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 ⌀ |
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
Hemingway rewriting model | 21 | This is one of the hundreds of experimental rewriting models I have.
it is based on the public domain works by Ernest Hemingway:
​
https://preview.redd.it/6mj0fi70ip5c1.png?width=501&format=png&auto=webp&s=7718c29551082190f0cb7a21775afffa402b1833
* The Sun Also Rises
* The Old Man of the Sea
Show Ernest a... | 2023-12-11T18:10:22 | https://www.reddit.com/r/LocalLLaMA/comments/18g03pc/hemingway_rewriting_model/ | FPham | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 18g03pc | false | null | t3_18g03pc | /r/LocalLLaMA/comments/18g03pc/hemingway_rewriting_model/ | false | false | 21 | {'enabled': False, 'images': [{'id': '4vtVMg9_DJIyL7ph-pEBTiyRqXIZRLfr-_IG680JgcI', 'resolutions': [{'height': 58, 'url': 'https://external-preview.redd.it/4rcie5FCfwyk4Tjrm9QXgY3jaK30Fa5XPhMblNAZ0wM.jpg?width=108&crop=smart&auto=webp&s=36c2a8657c6973d3380b50743eef1fc500e4ed11', 'width': 108}, {'height': 116, 'url': 'h... | |
Best models for translations? | 7 | I'm looking to translate Japanese and Chinese to English. What local models can I use for this? | 2023-12-11T17:55:11 | https://www.reddit.com/r/LocalLLaMA/comments/18g00i2/best_models_for_translations/ | getSAT | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 18g00i2 | false | null | t3_18g00i2 | /r/LocalLLaMA/comments/18g00i2/best_models_for_translations/ | false | false | self | 7 | null |
When using a ChatGPT trained model, it seems like you both have to trick it to be ChatGPT, but not go too far. | 6 | I have a chatgpt trained model, and I copied one of the ChatGPT4 Bot descriptions. It seemed that unlocked chatGPT quality responses, but at the same time, often added the chatGPT restriction.
If I changed the character's opening response it was the jackpot:
Chatgpt4 quality, but no restriction.
I'm sure plenty of ... | 2023-12-11T17:47:44 | https://www.reddit.com/r/LocalLLaMA/comments/18fzyoj/when_using_a_chatgpt_trained_model_it_seems_like/ | pr1vacyn0eb | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 18fzyoj | false | null | t3_18fzyoj | /r/LocalLLaMA/comments/18fzyoj/when_using_a_chatgpt_trained_model_it_seems_like/ | false | false | self | 6 | null |
Logit bias as a way to avoid specific words and phrases? | 1 | I've been playing around with using logit_bias to ban tokens like "delve", "conclusion", "respect", "consent" and other overused ChatGPTisms.
It seems to work most of the time, unless I really paint the model into a corner by asking it "Give me a list of reasons why respect, consent are important in roleplays" and th... | 2023-12-11T17:42:24 | https://www.reddit.com/r/LocalLLaMA/comments/18fzx8g/logit_bias_as_a_way_to_avoid_specific_words_and/ | noellarkin | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 18fzx8g | false | null | t3_18fzx8g | /r/LocalLLaMA/comments/18fzx8g/logit_bias_as_a_way_to_avoid_specific_words_and/ | false | false | self | 1 | null |
Mixtral 7bx8: No safeguards, Complete freedom. | 79 | I tested bs safety policy of model and it's completely free. Don't use it for bad things tho, or ~~agi won't feel you back.~~
[please don't make drugs, it's just a test bro](https://preview.redd.it/q3l7t7gu8p5c1.png?width=793&format=png&auto=webp&s=87fbcd40933bf9a8eac9d47ba2b215f8878bc8c3)
[please don't make drugs, ... | 2023-12-11T17:19:33 | https://www.reddit.com/r/LocalLLaMA/comments/18fzno8/mixtral_7bx8_no_safeguards_complete_freedom/ | nanowell | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 18fzno8 | false | null | t3_18fzno8 | /r/LocalLLaMA/comments/18fzno8/mixtral_7bx8_no_safeguards_complete_freedom/ | false | false | 79 | null | |
Are there any existing guides on how to deploy vLLM on a GPU cluster? | 1 | I'd like to play around with a formal setup where my LLM service can serve concurrent requests. vLLM seems to be the ideal solution for this, however, I'd like some guidance on how I could go about deploying it on a cloud service like AWS or runpod, taking advantage of a multi-node architecture. | 2023-12-11T16:53:49 | https://www.reddit.com/r/LocalLLaMA/comments/18fz1rd/are_there_any_existing_guides_on_how_to_deploy/ | MonkeyMaster64 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 18fz1rd | false | null | t3_18fz1rd | /r/LocalLLaMA/comments/18fz1rd/are_there_any_existing_guides_on_how_to_deploy/ | false | false | self | 1 | null |
Any good unsensored LLaMAs for rewording/paraphrasing? | 2 | Basically I am trying to reword video titles for an adult website. Wondering if there's any LLaMA's you'd reccomed? Im new to the LLaMa space so bear with me, and thanks for your help. | 2023-12-11T16:46:51 | https://www.reddit.com/r/LocalLLaMA/comments/18fyw40/any_good_unsensored_llamas_for/ | Critical-Author-1339 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 18fyw40 | false | null | t3_18fyw40 | /r/LocalLLaMA/comments/18fyw40/any_good_unsensored_llamas_for/ | false | false | self | 2 | null |
Just installed a recent llama.cpp branch, and the speed of Mixtral 8x7b is beyond insane, it's like a Christmas gift for us all (M2, 64 Gb). GPT 3.5 model level with such speed, locally | 408 | 2023-12-11T16:35:50 | https://v.redd.it/voe3nf2z0p5c1 | Shir_man | /r/LocalLLaMA/comments/18fyn1k/just_installed_a_recent_llamacpp_branch_and_the/ | 1970-01-01T00:00:00 | 0 | {} | 18fyn1k | false | {'reddit_video': {'bitrate_kbps': 5000, 'dash_url': 'https://v.redd.it/voe3nf2z0p5c1/DASHPlaylist.mpd?a=1704990951%2CZDNhNjBiZjAyMWNjMmJjNThiODFkY2UxMDYxZGVhMTM0ZTI4MzU2ZTYwNWExY2I1MzZiNGM4YTVkZjVjNzAxZg%3D%3D&v=1&f=sd', 'duration': 50, 'fallback_url': 'https://v.redd.it/voe3nf2z0p5c1/DASH_1080.mp4?source=fallback', 'h... | t3_18fyn1k | /r/LocalLLaMA/comments/18fyn1k/just_installed_a_recent_llamacpp_branch_and_the/ | false | false | 408 | {'enabled': False, 'images': [{'id': 'Y29pcGQ0ZzcxcDVjMWh_fm72NFLHDaNtWoWDVUAxGWktkeFGdItFgU9VoXKa', 'resolutions': [{'height': 49, 'url': 'https://external-preview.redd.it/Y29pcGQ0ZzcxcDVjMWh_fm72NFLHDaNtWoWDVUAxGWktkeFGdItFgU9VoXKa.png?width=108&crop=smart&format=pjpg&auto=webp&s=e00ae8ccfe0f053503939a4c6d515bd8ca97b... | ||
Concurrent inference using Ctransformers and Langchain | 1 | [removed] | 2023-12-11T16:32:00 | https://www.reddit.com/r/LocalLLaMA/comments/18fyjun/concurrent_inference_using_ctransformers_and/ | Character_Mistake393 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 18fyjun | false | null | t3_18fyjun | /r/LocalLLaMA/comments/18fyjun/concurrent_inference_using_ctransformers_and/ | false | false | self | 1 | null |
VSC Continue.dev with own Rest API | 8 | Hello, I have seen this tool called Continue.dev and I found it perfect for code help.
Is there any guide or way to use it with an endpoint of your own Rest API?
My intention is to create a Rest API that uses its own model locally, but I don't know how to create the endpoint correctly so that Continue.dev acc... | 2023-12-11T16:15:32 | https://www.reddit.com/r/LocalLLaMA/comments/18fy5yt/vsc_continuedev_with_own_rest_api/ | Outrageous-Food3302 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 18fy5yt | false | null | t3_18fy5yt | /r/LocalLLaMA/comments/18fy5yt/vsc_continuedev_with_own_rest_api/ | false | false | self | 8 | null |
I asked Mixtral 8x7B who the 8 experts are | 1 | 2023-12-11T15:59:05 | herozorro | i.redd.it | 1970-01-01T00:00:00 | 0 | {} | 18fxs4c | false | null | t3_18fxs4c | /r/LocalLLaMA/comments/18fxs4c/i_asked_mixtral_8x7b_who_the_8_experts_are/ | false | false | 1 | {'enabled': True, 'images': [{'id': 'quG1GDnB8ek069N9ybDDRDsRsFAjX5FmwI1phoqrc5A', 'resolutions': [{'height': 38, 'url': 'https://preview.redd.it/3rqt83uiuo5c1.jpeg?width=108&crop=smart&auto=webp&s=73583f68a1563b269aa7ad46b02dd402f4b83eb7', 'width': 108}, {'height': 76, 'url': 'https://preview.redd.it/3rqt83uiuo5c1.jpe... | |||
How to Train an AI Chat Bot Using Your Text Messages: Seeking Guidance | 9 | I have zero CS background but am quite computer literate and learn quickly with guides. I’m interested in creating a basic chatbot that is trained on datasets of my text message conversations with others to try and mimic my style of speaking for fun. Any guidance is greatly appreciated! | 2023-12-11T15:57:28 | https://www.reddit.com/r/LocalLLaMA/comments/18fxqrp/how_to_train_an_ai_chat_bot_using_your_text/ | SpaceXBeanz | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 18fxqrp | false | null | t3_18fxqrp | /r/LocalLLaMA/comments/18fxqrp/how_to_train_an_ai_chat_bot_using_your_text/ | false | false | self | 9 | null |
Running Wizard 7b (Q2) on an 8gb Android Phone | 5 | Just a datapoint.
Running on a Samsung Galaxy S23 Ultra.
Termux -> build llama.cpp (be sure to make [the change detailed on this Git issue](https://github.com/ggerganov/llama.cpp/issues/402) otherwise you'll get illegal instruction errors) -> wget your favorite models.
Wizard7b Q2 works. The phone gets incredibly ho... | 2023-12-11T15:21:39 | https://www.reddit.com/r/LocalLLaMA/comments/18fwxs4/running_wizard_7b_q2_on_an_8gb_android_phone/ | Due-Ad-7308 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 18fwxs4 | false | null | t3_18fwxs4 | /r/LocalLLaMA/comments/18fwxs4/running_wizard_7b_q2_on_an_8gb_android_phone/ | false | false | self | 5 | {'enabled': False, 'images': [{'id': 'tsK16-Yb6gDC7oC9bRb5FKcl4Stnx4CZh8MGDludw9Q', 'resolutions': [{'height': 54, 'url': 'https://external-preview.redd.it/3X-oX5q2vWM1paUuP9gIW5Oug8JXKceF2wAl2m0wzOU.jpg?width=108&crop=smart&auto=webp&s=26030bd00760ab130f734205005b96536ad1008f', 'width': 108}, {'height': 108, 'url': 'h... |
New local LLM application with simple fine-tuning and RAG, built from scratch in C++/CUDA | 1 | [removed] | 2023-12-11T15:11:39 | https://www.reddit.com/r/LocalLLaMA/comments/18fwpm6/new_local_llm_application_with_simple_finetuning/ | drydberg | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 18fwpm6 | false | null | t3_18fwpm6 | /r/LocalLLaMA/comments/18fwpm6/new_local_llm_application_with_simple_finetuning/ | false | false | self | 1 | null |
Dataset Distillation | 8 | Based on the paper but applied to text data using embeddings and logits
Paper:
[https://arxiv.org/abs/1811.10959](https://arxiv.org/abs/1811.10959)
[https://gist.github.com/thistleknot/57ef8e63de0f2b6df5753e7d7b305864](https://gist.github.com/thistleknot/57ef8e63de0f2b6df5753e7d7b305864) | 2023-12-11T15:05:40 | https://www.reddit.com/r/LocalLLaMA/comments/18fwkyk/dataset_distillation/ | Thistleknot | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 18fwkyk | false | null | t3_18fwkyk | /r/LocalLLaMA/comments/18fwkyk/dataset_distillation/ | false | false | self | 8 | {'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... |
written by mixtral 8×7b | 32 | Dear CEO of OpenAI,
We are writing to express our concern and disappointment regarding the recent drama that has unfolded within your company. As an outside observer, we were alarmed by the sudden firing of Sam Altman, the public confusion that ensued, and the mass resignation threats from employees.
We understand that... | 2023-12-11T15:01:27 | https://www.reddit.com/r/LocalLLaMA/comments/18fwhd5/written_by_mixtral_87b/ | GasBond | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 18fwhd5 | false | null | t3_18fwhd5 | /r/LocalLLaMA/comments/18fwhd5/written_by_mixtral_87b/ | false | false | self | 32 | null |
Sheared-LLaMA-1.3B-ShareGPT-GGUF | 17 | My first GGUF quantize))
I took the README from TheBloke.
[https://huggingface.co/LakoMoor/Sheared-LLaMA-1.3B-ShareGPT-GGUF](https://huggingface.co/LakoMoor/Sheared-LLaMA-1.3B-ShareGPT-GGUF) | 2023-12-11T14:55:21 | https://www.reddit.com/r/LocalLLaMA/comments/18fwcj9/shearedllama13bsharegptgguf/ | Substantial-Club-582 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 18fwcj9 | false | null | t3_18fwcj9 | /r/LocalLLaMA/comments/18fwcj9/shearedllama13bsharegptgguf/ | false | false | self | 17 | {'enabled': False, 'images': [{'id': 'AJSlo2x8pHhm1EBK0gKCpgtu3mvo3GVpKw0jflKGAR4', 'resolutions': [{'height': 58, 'url': 'https://external-preview.redd.it/sfVFwRRIasGT7w0evC_Sl-LwxYahI0Lf9wAnb9Rckto.jpg?width=108&crop=smart&auto=webp&s=2985cdf076980eb1c156d2cb164b3a68aefe4381', 'width': 108}, {'height': 116, 'url': 'h... |
How fast M1 Ultra or M2 Ultra compared to M1 Max or M2 Max for inferencing? | 1 | [removed] | 2023-12-11T14:33:38 | https://www.reddit.com/r/LocalLLaMA/comments/18fvvll/how_fast_m1_ultra_or_m2_ultra_compared_to_m1_max/ | bebopkim1372 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 18fvvll | false | null | t3_18fvvll | /r/LocalLLaMA/comments/18fvvll/how_fast_m1_ultra_or_m2_ultra_compared_to_m1_max/ | false | false | self | 1 | {'enabled': False, 'images': [{'id': 'U6NjXj5zmkZmT9O3lGQTGGU6w6IP9uALXviXPqYqU8Q', 'resolutions': [{'height': 81, 'url': 'https://external-preview.redd.it/bx4u8JlfZp8go03kKlxd9r9SCEngY04o_DESRcwswcc.jpg?width=108&crop=smart&auto=webp&s=9b0eb6686d787ebcfdd6ec787d94fa92dcda8f46', 'width': 108}, {'height': 162, 'url': 'h... |
Mixture of Experts Explained | 64 | 2023-12-11T14:24:50 | https://huggingface.co/blog/moe | hackerllama | huggingface.co | 1970-01-01T00:00:00 | 0 | {} | 18fvov0 | false | null | t3_18fvov0 | /r/LocalLLaMA/comments/18fvov0/mixture_of_experts_explained/ | false | false | 64 | {'enabled': False, 'images': [{'id': 'LGQcnAtm_XuZx8myZtiJbvkF9OXnaBmGd2mqjq04984', 'resolutions': [{'height': 56, 'url': 'https://external-preview.redd.it/8EvL2hjIm_2a10-rzZH_VlEo15SdtQxOljgVZg9_Vpw.jpg?width=108&crop=smart&auto=webp&s=5a71142d72a3cf50ccf8290d458e8d51c6f1f8db', 'width': 108}, {'height': 112, 'url': 'h... | ||
Can I run a local LLaMa on 1Ghz cpu and 64mb of RAM? | 1 | I saw a very tiny Linux machine called a Milk V Duo there any some tiny linux machine similar to this too.
But this one is a better deal. (i do not put link so it doesn't look like an ad).
I wonder if someone has the know-how of how to run LLaMa on such power. | 2023-12-11T14:21:00 | https://www.reddit.com/r/LocalLLaMA/comments/18fvlz7/can_i_run_a_local_llama_on_1ghz_cpu_and_64mb_of/ | Eznix86 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 18fvlz7 | false | null | t3_18fvlz7 | /r/LocalLLaMA/comments/18fvlz7/can_i_run_a_local_llama_on_1ghz_cpu_and_64mb_of/ | false | false | self | 1 | null |
Best way to make models understand certain language without fine tuning | 7 | I want to enable OpenHermes to communicate in my native language, but I can't afford to fine-tune it with my current device specifications. Is there a way to make this happen? Is translating the prompt before the model processes it a good idea? | 2023-12-11T13:58:27 | https://www.reddit.com/r/LocalLLaMA/comments/18fv4zz/best_way_to_make_models_understand_certain/ | laveriaroha | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 18fv4zz | false | null | t3_18fv4zz | /r/LocalLLaMA/comments/18fv4zz/best_way_to_make_models_understand_certain/ | false | false | self | 7 | null |
At the end of model I see _K, or _K_L, or _K_S, or _O. I'm trying to figure out what they mean. | 3 | 2023-12-11T13:49:11 | Sokar1723 | i.redd.it | 1970-01-01T00:00:00 | 0 | {} | 18fuy6o | false | null | t3_18fuy6o | /r/LocalLLaMA/comments/18fuy6o/at_the_end_of_model_i_see_k_or_k_l_or_k_s_or_o_im/ | false | false | 3 | {'enabled': True, 'images': [{'id': 'j6u2dtDQZChlgxUnisyQu096tNN1ii1NgCJBEVvmM9U', 'resolutions': [{'height': 73, 'url': 'https://preview.redd.it/vn7d0lrd7o5c1.png?width=108&crop=smart&auto=webp&s=aed11f6efb6fb2c445874fccba458e1da224ecda', 'width': 108}, {'height': 147, 'url': 'https://preview.redd.it/vn7d0lrd7o5c1.png... | |||
What doe the letters at the end of the model name mean? | 1 | At the end of model I see \_K, or \_K\_L, or \_K\_S, or \_O. What is the meaning of these? | 2023-12-11T13:46:36 | https://www.reddit.com/r/LocalLLaMA/comments/18fuwfj/what_doe_the_letters_at_the_end_of_the_model_name/ | Sokar1723 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 18fuwfj | false | null | t3_18fuwfj | /r/LocalLLaMA/comments/18fuwfj/what_doe_the_letters_at_the_end_of_the_model_name/ | false | false | self | 1 | null |
How to use Mixtral in Text Generate Web Ui? | 3 | How to use Mixtral in Text Generate Web Ui?
​
Similarly, when trying to use Qwen 72b, I get a LlamaCppModel error when I try to load mixtral into RAM. How to fix it? I want to make sure that this model is productive and does not require a lot of computing power.
​
I tried using GGUF. If this problem i... | 2023-12-11T13:44:54 | https://www.reddit.com/r/LocalLLaMA/comments/18fuv6a/how_to_use_mixtral_in_text_generate_web_ui/ | Secret_Joke_2262 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 18fuv6a | false | null | t3_18fuv6a | /r/LocalLLaMA/comments/18fuv6a/how_to_use_mixtral_in_text_generate_web_ui/ | false | false | self | 3 | null |
Need help with slow inference speeds on GPU | 1 | [removed] | 2023-12-11T13:43:20 | https://www.reddit.com/r/LocalLLaMA/comments/18fuu2c/need_help_with_slow_inference_speeds_on_gpu/ | Specialist-Ad2870 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 18fuu2c | false | null | t3_18fuu2c | /r/LocalLLaMA/comments/18fuu2c/need_help_with_slow_inference_speeds_on_gpu/ | false | false | 1 | null | |
Best way for few-shot learning and JSON: LMQL? Guidance? Grammars? | 2 | Hi,
I want to extract structured data from unstructured text using few-shot learning. My dream approach would be to use JSON for everything, i.e. for both the examples (by just adding json.dumps) and the return values, and to do some kind of formal constraining of the model results. I already used LMQL and guidance, b... | 2023-12-11T13:42:28 | https://www.reddit.com/r/LocalLLaMA/comments/18futhd/best_way_for_fewshot_learning_and_json_lmql/ | Bradymodion | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 18futhd | false | null | t3_18futhd | /r/LocalLLaMA/comments/18futhd/best_way_for_fewshot_learning_and_json_lmql/ | false | false | self | 2 | null |
New 7B Model at Open LLM Leaderboard | 1 | [removed] | 2023-12-11T13:40:02 | https://www.reddit.com/r/LocalLLaMA/comments/18furq5/new_7b_model_at_open_llm_leaderboard/ | Alarming-Turn2936 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 18furq5 | false | null | t3_18furq5 | /r/LocalLLaMA/comments/18furq5/new_7b_model_at_open_llm_leaderboard/ | false | false | 1 | null | |
Memory Problem using Mistral-7B | 1 | I'm trying to use Mistral-7B (through a cloud GPU)
everytime I just try to initialize it, the kernel crashes (due to memory)
here the code (very simple from HF)
`# Load model directly`
`from transformers import AutoTokenizer, AutoModelForCausalLM`
`tokenizer = AutoTokenizer.from_pretrained("mistralai/Mistral... | 2023-12-11T13:17:58 | https://www.reddit.com/r/LocalLLaMA/comments/18fuceo/memory_problem_using_mistral7b/ | 0ssamaak0 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 18fuceo | false | null | t3_18fuceo | /r/LocalLLaMA/comments/18fuceo/memory_problem_using_mistral7b/ | false | false | default | 1 | null |
Custom computer vision model | 1 | I'm looking for a solution to build a custom computer vision model.
Basically I'm looking for a concept like this, but open source ;-) :
[https://www.customvision.ai/](https://www.customvision.ai/)
I want to train a model with some labelled images and then be able to tag images with an API.
Any idea? Thanks a ... | 2023-12-11T13:14:27 | https://www.reddit.com/r/LocalLLaMA/comments/18fua4n/custom_computer_vision_model/ | takezo07 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 18fua4n | false | null | t3_18fua4n | /r/LocalLLaMA/comments/18fua4n/custom_computer_vision_model/ | false | false | self | 1 | null |
How ChatGPT's Data Analysis or Web Browsing work from the Backend pov ? | 2 | I have a question - How does the Web Browsing or Data Analysis modes of ChatGPT could work as far as backend is concerned ?
Let's say that 1000 ppl at once run prompt that makes use of Data Analysis - how is the code from multiple users evaluated in parallel ? Do they automatically run 1000 different docker container... | 2023-12-11T12:53:53 | https://www.reddit.com/r/LocalLLaMA/comments/18ftw71/how_chatgpts_data_analysis_or_web_browsing_work/ | mr_dicaprio | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 18ftw71 | false | null | t3_18ftw71 | /r/LocalLLaMA/comments/18ftw71/how_chatgpts_data_analysis_or_web_browsing_work/ | false | false | self | 2 | null |
Best option to get a model to answer question on a lot of selected book. | 5 | I'm planning to develop an AI system to offer free legal advice for a specific country. My resources include a large collection of PDF books, totaling over 100 GB, which I want the AI to process. I have medium to high development skills.
The documents are primarily in French, so I'm considering using a French language... | 2023-12-11T12:19:22 | https://www.reddit.com/r/LocalLLaMA/comments/18ftaax/best_option_to_get_a_model_to_answer_question_on/ | Sikode | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 18ftaax | false | null | t3_18ftaax | /r/LocalLLaMA/comments/18ftaax/best_option_to_get_a_model_to_answer_question_on/ | false | false | self | 5 | null |
🐺🐦⬛ Updated LLM Comparison/Test with new RP model: Rogue Rose 103B | 65 | Had some fun over the weekend with a new RP model while waiting for Mixtral to stabilize. Same testing/comparison procedure as usual, and the results had me update the rankings from my [**Big** LLM Comparison/Test: 3x 120B, 12x 70B, 2x 34B, GPT-4/3.5](https://www.reddit.com/r/LocalLLaMA/comments/185ff51/big_llm_compari... | 2023-12-11T12:16:06 | https://www.reddit.com/r/LocalLLaMA/comments/18ft8f5/updated_llm_comparisontest_with_new_rp_model/ | WolframRavenwolf | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 18ft8f5 | false | null | t3_18ft8f5 | /r/LocalLLaMA/comments/18ft8f5/updated_llm_comparisontest_with_new_rp_model/ | false | false | self | 65 | {'enabled': False, 'images': [{'id': '4TWR_VSyKNL16Ui6UrYSoCuO0FSV3vqXM_C69xJKUa4', 'resolutions': [{'height': 58, 'url': 'https://external-preview.redd.it/HRVlKs3sBaxtcPvxlYlBvgyZaZtwOLFTkpIqT_ViSQA.jpg?width=108&crop=smart&auto=webp&s=a5c66c71ecab943ff35f601674ebf62f223481ad', 'width': 108}, {'height': 116, 'url': 'h... |
MistralAI endpoints access | 7 | Surely we have some people from MistralAI hanging out here in the sub. Or at least friends of the people from MistralAI.
It would be a nice gesture from MistralAI to share a bunch of invitations to access their new API endpoints with the community here :) after all, people who are obsessed with LLMs are a perfect tar... | 2023-12-11T12:15:10 | https://www.reddit.com/r/LocalLLaMA/comments/18ft7sm/mistralai_endpoints_access/ | epicfilemcnulty | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 18ft7sm | false | null | t3_18ft7sm | /r/LocalLLaMA/comments/18ft7sm/mistralai_endpoints_access/ | false | false | self | 7 | null |
German language embedding model for fine tuned Mistral 7B model ( Leo LM &EM_German) for RAG based implementation. | 1 | Hi,
Quite new to LLMs . I was quite interested in building a query ,Qand A agent using RAG and llama index. As far as i know from most of the example (such as here : [https://colab.research.google.com/drive/16Ygf2IyGNkb725ZqtRmFQjwWBuzFX\_kl?usp=sharing](https://colab.research.google.com/drive/16Ygf2IyGNkb725ZqtRmFQj... | 2023-12-11T11:52:11 | https://www.reddit.com/r/LocalLLaMA/comments/18fstxw/german_language_embedding_model_for_fine_tuned/ | TheAmendingMonk | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 18fstxw | false | null | t3_18fstxw | /r/LocalLLaMA/comments/18fstxw/german_language_embedding_model_for_fine_tuned/ | false | false | self | 1 | {'enabled': False, 'images': [{'id': 'nkhh65ujo5BznFJFojoMPaKjGuLSpPj6KGhRov-ykOg', 'resolutions': [{'height': 108, 'url': 'https://external-preview.redd.it/0-fRWqjlLadVXj5pfYp4_Oe3xgBWE-_rdjVSn7hlohI.jpg?width=108&crop=smart&auto=webp&s=f34d2dfdbbfa7de0f1956f186fd8430ee96a1a55', 'width': 108}, {'height': 216, 'url': '... |
German language embedding model for fine tuned Mistral 7B model ( Leo LM &EM_German) for RAG based implementation. | 9 | Hi,
Quite new to LLMs . I was quite interested in building a query ,Qand A agent using RAG and llama index. As far as i know from most of the example (such as here : [https://colab.research.google.com/drive/16Ygf2IyGNkb725ZqtRmFQjwWBuzFX\_kl?usp=sharing](https://colab.research.google.com/drive/16Ygf2IyGNkb725ZqtRmFQj... | 2023-12-11T11:52:11 | https://www.reddit.com/r/LocalLLaMA/comments/18fsty1/german_language_embedding_model_for_fine_tuned/ | TheAmendingMonk | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 18fsty1 | false | null | t3_18fsty1 | /r/LocalLLaMA/comments/18fsty1/german_language_embedding_model_for_fine_tuned/ | false | false | self | 9 | {'enabled': False, 'images': [{'id': 'nkhh65ujo5BznFJFojoMPaKjGuLSpPj6KGhRov-ykOg', 'resolutions': [{'height': 108, 'url': 'https://external-preview.redd.it/0-fRWqjlLadVXj5pfYp4_Oe3xgBWE-_rdjVSn7hlohI.jpg?width=108&crop=smart&auto=webp&s=f34d2dfdbbfa7de0f1956f186fd8430ee96a1a55', 'width': 108}, {'height': 216, 'url': '... |
From "hello, what is your name?" to nsfw madness in 1 reply | 2 | I've just tried the official llama2-7b base model using [lit-gpt](https://github.com/Lightning-AI/lit-gpt) implementation and prompted the model with `"Hello, what is your"`. Last 5 sentences made my day. So many questions... In the end I had to manually interupt the generation. The output is reproducible.
`(.venv) u... | 2023-12-11T11:45:01 | https://www.reddit.com/r/LocalLLaMA/comments/18fspu0/from_hello_what_is_your_name_to_nsfw_madness_in_1/ | YYY_333 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 18fspu0 | false | null | t3_18fspu0 | /r/LocalLLaMA/comments/18fspu0/from_hello_what_is_your_name_to_nsfw_madness_in_1/ | false | false | nsfw | 2 | {'enabled': False, 'images': [{'id': 'ltwZVmlbwY12T05M4IaZYi04SOtBmYr3t6lgWW9l804', 'resolutions': [{'height': 54, 'url': 'https://external-preview.redd.it/RR0113OFai-4BZKlMe1wUOMcGTgqiStAWWoPTC4jns8.jpg?width=108&crop=smart&auto=webp&s=fe19c9d3dc7cddcd156ee21f935e68a0c5afffed', 'width': 108}, {'height': 108, 'url': 'h... |
Help me choose a MacBook for local inferencing | 1 | [removed] | 2023-12-11T11:36:42 | https://www.reddit.com/r/LocalLLaMA/comments/18fsl6x/help_me_choose_a_macbook_for_local_inferencing/ | SideShow_Bot | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 18fsl6x | false | null | t3_18fsl6x | /r/LocalLLaMA/comments/18fsl6x/help_me_choose_a_macbook_for_local_inferencing/ | false | false | self | 1 | null |
Petals vs vLLM vs ? for serving LLMs to many users | 9 | Small startup here. We have a few dozen systems with either 1 or 2 nVidia 4090 in each system. We want to make a chat bot service for a website and want to maximize concurrency, performance, and model flexibility. Which LLM serving framework should we use or take a look at? | 2023-12-11T11:34:25 | https://www.reddit.com/r/LocalLLaMA/comments/18fsjst/petals_vs_vllm_vs_for_serving_llms_to_many_users/ | humanoid64 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 18fsjst | false | null | t3_18fsjst | /r/LocalLLaMA/comments/18fsjst/petals_vs_vllm_vs_for_serving_llms_to_many_users/ | false | false | self | 9 | null |
4bit Mistral MoE running in llama.cpp! | 169 | 2023-12-11T11:30:59 | https://github.com/ggerganov/llama.cpp/pull/4406 | Aaaaaaaaaeeeee | github.com | 1970-01-01T00:00:00 | 0 | {} | 18fshrr | false | null | t3_18fshrr | /r/LocalLLaMA/comments/18fshrr/4bit_mistral_moe_running_in_llamacpp/ | false | false | 169 | {'enabled': False, 'images': [{'id': 'sPj3q9CQP6syMciDm1jvGUwQ-92QzIlN_rGiOZ_J2q4', 'resolutions': [{'height': 54, 'url': 'https://external-preview.redd.it/ZXMSs8BjVqATTlDsP_ADyrLtHoNT46OUq471Yr1GvY8.jpg?width=108&crop=smart&auto=webp&s=3b4f54e0fea8ce41b9f4f54f9e6dfd2b71066104', 'width': 108}, {'height': 108, 'url': 'h... | ||
Think step by step. Am I cheating? [Model Merge] | 1 | 2023-12-11T11:24:57 | https://www.reddit.com/gallery/18fsecg | xadiant | reddit.com | 1970-01-01T00:00:00 | 0 | {} | 18fsecg | false | null | t3_18fsecg | /r/LocalLLaMA/comments/18fsecg/think_step_by_step_am_i_cheating_model_merge/ | false | false | 1 | null | ||
Demo of Anagnorisis - completely local recommendation system powered by Llama 2. Radio mode. Work in progress. | 12 | 2023-12-11T11:18:41 | https://v.redd.it/wtapmju9gn5c1 | Another__one | /r/LocalLLaMA/comments/18fsazu/demo_of_anagnorisis_completely_local/ | 1970-01-01T00:00:00 | 0 | {} | 18fsazu | false | {'reddit_video': {'bitrate_kbps': 5000, 'dash_url': 'https://v.redd.it/wtapmju9gn5c1/DASHPlaylist.mpd?a=1704971927%2CN2I3NjU4Njc2MmMxNWZhNWJmOWFhNGQwZWZiMjYyYzc3OTA1YWNiZjhmZDIzYTBlZDU1NmQ2NzY2NTg1Njk0Zg%3D%3D&v=1&f=sd', 'duration': 366, 'fallback_url': 'https://v.redd.it/wtapmju9gn5c1/DASH_1080.mp4?source=fallback', '... | t3_18fsazu | /r/LocalLLaMA/comments/18fsazu/demo_of_anagnorisis_completely_local/ | false | false | 12 | {'enabled': False, 'images': [{'id': 'Z3EwZTkyZW1nbjVjMZRGhFZAeKb9FWF9vjzqaY_9NOXIuxlkDFYWGBUO3QX3', 'resolutions': [{'height': 74, 'url': 'https://external-preview.redd.it/Z3EwZTkyZW1nbjVjMZRGhFZAeKb9FWF9vjzqaY_9NOXIuxlkDFYWGBUO3QX3.png?width=108&crop=smart&format=pjpg&auto=webp&s=595ed9129d779ae5825b4ed396b413ee6fa46... | ||
LangCheck v0.3.0: Factual consistency improvements and text augmentations | 91 | Hi all – I wanted to share the v0.3.0 release of [LangCheck](https://langcheck.readthedocs.io/en/latest/quickstart.html), an open-source toolkit to evaluate LLM apps.
New features:
* Significant improvements to `factual_consistency()`, our most popular metric. It's now faster, higher-quality, and produces better text... | 2023-12-11T11:02:03 | https://www.reddit.com/r/LocalLLaMA/comments/18fs1um/langcheck_v030_factual_consistency_improvements/ | kennysong | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 18fs1um | false | null | t3_18fs1um | /r/LocalLLaMA/comments/18fs1um/langcheck_v030_factual_consistency_improvements/ | false | false | self | 91 | null |
Mistral pricing confusion | 1 | Hi, can someone please help me understand the new update Mistral has made with regard to hosting models behind their API endpoints?
​
I understood the model weights were open source with 7b and I know they just released the Mixtral weights. What is the difference between using the paid API vs downloading the w... | 2023-12-11T10:17:57 | https://www.reddit.com/r/LocalLLaMA/comments/18freg6/mistral_pricing_confusion/ | 99OG121314 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 18freg6 | false | null | t3_18freg6 | /r/LocalLLaMA/comments/18freg6/mistral_pricing_confusion/ | false | false | self | 1 | null |
Optimal and Cost-Effective GPUs and Server Specs for Local AI Model Development | 1 | Hi,
I'm reaching out to seek some valuable insights here regarding setting up a local AI development environment for a small team.
the main objectives are development and testing, we're exploring the most optimal and budget-friendly GPUs along with server specifications that would be suitable for running AI models ... | 2023-12-11T10:16:52 | https://www.reddit.com/r/LocalLLaMA/comments/18frdxb/optimal_and_costeffective_gpus_and_server_specs/ | MuieewitdaMu | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 18frdxb | false | null | t3_18frdxb | /r/LocalLLaMA/comments/18frdxb/optimal_and_costeffective_gpus_and_server_specs/ | false | false | self | 1 | null |
SparQ Attention: Bandwidth-Efficient LLM Inference | 23 | https://arxiv.org/abs/2312.04985
Very interesting!
"Our proposed technique can be applied directly to off-the-shelf LLMs during inference, without requiring any modification to the pre-training setup or additional fine-tuning. We show how SparQ Attention can decrease the attention memory bandwidth requirements up to ... | 2023-12-11T10:16:49 | https://www.reddit.com/r/LocalLLaMA/comments/18frdwt/sparq_attention_bandwidthefficient_llm_inference/ | BalorNG | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 18frdwt | false | null | t3_18frdwt | /r/LocalLLaMA/comments/18frdwt/sparq_attention_bandwidthefficient_llm_inference/ | false | false | self | 23 | {'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... |
How to Implement Function Calling Based on a Local Model | 23 | I'll briefly explain how to implement function calling with a local model, similar to OpenAI, and even package it into a service completely identical to OpenAI's. Indeed, I've successfully gone through the entire process to achieve this.
Firstly, we need to train a model using some specific SFT data. Even without dedi... | 2023-12-11T10:07:13 | https://www.reddit.com/r/LocalLLaMA/comments/18fr8u3/how_to_implement_function_calling_based_on_a/ | Low_Bad_6585 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 18fr8u3 | false | null | t3_18fr8u3 | /r/LocalLLaMA/comments/18fr8u3/how_to_implement_function_calling_based_on_a/ | false | false | self | 23 | {'enabled': False, 'images': [{'id': 'cerzAYW92FRw9rbIeYzWCK903lDfmdfxwP77Ts4o79Y', 'resolutions': [{'height': 58, 'url': 'https://external-preview.redd.it/tH4Q-Var-jfUQlVbukD0ZHTPj5Q13MmZhqdfFFRSqPI.jpg?width=108&crop=smart&auto=webp&s=4bb83cf83f549394eefadfc98920f3652f5c52c8', 'width': 108}, {'height': 116, 'url': 'h... |
Run local model on Windows 11 - tried LM Studio | 1 | I’m getting started with OS models & tried with LM studio & vLLM but both of them got stuck at some stage,
Any leads to documentation, Tutorials , how to’s ?
Ollama tried on mac works perfect!
TIA | 2023-12-11T10:00:01 | https://www.reddit.com/r/LocalLLaMA/comments/18fr4m0/run_local_model_on_windows_11_tried_lm_studio/ | AmazingPerspective79 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 18fr4m0 | false | null | t3_18fr4m0 | /r/LocalLLaMA/comments/18fr4m0/run_local_model_on_windows_11_tried_lm_studio/ | false | false | self | 1 | null |
Looks like Mistral-7B-Instruct-v0.2 is coming soon... | 47 | Buried in the newly updated Mistral docs is this
​
>docker run --gpus all \\
\-e HF\_TOKEN=$HF\_TOKEN -p 8000:8000 \\
ghcr.io/mistralai/mistral-src/vllm:latest \\
\--host 0.0.0.0 \\
\--model mistralai/Mistral-7B-Instruct-v0.2
That model does not exist in HF as of now. Looks like a new 7B model rele... | 2023-12-11T09:55:54 | https://www.reddit.com/r/LocalLLaMA/comments/18fr2hn/looks_like_mistral7binstructv02_is_coming_soon/ | distant_gradient | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 18fr2hn | false | null | t3_18fr2hn | /r/LocalLLaMA/comments/18fr2hn/looks_like_mistral7binstructv02_is_coming_soon/ | false | false | self | 47 | null |
Mistrsal officially announces Mixtral 8x7B | 119 | Mistrsal has officially announced the release of the MoE Mixtral 8x7B model in a tweet by the ceo
Tweet
https://x.com/arthurmensch/status/1734123845739548859?s=20
Blog post
https://mistral.ai/news/mixtral-of-experts/ | 2023-12-11T09:29:02 | https://www.reddit.com/r/LocalLLaMA/comments/18fqohd/mistrsal_officially_announces_mixtral_8x7b/ | Amgadoz | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 18fqohd | false | null | t3_18fqohd | /r/LocalLLaMA/comments/18fqohd/mistrsal_officially_announces_mixtral_8x7b/ | false | false | self | 119 | {'enabled': False, 'images': [{'id': 'IiJiFlTViX12HFlrM5q0VzRx5H8mF60G_H9r2vZmX5c', 'resolutions': [{'height': 108, 'url': 'https://external-preview.redd.it/uJhvFvYqcUuLXM2KDNn_-IS1BmbJh4hfjKlpz9TQZ8Y.jpg?width=108&crop=smart&auto=webp&s=eaaf4f5ac3d2e56c84d98fc1d570f804e32169b0', 'width': 108}], 'source': {'height': 20... |
Low GPU local machine for LLMs? | 1 | [removed] | 2023-12-11T08:53:24 | https://www.reddit.com/r/LocalLLaMA/comments/18fq6vf/low_gpu_local_machine_for_llms/ | Data_Driven_Guy | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 18fq6vf | false | null | t3_18fq6vf | /r/LocalLLaMA/comments/18fq6vf/low_gpu_local_machine_for_llms/ | false | false | self | 1 | null |
Can I Buy Valium Online Treat Fits and Alcohol Withdrawal? | 1 | 2023-12-11T08:46:49 | https://medznow.com/anti-anxiety/valium/ | ethan_robert1 | medznow.com | 1970-01-01T00:00:00 | 0 | {} | 18fq3pr | false | null | t3_18fq3pr | /r/LocalLLaMA/comments/18fq3pr/can_i_buy_valium_online_treat_fits_and_alcohol/ | false | false | nsfw | 1 | null | |
Mixtral Official release and numbers | 2 | https://mistral.ai/news/mixtral-of-experts/
They released 2 models. Base and instruct, the Instruct version trained with SFT and DPO which they say gives gpt3.5 level performance. | 2023-12-11T08:42:21 | https://www.reddit.com/r/LocalLLaMA/comments/18fq1i6/mixtral_official_release_and_numbers/ | Eastwindy123 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 18fq1i6 | false | null | t3_18fq1i6 | /r/LocalLLaMA/comments/18fq1i6/mixtral_official_release_and_numbers/ | false | false | self | 2 | null |
Mistral has an even more powerfull model in the prototype-phase | 143 | [https://mistral.ai/news/la-plateforme/](https://mistral.ai/news/la-plateforme/)
>**Mistral-medium**. Our highest-quality endpoint currently serves a prototype model, that is currently among the top serviced models available based on standard benchmarks. It masters English/French/Italian/German/Spanish and code and ob... | 2023-12-11T08:39:24 | https://www.reddit.com/r/LocalLLaMA/comments/18fq00r/mistral_has_an_even_more_powerfull_model_in_the/ | QuieselWusul | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 18fq00r | false | null | t3_18fq00r | /r/LocalLLaMA/comments/18fq00r/mistral_has_an_even_more_powerfull_model_in_the/ | false | false | self | 143 | null |
Mistral website was just updated | 261 | 2023-12-11T08:16:51 | https://mistral.ai/news/mixtral-of-experts/ | Tucko29 | mistral.ai | 1970-01-01T00:00:00 | 0 | {} | 18fpp3d | false | null | t3_18fpp3d | /r/LocalLLaMA/comments/18fpp3d/mistral_website_was_just_updated/ | false | false | default | 261 | null | |
Can someone explain what is mixtral 8x7B? | 8 | Everything is in the title
I understood that it was a moe (mixture of expert).
I can see that its original weight are a bit less than 8 times mistral's original weights size.
But it appears as one big model not 8 small models.
I though the point of moe was to have small specialised model and a "manager" deciding wich m... | 2023-12-11T07:47:47 | https://www.reddit.com/r/LocalLLaMA/comments/18fpan7/can_someone_explain_what_is_mixtral_8x7b/ | No_Afternoon_4260 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 18fpan7 | false | null | t3_18fpan7 | /r/LocalLLaMA/comments/18fpan7/can_someone_explain_what_is_mixtral_8x7b/ | false | false | self | 8 | null |
Best Model for Medical Use Case Training | 2 | What's the best one? | 2023-12-11T07:45:39 | https://www.reddit.com/r/LocalLLaMA/comments/18fp9kq/best_model_for_medical_use_case_training/ | Role-Fluffy | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 18fp9kq | false | null | t3_18fp9kq | /r/LocalLLaMA/comments/18fp9kq/best_model_for_medical_use_case_training/ | false | false | self | 2 | null |
Can I Buy Meridia Online To Lose Weight? | 1 | 2023-12-11T07:40:00 | https://medznow.com/weight-loss/meridia/ | ethan_robert1 | medznow.com | 1970-01-01T00:00:00 | 0 | {} | 18fp6u7 | false | null | t3_18fp6u7 | /r/LocalLLaMA/comments/18fp6u7/can_i_buy_meridia_online_to_lose_weight/ | false | false | nsfw | 1 | null | |
Can I Buy Ambien Online as a Sleeping Pill? | 1 | 2023-12-11T07:27:01 | https://medznow.com/sleeping-pills/ambien/ | ethan_robert1 | medznow.com | 1970-01-01T00:00:00 | 0 | {} | 18fp0l6 | false | null | t3_18fp0l6 | /r/LocalLLaMA/comments/18fp0l6/can_i_buy_ambien_online_as_a_sleeping_pill/ | false | false | nsfw | 1 | null | |
Was I wrong to look at Text Gen. Models? I need an Editor! Will T2T models prove leaps and bounds better for revising and/or writer's block assistance? | 2 | So I'd been scouring TG for a code gen./editor and that's all settled, went with Deepseek-Coding-Instructor. Because of this and my knack for getting caught in the weeds and jumping down every rabbit hole, I'd basically considered/read all about the generalist or creative-type TG models.
I planned on going with LZLV-... | 2023-12-11T07:02:21 | https://www.reddit.com/r/LocalLLaMA/comments/18fookg/was_i_wrong_to_look_at_text_gen_models_i_need_an/ | ArthurAardvark | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 18fookg | false | null | t3_18fookg | /r/LocalLLaMA/comments/18fookg/was_i_wrong_to_look_at_text_gen_models_i_need_an/ | false | false | self | 2 | {'enabled': False, 'images': [{'id': 'aT_NzUjXz4T4gC14KEKpdMPYAxfCYyQpPSjmLu7E1hY', 'resolutions': [{'height': 58, 'url': 'https://external-preview.redd.it/GibNZK79I186k6olB8YFoVBXiBnTHUlhNbG2N08geSs.jpg?width=108&crop=smart&auto=webp&s=bd3fdbffb62f61ecadbefaa9eb4088f492ded38a', 'width': 108}, {'height': 116, 'url': 'h... |
Can I Buy Dilaudid Online to Relief from Pain | 1 | 2023-12-11T06:53:41 | https://medznow.com/pain-relief/dilaudid/ | ethan_robert1 | medznow.com | 1970-01-01T00:00:00 | 0 | {} | 18fojyj | false | null | t3_18fojyj | /r/LocalLLaMA/comments/18fojyj/can_i_buy_dilaudid_online_to_relief_from_pain/ | false | false | nsfw | 1 | null | |
LlaVa-Med GGUF or atleast some tutorial or such to create it? | 2 | I need LlaVa-Med GGUF for a project I'm working on so that I can run it using llama.cpp. Can someone give me a link if it exists or atleast give me some tutorial on how to make a quant for a multi-modal model like this one? Thanks. | 2023-12-11T06:46:03 | https://www.reddit.com/r/LocalLLaMA/comments/18fofzt/llavamed_gguf_or_atleast_some_tutorial_or_such_to/ | Shoddy_Vegetable_115 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 18fofzt | false | null | t3_18fofzt | /r/LocalLLaMA/comments/18fofzt/llavamed_gguf_or_atleast_some_tutorial_or_such_to/ | false | false | self | 2 | null |
Can I Buy Kamagra Online to treat erectile Dysfunction | 1 | 2023-12-11T06:35:21 | https://medznow.com/men-health/kamagra/ | ethan_robert1 | medznow.com | 1970-01-01T00:00:00 | 0 | {} | 18foa8q | false | null | t3_18foa8q | /r/LocalLLaMA/comments/18foa8q/can_i_buy_kamagra_online_to_treat_erectile/ | false | false | nsfw | 1 | null | |
Real-time typing recognition | 11 | Does anyone remember ICQ?
It allowed the other person in chat to see what you typed as you typed.
Is there any way to implement like a parser or something that can interpret in real-time what is being typed by a user?
I think it’d be interesting to have a language model able to confirm they are following what you ar... | 2023-12-11T05:54:16 | https://www.reddit.com/r/LocalLLaMA/comments/18fnnci/realtime_typing_recognition/ | IntrepidlyIndy | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 18fnnci | false | null | t3_18fnnci | /r/LocalLLaMA/comments/18fnnci/realtime_typing_recognition/ | false | false | self | 11 | null |
How do I use Nous-Capybara 34B? | 3 | Seems like a simple question, I know. But I am still getting the bug where it generates only </s> and nothing else, weeks after it was supposedly fixed. I've updated KoboldCPP, Ooba, and SillyTavern, as well as downloaded new quants from TheBloke, and I can still get nothing out of the thing, no matter which backend I ... | 2023-12-11T05:51:04 | https://www.reddit.com/r/LocalLLaMA/comments/18fnlhq/how_do_i_use_nouscapybara_34b/ | smile_e_face | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 18fnlhq | false | null | t3_18fnlhq | /r/LocalLLaMA/comments/18fnlhq/how_do_i_use_nouscapybara_34b/ | false | false | self | 3 | null |
Fine-tuning? Looking for help | 6 | Hey! I'm usually in the policy world, but I'm eager to get hands-on to learn. I believe understanding the tech firsthand can really boost my work. Does anyone have a beginner-friendly guide or tips on fine-tuning LLMs?
I don’t have special equipment (m1 Mac) but happy to throw in a few dollars toward a server to speed... | 2023-12-11T05:34:03 | https://www.reddit.com/r/LocalLLaMA/comments/18fnbpv/finetuning_looking_for_help/ | nembal | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 18fnbpv | false | null | t3_18fnbpv | /r/LocalLLaMA/comments/18fnbpv/finetuning_looking_for_help/ | false | false | self | 6 | null |
Got myself a Ghetto 4way rtx 4090 rig for local LLM | 17 | ​
https://preview.redd.it/trrsulesnl5c1.jpg?width=980&format=pjpg&auto=webp&s=9e004ab938808dc76abf05f6de4733019de5737a | 2023-12-11T05:15:39 | https://www.reddit.com/r/LocalLLaMA/comments/18fn0z5/got_myself_a_ghetto_4way_rtx_4090_rig_for_local/ | NerdyTurd6969 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 18fn0z5 | false | null | t3_18fn0z5 | /r/LocalLLaMA/comments/18fn0z5/got_myself_a_ghetto_4way_rtx_4090_rig_for_local/ | false | false | 17 | null | |
I have a Mac Studio (M2 Ultra). How do I create an API server for llama.cpp which I access remotely? Something like ChatGPT for my LAN | 4 | I know how to use llama.cpp and run local servers in terminal, but I want to be able to send API requests from other machines on the network (or even out of network if it's possible). This Mac Studio is located in my company office and I should use the company VPN to connect to it (I can SSH or do Screen Sharing). | 2023-12-11T03:13:14 | https://www.reddit.com/r/LocalLLaMA/comments/18fkwhf/i_have_a_mac_studio_m2_ultra_how_do_i_create_an/ | nderstand2grow | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 18fkwhf | false | null | t3_18fkwhf | /r/LocalLLaMA/comments/18fkwhf/i_have_a_mac_studio_m2_ultra_how_do_i_create_an/ | false | false | self | 4 | null |
Which Mac specs are needed to learn LLM also for inference, testing or evaluating accuracy etc. | 2 | Hi everyone,
I am a total beginner in LLMs. I would really appreciate some help.
I want to learn LLMs. I might have to download these LLMs and run them locally to test, play around and learn different concepts of LLM.
Standard M3 Pro Specs are: 11-core CPU, 14-core GPU, 18GB
Q1 - 18 GB RAM is not enough for LLM ... | 2023-12-11T02:56:09 | https://www.reddit.com/r/LocalLLaMA/comments/18fkksn/which_mac_specs_are_needed_to_learn_llm_also_for/ | Adventurous-Sign4520 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 18fkksn | false | null | t3_18fkksn | /r/LocalLLaMA/comments/18fkksn/which_mac_specs_are_needed_to_learn_llm_also_for/ | false | false | self | 2 | null |
Is there some trick to posting to the LLM leaderboard? | 2 | I've now sent over a dozen models to the leaderboard for evaluation, and only one has actually completed. I know the models work (and work well).
Each time, they enter the pending queue, then the running queue... then they disappear, no sign of them anywhere. I figured I was doing something wrong, but then one got thr... | 2023-12-11T02:52:59 | https://www.reddit.com/r/LocalLLaMA/comments/18fkikx/is_there_some_trick_to_posting_to_the_llm/ | athirdpath | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 18fkikx | false | null | t3_18fkikx | /r/LocalLLaMA/comments/18fkikx/is_there_some_trick_to_posting_to_the_llm/ | false | false | self | 2 | null |
How do you find out which model of any size is best for a certain task? Like the best 7b, 13b, and 30b models at following instructions or literature analysis? | 1 | [removed] | 2023-12-11T02:38:08 | https://www.reddit.com/r/LocalLLaMA/comments/18fk8d6/how_do_you_find_out_which_model_of_any_size_is/ | Rich_Examination_637 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 18fk8d6 | false | null | t3_18fk8d6 | /r/LocalLLaMA/comments/18fk8d6/how_do_you_find_out_which_model_of_any_size_is/ | false | false | self | 1 | null |
Need some advice, taking my first dip into LLM | 4 | Hi All,
Firstly, thank you for the awesome community and I learnt alot over the months reading this subreddit.
I am looking to take my first dip into running my own LLM.
I am scouting the used marketplace, and found a decently priced Mac Studio Max M1, 64 gb and 1 tb.
I know that the open-source community is moving... | 2023-12-11T02:22:45 | https://www.reddit.com/r/LocalLLaMA/comments/18fjxra/need_some_advice_taking_my_first_dip_into_llm/ | Alrightly | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 18fjxra | false | null | t3_18fjxra | /r/LocalLLaMA/comments/18fjxra/need_some_advice_taking_my_first_dip_into_llm/ | false | false | self | 4 | null |
Could goliath-120b be recreated on top of the 32k context Yarn base model? | 22 | I've just discovered this model that extends the base Llama 2 to 32k context with much better results than scaling up the alpha parameter: [https://huggingface.co/NousResearch/Yarn-Llama-2-70b-32k](https://huggingface.co/NousResearch/Yarn-Llama-2-70b-32k)
Would it be possible to re-create the two fine tuned models Xwi... | 2023-12-11T02:15:26 | https://www.reddit.com/r/LocalLLaMA/comments/18fjsv1/could_goliath120b_be_recreated_on_top_of_the_32k/ | aikitoria | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 18fjsv1 | false | null | t3_18fjsv1 | /r/LocalLLaMA/comments/18fjsv1/could_goliath120b_be_recreated_on_top_of_the_32k/ | false | false | self | 22 | {'enabled': False, 'images': [{'id': 'zvMLfOJtrIs8oCN8f-xJ-wMIOOb7cRqM2ZNXCTnZP88', 'resolutions': [{'height': 58, 'url': 'https://external-preview.redd.it/L8srrgOYB80t4f8JNUwJFBuV14P03TqOm9wk0h-pYrs.jpg?width=108&crop=smart&auto=webp&s=db20640534f321d327c13001460be1d802feca72', 'width': 108}, {'height': 116, 'url': 'h... |
Fine Tuning using Git Commits | 6 | Has anyone tried fine tuning a model using git commit information?
Could this be good for pointing the code gen capabilities to be more similar to the code style of your company, and better reproduce implementation patterns? | 2023-12-11T01:02:47 | https://www.reddit.com/r/LocalLLaMA/comments/18fifc2/fine_tuning_using_git_commits/ | guiHotz | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 18fifc2 | false | null | t3_18fifc2 | /r/LocalLLaMA/comments/18fifc2/fine_tuning_using_git_commits/ | false | false | self | 6 | null |
Fireworks.ai Mixtral vs GPT-4 turbo | 32 | 2023-12-11T00:22:49 | https://www.reddit.com/gallery/18fhmx1 | aue_sum | reddit.com | 1970-01-01T00:00:00 | 0 | {} | 18fhmx1 | false | null | t3_18fhmx1 | /r/LocalLLaMA/comments/18fhmx1/fireworksai_mixtral_vs_gpt4_turbo/ | false | false | 32 | null | ||
Is Llama Guard any good? | 1 | [removed] | 2023-12-11T00:17:02 | https://www.reddit.com/r/LocalLLaMA/comments/18fhiq9/is_llama_guard_any_good/ | InevitableSky2801 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 18fhiq9 | false | null | t3_18fhiq9 | /r/LocalLLaMA/comments/18fhiq9/is_llama_guard_any_good/ | false | false | self | 1 | {'enabled': False, 'images': [{'id': 'nkhh65ujo5BznFJFojoMPaKjGuLSpPj6KGhRov-ykOg', 'resolutions': [{'height': 108, 'url': 'https://external-preview.redd.it/0-fRWqjlLadVXj5pfYp4_Oe3xgBWE-_rdjVSn7hlohI.jpg?width=108&crop=smart&auto=webp&s=f34d2dfdbbfa7de0f1956f186fd8430ee96a1a55', 'width': 108}, {'height': 216, 'url': '... |
Sorry if this is a dumb question but is the main idea behind LLMs to output text based on user input? | 21 | I just want to clarify my understanding of large language models is someone doesn't mind dumbing it down for me. My understanding is that there is of course a lot of math that computations that happens behind the scenes but ultimately this boils down input -> LLM -> output. It returning text back from user input, is th... | 2023-12-11T00:14:41 | https://www.reddit.com/r/LocalLLaMA/comments/18fhgzf/sorry_if_this_is_a_dumb_question_but_is_the_main/ | Suspicious_Two1151 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 18fhgzf | false | null | t3_18fhgzf | /r/LocalLLaMA/comments/18fhgzf/sorry_if_this_is_a_dumb_question_but_is_the_main/ | false | false | self | 21 | null |
Help, please: LLM 'glitches' after ~14 Prompt/Response | 5 | llama2\_70b\_chat\_uncensored.Q5\_K\_M.gguf running in Text Gen WebUI on M3 128 / 16 core cpu / 40 core GPU.
The following issue repeats itself regardless of which model I run (7B, 13B, 33B, 70B, all quantized): After 14 Prompt/Response exchanges, the model responds in an infinite loop of jibberish. Is there a co... | 2023-12-10T23:27:41 | https://www.reddit.com/r/LocalLLaMA/comments/18fgidr/help_please_llm_glitches_after_14_promptresponse/ | knob-0u812 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 18fgidr | false | null | t3_18fgidr | /r/LocalLLaMA/comments/18fgidr/help_please_llm_glitches_after_14_promptresponse/ | false | false | 5 | null | |
Best open-source locally downloadable LLM? | 4 | Preferably uncensored, token generation rate doesn't matter I'll leave my pc running for days on a singular prompt. Just the best for text completion and general inquiries. | 2023-12-10T21:18:26 | https://www.reddit.com/r/LocalLLaMA/comments/18fdo2v/best_opensource_locally_downloadable_llm/ | Role-Fluffy | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 18fdo2v | false | null | t3_18fdo2v | /r/LocalLLaMA/comments/18fdo2v/best_opensource_locally_downloadable_llm/ | false | false | self | 4 | null |
Are big models always better than small ones for Transfer Learning? | 3 | I have a private niche dataset that I've personally compiled over years on Excel and I feel like using Mistral 7B for transfer learning Instead of Llama 2 70B. I know it impacts the performance but does this choice impact performance significantly given my dataset is small (approximately 2.4 million rows) if I choose M... | 2023-12-10T21:16:30 | https://www.reddit.com/r/LocalLLaMA/comments/18fdmlb/are_big_models_always_better_than_small_ones_for/ | hackeddevil | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 18fdmlb | false | null | t3_18fdmlb | /r/LocalLLaMA/comments/18fdmlb/are_big_models_always_better_than_small_ones_for/ | false | false | self | 3 | null |
Further pre-train llama | 3 | So, I need a local LLM that understands portuguese. However, even llama 70b seems to mix up things in this language. After researching, I found out that llama 70b has less than one percent of data in portuguese. Therefore, fine-tuning wouldn’t be the choice, since it doesn’t even have enough tokens in my language. I’d ... | 2023-12-10T21:14:56 | https://www.reddit.com/r/LocalLLaMA/comments/18fdlcu/further_pretrain_llama/ | Original_Job6327 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 18fdlcu | false | null | t3_18fdlcu | /r/LocalLLaMA/comments/18fdlcu/further_pretrain_llama/ | false | false | self | 3 | null |
Local Raspberry pi LLM setup | 1 | [removed] | 2023-12-10T21:10:57 | https://www.reddit.com/r/LocalLLaMA/comments/18fdic3/local_raspberry_pi_llm_setup/ | dnllvrvz | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 18fdic3 | false | null | t3_18fdic3 | /r/LocalLLaMA/comments/18fdic3/local_raspberry_pi_llm_setup/ | false | false | self | 1 | {'enabled': False, 'images': [{'id': '9FQgD2CU2lz6aGiGDnwfQiINpgqUaIvcC9jwJuKV7TY', 'resolutions': [{'height': 81, 'url': 'https://external-preview.redd.it/w1MEqCMLpYNwwvzRg_E4LUF02IAngouDr3q0QuquNZE.jpg?width=108&crop=smart&auto=webp&s=41353cb98251b7ff46ec5c05ea4c34255b8533be', 'width': 108}, {'height': 162, 'url': 'h... |
Instruction at the beginning or end? | 3 | As I slowly go through building my internal thing for evaluating LLMs another thing came to my mind. When presented with bigger task / tasks with more context - should you put the instructions at the beginning or end of the prompt? I.e., let's assume we have alpca format and the task is summarization
```md
### Input:
... | 2023-12-10T20:31:38 | https://www.reddit.com/r/LocalLLaMA/comments/18fcmip/instruction_at_the_beginning_or_end/ | VertexMachine | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 18fcmip | false | null | t3_18fcmip | /r/LocalLLaMA/comments/18fcmip/instruction_at_the_beginning_or_end/ | false | false | self | 3 | null |
PDF mapping using LLM | 1 | [removed] | 2023-12-10T20:20:05 | https://www.reddit.com/r/LocalLLaMA/comments/18fcd88/pdf_mapping_using_llm/ | Tejasw__ | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 18fcd88 | false | null | t3_18fcd88 | /r/LocalLLaMA/comments/18fcd88/pdf_mapping_using_llm/ | false | false | self | 1 | null |
Easiest way to show my model to my mom? | 10 | I fine-tuned Mistral7B for a school project and created a chat application and I want to show my mom.
My problem is that my PC in my dorm can run this just fine but for the holidays im at home with a laptop that can’t run the model locally.
What would be the easiest/cheapest way to host this with a chat interface li... | 2023-12-10T19:56:00 | https://www.reddit.com/r/LocalLLaMA/comments/18fbtj0/easiest_way_to_show_my_model_to_my_mom/ | ItsPattex | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 18fbtj0 | false | null | t3_18fbtj0 | /r/LocalLLaMA/comments/18fbtj0/easiest_way_to_show_my_model_to_my_mom/ | false | false | self | 10 | null |
Long Form Writing Models? | 6 | While 200k token context windows in language models are impressive, I've noticed that their output doesn't match this potential scale. In my experience, trying various models with contexts ranging from 4k to 200k tokens, the outputs generally hover between 500 to 1500 words. This leaves me wondering: is there a model ... | 2023-12-10T19:44:37 | https://www.reddit.com/r/LocalLLaMA/comments/18fbk5e/long_form_writing_models/ | Danny_Davitoe | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 18fbk5e | false | null | t3_18fbk5e | /r/LocalLLaMA/comments/18fbk5e/long_form_writing_models/ | false | false | self | 6 | null |
All models failing 20 questions? | 18 | Is any local model able to play “20 questions” where either you or the LLM has to guess an object in 20 questions or less?
I feel like this is a pretty interesting benchmark pointing towards non autocomplete emergent intelligence.
All models i’ve tried (up to 33b) fails this dynamic either changing roles, saying “yes... | 2023-12-10T19:31:00 | https://www.reddit.com/r/LocalLLaMA/comments/18fb8yh/all_models_failing_20_questions/ | Fun_Land_6604 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 18fb8yh | false | null | t3_18fb8yh | /r/LocalLLaMA/comments/18fb8yh/all_models_failing_20_questions/ | false | false | self | 18 | null |
Benchmarks results reveal Mixtral-8x7B BEATS LLaMA-2-70b | 74 | Open Compass have just benched it. Confirms informal benchmarks I have seen elsewhere. | 2023-12-10T19:27:38 | PookaMacPhellimen | i.redd.it | 1970-01-01T00:00:00 | 0 | {} | 18fb675 | false | null | t3_18fb675 | /r/LocalLLaMA/comments/18fb675/benchmarks_results_reveal_mixtral8x7b_beats/ | false | false | 74 | {'enabled': True, 'images': [{'id': 'BvjbnjuHq4Bk4Py5qg9Y-jSpHkwnKI5tQWCYVS3Ed20', 'resolutions': [{'height': 54, 'url': 'https://preview.redd.it/tn1yqd3yqi5c1.jpeg?width=108&crop=smart&auto=webp&s=e6785f345271a45970d0fb3762bef2ef953666b0', 'width': 108}, {'height': 108, 'url': 'https://preview.redd.it/tn1yqd3yqi5c1.jp... | ||
Please share your latest coding llm stack | 3 | As rhe title suggests, please share your coding llm stack
Are you primarily using deepseek, wizard coder or somethin else, would love to learn from people who knows their stuff | 2023-12-10T19:09:55 | https://www.reddit.com/r/LocalLLaMA/comments/18faryl/please_share_your_latest_coding_llm_stack/ | Jasssinghhira | self.LocalLLaMA | 2023-12-11T00:22:40 | 0 | {} | 18faryl | false | null | t3_18faryl | /r/LocalLLaMA/comments/18faryl/please_share_your_latest_coding_llm_stack/ | false | false | self | 3 | null |
Ollama on jetson orin not using GPU | 1 | [removed] | 2023-12-10T18:53:27 | https://www.reddit.com/r/LocalLLaMA/comments/18faew1/ollama_on_jetson_orin_not_using_gpu/ | Organic_Club_5959 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 18faew1 | false | null | t3_18faew1 | /r/LocalLLaMA/comments/18faew1/ollama_on_jetson_orin_not_using_gpu/ | false | false | self | 1 | null |
Some small pieces of statistics. Mixtral-8x7B-Chat(Mixtral finetune by Fireworks.ai) on Poe.com gets the armageddon question right. Not even 70Bs can get this(Surprisingly, they can't even make a legal hallucination that makes sense.). I think everyone would find this interesting. | 87 | 2023-12-10T18:38:13 | bot-333 | i.redd.it | 1970-01-01T00:00:00 | 0 | {} | 18fa36a | false | null | t3_18fa36a | /r/LocalLLaMA/comments/18fa36a/some_small_pieces_of_statistics/ | false | false | 87 | {'enabled': True, 'images': [{'id': 'ReN_m3MKWCTCrWYQT_GbBHh602fyHo00siqeR9SUNTA', 'resolutions': [{'height': 88, 'url': 'https://preview.redd.it/t9gcrt03ii5c1.png?width=108&crop=smart&auto=webp&s=0ad3058953e9c20f02bdb633831d0101ebdc62a2', 'width': 108}, {'height': 176, 'url': 'https://preview.redd.it/t9gcrt03ii5c1.png... | |||
Some small pieces of statistics. Mixtral-8x7B-Chat(Mixtral finetune by Fireworks.ai) on Poe.com gets armageddon question right. Not even 70Bs can get this(Surprisingly, they can't even make a legal hallucination that makes sense.). I think everyone would find this interesting. | 1 | [deleted] | 2023-12-10T18:37:10 | bot-333 | i.redd.it | 1970-01-01T00:00:00 | 0 | {} | 18fa2cw | false | null | t3_18fa2cw | /r/LocalLLaMA/comments/18fa2cw/some_small_pieces_of_statistics/ | false | false | 1 | {'enabled': True, 'images': [{'id': '2z2_eYTOaQLbzM47NkmDdR1gAihoHqaGsCOPdzzwsoY', 'resolutions': [{'height': 88, 'url': 'https://preview.redd.it/wegf0n2chi5c1.png?width=108&crop=smart&auto=webp&s=c727737a5f0b38d06edeb8abb5221109df5d979f', 'width': 108}, {'height': 176, 'url': 'https://preview.redd.it/wegf0n2chi5c1.png... | ||
SML specifically for creating JSON? | 5 | In 90% of cases in which i use LLMs i actually only convert whatever unstructured input i have into JSON to further work with it. That model does not need to know the capital of france or how to cook a risotto or give me a poem on cooking risotto in france, but just be good at logic.
Is there a small language model t... | 2023-12-10T18:32:44 | https://www.reddit.com/r/LocalLLaMA/comments/18f9yw5/sml_specifically_for_creating_json/ | ComprehensiveBird317 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 18f9yw5 | false | null | t3_18f9yw5 | /r/LocalLLaMA/comments/18f9yw5/sml_specifically_for_creating_json/ | false | false | self | 5 | null |
Experimental Mixtral MoE on vLLM! | 11 | https://github.com/EmbeddedLLM/vllm-rocm/tree/mixtral8x7b
Now if only we can have quantisation happen too 🙏 | 2023-12-10T18:16:05 | https://www.reddit.com/r/LocalLLaMA/comments/18f9lhm/experimental_mixtral_moe_on_vllm/ | Eastwindy123 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 18f9lhm | false | null | t3_18f9lhm | /r/LocalLLaMA/comments/18f9lhm/experimental_mixtral_moe_on_vllm/ | false | false | self | 11 | {'enabled': False, 'images': [{'id': 'Sm3hC_pgQ5pu2OfFflkS9q-9vy01vL-Bfq7P0CyPnBk', 'resolutions': [{'height': 54, 'url': 'https://external-preview.redd.it/oj4ZFcHUPwqR78wlLhHqV7m-LLKY7sEUPajW8bza3RA.jpg?width=108&crop=smart&auto=webp&s=3c7c4d41850da30a4234f57aeef2fb50142959b9', 'width': 108}, {'height': 108, 'url': 'h... |
Help decide wich LLaMA- NOOB | 3 | Hi. Questions from a Noob
For my home system:
RYZEN 7940HS- 16 TO 32 GB 5600MHZ DDR5
1- BEST general purpose till today LLaMA for this system
2- will it use CPU AND GPU AND the internal chiplet dedicated A.I from AMD?
3- Instal on Linux or Windows?
4- Other ideia
5- Best way for install
​ | 2023-12-10T17:57:19 | https://www.reddit.com/r/LocalLLaMA/comments/18f96a7/help_decide_wich_llama_noob/ | maxpayne07 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 18f96a7 | false | null | t3_18f96a7 | /r/LocalLLaMA/comments/18f96a7/help_decide_wich_llama_noob/ | false | false | self | 3 | null |
Desktop AI, anyone tried this? | 2 | 2023-12-10T17:48:58 | https://www.reddit.com/gallery/18f8zs9 | Obvious-Double-8692 | reddit.com | 1970-01-01T00:00:00 | 0 | {} | 18f8zs9 | false | null | t3_18f8zs9 | /r/LocalLLaMA/comments/18f8zs9/desktop_ai_anyone_tried_this/ | false | false | default | 2 | null | |
Noob question on AI development | 3 | Dear AI enthusiasts,
I am looking to learn AI development for a very specific need. If I were to train/develop an AI model to the following: Understand a prescription, medical history then suggest a diet plan based on allergies etc what do you think my approach should be? Is there any exisiting model that can be trai... | 2023-12-10T17:41:12 | https://www.reddit.com/r/LocalLLaMA/comments/18f8to3/noob_question_on_ai_development/ | DeyVinci | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 18f8to3 | false | null | t3_18f8to3 | /r/LocalLLaMA/comments/18f8to3/noob_question_on_ai_development/ | false | false | self | 3 | null |
Questions about Training Data | 1 | Hello r/LocalLLaMA! I am an aspiring human-computer interaction researcher, and in my recent queries for how user-generated content relates to AI models, I have become quite curious in the recent development of training data.
My understanding is that GPT-3 was trained with largely internet data (from CommonCrawl), and... | 2023-12-10T17:38:09 | https://www.reddit.com/r/LocalLLaMA/comments/18f8res/questions_about_training_data/ | _kevinlee | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 18f8res | false | null | t3_18f8res | /r/LocalLLaMA/comments/18f8res/questions_about_training_data/ | false | false | self | 1 | null |
Desktop AI, Anyone Tried This? | 1 | Just started messing around with desktop AI. Found this open-source thing. Any of you checked it out? [https://jan.ai/](https://jan.ai/)
[https://github.com/janhq/jan](https://github.com/janhq/jan)
https://preview.redd.it/q2gdewj47i5c1.png?width=2940&format=png&auto=webp&s=3e9ce81d87103f19c62e135a3c1a8ccc12056be... | 2023-12-10T17:37:39 | https://www.reddit.com/r/LocalLLaMA/comments/18f8r18/desktop_ai_anyone_tried_this/ | Obvious-Double-8692 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 18f8r18 | false | null | t3_18f8r18 | /r/LocalLLaMA/comments/18f8r18/desktop_ai_anyone_tried_this/ | false | false | 1 | null | |
How to deal with loss for SFT for CausalLM | 3 | I'm currently trying to finetune Llama2 chat model.
​
The task is causal language modeling and I'm exploiting custom dataset, consisting of domain specific prompts and corresponding answers.
​
I'm currently using SFT trainer([https://huggingface.co/docs/trl/sft\_trainer](https://huggingface.co/docs/tr... | 2023-12-10T17:29:59 | https://www.reddit.com/r/LocalLLaMA/comments/18f8kxe/how_to_deal_with_loss_for_sft_for_causallm/ | __given__ | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 18f8kxe | false | null | t3_18f8kxe | /r/LocalLLaMA/comments/18f8kxe/how_to_deal_with_loss_for_sft_for_causallm/ | false | false | 3 | null | |
ollama local - smart file manager? | 2 | I have installed ollama and am running llama2 and mistral-openorca with no issues from the command line. I 've seen articles on training and on langchain. The computer is running ubuntu 22.04 new fresh install. hardware is aorus mb with ryzen threadripper 24 core, 128 GB RAM, nvidia RTX 3060 w 12 GB VRAM, if it matters... | 2023-12-10T17:28:35 | https://www.reddit.com/r/LocalLLaMA/comments/18f8jwo/ollama_local_smart_file_manager/ | justsayno_to_biggovt | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 18f8jwo | false | null | t3_18f8jwo | /r/LocalLLaMA/comments/18f8jwo/ollama_local_smart_file_manager/ | false | false | self | 2 | null |
Subsets and Splits
No community queries yet
The top public SQL queries from the community will appear here once available.