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 ⌀ |
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
To finetune or use a vector db? | 8 | We started a few months ago on a journey using Pinecone vector DB with the openai api. I’m interested in finetuning my own local model but I’m unsure whether it would be better to finetune or continue using a vector db for referencing my company content?
Any recommendations are appreciated.
Additional Qs:
Should I s... | 2023-11-07T01:59:46 | https://www.reddit.com/r/LocalLLaMA/comments/17pjk4b/to_finetune_or_use_a_vector_db/ | rich_atl | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 17pjk4b | false | null | t3_17pjk4b | /r/LocalLLaMA/comments/17pjk4b/to_finetune_or_use_a_vector_db/ | false | false | self | 8 | null |
Yi-34B-200K works on a single 3090 with 47K context/4bpw | 61 | I just spent more time that I'd like messing with Yi 200K before even testing it. Some notes to save others trouble, in case anyone is thinking about trying it:
* install exllamav2 from git with `pip install git+https://github.com/turboderp/exllamav2.git`. Make sure you have flash attention 2 as well.
* If you use lon... | 2023-11-07T01:21:32 | https://www.reddit.com/r/LocalLLaMA/comments/17pisuk/yi34b200k_works_on_a_single_3090_with_47k/ | mcmoose1900 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 17pisuk | false | null | t3_17pisuk | /r/LocalLLaMA/comments/17pisuk/yi34b200k_works_on_a_single_3090_with_47k/ | false | false | self | 61 | {'enabled': False, 'images': [{'id': '7S9Db1j2Jrs6n9j_iUSwJOf_qde3cKK3HAs51mEC0tM', 'resolutions': [{'height': 58, 'url': 'https://external-preview.redd.it/9GtXoliCUgG8AYfvXB3XQYrfs0HbBHX9EOQgnCb6eA0.jpg?width=108&crop=smart&auto=webp&s=71cb210a08f1c7da1871a330cf9d954a0b49b58c', 'width': 108}, {'height': 116, 'url': 'h... |
Benefits/Challenges using multiple GPUs | 3 | I have an RTX 4080 (16GB) and that works pretty good for most of my work/tests. I do stick to 7b/13b models for the most part because anything with the larger modes gets too slow. Especially for fine tuning 16GB is too limiting. Used cards like the Tesla P40 (24GB) can be bought very cheap these days (around $175). Is ... | 2023-11-07T01:15:11 | https://www.reddit.com/r/LocalLLaMA/comments/17pio9u/benefitschallenges_using_multiple_gpus/ | gamesntech | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 17pio9u | false | null | t3_17pio9u | /r/LocalLLaMA/comments/17pio9u/benefitschallenges_using_multiple_gpus/ | false | false | self | 3 | null |
New to local models, and after doing my research I'm still looking for answers to some basic questions | 2 | Hi all, I made sure to read many threads in this subreddit but still have some clarifying questions. Thanks in advance for your patience; I think I'm a little slow ha.
1) The reasons to run a local (read: non-OpenAI) setup are basically privacy, avoiding censorship, tinkering/hobbying, trying out other models, and im... | 2023-11-07T00:30:13 | https://www.reddit.com/r/LocalLLaMA/comments/17phr1b/new_to_local_models_and_after_doing_my_research/ | False_Pay_4009 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 17phr1b | false | null | t3_17phr1b | /r/LocalLLaMA/comments/17phr1b/new_to_local_models_and_after_doing_my_research/ | false | false | self | 2 | null |
Powerful Budget AI-Workstation Build Guide (48 GB VRAM @ $1.1k) | 57 | I built an AI workstation with 48 GB of VRAM, capable of running LLAMA 2 70b 4bit sufficiently at the price of $1,092 for the total end build. I got decent stable diffusion results as well, but this build definitely focused on local LLM's, as you could build a much better and cheaper build if you were planning to do fa... | 2023-11-07T00:22:08 | https://www.reddit.com/r/LocalLLaMA/comments/17phkwi/powerful_budget_aiworkstation_build_guide_48_gb/ | crossivejoker | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 17phkwi | false | null | t3_17phkwi | /r/LocalLLaMA/comments/17phkwi/powerful_budget_aiworkstation_build_guide_48_gb/ | false | false | self | 57 | {'enabled': False, 'images': [{'id': 'd8z_gVq50EBweQqdViAAKvfYXYTno4zPBLHxaAXEy80', 'resolutions': [{'height': 54, 'url': 'https://external-preview.redd.it/aRmWvv1UR-euWAjHnsZ5LV5FJYJgpgMj9Mew5_pHGXU.jpg?width=108&crop=smart&auto=webp&s=bc39e6cd1dc9b02d31051cb05bcca5bf4afec1e6', 'width': 108}, {'height': 108, 'url': 'h... |
GPT-4 Turbo and why it outputs up to 4K tokens. | 5 | So, the new [GPT-4 Turbo generates up to 4096 tokens](https://platform.openai.com/docs/models/gpt-4-and-gpt-4-turbo).
But it got me thinking, why would a model with a ctx of up to 128k tokens only output 4096 tokens? What long contexts have taught us, is that models trained with long contexts do not perform as good wi... | 2023-11-06T23:47:40 | https://www.reddit.com/r/LocalLLaMA/comments/17pguv6/gpt4_turbo_and_why_it_outputs_up_to_4k_tokens/ | 2muchnet42day | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 17pguv6 | false | null | t3_17pguv6 | /r/LocalLLaMA/comments/17pguv6/gpt4_turbo_and_why_it_outputs_up_to_4k_tokens/ | false | false | self | 5 | {'enabled': False, 'images': [{'id': 'XjYeH9UKcgyOWN9BfsAvdRtig11MoY4NbGzf8T8tohc', 'resolutions': [{'height': 56, 'url': 'https://external-preview.redd.it/nEedMLn73AsJU6AgxrHz6cvr0_KUZAuY26VUpixUKp8.jpg?width=108&crop=smart&auto=webp&s=3f9105ef3e7b58900470546335a78fe533005bb4', 'width': 108}, {'height': 113, 'url': 'h... |
Are there any "truly" uncensored models? | 1 | [removed] | 2023-11-06T23:29:44 | https://www.reddit.com/r/LocalLLaMA/comments/17pggwu/are_there_any_truly_uncensored_models/ | estrosfere | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 17pggwu | false | null | t3_17pggwu | /r/LocalLLaMA/comments/17pggwu/are_there_any_truly_uncensored_models/ | false | false | self | 1 | null |
How do you compare 100s of documents with a local LLM? | 5 | I have identified some dimensions (say 10) to compare some documents (language, size, security, complexity, scalability, privacy, etc). What approach do you use to do this with a local LLM?
I thought I'd first create a vectorstore from the documents, and then run the following query in a loop:
query = f"Summarise... | 2023-11-06T22:55:40 | https://www.reddit.com/r/LocalLLaMA/comments/17pfpm5/how_do_you_compare_100s_of_documents_with_a_local/ | ResearcherNo4728 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 17pfpm5 | false | null | t3_17pfpm5 | /r/LocalLLaMA/comments/17pfpm5/how_do_you_compare_100s_of_documents_with_a_local/ | false | false | self | 5 | null |
Fine-Tune an Embedding Model for RAG? | 3 | Did anyone fine-tune an existing embedding model for RAG? I have german texts and I am looking for ressources. I saw that people used a synthetic dataset from OpenAI API to fine-tune their model. Is it worth it (especially for German)? | 2023-11-06T22:10:02 | https://www.reddit.com/r/LocalLLaMA/comments/17pen2t/finetune_an_embedding_model_for_rag/ | LargeBrick7 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 17pen2t | false | null | t3_17pen2t | /r/LocalLLaMA/comments/17pen2t/finetune_an_embedding_model_for_rag/ | false | false | self | 3 | null |
I used the gpt-4 Turbo in the API and it was worse | 75 | Considering that the gpt-4-1106-preview for the api is already out, which is the GPT-4 Turbo, i thought i give it a try and see whether it could do the task the previous gpt-4 does in my project. I replaced it and it failed instantly. It was a assigning and formatting task where i give him a row of videos with descript... | 2023-11-06T21:25:55 | https://www.reddit.com/r/LocalLLaMA/comments/17pdkfx/i_used_the_gpt4_turbo_in_the_api_and_it_was_worse/ | StrangeImagination5 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 17pdkfx | false | null | t3_17pdkfx | /r/LocalLLaMA/comments/17pdkfx/i_used_the_gpt4_turbo_in_the_api_and_it_was_worse/ | false | false | self | 75 | null |
Google doesn't have a moat, openai does | 316 | 6 months after the leaked "We have no moat, neither does openai" memo, it is clear that indeed google didn't/doesn't have a moat regarding LLM.
Openai, on the other hand, does have a moat. And it's a big one.
Their gpt-4 has been the unrivalled LLM for 8 months straight with no other model approaching its general cap... | 2023-11-06T21:01:29 | https://www.reddit.com/r/LocalLLaMA/comments/17pcyfb/google_doesnt_have_a_moat_openai_does/ | Amgadoz | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 17pcyfb | false | null | t3_17pcyfb | /r/LocalLLaMA/comments/17pcyfb/google_doesnt_have_a_moat_openai_does/ | false | false | self | 316 | null |
New model ‘GPT-4 Turbo’ | 1 | [removed] | 2023-11-06T20:26:55 | adesigne | i.redd.it | 1970-01-01T00:00:00 | 0 | {} | 17pc5fd | false | null | t3_17pc5fd | /r/LocalLLaMA/comments/17pc5fd/new_model_gpt4_turbo/ | false | false | 1 | {'enabled': True, 'images': [{'id': 'noy7JMY25HGpORNgtXP4Dikg5upylBVGTLoQwQ3fWuE', 'resolutions': [{'height': 68, 'url': 'https://preview.redd.it/lbkv8m5jesyb1.jpg?width=108&crop=smart&auto=webp&s=1974a5c51f09b88cb0c7d80aaa90f124ab9927f0', 'width': 108}, {'height': 136, 'url': 'https://preview.redd.it/lbkv8m5jesyb1.jpg... | ||
Preview-version of GPT-4 Turbo has been released. What does this mean for local LLMs? | 40 | [Model page](https://help.openai.com/en/articles/8555510-gpt-4-turbo)
[Announcement post](https://openai.com/blog/new-models-and-developer-products-announced-at-devday)
\- 128k context (4k for model output limit)
\- knowledge cutoff of April 2023
\- cheaper than GPT-4 [\[pricing\]](https://openai.com/pricing#gpt-... | 2023-11-06T20:24:14 | https://www.reddit.com/r/LocalLLaMA/comments/17pc36o/previewversion_of_gpt4_turbo_has_been_released/ | remixer_dec | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 17pc36o | false | null | t3_17pc36o | /r/LocalLLaMA/comments/17pc36o/previewversion_of_gpt4_turbo_has_been_released/ | false | false | self | 40 | null |
Extracting data from emails for training? | 1 | Does anyone know of a good tool that can connect to a mailbox (e.g. over IMAP) and save the contents in a CSV or JSON file suitable for LLM training? I started writing my own but it's more complicated than it first seems as you need to strip out all the mail signatures and handle email chains with multiple nested repli... | 2023-11-06T20:20:08 | https://www.reddit.com/r/LocalLLaMA/comments/17pbznl/extracting_data_from_emails_for_training/ | davew111 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 17pbznl | false | null | t3_17pbznl | /r/LocalLLaMA/comments/17pbznl/extracting_data_from_emails_for_training/ | false | false | self | 1 | null |
How to use the Huggingfance inference API? | 1 | I'm currently trying to figure out how to use the models on hugginface with their inference api. Right now i try to use the Zephyr-7b-beta model ([https://huggingface.co/HuggingFaceH4/zephyr-7b-beta](https://huggingface.co/HuggingFaceH4/zephyr-7b-beta))
On the page it tells me, that the inference api is enabled for th... | 2023-11-06T20:14:41 | https://www.reddit.com/r/LocalLLaMA/comments/17pbva4/how_to_use_the_huggingfance_inference_api/ | StrangeImagination5 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 17pbva4 | false | null | t3_17pbva4 | /r/LocalLLaMA/comments/17pbva4/how_to_use_the_huggingfance_inference_api/ | false | false | 1 | {'enabled': False, 'images': [{'id': 'wTvEuGH623MKIN1j-YQrV723y3Wpr65tJmQjmMuI820', 'resolutions': [{'height': 58, 'url': 'https://external-preview.redd.it/BK2HxrkacYTlXTSl68JcO9bBCN6JLUPlVdYqOh9W6OY.jpg?width=108&crop=smart&auto=webp&s=ddb5bdeab6a052c01e76b31ce0c6a4a3d239cf4a', 'width': 108}, {'height': 116, 'url': 'h... | |
Llama.cpp with Facebook Sourced llama-2-7b. | 2 | I’m trying to get a local models running using Llama.cpp together with text-generation-webui.
I downloaded my models (llama-2-7b/13b/70b) but the included files are; checklist.txt, consolidated.00.pth and params.json.
I try to use llama.cpp to convert to a GGUF but repeatedly get the errors “Could not find tokenize... | 2023-11-06T20:12:16 | https://www.reddit.com/r/LocalLLaMA/comments/17pbt9i/llamacpp_with_facebook_sourced_llama27b/ | HAMBoneConnection | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 17pbt9i | false | null | t3_17pbt9i | /r/LocalLLaMA/comments/17pbt9i/llamacpp_with_facebook_sourced_llama27b/ | false | false | self | 2 | null |
Testing models for AI creative writing. | 4 | So i use my LLMs for creative writing, namely erotic stories. I have come to accept that i have to work WITH the machine as opposed to having the machine work for me as from my experience it's extremely stressful dealing with unruly LLMs.
So i come to you with a question. I am prompting this. at 200 max token paramete... | 2023-11-06T19:56:47 | https://www.reddit.com/r/LocalLLaMA/comments/17pbg81/testing_models_for_ai_creative_writing/ | DominicanGreg | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 17pbg81 | false | null | t3_17pbg81 | /r/LocalLLaMA/comments/17pbg81/testing_models_for_ai_creative_writing/ | false | false | self | 4 | null |
llama cpp python cuda error | 1 |
hi
I am using the latest langchain to load llama cpp
installed llama cpp python with: CMAKE\_ARGS="-DLLAMA\_METAL=on" FORCE\_CMAKE=1 pip install llama-cpp-python
nvcc --version
nvcc: NVIDIA (R) Cuda compiler driver
Copyright (c) 2005-2023 NVIDIA Corporation
Built on Tue\_Jul\_11\_02:20:44\_PDT\_2023
Cu... | 2023-11-06T19:41:32 | https://www.reddit.com/r/LocalLLaMA/comments/17pb3kz/llama_cpp_python_cuda_error/ | msRachels | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 17pb3kz | false | null | t3_17pb3kz | /r/LocalLLaMA/comments/17pb3kz/llama_cpp_python_cuda_error/ | false | false | self | 1 | null |
Anyone tried whisper large v3 | 1 | [removed] | 2023-11-06T19:21:52 | https://www.reddit.com/r/LocalLLaMA/comments/17pan18/anyone_tried_whisper_large_v3/ | ThenNeighborhood3723 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 17pan18 | false | null | t3_17pan18 | /r/LocalLLaMA/comments/17pan18/anyone_tried_whisper_large_v3/ | false | false | self | 1 | {'enabled': False, 'images': [{'id': 'Jui9Sa2zDoOCwA5CC8wIzHQuUlUTSopiMcxPZTFbSN4', 'resolutions': [{'height': 54, 'url': 'https://external-preview.redd.it/BNBOZQR3Gcxrgo9qpJwn956Woc8luapwT7hgMQiiRQk.jpg?width=108&crop=smart&auto=webp&s=5626dbad58504fbba97383c5cd3b4405604d9943', 'width': 108}, {'height': 108, 'url': 'h... |
OpenAI Dev Day Discussion | 1 | Haven’t seen any threads on discussing the OpenAI dev day, so here is a place we can discuss new functionality being announced! | 2023-11-06T18:37:58 | https://www.reddit.com/r/LocalLLaMA/comments/17p9mgc/openai_dev_day_discussion/ | Slimxshadyx | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 17p9mgc | false | null | t3_17p9mgc | /r/LocalLLaMA/comments/17p9mgc/openai_dev_day_discussion/ | false | false | self | 1 | null |
Is local LLM models (Zephyr, Mistral, etc..) good enough to generate embeddings? (using Ollama) | 2 | Hi everyone.
I'm a little confused about Ollama embeddings.
It seems like we could just use our LLM models like Mistral / Zephyr / Llama to do embeddings.
But when I search on Youtube people are much smaller models that specializes in embeddings only.
Do I have to use those small models that specializes in embeddin... | 2023-11-06T18:16:58 | https://www.reddit.com/r/LocalLLaMA/comments/17p94ss/is_local_llm_models_zephyr_mistral_etc_good/ | Uncensored4488 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 17p94ss | false | null | t3_17p94ss | /r/LocalLLaMA/comments/17p94ss/is_local_llm_models_zephyr_mistral_etc_good/ | false | false | self | 2 | null |
The OG LLM in 1983 on the Johnny Carson show. | 4 | See how far we've come in 40 years?
Johnny Carson, 1983
[https://www.youtube.com/watch?v=p6uFHC9lfzk](https://www.youtube.com/watch?v=p6uFHC9lfzk)
(for entertainment purposes only) | 2023-11-06T17:58:33 | https://www.reddit.com/r/LocalLLaMA/comments/17p8p0h/the_og_llm_in_1983_on_the_johnny_carson_show/ | jubjub07 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 17p8p0h | false | null | t3_17p8p0h | /r/LocalLLaMA/comments/17p8p0h/the_og_llm_in_1983_on_the_johnny_carson_show/ | false | false | self | 4 | {'enabled': False, 'images': [{'id': 'Xmz-cR5zsf4tMRFtf_utuniJmZ_EeSu6FJQEbM9ZaR0', 'resolutions': [{'height': 81, 'url': 'https://external-preview.redd.it/OI9aplIXkyirQ2Nj0nmRwpNeorqSC-r1o2NxFzXgVqk.jpg?width=108&crop=smart&auto=webp&s=e437bfba913ac0824f00b8a4adcb12979ead06d4', 'width': 108}, {'height': 162, 'url': 'h... |
Runpod vs Sagemaker speed | 2 | I am trying to transfer mistral 7b from sagemaker to runpod. On sagemaker i run an instance with 1x A10 and i tried with RTX 4090 on runpod. The issue that i have is that the same model takes 1 minute to complete the task on Sagemaker but 5m on Runpod, i even tried with H100 on runpod but the result was the same. Any i... | 2023-11-06T17:47:34 | https://www.reddit.com/r/LocalLLaMA/comments/17p8fq4/runpod_vs_sagemaker_speed/ | kbourro | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 17p8fq4 | false | null | t3_17p8fq4 | /r/LocalLLaMA/comments/17p8fq4/runpod_vs_sagemaker_speed/ | false | false | self | 2 | null |
How do you generate a single response with chat models? | 1 | All the models I use seem to generate the whole conversation instead of giving a single response in role play chat settings. Is there a good prompt or a model to prevent this? I know I can cut the rest of the conversation but the generation wastes resources. | 2023-11-06T17:47:15 | https://www.reddit.com/r/LocalLLaMA/comments/17p8fgw/how_do_you_generate_a_single_response_with_chat/ | demegir | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 17p8fgw | false | null | t3_17p8fgw | /r/LocalLLaMA/comments/17p8fgw/how_do_you_generate_a_single_response_with_chat/ | false | false | self | 1 | null |
OpenAi live stream keynote soon | 2 | Wildest rumors were that they would open source gpt3.
Live stream starts soon at: [https://www.youtube.com/watch?v=U9mJuUkhUzk&ab\_channel=OpenAI](https://www.youtube.com/watch?v=U9mJuUkhUzk&ab_channel=OpenAI)
Sorry if this is not worth for a post, I just wanted people to know that OpenAi is streaming the keynote. | 2023-11-06T17:35:24 | https://www.reddit.com/r/LocalLLaMA/comments/17p85q6/openai_live_stream_keynote_soon/ | MustBeSomethingThere | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 17p85q6 | false | null | t3_17p85q6 | /r/LocalLLaMA/comments/17p85q6/openai_live_stream_keynote_soon/ | false | false | self | 2 | {'enabled': False, 'images': [{'id': '5wTdFhNZCqJwgK0DBRCL8TXKFmS5PxCh3UTzXX_poWo', 'resolutions': [{'height': 81, 'url': 'https://external-preview.redd.it/ctFTYttU7p8MsepCeIXU82ZYVdIlqNMEwnSZqExnCZo.jpg?width=108&crop=smart&auto=webp&s=d56a3668d2b85f53d91b7b7f10dad451378db890', 'width': 108}, {'height': 162, 'url': 'h... |
Llama-2 attempts getting sued by Colab | 1 | I'm working on a entity extraction from medium size text corpus, I'm using Colab pro, Since I'm working with Llama-2 after downloading tried to give first text para it took half ram (around 7GB)to program to execute, don't know why next time when executing with next text corpus it is continuing from 7 again and total i... | 2023-11-06T17:18:35 | https://www.reddit.com/r/LocalLLaMA/comments/17p7rni/llama2_attempts_getting_sued_by_colab/ | Murky-Tumbleweed-486 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 17p7rni | false | null | t3_17p7rni | /r/LocalLLaMA/comments/17p7rni/llama2_attempts_getting_sued_by_colab/ | false | false | self | 1 | null |
Multimodal LLMs: a local model for sounds and sentiment? | 11 | Hi I am doing a personal project where I am running Whisper locally for transcription and basic multimodal LLava model using a single board computer [https://vimeo.com/879658471/616f6d57fa](https://vimeo.com/879658471/616f6d57fa)
I am now doing a project in which I am required to identify various emotions/activities ... | 2023-11-06T17:11:33 | https://www.reddit.com/r/LocalLLaMA/comments/17p7lmn/multimodal_llms_a_local_model_for_sounds_and/ | No_Turnover2057 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 17p7lmn | false | null | t3_17p7lmn | /r/LocalLLaMA/comments/17p7lmn/multimodal_llms_a_local_model_for_sounds_and/ | false | false | self | 11 | {'enabled': False, 'images': [{'id': 'XxPBJBUmo1wxZgVbAhPq8Rv5KbLdqDB9-XUglLW9OiU', 'resolutions': [{'height': 60, 'url': 'https://external-preview.redd.it/_3J1e2H52v9kSygwMjQahqHtyXKQcGqQ6YqiJoY17nw.jpg?width=108&crop=smart&auto=webp&s=6a3cb7573788ec06f8bdff6bed63b95be0324807', 'width': 108}, {'height': 121, 'url': 'h... |
Evaluating Hugging Face's Open Source Multimodal LLM | 10 | 2023-11-06T16:48:46 | https://blog.nomic.ai/posts/improving-multimodal-models-with-atlas | NomicAI | blog.nomic.ai | 1970-01-01T00:00:00 | 0 | {} | 17p729i | false | null | t3_17p729i | /r/LocalLLaMA/comments/17p729i/evaluating_hugging_faces_open_source_multimodal/ | false | false | 10 | {'enabled': False, 'images': [{'id': 'pGsQlm7S4UKP9m7i4GcNIgaLlvQ8Qy2jfYWy6SJk8Kw', 'resolutions': [{'height': 60, 'url': 'https://external-preview.redd.it/YIYwP5BUWkHkoPleV3PUTtSy-FMwgRCXfByveiTSGnQ.jpg?width=108&crop=smart&auto=webp&s=7723d4dec311211390fbfd86ed6ddfb25548c5d0', 'width': 108}, {'height': 120, 'url': 'h... | ||
Beginner's guide to finetuning Llama 2 and Mistral using QLoRA | 97 | Hey everyone,
I’ve seen a lot of interest in the community about getting started with finetuning.
Here's my new guide: **Finetuning Llama 2 & Mistral - A beginner’s guide to finetuning SOTA LLMs with QLoRA**. I focus on dataset creation, applying ChatML, and basic training hyperparameters. The code is kept simple for... | 2023-11-06T16:23:26 | https://www.reddit.com/r/LocalLLaMA/comments/17p6hup/beginners_guide_to_finetuning_llama_2_and_mistral/ | HatEducational9965 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 17p6hup | false | null | t3_17p6hup | /r/LocalLLaMA/comments/17p6hup/beginners_guide_to_finetuning_llama_2_and_mistral/ | false | false | self | 97 | {'enabled': False, 'images': [{'id': '0V3Hk81mZbfu8b0cp4jbXWJaWZ32CjVFsHWkERl5RU4', 'resolutions': [{'height': 54, 'url': 'https://external-preview.redd.it/J3Ce9CLYsslauAQ-5SN9ZihbjblyeEdrP2sDX3cPhv8.jpg?width=108&crop=smart&auto=webp&s=e1d6acf6b19772c1b4461e51f2085424e16bc35d', 'width': 108}, {'height': 108, 'url': 'h... |
Are LLMs surprisingly bad at simple math? | 1 | I only tried a bunch of famous 13B like Mythos, Tiefighter, Xwin... they are quite good at random internet quizzes, but when I ask something like 13651+75615, they all give wrong answers, even after multiple rerolls.
Is that normal or something is wrong with my settings? I'm using Ooba and SillyTavern. | 2023-11-06T16:17:32 | https://www.reddit.com/r/LocalLLaMA/comments/17p6d2p/are_llms_surprisingly_bad_at_simple_math/ | Sndragon88 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 17p6d2p | false | null | t3_17p6d2p | /r/LocalLLaMA/comments/17p6d2p/are_llms_surprisingly_bad_at_simple_math/ | false | false | self | 1 | null |
Best performance for 40-60K€ hardware: lost in the possibilities | 1 | Hi everyone,
I’ve created an app that helps people learn. Things have been going ok till the AI storm, where using GPT 3 and then 3.5 really changed the game for us.
One of my client is a government. For obvious reasons, they don’t enjoy the fact we’re a SaaS that uses OpenAI. So they’ve asked me if we would be able to... | 2023-11-06T16:15:56 | https://www.reddit.com/r/LocalLLaMA/comments/17p6buc/best_performance_for_4060k_hardware_lost_in_the/ | superap101 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 17p6buc | false | null | t3_17p6buc | /r/LocalLLaMA/comments/17p6buc/best_performance_for_4060k_hardware_lost_in_the/ | false | false | self | 1 | null |
Mistral Vision/Audio LoRAs & a Lossy 260K+ Token Context Window Prototype | 99 | Hi all, this is a follow up to my experimental library [multi-token](https://www.reddit.com/r/LocalLLaMA/comments/17ccp0l/multitoken_embed_arbitrary_modalities_images/) which makes it easier "attach" other modalities (images, audio, etc) to existing open source language models.
With \~$300 of compute I was able to tra... | 2023-11-06T15:56:11 | https://www.reddit.com/r/LocalLLaMA/comments/17p5vtk/mistral_visionaudio_loras_a_lossy_260k_token/ | sshh12 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 17p5vtk | false | null | t3_17p5vtk | /r/LocalLLaMA/comments/17p5vtk/mistral_visionaudio_loras_a_lossy_260k_token/ | false | false | self | 99 | {'enabled': False, 'images': [{'id': 'TzhpcDwSbksVG_i9CwDmOtz52oFHiZKQ7OK-1QMYoFc', 'resolutions': [{'height': 58, 'url': 'https://external-preview.redd.it/jwySnuIaVEesGlNQUOWPCKuH8id8dNW4D-P3DPOP7MQ.jpg?width=108&crop=smart&auto=webp&s=cc3758528608496f9e0b55b234259bd48e76813f', 'width': 108}, {'height': 116, 'url': 'h... |
New model released by alpin, Goliath-120B! | 76 | 2023-11-06T15:43:47 | https://huggingface.co/alpindale/goliath-120b | panchovix | huggingface.co | 1970-01-01T00:00:00 | 0 | {} | 17p5m2t | false | null | t3_17p5m2t | /r/LocalLLaMA/comments/17p5m2t/new_model_released_by_alpin_goliath120b/ | false | false | 76 | {'enabled': False, 'images': [{'id': 'U3TtVESnEQYuuFjDNAuglJfjpsZK1znyYLwSc-Q5mx4', 'resolutions': [{'height': 58, 'url': 'https://external-preview.redd.it/oi0_utef91tW_dGcivJWiE_qSwmUzci1683J0-RBz88.jpg?width=108&crop=smart&auto=webp&s=f9be6d10280d40205023660048d0180e7acd5acf', 'width': 108}, {'height': 116, 'url': 'h... | ||
Building/enhance a local LLM by crawling this sub | 1 | [removed] | 2023-11-06T15:17:05 | https://www.reddit.com/r/LocalLLaMA/comments/17p50ur/buildingenhance_a_local_llm_by_crawling_this_sub/ | herozorro | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 17p50ur | false | null | t3_17p50ur | /r/LocalLLaMA/comments/17p50ur/buildingenhance_a_local_llm_by_crawling_this_sub/ | false | false | self | 1 | {'enabled': False, 'images': [{'id': 'fEx3_FULeHE9NzJyjAmqaZvIyOX1WDPqCq5jQDW3_Pc', 'resolutions': [{'height': 81, 'url': 'https://external-preview.redd.it/CILZlyMI7N0HwEkWY8WZzULsx_GFvYFBWt9Mcod7TyA.jpg?width=108&crop=smart&auto=webp&s=e32f40e44fd46d4a9da2f38755c566f3c538d9c3', 'width': 108}, {'height': 162, 'url': 'h... |
Best text to speech diffusion model for reading books | 1 | [removed] | 2023-11-06T15:01:13 | https://www.reddit.com/r/LocalLLaMA/comments/17p4o10/best_text_to_speech_diffusion_model_for_reading/ | Puzzleheaded_Acadia1 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 17p4o10 | false | null | t3_17p4o10 | /r/LocalLLaMA/comments/17p4o10/best_text_to_speech_diffusion_model_for_reading/ | false | false | self | 1 | null |
Suggest a topic for a master's degree thesis related to LLMs? | 1 | I am a computer science student, currently in my 2nd year of masters. I currently have a college project where my team members and I have to research about various LLMs and ways to train them so they can answer questions about custom documents - how to embed knowledge into LLMs that it doesn't currently know.
​... | 2023-11-06T14:59:57 | https://www.reddit.com/r/LocalLLaMA/comments/17p4mtm/suggest_a_topic_for_a_masters_degree_thesis/ | PowerfulCap3557 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 17p4mtm | false | null | t3_17p4mtm | /r/LocalLLaMA/comments/17p4mtm/suggest_a_topic_for_a_masters_degree_thesis/ | false | false | self | 1 | null |
how would you build a chat llm for this subs content? | 1 | [removed] | 2023-11-06T14:55:24 | https://www.reddit.com/r/LocalLLaMA/comments/17p4jfq/how_would_you_build_a_chat_llm_for_this_subs/ | herozorro | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 17p4jfq | false | null | t3_17p4jfq | /r/LocalLLaMA/comments/17p4jfq/how_would_you_build_a_chat_llm_for_this_subs/ | false | false | self | 1 | null |
Best model up to 33b for writing erotic novels? | 11 |
Best model up to 33b for writing erotic novels? | 2023-11-06T14:43:01 | https://www.reddit.com/r/LocalLLaMA/comments/17p49t6/best_model_up_to_33b_for_writing_erotic_novels/ | Medium_Big_all_Good | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 17p49t6 | false | null | t3_17p49t6 | /r/LocalLLaMA/comments/17p49t6/best_model_up_to_33b_for_writing_erotic_novels/ | false | false | self | 11 | null |
Data Format for finetuning Llama2 to extract json | 3 | My question is how to use the system prompts which I use during generation in finetuning?
I am trying to finetune Llama2 7b on a custom dataset. But I am still confused about the data format for my use case. I want to extract information to json with given keys, which I am providing at the beginning. During generati... | 2023-11-06T14:38:47 | https://www.reddit.com/r/LocalLLaMA/comments/17p46hx/data_format_for_finetuning_llama2_to_extract_json/ | icelebratefestivus | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 17p46hx | false | null | t3_17p46hx | /r/LocalLLaMA/comments/17p46hx/data_format_for_finetuning_llama2_to_extract_json/ | false | false | self | 3 | {'enabled': False, 'images': [{'id': 'a1hmOnL77g0KEwQYz1ospL2mdtWnUUs4gvIEoj1uaZQ', 'resolutions': [{'height': 66, 'url': 'https://external-preview.redd.it/4MF3cr0DQxBbinGtwASoNlt0Gg05zjMQOT3gc83QBMg.jpg?width=108&crop=smart&auto=webp&s=c0427b01010fa2f8cf1698d7956cb7527aba26c4', 'width': 108}, {'height': 133, 'url': 'h... |
Is it possible to train BabyLM on consumer-grade hardware? | 10 | BabyLM was a competition with 700m training data to train an LM model that roughly equates the language skills of a 13 year old. One of the goals is to learn how to train LLMs yourself. However, I could not find infos on what sort of hardware is needed for this challenge. Obviously, this is not GPT-3, but probably stil... | 2023-11-06T13:54:12 | https://www.reddit.com/r/LocalLLaMA/comments/17p384y/is_it_possible_to_train_babylm_on_consumergrade/ | fabkosta | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 17p384y | false | null | t3_17p384y | /r/LocalLLaMA/comments/17p384y/is_it_possible_to_train_babylm_on_consumergrade/ | false | false | self | 10 | {'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... |
RAG: Flexible Context Retrieval around a matching chunk | 54 | Here's something I was thinking about and found existing solutions inadequate -- the so-called big-vs-small chunks dilemma: You want:
* small chunks for accurate embeddings
* large chunks to capture sufficient context to answer queries.
The solution is clearly to *decouple* chunking and retrieval. Ideally, we want to... | 2023-11-06T13:45:00 | https://www.reddit.com/r/LocalLLaMA/comments/17p31mc/rag_flexible_context_retrieval_around_a_matching/ | SatoshiNotMe | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 17p31mc | false | null | t3_17p31mc | /r/LocalLLaMA/comments/17p31mc/rag_flexible_context_retrieval_around_a_matching/ | false | false | self | 54 | {'enabled': False, 'images': [{'id': 'mCf-gvgLGIf97C4Q5Pay7BZQzUkl4WPZs5p9Ug1Hclk', 'resolutions': [{'height': 56, 'url': 'https://external-preview.redd.it/RigZZifec40luNenyE_Akjp1nwDkgYM3PY2sXKQiR9U.jpg?width=108&crop=smart&auto=webp&s=6f77c5c3077d3728cfb79ff9339119fb5fd7b59d', 'width': 108}, {'height': 113, 'url': 'h... |
01-ai/Yi-34B-200K Release | 63 | [https://huggingface.co/01-ai/Yi-34B-200K](https://huggingface.co/01-ai/Yi-34B-200K) | 2023-11-06T13:30:20 | https://www.reddit.com/r/LocalLLaMA/comments/17p2rjs/01aiyi34b200k_release/ | Serious-Commercial10 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 17p2rjs | false | null | t3_17p2rjs | /r/LocalLLaMA/comments/17p2rjs/01aiyi34b200k_release/ | false | false | self | 63 | {'enabled': False, 'images': [{'id': 'kmY3rlrmVU3WlcgsR_oWu3jytWsfBFUqjvJ9UfST5d4', 'resolutions': [{'height': 58, 'url': 'https://external-preview.redd.it/QWmRvBy_He1qc9JRmB81KMPRrYIPgH0maC9M87MUYLA.jpg?width=108&crop=smart&auto=webp&s=da85b4046f47f4a083dc6bf491fbba6a1ed444d2', 'width': 108}, {'height': 116, 'url': 'h... |
Models that are good at math and chemistry? | 2 | Are there any models that are good at maths and chemistry or which I can fine-tune to get better results? | 2023-11-06T12:19:26 | https://www.reddit.com/r/LocalLLaMA/comments/17p1gl0/models_that_are_good_at_math_and_chemistry/ | _Sneaky_Bastard_ | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 17p1gl0 | false | null | t3_17p1gl0 | /r/LocalLLaMA/comments/17p1gl0/models_that_are_good_at_math_and_chemistry/ | false | false | self | 2 | null |
RAG Embeddings | 8 | Hi,
I am experimenting with RAG and now wondering which embeddings I should use. Many blogposts use the "sentence-transformers/all-MiniLM-L6-v2" embeddings for the query and vectordatabase and the Llama2 for generating the output. So I am wondering if it is better to use to same embeddings here instead of 2 different ... | 2023-11-06T12:06:04 | https://www.reddit.com/r/LocalLLaMA/comments/17p18m9/rag_embeddings/ | Ill_Bodybuilder3499 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 17p18m9 | false | null | t3_17p18m9 | /r/LocalLLaMA/comments/17p18m9/rag_embeddings/ | false | false | self | 8 | null |
Code Completion | 1 | [removed] | 2023-11-06T11:41:28 | https://www.reddit.com/r/LocalLLaMA/comments/17p0u7b/code_completion/ | kranejwilson | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 17p0u7b | false | null | t3_17p0u7b | /r/LocalLLaMA/comments/17p0u7b/code_completion/ | false | false | self | 1 | null |
🐺🐦⬛ LLM Comparison/Test: Mistral 7B Updates (OpenHermes 2.5, OpenChat 3.5, Nous Capybara 1.9) | 259 | I interrupted my 70B tests to check out the brand-new updates for some of the top 7B models.
Mistral 7B just keeps getting better, and it's gotten more important for me now, because of a new use case which made me add an entirely new test series (see below).
## Models tested
- **[Nous-Capybara-7B-V1.9](https://huggi... | 2023-11-06T11:17:10 | https://www.reddit.com/r/LocalLLaMA/comments/17p0gut/llm_comparisontest_mistral_7b_updates_openhermes/ | WolframRavenwolf | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 17p0gut | false | null | t3_17p0gut | /r/LocalLLaMA/comments/17p0gut/llm_comparisontest_mistral_7b_updates_openhermes/ | false | false | self | 259 | {'enabled': False, 'images': [{'id': '2g4MtoKvhQOBCmeiXB1qv1h_5M24BeeYF64zcf4-rfg', 'resolutions': [{'height': 142, 'url': 'https://external-preview.redd.it/0z4RbV35RPDd2wqL6Oyz-uwz9kKNBAH0ePojGplYP2M.jpg?width=108&crop=smart&auto=webp&s=bbe38cbb6d4f7a7e6dd7d3c8b79c4ac9ba965545', 'width': 108}, {'height': 284, 'url': '... |
llm based Japanese-English translation model ALMA-7B-Ja-V2 and Benchmark Results. | 18 | The [previously announced model](https://www.reddit.com/r/LocalLLaMA/comments/1732t26/japaneseenglish_translation_model_alma7bja_release/) has been further improved.
- Minor improvements have been made to bring the performance closer to META's 54B model.
- The performance of the [quantization model](https://huggingfac... | 2023-11-06T10:31:30 | https://www.reddit.com/r/LocalLLaMA/comments/17oztbr/llm_based_japaneseenglish_translation_model/ | dahara111 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 17oztbr | false | null | t3_17oztbr | /r/LocalLLaMA/comments/17oztbr/llm_based_japaneseenglish_translation_model/ | false | false | self | 18 | {'enabled': False, 'images': [{'id': 'guX5POeapUFU8HyLSgs4BKeP8asyMcjsytR5Q29v77g', 'resolutions': [{'height': 58, 'url': 'https://external-preview.redd.it/Kutgr97-dep4_4gyw0M74u4Wh1gGcwvDV5u0CpLcNCo.jpg?width=108&crop=smart&auto=webp&s=ec104916d0106fb28e778c6e70419c2a47b17e60', 'width': 108}, {'height': 116, 'url': 'h... |
It started to scare me right now | 1 | ​
https://preview.redd.it/kerapapkcpyb1.png?width=946&format=png&auto=webp&s=873f426113877b3d8571f7aa4b60c86ebdc85c08
https://preview.redd.it/w9iurprpcpyb1.png?width=989&format=png&auto=webp&s=e93aab8764b3e401057c6f651b101092725640b3
​ | 2023-11-06T10:12:02 | https://www.reddit.com/r/LocalLLaMA/comments/17ozk07/it_started_to_scare_me_right_now/ | denyicz | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 17ozk07 | false | null | t3_17ozk07 | /r/LocalLLaMA/comments/17ozk07/it_started_to_scare_me_right_now/ | false | false | 1 | null | |
GTX1080 which LLM models? | 13 | Hi there, I am bound to get servers on [Hetzner.com](https://Hetzner.com) (company policy) and they only offer servers with one GTX1080 GPU [https://www.hetzner.com/sb?search=gpu](https://www.hetzner.com/sb?search=gpu)
If recall correctly these have 8GB VRAM. Can anyone help me understand what model sizes could gener... | 2023-11-06T09:22:07 | https://www.reddit.com/r/LocalLLaMA/comments/17oyx66/gtx1080_which_llm_models/ | olddoglearnsnewtrick | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 17oyx66 | false | null | t3_17oyx66 | /r/LocalLLaMA/comments/17oyx66/gtx1080_which_llm_models/ | false | false | self | 13 | null |
Finding better embedding models | 15 |
I am trying to develop a project akin to a private GPT system capable of parsing my files and providing answers to questions. Following experimentation with various models, including llama-2-7b, chat-hf, and flan-T5-large, and employing instructor-large embeddings, I encountered challenges in obtaining satisfactory re... | 2023-11-06T08:37:38 | https://www.reddit.com/r/LocalLLaMA/comments/17oyd1r/finding_better_embedding_models/ | Relative_Winner_4588 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 17oyd1r | false | null | t3_17oyd1r | /r/LocalLLaMA/comments/17oyd1r/finding_better_embedding_models/ | false | false | self | 15 | null |
What are the recommended LLM "backend" for RAG | 13 | I didn't see any posts talking about or comparing how different type/size of LLM influences the performance of the whole RAG system. It seems that most people are using ChatGPT and GPT-4. I'm wondering if there are any recommended local LLM capable of achieving RAG. "Llama Chat" is one example. Any other recommendation... | 2023-11-06T08:22:42 | https://www.reddit.com/r/LocalLLaMA/comments/17oy5q3/what_are_the_recommended_llm_backend_for_rag/ | wandering-ai | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 17oy5q3 | false | null | t3_17oy5q3 | /r/LocalLLaMA/comments/17oy5q3/what_are_the_recommended_llm_backend_for_rag/ | false | false | self | 13 | null |
What is the most logical GPU for service/inference? | 1 | What could be the most logical GPU for using a LLM at a production level? Should one go for GPUs like A100/H100 directly, or are there other GPUs that make sense? I've seen Quadro series GPUs on the internet, but I haven't come across a recommendation to use them directly.
Apart from this, if you have any general rec... | 2023-11-06T08:12:28 | https://www.reddit.com/r/LocalLLaMA/comments/17oy0op/what_is_the_most_logical_gpu_for_serviceinference/ | ARBasaran | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 17oy0op | false | null | t3_17oy0op | /r/LocalLLaMA/comments/17oy0op/what_is_the_most_logical_gpu_for_serviceinference/ | false | false | self | 1 | null |
A WebUI to use for my RAG application | 6 | So I built a RAG system and now I need an UI for it to be usable by others. What webui can I use? I have installed koboldcpp and it is pretty good, but I don't know how can I hook it up with my retrieval system. Also it feels like too much options for the end user to fiddle with.
I want it to be in such a way that it ... | 2023-11-06T05:26:43 | https://www.reddit.com/r/LocalLLaMA/comments/17ovoif/a_webui_to_use_for_my_rag_application/ | IamFuckinTomato | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 17ovoif | false | null | t3_17ovoif | /r/LocalLLaMA/comments/17ovoif/a_webui_to_use_for_my_rag_application/ | false | false | self | 6 | null |
LLMs on 4060Ti 16GB | 1 | Is there a list somewhere mentioning LLMs that can be used for inference on a 4060Ti 16GB? | 2023-11-06T05:18:51 | https://www.reddit.com/r/LocalLLaMA/comments/17ovk5z/llms_on_4060ti_16gb/ | fakenoob20 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 17ovk5z | false | null | t3_17ovk5z | /r/LocalLLaMA/comments/17ovk5z/llms_on_4060ti_16gb/ | false | false | self | 1 | null |
Best Local LLM for SuperAGI? | 1 | I understand that SuperAGI finally allows local LLMs to power Agents. I was wondering if anybody here has tried this, and if so, can you recommend a model? My laptop has a 16 gigabytes of vram. | 2023-11-06T05:04:05 | https://www.reddit.com/r/LocalLLaMA/comments/17ovbz1/best_local_llm_for_superagi/ | Seclusion72 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 17ovbz1 | false | null | t3_17ovbz1 | /r/LocalLLaMA/comments/17ovbz1/best_local_llm_for_superagi/ | false | false | self | 1 | null |
Best follows on huggingface | 1 | Hey, the following page on hf seems like a no bs way of following people who do great work and frankly it is motivating to see people put out new models and datasets on a regular basis. I only follow TheBloke and a few organizations like THUDM and openchat, I wanted to know who y'all follow!
​
TIA. | 2023-11-06T04:49:22 | https://www.reddit.com/r/LocalLLaMA/comments/17ov3b1/best_follows_on_huggingface/ | Dry_Long3157 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 17ov3b1 | false | null | t3_17ov3b1 | /r/LocalLLaMA/comments/17ov3b1/best_follows_on_huggingface/ | false | false | self | 1 | null |
Why do I suck at life and I can't get CodeLlama Instruct (7B q6) to work right (using LM Studio)? Any assistance is greatly appreciated. | 1 | First, I likely b0rked the whole thing when I started changing parameters, but I was under the impression it wasn't working very well (mainly using it for help programming, sql, php, html, js, css, python).
Here are the settings I have, none of which I know much more about than the tool-tip tells me. The settings ... | 2023-11-06T04:03:22 | https://www.reddit.com/r/LocalLLaMA/comments/17ouc06/why_do_i_suck_at_life_and_i_cant_get_codellama/ | saintpetejackboy | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 17ouc06 | false | null | t3_17ouc06 | /r/LocalLLaMA/comments/17ouc06/why_do_i_suck_at_life_and_i_cant_get_codellama/ | false | false | self | 1 | null |
The Next 01.AI model said to be 100B and to Rival GPT 4 | 162 | 2023-11-06T02:47:50 | https://www.bloomberg.com/news/articles/2023-11-05/kai-fu-lee-s-open-source-01-ai-bests-llama-2-according-to-hugging-face?leadSource=reddit_wall | metalman123 | bloomberg.com | 1970-01-01T00:00:00 | 0 | {} | 17osy7f | false | null | t3_17osy7f | /r/LocalLLaMA/comments/17osy7f/the_next_01ai_model_said_to_be_100b_and_to_rival/ | false | false | 162 | {'enabled': False, 'images': [{'id': '2EMSbRECUX_Fcc_L3eZg0XSW9tVHx36ZIZykIFGZOAw', 'resolutions': [{'height': 72, 'url': 'https://external-preview.redd.it/9VuW552dL_6DkyIkppGBOpugIfKBVIJ7DkpE7Zv_mLA.jpg?width=108&crop=smart&auto=webp&s=cd47170956865f6697228eec63cd2f6e198d9953', 'width': 108}, {'height': 144, 'url': 'h... | ||
I'm a student and I'm going live on my college radio station with an LLM developer at 9pm central if anyone wants to pop in :). | 1 | 2023-11-06T02:40:31 | https://kwur-90-3.mixlr.com/ | Ill-Foundation6710 | kwur-90-3.mixlr.com | 1970-01-01T00:00:00 | 0 | {} | 17ost7k | false | null | t3_17ost7k | /r/LocalLLaMA/comments/17ost7k/im_a_student_and_im_going_live_on_my_college/ | false | false | default | 1 | null | |
10x 1080 TI (11GB) or 1x 4090 (24GB) | 39 | As title says, i'm planning to build a server build for localLLM. On theory, 10x 1080 ti should net me 35,840 CUDA and 110 GB VRAM while 1x 4090 sits at 16,000+ CUDA and 24GB VRAM. However, the 1080Tis only have about 11GBPS of memory bandwidth while the 4090 has close to 1TBPS. Based on cost, 10x 1080ti \~\~ 1800USD (... | 2023-11-06T02:31:52 | https://www.reddit.com/r/LocalLLaMA/comments/17osn8t/10x_1080_ti_11gb_or_1x_4090_24gb/ | M000lie | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 17osn8t | false | null | t3_17osn8t | /r/LocalLLaMA/comments/17osn8t/10x_1080_ti_11gb_or_1x_4090_24gb/ | false | false | self | 39 | null |
Anyone heard of Grok from Twitter ? | 1 | [removed] | 2023-11-06T02:17:04 | https://www.reddit.com/r/LocalLLaMA/comments/17oscr7/anyone_heard_of_grok_from_twitter/ | AutomaticDriver5882 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 17oscr7 | false | null | t3_17oscr7 | /r/LocalLLaMA/comments/17oscr7/anyone_heard_of_grok_from_twitter/ | false | false | self | 1 | {'enabled': False, 'images': [{'id': '3jbXoXQVSjH1uoBl1GSZnIe4bWo43WeISi3EXPqnkI4', 'resolutions': [{'height': 54, 'url': 'https://external-preview.redd.it/w5p_5orFi_jRCnUv6noMTpPi1thdNfzYDpw2dIitvLo.jpg?width=108&crop=smart&auto=webp&s=14ba7532221192cf3e10f379a182bb85abdbfbc5', 'width': 108}, {'height': 108, 'url': 'h... |
Multipurpose AI app for all your AI interests and services. | 1 | [removed] | 2023-11-06T02:16:40 | https://www.reddit.com/r/LocalLLaMA/comments/17oscgu/multipurpose_ai_app_for_all_your_ai_interests_and/ | EtelsonRecomputing | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 17oscgu | false | null | t3_17oscgu | /r/LocalLLaMA/comments/17oscgu/multipurpose_ai_app_for_all_your_ai_interests_and/ | false | false | self | 1 | {'enabled': False, 'images': [{'id': 'j9BOoAGSccutND6ogshNyb-xWVFtmdUvHV_lLdzYeVk', 'resolutions': [{'height': 56, 'url': 'https://external-preview.redd.it/V0FBs4ANBGpyFs_PZ9-yzcRHWxeq6OF-hv624Ti8Fs0.jpg?width=108&crop=smart&auto=webp&s=76adf9aa07171352e3727b8d8bde812b5eb0f7ab', 'width': 108}, {'height': 113, 'url': 'h... |
Workstations that can fit >=2 RTX 4090? | 2 | I am building a workstation for LLM (can't run it in the cloud, unfortunately). Various vendors told me that only 1 RTX 4090 can fit in their desktops simply because it's so physically big that it blocks the other PCIe slot on the motherboard. They suggested looking for bitcoin mining equipment. I saw that Lambda labs ... | 2023-11-05T23:47:51 | https://www.reddit.com/r/LocalLLaMA/comments/17opcqk/workstations_that_can_fit_2_rtx_4090/ | CacheMeUp | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 17opcqk | false | null | t3_17opcqk | /r/LocalLLaMA/comments/17opcqk/workstations_that_can_fit_2_rtx_4090/ | false | false | self | 2 | null |
MLC vs llama.cpp | 5 | I have tried running mistral 7B with **MLC** on my **m1 metal**. And it kept crushing [(git issue with description).](https://github.com/mlc-ai/mlc-llm/issues/1186) Memory inefficiency problems.
Now I have a task to make the Bakllava-1 work with webGPU in the browser. And it looks like the MLC has support for it. was ... | 2023-11-05T23:41:07 | https://www.reddit.com/r/LocalLLaMA/comments/17op7kj/mlc_vs_llamacpp/ | Robert-treboR | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 17op7kj | false | null | t3_17op7kj | /r/LocalLLaMA/comments/17op7kj/mlc_vs_llamacpp/ | false | false | 5 | null | |
3.7x faster than A100? | 9 | [https://www.tomshardware.com/tech-industry/semiconductors/chinas-accel-analog-chip-promises-to-outpace-industry-best-in-ai-acceleration-for-vision-tasks](https://www.tomshardware.com/tech-industry/semiconductors/chinas-accel-analog-chip-promises-to-outpace-industry-best-in-ai-acceleration-for-vision-tasks)
Pretty int... | 2023-11-05T23:33:33 | https://www.reddit.com/r/LocalLLaMA/comments/17op1o9/37x_faster_than_a100/ | patbhakta | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 17op1o9 | false | null | t3_17op1o9 | /r/LocalLLaMA/comments/17op1o9/37x_faster_than_a100/ | false | false | self | 9 | {'enabled': False, 'images': [{'id': 'RUiVUo5A7sYUYLY8eIOCpq14L7zc6fX6-aDD5nnlwTU', 'resolutions': [{'height': 67, 'url': 'https://external-preview.redd.it/zXqd7Ep48qk2MEPox3QfA_pmtiYnluYLYPsZhHUCkDs.jpg?width=108&crop=smart&auto=webp&s=fa0b89c182eb6b7dad8bd692f758519fcc1b27e4', 'width': 108}, {'height': 135, 'url': 'h... |
New base model Yi 34B claims to outperform llama 70B | 1 | [deleted] | 2023-11-05T22:57:15 | https://huggingface.co/01-ai/Yi-34B | mcmoose1900 | huggingface.co | 1970-01-01T00:00:00 | 0 | {} | 17oo8dq | false | null | t3_17oo8dq | /r/LocalLLaMA/comments/17oo8dq/new_base_model_yi_34b_claims_to_outperform_llama/ | false | false | 1 | {'enabled': False, 'images': [{'id': 'hxjd0UgQaT8ovV28DV5cje4WT1lVrUNkzFu_3Ywpsr4', 'resolutions': [{'height': 58, 'url': 'https://external-preview.redd.it/Uuj4VKmpbFC4dyyGJN9SYPiG0POBJZAC1gKyzOONPCw.jpg?width=108&crop=smart&auto=webp&s=5fa71a1374ace1051521ad2fcd2facd37baf5e8f', 'width': 108}, {'height': 116, 'url': 'h... | |
Redpajama-Data-v2 is Incredible | 192 | I say this with a little sadness because I was building the same thing, and together.ai beat me to it, but…
https://github.com/togethercomputer/RedPajama-Data
Redpajama-Data-v2 is —by a huge margin— the most valuable LLM training dataset ever released, and it’s a game changer for the GPU poor.
Tiny bit of background... | 2023-11-05T21:30:05 | https://www.reddit.com/r/LocalLLaMA/comments/17om8xf/redpajamadatav2_is_incredible/ | georgejrjrjr | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 17om8xf | false | null | t3_17om8xf | /r/LocalLLaMA/comments/17om8xf/redpajamadatav2_is_incredible/ | false | false | self | 192 | {'enabled': False, 'images': [{'id': 'uux7Lu10AKTlSY7F2-MIJ90C-3pAwl3Q5k3IS92lL8A', 'resolutions': [{'height': 54, 'url': 'https://external-preview.redd.it/N4JpdL94rGI4qkLItRWRzIc7rMV-ZhioEkf5xpvu_to.jpg?width=108&crop=smart&auto=webp&s=e75a6f33e324dedafd20989e884deef7cd45564e', 'width': 108}, {'height': 108, 'url': 'h... |
Where does one even begin with LLMs and training ? | 27 | I got addicted to Stable Diffusion and custom training models. But I’m fascinated with the idea of fine tuning a LLM on my dataset to use for various tasks.
But things change so fast it’s hard to know what’s relevant and worth diving into. My question is, where do I begin in using LLMs and custom training ? | 2023-11-05T21:26:56 | https://www.reddit.com/r/LocalLLaMA/comments/17om6fc/where_does_one_even_begin_with_llms_and_training/ | tcp-security | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 17om6fc | false | null | t3_17om6fc | /r/LocalLLaMA/comments/17om6fc/where_does_one_even_begin_with_llms_and_training/ | false | false | self | 27 | null |
How do I define an output format using prompts? | 1 | I am building an application which uses codellama to generate code that is to be executed in order to achieve certain results based on user input.
How do make sure that only code is generated using just prompts? In case I have only a part of code to be filled, how do I generate only that part?
Eg:
df = pd.read(data)... | 2023-11-05T21:23:45 | https://www.reddit.com/r/LocalLLaMA/comments/17om3sz/how_do_i_define_an_output_format_using_prompts/ | ayush_shashank | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 17om3sz | false | null | t3_17om3sz | /r/LocalLLaMA/comments/17om3sz/how_do_i_define_an_output_format_using_prompts/ | false | false | self | 1 | null |
Rolling text-generation-webui with docker | 1 | Into my first week playing with text-generation-webui, having done a manual install on my local dev system. Now thinking ahead to deploying it on my homelab, which runs proxmox. Will probably spin up an instance of Ubuntu server. To make it easier to spin up/tear down, was thinking of going with the docker install opt... | 2023-11-05T19:55:31 | https://www.reddit.com/r/LocalLLaMA/comments/17ok68n/rolling_textgenerationwebui_with_docker/ | LostGoatOnHill | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 17ok68n | false | null | t3_17ok68n | /r/LocalLLaMA/comments/17ok68n/rolling_textgenerationwebui_with_docker/ | false | false | self | 1 | null |
Locally serving an LLM for chat task for family access? | 9 | Hey,
Just wondering if anyone is serving an open source LLM for chat, that is made available on your home network.
Looking to do such, from homelab running proxmox. Did you dev your own UI with something like Streamlit, using LangChain or vanilla Python? A clean simple UI already available?
Thanks for any insight | 2023-11-05T19:41:38 | https://www.reddit.com/r/LocalLLaMA/comments/17ojvdw/locally_serving_an_llm_for_chat_task_for_family/ | LostGoatOnHill | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 17ojvdw | false | null | t3_17ojvdw | /r/LocalLLaMA/comments/17ojvdw/locally_serving_an_llm_for_chat_task_for_family/ | false | false | self | 9 | null |
Huggingface Autotrain data format | 5 | What is the data format for autotrain and do I have to follow some naming conventions?
I am able to run the autotrain-advanced to fine-tune a dataset from Huggingface like timdettmers/openassistant-guanaco which is a jsonl format, where each row is a json object with a single key "text".
So I created my own training\... | 2023-11-05T19:26:02 | https://www.reddit.com/r/LocalLLaMA/comments/17ojj00/huggingface_autotrain_data_format/ | Koliham | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 17ojj00 | false | null | t3_17ojj00 | /r/LocalLLaMA/comments/17ojj00/huggingface_autotrain_data_format/ | false | false | self | 5 | null |
OOC instructions | 2 | I am trying to give the AI OOC instructions in square brackets but it seems to be ignoring them.
Model is Chronos Hermes 13b
Anything I should be paying attention to? | 2023-11-05T19:10:46 | https://www.reddit.com/r/LocalLLaMA/comments/17oj6k3/ooc_instructions/ | Al-Terego | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 17oj6k3 | false | null | t3_17oj6k3 | /r/LocalLLaMA/comments/17oj6k3/ooc_instructions/ | false | false | self | 2 | null |
feed pdf files into an LLM for question answering tasks | 1 | hello there, we are working on chatbot that will act as an assistant for new cancer patients , we scraped around 50 pdfs containing faq with their answers, now we have no idea whats the best approach to make this model , one of the teamates suggested to use langchain , is it a good framework? can it implement other llm... | 2023-11-05T19:06:34 | https://www.reddit.com/r/LocalLLaMA/comments/17oj372/feed_pdf_files_into_an_llm_for_question_answering/ | yumiko14 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 17oj372 | false | null | t3_17oj372 | /r/LocalLLaMA/comments/17oj372/feed_pdf_files_into_an_llm_for_question_answering/ | false | false | self | 1 | null |
I made a web UI for ExLlamaV2 | 65 | [Here's what it looks like currently.](https://www.youtube.com/watch?v=MzX6wy-ZUFw) and [here is the repo](https://github.com/turboderp/exui).
It's meant to be lightweight and fast, with minimal dependencies while still supporting a wide range of Llama-like models with various prompt formats and showcasing some of the... | 2023-11-05T18:43:18 | https://www.reddit.com/r/LocalLLaMA/comments/17oik90/i_made_a_web_ui_for_exllamav2/ | ReturningTarzan | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 17oik90 | false | null | t3_17oik90 | /r/LocalLLaMA/comments/17oik90/i_made_a_web_ui_for_exllamav2/ | false | false | self | 65 | {'enabled': False, 'images': [{'id': '5-Feg8-wmbk0omI5MV9MMa_WzgAcyCoWEApRMEAdsa0', 'resolutions': [], 'source': {'height': 96, 'url': 'https://external-preview.redd.it/YTpnA9k9i3DNUii2sBM8-cu2eTlYT3cVS9oyaJnZvJQ.png?auto=webp&s=c161de06f1dfa878ec3e3a8183e21388c30a79fc', 'width': 96}, 'variants': {}}]} |
Hardware for Startup | 1 | I’m looking to host an endpoint via ngrok for my RAG system. It’s been working well but my inference speed for my chain is about a minute with a i7 8700 and 1070.
In terms of hardware upgrade/server, what would yall recommend to be able to handle an endpoint for around 10-20 users? | 2023-11-05T18:31:31 | https://www.reddit.com/r/LocalLLaMA/comments/17oi9t9/hardware_for_startup/ | ConceptGT | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 17oi9t9 | false | null | t3_17oi9t9 | /r/LocalLLaMA/comments/17oi9t9/hardware_for_startup/ | false | false | self | 1 | null |
I just got 10k AWS credit, and I'll use it to host LLM for your app. | 46 | Hi there, I recently got 10k AWS credit for [my project](https://www.fullmetal.ai), which hosts LLM for app builders.
The API will be accessible for free until my credit expires. My only goal is to evaluate whether I've built something that's useful for this community or not.
The service should last around 5-10 month... | 2023-11-05T18:21:25 | https://www.reddit.com/r/LocalLLaMA/comments/17oi1rt/i_just_got_10k_aws_credit_and_ill_use_it_to_host/ | m0dE | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 17oi1rt | false | null | t3_17oi1rt | /r/LocalLLaMA/comments/17oi1rt/i_just_got_10k_aws_credit_and_ill_use_it_to_host/ | false | false | self | 46 | {'enabled': False, 'images': [{'id': 'ibz-WbgWLTq9fNGmdvXvmXTzV2aIzevVHMd_bWL6pI8', 'resolutions': [{'height': 51, 'url': 'https://external-preview.redd.it/PsFbR9pcdvnvrfb30xRrSwJpUgWhFd92XS9Sc91Zbyo.jpg?width=108&crop=smart&auto=webp&s=9a0618960627365724dd3323a310474b4ce0e12f', 'width': 108}, {'height': 103, 'url': 'h... |
I want to see them fight | 1 | How viable would it be to have all the popular open source models fight in Super Smash Bros? Like, each model has 2 weeks to ML the game and then throw them in a ring together, divisions split by model size.
Wouldn't you like to see OpenChat vs Falcon vs Hermes vs Zephyr in the 7B division?
Can Mistral Instruct ACTUA... | 2023-11-05T18:09:08 | https://www.reddit.com/r/LocalLLaMA/comments/17ohs4u/i_want_to_see_them_fight/ | Future_Might_8194 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 17ohs4u | false | null | t3_17ohs4u | /r/LocalLLaMA/comments/17ohs4u/i_want_to_see_them_fight/ | false | false | self | 1 | null |
Is there an interface that allows voice chat so that you could just talk to the LLM like it was an actual person? | 3 | Hey all,
I have been playing with LM Studio and loaded a couple different LLM’s but every time I try and do a role play with it, it continues on and keeps going with both sides of the conversation several times back and forth in each time it gets a prompt to run inference. So basically the LLM just keeps going and ans... | 2023-11-05T17:54:14 | https://www.reddit.com/r/LocalLLaMA/comments/17ohfzh/is_there_an_interface_that_allows_voice_chat_so/ | chrisssssssssn | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 17ohfzh | false | null | t3_17ohfzh | /r/LocalLLaMA/comments/17ohfzh/is_there_an_interface_that_allows_voice_chat_so/ | false | false | self | 3 | null |
Why does Mistral break down after 30-40 responses. | 43 | One issue I continue to have is that Mistral just starts to break down into idiocy when it has too much responses. It isn't soley based on context but more based of how many chats it made.
Common bugs would be it just repeating the same phrase with extremely low variation.
Does anyone else experience issues after a... | 2023-11-05T17:49:38 | https://www.reddit.com/r/LocalLLaMA/comments/17ohcds/why_does_mistral_break_down_after_3040_responses/ | DragonForg | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 17ohcds | false | null | t3_17ohcds | /r/LocalLLaMA/comments/17ohcds/why_does_mistral_break_down_after_3040_responses/ | false | false | self | 43 | null |
The Spell (Prompt) In My Book | 7 | This is a 2 step system prompt that is designed to pull the most relevant information your model has about whatever you are wanting to learn or work on and writes a system prompt to be fed into a new chat to create a confident expert in that area.
1. First, set this as the system prompt and then start the chat wit... | 2023-11-05T17:47:41 | https://www.reddit.com/r/LocalLLaMA/comments/17ohauh/the_spell_prompt_in_my_book/ | Future_Might_8194 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 17ohauh | false | null | t3_17ohauh | /r/LocalLLaMA/comments/17ohauh/the_spell_prompt_in_my_book/ | false | false | self | 7 | null |
ive lost 40 gigs after using LM Studio / Ollama over a few weeks | 1 | with M1/16gig ive run various models (always 7b) on LM Studio and Ollama. The more i use them the more the swap kicks in. I eject the model. the swap remains. i reboot the machine. the gigs used in swap just vanish.
ive tried to research where all these tmp files could be? I wonder if my machine is faulty.
at this p... | 2023-11-05T16:59:12 | https://www.reddit.com/r/LocalLLaMA/comments/17og8iq/ive_lost_40_gigs_after_using_lm_studio_ollama/ | herozorro | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 17og8iq | false | null | t3_17og8iq | /r/LocalLLaMA/comments/17og8iq/ive_lost_40_gigs_after_using_lm_studio_ollama/ | false | false | self | 1 | null |
Ayumi LLM ERP Benchmark, the leaderboard no one is cheating on | 62 | 2023-11-05T16:37:10 | http://ayumi.m8geil.de/ayumi_bench_v3_results.html | mcmoose1900 | ayumi.m8geil.de | 1970-01-01T00:00:00 | 0 | {} | 17ofroj | false | null | t3_17ofroj | /r/LocalLLaMA/comments/17ofroj/ayumi_llm_erp_benchmark_the_leaderboard_no_one_is/ | false | false | default | 62 | null | |
Beginner's guide to finetuning Llama2 and Mistral using QLoRA | 1 | [removed] | 2023-11-05T16:25:29 | https://www.reddit.com/r/LocalLLaMA/comments/17ofip7/beginners_guide_to_finetuning_llama2_and_mistral/ | HatEducational9965 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 17ofip7 | false | null | t3_17ofip7 | /r/LocalLLaMA/comments/17ofip7/beginners_guide_to_finetuning_llama2_and_mistral/ | false | false | self | 1 | {'enabled': False, 'images': [{'id': 'Z911fSszz0Bq3k8kEHPLOKN_fgPMzDd_FviaKn6nBxc', 'resolutions': [{'height': 108, 'url': 'https://external-preview.redd.it/EGFl3iRMeH6x9ozPsEct1EqU9d2VDLchKf2OQUaGnd0.jpg?width=108&crop=smart&auto=webp&s=aee223a92f6faec2227a261149c7bc33c3d33541', 'width': 108}, {'height': 216, 'url': '... |
What do you do when your LLM is completely wrong? | 8 | I'm rather new to running LLaMa, so I'm curious what other people do when they're faced with instances where the responses are completely wrong.
I'm using the [sheep-duck-llama-2-70b-v1.1.Q4_K_M.gguf](https://huggingface.co/TheBloke/sheep-duck-llama-2-70B-v1.1-GGUF) model, and it's telling me this:
> > The m68030 did... | 2023-11-05T16:15:29 | https://www.reddit.com/r/LocalLLaMA/comments/17ofart/what_do_you_do_when_your_llm_is_completely_wrong/ | johnklos | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 17ofart | false | null | t3_17ofart | /r/LocalLLaMA/comments/17ofart/what_do_you_do_when_your_llm_is_completely_wrong/ | false | false | self | 8 | {'enabled': False, 'images': [{'id': 'c4GIGI89h3ran0flunFlJD9GXFXflvy4v7ihIV6rjUA', 'resolutions': [{'height': 58, 'url': 'https://external-preview.redd.it/pQklJlgQbvjrG1ubl0pcS7zKmxNQ2MOoxjC71_OBpiA.jpg?width=108&crop=smart&auto=webp&s=6c20f59cfad81ef7174bf4642d69bbc627fc6c85', 'width': 108}, {'height': 116, 'url': 'h... |
Using Llama2 in a SaaS application | 7 | Hey everyone,
I am a software developer and I want to build a SaaS product that uses Llama2 models for user interaction. I have been experimenting with a bunch of models and have found what I want to use.
I have some questions about the architecture and legal stuff if anyone could help me and offer feedback.
So my i... | 2023-11-05T16:07:52 | https://www.reddit.com/r/LocalLLaMA/comments/17of4yj/using_llama2_in_a_saas_application/ | abandonedexplorer | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 17of4yj | false | null | t3_17of4yj | /r/LocalLLaMA/comments/17of4yj/using_llama2_in_a_saas_application/ | false | false | self | 7 | null |
How to use Rocm with windows? | 4 | I haven’t been able to find any YouTube videos or anything about this topic so I came here to ask this. Is there a way for it to automatically convert it to rocm like intel’s GPUs? | 2023-11-05T15:16:20 | https://www.reddit.com/r/LocalLLaMA/comments/17oe1u7/how_to_use_rocm_with_windows/ | SimRacer101 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 17oe1u7 | false | null | t3_17oe1u7 | /r/LocalLLaMA/comments/17oe1u7/how_to_use_rocm_with_windows/ | false | false | self | 4 | null |
Can I use a LocalLLaMA to create embeddings from my text? | 3 | I have a text I want to create embeddings for searching in the text. Is it possible with a LocalLLaMA? Which is currently the best? Mistral? | 2023-11-05T15:14:27 | https://www.reddit.com/r/LocalLLaMA/comments/17oe0bw/can_i_use_a_localllama_to_create_embeddings_from/ | Phptower | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 17oe0bw | false | null | t3_17oe0bw | /r/LocalLLaMA/comments/17oe0bw/can_i_use_a_localllama_to_create_embeddings_from/ | false | false | self | 3 | null |
Small local model for git/shell | 3 | Hey guys
can you recommend a **small** model that is as small as possible and can create shell and git commands? E.g: merge featureBranch2 into master and so on?
The model should be capable of doing "complex" git commands. It should run locally, be small and in the best case it is easy to make it run on cpu or gpu... | 2023-11-05T14:26:31 | https://www.reddit.com/r/LocalLLaMA/comments/17od1r6/small_local_model_for_gitshell/ | Tyson1405 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 17od1r6 | false | null | t3_17od1r6 | /r/LocalLLaMA/comments/17od1r6/small_local_model_for_gitshell/ | false | false | self | 3 | null |
Zero shot, few shot learning is related to the LLM's ability to learn something? | 10 | While reading some papers, when I saw the terms, I didn't see any meaning, but only related to prompting with examples, or not.
Why the term is named as __ learning? It makes beginners unfamilar to step this field. | 2023-11-05T14:18:28 | https://www.reddit.com/r/LocalLLaMA/comments/17ocwa5/zero_shot_few_shot_learning_is_related_to_the/ | Mundane_Definition_8 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 17ocwa5 | false | null | t3_17ocwa5 | /r/LocalLLaMA/comments/17ocwa5/zero_shot_few_shot_learning_is_related_to_the/ | false | false | self | 10 | null |
GGML k-quants question | 2 | Hi \*,
​
while reading the PR introducing k-quants to GGML I wondered what the "mins" where that are mentioned in the context of the super blocks that are scaled.
​
[https://github.com/ggerganov/llama.cpp/pull/1684](https://github.com/ggerganov/llama.cpp/pull/1684)
​
Could someone point me i... | 2023-11-05T14:15:14 | https://www.reddit.com/r/LocalLLaMA/comments/17ocu1x/ggml_kquants_question/ | mag4nat | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 17ocu1x | false | null | t3_17ocu1x | /r/LocalLLaMA/comments/17ocu1x/ggml_kquants_question/ | false | false | self | 2 | {'enabled': False, 'images': [{'id': 'igIqXHftcwgA3g61YDQSn9kgLirwcf070kdKoeHnn_U', 'resolutions': [{'height': 54, 'url': 'https://external-preview.redd.it/rpywGxuotbRG_stOyE91GkediB37PXyTXm9V89dFsxA.jpg?width=108&crop=smart&auto=webp&s=bc179dbcc4e30484e1306e348921b50cfd49e049', 'width': 108}, {'height': 108, 'url': 'h... |
Need a tutorial, please advise. | 1 | Hi, I was wondering if anyone had a step by step guide about where to download a model for story writing. What one should I chose?
My PC has an RTX 3090, 128 GB ram 5600 Mhz, and an i9 14900KS 6 Ghz 24 cores.
I'm assuming I can get some of the best models with this hardware?
How do I actually set up the model on my... | 2023-11-05T14:13:08 | https://www.reddit.com/r/LocalLLaMA/comments/17ocso3/need_a_tutorial_please_advise/ | Competitive-Wait4938 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 17ocso3 | false | null | t3_17ocso3 | /r/LocalLLaMA/comments/17ocso3/need_a_tutorial_please_advise/ | false | false | self | 1 | null |
Is the Nvidia Jetson AGX Orin any good? | 16 | Nvidia recently shouted out r/localllama recently for one of their products. It got me looking into their products more seriously.
https://developer.nvidia.com/blog/bringing-generative-ai-to-life-with-jetson/
According to Nvidia, the Jetson AGX Orin can do 4.4 tokens per second with Llama 2 70B LLM. Does anyone have... | 2023-11-05T12:58:14 | https://www.reddit.com/r/LocalLLaMA/comments/17obem7/is_the_nvidia_jetson_agx_orin_any_good/ | zippyfan | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 17obem7 | false | null | t3_17obem7 | /r/LocalLLaMA/comments/17obem7/is_the_nvidia_jetson_agx_orin_any_good/ | false | false | self | 16 | {'enabled': False, 'images': [{'id': 'jdP6q1xx_oCIuC_kN69tUEk30RfFMzieeYbO1lM-8R8', 'resolutions': [{'height': 60, 'url': 'https://external-preview.redd.it/LI7759FS8kYOLhSFPgKnWZ3YvumC6N1FmUekiLv9_qc.jpg?width=108&crop=smart&auto=webp&s=0a18ce9e9af67b0b78d63509ebbba725fdea68e9', 'width': 108}, {'height': 121, 'url': 'h... |
Is there a good overview over finetunes? | 2 | When looking at the huggingface repositories, there is a wealth of different finetunes, but it is hard to tell which is the best for which purpose. Is somewhere an overview page with recommendations which purpose works best with which finetuned models? | 2023-11-05T12:36:43 | https://www.reddit.com/r/LocalLLaMA/comments/17ob1rz/is_there_a_good_overview_over_finetunes/ | _allo_ | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 17ob1rz | false | null | t3_17ob1rz | /r/LocalLLaMA/comments/17ob1rz/is_there_a_good_overview_over_finetunes/ | false | false | self | 2 | null |
What is your LLM news feed ? | 47 | Where do you often go to learn about new llama-based (and other) models? | 2023-11-05T12:07:08 | https://www.reddit.com/r/LocalLLaMA/comments/17oagl0/what_is_your_llm_news_feed/ | UpvoteBeast | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 17oagl0 | false | null | t3_17oagl0 | /r/LocalLLaMA/comments/17oagl0/what_is_your_llm_news_feed/ | false | false | self | 47 | null |
What largest size of a model can I reasonably use in browser? | 3 | I wanted to play around with running LLM on the client's side in browsers, have anyone tried it? What are the largest models that are possible to run this way? What software can I use to run models in browser? I have experience running them on my PC, but doing that in browser seems kind of challenging, and there isn't ... | 2023-11-05T12:01:11 | https://www.reddit.com/r/LocalLLaMA/comments/17oad9q/what_largest_size_of_a_model_can_i_reasonably_use/ | Dolidodzik123 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 17oad9q | false | null | t3_17oad9q | /r/LocalLLaMA/comments/17oad9q/what_largest_size_of_a_model_can_i_reasonably_use/ | false | false | self | 3 | null |
AI voicechat script | 38 | Hey guys,
made a python script for realtime AI talk, all local. Maybe some of you can make use of it.
* [Demo video](https://www.youtube.com/watch?v=x7XmdXSsDXg)
* [Source code](https://github.com/KoljaB/LocalAIVoiceChat)
Fits in 8 GB VRAM. Setting and voice customizable (\~10 sec audioclip as clone source). Dem... | 2023-11-05T11:37:29 | https://www.reddit.com/r/LocalLLaMA/comments/17oa10v/ai_voicechat_script/ | Lonligrin | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 17oa10v | false | null | t3_17oa10v | /r/LocalLLaMA/comments/17oa10v/ai_voicechat_script/ | false | false | self | 38 | {'enabled': False, 'images': [{'id': 'IqXV-FuRISLF89oC3bxbBH5D_QsQnW-_VKdCjFfwgg4', 'resolutions': [{'height': 81, 'url': 'https://external-preview.redd.it/9P1tLKlS9dmhqWL2Wo1gLwXUqq-CwygJX3PancAWLpw.jpg?width=108&crop=smart&auto=webp&s=cb8db6ecd7cf0b1ea822302d244711654e005b3b', 'width': 108}, {'height': 162, 'url': 'h... |
Question about privacy on local models running on LM Studio | 3 | It appears that running the local models on personal computers is fully private and they cannot connect to Internet. Can someone please enlighten me on the privacy part just to be sure that I can trust putting personal/work information, project ideas, etc in the chats?
Thanks for your help | 2023-11-05T10:50:05 | https://www.reddit.com/r/LocalLLaMA/comments/17o9d53/question_about_privacy_on_local_models_running_on/ | Constant_Initial_808 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 17o9d53 | false | null | t3_17o9d53 | /r/LocalLLaMA/comments/17o9d53/question_about_privacy_on_local_models_running_on/ | false | false | self | 3 | null |
What can i run on a M1 Max with 32GB of RAM? | 2 | [removed] | 2023-11-05T10:48:39 | https://www.reddit.com/r/LocalLLaMA/comments/17o9chw/what_can_i_run_on_a_m1_max_with_32gb_of_ram/ | arnieistheman | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 17o9chw | false | null | t3_17o9chw | /r/LocalLLaMA/comments/17o9chw/what_can_i_run_on_a_m1_max_with_32gb_of_ram/ | false | false | self | 2 | null |
How do you evaluate models? | 20 | In most of my own experimentation, and most of the posts here, I see one of two approaches for evaluating models:
1. Benchmarks: This never really "worked" for me, since I don't care about general capabilities, I care about the model being good at my specific task. Plus, there are a lot of models that claim to "bea... | 2023-11-05T10:26:49 | https://www.reddit.com/r/LocalLLaMA/comments/17o92a0/how_do_you_evaluate_models/ | AtomicFlndr | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 17o92a0 | false | null | t3_17o92a0 | /r/LocalLLaMA/comments/17o92a0/how_do_you_evaluate_models/ | false | false | self | 20 | null |
Subsets and Splits
No community queries yet
The top public SQL queries from the community will appear here once available.