLaMA/comments/18jk4u3/t7610_dual_p40_inference/ | ConcaveTriangle5761 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 18jk4u3 | false | null | t3_18jk4u3 | /r/LocalLLaMA/comments/18jk4u3/t7610_dual_p40_inference/ | false | false | 10 | null | |
Dual Titan RTX somehow SLOWER than Tesla P40 | 1 | Like the title says. Not sure what's going on but dual Titan RTX is somehow performing worse than a Nvidia Tesla P40.
Here is comparison both running on the latest oobabooga commit 443be391f2a7cee8402d9a58203dbf6511ba288c as of posting.
Mistral 7B Dolphin2.2.1 Q8 GGUF:
Dual Titan RTX:
llama_print_timings: ... | 2023-12-16T05:11:19 | https://www.reddit.com/r/LocalLLaMA/comments/18jjw48/dual_titan_rtx_somehow_slower_than_tesla_p40/ | nero10578 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 18jjw48 | false | null | t3_18jjw48 | /r/LocalLLaMA/comments/18jjw48/dual_titan_rtx_somehow_slower_than_tesla_p40/ | false | false | self | 1 | null |
Is LLama.cpp + Mixtral unencumbered Open Source, or still under the Meta License? | 8 | Just wondering if there's a "fruit of the poisoned tree" effect going on when using something like Llama.cpp (or llama-cpp-python or llama\_index, etc.) which are all released under the [MIT License](https://github.com/ggerganov/llama.cpp/blob/master/LICENSE) when paired with Mistral's [Apache 2.0-licensed](https://hug... | 2023-12-16T05:05:09 | https://www.reddit.com/r/LocalLLaMA/comments/18jjsby/is_llamacpp_mixtral_unencumbered_open_source_or/ | PrinceOfLeon | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 18jjsby | false | null | t3_18jjsby | /r/LocalLLaMA/comments/18jjsby/is_llamacpp_mixtral_unencumbered_open_source_or/ | false | false | self | 8 | {'enabled': False, 'images': [{'id': 'DJPqvteONpGwVVw6LzaG6b8vlDa2rv2hETCaqe0z57s', 'resolutions': [{'height': 54, 'url': 'https://external-preview.redd.it/wyCM1fHzTa-IIqHgS1QTxdSYNXn668elDj0WmYMPf_k.jpg?width=108&crop=smart&auto=webp&s=d6fa197328d583bcae7a764b40fd1214265b6852', 'width': 108}, {'height': 108, 'url': 'h... |
With half a TB of ram and 8x 1080s, what’s the best unsafe coding model? | 58 | I am looking for a model to work as my coding and infosec partner. I say unsafe to mean I want to be able to tell it “produce golang code with a buffer overflow in it”, the kind of things chatgpt doesn’t do. Also something that I can ask security questions to, or feed word templates and have it format them, or give PDF... | 2023-12-16T04:14:23 | https://www.reddit.com/r/LocalLLaMA/comments/18jiw08/with_half_a_tb_of_ram_and_8x_1080s_whats_the_best/ | oldschooldaw | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 18jiw08 | false | null | t3_18jiw08 | /r/LocalLLaMA/comments/18jiw08/with_half_a_tb_of_ram_and_8x_1080s_whats_the_best/ | false | false | self | 58 | null |
Fine tuning for dummies | 45 | I am looking to do novel writing and I've found the output I get from any llm, including chatgpt, sounds wooden and boring.
From what I've read, fine tuning can help significantly. Given my equipment (3090), it sounds like qlora is the way to go.
That being said, I've been on YouTube, Google, and here and the topi... | 2023-12-16T04:07:15 | https://www.reddit.com/r/LocalLLaMA/comments/18jirmu/fine_tuning_for_dummies/ | Jenniher | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 18jirmu | false | null | t3_18jirmu | /r/LocalLLaMA/comments/18jirmu/fine_tuning_for_dummies/ | false | false | self | 45 | null |
Help me choose: Need local RAG, options for embedding, GPU, with GUI. PrivateGPT, localGPT, MemGPT, AutoGen, Taskweaver, GPT4All, or ChatDocs? | 23 | Hi
As post title implies, I'm a bit confused and need some guidance. I've tried some but not yet all of the apps listed in the title.
Looking to get a feel (via comments) for the "State of the Union" of LLM end-to-end apps with local RAG.
What I want to do:
1. Multi-format: I have folders of PDFs, epubs, and text-... | 2023-12-16T03:59:30 | https://www.reddit.com/r/LocalLLaMA/comments/18jimix/help_me_choose_need_local_rag_options_for/ | TheWebbster | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 18jimix | false | null | t3_18jimix | /r/LocalLLaMA/comments/18jimix/help_me_choose_need_local_rag_options_for/ | false | false | self | 23 | null |
What's the easiest way to run Phi-2 locally currently? | 2 | Seems like there's a quantised version working in browser here: [https://huggingface.co/spaces/radames/Candle-phi1-phi2-wasm-demo?model=phi\_2\_0\_q4k](https://huggingface.co/spaces/radames/Candle-phi1-phi2-wasm-demo?model=phi_2_0_q4k). But doesn't look like tools like LM Studio or Ollama are supporting Phi-2 yet! | 2023-12-16T03:26:55 | https://www.reddit.com/r/LocalLLaMA/comments/18ji1nf/whats_the_easiest_way_to_run_phi2_locally/ | mikachip | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 18ji1nf | false | null | t3_18ji1nf | /r/LocalLLaMA/comments/18ji1nf/whats_the_easiest_way_to_run_phi2_locally/ | false | false | default | 2 | {'enabled': False, 'images': [{'id': 'fuO00O7qX3jXuj6gAg_bAx3TaTHxTk8hT0pE_5GOrbQ', 'resolutions': [{'height': 58, 'url': 'https://external-preview.redd.it/2wvCpjPYxmaxmOyPHrWjhXsua5erHt5Y07a0XHPjmHc.jpg?width=108&crop=smart&auto=webp&s=7e1c3b47e73de83455e9dcd72b43d9122a26fa40', 'width': 108}, {'height': 116, 'url': 'h... |
Ethics in LLM Training Data: Any Thought? | 1 | Hello beautiful Llama community
I'm curious about the datasets used for the training of LLMs.
I couldn't find much about their sources, except maybe for BLOOM.
Even open source models like mistral do reveal anything about the datasets used to train their LLMs. The only thing I found is they used available datasets... | 2023-12-16T03:25:56 | https://www.reddit.com/r/LocalLLaMA/comments/18ji110/ethics_in_llm_training_data_any_thought/ | steph_pop | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 18ji110 | false | null | t3_18ji110 | /r/LocalLLaMA/comments/18ji110/ethics_in_llm_training_data_any_thought/ | false | false | self | 1 | null |
Mistral or Mixtral with tabular data | 2 | Greetings! I’m a noob!
I’ve been testing out different 7B models as well as 70B models and I’ve landed on Mistral and Mixtral.
Now for the question.
I have tabular data that I’m trying to query in a basic csv. The data pertains to finding prices based on the names of dogs breeds. Basically I type in, German Sheppar... | 2023-12-16T03:07:00 | https://www.reddit.com/r/LocalLLaMA/comments/18jhori/mistral_or_mixtral_with_tabular_data/ | Tymid | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 18jhori | false | null | t3_18jhori | /r/LocalLLaMA/comments/18jhori/mistral_or_mixtral_with_tabular_data/ | false | false | self | 2 | null |
LLM PC build, looking for input or suggestions | 3 | I've been running on a system that is pretty old now, besides the 4090 in it.
I'm thinking of putting together a system for about $2000 to $4000. Here's the part list I have, I already have a decent PSU. I was thinking of getting another 4090 but I'm not sure if it will fit in this mobo without risers.
Any sugge... | 2023-12-16T03:00:06 | https://www.reddit.com/r/LocalLLaMA/comments/18jhk3l/llm_pc_build_looking_for_input_or_suggestions/ | SantaBooks | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 18jhk3l | false | null | t3_18jhk3l | /r/LocalLLaMA/comments/18jhk3l/llm_pc_build_looking_for_input_or_suggestions/ | false | false | self | 3 | null |
Subsets and Splits
No community queries yet
The top public SQL queries from the community will appear here once available.