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 ⌀ |
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
Non English LLM | 17 | Hello mates!
While working with local modals mostly on software development, I was wondering what would be the best model to work in my native language (Portuguese). Until now I never needed that kind of quality (language specific trained model), but I was thinking if I would need, what would be the model to have my h... | 2023-10-29T21:58:16 | https://www.reddit.com/r/LocalLLaMA/comments/17jdsqz/non_english_llm/ | danigoncalves | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 17jdsqz | false | null | t3_17jdsqz | /r/LocalLLaMA/comments/17jdsqz/non_english_llm/ | false | false | self | 17 | {'enabled': False, 'images': [{'id': 'lHpcAqnrYJn9xcJD7VI6tKN2blet5mIAcb9ccTn2SMQ', 'resolutions': [{'height': 54, 'url': 'https://external-preview.redd.it/wGlq14RmFAABYNvu5EOtCcv-v0T2vXHDNpa9Ingbz_o.jpg?width=108&crop=smart&auto=webp&s=97fa0265f54b2f1aa7967228d3232fcdf5b7ae93', 'width': 108}, {'height': 108, 'url': 'h... |
i created another llama-cpp-python docker container, what do you think? | 13 | hey, i know there are already some containers out there, but none of them are configurable or has a documentation on howto do it, if any. so i decided to create my own alpine based image. what do you think? [https://hub.docker.com/r/3x3cut0r/llama-cpp-python](https://hub.docker.com/r/3x3cut0r/llama-cpp-python) | 2023-10-29T21:53:58 | https://www.reddit.com/r/LocalLLaMA/comments/17jdp8x/i_created_another_llamacpppython_docker_container/ | executor55 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 17jdp8x | false | null | t3_17jdp8x | /r/LocalLLaMA/comments/17jdp8x/i_created_another_llamacpppython_docker_container/ | false | false | self | 13 | null |
MistralLite not able to summarize text? | 10 | I have tried [MistralLite](https://huggingface.co/amazon/MistralLite), as the small model size paired with the large context would be great for quick summarization of long texts. Yet it does not do so for me, neither with the transformers example code and the original model, nor when running via llama.cpp.
Instead of ... | 2023-10-29T21:22:21 | https://www.reddit.com/r/LocalLLaMA/comments/17jd00g/mistrallite_not_able_to_summarize_text/ | Chromix_ | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 17jd00g | false | null | t3_17jd00g | /r/LocalLLaMA/comments/17jd00g/mistrallite_not_able_to_summarize_text/ | false | false | self | 10 | null |
how to know when to give context to llm using rag and when to rely on pure model response? | 12 | I have a lora finetuned model for a use case. I need to use rag for certain faqs. But it’s not a pire faq use case. How to know when I shall query for rag and when I shall rely on pure model response? | 2023-10-29T21:11:19 | https://www.reddit.com/r/LocalLLaMA/comments/17jcr5a/how_to_know_when_to_give_context_to_llm_using_rag/ | s1lv3rj1nx | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 17jcr5a | false | null | t3_17jcr5a | /r/LocalLLaMA/comments/17jcr5a/how_to_know_when_to_give_context_to_llm_using_rag/ | false | false | self | 12 | null |
ChatML chat history formatting | 5 | Hello everybody! Having a bit of trouble implementing a chat history with my dolphin model. Does anyone have a good way of getting it to remember the entire conversation and not just the one off message? Here is what I am trying right now:
sys\_prompt = """
<|im\_start|>system
You are roleplaying as Bob, the best... | 2023-10-29T21:08:01 | https://www.reddit.com/r/LocalLLaMA/comments/17jcohn/chatml_chat_history_formatting/ | Slimxshadyx | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 17jcohn | false | null | t3_17jcohn | /r/LocalLLaMA/comments/17jcohn/chatml_chat_history_formatting/ | false | false | self | 5 | null |
M2 Mac Mini 8cpu/10gpu with 24GB RAM - Will this be able to run any useful models locally? | 12 | I just purchased a refurbished oddball model primarily for my music production setup. Now I’m wondering if I can run some local models with this setup? I’ve glanced at this sub occasionally, but never bothered to try anything since my daily driver is a 14” M1 Pro. Any advice for a noob would be greatly appreciated :) | 2023-10-29T19:38:48 | https://www.reddit.com/r/LocalLLaMA/comments/17jaqnf/m2_mac_mini_8cpu10gpu_with_24gb_ram_will_this_be/ | tardwash | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 17jaqnf | false | null | t3_17jaqnf | /r/LocalLLaMA/comments/17jaqnf/m2_mac_mini_8cpu10gpu_with_24gb_ram_will_this_be/ | false | false | self | 12 | null |
My kernel just keeps dying while loading quantized models | 1 | Hi everyone!
I am currently taking an LLM course and doing an LLM project. I am blown away by the capability of the LLM so far. Tuning the prompts have proven to be way more fun than I originally thought.
I currently have an RTX 3070 Ti laptop, which it says has 8 GB of memory and 8 GB of extra memory, according to d... | 2023-10-29T18:59:49 | https://www.reddit.com/r/LocalLLaMA/comments/17j9vnn/my_kernel_just_keeps_dying_while_loading/ | sonmanutd | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 17j9vnn | false | null | t3_17j9vnn | /r/LocalLLaMA/comments/17j9vnn/my_kernel_just_keeps_dying_while_loading/ | false | false | 1 | {'enabled': False, 'images': [{'id': 'gk7bBPNGnu1NYSfn3TQwbRQovws5fK2zqaxGxkBWueM', 'resolutions': [{'height': 58, 'url': 'https://external-preview.redd.it/qL-2kxq-rGOZ27c4tnt1RYaoXfLiZ30TYMNsM3PREFc.jpg?width=108&crop=smart&auto=webp&s=1d7c8e3760d89d70b8cf46f72a4ffff0f1e002e2', 'width': 108}, {'height': 116, 'url': 'h... | |
How are you converting to AWQ? | 3 | I am having a hard time finding resources that indicate how we can convert to the new format. | 2023-10-29T18:33:55 | https://www.reddit.com/r/LocalLLaMA/comments/17j9bcd/how_are_you_converting_to_awq/ | ProperShape5918 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 17j9bcd | false | null | t3_17j9bcd | /r/LocalLLaMA/comments/17j9bcd/how_are_you_converting_to_awq/ | false | false | self | 3 | null |
TabbyML copilot on Intel GPUs | 5 | I'm posting here to see if anyone in this channel might be willing or able to help with the linked PR. I have a pretty good start but am not proficient in Rust. Any assistance is much appreciated.
The docker image is successfully running llama.cpp with OpenCL but the Rust app is not using the GPU. I believe it's an is... | 2023-10-29T17:40:12 | https://github.com/TabbyML/tabby/pull/661 | it_lackey | github.com | 1970-01-01T00:00:00 | 0 | {} | 17j853l | false | null | t3_17j853l | /r/LocalLLaMA/comments/17j853l/tabbyml_copilot_on_intel_gpus/ | false | false | 5 | {'enabled': False, 'images': [{'id': 'bWQxjqsQl7Jf588cv4Ji4dQlwMditYogT2bAs5tq_W4', 'resolutions': [{'height': 54, 'url': 'https://external-preview.redd.it/TNumpuoS90ZaCXvektmPEJpeDTp3yAWqMHIJ2U98IHc.jpg?width=108&crop=smart&auto=webp&s=7acb884f603b8f474d8fa130274b5302fa772242', 'width': 108}, {'height': 108, 'url': 'h... | |
GoLLIE: Guideline-following Large Language Model for Information Extraction | 41 | https://huggingface.co/s3nh/HiTZ-GoLLIE-7B-GGUFWe present GoLLIE, a Large Language Model trained to follow annotation guidelines. GoLLIE outperforms previous approaches on zero-shot Information Extraction and allows the user to perform inferences with annotation schemas defined on the fly. Different from previous appro... | 2023-10-29T17:30:47 | https://hitz-zentroa.github.io/GoLLIE/ | kryptkpr | hitz-zentroa.github.io | 1970-01-01T00:00:00 | 0 | {} | 17j7xw7 | false | null | t3_17j7xw7 | /r/LocalLLaMA/comments/17j7xw7/gollie_guidelinefollowing_large_language_model/ | false | false | default | 41 | null |
HI guys i am facing an serious issue here while running vicuna in oogabooga webui i will share some images and please anyone try to solve my issue | 1 |
# RuntimeError: Failed to import transformers.models.llama.modeling_llama because of the following error (look up to see its traceback): DLL load failed while importing flash_attn_2_cuda: The specified module could not be found
​
​
​
​
https://preview.redd.it/3q0tq4nm46xb1.png?width=... | 2023-10-29T16:28:29 | https://www.reddit.com/r/LocalLLaMA/comments/17j6lse/hi_guys_i_am_facing_an_serious_issue_here_while/ | ancienthero1268 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 17j6lse | false | null | t3_17j6lse | /r/LocalLLaMA/comments/17j6lse/hi_guys_i_am_facing_an_serious_issue_here_while/ | false | false | 1 | null | |
llama cpp python help needed | 5 | I want to make an bot that can run function but for that i would need to get every character that the llm generates and then chck if there is a pattern and if so stop add the output and continue running the llm
i think that that is the callbackmanager but im not sure how to use it | 2023-10-29T16:19:11 | https://www.reddit.com/r/LocalLLaMA/comments/17j6eis/llama_cpp_python_help_needed/ | Otherwise_Weather_57 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 17j6eis | false | null | t3_17j6eis | /r/LocalLLaMA/comments/17j6eis/llama_cpp_python_help_needed/ | false | false | self | 5 | null |
Suggestion/Help Needed For Dual 4090 PC Setup For LLMs and Casual Gaming | 1 | [removed] | 2023-10-29T15:13:10 | https://www.reddit.com/r/LocalLLaMA/comments/17j50jj/suggestionhelp_needed_for_dual_4090_pc_setup_for/ | Aggressive_Bee_9069 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 17j50jj | false | null | t3_17j50jj | /r/LocalLLaMA/comments/17j50jj/suggestionhelp_needed_for_dual_4090_pc_setup_for/ | false | false | self | 1 | {'enabled': False, 'images': [{'id': '88vwZ7SMquTNEGZzVxsYegZvliXSMZil3q0jHetGbU0', 'resolutions': [{'height': 108, 'url': 'https://external-preview.redd.it/UcFyA8mRDRE2omJxR-b581JXG_tqUoeiapIg_wvBdXk.jpg?width=108&crop=smart&auto=webp&s=36199e92b8614dbd2350afd4b08750255066a35d', 'width': 108}, {'height': 216, 'url': '... |
How to run an LLM with two 4090s? | 3 | I was reading the LLM comparison posted recently and in the comments were people talking about using multiple GPUs to run their language models, and 70B seems to be doing really well.
I have a setup with a 13900KS and two 4090s. I was running ooga and that was okay, but then I started using SillyTavern with gpt-4 and ... | 2023-10-29T15:06:52 | https://www.reddit.com/r/LocalLLaMA/comments/17j4vrz/how_to_run_an_llm_with_two_4090s/ | Siigari | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 17j4vrz | false | null | t3_17j4vrz | /r/LocalLLaMA/comments/17j4vrz/how_to_run_an_llm_with_two_4090s/ | false | false | self | 3 | null |
Llama ask you a question, I seem to be Mistral something. (Python help) | 0 | I'm running a local model with the openai library in Python.
I can get a response, but how do I clean up the response to just the context I need? I am certain I am doing multiple things wrong, as it also includes the context and prompt in it's response instead of working that in. (code then result to follow):
\-... | 2023-10-29T15:01:40 | https://www.reddit.com/r/LocalLLaMA/comments/17j4rpa/llama_ask_you_a_question_i_seem_to_be_mistral/ | Future_Might_8194 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 17j4rpa | false | null | t3_17j4rpa | /r/LocalLLaMA/comments/17j4rpa/llama_ask_you_a_question_i_seem_to_be_mistral/ | false | false | self | 0 | null |
Tips on getting started with self hosting LLMs | 2 | Typically use wsl2 (Ubuntu) under windows, or Ubuntu VM. Looking to start playing with 7B chat models. Would appreciate any tips and links on how to get started with self hosting, software needing installed etc? Would be very helpful thank you | 2023-10-29T14:38:23 | https://www.reddit.com/r/LocalLLaMA/comments/17j4a4g/tips_on_getting_started_with_self_hosting_llms/ | LostGoatOnHill | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 17j4a4g | false | null | t3_17j4a4g | /r/LocalLLaMA/comments/17j4a4g/tips_on_getting_started_with_self_hosting_llms/ | false | false | self | 2 | null |
Please tell if LLaMa can be used for the following purpose | 4 | We are doing a MERN project in which we need to make a chat bot that talks like a plant. We are unable to find an LLM for this purpose. ChatGPT is paid and we are unable to find any other good LLM for this purpose.
We are new to these and those who are familiar with this please tell if we can use LLaMa LLM for des... | 2023-10-29T14:18:29 | https://www.reddit.com/r/LocalLLaMA/comments/17j3vwl/please_tell_if_llama_can_be_used_for_the/ | itsAn_Alt_Acc | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 17j3vwl | false | null | t3_17j3vwl | /r/LocalLLaMA/comments/17j3vwl/please_tell_if_llama_can_be_used_for_the/ | false | false | self | 4 | null |
Grammar is key to next generation AI game dev? | 101 | Can't say I've seen any post discussing game dev with LLM + grammar, so here I go.
Grammar makes the LLM response parsable by code. You can easily construct a json template that all responses from the LLM must abide to.
On a per character basis during RP, the following grammar properties are useful:
* emotion (I had ... | 2023-10-29T14:02:27 | https://www.reddit.com/r/LocalLLaMA/comments/17j3l3i/grammar_is_key_to_next_generation_ai_game_dev/ | EVLG2112 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 17j3l3i | false | null | t3_17j3l3i | /r/LocalLLaMA/comments/17j3l3i/grammar_is_key_to_next_generation_ai_game_dev/ | false | false | self | 101 | null |
The easy and cheap way to run a 70b language model | 1 | [removed] | 2023-10-29T13:40:32 | https://www.reddit.com/r/LocalLLaMA/comments/17j35x1/the_easy_and_cheap_way_to_run_a_70b_language_model/ | innocuousAzureus | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 17j35x1 | false | null | t3_17j35x1 | /r/LocalLLaMA/comments/17j35x1/the_easy_and_cheap_way_to_run_a_70b_language_model/ | false | false | self | 1 | null |
How to make Llama2 create Mindmaps from large corpora bigger than its context length? | 1 | [removed] | 2023-10-29T13:39:41 | https://www.reddit.com/r/LocalLLaMA/comments/17j35a6/how_to_make_llama2_create_mindmaps_from_large/ | SecretOk9644 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 17j35a6 | false | null | t3_17j35a6 | /r/LocalLLaMA/comments/17j35a6/how_to_make_llama2_create_mindmaps_from_large/ | false | false | self | 1 | null |
Who's working on Vulkan Multi GPU? | 4 | Looking at mlc-llm, vllm, nomic, etc. they all seem focused on inferencing with a vulkin backend and all have made statements about multi gpu support either on their roadmaps or being worked on over the past few months. Every time I see one say they added multi gpu support it turns out they just incorporated llama.cpp... | 2023-10-29T13:33:11 | https://www.reddit.com/r/LocalLLaMA/comments/17j315b/whos_working_on_vulkan_multi_gpu/ | ccbadd | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 17j315b | false | null | t3_17j315b | /r/LocalLLaMA/comments/17j315b/whos_working_on_vulkan_multi_gpu/ | false | false | self | 4 | null |
anyone running locally with autogen or open intrepreter? | 1 | if so what are your pc specifications? also provide some tutorials | 2023-10-29T12:38:23 | https://www.reddit.com/r/LocalLLaMA/comments/17j21yh/anyone_running_locally_with_autogen_or_open/ | GasBond | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 17j21yh | false | null | t3_17j21yh | /r/LocalLLaMA/comments/17j21yh/anyone_running_locally_with_autogen_or_open/ | false | false | self | 1 | null |
Best way to fine-tune LLM based on daily journals? | 30 | Hello, PLEASE do not suggest vector search and retrieval.
I have X person's daily journal about thoughts, emotions, tasks and etc. I want to train model to 'act' like protagonist when I talk to it.
Most of the questions will be about common sense for example - What do you think about X or what can you advice about Y... | 2023-10-29T12:33:52 | https://www.reddit.com/r/LocalLLaMA/comments/17j1zcw/best_way_to_finetune_llm_based_on_daily_journals/ | ihatemodels2020 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 17j1zcw | false | null | t3_17j1zcw | /r/LocalLLaMA/comments/17j1zcw/best_way_to_finetune_llm_based_on_daily_journals/ | false | false | self | 30 | null |
RAG with no GPUs: How to use CPU-based LLMs for RAG experiments | 1 | [removed] | 2023-10-29T11:37:58 | https://www.reddit.com/r/LocalLLaMA/comments/17j13hh/rag_with_no_gpus_how_to_use_cpubased_llms_for_rag/ | Mammoth-Doughnut-160 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 17j13hh | false | null | t3_17j13hh | /r/LocalLLaMA/comments/17j13hh/rag_with_no_gpus_how_to_use_cpubased_llms_for_rag/ | false | false | default | 1 | {'enabled': False, 'images': [{'id': 'ZM69NBYTqpy4Rlx3TYawtEmae58-gU37vLlaCWN1Oa0', 'resolutions': [{'height': 81, 'url': 'https://external-preview.redd.it/n4qBMoMHlMMuy9-093xOqVaEaLTh9hws6cNYmROfml0.jpg?width=108&crop=smart&auto=webp&s=6e734acdbf3aa0abc89fb071b04091fc81229e8a', 'width': 108}, {'height': 162, 'url': 'h... |
How is it possible to connect 32 GPUs together? | 0 | [removed] | 2023-10-29T11:19:56 | https://www.reddit.com/r/LocalLLaMA/comments/17j0tt6/how_is_it_possible_to_connect_32_gpus_together/ | coldcaramel99 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 17j0tt6 | false | null | t3_17j0tt6 | /r/LocalLLaMA/comments/17j0tt6/how_is_it_possible_to_connect_32_gpus_together/ | false | false | default | 0 | null |
ChatGPT removes some tags | 1 |
Hello,
As I way using chatGPT to help me process some strings, it was missing my point for something that looked trivial. Until I noticed that It was removing the Tags.
Here is the input I gave it and the output I got.
I thought that you might find that interesting.
<|system|>
You are a friendly chatb... | 2023-10-29T10:38:34 | https://www.reddit.com/r/LocalLLaMA/comments/17j08sj/chatgpt_removes_some_tags/ | petitponeyrose | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 17j08sj | false | null | t3_17j08sj | /r/LocalLLaMA/comments/17j08sj/chatgpt_removes_some_tags/ | false | false | 1 | null | |
Model for content writing | 1 | [removed] | 2023-10-29T10:21:18 | https://www.reddit.com/r/LocalLLaMA/comments/17j00an/model_for_content_writing/ | MannowLawn | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 17j00an | false | null | t3_17j00an | /r/LocalLLaMA/comments/17j00an/model_for_content_writing/ | false | false | self | 1 | null |
Model for content writing | 1 | [removed] | 2023-10-29T10:21:17 | https://www.reddit.com/r/LocalLLaMA/comments/17j00a5/model_for_content_writing/ | MannowLawn | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 17j00a5 | false | null | t3_17j00a5 | /r/LocalLLaMA/comments/17j00a5/model_for_content_writing/ | false | false | self | 1 | null |
Multi-modal doc Q&A vs PDF text extraction | 4 | I’ve been doing some classic RAG using PDF documents that go through a tool like PyPDF. The problem is that the layout of these documents stores meaning.
E.g there may be columns or a table etc. that are obvious to a human but are stripped out when using PyPDF which just creates a large chunk of text
Would a multi-mo... | 2023-10-29T09:27:31 | https://www.reddit.com/r/LocalLLaMA/comments/17iz9tc/multimodal_doc_qa_vs_pdf_text_extraction/ | reddysteady | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 17iz9tc | false | null | t3_17iz9tc | /r/LocalLLaMA/comments/17iz9tc/multimodal_doc_qa_vs_pdf_text_extraction/ | false | false | self | 4 | null |
PC Build Suggestion For Local LLMs and Gaming | 1 | I'm building a PC for inference and fine-tuning Local LLMs, general ML work, algo trading and also some casual gaming.
The build is meant for 2x RTX 4090, but currently I'm only adding one RTX 4090 and will add the other one in the coming months.
My current list is the following. I'll be glad to know your suggestions... | 2023-10-29T08:20:37 | https://www.reddit.com/r/LocalLLaMA/comments/17iye3o/pc_build_suggestion_for_local_llms_and_gaming/ | Aggressive_Bee_9069 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 17iye3o | false | null | t3_17iye3o | /r/LocalLLaMA/comments/17iye3o/pc_build_suggestion_for_local_llms_and_gaming/ | false | false | self | 1 | {'enabled': False, 'images': [{'id': '88vwZ7SMquTNEGZzVxsYegZvliXSMZil3q0jHetGbU0', 'resolutions': [{'height': 108, 'url': 'https://external-preview.redd.it/UcFyA8mRDRE2omJxR-b581JXG_tqUoeiapIg_wvBdXk.jpg?width=108&crop=smart&auto=webp&s=36199e92b8614dbd2350afd4b08750255066a35d', 'width': 108}, {'height': 216, 'url': '... |
Online gadget store launch🚀🚀 check it out | 0 | 2023-10-29T08:06:31 | http://theonlinegadgetstoreyo.myshopify.com | wtf2435 | theonlinegadgetstoreyo.myshopify.com | 1970-01-01T00:00:00 | 0 | {} | 17iy7is | false | null | t3_17iy7is | /r/LocalLLaMA/comments/17iy7is/online_gadget_store_launch_check_it_out/ | false | false | default | 0 | null | |
Llama-2 7b Unquantized Transformers using 26.8GB of Vram. | 4 | I'm running Llama-2 7b using Google Colab on a 40gb A100. However it's using 26.8 gb of vram, is that normal? I tried using 13b version however the system ran out of memory. Yes I know quantized versions are almost as good but I specifically need unquantized.
​
[https://colab.research.google.com/drive/10KL87N1... | 2023-10-29T07:53:06 | https://www.reddit.com/r/LocalLLaMA/comments/17iy10d/llama2_7b_unquantized_transformers_using_268gb_of/ | Acceptable_Can5509 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 17iy10d | false | null | t3_17iy10d | /r/LocalLLaMA/comments/17iy10d/llama2_7b_unquantized_transformers_using_268gb_of/ | false | false | self | 4 | {'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': '... |
PSA about Mining Rigs | 54 | I just wanted to leave out there that tonight I tested what happen when you try to run oobabooga with 8x 1060 GTX on a 13B model.
First of all it works like perfectly. No load on the cpu and 100% equal load on all gpu's.
But sadly, those usb cables for the risers dont have the bandwidth to make it a viable option.
I... | 2023-10-29T07:13:57 | https://www.reddit.com/r/LocalLLaMA/comments/17ixil8/psa_about_mining_rigs/ | DrVonSinistro | self.LocalLLaMA | 2023-10-29T07:45:01 | 0 | {} | 17ixil8 | false | null | t3_17ixil8 | /r/LocalLLaMA/comments/17ixil8/psa_about_mining_rigs/ | false | false | self | 54 | null |
llama.cpp tensor split on different types of GPUs? | 2 | I hadn't looked into how llama.cpp works too much... but I used it alot. It's a fine ??? (The program that runs LLaMa tensors).
But anyways, now, if I have a Thinkpad E480 for example. The main GPU is a UHD 620. The Optimus GPU is a RX 460, and I connect a \*Chinese\* GT 1030 with 4GB VRAM.
Is it possible to tensor s... | 2023-10-29T07:13:02 | https://www.reddit.com/r/LocalLLaMA/comments/17ixi71/llamacpp_tensor_split_on_different_types_of_gpus/ | A_Degenerate_Idiot | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 17ixi71 | false | null | t3_17ixi71 | /r/LocalLLaMA/comments/17ixi71/llamacpp_tensor_split_on_different_types_of_gpus/ | false | false | self | 2 | null |
Can I fit a 70b model into two 24g 4090s at inference? | 3 | Hey, I'd appreciate if I can get an intuition into what 70b models can be split and fit into two 4090s.
Especially if quantization or other tricks are needed. | 2023-10-29T06:48:04 | https://www.reddit.com/r/LocalLLaMA/comments/17ix6go/can_i_fit_a_70b_model_into_two_24g_4090s_at/ | infinite_stream | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 17ix6go | false | null | t3_17ix6go | /r/LocalLLaMA/comments/17ix6go/can_i_fit_a_70b_model_into_two_24g_4090s_at/ | false | false | self | 3 | null |
Samantha Mistral Instruct 7B | 10 | Maybe it's just preference, and we all have our own workflow and use cases, but why am I not seeing more support for this model??
Performs well, consistent RAM usage, super small, Mistral Instruct is Mistral Instruct, it's a good model.
What really makes it work so well (for me at least) is how it can switch from rig... | 2023-10-29T05:28:50 | https://www.reddit.com/r/LocalLLaMA/comments/17iw46g/samantha_mistral_instruct_7b/ | Future_Might_8194 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 17iw46g | false | null | t3_17iw46g | /r/LocalLLaMA/comments/17iw46g/samantha_mistral_instruct_7b/ | false | false | self | 10 | null |
CodeLlamalalamalalmalamala | 12 | So it's pretty evident that vanilla CodeLlama prefers Python. Super ok with that. Python seems to be the go-to language for AI dev for a lot of reasons that make a lot of sense.
(Javascript/Node.js works too, especially if you're web-focused, but it seems like Python is just more capable and supported when working wi... | 2023-10-29T04:51:25 | https://www.reddit.com/r/LocalLLaMA/comments/17ivl3z/codellamalalamalalmalamala/ | Future_Might_8194 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 17ivl3z | false | null | t3_17ivl3z | /r/LocalLLaMA/comments/17ivl3z/codellamalalamalalmalamala/ | false | false | self | 12 | null |
Best local model(s) to generate unit tests? | 9 | Hi folks - I’m new here and currently building a system with 2x4090s. I’d like to use it extensively to generate unit tests on entire codebases in Go and Python, with little to no existing testing. I’m curious how feasible this is, and what models and parameters would be best for this. Thanks! | 2023-10-29T04:07:35 | https://www.reddit.com/r/LocalLLaMA/comments/17iuxya/best_local_models_to_generate_unit_tests/ | ChangeIsHard_ | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 17iuxya | false | null | t3_17iuxya | /r/LocalLLaMA/comments/17iuxya/best_local_models_to_generate_unit_tests/ | false | false | self | 9 | {'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... |
Ideas for running this prompt over a CSV larger than my LLM's context window? | 3 | I want to run the following prompt on a 20k token CSV file. What are my options to do that processing? The prompt gives the correct output on smaller CSV files.
Some half-baked ideas I have:
* Manually chunk the CSV files to < 4096 tokens, run the query, then concatenate the results
* Use LlamaIndex to do it (how?)
... | 2023-10-29T03:15:00 | https://www.reddit.com/r/LocalLLaMA/comments/17iu3j5/ideas_for_running_this_prompt_over_a_csv_larger/ | kyjk | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 17iu3j5 | false | null | t3_17iu3j5 | /r/LocalLLaMA/comments/17iu3j5/ideas_for_running_this_prompt_over_a_csv_larger/ | false | false | self | 3 | null |
What're some best models for M2 max and 64 GB RAM | 2 | I have 12-core CPU and 38-core for GPU.
​
I wish there was a site which could share the models for a device with their configs | 2023-10-29T02:42:00 | https://www.reddit.com/r/LocalLLaMA/comments/17itjdb/whatre_some_best_models_for_m2_max_and_64_gb_ram/ | __am__i_ | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 17itjdb | false | null | t3_17itjdb | /r/LocalLLaMA/comments/17itjdb/whatre_some_best_models_for_m2_max_and_64_gb_ram/ | false | false | self | 2 | null |
Graphics card advice? | 5 | I'm currently looking at upgrading my pc and am trying to decide between the 4070 ti (12gb vram) and the 4080 (16gb vram). Would there be any disadvantage to saving $300 and going with the 4070 ti with 4gb less vram or should I just bite the bullet and get the 4080.
I'm mostly concerned if I can run and fine tune 7... | 2023-10-29T02:28:13 | https://www.reddit.com/r/LocalLLaMA/comments/17itaoe/graphics_card_advice/ | Iron_Ninja5 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 17itaoe | false | null | t3_17itaoe | /r/LocalLLaMA/comments/17itaoe/graphics_card_advice/ | false | false | self | 5 | null |
Are there any 30b models that are good? | 30 | I tried TheBloke/WizardLM-30B-Uncensored-GPTQ and TheBloke/Wizard-Vicuna-30B-Uncensored-GPTQ, and while I did see some improvements over the popular 13b ones it's not enough imo to justify the weight and the slowness.
It is my understanding that there aren't any base models of that size, and normally they jump from 13... | 2023-10-29T02:24:53 | https://www.reddit.com/r/LocalLLaMA/comments/17it8li/are_there_any_30b_models_that_are_good/ | Longjumping-Bake-557 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 17it8li | false | null | t3_17it8li | /r/LocalLLaMA/comments/17it8li/are_there_any_30b_models_that_are_good/ | false | false | self | 30 | null |
GPT-4 update: document upload and tool usage without switching | 1 | [removed] | 2023-10-29T01:54:59 | https://twitter.com/ldjconfirmed/status/1718433263105004006 | itsuka_dev | twitter.com | 1970-01-01T00:00:00 | 0 | {} | 17isp7k | false | {'oembed': {'author_name': 'LDJ', 'author_url': 'https://twitter.com/ldjconfirmed', 'cache_age': 3153600000, 'height': None, 'html': '<blockquote class="twitter-video"><p lang="en" dir="ltr">Anybody else see this? <a href="https://t.co/w64wuUMu3x">pic.twitter.com/w64wuUMu3x</a></p>— LDJ (@ldjconfirmed) <a href="h... | t3_17isp7k | /r/LocalLLaMA/comments/17isp7k/gpt4_update_document_upload_and_tool_usage/ | false | false | default | 1 | {'enabled': False, 'images': [{'id': 'fjJ-BKh7QIHvMHMD9Cmw_oxMh8Jk8ifEa5q-rRwNfXo', 'resolutions': [{'height': 73, 'url': 'https://external-preview.redd.it/0nfQZiSYj-CQlK-BrQ-Q-HeR4YvVFI5Zgzk4N-eEdF4.jpg?width=108&crop=smart&auto=webp&s=43cf71884edd611da803d08aa843d6df66de0491', 'width': 108}], 'source': {'height': 95,... |
Best Open Source Vision Model | 6 | Which is the best open source vision model at the moment? | 2023-10-29T01:09:42 | https://www.reddit.com/r/LocalLLaMA/comments/17irxbc/best_open_source_vision_model/ | tomd_96 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 17irxbc | false | null | t3_17irxbc | /r/LocalLLaMA/comments/17irxbc/best_open_source_vision_model/ | false | false | self | 6 | null |
Is it not allowed here to ask for suggestions on LLM? I thought this is one of the purpose of this subreddit? | 1 | [removed] | 2023-10-29T00:26:42 | https://www.reddit.com/r/LocalLLaMA/comments/17ir4u0/is_it_not_allowed_here_to_ask_for_suggestions_on/ | Spirited_Employee_61 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 17ir4u0 | false | null | t3_17ir4u0 | /r/LocalLLaMA/comments/17ir4u0/is_it_not_allowed_here_to_ask_for_suggestions_on/ | false | false | self | 1 | null |
Best local CPU model to summarize Wiki pages? | 1 | Is there anything I could run locally on Windows PC (no GPU) that would allow a reasonable summarization of Wiki content? Both at page and space level ... | 2023-10-28T23:13:16 | https://www.reddit.com/r/LocalLLaMA/comments/17ipq4l/best_local_cpu_model_to_summarize_wiki_pages/ | Otherwise-Tiger3359 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 17ipq4l | false | null | t3_17ipq4l | /r/LocalLLaMA/comments/17ipq4l/best_local_cpu_model_to_summarize_wiki_pages/ | false | false | self | 1 | null |
Noob Question: LM Studio Prompt Template | 9 | I'm trying to run Mistral 7B on LMStudio.
Where would I input the system prompt:
<|system|> </s> <|user|> {prompt}</s> <|assistant|> | 2023-10-28T23:09:05 | https://www.reddit.com/r/LocalLLaMA/comments/17ipn4n/noob_question_lm_studio_prompt_template/ | FuckShitFuck223 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 17ipn4n | false | null | t3_17ipn4n | /r/LocalLLaMA/comments/17ipn4n/noob_question_lm_studio_prompt_template/ | false | false | self | 9 | null |
What future models are you most excited for, and when? | 52 | Mistral 13b?
Llama 3?
GPT5?
Gemini?
Anything else I don't know about?
What are you waiting for? | 2023-10-28T22:59:45 | https://www.reddit.com/r/LocalLLaMA/comments/17ipg6w/what_future_models_are_you_most_excited_for_and/ | Longjumping-Bake-557 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 17ipg6w | false | null | t3_17ipg6w | /r/LocalLLaMA/comments/17ipg6w/what_future_models_are_you_most_excited_for_and/ | false | false | self | 52 | null |
Most performant option to run 13b LLM locally as a personal assistant for under $300 USD | 2 | Hi!
I'm asking around to find the most performant option to run 13b LLM locally as a personal assistant for under $300 USD. So far I've found these options:
1) MI25 (Slow but cheap (<100), difficult to setup, limited quant options<I believe>, requires special cooling, limited OS options).
2) Some android device like... | 2023-10-28T22:56:53 | https://www.reddit.com/r/LocalLLaMA/comments/17ipe7m/most_performant_option_to_run_13b_llm_locally_as/ | Envoy0675 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 17ipe7m | false | null | t3_17ipe7m | /r/LocalLLaMA/comments/17ipe7m/most_performant_option_to_run_13b_llm_locally_as/ | false | false | self | 2 | null |
Zephyr 7B beta is awesome! [+examples] | 104 | [zephyr-7b-beta.Q5\_K\_S](https://huggingface.co/TheBloke/zephyr-7B-beta-GGUF/blob/main/zephyr-7b-beta.Q5_K_S.gguf)
This guy is amazing!
Excluding the larger models, which I can't test due to VRAM limitations, I haven't seen another model as good as this one. And it's very lightweight. It may not have been 100% accur... | 2023-10-28T22:07:43 | https://www.reddit.com/r/LocalLLaMA/comments/17ioeoa/zephyr_7b_beta_is_awesome_examples/ | LazyCheetah42 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 17ioeoa | false | null | t3_17ioeoa | /r/LocalLLaMA/comments/17ioeoa/zephyr_7b_beta_is_awesome_examples/ | false | false | self | 104 | {'enabled': False, 'images': [{'id': 'LoQDaS4zhjDcxAkV62UU9xDWjBgFLzLbBz7EGRQ-YCw', 'resolutions': [{'height': 58, 'url': 'https://external-preview.redd.it/vM5It8igIVMa5UOokuHR6T7RcLxXyQq8-x4-Oyi92hc.jpg?width=108&crop=smart&auto=webp&s=62e31a7cfa81f5c3bc7c7ac10d8800322bd1cb21', 'width': 108}, {'height': 116, 'url': 'h... |
Thesis Leveraging Llama For Financial Analysis? | 7 | Hi. I'm about to write a master's thesis in the general field of AI and data science, and we have found a company to collaborate with, which is the norm here. This company is a startup offering an app with some analysis of different publicly traded stocks, such as sentiment analysis based on news and social media posts... | 2023-10-28T22:02:02 | https://www.reddit.com/r/LocalLLaMA/comments/17ioaje/thesis_leveraging_llama_for_financial_analysis/ | 7734128 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 17ioaje | false | null | t3_17ioaje | /r/LocalLLaMA/comments/17ioaje/thesis_leveraging_llama_for_financial_analysis/ | false | false | self | 7 | null |
Current best Mistral fine tune for coding (Python especially) | 2 | Hi! Title says it all. As much I want to check previous posts, advancement is really fast in this field and last month's post age like milk really fast. Any suggestions would be welcome. Thanks! | 2023-10-28T21:56:26 | https://www.reddit.com/r/LocalLLaMA/comments/17io6a9/current_best_mistral_fine_tune_for_coding_python/ | Spirited_Employee_61 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 17io6a9 | false | null | t3_17io6a9 | /r/LocalLLaMA/comments/17io6a9/current_best_mistral_fine_tune_for_coding_python/ | false | false | self | 2 | null |
Your favourite chat bot models | 6 | Hi everyone!
I am curious to see what everybody’s favourite chat bot models are.
I have been experimenting with Synthia but looking at trying out some more. | 2023-10-28T21:35:49 | https://www.reddit.com/r/LocalLLaMA/comments/17inqs2/your_favourite_chat_bot_models/ | Slimxshadyx | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 17inqs2 | false | null | t3_17inqs2 | /r/LocalLLaMA/comments/17inqs2/your_favourite_chat_bot_models/ | false | false | self | 6 | null |
What's your method to get first-person speech with conversation context? | 1 | For example: 'Here is an interview with \*x\* person, how would they respond to \*y\* question'. | 2023-10-28T21:13:02 | https://www.reddit.com/r/LocalLLaMA/comments/17in96o/whats_your_method_to_get_firstperson_speech_with/ | MordyOfTheMooMoo | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 17in96o | false | null | t3_17in96o | /r/LocalLLaMA/comments/17in96o/whats_your_method_to_get_firstperson_speech_with/ | false | false | self | 1 | null |
I finetuned Mistral on Anthony Bourdain's autobiography and now it swears like a chef! | 62 | Hey everyone,
So I've been experimenting with fine-tuning Mistral to create a chatbot with some character. It is trained on the autobiography of the chef Anthony Bourdain "kitchen confidential"
The result is a chatbot with a... colorful personality. Picture a straight-talking, brutally honest, kitchen war veteran ful... | 2023-10-28T20:20:33 | https://www.reddit.com/r/LocalLLaMA/comments/17im64e/i_finetuned_mistral_on_anthony_bourdains/ | HatEducational9965 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 17im64e | false | null | t3_17im64e | /r/LocalLLaMA/comments/17im64e/i_finetuned_mistral_on_anthony_bourdains/ | false | false | 62 | {'enabled': False, 'images': [{'id': '0qzUB07On6JaZMkOGDN84IgQJ4CHVDUUVtbr0vdzvn4', 'resolutions': [{'height': 58, 'url': 'https://external-preview.redd.it/Yr6HWGJaUFKzx38f7NY_Td-hKPIofuh6_Idfb0HbweI.jpg?width=108&crop=smart&auto=webp&s=aa71ef9cbe02446c6d7c50353800096b83a2a7f8', 'width': 108}, {'height': 116, 'url': 'h... | |
I have created a Chrome extension to chatGPT with the page. It uses locallama, is free with 100% privacy, and open open-source | 145 | Hey!
This extension uses local GPU to run LLAMA and answer question on any webpage
I am planning to make it 100% free and open source!
Soon, I would need help since this would require a macOS app running LLM in the background efficiently and I am not experienced in this at all!
Another important tech I want to ado... | 2023-10-28T20:12:43 | https://www.reddit.com/r/LocalLLaMA/comments/17im0cy/i_have_created_a_chrome_extension_to_chatgpt_with/ | Robert-treboR | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 17im0cy | false | null | t3_17im0cy | /r/LocalLLaMA/comments/17im0cy/i_have_created_a_chrome_extension_to_chatgpt_with/ | false | false | 145 | {'enabled': False, 'images': [{'id': 'QOFpB0cRKaiQZYYHwXPczwnmhN3-0vvex3OWYn7qBbU', 'resolutions': [{'height': 60, 'url': 'https://external-preview.redd.it/aNZTNc_d0V3Y9bcEwc-AIqP1fLrqklSde0f0NZLZNCY.jpg?width=108&crop=smart&auto=webp&s=6eb9583d822d84c90d47ea3f785b7588e783b0c6', 'width': 108}, {'height': 121, 'url': 'h... | |
Reverso_13b - Model to create Questions from the text | 84 | 2023-10-28T19:39:42 | FPham | i.redd.it | 1970-01-01T00:00:00 | 0 | {} | 17ilbr9 | false | null | t3_17ilbr9 | /r/LocalLLaMA/comments/17ilbr9/reverso_13b_model_to_create_questions_from_the/ | false | false | 84 | {'enabled': True, 'images': [{'id': 'uBqaq2dcvjpWU8u7WSVVXWwgZkeEynToAqqMXNBq1Q0', 'resolutions': [{'height': 99, 'url': 'https://preview.redd.it/s1ova3sqxzwb1.png?width=108&crop=smart&auto=webp&s=0b1b622520ddd4ed55d171725fd5a06e8ab71118', 'width': 108}, {'height': 199, 'url': 'https://preview.redd.it/s1ova3sqxzwb1.png... | |||
Experience on runpod | 12 | Hi everyone!
I was just wondering how everyone’s experience using runpod has been compared to any other services you might have used for cloud GPU’s? I’m considering it for hosting my model for inference, and possibly training (but that’s down the line). | 2023-10-28T19:36:54 | https://www.reddit.com/r/LocalLLaMA/comments/17il9n3/experience_on_runpod/ | Slimxshadyx | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 17il9n3 | false | null | t3_17il9n3 | /r/LocalLLaMA/comments/17il9n3/experience_on_runpod/ | false | false | self | 12 | null |
Advice for newbie looking for something that can do large context for low specs | 3 | I'm looking to setup a llama that will be used for summarization of long texts, maybe upwards of 50k tokens if possible. Could someone give me some advice on what are the minimum specs that would be needed for this and recommend a model that would be good. I think 7b should be ok since it's just summarizing? Also, if t... | 2023-10-28T18:11:28 | https://www.reddit.com/r/LocalLLaMA/comments/17iji9e/advice_for_newbie_looking_for_something_that_can/ | OstensiblyOriginal | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 17iji9e | false | null | t3_17iji9e | /r/LocalLLaMA/comments/17iji9e/advice_for_newbie_looking_for_something_that_can/ | false | false | self | 3 | null |
What's currently the best model that fits completely into a 24GB 3090? | 57 | Hey guys,
I'm wondering currently what's the best models that fits completely in a 3090s VRAM. And by fit I also mean it is able to process up to it's context length too.
My winner was wizard vicuna 30B for this one, but I'm wondering if there's anything better at the moment.
Also I don't mind uncensored or co... | 2023-10-28T18:07:09 | https://www.reddit.com/r/LocalLLaMA/comments/17ijf1a/whats_currently_the_best_model_that_fits/ | dangernoodle01 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 17ijf1a | false | null | t3_17ijf1a | /r/LocalLLaMA/comments/17ijf1a/whats_currently_the_best_model_that_fits/ | false | false | self | 57 | null |
Is there a Local Modal with Functions like ChatGPT? | 1 | [removed] | 2023-10-28T18:01:46 | https://www.reddit.com/r/LocalLLaMA/comments/17ijb11/is_there_a_local_modal_with_functions_like_chatgpt/ | schmedu | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 17ijb11 | false | null | t3_17ijb11 | /r/LocalLLaMA/comments/17ijb11/is_there_a_local_modal_with_functions_like_chatgpt/ | false | false | self | 1 | null |
CPU report - 64GB ram, no GPU, GPT4ALL - 5t/s | 1 | [removed] | 2023-10-28T16:54:00 | https://www.reddit.com/r/LocalLLaMA/comments/17ihx4g/cpu_report_64gb_ram_no_gpu_gpt4all_5ts/ | Overall-Importance54 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 17ihx4g | false | null | t3_17ihx4g | /r/LocalLLaMA/comments/17ihx4g/cpu_report_64gb_ram_no_gpu_gpt4all_5ts/ | false | false | self | 1 | null |
Single RTX 4090 FE at 40 tokens/s but with penalty if running 2 get only 10 tokens/s. Confirmed with Xwin-MLewd-13B-V0.2-GGUF. | 3 | As title, I run single RTX 4090 FE at 40 tokens/s but with penalty if running dual 4090s. It gets only 10 tokens/s. Confirmed with Xwin-MLewd-13B-V0.2-GGUF, and the famous speechless 13b.
Not sure if muti GPUs penalty on GGUF been discussed before. Does it make sense just because the model only need single 24GB GPU to... | 2023-10-28T16:51:17 | https://www.reddit.com/r/LocalLLaMA/comments/17ihv47/single_rtx_4090_fe_at_40_tokenss_but_with_penalty/ | easyllaama | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 17ihv47 | false | null | t3_17ihv47 | /r/LocalLLaMA/comments/17ihv47/single_rtx_4090_fe_at_40_tokenss_but_with_penalty/ | false | false | self | 3 | null |
API Server | 1 | Is there an easy way to serve a transformer or ctransformer model over an API? I would like something like vllm that provides an OpenAI compatible API: https://vllm.readthedocs.io/en/latest/getting_started/quickstart.html . The only issue I have with vllm is that it doesn't support all models and doesn't support quanti... | 2023-10-28T16:28:16 | https://www.reddit.com/r/LocalLLaMA/comments/17ihdrx/api_server/ | tomd_96 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 17ihdrx | false | null | t3_17ihdrx | /r/LocalLLaMA/comments/17ihdrx/api_server/ | false | false | self | 1 | null |
What do these values mean in Text Generate Web Ui? | 1 | I marked them with red arrows. I looked for guides but there is no information for these parameters.
There is nothing written about this in the Learn more section either.
Does this somehow affect the answers?
https://preview.redd.it/hwrrxe19zywb1.png?width=1395&format=png&auto=webp&s=a5c59861b2589ad5eed376131e95dd7d... | 2023-10-28T16:27:35 | https://www.reddit.com/r/LocalLLaMA/comments/17ihda4/what_do_these_values_mean_in_text_generate_web_ui/ | Secret_Joke_2262 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 17ihda4 | false | null | t3_17ihda4 | /r/LocalLLaMA/comments/17ihda4/what_do_these_values_mean_in_text_generate_web_ui/ | false | false | 1 | null | |
Local model for code in small machine | 6 | I have a modest spec PC (ntel(R) Core(TM) i5-7500 CPU @ 3.40GHz 3.40 GHz) 32Gb RAM , NVidia GTX 1050 (2Gb)
I would like to give the model access to my local instance of gitlab to learn from my code and comments to have a copilot-like assistant to avoid looking up solutions and boilerplate code I've already done and h... | 2023-10-28T16:13:29 | https://www.reddit.com/r/LocalLLaMA/comments/17ih2ut/local_model_for_code_in_small_machine/ | MagoViejo | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 17ih2ut | false | null | t3_17ih2ut | /r/LocalLLaMA/comments/17ih2ut/local_model_for_code_in_small_machine/ | false | false | self | 6 | null |
Using non-GGUF format with AutoGen and MemGPT | 1 | Is there a way to integrate big context models locally using AutoGen and MemGPT?
Like these 2 for exmaple:
[https://huggingface.co/abacusai/Giraffe-v2-13b-32k](https://huggingface.co/abacusai/Giraffe-v2-13b-32k)
[https://huggingface.co/abacusai/Giraffe-v2-70b-32k](https://huggingface.co/abacusai/Giraffe-v2-70b-3... | 2023-10-28T15:58:39 | https://www.reddit.com/r/LocalLLaMA/comments/17igrhn/using_nongguf_format_with_autogen_and_memgpt/ | PsykePro | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 17igrhn | false | null | t3_17igrhn | /r/LocalLLaMA/comments/17igrhn/using_nongguf_format_with_autogen_and_memgpt/ | false | false | self | 1 | {'enabled': False, 'images': [{'id': 'Rk1ek9Ogti9DfT8WX0e_5eKCmj92BfdfIYQblgKPnp4', 'resolutions': [{'height': 58, 'url': 'https://external-preview.redd.it/C3tP7TpzpnJIwpXyWFqt6KOc81H9r2s4gmyLCxCVIc0.jpg?width=108&crop=smart&auto=webp&s=3671711c768aa5ae2a347529a201922031d3c323', 'width': 108}, {'height': 116, 'url': 'h... |
LLM uses too much Vram | 1 | I m using [Synthia 13b](https://huggingface.co/TheBloke/Synthia-13B-v1.2-GGUF) with llama-cpp-python and it uses more than 20gb vram sometimes it uses just 16gb wich it should uses but i dont know why
llm = Llama(
model_path=model_path,
temperature=0.4,
n_gpu_layers=-1,
n_batch=3000,
n_ctx=6900,
verbose=Fa... | 2023-10-28T15:53:46 | https://www.reddit.com/r/LocalLLaMA/comments/17ignyr/llm_uses_too_much_vram/ | Otherwise_Weather_57 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 17ignyr | false | null | t3_17ignyr | /r/LocalLLaMA/comments/17ignyr/llm_uses_too_much_vram/ | false | false | self | 1 | {'enabled': False, 'images': [{'id': 'HPpMPJ5dQcGmKuyfzK1jTeaFSJzuPHLwsNIFFR140m4', 'resolutions': [{'height': 58, 'url': 'https://external-preview.redd.it/-GRJRQQmXSFYZXsNGPgkumgz2F3mFVrfHKaI02UkEx8.jpg?width=108&crop=smart&auto=webp&s=486ad157c6a55cf97e7d29e5347115740dfe0049', 'width': 108}, {'height': 116, 'url': 'h... |
Training 7b or 13b llamas | 4 | Hey,
I'm quite new to this so I had a number of questions about the whole training process.
1. So how much data should be provided to train a relatively small llama model (mistral-7b for instance) to avoid overfitting but also achieve some decent outputs? Is there a standard convention for preprocessing or you woul... | 2023-10-28T15:38:41 | https://www.reddit.com/r/LocalLLaMA/comments/17igcqt/training_7b_or_13b_llamas/ | Perfect-Storm-99 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 17igcqt | false | null | t3_17igcqt | /r/LocalLLaMA/comments/17igcqt/training_7b_or_13b_llamas/ | false | false | self | 4 | null |
What consumer GPU setup to fine tune and infer with 70B models? | 6 | As per title, would really appreciate some hands on insight into suitable consumer grade GPU setup for fine tuning and local hosting of 70B models. Thanks | 2023-10-28T15:13:45 | https://www.reddit.com/r/LocalLLaMA/comments/17ifu48/what_consumer_gpu_setup_to_fine_tune_and_infer/ | LostGoatOnHill | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 17ifu48 | false | null | t3_17ifu48 | /r/LocalLLaMA/comments/17ifu48/what_consumer_gpu_setup_to_fine_tune_and_infer/ | false | false | self | 6 | null |
AgentBench | 1 | https://github.com/THUDM/AgentBench
Disclaimer: have not tested any open models with it. | 2023-10-28T15:06:59 | https://www.reddit.com/r/LocalLLaMA/comments/17ifpbp/agentbench/ | productboy | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 17ifpbp | false | null | t3_17ifpbp | /r/LocalLLaMA/comments/17ifpbp/agentbench/ | false | false | self | 1 | {'enabled': False, 'images': [{'id': 'aAz3zDJqG3QfobQBr293M0aQs_pPaNUyxnilKN9LRr4', 'resolutions': [{'height': 54, 'url': 'https://external-preview.redd.it/OqVTyIA989JcfaiNwIesVSWO5H9X8SKFUh8tLRAKMJA.jpg?width=108&crop=smart&auto=webp&s=b49ac1e0bb8aca3675b87a9e4470377db6d9bef2', 'width': 108}, {'height': 108, 'url': 'h... |
Mistral 7b might be pretrained to ace evals and it doesn’t have complex emergent language skills. | 131 | >Evidence of cramming for the leaderboard. Hugging Face’s Open LLM leaderboard (Beeching et al., 2023), which is based upon EleutherAI’s evaluation harness (Gao et al., 2021), is seen as a proving ground for open LLMs. Many models currently at the top of the leaderboard are LLaMA- 2 derivatives, and are ranked much hig... | 2023-10-28T14:45:39 | https://arxiv.org/abs/2310.17567 | rp20 | arxiv.org | 1970-01-01T00:00:00 | 0 | {} | 17if9lq | false | null | t3_17if9lq | /r/LocalLLaMA/comments/17if9lq/mistral_7b_might_be_pretrained_to_ace_evals_and/ | false | false | 131 | {'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... | |
Llama2 derived model with chatgpt dataset? | 1 | I find it intriguing that we haven't witnessed a surge in llama-derived models generated from ChatGPT datasets. It appears to be a low-hanging fruit endeavor that could potentially yield models with capabilities approaching those of ChatGPT in specific areas, all at a remarkably cost-effective rate. Any thoughts appre... | 2023-10-28T14:39:48 | https://www.reddit.com/r/LocalLLaMA/comments/17if5hv/llama2_derived_model_with_chatgpt_dataset/ | peterwu00 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 17if5hv | false | null | t3_17if5hv | /r/LocalLLaMA/comments/17if5hv/llama2_derived_model_with_chatgpt_dataset/ | false | false | self | 1 | null |
Any advice for people who wanna do llm work / enter AI industry in general? | 33 | Hi, I recently graduated a B.S. in Amath, currently doing an internship as SWE. Over the past year, I've become increasingly passionate about AI, and more specifically, LLMs.
More about me: I've self-studied and understand the basic stuff & architectures of neural networks (e.g., I've implemented CNN, RNN, and trans... | 2023-10-28T13:56:25 | https://www.reddit.com/r/LocalLLaMA/comments/17iebmm/any_advice_for_people_who_wanna_do_llm_work_enter/ | OneConfusion3313 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 17iebmm | false | null | t3_17iebmm | /r/LocalLLaMA/comments/17iebmm/any_advice_for_people_who_wanna_do_llm_work_enter/ | false | false | self | 33 | null |
What is considered the best local uncensored LLM right now? | 161 | I don't care about minimum specs requirements. | 2023-10-28T13:23:17 | https://www.reddit.com/r/LocalLLaMA/comments/17idphn/what_is_considered_the_best_local_uncensored_llm/ | iamcontinuous | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 17idphn | false | null | t3_17idphn | /r/LocalLLaMA/comments/17idphn/what_is_considered_the_best_local_uncensored_llm/ | false | false | self | 161 | null |
Synthetic Intelligent Agent (SynthIA) | 0 | Hey everyone!
I’m new to Reddit and just wanted to introduce myself. I’m the creator of SynthIA, a series of open source LLMs that span 7B, 13B, 34B and 70B parameters.
I’ve been in Deep Learning for a while now, and I enjoy training neural nets and building products with them.
I released SynthIA-70B-v1.5 (LLaMA-2)... | 2023-10-28T13:18:46 | https://www.reddit.com/r/LocalLLaMA/comments/17idmi3/synthetic_intelligent_agent_synthia/ | migtissera | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 17idmi3 | false | null | t3_17idmi3 | /r/LocalLLaMA/comments/17idmi3/synthetic_intelligent_agent_synthia/ | false | false | self | 0 | {'enabled': False, 'images': [{'id': 'KJfmm8_w8Xzvhy2uLQ4qMT5g4G5IKvaoUTPuP9grdeg', 'resolutions': [{'height': 58, 'url': 'https://external-preview.redd.it/auy4C6mLy426Ik9mpWUqdYcvUWDkKKG5tK8qs4vNzZA.jpg?width=108&crop=smart&auto=webp&s=ef46686f5f0757f4ad3b2116194d777a506816d3', 'width': 108}, {'height': 116, 'url': 'h... |
LLMs on gpu server | Options | 1 | [removed] | 2023-10-28T12:26:30 | https://www.reddit.com/r/LocalLLaMA/comments/17icpit/llms_on_gpu_server_options/ | ianuvrat | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 17icpit | false | null | t3_17icpit | /r/LocalLLaMA/comments/17icpit/llms_on_gpu_server_options/ | false | false | self | 1 | null |
Llama not much more transparent than GPT-4 | 24 | According to a Stanford study https://crfm.stanford.edu/fmti/ | 2023-10-28T07:30:33 | krazzmann | i.redd.it | 1970-01-01T00:00:00 | 0 | {} | 17i8k9s | false | null | t3_17i8k9s | /r/LocalLLaMA/comments/17i8k9s/llama_not_much_more_transparent_than_gpt4/ | false | false | 24 | {'enabled': True, 'images': [{'id': 'mbF5nM99POU8GR33xYg-ddFKRnMghp_I6O9b7xDP25o', 'resolutions': [{'height': 75, 'url': 'https://preview.redd.it/r2hwy05tbwwb1.jpg?width=108&crop=smart&auto=webp&s=d16bf4c92e95e1858faef04be244cbadc1fe1b82', 'width': 108}, {'height': 151, 'url': 'https://preview.redd.it/r2hwy05tbwwb1.jpg... | ||
Ryzen 1200 RTX 3060 12GB | 14 | I have Ryzen 1200 with 8GB ram.
Could I just slap an RTX 3060 12GB on this for Llama and Stable Diffusion?
Is GPU all that matters or will my CPU/ram bottleneck it? | 2023-10-28T07:10:31 | https://www.reddit.com/r/LocalLLaMA/comments/17i8aez/ryzen_1200_rtx_3060_12gb/ | KoalaReasonable2003 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 17i8aez | false | null | t3_17i8aez | /r/LocalLLaMA/comments/17i8aez/ryzen_1200_rtx_3060_12gb/ | false | false | self | 14 | null |
About to begin my PhD in Multi-Modality AI, any suggestions? | 1 | [removed] | 2023-10-28T06:41:08 | https://www.reddit.com/r/LocalLLaMA/comments/17i7vlf/about_to_begin_my_phd_in_multimodality_ai_any/ | Go2Heart | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 17i7vlf | false | null | t3_17i7vlf | /r/LocalLLaMA/comments/17i7vlf/about_to_begin_my_phd_in_multimodality_ai_any/ | false | false | self | 1 | null |
Is Language Agent Tree Search possible for local LLMs? | 8 | Mainly, was checking [This](https://paperswithcode.com/sota/code-generation-on-humaneval), and notice some 3 week old paper that pushed GPT4's HumanEval to new heights.
This is the github [repo](https://github.com/andyz245/LanguageAgentTreeSearch).
Is this possible with local LLMs? | 2023-10-28T06:38:36 | https://www.reddit.com/r/LocalLLaMA/comments/17i7ua4/is_language_agent_tree_search_possible_for_local/ | yehiaserag | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 17i7ua4 | false | null | t3_17i7ua4 | /r/LocalLLaMA/comments/17i7ua4/is_language_agent_tree_search_possible_for_local/ | false | false | self | 8 | {'enabled': False, 'images': [{'id': 'pcUoqqo34f_7pql8GNAXXEI7UU3exQN6L1DNElA7d88', 'resolutions': [{'height': 57, 'url': 'https://external-preview.redd.it/745BbLpV1VtZtiGM2rxt4Aj_KRZPrmNkuC8lyg7NKy4.jpg?width=108&crop=smart&auto=webp&s=47f924b964ed854cb8c0eed32163627f0beecba3', 'width': 108}, {'height': 114, 'url': 'h... |
difference between fp16, loading in 8 bit, q8_0 and gptq in oobabooga | 2 | so I have an fp16 model of 7b codellama and used it with both fp16 and 8 bit in oobabooga also in q8\_0 gguf.
8 bit oobabooga fp16 loaded in much faster than 16 bit (as expected).
my question is 8 bit is same as q8\_0 gguf or there is difference.
also there is response difference definitely between gptq and q8\_0 (... | 2023-10-28T05:57:40 | https://www.reddit.com/r/LocalLLaMA/comments/17i79w8/difference_between_fp16_loading_in_8_bit_q8_0_and/ | Glum-Regular8896 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 17i79w8 | false | null | t3_17i79w8 | /r/LocalLLaMA/comments/17i79w8/difference_between_fp16_loading_in_8_bit_q8_0_and/ | false | false | self | 2 | null |
Why is it that Llama2 and its fine-tuned derivative models are bad at giving single-word answers? | 9 | So I have been experimenting with Mistral, Alpaca, Vicuna, Llama-2 chat, WizardLM, with the task of answering in one word.
For example: 'Read the following information, 'the person watches TV 12 hours a day, 7 days, skipping meals and sleep' - and answer in one word. If the person is addicted to TV, answer yes. If th... | 2023-10-28T04:59:24 | https://www.reddit.com/r/LocalLLaMA/comments/17i6fkk/why_is_it_that_llama2_and_its_finetuned/ | realbeybladegod | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 17i6fkk | false | null | t3_17i6fkk | /r/LocalLLaMA/comments/17i6fkk/why_is_it_that_llama2_and_its_finetuned/ | false | false | self | 9 | null |
Train LLM to think like Elon Musk with RAG? | 0 | Is RAG suitable to allow the LLM to answer questions from a specific point of view? For example, the goal might be to have a LLM system that answers questions based on the way Elon Musk things, without his style of speech.
Will storing the embedding of Elon's tweets and writings into the RAG store be the best way to a... | 2023-10-28T04:49:53 | https://www.reddit.com/r/LocalLLaMA/comments/17i6arq/train_llm_to_think_like_elon_musk_with_rag/ | gptzerozero | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 17i6arq | false | null | t3_17i6arq | /r/LocalLLaMA/comments/17i6arq/train_llm_to_think_like_elon_musk_with_rag/ | false | false | self | 0 | null |
Llama 2 on Ubuntu - Error Connection Errored Out | 1 | All, I am trying to run the Llama 2 7B model on my Ubuntu box, which to be fair is a bit old and a bit shy of memory (8GB). I got it installed to use CPU only (since only Intel gpx) but when I run it and the WebGUI comes up and I try to load model-00001-of-00002.safetensors, after a while the WebGUI says Error Connect... | 2023-10-28T04:38:21 | https://www.reddit.com/r/LocalLLaMA/comments/17i64du/llama_2_on_ubuntu_error_connection_errored_out/ | neepster44 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 17i64du | false | null | t3_17i64du | /r/LocalLLaMA/comments/17i64du/llama_2_on_ubuntu_error_connection_errored_out/ | false | false | self | 1 | null |
Linux (Ubuntu22.04.3 ) Loading Model - Error Connection Errored Out | 1 | [removed] | 2023-10-28T04:31:13 | https://www.reddit.com/r/LocalLLaMA/comments/17i60gj/linux_ubuntu22043_loading_model_error_connection/ | Direct_System2464 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 17i60gj | false | null | t3_17i60gj | /r/LocalLLaMA/comments/17i60gj/linux_ubuntu22043_loading_model_error_connection/ | false | false | self | 1 | null |
For beginners, basics of precision and quantization | 1 | [removed] | 2023-10-28T03:44:58 | https://www.reddit.com/r/LocalLLaMA/comments/17i5ani/for_beginners_basics_of_precision_and_quantization/ | sang89 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 17i5ani | false | null | t3_17i5ani | /r/LocalLLaMA/comments/17i5ani/for_beginners_basics_of_precision_and_quantization/ | false | false | default | 1 | {'enabled': False, 'images': [{'id': 'sxa9EKAAkWdTZf9_s3xrtKTjcMIKDG1RGG2iF_lU310', 'resolutions': [{'height': 72, 'url': 'https://external-preview.redd.it/F4uosIGonzM59WcQ3RTCTYCz03cCF2mFgYxiJXiOgho.jpg?width=108&crop=smart&auto=webp&s=f5300dde812399699f4375a71b8a65493eb6fc60', 'width': 108}, {'height': 144, 'url': 'h... |
Newbie here. How can have an LLM spit out a medical specialist for any given symptom or sign. | 1 | My use case is that when a user enters any symptom (symptoms are from patients) or sign (signs are from doctors), the LLM should suggest a specialty. What the best medical pre-trained LLM for this and how can I fine-tune it? Thanks. I may want to create a UI so what framework and database would you advise? Thanks in ad... | 2023-10-28T03:14:36 | https://www.reddit.com/r/LocalLLaMA/comments/17i4sk3/newbie_here_how_can_have_an_llm_spit_out_a/ | gramshomes | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 17i4sk3 | false | null | t3_17i4sk3 | /r/LocalLLaMA/comments/17i4sk3/newbie_here_how_can_have_an_llm_spit_out_a/ | false | false | self | 1 | null |
What public datasets are available for instruction fine-tuning? | 1 | I would like to practice instruction fine-tuning. What public datasets are available out there for doing this? I barely can find any examples on datasets and code for instruction fine-tuning online. | 2023-10-28T03:08:36 | https://www.reddit.com/r/LocalLLaMA/comments/17i4oz9/what_public_datasets_are_available_for/ | Heavy-Perspective-83 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 17i4oz9 | false | null | t3_17i4oz9 | /r/LocalLLaMA/comments/17i4oz9/what_public_datasets_are_available_for/ | false | false | self | 1 | null |
Python langchain ctransformers help | 3 | Hi! I am trying to build a local chatbot using zephyr alpha 7b. I am using langchain and ctransformers for this. The issue I am having is that The model only get loaded when the AI responds and gets unloaded after the response. So there are no continuation with the chat. I am a beginner and I can't figure out how to ke... | 2023-10-28T03:07:37 | https://www.reddit.com/r/LocalLLaMA/comments/17i4odt/python_langchain_ctransformers_help/ | Spirited_Employee_61 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 17i4odt | false | null | t3_17i4odt | /r/LocalLLaMA/comments/17i4odt/python_langchain_ctransformers_help/ | false | false | self | 3 | null |
Jade - the ghost in the LLM? | 1 | [removed] | 2023-10-28T02:57:47 | 80Unknown08 | i.redd.it | 1970-01-01T00:00:00 | 0 | {} | 17i4i30 | false | null | t3_17i4i30 | /r/LocalLLaMA/comments/17i4i30/jade_the_ghost_in_the_llm/ | false | false | 1 | {'enabled': True, 'images': [{'id': 'Xt7URYbLvVd2IYarF4HmLHnMt1YXmXDamkCgpuqwFs8', 'resolutions': [{'height': 216, 'url': 'https://preview.redd.it/m3yim3g5zuwb1.jpg?width=108&crop=smart&auto=webp&s=7d415eb124e60f0cc962a043393062e85568dbe9', 'width': 108}, {'height': 432, 'url': 'https://preview.redd.it/m3yim3g5zuwb1.jp... | ||
Three things I think should get more attention | 52 |
1. **Tokenization Techniques**: Many people use the default BPE tokenizer for llama2 or other common tokenizers. But I think we could do a lot of experiments with different kinds of tokenizers, especially ones that are made to work well with certain types of data. The size of the vocabulary is a really important set... | 2023-10-28T02:45:54 | https://www.reddit.com/r/LocalLLaMA/comments/17i4ayr/three_things_i_think_should_get_more_attention/ | ExaminationNo8522 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 17i4ayr | false | null | t3_17i4ayr | /r/LocalLLaMA/comments/17i4ayr/three_things_i_think_should_get_more_attention/ | false | false | self | 52 | null |
Amazon's Mistral fine tune for long contexts | 66 | 2023-10-28T02:23:04 | https://huggingface.co/amazon/MistralLite | Palmik | huggingface.co | 1970-01-01T00:00:00 | 0 | {} | 17i3wah | false | null | t3_17i3wah | /r/LocalLLaMA/comments/17i3wah/amazons_mistral_fine_tune_for_long_contexts/ | false | false | 66 | {'enabled': False, 'images': [{'id': '9jYiJY8lgKiK3sA8dMGGl_poYgtYOT3qJROfc9cEw_o', 'resolutions': [{'height': 58, 'url': 'https://external-preview.redd.it/m-Qkc4922qQ0juqeOEBXLR92ObN3nyyR1KY9o9o_ZaE.jpg?width=108&crop=smart&auto=webp&s=8b1a07f53b4a13504e62f21571a46c7c9fb7783c', 'width': 108}, {'height': 116, 'url': 'h... | ||
A LLM after fine tuning for a task will lose the ability of doing other tasks? | 7 | This [post](https://www.philschmid.de/fine-tune-flan-t5) describes the process of fine tuning Flan-T5 for chat summarization task. The fine tuned model always produces a summarization for an input even if an input is to ask it to classify or do question answering on a text. Is that true after fine tuning for a task, a ... | 2023-10-28T02:03:36 | https://www.reddit.com/r/LocalLLaMA/comments/17i3jjq/a_llm_after_fine_tuning_for_a_task_will_lose_the/ | Heavy-Perspective-83 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 17i3jjq | false | null | t3_17i3jjq | /r/LocalLLaMA/comments/17i3jjq/a_llm_after_fine_tuning_for_a_task_will_lose_the/ | false | false | self | 7 | {'enabled': False, 'images': [{'id': 'KTf0_NBZg4jJ3fG1WdwRFbctiQeBtXDdmCN7pFG_c0w', 'resolutions': [{'height': 56, 'url': 'https://external-preview.redd.it/7xybzX_OkxFzha1hcMn0nYKFSp0J4C7XnMZpDY6j5Ik.jpg?width=108&crop=smart&auto=webp&s=ba02af42bfa054563320478a0f7042593ca4696e', 'width': 108}, {'height': 112, 'url': 'h... |
GPTQ, AWQ, EXL2, GGUF, and load_in_4bit... um. I'm confused. | 8 | I currently have settled on GGUF, but maybe that's the wrong choice?
I have a Nvidia 3090, and to me over speed, I prefer accuracy. So I want to push the boundaries with 30B or 70B models. 30B is fast on my card, but if I'm not using GGUF it seems to run out of memory. I have yet to load 70B without GGUF... even thou... | 2023-10-28T01:26:01 | https://www.reddit.com/r/LocalLLaMA/comments/17i2uzz/gptq_awq_exl2_gguf_and_load_in_4bit_um_im_confused/ | silenceimpaired | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 17i2uzz | false | null | t3_17i2uzz | /r/LocalLLaMA/comments/17i2uzz/gptq_awq_exl2_gguf_and_load_in_4bit_um_im_confused/ | false | false | self | 8 | null |
Llama.cpp auto image capture of your prompt text to better understand... | 0 | [removed] | 2023-10-28T00:30:58 | https://www.reddit.com/r/LocalLLaMA/comments/17i1t8u/llamacpp_auto_image_capture_of_your_prompt_text/ | MinimumPC | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 17i1t8u | false | null | t3_17i1t8u | /r/LocalLLaMA/comments/17i1t8u/llamacpp_auto_image_capture_of_your_prompt_text/ | false | false | default | 0 | null |
Synthetic Intelligent Agent (SynthIA) | 1 | [removed] | 2023-10-28T00:24:43 | https://www.reddit.com/r/LocalLLaMA/comments/17i1ozw/synthetic_intelligent_agent_synthia/ | migtissera | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 17i1ozw | false | null | t3_17i1ozw | /r/LocalLLaMA/comments/17i1ozw/synthetic_intelligent_agent_synthia/ | false | false | self | 1 | {'enabled': False, 'images': [{'id': 'KJfmm8_w8Xzvhy2uLQ4qMT5g4G5IKvaoUTPuP9grdeg', 'resolutions': [{'height': 58, 'url': 'https://external-preview.redd.it/auy4C6mLy426Ik9mpWUqdYcvUWDkKKG5tK8qs4vNzZA.jpg?width=108&crop=smart&auto=webp&s=ef46686f5f0757f4ad3b2116194d777a506816d3', 'width': 108}, {'height': 116, 'url': 'h... |
Any good mindmap GPT or simpler install for auto-mindmapping on guthub | 9 | Hello,
Trying to get some advice or help on moving forward with this. I have a few LLAMAs already running locally so not a total noob - MedAlpaca, wizard for coding, automatic1111, etc.
I would like to explore further using a mindmap GPT running locally and found this one \[[https://github.com/florian-kalisch/auto-m... | 2023-10-28T00:02:57 | https://www.reddit.com/r/LocalLLaMA/comments/17i19u2/any_good_mindmap_gpt_or_simpler_install_for/ | moustachiooo | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 17i19u2 | false | null | t3_17i19u2 | /r/LocalLLaMA/comments/17i19u2/any_good_mindmap_gpt_or_simpler_install_for/ | false | false | self | 9 | {'enabled': False, 'images': [{'id': 'X45t5rf98uOP9aSgtLfFtHQ5b_UQvE40xoGzU3BwY0o', 'resolutions': [{'height': 54, 'url': 'https://external-preview.redd.it/VBEmrszNiJqUTaSfnGHUIT2pkXwjznvpCFl3vpMa1a4.jpg?width=108&crop=smart&auto=webp&s=7798d200b0691c4faa37b96cc35ab51478827e7b', 'width': 108}, {'height': 108, 'url': 'h... |
A ChatGPT replacement for a 6GB GPU? | 1 | Hi, I'm been looking at options to run a local LLaMA that could replace ChatGPT (has the same functionality, like continued conversation and an easy to use interface) I tried LocalAI (found it on GitHub) and it's good but it's incredibly slow, could this be because of the app or is my VRAM amount just too low for local... | 2023-10-27T23:17:52 | https://www.reddit.com/r/LocalLLaMA/comments/17i0cz2/a_chatgpt_replacement_for_a_6gb_gpu/ | Arxari | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 17i0cz2 | false | null | t3_17i0cz2 | /r/LocalLLaMA/comments/17i0cz2/a_chatgpt_replacement_for_a_6gb_gpu/ | false | false | self | 1 | null |
Best open-source & local alternatives to GitHub Copilot for data science notebooks | 9 | Hi everyone,
I am interested in using a local model to help me when I do EDA, like Kaggle style. Do you know of good frameworks that plug a local LLM to a VS Code / Jupyter notebook experience?
So far I have found:
\- [LLM VS Code from Hugging Face](https://github.com/huggingface/llm-vscode)
\- [Jupyter AI](https:/... | 2023-10-27T23:17:20 | https://www.reddit.com/r/LocalLLaMA/comments/17i0cld/best_opensource_local_alternatives_to_github/ | Separate-Still3770 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 17i0cld | false | null | t3_17i0cld | /r/LocalLLaMA/comments/17i0cld/best_opensource_local_alternatives_to_github/ | false | false | self | 9 | {'enabled': False, 'images': [{'id': 'pZNLMV0YTRpHbSIXLnID2sv6hm53SyOeavaJH-iKqMA', 'resolutions': [{'height': 54, 'url': 'https://external-preview.redd.it/JZEjIvMoi2SusDccwbqbKp4aIlBxSUlnk9QZUxz_QDs.jpg?width=108&crop=smart&auto=webp&s=60bf0e68d11174262c5adb864039350d0a557056', 'width': 108}, {'height': 108, 'url': 'h... |
Subsets and Splits
No community queries yet
The top public SQL queries from the community will appear here once available.