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 ⌀ |
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
The Repeating Issue? | 3 | As a noob, I’m using KoboldAI and Oobabooga simultaneously at the moment, but I found that with the same model (wizard vacuna 13b ggml) kobold never repeated sentences as much as ooba did. (llama.cpp)
I know nothing about the settings and I wonder how can I fix the repeating issue when using ooba, or is there a guide?... | 2023-07-07T03:21:07 | https://www.reddit.com/r/LocalLLaMA/comments/14sv1ne/the_repeating_issue/ | Mildred_D | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 14sv1ne | false | null | t3_14sv1ne | /r/LocalLLaMA/comments/14sv1ne/the_repeating_issue/ | false | false | self | 3 | null |
Llama is good but, what else is available? Qualitatively | 13 | I am looking to build a local LLM model, but I dont want to be constrained by the licensing if I want to build something that can be commercially available? I know Dolly and H2O have decent models. do you guys have any suggetions of the other models that perform just as well or strategies to make them do so? I want to ... | 2023-07-07T02:46:01 | https://www.reddit.com/r/LocalLLaMA/comments/14su9fp/llama_is_good_but_what_else_is_available/ | Altruistic-Ask-773 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 14su9fp | false | null | t3_14su9fp | /r/LocalLLaMA/comments/14su9fp/llama_is_good_but_what_else_is_available/ | false | false | self | 13 | null |
4060 Ti vs 3070 vs 3060 Ti Stable Diffusion benchmark | 47 | I saw a post talking about 4060 Ti being a bad card because of the 128 bit memory bus. However I can't find any benchmark for generative AI.
A video on Bilibili compares the performance of different GPUs for Stable Diffusion. The chart shows the time (in seconds) needed to generate a image with Stable Diffusion, so th... | 2023-07-07T02:11:48 | regunakyle | i.redd.it | 1970-01-01T00:00:00 | 0 | {} | 14sti62 | false | null | t3_14sti62 | /r/LocalLLaMA/comments/14sti62/4060_ti_vs_3070_vs_3060_ti_stable_diffusion/ | false | false | 47 | {'enabled': True, 'images': [{'id': '2QAdM0ad_wcWX9r7QAUyIzV7tvg5IO1ppXpiqcZ7-A0', 'resolutions': [{'height': 62, 'url': 'https://preview.redd.it/mu20scrxbgab1.jpg?width=108&crop=smart&auto=webp&s=24d50386cd7a39a1a93d6492d6b712dac7aca71c', 'width': 108}, {'height': 125, 'url': 'https://preview.redd.it/mu20scrxbgab1.jpg... | ||
LongLLaMA, a LLM capable of handling long contexts of 256k tokens | 2 | 2023-07-07T01:58:26 | https://twitter.com/_akhaliq/status/1677131408265945088 | ninjasaid13 | twitter.com | 1970-01-01T00:00:00 | 0 | {} | 14st6ba | false | {'oembed': {'author_name': 'AK', 'author_url': 'https://twitter.com/_akhaliq', 'cache_age': 3153600000, 'height': None, 'html': '<blockquote class="twitter-video"><p lang="en" dir="ltr">Focused Transformer: Contrastive Training for Context Scaling<br><br>paper page: <a href="https://t.co/nMD1r6e21b">https://t.co/nMD1r6... | t3_14st6ba | /r/LocalLLaMA/comments/14st6ba/longllama_a_llm_capable_of_handling_long_contexts/ | false | false | default | 2 | {'enabled': False, 'images': [{'id': 'yZB-Op42aidgsC58AESnRAIxZl5MNXE47YaH2fOrL2Q', 'resolutions': [{'height': 116, 'url': 'https://external-preview.redd.it/8m2D72Vzmkgfwrvj-wgZL8Kja5a-JyDIBVxPf8ydkL4.jpg?width=108&crop=smart&auto=webp&v=enabled&s=cad6cc0edfd4e7c04ba1c6e5c489357db6ea061a', 'width': 108}, {'height': 232... | |
What should I look out for during fine tuning? | 4 | I’m fine tuning using the oogabooga GUI.
I know “loss” is an important metric. Their guide recommends stopping at around loss = 1
Intuitively what’s the difference between a loss of 1.1 and 1.0?
For example, my data started at a loss of 2.0. After only about 0.1 epochs, it drops to 1.1. Then continued training for l... | 2023-07-07T01:37:08 | https://www.reddit.com/r/LocalLLaMA/comments/14ssp6n/what_should_i_look_out_for_during_fine_tuning/ | Tasty-Lobster-8915 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 14ssp6n | false | null | t3_14ssp6n | /r/LocalLLaMA/comments/14ssp6n/what_should_i_look_out_for_during_fine_tuning/ | false | false | self | 4 | null |
VRAM or RAM for cost effective home build | 1 | I have been wondering what sort of performance people have been getting out of CPU based builds running local llama?
I haven't seen a similar post since the release of 8k token limits and ExLLAMA. It's not to hard to imagine a build with 64gb of RAM blowing a mid teir GPU out of the water in terms of model capability... | 2023-07-07T01:27:33 | https://www.reddit.com/r/LocalLLaMA/comments/14ssguq/vram_or_ram_for_cost_effective_home_build/ | Far-Notice1730 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 14ssguq | false | null | t3_14ssguq | /r/LocalLLaMA/comments/14ssguq/vram_or_ram_for_cost_effective_home_build/ | false | false | self | 1 | null |
A6000 vs 2x 4090 | 14 | I've been experimenting with llms for the past few months. I feel like I've been held back by lacking vram. I'm considering upgrading to either an A6000 or dual 4090s.
The A6000 has more vram and costs roughly the same as 2x 4090s. The A6000 would run slower than the 4090s but the A6000 would be a single card and have... | 2023-07-07T01:00:17 | https://www.reddit.com/r/LocalLLaMA/comments/14srull/a6000_vs_2x_4090/ | drnick316 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 14srull | false | null | t3_14srull | /r/LocalLLaMA/comments/14srull/a6000_vs_2x_4090/ | false | false | self | 14 | null |
Dilbert Comic | 0 | 2023-07-07T00:36:50 | https://www.reddit.com/r/dilbert/comments/14sktuy/dilbert_reborn_june_30th_2023_shared_for_all_on/ | kubbiember | reddit.com | 1970-01-01T00:00:00 | 0 | {} | 14sracc | false | null | t3_14sracc | /r/LocalLLaMA/comments/14sracc/dilbert_comic/ | false | false | default | 0 | {'enabled': False, 'images': [{'id': '-OrtaAE98-Yo261LD87_xRkwvd3emJZP-0nwVbk7ZNs', 'resolutions': [{'height': 38, 'url': 'https://external-preview.redd.it/jZBjwHltyEl4aJdS31MKefTMSQkJXWjRkARJm9iK5YU.png?width=108&crop=smart&auto=webp&v=enabled&s=307b34ab94c177ad1f1a014b22835bf5a456578e', 'width': 108}, {'height': 77, ... | |
Vector Search w/ LMMs vs Classic Text Search (i.e. elasticsearch), has anyone done pricing/performance experiments? | 7 | Title! I am sure there has been some research done on this topic but not sure where. Curious if anyone has found vector search via some open-soruce model (through vector store) is more performant/cheaper than elasticsearch. Thanks | 2023-07-07T00:02:13 | https://www.reddit.com/r/LocalLLaMA/comments/14sqg2j/vector_search_w_lmms_vs_classic_text_search_ie/ | Working_Ideal3808 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 14sqg2j | false | null | t3_14sqg2j | /r/LocalLLaMA/comments/14sqg2j/vector_search_w_lmms_vs_classic_text_search_ie/ | false | false | self | 7 | null |
Fill in blanks with conversation (Prompt now working?) | 5 | I am trying to get an appropriate response for this prompt:
Fill in the RESPONSE part of this conversation between a human and a bot. Bot: Hi. Human RESPONSE. Bot: I am 10 years old! How about you?
Where response would be something like: "Hi, how old are you?"
Why isn't this working on anything less than ChatGPT? A... | 2023-07-06T22:51:02 | https://www.reddit.com/r/LocalLLaMA/comments/14son0l/fill_in_blanks_with_conversation_prompt_now/ | ilovejoi36912 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 14son0l | false | null | t3_14son0l | /r/LocalLLaMA/comments/14son0l/fill_in_blanks_with_conversation_prompt_now/ | false | false | self | 5 | null |
LLMs on a 32-bit device with 2GB of RAM | 5 | Pardon the messiness of this post, my thought process can be pretty hectic lol
# 2023-07-11 Update
u/pedantic_pineapple brought some light back into this. I've had some difficulty getting it working, however (listing this to save time if someone else sees this post):
1. Using `pip install languagemodels` ends up dow... | 2023-07-06T22:17:51 | https://www.reddit.com/r/LocalLLaMA/comments/14snrcp/llms_on_a_32bit_device_with_2gb_of_ram/ | MeowAnnabelle | self.LocalLLaMA | 2023-07-12T05:03:50 | 0 | {} | 14snrcp | false | null | t3_14snrcp | /r/LocalLLaMA/comments/14snrcp/llms_on_a_32bit_device_with_2gb_of_ram/ | false | false | self | 5 | null |
Best model that can run on Colab | 7 | Hi everyone
First of all, I want to thank everyone in this sub who is contribute to the progress of Open source llms. Than you so much!
I want to experiment with medium sized models (7b/13b) but my gpu is old and has only 2GB vram.
So I'll probably be using google colab's **free** gpu, which is nvidia T4 with around... | 2023-07-06T22:14:05 | https://www.reddit.com/r/LocalLLaMA/comments/14snnj5/best_model_that_can_run_on_colab/ | Amgadoz | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 14snnj5 | false | null | t3_14snnj5 | /r/LocalLLaMA/comments/14snnj5/best_model_that_can_run_on_colab/ | false | false | self | 7 | null |
Trying Classifier Free Guidance and Negative prompt - some ideas how to test it properly? | 17 | 2023-07-06T21:21:21 | FPham | i.redd.it | 1970-01-01T00:00:00 | 0 | {} | 14sm839 | false | null | t3_14sm839 | /r/LocalLLaMA/comments/14sm839/trying_classifier_free_guidance_and_negative/ | false | false | 17 | {'enabled': True, 'images': [{'id': 'LAqNZ684cJaVml-0PGv5zOdQ1G75ZEn3ytdxN0YHZDg', 'resolutions': [{'height': 123, 'url': 'https://preview.redd.it/i3vo0ys1weab1.jpg?width=108&crop=smart&auto=webp&s=892c938cc454a403587c01016721ede66857b3d7', 'width': 108}, {'height': 246, 'url': 'https://preview.redd.it/i3vo0ys1weab1.jp... | |||
I guess George Hotz was correct. | 78 | 2023-07-06T21:16:53 | https://arxiv.org/abs/2305.14705 | MrBeforeMyTime | arxiv.org | 1970-01-01T00:00:00 | 0 | {} | 14sm3p0 | false | null | t3_14sm3p0 | /r/LocalLLaMA/comments/14sm3p0/i_guess_george_hotz_was_correct/ | false | false | 78 | {'enabled': False, 'images': [{'id': 'q3evP6JeDpAC2MdSQHWYxnCYTqbJkElIQsLFqVSdkss', 'resolutions': [{'height': 63, 'url': 'https://external-preview.redd.it/0HhwdU6MKIAKjL9Y8-B_iH374a3NiPTy0ib8lmloRzA.jpg?width=108&crop=smart&auto=webp&s=2711d572cfc6c713893cf24e8c4a7344d5ad8a4c', 'width': 108}, {'height': 126, 'url': 'h... | ||
What's the current best model if you have no concern about the hardware? | 1 | I have access to a semi-supercomputer and I wonder what's the best model I perhaps could run on it specifically for my personal use. | 2023-07-06T19:58:57 | https://www.reddit.com/r/LocalLLaMA/comments/14sjz7q/whats_the_current_best_model_if_you_have_no/ | hattapliktir | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 14sjz7q | false | null | t3_14sjz7q | /r/LocalLLaMA/comments/14sjz7q/whats_the_current_best_model_if_you_have_no/ | false | false | self | 1 | null |
Does RAM make a big difference? | 1 | [removed] | 2023-07-06T19:58:01 | https://www.reddit.com/r/LocalLLaMA/comments/14sjyan/does_ram_make_a_big_difference/ | Asoery | self.LocalLLaMA | 2023-07-06T20:02:04 | 0 | {} | 14sjyan | false | null | t3_14sjyan | /r/LocalLLaMA/comments/14sjyan/does_ram_make_a_big_difference/ | false | false | default | 1 | null |
Help with QLoRA Fine Tune | 5 | I'm following nearly the same example from the this repository:
https://github.com/mzbac/qlora-fine-tune
-Except I'm testing it with one of the standard hardcoded datasets in his script, 'alpaca'. Here's the command:
python qlora.py --model_name_or_path TheBloke/wizardLM-13B-1.0-fp16 --dataset alpaca --bf16
That da... | 2023-07-06T18:59:07 | https://www.reddit.com/r/LocalLLaMA/comments/14sidp3/help_with_qlora_fine_tune/ | gentlecucumber | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 14sidp3 | false | null | t3_14sidp3 | /r/LocalLLaMA/comments/14sidp3/help_with_qlora_fine_tune/ | false | false | self | 5 | {'enabled': False, 'images': [{'id': 'Sps2Xxji1GXjTiQi3CmfFiIIh8o2K1Rd4E9wU0Fes0U', 'resolutions': [{'height': 54, 'url': 'https://external-preview.redd.it/j_Pylg0cD-lDn5wTlAJ6VSvXnujwT6XnCnq4InZSz2k.jpg?width=108&crop=smart&auto=webp&s=8348f876b1e97108c598081be7555cf87557b917', 'width': 108}, {'height': 108, 'url': 'h... |
Finetuning guide for MPT | 15 | I've written up the exact steps doing a full finetune on an MPT model here:
https://gist.github.com/float-trip/679019a23f246b17d2dff9e2cf55c387
The official Mosaic docs are fine, but aspirational in places. They're not always up-to-date regarding bugs in the library.
As for _why_ to finetune MPT - it's 5-10x cheaper... | 2023-07-06T18:45:22 | https://www.reddit.com/r/LocalLLaMA/comments/14si12b/finetuning_guide_for_mpt/ | float-trip | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 14si12b | false | null | t3_14si12b | /r/LocalLLaMA/comments/14si12b/finetuning_guide_for_mpt/ | false | false | self | 15 | {'enabled': False, 'images': [{'id': 'OAXSl8SY6T3JK9MGQyKxkoYbqZ71HQRYXLeB8CV0NXg', 'resolutions': [{'height': 54, 'url': 'https://external-preview.redd.it/4-DxLM-C2Ve3tHmVL5ITI6GRtMVG8PzzdBuCKiaabfE.jpg?width=108&crop=smart&auto=webp&s=d5811c5bda5fece1040636a6af8702ba790f0fd4', 'width': 108}, {'height': 108, 'url': 'h... |
For those who train models: how do you normalize your data? | 2 | Assume I have a set of books. Some are perfectly formatted with OCR capabilities from Amazon. Others are scanned in and uploaded to archive.org (say, very old texts). Others have been OCR'd by me manually. How can I ensure each of these are treated the same and fed into the model correctly?
Are there tools for this? N... | 2023-07-06T17:39:08 | https://www.reddit.com/r/LocalLLaMA/comments/14sg873/for_those_who_train_models_how_do_you_normalize/ | JebryyathHS | self.LocalLLaMA | 2023-07-13T00:21:16 | 0 | {} | 14sg873 | false | null | t3_14sg873 | /r/LocalLLaMA/comments/14sg873/for_those_who_train_models_how_do_you_normalize/ | false | false | default | 2 | null |
Is it possible to change a mining rig into a GPT trainer? | 9 | Hey folks,
I have an old rig of an Octominer with a couple 3090s and 3080s. I would love to either rent out the gpu power/mem or build my own models. In the mining world there are a lot more MOBOs that can have many GPUs like 12. Would I be able to use the mono there or should I just build a gaming PC etc? I guess I'... | 2023-07-06T17:39:05 | https://www.reddit.com/r/LocalLLaMA/comments/14sg854/is_it_possible_to_change_a_mining_rig_into_a_gpt/ | gosume | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 14sg854 | false | null | t3_14sg854 | /r/LocalLLaMA/comments/14sg854/is_it_possible_to_change_a_mining_rig_into_a_gpt/ | false | false | self | 9 | null |
My largest ever quants, GPT 3 sized! BLOOMZ 176B and BLOOMChat 1.0 176B | 325 | For the last month I've been trying to quantise two mega models, probably the largest models on Hugging Face Hub: Big Science's [BLOOMZ](https://huggingface.co/bigscience/bloomz) and Sambanova Systems' [BLOOMChat 1.0](https://huggingface.co/sambanovasystems/BLOOMChat-176B-v1).
I tried various systems, but all the HW a... | 2023-07-06T16:12:08 | https://www.reddit.com/r/LocalLLaMA/comments/14sdskp/my_largest_ever_quants_gpt_3_sized_bloomz_176b/ | The-Bloke | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 14sdskp | false | null | t3_14sdskp | /r/LocalLLaMA/comments/14sdskp/my_largest_ever_quants_gpt_3_sized_bloomz_176b/ | false | false | self | 325 | {'enabled': False, 'images': [{'id': 'gXQ-wVUM2Tyx_6Y872ShG3Aaorh5qEh0nAGMrxUIbaU', 'resolutions': [{'height': 58, 'url': 'https://external-preview.redd.it/Pl8R_0F9Tk0OfJMzghy_fs_WW7nqD8aYz19Tli-iHBw.jpg?width=108&crop=smart&auto=webp&s=adabb132efe463e3081b83a0a07cc3430c9a1911', 'width': 108}, {'height': 116, 'url': 'h... |
Using LLM locally with HuggingFace blocked? | 0 | I want to try to use either Falcon, Dolly, or Mosaic to run a model locally on my work laptop. Unfortunately, HuggingFace is blocked on my computer. How would I go about this issue? | 2023-07-06T15:29:37 | https://www.reddit.com/r/LocalLLaMA/comments/14sckrf/using_llm_locally_with_huggingface_blocked/ | sisiwnsjhsjajzjxjs | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 14sckrf | false | null | t3_14sckrf | /r/LocalLLaMA/comments/14sckrf/using_llm_locally_with_huggingface_blocked/ | false | false | default | 0 | null |
SuperAGI with KoboldCpp backend | 14 | Hey.
I haven't seen much discussion about [SuperAGI](https://superagi.com/) here, possibly because it mainly seems to target OpenAi (even though they have bundled oobabooga recently). But since I use koboldcpp (and thus ggml), and I don't want to have double models, I created a koboldcpp backend for it.
Results so fa... | 2023-07-06T15:18:20 | https://www.reddit.com/r/LocalLLaMA/comments/14sc98c/superagi_with_koboldcpp_backend/ | neph1010 | self.LocalLLaMA | 2023-07-06T16:15:24 | 0 | {} | 14sc98c | false | null | t3_14sc98c | /r/LocalLLaMA/comments/14sc98c/superagi_with_koboldcpp_backend/ | false | false | 14 | {'enabled': False, 'images': [{'id': 'UJCmnHuTn9r_Y3u-nHjo5TpdgWhE5vSjvuGFQhXJMaM', 'resolutions': [{'height': 54, 'url': 'https://external-preview.redd.it/CcKWWFQNGBkfC3w3r2EbiFSEq_OD8fwzmYbnt8xDzZc.jpg?width=108&crop=smart&auto=webp&s=c71a8b4cb3b337d965b9df23b446f28d66554de5', 'width': 108}, {'height': 108, 'url': 'h... | |
Is there any service like MosaicML to train LLMs, but more focused on individuals instead of enterprises? | 0 | The title | 2023-07-06T13:57:22 | https://www.reddit.com/r/LocalLLaMA/comments/14sa0gh/is_there_any_service_like_mosaicml_to_train_llms/ | mr_house7 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 14sa0gh | false | null | t3_14sa0gh | /r/LocalLLaMA/comments/14sa0gh/is_there_any_service_like_mosaicml_to_train_llms/ | false | false | default | 0 | null |
Fine-tune on personal chats | 1 | Did you know that you can download all your personal conversations on Facebook?
Then use that to fine-tune a LLM to answer like you. | 2023-07-06T13:25:02 | https://www.reddit.com/r/LocalLLaMA/comments/14s95ri/finetune_on_personal_chats/ | veentastudios | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 14s95ri | false | null | t3_14s95ri | /r/LocalLLaMA/comments/14s95ri/finetune_on_personal_chats/ | false | false | self | 1 | null |
Is there anything to really chat with an AI as you would do with somebody over the phone ? | 18 | I mean any project, whether free or open source, that would allow you to chat with a bot without using a mouse or keyboard. Ideally, you would be stop or pause the bot's responses by simply saying "STOP" or something similar.
So far, none of the solutions I have tried have provided a smooth conversational experienc... | 2023-07-06T13:10:46 | https://www.reddit.com/r/LocalLLaMA/comments/14s8sy6/is_there_anything_to_really_chat_with_an_ai_as/ | alexthai7 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 14s8sy6 | false | null | t3_14s8sy6 | /r/LocalLLaMA/comments/14s8sy6/is_there_anything_to_really_chat_with_an_ai_as/ | false | false | self | 18 | null |
LLaMa 65B GPU benchmarks | 111 | I spent half a day conducting a benchmark test of the 65B model on some of the most powerful GPUs aviailable to individuals.
Test Method: I ran the latest Text-Generation-Webui on Runpod, loading Exllma, Exllma\_HF, and LLaMa.cpp for comparative testing. I used a specific prompt to ask them to generate a long story, m... | 2023-07-06T12:19:21 | https://www.reddit.com/r/LocalLLaMA/comments/14s7j9j/llama_65b_gpu_benchmarks/ | Big_Communication353 | self.LocalLLaMA | 2023-07-06T23:56:31 | 0 | {} | 14s7j9j | false | null | t3_14s7j9j | /r/LocalLLaMA/comments/14s7j9j/llama_65b_gpu_benchmarks/ | false | false | self | 111 | null |
num_beams > 1 breaking my model (Open-LLaMA7b - Alpaca-finetuned) | 3 | As the title states, I'm experiencing some weird results when using num\_beams > 1. The first 150-ish tokens are great, much better than if I use num\_beams == 1. However, after that point, it starts outputting gibberish. I've tried tweaking max\_new\_tokens and max\_length to see if the issue lies there. The model... | 2023-07-06T12:05:09 | https://www.reddit.com/r/LocalLLaMA/comments/14s77av/num_beams_1_breaking_my_model_openllama7b/ | BuzzLightr | self.LocalLLaMA | 2023-07-06T12:11:33 | 0 | {} | 14s77av | false | null | t3_14s77av | /r/LocalLLaMA/comments/14s77av/num_beams_1_breaking_my_model_openllama7b/ | false | false | self | 3 | null |
Free LLM api | 1 | What are some free LLM api which are alternative for OpenAI API | 2023-07-06T10:01:14 | https://www.reddit.com/r/LocalLLaMA/comments/14s4hou/free_llm_api/ | Exciting-Purpose-711 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 14s4hou | false | null | t3_14s4hou | /r/LocalLLaMA/comments/14s4hou/free_llm_api/ | false | false | self | 1 | null |
New base model InternLM 7B weights released, with 8k context window. | 49 | 2023-07-06T07:39:08 | https://github.com/InternLM/InternLM | logicchains | github.com | 1970-01-01T00:00:00 | 0 | {} | 14s1p96 | false | null | t3_14s1p96 | /r/LocalLLaMA/comments/14s1p96/new_base_model_internlm_7b_weights_released_with/ | false | false | 49 | {'enabled': False, 'images': [{'id': '2tVUfp5lAxozL-49NKZd2aSVbQLlqCzZXLzttctaQB8', 'resolutions': [{'height': 54, 'url': 'https://external-preview.redd.it/-L_o9_ksbyTG8oYmftdYYRNi0-70J1OYYk4hPlLwJzQ.jpg?width=108&crop=smart&auto=webp&s=4749d28246824b1dd6e283cb57232c25cc4aeac2', 'width': 108}, {'height': 108, 'url': 'h... | ||
Using other tokenizers? | 1 | Hi,
​
I'm trying to apply llama in understanding Korean text. However, the original tokenizer for llama seems to greatly over-estimate the number of tokens.
With the same input text, llama tokenizer would give 5\~6 times more tokens than KoBERT tokenizer.
I assume this is because llama was not built with Kor... | 2023-07-06T06:16:08 | https://www.reddit.com/r/LocalLLaMA/comments/14s038q/using_other_tokenizers/ | manjimin | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 14s038q | false | null | t3_14s038q | /r/LocalLLaMA/comments/14s038q/using_other_tokenizers/ | false | false | self | 1 | null |
SillyTavern use-cases? | 11 | I've seen a few people mention they are using SillyTavern and not Ooba.
Curious what use-cases are you using in Silly Tavern that are not available in Ooba? | 2023-07-06T05:42:18 | https://www.reddit.com/r/LocalLLaMA/comments/14rzdsk/sillytavern_usecases/ | robo_cap | self.LocalLLaMA | 2023-07-06T16:29:03 | 0 | {} | 14rzdsk | false | null | t3_14rzdsk | /r/LocalLLaMA/comments/14rzdsk/sillytavern_usecases/ | false | false | self | 11 | null |
after a bit of tweaking, i got gpt3clippy working via oobabooga | 3 | "just follow the errors until its fixed"
[using the openai extensions ofc](https://preview.redd.it/kiqaryf98aab1.png?width=1915&format=png&auto=webp&s=01a3ebdc9732d639082273d1b1503feeb8610399) | 2023-07-06T05:41:25 | https://www.reddit.com/r/LocalLLaMA/comments/14rzd7r/after_a_bit_of_tweaking_i_got_gpt3clippy_working/ | happydadinau | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 14rzd7r | false | null | t3_14rzd7r | /r/LocalLLaMA/comments/14rzd7r/after_a_bit_of_tweaking_i_got_gpt3clippy_working/ | false | false | 3 | null | |
Reproducing LLAMA or doing LoRa on large corpus of pirated books | 18 | I was thinking whether it's feasible to reproduce LAMA on new large corpuse of pirated books. I did LoRa experiments and it seems unlikely that it would scale beyond 100s of books well. If so, how much compute would I need to repruduce 7b model from skratch? | 2023-07-06T05:30:51 | https://www.reddit.com/r/LocalLLaMA/comments/14rz5p1/reproducing_llama_or_doing_lora_on_large_corpus/ | Itchy_Monk2686 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 14rz5p1 | false | null | t3_14rz5p1 | /r/LocalLLaMA/comments/14rz5p1/reproducing_llama_or_doing_lora_on_large_corpus/ | false | false | self | 18 | null |
LongNet: Scaling Transformers to 1,000,000,000 Tokens | 126 | [https://arxiv.org/pdf/2307.02486.pdf](https://arxiv.org/pdf/2307.02486.pdf) Yeeehaww | 2023-07-06T05:04:28 | https://www.reddit.com/r/LocalLLaMA/comments/14rym30/longnet_scaling_transformers_to_1000000000_tokens/ | iuwuwwuwuuwwjueej | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 14rym30 | false | null | t3_14rym30 | /r/LocalLLaMA/comments/14rym30/longnet_scaling_transformers_to_1000000000_tokens/ | false | false | self | 126 | null |
What's the most sophisticated offline chat LLM available now for either a Macbook M2 Max or a 3070ti GPU desktop I can run? | 10 | Please, I am begging you, help a fool out | 2023-07-06T04:19:33 | https://www.reddit.com/r/LocalLLaMA/comments/14rxnq7/whats_the_most_sophisticated_offline_chat_llm/ | Careful_Tower_5984 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 14rxnq7 | false | null | t3_14rxnq7 | /r/LocalLLaMA/comments/14rxnq7/whats_the_most_sophisticated_offline_chat_llm/ | false | false | self | 10 | null |
Can we train for lora with SuperHOT model | 3 | Hi guys,
I'm happy with the performance of the SUPERHOT version of vicuna model(I use this model:TheBloke/Vicuna-33B-1-3-SuperHOT-8K-fp16,and Bloke is a hero!), but I can't seem to find a way to train it(the textgen-webui shows LoRA training has only currently been validated for LLaMA,OPT,GPT-J,and GPT-NeoX models.(Fo... | 2023-07-06T03:41:57 | https://www.reddit.com/r/LocalLLaMA/comments/14rwue7/can_we_train_for_lora_with_superhot_model/ | baibaideyun | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 14rwue7 | false | null | t3_14rwue7 | /r/LocalLLaMA/comments/14rwue7/can_we_train_for_lora_with_superhot_model/ | false | false | self | 3 | null |
A Comparison of Large Language Models (LLMs) in Biomedical Domain | 60 | 2023-07-06T01:11:08 | https://provectus.com/blog/comparison-large-language-models-biomedical-domain/ | DarronFeldstein | provectus.com | 1970-01-01T00:00:00 | 0 | {} | 14rtg35 | false | null | t3_14rtg35 | /r/LocalLLaMA/comments/14rtg35/a_comparison_of_large_language_models_llms_in/ | false | false | 60 | {'enabled': False, 'images': [{'id': 'BH4nT_ARjSTG5EiwLpm_dYy4TBePmD2SqCfFdon59d4', 'resolutions': [{'height': 71, 'url': 'https://external-preview.redd.it/bWWW95gY_HusS7i11uG-DqBhSeW5TXDtxSooDr1p5uk.jpg?width=108&crop=smart&auto=webp&s=fd190d954899750bd6dc1628562f2551bb41f152', 'width': 108}, {'height': 143, 'url': 'h... | ||
Best option between 2x3060 or 1x3090. | 4 | The CUDA cores total comes to the same, the memory too.
Now that most a.i. programs can use multiple GPUs, I'm not sure who wins.
I've got a 3060 12gb and got a little play money (400$ USD).
My options are : sell my 3060 and buy a 3090 with the card money and money
Or:
Get another 3060 12gb because I have 2 pciE po... | 2023-07-06T00:06:09 | https://www.reddit.com/r/LocalLLaMA/comments/14rs0ko/best_option_between_2x3060_or_1x3090/ | oodelay | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 14rs0ko | false | null | t3_14rs0ko | /r/LocalLLaMA/comments/14rs0ko/best_option_between_2x3060_or_1x3090/ | false | false | self | 4 | null |
Tool for deploying open source LLMs on your own cloud | 86 | Hey all! I’ve been a long time lurker on the subreddit and wanted to share something that me and a friend built. We wanted to create apps on top of open source LLMs and struggled to set them up in our cloud environment efficiently. We realized that the tool we were building for this in itself would probably be pretty ... | 2023-07-05T23:22:48 | https://www.reddit.com/r/LocalLLaMA/comments/14rqyx8/tool_for_deploying_open_source_llms_on_your_own/ | torque-mcclyde | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 14rqyx8 | false | null | t3_14rqyx8 | /r/LocalLLaMA/comments/14rqyx8/tool_for_deploying_open_source_llms_on_your_own/ | false | false | self | 86 | {'enabled': False, 'images': [{'id': 'VmEI9xR7ThLUCoCQt_1r0IkPqbNd7G_2woLRY0qHRlA', 'resolutions': [{'height': 54, 'url': 'https://external-preview.redd.it/zE7ysnCouseCL3hmxQZMU1VQk2Q21s3-8ru_wFC0yWQ.jpg?width=108&crop=smart&auto=webp&s=b56200d611e5cb9e2c61a353771462fd0299a9f1', 'width': 108}, {'height': 108, 'url': 'h... |
A tool for fast inference running on your own cloud | 1 | Hey all! I’ve been a long time lurker on the subreddit and wanted to share something that me and a friend built. We wanted to create apps on top of open source LLMs and struggled to set them up in our cloud environment efficiently. We realized that the tool we were building for this in itself would probably be pretty ... | 2023-07-05T23:20:19 | https://www.reddit.com/r/LocalLLaMA/comments/14rqwk1/a_tool_for_fast_inference_running_on_your_own/ | torque-mcclyde | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 14rqwk1 | false | null | t3_14rqwk1 | /r/LocalLLaMA/comments/14rqwk1/a_tool_for_fast_inference_running_on_your_own/ | false | false | default | 1 | {'enabled': False, 'images': [{'id': 'VmEI9xR7ThLUCoCQt_1r0IkPqbNd7G_2woLRY0qHRlA', 'resolutions': [{'height': 54, 'url': 'https://external-preview.redd.it/zE7ysnCouseCL3hmxQZMU1VQk2Q21s3-8ru_wFC0yWQ.jpg?width=108&crop=smart&auto=webp&v=enabled&s=1fb8b582a80b4a6c8a94a1c876245c7d3359a1db', 'width': 108}, {'height': 108,... |
Haven: Easily run LLMs on inside your own cloud | 1 | [removed] | 2023-07-05T23:06:49 | https://www.reddit.com/r/LocalLLaMA/comments/14rqkhh/haven_easily_run_llms_on_inside_your_own_cloud/ | h-konsti | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 14rqkhh | false | null | t3_14rqkhh | /r/LocalLLaMA/comments/14rqkhh/haven_easily_run_llms_on_inside_your_own_cloud/ | false | false | default | 1 | {'enabled': False, 'images': [{'id': 'VmEI9xR7ThLUCoCQt_1r0IkPqbNd7G_2woLRY0qHRlA', 'resolutions': [{'height': 54, 'url': 'https://external-preview.redd.it/zE7ysnCouseCL3hmxQZMU1VQk2Q21s3-8ru_wFC0yWQ.jpg?width=108&crop=smart&auto=webp&v=enabled&s=1fb8b582a80b4a6c8a94a1c876245c7d3359a1db', 'width': 108}, {'height': 108,... |
A small llama.cpp server playground | 22 | ​
https://preview.redd.it/hl0tzxk008ab1.png?width=1337&format=png&auto=webp&s=5f37d2928ba12c9f0e9efc7013bc35e6728e8906
Hello People, i hope you are well.
I want to share a small fronted in which i have been working, made with Vue, is very simple and still under development due to the nature of the server.cpp.... | 2023-07-05T22:20:17 | https://www.reddit.com/r/LocalLLaMA/comments/14rpce2/a_small_llamacpp_server_playground/ | hwpoison | self.LocalLLaMA | 2023-07-05T23:51:17 | 0 | {} | 14rpce2 | false | null | t3_14rpce2 | /r/LocalLLaMA/comments/14rpce2/a_small_llamacpp_server_playground/ | false | false | 22 | {'enabled': False, 'images': [{'id': 'DJPqvteONpGwVVw6LzaG6b8vlDa2rv2hETCaqe0z57s', 'resolutions': [{'height': 54, 'url': 'https://external-preview.redd.it/ohwupr9MqnYXF974_2-gAgkZDuFxjDg48bFY3KdCQdc.jpg?width=108&crop=smart&auto=webp&s=b6caea286bbf31bdb473212eb5668f45376977be', 'width': 108}, {'height': 108, 'url': 'h... | |
Why does gpt 4 give me failed to load model? | 0 | C:\\Users\\Laptop\\Downloads\\Aishit\\LLama>main -i --interactive-first -r "### Human:" --temp 0 -c 2048 -n -1 --ignore-eos --repeat\_penalty 1.2 --instruct -m ggml-model-q4\_1.bin
main: build = 794 (ec326d3)
main: seed = 1688595156
llama.cpp: loading model from ggml-model-q4\_1.bin
error loading model: unexpected... | 2023-07-05T22:14:53 | https://www.reddit.com/r/LocalLLaMA/comments/14rp7d1/why_does_gpt_4_give_me_failed_to_load_model/ | Puzzleheaded-Nose-94 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 14rp7d1 | false | null | t3_14rp7d1 | /r/LocalLLaMA/comments/14rp7d1/why_does_gpt_4_give_me_failed_to_load_model/ | false | false | default | 0 | null |
Intel AI built into CPU's, is it at all useful for text or image generation? What is it? | 31 | Just noticed My CPU (12th gen) has what they call "Integrated AI" and even has "Intel® Gaussian & Neural Accelerator (Intel® GNA)" listed in the device manager.
See more here:
[https://www.intel.com/content/www/us/en/products/docs/processors/core/intelligent-pc-overview.html](https://www.intel.com/content/www/us/en/... | 2023-07-05T21:56:39 | https://www.reddit.com/r/LocalLLaMA/comments/14roq0p/intel_ai_built_into_cpus_is_it_at_all_useful_for/ | SGAShepp | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 14roq0p | false | null | t3_14roq0p | /r/LocalLLaMA/comments/14roq0p/intel_ai_built_into_cpus_is_it_at_all_useful_for/ | false | false | self | 31 | {'enabled': False, 'images': [{'id': '7wlnlsb1p8kqETD6MDhVPbujRAXC14mk8BJ3S2O8fCg', 'resolutions': [{'height': 71, 'url': 'https://external-preview.redd.it/Hlbf52-zMgk3lZiQPiNlVwXxuQqfSuHNMRFDsvyExVQ.jpg?width=108&crop=smart&auto=webp&s=6a95ee4184562ea6e68359542a9ba4fac4f67356', 'width': 108}, {'height': 142, 'url': 'h... |
Fine tuning Falcon 7B Instruct | 5 | I am trying to fine tune Falcon-7b-Instruct:
Modules: "query\_key\_value", "dense", "dense\_h\_to\_4h" and "dense\_4h\_to\_h") using peft-LoRA with 64,32 and 16 as ranks tried.
Dataset: 80 page FAQ dataset (structured as question-answer pairs. 280 in total)
I'm observing the following:
1. The model keeps rambling whi... | 2023-07-05T21:08:14 | https://www.reddit.com/r/LocalLLaMA/comments/14rnfzs/fine_tuning_falcon_7b_instruct/ | anindya_42 | self.LocalLLaMA | 2023-07-06T06:30:45 | 0 | {} | 14rnfzs | false | null | t3_14rnfzs | /r/LocalLLaMA/comments/14rnfzs/fine_tuning_falcon_7b_instruct/ | false | false | self | 5 | null |
Local LLaMa on Android phone | 70 | Wow! I just tried the 'server thats available in llama.cpp on my android phone, and its VERY user friendly. I can keep running this on the go for private chats. (for things that i can't use chatgpt :)
Steps:
1. Install termux from f-droid
2. Install gcc from its-pointless repo
3. compile llama.cpp using the following ... | 2023-07-05T21:04:50 | https://v.redd.it/vizurn39o7ab1 | AstrionX | v.redd.it | 1970-01-01T00:00:00 | 0 | {} | 14rncnb | false | {'reddit_video': {'bitrate_kbps': 4800, 'dash_url': 'https://v.redd.it/vizurn39o7ab1/DASHPlaylist.mpd?a=1692045165%2CZDVmYWY3YzU0YjIwYmMzYWJmMTBhZTUwNGNhMTEwNGZkNTdiMmFhYzMzMDU3OTY5NmJjNTMxYTRhM2E1NjU0Yg%3D%3D&v=1&f=sd', 'duration': 44, 'fallback_url': 'https://v.redd.it/vizurn39o7ab1/DASH_1080.mp4?source=fallback', 'h... | t3_14rncnb | /r/LocalLLaMA/comments/14rncnb/local_llama_on_android_phone/ | false | false | 70 | {'enabled': False, 'images': [{'id': 'aXM0Y25iMTlvN2FiMV3eHZlopqjlHOBu_t4lZJR4GWPFEVeS8als-ruFyBYQ', 'resolutions': [{'height': 216, 'url': 'https://external-preview.redd.it/aXM0Y25iMTlvN2FiMV3eHZlopqjlHOBu_t4lZJR4GWPFEVeS8als-ruFyBYQ.png?width=108&crop=smart&format=pjpg&auto=webp&s=3960d6409a2008b461e47572959266c5a4dd... | |
Considering migrating from Ubuntu 22.04 to Debian 12 | 1 | Hello,
I've been contemplating a switch from Ubuntu 22.04 to Debian 12 and would love to hear about your experiences, especially regarding running inferencing on GGML with full functionality, including GPU acceleration (CUDA).
Recently, I gave Fedora 38 a try, but unfortunately, I encountered compatibility issues wit... | 2023-07-05T20:31:11 | https://www.reddit.com/r/LocalLLaMA/comments/14rmfcm/considering_migrating_from_ubuntu_2204_to_debian/ | brunomoreirab | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 14rmfcm | false | null | t3_14rmfcm | /r/LocalLLaMA/comments/14rmfcm/considering_migrating_from_ubuntu_2204_to_debian/ | false | false | self | 1 | null |
Triton vs Llama.cpp? | 2 | Can anyone explain the difference to me? It seems, based on my very small understanding, that both options allow for a way to run inference on just a CPU? Are there any pros/cons?
For background, I'm looking into the best way to run various models like falcon or MPT in a datacenter cluster where we have "buckets of R... | 2023-07-05T20:10:24 | https://www.reddit.com/r/LocalLLaMA/comments/14rluww/triton_vs_llamacpp/ | SigmaSixShooter | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 14rluww | false | null | t3_14rluww | /r/LocalLLaMA/comments/14rluww/triton_vs_llamacpp/ | false | false | self | 2 | null |
Building a Professional QA Chatbot using 4xV100s | 3 | I'm seeking guidance from the community regarding the development of a professional QA chatbot. Due to the nature of my project, I am unable to use ChatGPT and instead require a private language model. I currently have 4xV100s at my disposal and I'm aiming to strike a balance between the speed of inferencing and the qu... | 2023-07-05T19:58:56 | https://www.reddit.com/r/LocalLLaMA/comments/14rljdd/building_a_professional_qa_chatbot_using_4xv100s/ | vinwizard | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 14rljdd | false | null | t3_14rljdd | /r/LocalLLaMA/comments/14rljdd/building_a_professional_qa_chatbot_using_4xv100s/ | false | false | self | 3 | null |
Issues using P40s | 5 | Hi, Im trying to get 2x P40s working on a Asus Z270-p. Ive got 4g decoding on, tried setting everything to gen2. I removed all the drives and m.2s. But it still wont post. If i remove either of the 2 cards it posts just fine and boots. But with 2 it refuses to do anything.
It doesnt matter which slot i use either. An... | 2023-07-05T19:25:28 | https://www.reddit.com/r/LocalLLaMA/comments/14rkncu/issues_using_p40s/ | ISwearImNotAnAI | self.LocalLLaMA | 2023-07-13T13:12:41 | 0 | {} | 14rkncu | false | null | t3_14rkncu | /r/LocalLLaMA/comments/14rkncu/issues_using_p40s/ | false | false | self | 5 | null |
How to create a LoRA from one book or group of tematic books | 3 | Hi! I am "half-newbie" in LLM, I know how to use (power user), install, solve basic problems and I have a basic knowledge in programming. I know how to use another type of AI too, the Stable Diffusion, I have been studying this program for over seven months. I fond the Oobabooga, KoboldAI and other programs and I think... | 2023-07-05T19:09:13 | https://www.reddit.com/r/LocalLLaMA/comments/14rk7g9/how_to_create_a_lora_from_one_book_or_group_of/ | Shadow_One111 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 14rk7g9 | false | null | t3_14rk7g9 | /r/LocalLLaMA/comments/14rk7g9/how_to_create_a_lora_from_one_book_or_group_of/ | false | false | self | 3 | null |
Training options for tasks unsupported by HF | 1 | Hugging face has a fairly limited number of tasks they support. Are there any other implementations of LoRA that people use where you can customize a bit more, changing final layer and loss function. | 2023-07-05T18:46:29 | https://www.reddit.com/r/LocalLLaMA/comments/14rjkim/training_options_for_tasks_unsupported_by_hf/ | Artistic_Load909 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 14rjkim | false | null | t3_14rjkim | /r/LocalLLaMA/comments/14rjkim/training_options_for_tasks_unsupported_by_hf/ | false | false | self | 1 | null |
Is it safe to delete these files in my local LLM folder? What am I losing if I get rid of the GIT folder entirely? I'm just a user of this stuff, not a developer. | 0 | ​
https://preview.redd.it/n5eina1mx6ab1.png?width=851&format=png&auto=webp&s=515f4fe032344c8d18fa325c6204550e157a355a | 2023-07-05T18:35:52 | https://www.reddit.com/r/LocalLLaMA/comments/14rj9vv/is_it_safe_to_delete_these_files_in_my_local_llm/ | cleverestx | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 14rj9vv | false | null | t3_14rj9vv | /r/LocalLLaMA/comments/14rj9vv/is_it_safe_to_delete_these_files_in_my_local_llm/ | false | false | 0 | null | |
HuggingChatAllInOne: Run HF and GPTQ models using HuggingChat UI easily | 6 | [HuggingChatAllInOne](https://github.com/bodaay/HuggingChatAllInOne)
Hey everyone,
The main goal of this repo is to make it super easy for anyone to get HuggingChat running as a UI and text-generation inference server, all in one Docker file. I've also included runpods templates to make launching these even easier.
... | 2023-07-05T18:16:47 | https://www.reddit.com/r/LocalLLaMA/comments/14riqo5/huggingchatallinone_run_hf_and_gptq_models_using/ | bodaaay | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 14riqo5 | false | null | t3_14riqo5 | /r/LocalLLaMA/comments/14riqo5/huggingchatallinone_run_hf_and_gptq_models_using/ | false | false | 6 | {'enabled': False, 'images': [{'id': 'JpVrs0sCIibdEY5Co5OrLqyeeam7AaElRlena8NUxso', 'resolutions': [{'height': 54, 'url': 'https://external-preview.redd.it/zsUwsk7z94weoTmWAWT-oOlXDwqbNZa7DLFiIWINhvc.jpg?width=108&crop=smart&auto=webp&s=b372cbcc0a14432f8758f0ff5be2d8bbed44848b', 'width': 108}, {'height': 108, 'url': 'h... | |
SillyTavern 1.8 released! | 100 | 2023-07-05T18:08:19 | https://github.com/SillyTavern/SillyTavern/releases | WolframRavenwolf | github.com | 1970-01-01T00:00:00 | 0 | {} | 14riib1 | false | null | t3_14riib1 | /r/LocalLLaMA/comments/14riib1/sillytavern_18_released/ | false | false | 100 | {'enabled': False, 'images': [{'id': 'bDW7jyCB5L7RKBwRUqrzWSn3bIb_Szu_GogYRebiCjw', 'resolutions': [{'height': 54, 'url': 'https://external-preview.redd.it/NFgRhAZ_cgs4xao5V1cOWNjptqU5JwIiGBtsvOdhlPU.jpg?width=108&crop=smart&auto=webp&s=22d2e1896c94ecebda58fed69478453d4b16fd4f', 'width': 108}, {'height': 108, 'url': 'h... | ||
How Processing Prompt Works [BLAS]? | 1 | Explain why this Processing Prompt \[BLAS\] (1024 / 1204 tokens) occurs on every request. because of this, the response time is about 400 seconds. how to reduce it?
https://preview.redd.it/z6me60ydp6ab1.png?width=960&format=png&auto=webp&s=501a74548fcdf5ea92b18f172a6599bd29c06623 | 2023-07-05T17:49:49 | https://www.reddit.com/r/LocalLLaMA/comments/14rhyv2/how_processing_prompt_works_blas/ | roman1338sf | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 14rhyv2 | false | null | t3_14rhyv2 | /r/LocalLLaMA/comments/14rhyv2/how_processing_prompt_works_blas/ | false | false | 1 | null | |
Expanding LLM Context Window | 22 | Spent the day off yesterday diving into how Position Interpolation works and made a quick writeup. These are the main benefits:
* With only 1000 training steps, the context window for LLaMA models ranging in size from 7B to 65B was extended **from 2048 tokens to** **32768 tokens.**
* Model quality is preserved for... | 2023-07-05T17:37:05 | https://www.reddit.com/r/LocalLLaMA/comments/14rhmh7/expanding_llm_context_window/ | No-Butterscotch-6654 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 14rhmh7 | false | null | t3_14rhmh7 | /r/LocalLLaMA/comments/14rhmh7/expanding_llm_context_window/ | false | false | self | 22 | {'enabled': False, 'images': [{'id': '1PHN92PLkTXF0w6hSsddwd0MiEoiT335FbY3YGQDzwk', 'resolutions': [{'height': 57, 'url': 'https://external-preview.redd.it/hiSxnz13VpRhICMQat5lA6nbc5xWZgJGblM2hqQ5viY.jpg?width=108&crop=smart&auto=webp&s=941d3dba1d0b9bbcfff7277e0c176792002d435d', 'width': 108}, {'height': 114, 'url': 'h... |
What am I doing wrong with WizardCoder-15B-v1.0??? | 4 | I can't for the life of me get any sensible code from this model.
I'm using oobabooga as the front end and the instruct prompt is the standard Llama ### Instruct: ### Response: , but when I ask it to generate extremely simple code it just spits out insane levels of garbage. For example:
write python code that... | 2023-07-05T17:14:18 | https://www.reddit.com/r/LocalLLaMA/comments/14rgyty/what_am_i_doing_wrong_with_wizardcoder15bv10/ | GeeBee72 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 14rgyty | false | null | t3_14rgyty | /r/LocalLLaMA/comments/14rgyty/what_am_i_doing_wrong_with_wizardcoder15bv10/ | false | false | self | 4 | null |
Flan-Open-Llama-13B | 19 | 2023-07-05T16:16:40 | https://twitter.com/enricoshippole/status/1676624675030401026?s=46&t=4Lg1z9tXUANCKLiHwRSk_A | Acrobatic-Site2065 | twitter.com | 1970-01-01T00:00:00 | 0 | {} | 14rfam5 | false | {'oembed': {'author_name': 'Enrico Shippole', 'author_url': 'https://twitter.com/EnricoShippole', 'cache_age': 3153600000, 'height': None, 'html': '<blockquote class="twitter-video"><p lang="en" dir="ltr">Releasing Flan-Open-Llama-13b, an OpenLLaMA model fine-tuned on the FLAN instruction dataset. <a href="https://t.co... | t3_14rfam5 | /r/LocalLLaMA/comments/14rfam5/flanopenllama13b/ | false | false | 19 | {'enabled': False, 'images': [{'id': '9bLRg0I8ZS0XoyaiPFyy_-25YZBXFO1U_UBMsP36La8', 'resolutions': [{'height': 108, 'url': 'https://external-preview.redd.it/F5zgOKEBW2GfhMHZiuO6Ny9TfMAULpr8mFXV-Sm2Yoc.jpg?width=108&crop=smart&auto=webp&s=7ee521093583c9b8c452daaa361258c69e9185cf', 'width': 108}], 'source': {'height': 14... | ||
Does ExLlama not truncate the prompt length? | 10 | I have a 3090. I am currently running a superhot model using 3840 max_seq_len /2 compress_pos_emb
It seems to work but if I go over the prompt limit, I get the following error:
RuntimeError: start (0) + length (3841) exceeds dimension size (3840).
I'm not sure why this is a problem. There's a setting in text-gen... | 2023-07-05T15:50:23 | https://www.reddit.com/r/LocalLLaMA/comments/14rejf6/does_exllama_not_truncate_the_prompt_length/ | zippyfan | self.LocalLLaMA | 2023-07-05T16:06:35 | 0 | {} | 14rejf6 | false | null | t3_14rejf6 | /r/LocalLLaMA/comments/14rejf6/does_exllama_not_truncate_the_prompt_length/ | false | false | self | 10 | null |
GPT4 for data annotation | 1 |
I am trying to use GPT4/GPT3.5 for data annotation to prepare a supposed gold standard data to train my own smaller models (like Orca), and I am unable to. Most times, it does not even return valid JSON. Even if it does, it does not give consistent results even if I set temperature to zero. There are times it i... | 2023-07-05T12:29:32 | https://www.reddit.com/r/LocalLLaMA/comments/14r9awd/gpt4_for_data_annotation/ | mr_dark_matter | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 14r9awd | false | null | t3_14r9awd | /r/LocalLLaMA/comments/14r9awd/gpt4_for_data_annotation/ | false | false | default | 1 | null |
Deploying models on HuggingFace | 1 | Sorry if this has been asked before: I'd like to deploy conversationals LLMs with HuggingFace (I'm looking for cheaper GPT3.5 replacements, and I a willing to take a drop in answer quality).
However mosts models I'm considering need large amounts of memory (for example, TheBloke/vicuna-13B-1.1-HF requires 26GB). ... | 2023-07-05T10:31:20 | https://www.reddit.com/r/LocalLLaMA/comments/14r6uhx/deploying_models_on_huggingface/ | Lesterpaintstheworld | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 14r6uhx | false | null | t3_14r6uhx | /r/LocalLLaMA/comments/14r6uhx/deploying_models_on_huggingface/ | false | false | default | 1 | null |
Help presenting key differences between two different versions of a document | 10 | Hey,
not sure if LLM would suit the best, but basicly i would like to get the key differences between two different versions of our terms and conditions, each being some 5 pages long so I don’t think feeding it to GPT via API is an option for example, i haven’t tinkered with LLMs locally (yet) but as I am building an ... | 2023-07-05T09:08:08 | https://www.reddit.com/r/LocalLLaMA/comments/14r57nk/help_presenting_key_differences_between_two/ | MRWONDERFU | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 14r57nk | false | null | t3_14r57nk | /r/LocalLLaMA/comments/14r57nk/help_presenting_key_differences_between_two/ | false | false | self | 10 | null |
how to distill llm's in-context learning ,any suggestions? | 1 | **how to distill llm's in-context learning ,any suggestions?** | 2023-07-05T09:04:46 | https://www.reddit.com/r/LocalLLaMA/comments/14r55b7/how_to_distill_llms_incontext_learning_any/ | MousaicFall | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 14r55b7 | false | null | t3_14r55b7 | /r/LocalLLaMA/comments/14r55b7/how_to_distill_llms_incontext_learning_any/ | false | false | default | 1 | null |
Orca mini 3B is, as you might expect, not a genius level intellect | 63 | ​
[I tried to write a little program that uses llama.cpp to generate writing samples, for reasons. It has successfully written hundreds of essays already, but occasionally it just refuses for dumb reasons.](https://preview.redd.it/ggsc77g1n3ab1.png?width=1741&format=png&auto=webp&s=047ae275d8fb28d4afe0465217d94... | 2023-07-05T07:41:00 | https://www.reddit.com/r/LocalLLaMA/comments/14r3lhe/orca_mini_3b_is_as_you_might_expect_not_a_genius/ | Robot_Graffiti | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 14r3lhe | false | null | t3_14r3lhe | /r/LocalLLaMA/comments/14r3lhe/orca_mini_3b_is_as_you_might_expect_not_a_genius/ | false | false | 63 | null | |
prompting orca-mini-v2_7b.ggmlv3.q8_0.bin | 7 | It didn't quite get the answer correct to the problem:
[https://paste.c-net.org/SuggestVance](https://paste.c-net.org/SuggestVance)
I told it to "think through step by step" and set temperature to 0.
Can someone give me tips to get better results from this model? thanks | 2023-07-05T06:55:35 | https://www.reddit.com/r/LocalLLaMA/comments/14r2r15/prompting_orcaminiv2_7bggmlv3q8_0bin/ | dewijones92 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 14r2r15 | false | null | t3_14r2r15 | /r/LocalLLaMA/comments/14r2r15/prompting_orcaminiv2_7bggmlv3q8_0bin/ | false | false | self | 7 | null |
How do you choose LLM for local inference? | 5 | What criteria do you use to select the most appropriate LLMs for local inference? Is there a specific LLM architecture you prefer? Do you consider support for CUDA/Metal? What about the quantization size or the amount of RAM required?
Which of these (or any other) factors are the most crucial to your selection process... | 2023-07-05T06:47:27 | https://www.reddit.com/r/LocalLLaMA/comments/14r2ljj/how_do_you_choose_llm_for_local_inference/ | Greg_Z_ | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 14r2ljj | false | null | t3_14r2ljj | /r/LocalLLaMA/comments/14r2ljj/how_do_you_choose_llm_for_local_inference/ | false | false | self | 5 | null |
What is the best text web ui currently? | 32 | anyone know what has the most models supported & fastest web ui? or atleast what everyone is using. Ive seen [https://github.com/oobabooga/text-generation-webui](https://github.com/oobabooga/text-generation-webui) and [https://github.com/ParisNeo/lollms-webui](https://github.com/ParisNeo/lollms-webui).
im wonderin... | 2023-07-05T04:39:42 | https://www.reddit.com/r/LocalLLaMA/comments/14r0ar1/what_is_the_best_text_web_ui_currently/ | ArrodesDev | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 14r0ar1 | false | null | t3_14r0ar1 | /r/LocalLLaMA/comments/14r0ar1/what_is_the_best_text_web_ui_currently/ | false | false | self | 32 | {'enabled': False, 'images': [{'id': '0Mf47iIzydtRJnU06dNsQpHHYsNgVZDQKhZB6wz-XK0', 'resolutions': [{'height': 54, 'url': 'https://external-preview.redd.it/tKzDrXC-irF0dIy-F4Sw2BKUGKg2LT-wl7YAeU6WJtA.jpg?width=108&crop=smart&auto=webp&s=feebb78e5768ba366d52d83bf17c105afd5fc4c4', 'width': 108}, {'height': 108, 'url': 'h... |
Experimental open-source interface for interacting with various generative neural networks. | 32 | 2023-07-05T04:02:28 | https://www.reddit.com/gallery/14qzm0f | Svgsprite | reddit.com | 1970-01-01T00:00:00 | 0 | {} | 14qzm0f | false | null | t3_14qzm0f | /r/LocalLLaMA/comments/14qzm0f/experimental_opensource_interface_for_interacting/ | false | false | 32 | null | ||
I am having some issues with ooba | 1 | When loading a ggml model, the command line used to show something like "gpu accelerated", but now I'm not seeing that anymore. Also, it seems that when I unload a model, it stays in ram.
Should I do a reinstall? Any other suggestions?
​
2023-07-04 22:21:51 INFO:llama.cpp weights detected: models\TheBlok... | 2023-07-05T03:25:05 | https://www.reddit.com/r/LocalLLaMA/comments/14qyx94/i_am_having_some_issues_with_ooba/ | L_vE_scRmBLd_wRds | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 14qyx94 | false | null | t3_14qyx94 | /r/LocalLLaMA/comments/14qyx94/i_am_having_some_issues_with_ooba/ | false | false | default | 1 | null |
Local training 2GPU methods and benchmarks, with/without NVlink | 12 | Curious if anyone has has trained models that don’t fit on one GPU.
My understanding is there are a few methods to do this:
PP- pipeline parallelism
ZeRO
TP - tensor parallelism
According to hugging face these should be about the same with NVlink and PP should be the fastest without. I haven’t seen solid benchmark... | 2023-07-05T03:03:22 | https://www.reddit.com/r/LocalLLaMA/comments/14qyief/local_training_2gpu_methods_and_benchmarks/ | Artistic_Load909 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 14qyief | false | null | t3_14qyief | /r/LocalLLaMA/comments/14qyief/local_training_2gpu_methods_and_benchmarks/ | false | false | self | 12 | null |
CPU Inference Time Falcon-7b | 5 | I'm having a hard time understanding inference time on CPU. Could someone guide me on how to estimate inference time for max_length=2048, k=10, do_sample=True? I need to run this on a notebook. Here are my laptop specs:
Intel 11th Gen i7-11800H @ 2.30Ghz 16 Cpus ~ 2.3Ghz 32GB RAM. My GPU is NVIDIA GeForce RTX 3060 Lap... | 2023-07-05T03:03:18 | https://www.reddit.com/r/LocalLLaMA/comments/14qyics/cpu_inference_time_falcon7b/ | Reasonable-Bowler-54 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 14qyics | false | null | t3_14qyics | /r/LocalLLaMA/comments/14qyics/cpu_inference_time_falcon7b/ | false | false | self | 5 | null |
When you train a LoRA at 256 token cutoff length/context window, what does that mean for its behavior? | 7 | I know that the training process itself is only going to look at 256 token chunks at once, and the typical llama model is trained/finetuned at 2048 token context. I've read that the behavior of a LoRA trained with 256 cutoff length/token context also suffers from that limitation, and it can't "see" beyond the 256 token... | 2023-07-04T23:24:55 | https://www.reddit.com/r/LocalLLaMA/comments/14qu6nz/when_you_train_a_lora_at_256_token_cutoff/ | SoylentMithril | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 14qu6nz | false | null | t3_14qu6nz | /r/LocalLLaMA/comments/14qu6nz/when_you_train_a_lora_at_256_token_cutoff/ | false | false | self | 7 | null |
Isn't GPT-2 enough for most tasks nowadays? Why should I use a really large model? | 1 | [removed] | 2023-07-04T21:53:05 | https://www.reddit.com/r/LocalLLaMA/comments/14qs4vh/isnt_gpt2_enough_for_most_tasks_nowadays_why/ | nderstand2grow | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 14qs4vh | false | null | t3_14qs4vh | /r/LocalLLaMA/comments/14qs4vh/isnt_gpt2_enough_for_most_tasks_nowadays_why/ | false | false | default | 1 | null |
CPU or GPU for inference only ? | 5 | Hey, I'm currently thinking of building something to do inference only with LLMs.
Does a GPU make a difference or can I run using only a CPU ?
Do you think the new am5/ddr5 combo is more relevant for this kind of tasks than am4/ddr4?
Also if I want to use diffusion models for image generation, is a GPU required ?
M... | 2023-07-04T21:46:05 | https://www.reddit.com/r/LocalLLaMA/comments/14qryw5/cpu_or_gpu_for_inference_only/ | 1PLSXD | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 14qryw5 | false | null | t3_14qryw5 | /r/LocalLLaMA/comments/14qryw5/cpu_or_gpu_for_inference_only/ | false | false | self | 5 | null |
I measured the effect of RAM overclocking on LLM speed. | 57 | I tested, how RAM speed affects generation speed. In short, 11% increase in RAM frequency leads to 6% increase in generation speed. The details follow:
The test setup was AMD Ryzen 9 3950X and 64Gb RAM (Kingston Renegate)
I started the model like this: `.\koboldcpp.exe --model airoboros-65b-gpt4-1.4.ggmlv3.q5_K_M.b... | 2023-07-04T21:34:50 | https://www.reddit.com/r/LocalLLaMA/comments/14qrp0s/i_measured_the_effect_of_ram_overclocking_on_llm/ | Barafu | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 14qrp0s | false | null | t3_14qrp0s | /r/LocalLLaMA/comments/14qrp0s/i_measured_the_effect_of_ram_overclocking_on_llm/ | false | false | self | 57 | null |
Huggingface alternative | 39 | I'm currently downloading a model from huggingface with 200 KB/s. It should be 100x as fast. Has anybody experienced that? Does anyone download their LLMs from a different source? I've recently stumbled upon [ai.torrents.luxe](https://ai.torrents.luxe) but it's not up to date and lacks many (especially ggml) models.
... | 2023-07-04T18:43:14 | https://www.reddit.com/r/LocalLLaMA/comments/14qncmy/huggingface_alternative/ | Mefi282 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 14qncmy | false | null | t3_14qncmy | /r/LocalLLaMA/comments/14qncmy/huggingface_alternative/ | false | false | self | 39 | null |
How many of you built a rig specifically to self host LLMs as a hobby? | 214 | So, I am curious how many folks have invested in hardware to run local LLMs. I am not talking about ML/AI pros who work for tech companies and who buy this stuff anyway to earn living--talking about hobbyists: what are your use cases and do you feel it was worth it?
Building a home server right now, and was curious if... | 2023-07-04T18:12:34 | https://www.reddit.com/r/LocalLLaMA/comments/14qmk3v/how_many_of_you_built_a_rig_specifically_to_self/ | Infinite100p | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 14qmk3v | false | null | t3_14qmk3v | /r/LocalLLaMA/comments/14qmk3v/how_many_of_you_built_a_rig_specifically_to_self/ | false | false | self | 214 | null |
How does LLaMA.cpp run on the CPU? | 1 | [removed] | 2023-07-04T18:11:54 | https://www.reddit.com/r/LocalLLaMA/comments/14qmji1/how_does_llamacpp_run_on_the_cpu/ | Frequent-Let-7893 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 14qmji1 | false | null | t3_14qmji1 | /r/LocalLLaMA/comments/14qmji1/how_does_llamacpp_run_on_the_cpu/ | false | false | default | 1 | null |
Did anyone try to benchmark LLM's for coding against each other and against proprietary ones like Copilot X? | 18 | Curious what the state of open source LLMs vs closed ones is right now.
E.g., how does starcoder compare against Copilot? | 2023-07-04T18:08:42 | https://www.reddit.com/r/LocalLLaMA/comments/14qmggp/did_anyone_try_to_benchmark_llms_for_coding/ | Infinite100p | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 14qmggp | false | null | t3_14qmggp | /r/LocalLLaMA/comments/14qmggp/did_anyone_try_to_benchmark_llms_for_coding/ | false | false | self | 18 | null |
How does LLaMA.cpp run on the CPU? | 1 | [removed] | 2023-07-04T17:51:36 | https://www.reddit.com/r/LocalLLaMA/comments/14qm063/how_does_llamacpp_run_on_the_cpu/ | Old-Leadership-3316 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 14qm063 | false | null | t3_14qm063 | /r/LocalLLaMA/comments/14qm063/how_does_llamacpp_run_on_the_cpu/ | false | false | default | 1 | null |
[Discussion] Is the OpenLLM Leaderboard not reliable? (https://huggingface.co/blog/evaluating-mmlu-leaderboard) | 2 | After the recent discussion, that showed the MMLU evaluation numbers of the current top model (Falcon-40B) on the leaderboard were were significantly lower than the numbers in the [published LLaMa paper](https://arxiv.org/abs/2302.13971). There are serious doubts whether other scores in the leaderboard also have the... | 2023-07-04T17:37:16 | https://www.reddit.com/r/LocalLLaMA/comments/14qln89/discussion_is_the_openllm_leaderboard_not/ | awinml1 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 14qln89 | false | null | t3_14qln89 | /r/LocalLLaMA/comments/14qln89/discussion_is_the_openllm_leaderboard_not/ | false | false | self | 2 | {'enabled': False, 'images': [{'id': 'q3evP6JeDpAC2MdSQHWYxnCYTqbJkElIQsLFqVSdkss', 'resolutions': [{'height': 63, 'url': 'https://external-preview.redd.it/0HhwdU6MKIAKjL9Y8-B_iH374a3NiPTy0ib8lmloRzA.jpg?width=108&crop=smart&auto=webp&s=2711d572cfc6c713893cf24e8c4a7344d5ad8a4c', 'width': 108}, {'height': 126, 'url': 'h... |
Prompting tips for short outputs. | 2 | I'm building a voice assistant program that allows you to speak your commands into a microphone and hear a spoken response from your AI assistant. It's moving along well, however one issue is that I suffer from long speech generation times while using tortoise-tts-fast, (which is expected). I'd like to speed up my exec... | 2023-07-04T16:56:24 | https://www.reddit.com/r/LocalLLaMA/comments/14qkkq2/prompting_tips_for_short_outputs/ | yeetblaster | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 14qkkq2 | false | null | t3_14qkkq2 | /r/LocalLLaMA/comments/14qkkq2/prompting_tips_for_short_outputs/ | false | false | self | 2 | null |
How can I make my LLaMA 13b model to initiate conversations and kept conversation alive? | 22 | I need some help with my LLaMA 13b model, which I've finetuned to be girlfriend. problem is conversation run dry pretty quick cause i don't khow how to talk to girl
Here are a few specific questions I have:
​
1. How can I encourage my LLaMA 13b model to initiate conversations ? Are there any specific promp... | 2023-07-04T16:01:35 | https://www.reddit.com/r/LocalLLaMA/comments/14qj4y3/how_can_i_make_my_llama_13b_model_to_initiate/ | catgirl_code_in_lisp | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 14qj4y3 | false | null | t3_14qj4y3 | /r/LocalLLaMA/comments/14qj4y3/how_can_i_make_my_llama_13b_model_to_initiate/ | false | false | self | 22 | null |
Would a vram pcie expansion card be possible in the future? | 1 | Edit: OK clearly this wasn't a good idea, but thank you to everyone who commented. I've learned a lot and these was some interesting bits of technical knowledge shared. I'll leave this up for anyone who has a similar idea and wants to learn. Original post below.
Obviously there might not be a huge market for it so ... | 2023-07-04T15:43:30 | https://www.reddit.com/r/LocalLLaMA/comments/14qinru/would_a_vram_pcie_expansion_card_be_possible_in/ | TheSilentFire | self.LocalLLaMA | 2023-07-04T19:05:35 | 0 | {} | 14qinru | false | null | t3_14qinru | /r/LocalLLaMA/comments/14qinru/would_a_vram_pcie_expansion_card_be_possible_in/ | false | false | self | 1 | null |
If you owned a nvidia tesla a100, what would you do with it? | 19 | I see a lot of people interested in hosting local LLMs but I’m very curious if you had one of these and the hardware wouldn’t be a limit, what would build/do.
Seriously replies please! | 2023-07-04T15:16:18 | https://www.reddit.com/r/LocalLLaMA/comments/14qhz3h/if_you_owned_a_nvidia_tesla_a100_what_would_you/ | mehrdotcom | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 14qhz3h | false | null | t3_14qhz3h | /r/LocalLLaMA/comments/14qhz3h/if_you_owned_a_nvidia_tesla_a100_what_would_you/ | false | false | self | 19 | null |
Retrieving a list of movies from a natural language query, given their plots | 2 | Hi All,
I have a requirement to develop an application, which requires me to retrieve a list of movies based on a user query. I also need all models that I will be using, to run locally on my computer.
I have a dataset of around 1000 movies, and their corresponding plots. The plots are of 3-4 lines of length. The qu... | 2023-07-04T14:30:32 | https://www.reddit.com/r/LocalLLaMA/comments/14qgs2e/retrieving_a_list_of_movies_from_a_natural/ | jlteja | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 14qgs2e | false | null | t3_14qgs2e | /r/LocalLLaMA/comments/14qgs2e/retrieving_a_list_of_movies_from_a_natural/ | false | false | self | 2 | null |
How To Fine-Tune LLaMA, OpenLLaMA, And XGen, With JAX On A GPU Or A TPU | 17 | Hello,
Fine-tuning your own large language model is the best way to achieve state-of-the-art results, even better than ChatGPT or GPT-4, especially if you fine-tune a modern AI model like LLaMA, OpenLLaMA, or XGen.
Properly fine-tuning these models is not necessarily easy though, so I made an A to Z tutorial abo... | 2023-07-04T14:26:32 | https://www.reddit.com/r/LocalLLaMA/comments/14qgohb/how_to_finetune_llama_openllama_and_xgen_with_jax/ | juliensalinas | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 14qgohb | false | null | t3_14qgohb | /r/LocalLLaMA/comments/14qgohb/how_to_finetune_llama_openllama_and_xgen_with_jax/ | false | false | self | 17 | {'enabled': False, 'images': [{'id': 'LhzkLCKLhtqmDpjqTfdfMYtWTvHTU-ULOR5ZfOPggsw', 'resolutions': [{'height': 108, 'url': 'https://external-preview.redd.it/Ihxn5Je-rcWPIGyfcNZe7ZigQLSf-yKerNwlruBPEUE.jpg?width=108&crop=smart&auto=webp&s=d7d7a562c243abdc8b5ca815ce970a7cd2532531', 'width': 108}, {'height': 216, 'url': '... |
Nuggt: A LLM Agent that runs on Wizcoder-15B (4-bit Quantised). It's time to democratise LLM Agents | 155 | Well I dont know where to begin... Last month I started on this project called Nuggt because I was fed-up with how all the autonomous agents out there require GPT-4 (at least 3 months ago) and GPT-4 is expensive and I didnt have no API keys at that time. So I wanted to create something with GPT-3.5 and thats when this ... | 2023-07-04T12:50:57 | https://www.reddit.com/r/LocalLLaMA/comments/14qednx/nuggt_a_llm_agent_that_runs_on_wizcoder15b_4bit/ | Loya_3005 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 14qednx | false | null | t3_14qednx | /r/LocalLLaMA/comments/14qednx/nuggt_a_llm_agent_that_runs_on_wizcoder15b_4bit/ | false | false | 155 | {'enabled': False, 'images': [{'id': 'Px_pkg6B-CL-cuOhDnXAiLZ5A9nyK3QroLHFscu3fS4', 'resolutions': [{'height': 54, 'url': 'https://external-preview.redd.it/qPST_FVnNqkhdZxixTB8Z74UA_F55MjG5Ueogh-J0Ks.jpg?width=108&crop=smart&auto=webp&v=enabled&s=3708da66faca8e494f21da75157764129c3b43d8', 'width': 108}, {'height': 108,... | |
torch.cuda.outofMemoryError need help | 2 | Hi everyone,
i am currently trying to use localGPT for a project and i encountered a problem.
Basically i have two setup :
\- my home setup with : i5 8600K, 32Gb DDR4 and an RTX 2080
\- my work setup with : i7 8700k , 128Gb DDR4 and an Nvidia A2
in both setup localGPT was installed the same way and ... | 2023-07-04T11:30:40 | https://www.reddit.com/r/LocalLLaMA/comments/14qcqlw/torchcudaoutofmemoryerror_need_help/ | Assasinshock | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 14qcqlw | false | null | t3_14qcqlw | /r/LocalLLaMA/comments/14qcqlw/torchcudaoutofmemoryerror_need_help/ | false | false | self | 2 | null |
Can I combine two RTX 3060 12 GB to reach 24 GB VRAM? | 16 | So there is the question already.
Could I then fit a 30 B LLaMA model inside (let's say GPTQ loading with ExLlama) or would it still consider it as 12 GB for some reason? Does anybody has experience with this kind of setup? (I'm not talking about playing games with both cards, I know that SLI or NVlink is not supporte... | 2023-07-04T11:18:26 | https://www.reddit.com/r/LocalLLaMA/comments/14qchl1/can_i_combine_two_rtx_3060_12_gb_to_reach_24_gb/ | psi-love | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 14qchl1 | false | null | t3_14qchl1 | /r/LocalLLaMA/comments/14qchl1/can_i_combine_two_rtx_3060_12_gb_to_reach_24_gb/ | false | false | self | 16 | null |
My custom trained LoRa, showing funny results, and it keeps format of dataset's text which is good. | 24 | ​
[Funny results](https://preview.redd.it/lj5x2w1hww9b1.png?width=1410&format=png&auto=webp&s=6a3b5ac3cbfa5c6948e2d7bdebb07d28ac035903)
I have written in [my previous post](https://www.reddit.com/r/LocalLLaMA/comments/14oib8x/how_to_properly_format_data_for_lora_training/) , I trained LoRa with formatted text.... | 2023-07-04T09:00:43 | https://www.reddit.com/r/LocalLLaMA/comments/14q9tl0/my_custom_trained_lora_showing_funny_results_and/ | DaniyarQQQ | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 14q9tl0 | false | null | t3_14q9tl0 | /r/LocalLLaMA/comments/14q9tl0/my_custom_trained_lora_showing_funny_results_and/ | false | false | 24 | null | |
Local LLMs GPUs | 1 |
I have a AWS EC-2 with Tesla V-100. I am not able to figure out which LOCAL LLM can leverage this. I need it to answer questions based on my docs. Any tuts or articles, you guys can point me to? | 2023-07-04T07:47:39 | https://www.reddit.com/r/LocalLLaMA/comments/14q8hqg/local_llms_gpus/ | Assholefrmcoinexchan | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 14q8hqg | false | null | t3_14q8hqg | /r/LocalLLaMA/comments/14q8hqg/local_llms_gpus/ | false | false | self | 1 | null |
Llama33B vs Falcon40B vs MPT30B | 8 | Since these models are relatively in a similar range in terms of parameters, it will be good to have a discussion on their capabilities and comparison with each other.
I think it will be a good help for all starting out and wondering about these models, which one to use, if we can share our experiences with these ... | 2023-07-04T07:43:47 | https://www.reddit.com/r/LocalLLaMA/comments/14q8fb0/llama33b_vs_falcon40b_vs_mpt30b/ | Raise_Fickle | self.LocalLLaMA | 2023-07-04T08:24:54 | 0 | {} | 14q8fb0 | false | null | t3_14q8fb0 | /r/LocalLLaMA/comments/14q8fb0/llama33b_vs_falcon40b_vs_mpt30b/ | false | false | self | 8 | null |
oobabooga Update broke loading u/The-Bloke huggingface models? | 5 | Might just be user error but I have been using Runpod and [u/The-Bloke](https://www.reddit.com/u/The-Bloke/) 's brilliant "RunPod TheBloke LLMs" template to easily and cheaply run LLMs for my pleasure.
​
Just today on loading up the template oobabooga seems to have updated and now I cannot load any model from... | 2023-07-04T07:39:34 | https://www.reddit.com/r/LocalLLaMA/comments/14q8co0/oobabooga_update_broke_loading_uthebloke/ | shzam123 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 14q8co0 | false | null | t3_14q8co0 | /r/LocalLLaMA/comments/14q8co0/oobabooga_update_broke_loading_uthebloke/ | false | false | self | 5 | null |
Orca-Mini-V2-7b | 121 | Today I released Orca-Mini-V2-7b
[https://huggingface.co/psmathur/orca\_mini\_v2\_7b](https://huggingface.co/psmathur/orca_mini_v2_7b)
This is an **Uncensored** LLaMA-7b model build in collaboration with [**Eric Hartford**](https://huggingface.co/ehartford). This is trained on explain tuned datasets, created usin... | 2023-07-04T06:18:44 | https://www.reddit.com/r/LocalLLaMA/comments/14q6vb5/orcaminiv27b/ | Remarkable-Spite-107 | self.LocalLLaMA | 2023-07-04T15:40:59 | 0 | {} | 14q6vb5 | false | null | t3_14q6vb5 | /r/LocalLLaMA/comments/14q6vb5/orcaminiv27b/ | false | false | 121 | {'enabled': False, 'images': [{'id': '1uGbV5HvP41r5yFPi4ITJNR7v4Gxs8IFOGL2--WjGco', 'resolutions': [{'height': 31, 'url': 'https://external-preview.redd.it/La5WIG1yXSEdA3CzXY7HM1Y_xUnL0pBSsC2wReHDPkg.png?width=108&crop=smart&auto=webp&s=fb2779db0eacc5e7fdee47db9d2a6d10cdef4acf', 'width': 108}, {'height': 63, 'url': 'ht... | |
I made a cyber-dog character with Pygmalion, and she got a little weird | 0 | [deleted] | 2023-07-04T05:46:57 | https://www.reddit.com/gallery/14q6a0h | bigorders | reddit.com | 1970-01-01T00:00:00 | 0 | {} | 14q6a0h | false | null | t3_14q6a0h | /r/LocalLLaMA/comments/14q6a0h/i_made_a_cyberdog_character_with_pygmalion_and/ | false | false | 0 | null | |
I made a cyber-dog character, and she got a little weird | 1 | [deleted] | 2023-07-04T05:44:50 | [deleted] | 1970-01-01T00:00:00 | 0 | {} | 14q68lg | false | null | t3_14q68lg | /r/LocalLLaMA/comments/14q68lg/i_made_a_cyberdog_character_and_she_got_a_little/ | false | false | default | 1 | null | ||
Any option for a low end pc? | 39 | I Have this:
Intel(R) Core(TM) i5-7200U CPU @ 2.50GHz 2.71 GHz (7th gen)
8gb RAM
1GB VRAM (integrated video card)
​
Dont diss me, I know its bad, It was the best I could get, Im poor, and I only have this cuz I bought it broken and fixed it.
​
I dont mind having to wait more for answers, the mai... | 2023-07-04T05:13:37 | https://www.reddit.com/r/LocalLLaMA/comments/14q5n5c/any_option_for_a_low_end_pc/ | Chekhovs_Shotgun | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 14q5n5c | false | null | t3_14q5n5c | /r/LocalLLaMA/comments/14q5n5c/any_option_for_a_low_end_pc/ | false | false | self | 39 | null |
Subsets and Splits
No community queries yet
The top public SQL queries from the community will appear here once available.