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 ⌀ |
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
Pre-Training Artifacts in Falcon-740 | 1 | [removed] | 2023-07-29T20:59:01 | https://www.reddit.com/r/LocalLLaMA/comments/15d2qo4/pretraining_artifacts_in_falcon740/ | Mbando | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 15d2qo4 | false | null | t3_15d2qo4 | /r/LocalLLaMA/comments/15d2qo4/pretraining_artifacts_in_falcon740/ | false | false | self | 1 | null |
Anyone know how I can use llama 2 to do roleplay? | 2 | Well I see at 4chan people doing roleplay with llama2. So I want to try it. But with google colab and llama2 | 2023-07-29T20:24:03 | https://www.reddit.com/r/LocalLLaMA/comments/15d1xdp/anyone_know_how_i_can_use_llama_2_to_do_roleplay/ | juanse2609 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 15d1xdp | false | null | t3_15d1xdp | /r/LocalLLaMA/comments/15d1xdp/anyone_know_how_i_can_use_llama_2_to_do_roleplay/ | false | false | self | 2 | null |
Parsing ArXiV Document/Paper into Sections | 3 | Hey everyone! Is there a way of parsing a downloaded ArXiV pdf document into its constituent sections via Python? I want to get rid of all tables and figures and only use the text present in the document. Thank you. | 2023-07-29T19:45:13 | https://www.reddit.com/r/LocalLLaMA/comments/15d10ws/parsing_arxiv_documentpaper_into_sections/ | psj_2908 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 15d10ws | false | null | t3_15d10ws | /r/LocalLLaMA/comments/15d10ws/parsing_arxiv_documentpaper_into_sections/ | false | false | self | 3 | null |
Subreddit Wiki is forbidden (including the model page) | 1 | [removed] | 2023-07-29T19:18:06 | https://www.reddit.com/r/LocalLLaMA/comments/15d0efz/subreddit_wiki_is_forbidden_including_the_model/ | All_men_are_brothers | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 15d0efz | false | null | t3_15d0efz | /r/LocalLLaMA/comments/15d0efz/subreddit_wiki_is_forbidden_including_the_model/ | false | false | self | 1 | null |
Oobabooga same output, repetition | 7 | Anyway know why oobabooga ui regenerates same text and Kobold.cpp does not? | 2023-07-29T18:32:55 | https://www.reddit.com/r/LocalLLaMA/comments/15czc3x/oobabooga_same_output_repetition/ | Emergency_Drink_7063 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 15czc3x | false | null | t3_15czc3x | /r/LocalLLaMA/comments/15czc3x/oobabooga_same_output_repetition/ | false | false | self | 7 | null |
llama 13b is performing worse than llama 7b? | 18 | I am using both the models for the same usecase, which is question answering from a pdf document.
I am using llama-2-7b-chat-hf and llama-2-13b-chat-hf models.
The remaining pipeline being the same, the responses I'm getting from the 13b version is significantly worse than the 7b counterpart. The 7b model will provi... | 2023-07-29T18:18:39 | https://www.reddit.com/r/LocalLLaMA/comments/15cyzyw/llama_13b_is_performing_worse_than_llama_7b/ | comical_cow | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 15cyzyw | false | null | t3_15cyzyw | /r/LocalLLaMA/comments/15cyzyw/llama_13b_is_performing_worse_than_llama_7b/ | false | false | self | 18 | null |
Out of CUDA memory with Llama2-13B on RTX4090 | 18 | First attempts so probably being a moron :( Help please.
Config **1 x RTX 4090 - 16 vCPU 83 GB RAM** on runpod via TheBloke TextGen UI.
Model is **meta-llama/Llama-2-13b-hf**
Error message is:
`torch.cuda.OutOfMemoryError: CUDA out of memory. Tried to allocate 136.00 MiB (GPU 0; 23.65 GiB total capacity; 22.68 GiB... | 2023-07-29T17:13:50 | https://www.reddit.com/r/LocalLLaMA/comments/15cxi0n/out_of_cuda_memory_with_llama213b_on_rtx4090/ | olddoglearnsnewtrick | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 15cxi0n | false | null | t3_15cxi0n | /r/LocalLLaMA/comments/15cxi0n/out_of_cuda_memory_with_llama213b_on_rtx4090/ | false | false | self | 18 | null |
Finetuned WizardCoder for Text-To-SQL Tasks | 1 | ### Demo
https://huggingface.co/spaces/richardr1126/sql-skeleton-wizardcoder-demo
# Introduction
This project aims to use off-the-shelf large language models for text-to-SQL program sysnthesis tasks. After experimenting with various models, fine-tuning hyperparameters, and training datasets an optimal solution was id... | 2023-07-29T17:08:12 | https://huggingface.co/richardr1126/spider-skeleton-wizard-coder-merged | richardr1126 | huggingface.co | 1970-01-01T00:00:00 | 0 | {} | 15cxdfn | false | null | t3_15cxdfn | /r/LocalLLaMA/comments/15cxdfn/finetuned_wizardcoder_for_texttosql_tasks/ | false | false | 1 | {'enabled': False, 'images': [{'id': '24K_G7zmjIzC04FcpC6WpnL85CEiB-51givrlByGgQk', 'resolutions': [{'height': 58, 'url': 'https://external-preview.redd.it/-BATHQ9bg4kKD0XuvUwHHN4hYq1PYpUzQt0phM3zRF8.jpg?width=108&crop=smart&auto=webp&s=4982f598fe7580ad3aabb483b6f99b9560fdbd7d', 'width': 108}, {'height': 116, 'url': 'h... | |
Best library to use llama 2 in python project. | 3 | I want to start making some python project that uses llama 2 for predicting some text. I haven't done anything with llama-like models before, except using ChatGPT through its API. I wonder what the best python libraries exist that allow inference of llama 2 that could be easily used. It would be preferable to have all ... | 2023-07-29T17:04:33 | https://www.reddit.com/r/LocalLLaMA/comments/15cxae8/best_library_to_use_llama_2_in_python_project/ | Another__one | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 15cxae8 | false | null | t3_15cxae8 | /r/LocalLLaMA/comments/15cxae8/best_library_to_use_llama_2_in_python_project/ | false | false | self | 3 | null |
how to run TheBloke/airoboros-l2-70B-gpt4-1.4.1-GPTQ in uncensored mode on text-generation-webui. | 1 | [removed] | 2023-07-29T17:01:23 | https://www.reddit.com/r/LocalLLaMA/comments/15cx7of/how_to_run_theblokeairoborosl270bgpt4141gptq_in/ | 4rfgvbgredfc | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 15cx7of | false | null | t3_15cx7of | /r/LocalLLaMA/comments/15cx7of/how_to_run_theblokeairoborosl270bgpt4141gptq_in/ | false | false | self | 1 | null |
how to run TheBloke/airoboros-l2-70B-gpt4-1.4.1-GPTQ in uncensored mode on text-generation-webui. | 1 | [removed] | 2023-07-29T16:53:11 | https://www.reddit.com/r/LocalLLaMA/comments/15cx0x3/how_to_run_theblokeairoborosl270bgpt4141gptq_in/ | 4rfgvbgredfc | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 15cx0x3 | false | null | t3_15cx0x3 | /r/LocalLLaMA/comments/15cx0x3/how_to_run_theblokeairoborosl270bgpt4141gptq_in/ | false | false | nsfw | 1 | null |
Fine-tuning for custom domain knowledge | 44 | I would like to see if anyone has had success fine-tuning a LLaMa model for knowledge adoption.
It seems there are many examples of successfully fine-tuning for style and behavioral steering, but not as much for informational recall. If you know of an example, please share the code and dataset(if possible)!
I have at... | 2023-07-29T16:37:05 | https://www.reddit.com/r/LocalLLaMA/comments/15cwndg/finetuning_for_custom_domain_knowledge/ | rinse_repeat_wash | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 15cwndg | false | null | t3_15cwndg | /r/LocalLLaMA/comments/15cwndg/finetuning_for_custom_domain_knowledge/ | false | false | self | 44 | null |
How to authenticate in TextGen UI to download "protected" models from HF? | 2 | I am trying to download meta-llama/Llama-2-13b-hf from huggingface via TextGen but get a 403 error. I am registered on HF and can download via git but would like to understand how to do this via the TextGen UI. Thanks. | 2023-07-29T16:22:46 | https://www.reddit.com/r/LocalLLaMA/comments/15cwbf6/how_to_authenticate_in_textgen_ui_to_download/ | olddoglearnsnewtrick | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 15cwbf6 | false | null | t3_15cwbf6 | /r/LocalLLaMA/comments/15cwbf6/how_to_authenticate_in_textgen_ui_to_download/ | false | false | self | 2 | null |
Renting Cloud GPUs | 18 | I want to run Llama 2's 70B-chat model to assist another program I'm running. I am unable to run it efficiently on my own machine, so it looks like I'll have to rent GPUs until I can afford to build my own rig. What specs should I be looking out for? How fast would chat completion run? What are the down-sides of crowd-... | 2023-07-29T15:24:35 | https://www.reddit.com/r/LocalLLaMA/comments/15cuycs/renting_cloud_gpus/ | felatun | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 15cuycs | false | null | t3_15cuycs | /r/LocalLLaMA/comments/15cuycs/renting_cloud_gpus/ | false | false | self | 18 | null |
Is it just me or Llama 2 can't output very long responses in instruct mode? | 5 | So previous LLaMa like Airoboros 7B can easily generate 512 new tokens and still want a few more on prompts like "Describe in detail how \[...\]. Write several paragraphs."
But so far 7B models I tried on this prompt run for like 150-200 tokens and consider the task done.
Am I doing something wrong or that's how Llla... | 2023-07-29T14:23:49 | https://www.reddit.com/r/LocalLLaMA/comments/15ctki2/is_it_just_me_or_llama_2_cant_output_very_long/ | artoonu | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 15ctki2 | false | null | t3_15ctki2 | /r/LocalLLaMA/comments/15ctki2/is_it_just_me_or_llama_2_cant_output_very_long/ | false | false | self | 5 | null |
Llama text output to speech | 2 | I'm new to llama and AI/LLM.
I'm wondering if it's feasible to use llama as a speaking conversation partner.
Assuming Llama can coherently and clearly understand a person speaking, how fast will it be able to generate a response and talk back via TTS? | 2023-07-29T14:07:29 | https://www.reddit.com/r/LocalLLaMA/comments/15ct7lr/llama_text_output_to_speech/ | Such-Stay2346 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 15ct7lr | false | null | t3_15ct7lr | /r/LocalLLaMA/comments/15ct7lr/llama_text_output_to_speech/ | false | false | self | 2 | null |
Other GPUs on exllama? | 10 |
If you'd used exllama with workstation GPUs, older workstation GPUs (P100, P40) colab, AMD could you share results?
Does rocm fit less context per gb like how flash attention has panned out for SD? | 2023-07-29T14:04:31 | https://www.reddit.com/r/LocalLLaMA/comments/15ct582/other_gpus_on_exllama/ | Aaaaaaaaaeeeee | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 15ct582 | false | null | t3_15ct582 | /r/LocalLLaMA/comments/15ct582/other_gpus_on_exllama/ | false | false | self | 10 | null |
Estimating RAG System Throughput on AWS GPU Instances | 8 | I'm interested in running a Retrieval-Augmented Generation (RAG) system on AWS using GPU instances. I'm looking to get advice on how to estimate the query throughput I could expect to support a desired number of concurrent users on a given node configuration.
Details:
My RAG system uses dense vector retrieval and lla... | 2023-07-29T14:01:59 | https://www.reddit.com/r/LocalLLaMA/comments/15ct361/estimating_rag_system_throughput_on_aws_gpu/ | nuusain | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 15ct361 | false | null | t3_15ct361 | /r/LocalLLaMA/comments/15ct361/estimating_rag_system_throughput_on_aws_gpu/ | false | false | self | 8 | null |
Best LLM for coding? | 97 | What's the best open source LLM for coding?
Specifically, I want it to take my code and the correct code and explain to me why my code is wrong. | 2023-07-29T13:42:44 | https://www.reddit.com/r/LocalLLaMA/comments/15csnst/best_llm_for_coding/ | Chirumer | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 15csnst | false | null | t3_15csnst | /r/LocalLLaMA/comments/15csnst/best_llm_for_coding/ | false | false | self | 97 | null |
Custom home server or pc upgrade ? | 7 | I currently have an MacBook Pro 14 with M1 processor and a computer with:
\- AMD Ryzen 7 1700X Eight-Core Processor
\- MSI Nvidia GTX1080
\- 32 GB DDR3 RAM
\- 1 x 256GB NvME
\- 1 x 500 GB SSD
\- 1x 1TB Hard drive
I tried 13B parameters such as LLama which still work, but are quite slow. Anything bigger seems to ... | 2023-07-29T13:32:17 | https://www.reddit.com/r/LocalLLaMA/comments/15csfuk/custom_home_server_or_pc_upgrade/ | AntiqueSalamander310 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 15csfuk | false | null | t3_15csfuk | /r/LocalLLaMA/comments/15csfuk/custom_home_server_or_pc_upgrade/ | false | false | self | 7 | null |
This is Voxta - We made her - This is all real time | 51 | 2023-07-29T13:13:17 | https://v.redd.it/mr1wyyrvlweb1 | ReignMocap | /r/LocalLLaMA/comments/15cs1kr/this_is_voxta_we_made_her_this_is_all_real_time/ | 1970-01-01T00:00:00 | 0 | {} | 15cs1kr | false | {'reddit_video': {'bitrate_kbps': 0, 'dash_url': 'https://v.redd.it/mr1wyyrvlweb1/DASHPlaylist.mpd?a=1693314815%2CY2IzMWJkZjcxNTI1YWFlZjA5OTFmN2ViNmY2NTkyY2Q2M2M5ZjVjY2I0NjhiMmNjMDQyZWQzMjA5ZDI0YjUzMA%3D%3D&v=1&f=sd', 'duration': 75, 'fallback_url': 'https://v.redd.it/mr1wyyrvlweb1/DASH_1080.mp4?source=fallback', 'heig... | t3_15cs1kr | /r/LocalLLaMA/comments/15cs1kr/this_is_voxta_we_made_her_this_is_all_real_time/ | false | false | nsfw | 51 | {'enabled': False, 'images': [{'id': 'UvKYWTvRhmHHVlaIZseqdwSKiRUQNk_hhgDFZyh_jU0', 'resolutions': [{'height': 60, 'url': 'https://external-preview.redd.it/2PBC_1q67ZKoJ6K7F8UmmwcDwyBhMVCWP8E8b3UbQ4E.png?width=108&crop=smart&format=pjpg&auto=webp&s=f0af2f593a717e3794568e74c0424b033b64cbcb', 'width': 108}, {'height': 12... | |
Ctransformers now support LLaMa 2 70B | 20 | 2023-07-29T12:41:51 | https://github.com/marella/ctransformers/releases | Acrobatic-Site2065 | github.com | 1970-01-01T00:00:00 | 0 | {} | 15crdwa | false | null | t3_15crdwa | /r/LocalLLaMA/comments/15crdwa/ctransformers_now_support_llama_2_70b/ | false | false | 20 | {'enabled': False, 'images': [{'id': 's7thFEAvi5RcBWVol6CRCa9kohe_K86XMAL9nrkyDUA', 'resolutions': [{'height': 54, 'url': 'https://external-preview.redd.it/v2U5P1rYB91SIqAGk1tweDnQYAPubWF9Rb1_eYqwCEE.jpg?width=108&crop=smart&auto=webp&s=280186b154e3618a038e3140e827bafc535750bc', 'width': 108}, {'height': 108, 'url': 'h... | ||
I don't think llama likes me | 85 | 2023-07-29T12:10:19 | SrDigbyChickenCeaser | i.redd.it | 1970-01-01T00:00:00 | 0 | {} | 15cqrri | false | null | t3_15cqrri | /r/LocalLLaMA/comments/15cqrri/i_dont_think_llama_likes_me/ | false | false | 85 | {'enabled': True, 'images': [{'id': 'O1mDIt-v4q9M6zmrQopfIH7VVuYmthF9HiJ4NdTtkAA', 'resolutions': [{'height': 115, 'url': 'https://preview.redd.it/42uh2i9qaweb1.png?width=108&crop=smart&auto=webp&s=b751832ac8f1194dcd80b336ea00aab9d6880c66', 'width': 108}, {'height': 230, 'url': 'https://preview.redd.it/42uh2i9qaweb1.pn... | |||
I am getting worse llama-2-70b-guanaco-qlora.ggmlv3.q8_0.bin than airoboros-65B-gpt4-1.2-GGML | 14 | llama-2-70b-guanaco-qlora.ggmlv3.q8\_0.bin - think step by step
[https://paste.c-net.org/FatigueTended](https://paste.c-net.org/FatigueTended)
relationship entity prompt:
[https://paste.c-net.org/AlvinDollars](https://paste.c-net.org/AlvinDollars)
airoboros-65B-gpt4-1.2-GGML did much better:
[https://www... | 2023-07-29T11:06:38 | https://www.reddit.com/r/LocalLLaMA/comments/15cplvh/i_am_getting_worse_llama270bguanacoqloraggmlv3q8/ | dewijones92 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 15cplvh | false | null | t3_15cplvh | /r/LocalLLaMA/comments/15cplvh/i_am_getting_worse_llama270bguanacoqloraggmlv3q8/ | false | false | self | 14 | null |
Unveiling the Gender Demography of Emerging Tech Communities (Poll) | 0 | Comment on what compels you to try out the tech.
[View Poll](https://www.reddit.com/poll/15cmq2q) | 2023-07-29T08:15:20 | https://www.reddit.com/r/LocalLLaMA/comments/15cmq2q/unveiling_the_gender_demography_of_emerging_tech/ | runawaychicken | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 15cmq2q | false | null | t3_15cmq2q | /r/LocalLLaMA/comments/15cmq2q/unveiling_the_gender_demography_of_emerging_tech/ | false | false | self | 0 | null |
Model suggestion please | 1 | My need is ingesting newspaper articles and finding named entities (esp people, places and orgs) and also generate a few summary phrases.
Been playing with ChatGPT4 and results are much better than my traditional Stanford Stanza NLP approach.
What are the best self hosted models suggested to achieve results similar (... | 2023-07-29T07:58:23 | https://www.reddit.com/r/LocalLLaMA/comments/15cmfo2/model_suggestion_please/ | olddoglearnsnewtrick | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 15cmfo2 | false | null | t3_15cmfo2 | /r/LocalLLaMA/comments/15cmfo2/model_suggestion_please/ | false | false | self | 1 | null |
Making KoboldCpp save all output | 7 | I believe there are some people with zero coding experience who wish KoboldCpp had an option to save all output. I know there is "save story" button, but maybe you want all of them in one place. It's actually fairly easy; modify `koboldcpp.py` as below. What you want to do is to insert lines that starts with the plus s... | 2023-07-29T07:50:40 | https://www.reddit.com/r/LocalLLaMA/comments/15cmb4q/making_koboldcpp_save_all_output/ | SpecialNothingness | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 15cmb4q | false | null | t3_15cmb4q | /r/LocalLLaMA/comments/15cmb4q/making_koboldcpp_save_all_output/ | false | false | self | 7 | null |
Text reclassification prompts/code | 2 | Hey all,
I created some prompts to reclassify text to more meaningful input data for LLM or ML training/fine tuning, would anyone be interested or find any value in this?
I've also been working on a lot of projects like this and I'm wondering if there are specific communities that are centered around this sort of t... | 2023-07-29T07:44:54 | https://www.reddit.com/r/LocalLLaMA/comments/15cm7oa/text_reclassification_promptscode/ | MutedCatch | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 15cm7oa | false | null | t3_15cm7oa | /r/LocalLLaMA/comments/15cm7oa/text_reclassification_promptscode/ | false | false | self | 2 | {'enabled': False, 'images': [{'id': 'zaCeJ6rv6oJ_XMp0760EfPd4fXPVp97mY42SJCuVNU8', 'resolutions': [{'height': 108, 'url': 'https://external-preview.redd.it/pE9mM7R8v90jbI3S_gq_iPYp8UGBK4HR_-kfGqIC7GA.jpg?width=108&crop=smart&auto=webp&s=67ff44720d8757ccc066104f80e34c8b1352fd39', 'width': 108}, {'height': 216, 'url': '... |
Experience with cerebras/btlm-3b-8k-base | 1 | Has anybody tried using this model?
Can someone give the target_modules of this model to finetune with qlora | 2023-07-29T05:49:53 | https://www.reddit.com/r/LocalLLaMA/comments/15ck91i/experience_with_cerebrasbtlm3b8kbase/ | Sufficient_Run1518 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 15ck91i | false | null | t3_15ck91i | /r/LocalLLaMA/comments/15ck91i/experience_with_cerebrasbtlm3b8kbase/ | false | false | self | 1 | null |
Ai chatbot that gives robotic like responses? | 10 | Is there an chatbot that just answers questions without any assistant-like fluff text?
Example:
2 + 2 = 4
Instead of:
"Sure, here you go: 2 + 2 = 4.
Let me know if you need anything else!" | 2023-07-29T04:53:46 | https://www.reddit.com/r/LocalLLaMA/comments/15cj9ex/ai_chatbot_that_gives_robotic_like_responses/ | TheRollingDucat | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 15cj9ex | false | null | t3_15cj9ex | /r/LocalLLaMA/comments/15cj9ex/ai_chatbot_that_gives_robotic_like_responses/ | false | false | self | 10 | null |
New model from StabilityAi: Stable Beluga | 73 | A week ago or so StabilityAi launched the models FreeWilly and FreeWily2, based on Lamma 1 65b and Lamma 2 70B respectively. Then they renamed it to Stable Beluga, and today they lanched new Lamma 2 based variants with 7b and 13b parameters. What do you guys think?
Link 7B: https://huggingface.co/stabilityai/StableBel... | 2023-07-29T02:29:06 | https://www.reddit.com/r/LocalLLaMA/comments/15cgjej/new_model_from_stabilityai_stable_beluga/ | MacacoVelhoKK | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 15cgjej | false | null | t3_15cgjej | /r/LocalLLaMA/comments/15cgjej/new_model_from_stabilityai_stable_beluga/ | false | false | self | 73 | {'enabled': False, 'images': [{'id': 'kULT4QMVrffgHYLCSiGSdCHwSaPimBVWJBNMsitsDc0', 'resolutions': [{'height': 58, 'url': 'https://external-preview.redd.it/Z-Cj42ScBNi2-Yi3QHqXq91FsN_5AtZasUi9tPVXmL4.jpg?width=108&crop=smart&auto=webp&s=1a3de829906ed5dbdfef8865371a5246972a72c9', 'width': 108}, {'height': 116, 'url': 'h... |
GPU requirement question | 2 | Hello, I see a lot of posts about "vram" being the most important factor for LLM models.
So I wonder, does that mean an old Nvidia m10 or an AMD firepro s9170 (both 32gb) outperforms an AMD instinct mi50 16gb?
Asking because I recently bought 2 new ones and wondering if I should just sell them and get something else... | 2023-07-29T02:25:23 | https://www.reddit.com/r/LocalLLaMA/comments/15cggtf/gpu_requirement_question/ | Slight_Bath_4449 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 15cggtf | false | null | t3_15cggtf | /r/LocalLLaMA/comments/15cggtf/gpu_requirement_question/ | false | false | self | 2 | null |
How to reproduce a dataset from a paper called SUR-Adapter? | 1 | I'm trying to reproduce a dataset used here: [SUR-Adapter](https://github.com/Qrange-group/SUR-adapter).
[Examples of SUR-Adapter prompt understanding](https://preview.redd.it/peqeiuxvateb1.jpg?width=12310&format=pjpg&auto=webp&s=ecf8fe4303c3ab3fb0e5f6e3942d4440ea3c20bf)
SUR-Adapter uses an LLM like Llama to give ... | 2023-07-29T02:06:53 | https://www.reddit.com/r/LocalLLaMA/comments/15cg362/how_to_reproduce_a_dataset_from_a_paper_called/ | ninjasaid13 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 15cg362 | false | null | t3_15cg362 | /r/LocalLLaMA/comments/15cg362/how_to_reproduce_a_dataset_from_a_paper_called/ | false | false | 1 | null | |
Beginner help? | 18 | Hey all!
Been reading along for a while and an avid proponent of AI. I am somewhat capable when it comes to coding but I do feel like I’m somehow fairly behind on being able to grasp concepts behind AI.
I am a ChatGPT subscriber (I want to cancel) and I now have been able to run Wizard on Gpt4all. I’d like to begin ... | 2023-07-29T01:36:14 | https://www.reddit.com/r/LocalLLaMA/comments/15cfg2j/beginner_help/ | justanewacct | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 15cfg2j | false | null | t3_15cfg2j | /r/LocalLLaMA/comments/15cfg2j/beginner_help/ | false | false | self | 18 | null |
Any LLM Llama script from any GitHub repository that can summarize extensive portions of multiple long text (.txt) or DOCX documents from a folder and produce a summarized TXT file as the output. | 1 | as above | 2023-07-29T01:11:35 | https://www.reddit.com/r/LocalLLaMA/comments/15cexh0/any_llm_llama_script_from_any_github_repository/ | ZealousidealBadger47 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 15cexh0 | false | null | t3_15cexh0 | /r/LocalLLaMA/comments/15cexh0/any_llm_llama_script_from_any_github_repository/ | false | false | self | 1 | null |
LLaMA-2-7B-32K by togethercomputer | 132 | 2023-07-29T00:36:55 | https://huggingface.co/togethercomputer/LLaMA-2-7B-32K | brown2green | huggingface.co | 1970-01-01T00:00:00 | 0 | {} | 15ce6sq | false | null | t3_15ce6sq | /r/LocalLLaMA/comments/15ce6sq/llama27b32k_by_togethercomputer/ | false | false | 132 | {'enabled': False, 'images': [{'id': 'yoAlnlO31bWvxDt2ZPQlTqH9iazTvQwoeS-sUqsWgtw', 'resolutions': [{'height': 58, 'url': 'https://external-preview.redd.it/85BR1V8c4hx_wcFHOrIntRGZZLf-PLK-slB3rJOTsOY.jpg?width=108&crop=smart&auto=webp&s=ecde1bdfdd91dfd590fabe657c5615966e36eb14', 'width': 108}, {'height': 116, 'url': 'h... | ||
Transformer accuracy in Exllama? | 1 | [removed] | 2023-07-28T22:37:46 | https://www.reddit.com/r/LocalLLaMA/comments/15cbgjn/transformer_accuracy_in_exllama/ | sinsro | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 15cbgjn | false | null | t3_15cbgjn | /r/LocalLLaMA/comments/15cbgjn/transformer_accuracy_in_exllama/ | false | false | self | 1 | null |
Using Lora Model with Llama Index | 2 | Hi all,
I was able to fine-tune llama using qlora. I was also able to get llama\_index working to get context from documents.
However, I'm having issues merging these together. Mainly with the error message "'LlamaForCausalLM' object has no attribute 'metadata'" when trying to set up the ServiceContext
service\_cont... | 2023-07-28T22:27:21 | https://www.reddit.com/r/LocalLLaMA/comments/15cb7kq/using_lora_model_with_llama_index/ | Pro-Status | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 15cb7kq | false | null | t3_15cb7kq | /r/LocalLLaMA/comments/15cb7kq/using_lora_model_with_llama_index/ | false | false | self | 2 | null |
How are you using Llama 2 commercially ? | 1 | I am curious to see the different use case possibilities | 2023-07-28T21:53:35 | https://www.reddit.com/r/LocalLLaMA/comments/15cadgj/how_are_you_using_llama_2_commercially/ | Ken_Sanne | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 15cadgj | false | null | t3_15cadgj | /r/LocalLLaMA/comments/15cadgj/how_are_you_using_llama_2_commercially/ | false | false | self | 1 | null |
Transformer accuracy in Exllama? | 1 | [removed] | 2023-07-28T21:39:19 | https://www.reddit.com/r/LocalLLaMA/comments/15ca0n0/transformer_accuracy_in_exllama/ | calm-aspargus | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 15ca0n0 | false | null | t3_15ca0n0 | /r/LocalLLaMA/comments/15ca0n0/transformer_accuracy_in_exllama/ | false | false | self | 1 | null |
LLM with voice generation | 1 |
There used to be a tool called [try-alters.com](https://try-alters.com) which you could use to chat with characters(like Trump, Obama, and Shrek) which used GPT 4 with some pre prompts so you the AI pretended to be whoever you wanted, and it used elevenlabs to generate the voice for that character with the output from... | 2023-07-28T21:15:41 | https://www.reddit.com/r/LocalLLaMA/comments/15c9feq/llm_with_voice_generation/ | SimRacer101 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 15c9feq | false | null | t3_15c9feq | /r/LocalLLaMA/comments/15c9feq/llm_with_voice_generation/ | false | false | self | 1 | null |
The jailbreak works with Llama-2-7B-Chat-GGML | 1 | [removed] | 2023-07-28T20:53:05 | https://www.reddit.com/r/LocalLLaMA/comments/15c8v2p/the_jailbreak_works_with_llama27bchatggml/ | arch-btw- | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 15c8v2p | false | null | t3_15c8v2p | /r/LocalLLaMA/comments/15c8v2p/the_jailbreak_works_with_llama27bchatggml/ | false | false | self | 1 | {'enabled': False, 'images': [{'id': 'oFSJObsRJoaZQlhlV6gnh074pJdzH3DovnJiEy198Qs', 'resolutions': [{'height': 54, 'url': 'https://external-preview.redd.it/MazETya56rbIuDFJAGNnTdIqX9An9dQF6xAUHs-19NE.jpg?width=108&crop=smart&auto=webp&s=78fbed7964dfb03ff2611dd4554b755731cb9615', 'width': 108}, {'height': 108, 'url': 'h... |
Llama2 wants to secure the southern border | 1 | [removed] | 2023-07-28T20:50:59 | https://www.reddit.com/gallery/15c8t8n | Happy_Chicken9835 | reddit.com | 1970-01-01T00:00:00 | 0 | {} | 15c8t8n | false | null | t3_15c8t8n | /r/LocalLLaMA/comments/15c8t8n/llama2_wants_to_secure_the_southern_border/ | false | false | default | 1 | null |
New AI related jobs? | 6 | I remembered when everyone was trying to learn to code to get a better job, so that got me thinking, is there any chance that something AI related (like LLMs) could be the "new programming" and have a bunch of people interested in?
Because programming is sadly oversaturated (for trainees with no degree, especifically... | 2023-07-28T20:49:25 | https://www.reddit.com/r/LocalLLaMA/comments/15c8rrr/new_ai_related_jobs/ | allmightyloser | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 15c8rrr | false | null | t3_15c8rrr | /r/LocalLLaMA/comments/15c8rrr/new_ai_related_jobs/ | false | false | self | 6 | null |
Is there a way to force Llama2 to generate longer text? | 4 | I'm getting frustrated with it stopping and refusing to continue a story. Any sort of setting? | 2023-07-28T20:25:02 | https://www.reddit.com/r/LocalLLaMA/comments/15c864d/is_there_a_way_to_force_llama2_to_generate_longer/ | audiosheep | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 15c864d | false | null | t3_15c864d | /r/LocalLLaMA/comments/15c864d/is_there_a_way_to_force_llama2_to_generate_longer/ | false | false | self | 4 | null |
New model from KoboldAI based on llama-2 - "Holodeck" | 33 | 2023-07-28T20:03:22 | https://huggingface.co/KoboldAI/LLAMA2-13B-Holodeck-1-GGML | harrro | huggingface.co | 1970-01-01T00:00:00 | 0 | {} | 15c7mnw | false | null | t3_15c7mnw | /r/LocalLLaMA/comments/15c7mnw/new_model_from_koboldai_based_on_llama2_holodeck/ | false | false | 33 | {'enabled': False, 'images': [{'id': 'hK9mf3IwmrVwZ6yRKPEn8aiig619KxMaFIa93exluIQ', 'resolutions': [{'height': 58, 'url': 'https://external-preview.redd.it/UrciGQ4sIBgMN-JM6jzyV9JRAPBDCSz_a1htJrKo558.jpg?width=108&crop=smart&auto=webp&s=402939d6bb14115a73b0493a34968bff2093b4a5', 'width': 108}, {'height': 116, 'url': 'h... | ||
WizardCoder extremely slow | 1 | Hey, I am currently build a small app for running wizardCoder locally on a RTX 3090. The inference with the huggingface-model loaded in 8 bit is however fairly slow. Are there any other ways for a faster inference? | 2023-07-28T19:40:13 | https://www.reddit.com/r/LocalLLaMA/comments/15c71qf/wizardcoder_extremely_slow/ | eggandbacon_0056 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 15c71qf | false | null | t3_15c71qf | /r/LocalLLaMA/comments/15c71qf/wizardcoder_extremely_slow/ | false | false | self | 1 | null |
Llama-2-70B-GPTQ seems very bad at coding. Am I doing it wrong? | 9 | ​
[exllama webui](https://preview.redd.it/d5eo14p59reb1.png?width=1923&format=png&auto=webp&s=759f2a17c9e19f5d4c432b40513cb61254614d1b)
I got the model from TheBloke/Llama-2-70B-GPTQ (gptq-4bit-32g-actorder\_True)
Using an AWS instance with 4x T4 GPUs (but actually 3 is sufficient).
Using exllama with `-gs 1... | 2023-07-28T19:12:59 | https://www.reddit.com/r/LocalLLaMA/comments/15c6co5/llama270bgptq_seems_very_bad_at_coding_am_i_doing/ | Remarkable_Ad4470 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 15c6co5 | false | null | t3_15c6co5 | /r/LocalLLaMA/comments/15c6co5/llama270bgptq_seems_very_bad_at_coding_am_i_doing/ | false | false | 9 | null | |
Do any of you have slight concerns that these models may have some subjective experience and we are effectively creating and killing people every time we train and delete them? | 0 | I know this will be dismissed out of hand by many, but the idea that LLMs, and especially their successor models, might be capable of subjective experience is being seriously entertained by some major academics
[https://www.youtube.com/watch?v=-BcuCmf00\_Y](https://www.youtube.com/watch?v=-BcuCmf00_Y)
As we see thes... | 2023-07-28T18:20:30 | https://www.reddit.com/r/LocalLLaMA/comments/15c507y/do_any_of_you_have_slight_concerns_that_these/ | 30299578815310 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 15c507y | false | null | t3_15c507y | /r/LocalLLaMA/comments/15c507y/do_any_of_you_have_slight_concerns_that_these/ | false | false | self | 0 | {'enabled': False, 'images': [{'id': 'xAWhV5Tinq2x4GS5F2dTr9e9-vE8jz5BVHebAZ8PjJM', 'resolutions': [{'height': 81, 'url': 'https://external-preview.redd.it/Hd4Rtz7WPKvWNza4iHT4QUqAOEjVQLpDMees9mlKKyQ.jpg?width=108&crop=smart&auto=webp&s=271abc1717bc2ba279dda41852f58454dfb4aef0', 'width': 108}, {'height': 162, 'url': 'h... |
Help getting LocalAI working on older hardware | 1 | DevOps guy here, trying to get a local 7b model running on my old piece of shit desktop (i5 2500k @ 4.5 GHz / 32GB RAM / GTX 1060 6GB).
I've managed to get LocalAI to successfully load the model, by compiling from master without AVX2, but I'm unable to get the model to generate a response. The API request just hangs i... | 2023-07-28T18:08:16 | https://www.reddit.com/r/LocalLLaMA/comments/15c4p3c/help_getting_localai_working_on_older_hardware/ | SilverbackReborn | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 15c4p3c | false | null | t3_15c4p3c | /r/LocalLLaMA/comments/15c4p3c/help_getting_localai_working_on_older_hardware/ | false | false | self | 1 | null |
Have any of you had luck applying your LLM skills professionally or is this mostly a hobby for you? | 26 | What do you all do professionally? Are your places of work receptive to this stuff? | 2023-07-28T18:08:06 | https://www.reddit.com/r/LocalLLaMA/comments/15c4oy3/have_any_of_you_had_luck_applying_your_llm_skills/ | 029187 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 15c4oy3 | false | null | t3_15c4oy3 | /r/LocalLLaMA/comments/15c4oy3/have_any_of_you_had_luck_applying_your_llm_skills/ | false | false | self | 26 | null |
Dockerized Full Stack llama.cpp API server and R (rshiny) application | 14 | [removed] | 2023-07-28T18:02:30 | Happy_Chicken9835 | i.redd.it | 1970-01-01T00:00:00 | 0 | {} | 15c4ju3 | false | null | t3_15c4ju3 | /r/LocalLLaMA/comments/15c4ju3/dockerized_full_stack_llamacpp_api_server_and_r/ | false | false | 14 | {'enabled': True, 'images': [{'id': '7gJrKf0dPMQZAq5SMQEuBh64nrXMfq0AEgNsMKu26vc', 'resolutions': [{'height': 97, 'url': 'https://preview.redd.it/7lhr550pwqeb1.jpg?width=108&crop=smart&auto=webp&s=d905c684f73dd67426be9bace23de1539f759adb', 'width': 108}, {'height': 195, 'url': 'https://preview.redd.it/7lhr550pwqeb1.jpg... | ||
I have spent that last 7 months building an open-source mind mapping tool that combines fractals with Ai. Here is some of what it can do. | 1 | [removed] | 2023-07-28T17:49:13 | https://www.reddit.com/r/LocalLLaMA/comments/15c47or/i_have_spent_that_last_7_months_building_an/ | Intrepid-Air6525 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 15c47or | false | null | t3_15c47or | /r/LocalLLaMA/comments/15c47or/i_have_spent_that_last_7_months_building_an/ | false | false | 1 | {'enabled': False, 'images': [{'id': 'j7hqsJ-JheSRZ8wssndPSy4QBqePCw0DHdaUdXioySw', 'resolutions': [{'height': 59, 'url': 'https://external-preview.redd.it/bg5t4oGicQV1criF1mjnKc5UAA6BjFWjRUKDj65ePTI.jpg?width=108&crop=smart&auto=webp&s=f9adabbb37913b9c83c7853cc62bd58e424583f4', 'width': 108}, {'height': 118, 'url': 'h... | |
We just launched a YC company to help devs work with LLMs and vector DBs | 1 | [removed] | 2023-07-28T17:16:43 | https://www.reddit.com/r/LocalLLaMA/comments/15c3dxu/we_just_launched_a_yc_company_to_help_devs_work/ | hegel-ai | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 15c3dxu | false | null | t3_15c3dxu | /r/LocalLLaMA/comments/15c3dxu/we_just_launched_a_yc_company_to_help_devs_work/ | false | false | self | 1 | {'enabled': False, 'images': [{'id': 'tQ1SPjcWzbiiFnhwUbZ6366HlV7H35X13LYc2mUgPSY', 'resolutions': [{'height': 33, 'url': 'https://external-preview.redd.it/PEYotcaNhzJA4H5BPMrbVdD7z70cTz3w5RzP6-5X4oY.jpg?width=108&crop=smart&auto=webp&s=9eeef23a922cd053a5affc57ae6fd857ae0dfe61', 'width': 108}, {'height': 66, 'url': 'ht... |
Best model to use | 6 | Hi! I was wondering which fine-tuned 7b model would be best for local casual use. If you have any suggestions I’d appreciate it if you leave them in the comments below. | 2023-07-28T16:45:44 | https://www.reddit.com/r/LocalLLaMA/comments/15c2lg4/best_model_to_use/ | NeoPlayzGames | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 15c2lg4 | false | null | t3_15c2lg4 | /r/LocalLLaMA/comments/15c2lg4/best_model_to_use/ | false | false | self | 6 | null |
Hardware options for LLM | 1 | I'm newbie to LLM, just preping HW setup for first run of local model. As far as i could found info, I understood that on 12GB VRAM (RTX 4070), and 64GB RAM DDR5, I should be able to run 13B models in CPU&GPU configuration - easily, and maybe even 60B on CPU alone.
I was wondering, did anybody tried hybrid memory setu... | 2023-07-28T16:40:36 | https://www.reddit.com/r/LocalLLaMA/comments/15c2gos/hardware_options_for_llm/ | dodo13333 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 15c2gos | false | null | t3_15c2gos | /r/LocalLLaMA/comments/15c2gos/hardware_options_for_llm/ | false | false | self | 1 | null |
Is LLaMa 2 a Poison Pill? | 0 | I have heard so many complaints about it being overly censored. I tried asking it how to kill a process but it refuses on the premise that "we should not treat software and computer systems with violence".
So I can't help but suspect if this base model is released in order to cripple or destroy the open model ecosyst... | 2023-07-28T16:38:00 | https://www.reddit.com/r/LocalLLaMA/comments/15c2eh8/is_llama_2_a_poison_pill/ | pigpag_ | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 15c2eh8 | false | null | t3_15c2eh8 | /r/LocalLLaMA/comments/15c2eh8/is_llama_2_a_poison_pill/ | false | false | self | 0 | null |
Building a PC - Ideias | 1 | I´m building a PC and right now I´ve:
\- Processor: 7900 x (amd)
\- 64 GB RAM DDR5 6000
​
But the issue is at the GPU level. The RTX 4080 (RTX 4080 Trinity ZOTAC) is 50 USD more them the 7900 XTX (Vapor-X Sapphir). I can´t aford the 4090, prices are crazy in my region.
XTX has more VRAM, in theory more ... | 2023-07-28T16:21:52 | https://www.reddit.com/r/LocalLLaMA/comments/15c1zm7/building_a_pc_ideias/ | No_One_BR | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 15c1zm7 | false | null | t3_15c1zm7 | /r/LocalLLaMA/comments/15c1zm7/building_a_pc_ideias/ | false | false | self | 1 | null |
Can I run any thing with Quadro T1000 4GB VRAM? | 1 | I have a P53 and was wondering if I can try running any small(tiny) models using it. Would more RAM help since I can’t increase the VRAM. I am not very concerned about speed just want to tinker around with any model.
Thanks. | 2023-07-28T16:20:06 | https://www.reddit.com/r/LocalLLaMA/comments/15c1xyk/can_i_run_any_thing_with_quadro_t1000_4gb_vram/ | ajollygdfellow | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 15c1xyk | false | null | t3_15c1xyk | /r/LocalLLaMA/comments/15c1xyk/can_i_run_any_thing_with_quadro_t1000_4gb_vram/ | false | false | self | 1 | null |
Llama2 | 1 | [removed] | 2023-07-28T16:17:34 | Upbeat-Ad-2183 | i.redd.it | 1970-01-01T00:00:00 | 0 | {} | 15c1vv9 | false | null | t3_15c1vv9 | /r/LocalLLaMA/comments/15c1vv9/llama2/ | false | false | 1 | {'enabled': True, 'images': [{'id': 'EXaoOCjkFhpu5KDFO9w4GNeEP_wO_94tr1xgkOOd6yQ', 'resolutions': [{'height': 72, 'url': 'https://preview.redd.it/a9vc5y5zdqeb1.jpg?width=108&crop=smart&auto=webp&s=0d4703d6f8f2b6e22a2739f8ec74ff87eb4c1d7a', 'width': 108}, {'height': 144, 'url': 'https://preview.redd.it/a9vc5y5zdqeb1.jpg... | ||
Llama2 | 1 | [removed] | 2023-07-28T16:15:50 | Upbeat-Ad-2183 | i.redd.it | 1970-01-01T00:00:00 | 0 | {} | 15c1ub9 | false | null | t3_15c1ub9 | /r/LocalLLaMA/comments/15c1ub9/llama2/ | false | false | 1 | {'enabled': True, 'images': [{'id': 'pau6GjTUSpQlbj3h_IyNNg8yxQIuIfwctEnxCGvVQBk', 'resolutions': [{'height': 72, 'url': 'https://preview.redd.it/lrfu0c1odqeb1.jpg?width=108&crop=smart&auto=webp&s=79c7d74d5f608b2a83bfefe87961782955ae62af', 'width': 108}, {'height': 144, 'url': 'https://preview.redd.it/lrfu0c1odqeb1.jpg... | ||
Self-hosted LLama2 in AI Code Assistant : Refact | 27 | 2023-07-28T16:15:39 | https://github.com/smallcloudai/refact | no_doping | github.com | 1970-01-01T00:00:00 | 0 | {} | 15c1u4d | false | null | t3_15c1u4d | /r/LocalLLaMA/comments/15c1u4d/selfhosted_llama2_in_ai_code_assistant_refact/ | false | false | 27 | {'enabled': False, 'images': [{'id': '0VxXGSDkUeuqlx4ZaeVpQgNbrSZkeEBnI4BxeMfydDU', 'resolutions': [{'height': 54, 'url': 'https://external-preview.redd.it/h6GWMSJxpOFGjmW6LiOjkkKGh3tcrxAHXiVx6pCVfsA.jpg?width=108&crop=smart&auto=webp&s=bc55a8ebc1e0cb3815c5aca119b6d5a5eff3f885', 'width': 108}, {'height': 108, 'url': 'h... | ||
llama.cpp、vllm or exllma and others？ | 1 | [removed] | 2023-07-28T16:14:07 | https://www.reddit.com/r/LocalLLaMA/comments/15c1sn4/llamacppvllm_or_exllma_and_others/ | cool_xixi | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 15c1sn4 | false | null | t3_15c1sn4 | /r/LocalLLaMA/comments/15c1sn4/llamacppvllm_or_exllma_and_others/ | false | false | self | 1 | {'enabled': False, 'images': [{'id': 'DJPqvteONpGwVVw6LzaG6b8vlDa2rv2hETCaqe0z57s', 'resolutions': [{'height': 54, 'url': 'https://external-preview.redd.it/ohwupr9MqnYXF974_2-gAgkZDuFxjDg48bFY3KdCQdc.jpg?width=108&crop=smart&auto=webp&s=b6caea286bbf31bdb473212eb5668f45376977be', 'width': 108}, {'height': 108, 'url': 'h... |
Is it possible to run anything on gtx 1660 Super ? | 2 | I have an nvidia gtx 1660 super card with 6gb vram and 32gb of ram. Is there any quantized small models that i could possibly run locally ? | 2023-07-28T16:01:39 | https://www.reddit.com/r/LocalLLaMA/comments/15c1gx0/is_it_possible_to_run_anything_on_gtx_1660_super/ | siam19 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 15c1gx0 | false | null | t3_15c1gx0 | /r/LocalLLaMA/comments/15c1gx0/is_it_possible_to_run_anything_on_gtx_1660_super/ | false | false | self | 2 | null |
LLongMA-2 16k: A Llama 2 16k model | 237 | Releasing LLongMA-2 16k, a suite of Llama-2 models, trained at 16k context length using linear positional interpolation scaling. The model was trained in collaboration with u/emozilla of NousResearch and u/kaiokendev.
The 13b model can be found on huggingface here: [https://huggingface.co/conceptofmind/LLongMA-2-13b-1... | 2023-07-28T15:32:16 | https://www.reddit.com/r/LocalLLaMA/comments/15c0pbs/llongma2_16k_a_llama_2_16k_model/ | EnricoShippole | self.LocalLLaMA | 1970-01-01T00:00:00 | 2 | {'gid_2': 2} | 15c0pbs | false | null | t3_15c0pbs | /r/LocalLLaMA/comments/15c0pbs/llongma2_16k_a_llama_2_16k_model/ | false | false | 237 | {'enabled': False, 'images': [{'id': 'UTrFWuaTSGL3VcrwmOeadZJBpghhjlyKIEuCqAexkDU', 'resolutions': [{'height': 58, 'url': 'https://external-preview.redd.it/piTf6fAplYyDsBUDFPgs6dVjRJlkAkLBfjQHBBKrbgk.jpg?width=108&crop=smart&auto=webp&s=53b41a86ebe64f74a499fbb67cdb359e665b7dbf', 'width': 108}, {'height': 116, 'url': 'h... | |
Hardware upgrade | 1 | 2023-07-28T15:20:06 | https://www.reddit.com/gallery/15c0dpt | Nondzu | reddit.com | 1970-01-01T00:00:00 | 0 | {} | 15c0dpt | false | null | t3_15c0dpt | /r/LocalLLaMA/comments/15c0dpt/hardware_upgrade/ | false | false | 1 | null | ||
Training Lora with Llama2-13B loss does not go down | 10 | Hello everyone.
I have prepared my own dataset which weights about 30MB and I'm trying to train LoRA.
I'm using oobabooga with default settings and loaded dataset as raw file. I'm using **TheBloke/Llama-2-13B-fp16** as model to train.
The problem is that training is going about 20 hours and **losss is still around 8... | 2023-07-28T14:53:20 | https://www.reddit.com/r/LocalLLaMA/comments/15bzoby/training_lora_with_llama213b_loss_does_not_go_down/ | DaniyarQQQ | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 15bzoby | false | null | t3_15bzoby | /r/LocalLLaMA/comments/15bzoby/training_lora_with_llama213b_loss_does_not_go_down/ | false | false | self | 10 | null |
I didn't think this level of censorship has possible | 248 | 2023-07-28T14:11:16 | Imaginary-Being8395 | i.redd.it | 1970-01-01T00:00:00 | 0 | {} | 15bykq4 | false | null | t3_15bykq4 | /r/LocalLLaMA/comments/15bykq4/i_didnt_think_this_level_of_censorship_has/ | false | false | 248 | {'enabled': True, 'images': [{'id': 'LqUJjN2V6GW7Qf7qv8iuN23SKPzthWpVV8yndQRN8sk', 'resolutions': [{'height': 67, 'url': 'https://preview.redd.it/m1l0regarpeb1.png?width=108&crop=smart&auto=webp&s=8eee822b266877ec5e9121558f5f5e1d43cb88e2', 'width': 108}, {'height': 135, 'url': 'https://preview.redd.it/m1l0regarpeb1.png... | |||
Researchers think they found some universal jailbreak prompts that work on many LLMs | 61 | 2023-07-28T14:02:09 | https://llm-attacks.org | chakalakasp | llm-attacks.org | 1970-01-01T00:00:00 | 0 | {} | 15bybxr | false | null | t3_15bybxr | /r/LocalLLaMA/comments/15bybxr/researchers_think_they_found_some_universal/ | false | false | default | 61 | null | |
Best setup and Settings for a Beginner? | 2 | Hey everyone!
I'm quite new when it comes to local chat models but I've got "oobabooga/text-generation-webui" installed on my Device and tried out "NousResearch\_Nous-Hermes-Llama2-13b".
It works, but it feels like it's pretty slow. (and becomes slower with each subsequent message). Most I got was like 0,45 Tokens ... | 2023-07-28T13:49:56 | https://www.reddit.com/r/LocalLLaMA/comments/15by0uk/best_setup_and_settings_for_a_beginner/ | ChrisX930 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 15by0uk | false | null | t3_15by0uk | /r/LocalLLaMA/comments/15by0uk/best_setup_and_settings_for_a_beginner/ | false | false | self | 2 | null |
An interesting take on the recent expansion of context size in LLM’s and the hidden cost of size vs. accuracy | 30 | Working with AI, in Context | 2023-07-28T13:45:25 | https://medium.com/@greg.broadhead/working-with-ai-in-context-958d7936c42e | Khan_Tango | medium.com | 1970-01-01T00:00:00 | 0 | {} | 15bxwxl | false | null | t3_15bxwxl | /r/LocalLLaMA/comments/15bxwxl/an_interesting_take_on_the_recent_expansion_of/ | false | false | default | 30 | null |
Index Error | 2 | I get the following error on multiple Llama2 7B chat models. I can run Llama2\_13B chat just fine, but the 7B keeps giving me this error:
​
Traceback (most recent call last):
File "C:\\oobabooga\_windows\\text-generation-webui\\modules\\[callbacks.py](https://callbacks.py)", line 55, in gentask
ret = self... | 2023-07-28T12:59:02 | https://www.reddit.com/r/LocalLLaMA/comments/15bws34/index_error/ | Comprehensive_Life_4 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 15bws34 | false | null | t3_15bws34 | /r/LocalLLaMA/comments/15bws34/index_error/ | false | false | self | 2 | null |
How do you point an LLM to a Folder, so that the knowledgebase is always updated by yourself? (TXT or Markdown) | 1 | [removed] | 2023-07-28T12:22:32 | https://www.reddit.com/r/LocalLLaMA/comments/15bvyu1/how_do_you_point_an_llm_to_a_folder_so_that_the/ | BetterProphet5585 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 15bvyu1 | false | null | t3_15bvyu1 | /r/LocalLLaMA/comments/15bvyu1/how_do_you_point_an_llm_to_a_folder_so_that_the/ | false | false | self | 1 | null |
The destroyer of fertility rates | 705 | 2023-07-28T12:03:01 | HOLUPREDICTIONS | i.redd.it | 1970-01-01T00:00:00 | 0 | {} | 15bvj5d | false | null | t3_15bvj5d | /r/LocalLLaMA/comments/15bvj5d/the_destroyer_of_fertility_rates/ | false | false | 705 | {'enabled': True, 'images': [{'id': 'MlGkmQXLprW2sXPAeg7nCYrI_Z3gB8LHwNJ0T1hV4eY', 'resolutions': [{'height': 87, 'url': 'https://preview.redd.it/vpv8havo3peb1.jpg?width=108&crop=smart&auto=webp&s=382a8446335b2a8ac2ae802f12784ddd017617de', 'width': 108}, {'height': 175, 'url': 'https://preview.redd.it/vpv8havo3peb1.jpg... | |||
Can I offload model layers to ram with exllama? | 3 | I use oobabooga and when I heard about exllama I was hyped, but after all this time I have not been able to use it.
When I select exllama, the slider to select the amount of layers to offload to ram disappears, I use 13b models with a 8gb vram card, so I have to offload some layers, is it possible?
I also tried to li... | 2023-07-28T11:44:11 | https://www.reddit.com/r/LocalLLaMA/comments/15bv4sk/can_i_offload_model_layers_to_ram_with_exllama/ | AltruisticMission865 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 15bv4sk | false | null | t3_15bv4sk | /r/LocalLLaMA/comments/15bv4sk/can_i_offload_model_layers_to_ram_with_exllama/ | false | false | self | 3 | null |
Llama 2 based models | 2 | I've been deploying multiple Open-source models on AWS and doing inference on them. I've been exploring LLMs since the past 2 months, and one thing l fail to understand is, how everyone is getting more than 1 line outputs from these LLMs, while I just manage to get 2-3 words of output from the LLM
I've used Llama2-7b, ... | 2023-07-28T11:23:45 | https://www.reddit.com/r/LocalLLaMA/comments/15bupka/llama_2_based_models/ | toximaniac | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 15bupka | false | null | t3_15bupka | /r/LocalLLaMA/comments/15bupka/llama_2_based_models/ | false | false | self | 2 | null |
Can you detect an EVIL superintellegence? MALOVELENT.AI game | 9 |
Hello everyone, I just finished a little project I was working on. I call it malevolent.ai. It is a game where people can talk to different AI's and try to determine if they are talking to an evil ai or not. I thought about publishing this as an actual website but it would cost too much money to keep it online and r... | 2023-07-28T11:18:27 | https://www.reddit.com/r/LocalLLaMA/comments/15bulni/can_you_detect_an_evil_superintellegence/ | roughman99 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 15bulni | false | null | t3_15bulni | /r/LocalLLaMA/comments/15bulni/can_you_detect_an_evil_superintellegence/ | false | false | self | 9 | {'enabled': False, 'images': [{'id': 'Z7-BVR0Dph-ckXY_kjhTg_oRsltQNfAskHpNx4Quf_Q', 'resolutions': [{'height': 54, 'url': 'https://external-preview.redd.it/niQSj283dpNxbSrIq66fZ4aHb_MOnoR2ulAcHpZaT4o.jpg?width=108&crop=smart&auto=webp&s=91b3653fadf460f8dc00011763759b06d5e83241', 'width': 108}, {'height': 108, 'url': 'h... |
How to increase overall length of text by having it write in chapters? | 4 | On consumer hardware, how can people generate longer stories?
Usually, user provides a prompt, then the AI provides an output.
How can you have the AI write an extended story? For example, the first output would be The Beginning, the next The Middle, the last The End.
How can you have the AI keep the whole... | 2023-07-28T11:00:57 | https://www.reddit.com/r/LocalLLaMA/comments/15bu8gu/how_to_increase_overall_length_of_text_by_having/ | innocuousAzureus | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 15bu8gu | false | null | t3_15bu8gu | /r/LocalLLaMA/comments/15bu8gu/how_to_increase_overall_length_of_text_by_having/ | false | false | self | 4 | null |
RTX 3050 has a far better GPU COMPUTE score than the 4060 ... What does it mean ? | 25 | Would a 3050 be better than a 4060 at running LLM models ? | 2023-07-28T08:59:25 | https://www.reddit.com/r/LocalLLaMA/comments/15bs00p/rtx_3050_has_a_far_better_gpu_compute_score_than/ | alexthai7 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 15bs00p | false | null | t3_15bs00p | /r/LocalLLaMA/comments/15bs00p/rtx_3050_has_a_far_better_gpu_compute_score_than/ | false | false | self | 25 | null |
Dockerized Full Stack llama.cpp API server and R (rshiny) application | 1 | [removed] | 2023-07-28T08:52:43 | Happy_Chicken9835 | i.redd.it | 1970-01-01T00:00:00 | 0 | {} | 15brvzy | false | null | t3_15brvzy | /r/LocalLLaMA/comments/15brvzy/dockerized_full_stack_llamacpp_api_server_and_r/ | false | false | 1 | {'enabled': True, 'images': [{'id': 'ZY_mURRXxQ9rFpc1nEUcEdns_rxjhWupp2YqCP6t9kc', 'resolutions': [{'height': 97, 'url': 'https://preview.redd.it/tt7mul1m6oeb1.jpg?width=108&crop=smart&auto=webp&s=717928d10221849ab065c214f2a0f9f2464193ad', 'width': 108}, {'height': 195, 'url': 'https://preview.redd.it/tt7mul1m6oeb1.jpg... | ||
A great summary/book notes prompt I have created... | 4 | I have found this to be most useful in Claude since the context length is so high and one can upload docs.
It is a multi-chain prompt:
So upload your doc then...
"make book notes for this book like Aseem Thakar. do chapter by chapter. indepth, do not lose detail."
then if you need more chapters...
"continue from ... | 2023-07-28T07:04:56 | https://www.reddit.com/r/LocalLLaMA/comments/15bq1re/a_great_summarybook_notes_prompt_i_have_created/ | ArmoredBattalion | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 15bq1re | false | null | t3_15bq1re | /r/LocalLLaMA/comments/15bq1re/a_great_summarybook_notes_prompt_i_have_created/ | false | false | self | 4 | null |
LORAHUB: EFFICIENT CROSS-TASK GENERALIZATION VIA DYNAMIC LORA COMPOSITION | 29 | ABSTRACT
>Low-rank adaptations (LoRA) are often employed to fine-tune large language models (LLMs) for new tasks. This paper investigates LoRA composability for cross-task generalization and introduces LoraHub, a strategic framework devised for the purposive assembly of LoRA modules trained on diverse given tasks, w... | 2023-07-28T06:56:37 | https://www.reddit.com/r/LocalLLaMA/comments/15bpwb0/lorahub_efficient_crosstask_generalization_via/ | ninjasaid13 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 15bpwb0 | false | null | t3_15bpwb0 | /r/LocalLLaMA/comments/15bpwb0/lorahub_efficient_crosstask_generalization_via/ | false | false | self | 29 | {'enabled': False, 'images': [{'id': 'ySWJANpphaORKInKmb5zfuKalmeGhJyUmfreENdhMlQ', 'resolutions': [{'height': 54, 'url': 'https://external-preview.redd.it/mNTtfzjcHSTGyYyVSxgjd2Ss3NsXS_GhLnINf3DUAv8.jpg?width=108&crop=smart&auto=webp&s=0f20f0d09960201ca6890be7bbb125c12f0748cd', 'width': 108}, {'height': 108, 'url': 'h... |
Running 70B models possible on modest desktop / GPU combo (32 GB ram + 12GB VRAM) | 74 | I just wanted to report that with some faffing around I was able to get a 70B 3 bit model inferencing at \~1 token / second on Win 11. It was a LOT slower via WSL, possibly because I couldn't get --mlock to work on such a high memory requirement.
./main -m \\Models\\TheBloke\\Llama-2-70B-Chat-GGML\\llama-2-70b-chat.gg... | 2023-07-28T06:31:01 | https://www.reddit.com/r/LocalLLaMA/comments/15bpggs/running_70b_models_possible_on_modest_desktop_gpu/ | gofiend | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 15bpggs | false | null | t3_15bpggs | /r/LocalLLaMA/comments/15bpggs/running_70b_models_possible_on_modest_desktop_gpu/ | false | false | self | 74 | null |
Fine-tuning btlm-3b | 5 | Has anyone managed to fine-tune the BTLM-3B from cerebras? I tried adapting a llama2 collab, but I got the following error in trainer.train()
> "RuntimeError: a view of a leaf Variable that requires grad is being used in an in-place operation"
it seems to stem from "modeling_btlm.py"
Wondering if anyone has managed... | 2023-07-28T06:14:44 | https://www.reddit.com/r/LocalLLaMA/comments/15bp658/finetuning_btlm3b/ | Disastrous_Elk_6375 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 15bp658 | false | null | t3_15bp658 | /r/LocalLLaMA/comments/15bp658/finetuning_btlm3b/ | false | false | self | 5 | null |
oobabooga webui regenerates same response, but Kobold.cpp doesn't. | 1 | Hello, can someone help me figure out what I'm doing wrong? I'd like to use oobabooga with Llama 2 7b chat, but it's very repetitive in general and I can't get a different output when regenerating. Kobold.cpp is giving a much more pleasant experience for story telling, but its slower. | 2023-07-28T06:11:05 | https://www.reddit.com/r/LocalLLaMA/comments/15bp3rf/oobabooga_webui_regenerates_same_response_but/ | Emergency_Drink_7063 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 15bp3rf | false | null | t3_15bp3rf | /r/LocalLLaMA/comments/15bp3rf/oobabooga_webui_regenerates_same_response_but/ | false | false | self | 1 | null |
The KoboldCpp FAQ and Knowledgebase - A comprehensive resource for newbies | 81 | To help answer the commonly asked questions and issues regarding KoboldCpp and ggml, I've assembled a comprehensive resource addressing them.
## [The KoboldCpp FAQ and Knowledgebase](https://github.com/LostRuins/koboldcpp/wiki)
Covers everything from "how to extend context past 2048 with rope scaling", "what is smart... | 2023-07-28T04:58:41 | https://www.reddit.com/r/LocalLLaMA/comments/15bnsju/the_koboldcpp_faq_and_knowledgebase_a/ | HadesThrowaway | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 15bnsju | false | null | t3_15bnsju | /r/LocalLLaMA/comments/15bnsju/the_koboldcpp_faq_and_knowledgebase_a/ | false | false | self | 81 | {'enabled': False, 'images': [{'id': 'SranydDsTrtSaHwiKfJiQ8O6z-OQrxBNPAec8DlgepM', 'resolutions': [{'height': 54, 'url': 'https://external-preview.redd.it/cWhk4HRILqs3JlO6Hf_sgi_YSWnjf-8u9-O9l9BYXPU.jpg?width=108&crop=smart&auto=webp&s=b4d998be0773bc2c099ebc74d3a2f89af655aa4e', 'width': 108}, {'height': 108, 'url': 'h... |
Step aside, Replika. Llama is just incredible for role-playing chat. Details of my Mac setup! | 67 | So this is a bit of a 101 post, I think, and I'm probably a noob compared to some folks here. It would have helped me to read this.
But also: *this is phenomenal!* Especially for my specific kink! Some people are going to get lost in this. I've tried Replika in the past and it's been pretty disappointing compared to L... | 2023-07-28T03:04:44 | https://www.reddit.com/r/LocalLLaMA/comments/15bln1a/step_aside_replika_llama_is_just_incredible_for/ | Ok_Ostrich788 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 15bln1a | false | null | t3_15bln1a | /r/LocalLLaMA/comments/15bln1a/step_aside_replika_llama_is_just_incredible_for/ | false | false | nsfw | 67 | {'enabled': False, 'images': [{'id': 't6DguaivFKnNtM-dvA1lByb5xG75-7OTREMJQESa2No', 'resolutions': [{'height': 54, 'url': 'https://external-preview.redd.it/7Ht9h6ZLwAuxQVSDa0Xuek6Ypp3ycZqK0oxRwST2o6w.jpg?width=108&crop=smart&auto=webp&s=d02c896ff248941637f893a517dc11079946a61d', 'width': 108}, {'height': 108, 'url': 'h... |
Jobs Where You Can Work With Local LLMs? | 12 | Aside from data scientist and ML engineer. I know a lot of those roles require a graduate degree in CS.
Is it useful to companies if you can deploy an LLM with Oobabooga and finetune LoRAs and QLoRAs? What if you add web scraping and Python to the mix? | 2023-07-28T02:58:23 | https://www.reddit.com/r/LocalLLaMA/comments/15bli8a/jobs_where_you_can_work_with_local_llms/ | renegadellama | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 15bli8a | false | null | t3_15bli8a | /r/LocalLLaMA/comments/15bli8a/jobs_where_you_can_work_with_local_llms/ | false | false | self | 12 | null |
Best version for local CPU inference | 1 | being playing around with some version and looking for best performance on new machine with 2 x 20 CPU cores and 192GB RAM, 12 GB VRAM, intended use for the model is to help on python coding, which llama flavor will be better to install locally and run? | 2023-07-28T02:38:01 | https://www.reddit.com/r/LocalLLaMA/comments/15bl3ki/best_version_for_local_cpu_inference/ | CalligrapherRich5100 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 15bl3ki | false | null | t3_15bl3ki | /r/LocalLLaMA/comments/15bl3ki/best_version_for_local_cpu_inference/ | false | false | self | 1 | null |
Model for analyzing court judgements | 1 | I have with me 1000+ Supreme Court Of India Judgement in .pdf format. Please suggest me a AI model for fine tuning it and querying these judgements. e.g. Show me all judgements related to rape and murder where Judge Mr. XXX gave a conviction. Give a summary of each judgement and relevant paragraph numbers. | 2023-07-28T02:34:19 | https://www.reddit.com/r/LocalLLaMA/comments/15bl0tj/model_for_analyzing_court_judgements/ | subhashp | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 15bl0tj | false | null | t3_15bl0tj | /r/LocalLLaMA/comments/15bl0tj/model_for_analyzing_court_judgements/ | false | false | self | 1 | null |
Extract information from a business document | 1 | I am trying to extract information from business documents. What should the prompt be? I used prompts like "Extract wages and tips, employee name, employee address" for a given W2 document.
I am using Llama-2-7b-chat-hf llm locally. | 2023-07-28T02:21:02 | https://www.reddit.com/r/LocalLLaMA/comments/15bkr38/extract_information_from_a_business_document/ | Few_Understanding76 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 15bkr38 | false | null | t3_15bkr38 | /r/LocalLLaMA/comments/15bkr38/extract_information_from_a_business_document/ | false | false | self | 1 | null |
Why doesn't the TensorRT format of Large Language Models attract much attention? | 0 | I have seen different formats of large language models such as HuggingFace, Pytorch + Fairscale, ONNX, and ggml. I observe that while TensorRT is often said as the go-to format when discussing fast inference, the reality is that I don't find people discussing or repositories making a TensorRT version of models such as ... | 2023-07-28T02:19:53 | https://www.reddit.com/r/LocalLLaMA/comments/15bkq6e/why_doesnt_the_tensorrt_format_of_large_language/ | Due_Experience7898 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 15bkq6e | false | null | t3_15bkq6e | /r/LocalLLaMA/comments/15bkq6e/why_doesnt_the_tensorrt_format_of_large_language/ | false | false | self | 0 | null |
Bleat - Function calling with LLaMA 2 | 66 | I've been working on a simple LoRA adapter for LLaMA 2 that allows it to do function calling. It works okay, but I still want to add some of the things OpenAI's is lacking (multiple calls, etc.). There is a Colab notebook to play with if you want. You can also host it locally with the script in the HuggingFace repo. En... | 2023-07-28T02:11:02 | https://www.reddit.com/r/LocalLLaMA/comments/15bkju6/bleat_function_calling_with_llama_2/ | ifansnek | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 15bkju6 | false | null | t3_15bkju6 | /r/LocalLLaMA/comments/15bkju6/bleat_function_calling_with_llama_2/ | false | false | self | 66 | {'enabled': False, 'images': [{'id': 'xGAmhJtXa7911jE13NHB_U-YQTI78ZcvihCLWJyqwKs', 'resolutions': [{'height': 58, 'url': 'https://external-preview.redd.it/wQhYytGxyYNUB3GekDoEgG2bISiO6_mgHierJc8GODY.jpg?width=108&crop=smart&auto=webp&s=6e5ffd583f6bee58c898a65848945926b96d9aa9', 'width': 108}, {'height': 116, 'url': 'h... |
LLMA 2 70B-Chat seem being instruct or aligned to refuse offensive or controversial topic | 0 | I do test on replicate and it lot refuse prompt and give me lot lecture to respect historical figure and not make fun of it or meme. It seem it need finetune first it you want make it able to chat and disscus controversial topic.
​ | 2023-07-28T01:44:17 | https://www.reddit.com/r/LocalLLaMA/comments/15bjzmf/llma_2_70bchat_seem_being_instruct_or_aligned_to/ | Merchant_Lawrence | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 15bjzmf | false | null | t3_15bjzmf | /r/LocalLLaMA/comments/15bjzmf/llma_2_70bchat_seem_being_instruct_or_aligned_to/ | false | false | self | 0 | null |
LLM for software Project | 2 | LLM for software Project
What is the tool like chatGPT or Cody(from SourceGraph) which we can use to educate on our software project(like an android application code base) and ask questions about it? | 2023-07-28T01:11:57 | https://www.reddit.com/r/LocalLLaMA/comments/15bjaym/llm_for_software_project/ | IncreaseObvious | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 15bjaym | false | null | t3_15bjaym | /r/LocalLLaMA/comments/15bjaym/llm_for_software_project/ | false | false | self | 2 | null |
how to embed code? | 4 | looking for a proper model for vectorizing codebases. i’m working on a visual tool for navigating and understanding projects but I’m not sure how to go about chunking the code to embed it—
For instance:
- should be some sort of strategy when it comes to deciding how big the chucks are and where the cutoff happens?
... | 2023-07-28T00:12:43 | https://www.reddit.com/r/LocalLLaMA/comments/15bi0yx/how_to_embed_code/ | LyPreto | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 15bi0yx | false | null | t3_15bi0yx | /r/LocalLLaMA/comments/15bi0yx/how_to_embed_code/ | false | false | self | 4 | null |
Lessons learned from cloning myself into an AI and posting it on Reddit | 74 | Over 1000 of y'all talked to the 65b AI version of me. [Original post with tech specs.](https://www.reddit.com/r/LocalLLaMA/comments/154to1w/i_trained_the_65b_model_on_my_texts_so_i_can_talk/) Figured I'd provide an update post with what I learned from the experience, what I found out from trying to make it more "usefu... | 2023-07-27T23:48:41 | https://www.reddit.com/r/LocalLLaMA/comments/15bhh2j/lessons_learned_from_cloning_myself_into_an_ai/ | LetMeGuessYourAlts | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 15bhh2j | false | null | t3_15bhh2j | /r/LocalLLaMA/comments/15bhh2j/lessons_learned_from_cloning_myself_into_an_ai/ | false | false | self | 74 | null |
What’s the best model for NSFW role play? | 137 | Would love to hear some experiences | 2023-07-27T22:46:01 | https://www.reddit.com/r/LocalLLaMA/comments/15bg093/whats_the_best_model_for_nsfw_role_play/ | bangarangguy | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 15bg093 | false | null | t3_15bg093 | /r/LocalLLaMA/comments/15bg093/whats_the_best_model_for_nsfw_role_play/ | false | false | nsfw | 137 | null |
Fine tuning LLaMA-2 for music melody generation - would qLoRA be effective? | 4 | I'm working on fine-tuning LLaMA-2-7B for music melody generation. This isn't traditionally covered in language training data, so I don't think techniques like LoRA/qLoRA would be effective. Can anyone confirm if fine-tuning the full model is more suitable for this and is still possible with SFTTrainer?
Also, I'm on a... | 2023-07-27T22:38:41 | https://www.reddit.com/r/LocalLLaMA/comments/15bftve/fine_tuning_llama2_for_music_melody_generation/ | SuperwhizAJ | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 15bftve | false | null | t3_15bftve | /r/LocalLLaMA/comments/15bftve/fine_tuning_llama2_for_music_melody_generation/ | false | false | self | 4 | null |
Anyone good a data manipulation? | 8 | I am currently looking through the alpaca\_cleaned dataset, there is an extremely large number (32k) without an input prompt, is this oversight or is it about keeping the memory usage low? I only ask as I am going though the first 10 entries and it seems that they all could use some extra clarification.
I will co... | 2023-07-27T22:36:20 | https://www.reddit.com/r/LocalLLaMA/comments/15bfrvd/anyone_good_a_data_manipulation/ | ScottishGPT | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 15bfrvd | false | null | t3_15bfrvd | /r/LocalLLaMA/comments/15bfrvd/anyone_good_a_data_manipulation/ | false | false | self | 8 | null |
Subsets and Splits
No community queries yet
The top public SQL queries from the community will appear here once available.