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 ⌀ |
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
PromptTools Playground: Open-source, self-hostable UI for LLM experimentation | 1 | 2023-07-31T21:02:59 | https://v.redd.it/xxy4ulxj7dfb1 | hegel-ai | v.redd.it | 1970-01-01T00:00:00 | 0 | {} | 15es02f | false | {'reddit_video': {'bitrate_kbps': 0, 'dash_url': 'https://v.redd.it/xxy4ulxj7dfb1/DASHPlaylist.mpd?a=1693529585%2CODRiNTJmNjJmZmU3MGI4NDZkNDJlOGEyNWY0NWNkYTQ0MmZmYTc4MjJmNDM4NDA4ODk5MDA1ZDNhNjIzYzM3Yw%3D%3D&v=1&f=sd', 'duration': 68, 'fallback_url': 'https://v.redd.it/xxy4ulxj7dfb1/DASH_1080.mp4?source=fallback', 'heig... | t3_15es02f | /r/LocalLLaMA/comments/15es02f/prompttools_playground_opensource_selfhostable_ui/ | false | false | default | 1 | {'enabled': False, 'images': [{'id': 'TVeif5JznupmeyrM1RSzI7oxj3mm54zQsBNe7gKHnnc', 'resolutions': [{'height': 67, 'url': 'https://external-preview.redd.it/RamjSowwUstX3yDT658gvCJEnje7bUeqNuliL0uMWx0.png?width=108&crop=smart&format=pjpg&auto=webp&s=270a6f890ba6a89a0b9b50391f7606e11256d061', 'width': 108}, {'height': 13... | |
Recommended version? | 5 | I'm lost with all the new TheBloke versions coming out hoursly, or even minutely. If you had to choose, which one would be best for:
1. A Windows 10 system with a 3080Ti , 32GB system RAM and a Ryzen 9 7900X
2. General instructions (how do I...) and writing
3. Preferably uncensored, but that's mainly because I loooath... | 2023-07-31T20:40:17 | https://www.reddit.com/r/LocalLLaMA/comments/15erevo/recommended_version/ | 0260n4s | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 15erevo | false | null | t3_15erevo | /r/LocalLLaMA/comments/15erevo/recommended_version/ | false | false | self | 5 | null |
How can I evaluate the quality of a custom chatbot? | 6 | Hey all, can you recommend some resources or a general approach for benchmarking/evaluating the quality of responses that a chatbot produces? Some factors I'm thinking about that contribute to the subjective quality of my chatbot's responses:
\* Data provided in the prompt
\* Data used to finetune
\* The prompt te... | 2023-07-31T20:11:38 | https://www.reddit.com/r/LocalLLaMA/comments/15eqntk/how_can_i_evaluate_the_quality_of_a_custom_chatbot/ | dondochaka | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 15eqntk | false | null | t3_15eqntk | /r/LocalLLaMA/comments/15eqntk/how_can_i_evaluate_the_quality_of_a_custom_chatbot/ | false | false | self | 6 | null |
Getting about .5-1 t/s with a RTX3090 | 2 | So after WSL2 blew up from a Windows 11 update, I did a clean install. Previously I could reliably get something like 20-30t/s from 30b sized models. Now I'm struggling to get even 2 t/s. GGML models get slightly better speeds but gptq and hf models are pretty slow. I'm baffled and have tried many combinations of CUDA ... | 2023-07-31T20:07:35 | https://www.reddit.com/r/LocalLLaMA/comments/15eqk3n/getting_about_51_ts_with_a_rtx3090/ | jfranzen8705 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 15eqk3n | false | null | t3_15eqk3n | /r/LocalLLaMA/comments/15eqk3n/getting_about_51_ts_with_a_rtx3090/ | false | false | 2 | null | |
Has anyone had any luck with any models using private GPT? | 0 | Pretty new to this topic, anyone had any luck with any Llm models for privategpt? | 2023-07-31T19:36:25 | https://www.reddit.com/r/LocalLLaMA/comments/15epqfn/has_anyone_had_any_luck_with_any_models_using/ | lsimcoates | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 15epqfn | false | null | t3_15epqfn | /r/LocalLLaMA/comments/15epqfn/has_anyone_had_any_luck_with_any_models_using/ | false | false | self | 0 | null |
Oobabooga "chat saver" plugin for Chrome. | 1 | 2023-07-31T19:26:04 | https://chrome.google.com/webstore/detail/chat-saver/onakaaoddpdfopdjagagepfkhpehfbae | zapeggo | chrome.google.com | 1970-01-01T00:00:00 | 0 | {} | 15epgnf | false | null | t3_15epgnf | /r/LocalLLaMA/comments/15epgnf/oobabooga_chat_saver_plugin_for_chrome/ | false | false | 1 | {'enabled': False, 'images': [{'id': 'kUUo21PMU-yaTeFGS1fJK0A3xdftMCwtgvOgLDAEy18', 'resolutions': [{'height': 108, 'url': 'https://external-preview.redd.it/Y7G61u3whacQwSzCbv6PWKSEM3Drcs4u74OcI7hwCuo.jpg?width=108&crop=smart&auto=webp&s=74827950d19c2f15ca8efff5ccd1f17602831ad7', 'width': 108}], 'source': {'height': 12... | ||
Accurate answers after fine tuning fastchat | 1 | I fine tuning fast chat using peft-lora on a custom question answer based dataset. It generates nice outputs after fine tuning, pretty relevant. However it doesn't give accurate output for exact questions. Any idea about how to fix it? | 2023-07-31T19:05:57 | https://www.reddit.com/r/LocalLLaMA/comments/15eoxer/accurate_answers_after_fine_tuning_fastchat/ | mathageche | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 15eoxer | false | null | t3_15eoxer | /r/LocalLLaMA/comments/15eoxer/accurate_answers_after_fine_tuning_fastchat/ | false | false | default | 1 | null |
Idea: Alternating token generation from a big and small model? | 14 | I was thinking... could we use a guidance style system to generate alternating tokens from a big and a small model? I suspect the large model's next-word (or words) would help steer the smaller model by example, so it would complete the next word (or handful of words) then kick back to the larger model for another word... | 2023-07-31T19:00:26 | https://www.reddit.com/r/LocalLLaMA/comments/15eornw/idea_alternating_token_generation_from_a_big_and/ | teachersecret | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 15eornw | false | null | t3_15eornw | /r/LocalLLaMA/comments/15eornw/idea_alternating_token_generation_from_a_big_and/ | false | false | self | 14 | null |
PLEASE HELP ME! What does this error mean and how to solve it? | 1 | Hi,
For the past week, I've been facing this error on the Oobabooga webui when I try to load an 8-bit quantazed versions of some TheBlock's models. I am aware that Exllama only supports 4-bit and not 8-bit quantization, so I try to load the model using AutoGPTQ. However, when I do that I get this error message as show... | 2023-07-31T19:00:24 | https://www.reddit.com/r/LocalLLaMA/comments/15eormu/please_help_me_what_does_this_error_mean_and_how/ | Iory1998 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 15eormu | false | null | t3_15eormu | /r/LocalLLaMA/comments/15eormu/please_help_me_what_does_this_error_mean_and_how/ | false | false | 1 | null | |
Alignment Broke Llama-2’s Brain | 0 | Context: I asked it to make a weather script. | 2023-07-31T18:36:30 | Difficult-Yam-1347 | i.redd.it | 1970-01-01T00:00:00 | 0 | {} | 15eo5kt | false | null | t3_15eo5kt | /r/LocalLLaMA/comments/15eo5kt/alignment_broke_llama2s_brain/ | false | false | 0 | {'enabled': True, 'images': [{'id': 'n3DRgFb2_UvqInT-gpUrfENhfo5uP1WDaIq1SK1rFcA', 'resolutions': [{'height': 191, 'url': 'https://preview.redd.it/hcutgqthhcfb1.jpg?width=108&crop=smart&auto=webp&s=f59bd30b7347cb744b1c23907b8833a5130f0088', 'width': 108}, {'height': 382, 'url': 'https://preview.redd.it/hcutgqthhcfb1.jp... | ||
PC configuration to run a llama2 70B | 25 | Greetings,
I'm trying to figure out what might suit my case without having to sell my kidneys.
I would like to be able to run llama2 and future similar models locally on the gpu, but I am not really sure about the hardware requirements.
I had been thinking about an RTX A6000, but reading around it seems like it may ... | 2023-07-31T18:36:09 | https://www.reddit.com/r/LocalLLaMA/comments/15eo58x/pc_configuration_to_run_a_llama2_70b/ | SpatolaNellaRoccia | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 15eo58x | false | null | t3_15eo58x | /r/LocalLLaMA/comments/15eo58x/pc_configuration_to_run_a_llama2_70b/ | false | false | self | 25 | null |
Does anyone know how to make a variant of LLaMA 2? | 8 | I want to make a personal project of a chatbot based on LLaMA 2, like Vicuna, Beluga, etc.
Just searching online I can't find an exact way of how to do it, hence my question, does anyone know how to do it? Or is there a tutorial on how to do it? | 2023-07-31T18:12:18 | https://www.reddit.com/r/LocalLLaMA/comments/15enjgy/does_anyone_know_how_to_make_a_variant_of_llama_2/ | danielbrdz | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 15enjgy | false | null | t3_15enjgy | /r/LocalLLaMA/comments/15enjgy/does_anyone_know_how_to_make_a_variant_of_llama_2/ | false | false | self | 8 | null |
Running LLMs locally on Android | 1 | [removed] | 2023-07-31T18:04:33 | https://www.reddit.com/r/LocalLLaMA/comments/15encah/running_llms_locally_on_android/ | atezan | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 15encah | false | null | t3_15encah | /r/LocalLLaMA/comments/15encah/running_llms_locally_on_android/ | false | false | self | 1 | null |
4090 GPU paired with which CPU? | 4 | Hey,
Currently building a custom PC for the 4090. I will mainly be using it for Stable Diffusion but would like to dive into the world of AI and potentially some deepfake.
I am currently thinking of just getting the AMD 7800X3D.
Do you think this would be okay to run most things (I know a bit vague. GPT4All would be... | 2023-07-31T17:53:58 | https://www.reddit.com/r/LocalLLaMA/comments/15en23m/4090_gpu_paired_with_which_cpu/ | Visible_Guest_2986 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 15en23m | false | null | t3_15en23m | /r/LocalLLaMA/comments/15en23m/4090_gpu_paired_with_which_cpu/ | false | false | self | 4 | null |
Question - Is PrivateGPT or LocalGPT .db .pkl files on the way to building a model that would be sharable? I'm feeding documentation for a new code syntax. | 1 | [removed] | 2023-07-31T17:52:56 | https://www.reddit.com/r/LocalLLaMA/comments/15en14f/question_is_privategpt_or_localgpt_db_pkl_files/ | Iam_a_honeybadger | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 15en14f | false | null | t3_15en14f | /r/LocalLLaMA/comments/15en14f/question_is_privategpt_or_localgpt_db_pkl_files/ | false | false | default | 1 | null |
LLM ballparks | 3 | I'm just getting started with language models but the technology shift has been pretty exciting.
My experience with LLMs has so far been: Using GPT-3.5 and GPT-4.0 for light assistance with work, as well as help with creative writing and writing analysis, and solo roleplay/gameplay experimentation stuff; and running a... | 2023-07-31T17:06:36 | https://www.reddit.com/r/LocalLLaMA/comments/15eltml/llm_ballparks/ | NitroXanax | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 15eltml | false | null | t3_15eltml | /r/LocalLLaMA/comments/15eltml/llm_ballparks/ | false | false | self | 3 | null |
Need help loading local dataset for Qlora training | 1 | I'm trying to train my own qlora and am following a tutorial. The problem is that the tuorial uses a [huggingface dataset](https://huggingface.co/datasets/AlexanderDoria/novel17_test/tree/main), which does load properly for me, but if I try to load the same exact data locally, it fails:
orig_dataset = load_datase... | 2023-07-31T16:44:56 | https://www.reddit.com/r/LocalLLaMA/comments/15el9nn/need_help_loading_local_dataset_for_qlora_training/ | feldcot | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 15el9nn | false | null | t3_15el9nn | /r/LocalLLaMA/comments/15el9nn/need_help_loading_local_dataset_for_qlora_training/ | false | false | self | 1 | {'enabled': False, 'images': [{'id': 'Mxe46f_-BMRsLioYlhVeQB2lSHKxmvi8c_TVpwaypAM', 'resolutions': [{'height': 58, 'url': 'https://external-preview.redd.it/0QGKrCq74FL_ogxYqWxEqCPH4TywnTfoMQbHw6wvIUQ.jpg?width=108&crop=smart&auto=webp&s=342faeee6eeb90e47e572ff4ccc57331cee83ac6', 'width': 108}, {'height': 116, 'url': 'h... |
Vicuna 13b locked at 512 tokens | 1 | Using private Gpt I'm trying to use the vicuna13b model but whatever I do it is capped at 512 token, even when I specify in my requirements to increase this. For other models I can get this working.
I have heard good things about this model so wanted to give it a try, does anyone have any ides? | 2023-07-31T16:35:55 | https://www.reddit.com/r/LocalLLaMA/comments/15el1lt/vicuna_13b_locked_at_512_tokens/ | lsimcoates | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 15el1lt | false | null | t3_15el1lt | /r/LocalLLaMA/comments/15el1lt/vicuna_13b_locked_at_512_tokens/ | false | false | self | 1 | null |
If I want consistency through a long story, would Lora training be an effective way to get around the token limits? | 5 | If using oobabooga, would Lora training a model with the generated conversation thus far help the model keep context indefinitely? Or at the very least would it help it understand the overall "theme" better?
If so are there any good guides on training? | 2023-07-31T16:31:48 | https://www.reddit.com/r/LocalLLaMA/comments/15ekxwc/if_i_want_consistency_through_a_long_story_would/ | countrycruiser | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 15ekxwc | false | null | t3_15ekxwc | /r/LocalLLaMA/comments/15ekxwc/if_i_want_consistency_through_a_long_story_would/ | false | false | self | 5 | null |
Fine tune Wizard Vicuna 7B using domain specific dataset | 5 | I'm trying to fine tune the Wizard Vicuna 7B model using medical domain dataset. What is the best way to do so? And also what is the most efficient way to create a dataset for fine tuning this model since the dataset that I currently have is basically some txt files (not in instruction format)? | 2023-07-31T16:26:53 | https://www.reddit.com/r/LocalLLaMA/comments/15ektcg/fine_tune_wizard_vicuna_7b_using_domain_specific/ | FirstReporter4868 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 15ektcg | false | null | t3_15ektcg | /r/LocalLLaMA/comments/15ektcg/fine_tune_wizard_vicuna_7b_using_domain_specific/ | false | false | self | 5 | null |
2x a6000s but only 3.5 tokens/s with 7b-chat-hf. What am I doing wrong? | 40 | I have access to a brand new Dell workstation with 2 A6000s with 48gb v ram each. It has a Xeon processor and 128gb memory. A “decent” machine to say the least. I am trying to run the llama 7b-hf model via oobabooga but am only getting 7-8 tokens a second. I am just trying to run the base model. I am brand new to this... | 2023-07-31T16:17:48 | https://www.reddit.com/r/LocalLLaMA/comments/15ekkx4/2x_a6000s_but_only_35_tokenss_with_7bchathf_what/ | blind_trooper | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 15ekkx4 | false | null | t3_15ekkx4 | /r/LocalLLaMA/comments/15ekkx4/2x_a6000s_but_only_35_tokenss_with_7bchathf_what/ | false | false | self | 40 | null |
Best model for pentesting? | 1 | Does anyone know the best model for penetration testing purposes? Seems like a lot of them are unwilling or very hesitant to provide much if any information (commands, how-to’s, etc.) due to it being “unethical” or “illegal.” ChatGPT tends to somewhat provide information but only after lots of going back and forth. | 2023-07-31T15:58:57 | https://www.reddit.com/r/LocalLLaMA/comments/15ek2kh/best_model_for_pentesting/ | FrisbeeSunday | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 15ek2kh | false | null | t3_15ek2kh | /r/LocalLLaMA/comments/15ek2kh/best_model_for_pentesting/ | false | false | self | 1 | null |
Seeking Guidance on Building JSONL Dataset for Fine-Tuning LLaMA 2 Model on Product Mapping (sequence2sequence process ) | 3 | Hello r/LocalLLaMA Community,
I'm currently working on a project and am facing a challenge that I'm sure many of you might have tackled before. Any guidance or advice would be immensely appreciated.
**Project Background:**
The project involves handling product data, each product being characterized by its distinct ... | 2023-07-31T15:19:06 | https://www.reddit.com/r/LocalLLaMA/comments/15ej23k/seeking_guidance_on_building_jsonl_dataset_for/ | clichedwriterr | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 15ej23k | false | null | t3_15ej23k | /r/LocalLLaMA/comments/15ej23k/seeking_guidance_on_building_jsonl_dataset_for/ | false | false | self | 3 | null |
What's the best way for me to chat with old FOIA documents? | 3 | I'd like to chat with old Freedom of Information Act documents. They're PDF's, but they're all just pictures of text. Nothing was actually typed and saved as a PDF file cause we're talking about documents from the 1950's and 1960's. But maybe the A.i can still read this?
Anyway, I tried using Quivr to upload a FOIA pd... | 2023-07-31T14:51:11 | https://www.reddit.com/r/LocalLLaMA/comments/15eic85/whats_the_best_way_for_me_to_chat_with_old_foia/ | rondonjohnald | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 15eic85 | false | null | t3_15eic85 | /r/LocalLLaMA/comments/15eic85/whats_the_best_way_for_me_to_chat_with_old_foia/ | false | false | self | 3 | null |
KoboldCpp as a module (without web interface) | 6 | Here is an example script:
import sys
sys.path.insert(0, 'koboldcpp-1.36')
import koboldcpp
sys.path.pop(0)
koboldcpp.run_as_module = True
from argparse import Namespace
koboldcpp.args = Namespace(model=None, model_param='D:/koboldcpp/guanaco-65B.ggmlv3.q4_K_M.bin', port=5001... | 2023-07-31T14:48:00 | https://www.reddit.com/r/LocalLLaMA/comments/15ei920/koboldcpp_as_a_module_without_web_interface/ | SpecialNothingness | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 15ei920 | false | null | t3_15ei920 | /r/LocalLLaMA/comments/15ei920/koboldcpp_as_a_module_without_web_interface/ | false | false | self | 6 | null |
Non profit for training open source LLMs | 1 | [removed] | 2023-07-31T14:39:19 | https://www.reddit.com/r/LocalLLaMA/comments/15ei0q8/non_profit_for_training_open_source_llms/ | NessimBA | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 15ei0q8 | false | null | t3_15ei0q8 | /r/LocalLLaMA/comments/15ei0q8/non_profit_for_training_open_source_llms/ | false | false | self | 1 | null |
Clarification on using AI-generated data for commercial model fine-tuning | 13 | I'm looking to build a clearer picture of which fine tuning datasets can and cannot be used for fine tuning models which will be deployed commercially. Specifically, I'm interested in understanding the consensus on using datasets containing samples generated by OpenAI's GPT models.
I've seen conflicting perspectives ... | 2023-07-31T14:26:59 | https://www.reddit.com/r/LocalLLaMA/comments/15ehp5d/clarification_on_using_aigenerated_data_for/ | nuusain | self.LocalLLaMA | 2023-07-31T16:52:38 | 0 | {} | 15ehp5d | false | null | t3_15ehp5d | /r/LocalLLaMA/comments/15ehp5d/clarification_on_using_aigenerated_data_for/ | false | false | self | 13 | {'enabled': False, 'images': [{'id': '_rEX1xvwdv17x6NFAWQpYFNONQ0BKA5Qw0Eo0JX0zWU', 'resolutions': [{'height': 58, 'url': 'https://external-preview.redd.it/PUH10BjM5sFuvroA3mzy6AwPeP3T-kvtFLWUoE6Dho8.jpg?width=108&crop=smart&auto=webp&s=17279fa911dbea17f2a87e187f47ad903120ba87', 'width': 108}, {'height': 116, 'url': 'h... |
GGML models repeating themselves on Webui | 8 | So pleased that I found I can run 60b+ GGML models on my CPU, albeit slowly, but I'm finding that they are repeating the same next over and over with only minor variations. I've played around with the repeation penalty, maxing it out, as well as increasing temperature and top p. Is there anything I can do to prevent ... | 2023-07-31T13:23:16 | https://www.reddit.com/r/LocalLLaMA/comments/15eg47j/ggml_models_repeating_themselves_on_webui/ | Mediocre_Tourist401 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 15eg47j | false | null | t3_15eg47j | /r/LocalLLaMA/comments/15eg47j/ggml_models_repeating_themselves_on_webui/ | false | false | self | 8 | null |
Plausible to Train Small Models on MacBook Pro M2 Max? | 2 | To the best of my understanding it's more cost effective to build a machine w/ Nvidia cards, I'd like to be able to train small (like Flacon 7b) models, and I'm buying a new MacBook anyway.
If I get an M2 Max with 12‑core CPU, 30‑core GPU, 16‑core Neural Engine and 64GB unified memory, is it plausible I would be be ab... | 2023-07-31T13:19:04 | https://www.reddit.com/r/LocalLLaMA/comments/15eg0j5/plausible_to_train_small_models_on_macbook_pro_m2/ | Mbando | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 15eg0j5 | false | null | t3_15eg0j5 | /r/LocalLLaMA/comments/15eg0j5/plausible_to_train_small_models_on_macbook_pro_m2/ | false | false | self | 2 | null |
How to test if 1 GPU is enough for concurrency when trying LLAMA | 1 | Hello all, I'm back again with a question, can I ask how do you test if 1 GPU is enough to do the concurrency in LLAMA models? I used oobabooga installer.
Thank you | 2023-07-31T12:46:18 | https://www.reddit.com/r/LocalLLaMA/comments/15ef8ks/how_to_test_if_1_gpu_is_enough_for_concurrency/ | Cultural-Pizza-1916 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 15ef8ks | false | null | t3_15ef8ks | /r/LocalLLaMA/comments/15ef8ks/how_to_test_if_1_gpu_is_enough_for_concurrency/ | false | false | self | 1 | null |
How to overcome the issues of the limit of ~4,000 tokens per input, when dealing with documents summarization? | 38 | As we all knows, llama 2 is quite impressive, and performers well tasks related to summarization.
But how would you deal with summarization of a long document (let's say a book for example)? Is the only solution to make subsets of the text and iteratively feed it? Obtaining summary of summary until the results is ok? ... | 2023-07-31T12:09:33 | https://www.reddit.com/r/LocalLLaMA/comments/15eef2s/how_to_overcome_the_issues_of_the_limit_of_4000/ | Sad-Vegetable6767 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 15eef2s | false | null | t3_15eef2s | /r/LocalLLaMA/comments/15eef2s/how_to_overcome_the_issues_of_the_limit_of_4000/ | false | false | self | 38 | null |
Any other smaller LLM (smaLLM? :D) users here? | 106 | I'll introduce myself, because ... idk.
Hi, I'm Sol!
I've been working with LLMs since they became popular thanks to ChatGPT. My first attempts of running LLMs locally was by using transformers and running small GPTs etc, with not-completely-useless results.
Eventually I migrated to gpt4all, but now I'm using llam... | 2023-07-31T11:19:19 | https://www.reddit.com/r/LocalLLaMA/comments/15edcz2/any_other_smaller_llm_smallm_d_users_here/ | Solstice_Projekt | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 15edcz2 | false | null | t3_15edcz2 | /r/LocalLLaMA/comments/15edcz2/any_other_smaller_llm_smallm_d_users_here/ | false | false | self | 106 | null |
LLaMA 2 models tuned for NLP? | 4 | So I am very, VERY impressed with llama 2. It understand so many languages and can ignore irrelevant information easily. I would like it to classify, summarize or extract some data from text. But here lies a problem:
- Base (at least 7B) model is too stupid to answer instructions reliably
- Chat model answers instruc... | 2023-07-31T10:59:18 | https://www.reddit.com/r/LocalLLaMA/comments/15ecybr/llama_2_models_tuned_for_nlp/ | RicoElectrico | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 15ecybr | false | null | t3_15ecybr | /r/LocalLLaMA/comments/15ecybr/llama_2_models_tuned_for_nlp/ | false | false | self | 4 | null |
Adding keywords related to topic to LLM context improves performance, here's my prompt to generate them and some keywords for being a machine-learning engineer. | 8 | Whenever I am working with any LLM (typically GPT-4) I generate keywords relevant to my context. I find it has better results and I recommend the same. First I generate them for the topic I'm interested in:
>In the next prompt, Use the mantle of a ‘context generator’ related to the topic of: “Python Development for M... | 2023-07-31T10:43:38 | https://www.reddit.com/r/LocalLLaMA/comments/15ecn67/adding_keywords_related_to_topic_to_llm_context/ | hanjoyoutaku | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 15ecn67 | false | null | t3_15ecn67 | /r/LocalLLaMA/comments/15ecn67/adding_keywords_related_to_topic_to_llm_context/ | false | false | self | 8 | null |
The possibilities of local language models are truly endless | 1 | [removed] | 2023-07-31T10:19:44 | yungfishstick | i.redd.it | 1970-01-01T00:00:00 | 0 | {} | 15ec6f7 | false | null | t3_15ec6f7 | /r/LocalLLaMA/comments/15ec6f7/the_possibilities_of_local_language_models_are/ | false | false | 1 | {'enabled': True, 'images': [{'id': 'bshZ_t8jjnAS2M04SXSZwKTbNSdjOxKC5_7I_iHuf4o', 'resolutions': [{'height': 87, 'url': 'https://preview.redd.it/tgpode6v0afb1.jpg?width=108&crop=smart&auto=webp&s=d7092ce7e0c03f6d1f34124d84042eb60b1694ee', 'width': 108}, {'height': 174, 'url': 'https://preview.redd.it/tgpode6v0afb1.jpg... | ||
Online LLM comparison Tool | 2 | Hello everyone,
​
how is the website called where I can run multiple LLMs with one prompt and compare the answers.
​
A Tool with contains Falcon & Llama 2 would be for my needs.
​
Thank yall! | 2023-07-31T09:31:17 | https://www.reddit.com/r/LocalLLaMA/comments/15eba3p/online_llm_comparison_tool/ | jnk_str | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 15eba3p | false | null | t3_15eba3p | /r/LocalLLaMA/comments/15eba3p/online_llm_comparison_tool/ | false | false | self | 2 | null |
What does k-quant mean? | 15 | I am new to this AI stuff but I successfully managed to run GGML models on my computer with cuBLAS. But I don't understand why some models have several versions of varying size with weird labels like q2\_K, q3\_K\_S, q3\_K\_M, ect.
​
Can someone explain why I should care and what k-quand method I should pick... | 2023-07-31T09:25:10 | https://www.reddit.com/r/LocalLLaMA/comments/15eb67i/what_does_kquant_mean/ | Explorer-Necessary | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 15eb67i | false | null | t3_15eb67i | /r/LocalLLaMA/comments/15eb67i/what_does_kquant_mean/ | false | false | self | 15 | null |
What is the best way to create a Free & light knowledge-base specific LLM chatbot ? | 8 | I want to do something like this but haven't found a free and cheap solution yet. Almost everything uses the OpenAI API key and running OpenLLM locally requires high-spec hardware. So far what I've done is use consine similarity to get the information asked in the chat, then throw that text to a free chatbot API (which... | 2023-07-31T08:46:29 | https://www.reddit.com/r/LocalLLaMA/comments/15eahhi/what_is_the_best_way_to_create_a_free_light/ | balianone | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 15eahhi | false | null | t3_15eahhi | /r/LocalLLaMA/comments/15eahhi/what_is_the_best_way_to_create_a_free_light/ | false | false | self | 8 | null |
Extremely repetitive/deterministic content over multiple generations | 14 | This happens with any LlaMa model (e.g. Vicuna), although it seems to happen even more with LlaMa-2. Right now my present is Asterism on Oobabooga and I'm using the Llama-2 Chat GPTQ.
Just look at the two different generations (clicking on Regenerate):
​
https://preview.redd.it/spk9xkzeh9fb1.png?width=919&for... | 2023-07-31T08:33:36 | https://www.reddit.com/r/LocalLLaMA/comments/15ea9jl/extremely_repetitivedeterministic_content_over/ | CulturedNiichan | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 15ea9jl | false | null | t3_15ea9jl | /r/LocalLLaMA/comments/15ea9jl/extremely_repetitivedeterministic_content_over/ | false | false | 14 | null | |
Can I create my own LLM API instead of using OpenaiAPI? | 20 | Hi.
I am not a developer, but I've installed WizardLM 13b GPTQ, and it works fine.
Can I create an API somehow for this and connect it to ex. Obsidian, Joplin, and for any other softwares? Is this possible? If yes, do you have a recommendation on how to, a guide, a link?
Thank you so much. | 2023-07-31T08:23:57 | https://www.reddit.com/r/LocalLLaMA/comments/15ea38z/can_i_create_my_own_llm_api_instead_of_using/ | AdamsText | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 15ea38z | false | null | t3_15ea38z | /r/LocalLLaMA/comments/15ea38z/can_i_create_my_own_llm_api_instead_of_using/ | false | false | self | 20 | null |
Exploring a Non-Profit, Community-Led Approach to Open Source AI | 1 | [removed] | 2023-07-31T08:04:52 | https://www.reddit.com/r/LocalLLaMA/comments/15e9qsw/exploring_a_nonprofit_communityled_approach_to/ | NessimBA | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 15e9qsw | false | null | t3_15e9qsw | /r/LocalLLaMA/comments/15e9qsw/exploring_a_nonprofit_communityled_approach_to/ | false | false | self | 1 | null |
Using Open-Source LLM Models vs. Expensive OpenAI APIs: A Logical Choice for Consumer Apps? | 33 | I'm currently developing an interpreter app for mobile that generates short comments and audio based on given single prompt. The goal is to keep it simple, with one-time generation (no-chatting for now) and a monthly limit for users. I've been personally using opensource LLM's for good amount of time (coding, instructi... | 2023-07-31T07:23:27 | https://www.reddit.com/r/LocalLLaMA/comments/15e915q/using_opensource_llm_models_vs_expensive_openai/ | sarimsak13 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 15e915q | false | null | t3_15e915q | /r/LocalLLaMA/comments/15e915q/using_opensource_llm_models_vs_expensive_openai/ | false | false | self | 33 | null |
Create GraphDB using LLMs | 2 | Hey everyone, I was wondering, if anyone has ventured into creating graphDB from raw unstructured text corpus using LLMs, or had any experience with this.
I came across this repo : [https://github.com/varunshenoy/GraphGPT](https://github.com/varunshenoy/GraphGPT), which uses gpt3.5/4 to generate graphs. Anything tha... | 2023-07-31T07:08:00 | https://www.reddit.com/r/LocalLLaMA/comments/15e8rx3/create_graphdb_using_llms/ | Raise_Fickle | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 15e8rx3 | false | null | t3_15e8rx3 | /r/LocalLLaMA/comments/15e8rx3/create_graphdb_using_llms/ | false | false | self | 2 | {'enabled': False, 'images': [{'id': 'e6ayVEN750ITdNyz3BdBwUizxSoSDZy71MD-qSJl8-I', 'resolutions': [{'height': 54, 'url': 'https://external-preview.redd.it/3MPmCm1ocIvLLCwfs0wPeebggyiN4fFfGIlLEVGOxug.jpg?width=108&crop=smart&auto=webp&s=537be5c0592d1c1ea21444e34fb386fb9f51095b', 'width': 108}, {'height': 108, 'url': 'h... |
Best M1 MacOS app for running models locally? | 14 | Looking for a UI Mac app that can run LLaMA/2 models locally. I remember seeing what looked like a solid one on GitHub but I had my intel Mac at the time and I believe it’s only compatible on Apple silicon. | 2023-07-31T06:23:09 | https://www.reddit.com/r/LocalLLaMA/comments/15e80g7/best_m1_macos_app_for_running_models_locally/ | sardoa11 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 15e80g7 | false | null | t3_15e80g7 | /r/LocalLLaMA/comments/15e80g7/best_m1_macos_app_for_running_models_locally/ | false | false | self | 14 | null |
Running LLama in cloud | 1 | My friend works in consulting. ChatGPT could've helped him immensely since his work mostly includes researching, creating PPTs but it's banned internally due to secretive nature of his data.
So, I'm thinking of hosting LLama for him on cloud. I was thinking of creating a script which you can just run in your serv... | 2023-07-31T06:10:22 | https://www.reddit.com/r/LocalLLaMA/comments/15e7seu/running_llama_in_cloud/ | middlenameishardwork | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 15e7seu | false | null | t3_15e7seu | /r/LocalLLaMA/comments/15e7seu/running_llama_in_cloud/ | false | false | self | 1 | null |
Finetuning Llama model for code analysis? | 1 | [removed] | 2023-07-31T05:47:56 | https://www.reddit.com/r/LocalLLaMA/comments/15e7ecc/finetuning_llama_model_for_code_analysis/ | CodeIsTrash | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 15e7ecc | false | null | t3_15e7ecc | /r/LocalLLaMA/comments/15e7ecc/finetuning_llama_model_for_code_analysis/ | false | false | default | 1 | null |
How do we fine-tune Llama 2 model for Custom Intent Classification? | 1 | [removed] | 2023-07-31T05:41:19 | https://www.reddit.com/r/LocalLLaMA/comments/15e7a5g/how_do_we_finetune_llama_2_model_for_custom/ | Interesting_Low_9766 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 15e7a5g | false | null | t3_15e7a5g | /r/LocalLLaMA/comments/15e7a5g/how_do_we_finetune_llama_2_model_for_custom/ | false | false | self | 1 | null |
Variants of LLaMa or similar that can "see" and describe images? | 31 | After playing around with Bard a bit, I was quite impressed by its ability to let you upload images and have Bard talk about those images with a great degree of nuance. What's the current best in class among open source models, which still maintain the raw horsepower at general language tasks / chatting that models lik... | 2023-07-31T04:49:50 | https://www.reddit.com/r/LocalLLaMA/comments/15e6ed7/variants_of_llama_or_similar_that_can_see_and/ | ascendant23 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 15e6ed7 | false | null | t3_15e6ed7 | /r/LocalLLaMA/comments/15e6ed7/variants_of_llama_or_similar_that_can_see_and/ | false | false | self | 31 | null |
GitHub - Alpha-VLLM/LLaMA2-Accessory: An Open-source Toolkit for LLM Development | 10 | 2023-07-31T04:47:06 | https://github.com/Alpha-VLLM/LLaMA2-Accessory | ninjasaid13 | github.com | 1970-01-01T00:00:00 | 0 | {} | 15e6cl2 | false | null | t3_15e6cl2 | /r/LocalLLaMA/comments/15e6cl2/github_alphavllmllama2accessory_an_opensource/ | false | false | 10 | {'enabled': False, 'images': [{'id': 'uM8Hr3z9NcRtCYH991oK-J-LYQ2zddLwBbo3P4nQi-A', 'resolutions': [{'height': 54, 'url': 'https://external-preview.redd.it/5ncE2ywEBOmoEUtNULhJcEU_wmvSSok1g5GNRrD6fSc.jpg?width=108&crop=smart&auto=webp&s=6541c0d909e84110c6c725cfe9a7af0c766a1a3e', 'width': 108}, {'height': 108, 'url': 'h... | ||
New trained storytelling LoRA returns really interesting results. | 33 | Hello everyone.
Several weeks ago, I had posted about training my own storytelling LoRA with different structure and it returned funny results.
Just now, I've finished another LoRA, with 30 MB of training raw data. I've used **conceptofmind/LLongMA-2-13b-16k** as training basis. Loaded it in 8-bit mode and trained fo... | 2023-07-31T04:45:38 | https://www.reddit.com/r/LocalLLaMA/comments/15e6bmm/new_trained_storytelling_lora_returns_really/ | DaniyarQQQ | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 15e6bmm | false | null | t3_15e6bmm | /r/LocalLLaMA/comments/15e6bmm/new_trained_storytelling_lora_returns_really/ | false | false | self | 33 | null |
How to determine the best number of inference tokens after fine-tuning llama2? | 1 | After my fine-tuning of llama2-13b-chat with 80,000 instructions, I find my new llama-2-13b-chat likes to say a lot of things when I ask it a simple question.
If I set the number of tokens == 100, it can be usually interrupted at the exactly position of 100 tokens when it chat with me. But I do not know if it tends ... | 2023-07-31T03:28:49 | https://www.reddit.com/r/LocalLLaMA/comments/15e4x6b/how_to_determine_the_best_number_of_inference/ | badage | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 15e4x6b | false | null | t3_15e4x6b | /r/LocalLLaMA/comments/15e4x6b/how_to_determine_the_best_number_of_inference/ | false | false | self | 1 | null |
Got a second GPU, what do I need to know about getting them to work together and any other suggestions? | 1 | [removed] | 2023-07-31T03:15:20 | https://www.reddit.com/r/LocalLLaMA/comments/15e4o6s/got_a_second_gpu_what_do_i_need_to_know_about/ | Virtamancer | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 15e4o6s | false | null | t3_15e4o6s | /r/LocalLLaMA/comments/15e4o6s/got_a_second_gpu_what_do_i_need_to_know_about/ | false | false | self | 1 | null |
LLM API streaming remote | 3 | I have a project with the new Llama2 and I have a custom frontend that my partner is building and they want the text generation to stream directly to the client browser without the delay. So far, I have used Langchain, oobabooga, FastAPI, and other smaller repos to generate the text and send it to port directly but i... | 2023-07-31T02:08:52 | https://www.reddit.com/r/LocalLLaMA/comments/15e3d5o/llm_api_streaming_remote/ | muckitymuck | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 15e3d5o | false | null | t3_15e3d5o | /r/LocalLLaMA/comments/15e3d5o/llm_api_streaming_remote/ | false | false | self | 3 | null |
Computer specs CPU-ONLY to run Llama-2-70B-GGML | 1 | Can AMD Epyc run it? | 2023-07-31T00:32:36 | https://www.reddit.com/r/LocalLLaMA/comments/15e1cgi/computer_specs_cpuonly_to_run_llama270bggml/ | grigio | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 15e1cgi | false | null | t3_15e1cgi | /r/LocalLLaMA/comments/15e1cgi/computer_specs_cpuonly_to_run_llama270bggml/ | false | false | self | 1 | null |
How many prompts can local LLaMa-2 handle on a M1 Macbook simultaneously? | 3 | Trying to figure out how to basically create an API (like OpenAI) that can respond to multiple prompts at the same time.
I tried executing multiple on command line, but all of them hang when running more than one.
./main -m ./models/llama-2-7b-chat.ggmlv3.q8_0.bin -n 1024 -p "<prompt>"
​ | 2023-07-31T00:18:24 | https://www.reddit.com/r/LocalLLaMA/comments/15e11o0/how_many_prompts_can_local_llama2_handle_on_a_m1/ | advisa | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 15e11o0 | false | null | t3_15e11o0 | /r/LocalLLaMA/comments/15e11o0/how_many_prompts_can_local_llama2_handle_on_a_m1/ | false | false | self | 3 | null |
Need guidance fine-tuning LLAMA-2 | 28 | Hi all!
This is my first time working with LLMs and I am planning on fine-tuning LLAMA 2 on an extensive bibliography of a philosopher. To that end, I have extracted large quantities of text and stored them in a pandas dataframe. Rows are books and columns are title and body of text.
I am now looking into fine-tuning... | 2023-07-30T23:53:57 | https://www.reddit.com/r/LocalLLaMA/comments/15e0hx0/need_guidance_finetuning_llama2/ | Por-Tutatis | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 15e0hx0 | false | null | t3_15e0hx0 | /r/LocalLLaMA/comments/15e0hx0/need_guidance_finetuning_llama2/ | false | false | self | 28 | null |
Problems with llama models getting 'stuck'. | 2 | Hi,
I'm having trouble with the models getting stuck in the middle of text generation. It doesn't crash or stop, but rather takes a very long pause and then continues like nothing happened. If I am using the 70B model on my cpu, this pause can be for twenty minutes. Is there something I am doing wrong or something ... | 2023-07-30T23:47:29 | https://www.reddit.com/r/LocalLLaMA/comments/15e0cvt/problems_with_llama_models_getting_stuck/ | Red_Redditor_Reddit | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 15e0cvt | false | null | t3_15e0cvt | /r/LocalLLaMA/comments/15e0cvt/problems_with_llama_models_getting_stuck/ | false | false | self | 2 | null |
does oobabooga-windows support llama 2? Or is an update required? | 1 | For reference it took me over a week to get the installers properly working and this was 2-3 months ago (I havent updated it or touch any of the install scripts out of fear it would somehow break my original install)
However I've seen the recent release with llama 2 and want to test it out.
Is it easy to update oobab... | 2023-07-30T23:36:26 | https://www.reddit.com/r/LocalLLaMA/comments/15e0421/does_oobaboogawindows_support_llama_2_or_is_an/ | RoyalCities | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 15e0421 | false | null | t3_15e0421 | /r/LocalLLaMA/comments/15e0421/does_oobaboogawindows_support_llama_2_or_is_an/ | false | false | self | 1 | null |
How long would it take for Local LLMs to catch up with gpt-4? Few or several years? | 194 | Unless there's a big breakthrough in LLM model architecture and or consumer hardware, it sounds like it would be very difficult for local LLMs to catch up with gpt-4.
According to [leaked information about GPT-4 architecture, datasets, costs](https://the-decoder.com/gpt-4-architecture-datasets-costs-and-more-leaked/),... | 2023-07-30T22:14:14 | https://www.reddit.com/r/LocalLLaMA/comments/15dy75o/how_long_would_it_take_for_local_llms_to_catch_up/ | jl303 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 15dy75o | false | null | t3_15dy75o | /r/LocalLLaMA/comments/15dy75o/how_long_would_it_take_for_local_llms_to_catch_up/ | false | false | self | 194 | {'enabled': False, 'images': [{'id': 'y-gnN5eXSJbM_w4V7MFNRnsV0zLNgW29jexasYfiSF8', 'resolutions': [{'height': 60, 'url': 'https://external-preview.redd.it/R_jSGuxJFUWYMWl5tUlkHT9p7fvcbwdJI7DlycZa0fI.jpg?width=108&crop=smart&auto=webp&s=227d2c8a109e1eb11330647295127703bb2cc674', 'width': 108}, {'height': 121, 'url': 'h... |
Is there anyway to add classifier free guidance to inference-optimized libraries like ctranslate/vllm? | 8 | I've been experimenting quite a bit with classifier free guidance and found it to be super useful when generating text. There's a huggingface [implementation](https://github.com/huggingface/transformers/issues/24536) that can be easily added to your HF model and you can generate texts pretty easily. The only problem is... | 2023-07-30T21:33:47 | https://www.reddit.com/r/LocalLLaMA/comments/15dx716/is_there_anyway_to_add_classifier_free_guidance/ | Ok_Coyote_8904 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 15dx716 | false | null | t3_15dx716 | /r/LocalLLaMA/comments/15dx716/is_there_anyway_to_add_classifier_free_guidance/ | false | false | self | 8 | {'enabled': False, 'images': [{'id': 'NlR-Br6fGYKIfU9IPAIUkt0q3Nlyo4exb70MySsniqU', 'resolutions': [{'height': 54, 'url': 'https://external-preview.redd.it/NjVtlNBVVhtKFj4TvBhXEVK-xtO6qB0KsuxtUooQh1M.jpg?width=108&crop=smart&auto=webp&s=18b080e6d9d63990657d8b98b6bb4790b2798819', 'width': 108}, {'height': 108, 'url': 'h... |
CPU, GPU or RAM? | 10 | What's the most important for running models locally?
I'm going to build a PC with a Ryzen 5 5600 CPU, a 6800 XT GPU and 32GB ram at 3600MHz (CL16). What kind of performance/capacities can I expect?
I can slowly run a 7b model on a much less powerful CPU, so I guess it should be much better? | 2023-07-30T21:20:08 | https://www.reddit.com/r/LocalLLaMA/comments/15dwumk/cpu_gpu_or_ram/ | AloneInTheWhole | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 15dwumk | false | null | t3_15dwumk | /r/LocalLLaMA/comments/15dwumk/cpu_gpu_or_ram/ | false | false | self | 10 | null |
Running LLAMA | 4 | Hello all, I am newbie here sorry if my question is a bit of out topic.
I am a devops engineer trying to run LLAMA models, do we still need a huge computation resource to run a model? Or is it when only trying to training the model?
It seems only using CPU I can still the webUI + downloaded models (llama2 7b) and wh... | 2023-07-30T20:45:54 | https://www.reddit.com/r/LocalLLaMA/comments/15dvz7k/running_llama/ | Cultural-Pizza-1916 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 15dvz7k | false | null | t3_15dvz7k | /r/LocalLLaMA/comments/15dvz7k/running_llama/ | false | false | self | 4 | null |
Was trying to install SillyTavern on Mac and got the following error; What went wrong? | 1 | /Users/\*\*\*\*/Desktop/SillyTavern/start.sh
Installing Node Modules...
npm ERR! code ENOENT
npm ERR! syscall open
npm ERR! path /Users/\*\*\*\*/package.json
npm ERR! errno -2
npm ERR! enoent ENOENT: no such file or directory, open '/Users/\*\*\*\*/package.json'
npm ERR! enoent This is related to npm not being a... | 2023-07-30T20:13:01 | https://www.reddit.com/r/LocalLLaMA/comments/15dv52c/was_trying_to_install_sillytavern_on_mac_and_got/ | ChromeGhost | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 15dv52c | false | null | t3_15dv52c | /r/LocalLLaMA/comments/15dv52c/was_trying_to_install_sillytavern_on_mac_and_got/ | false | false | self | 1 | null |
Created a tutorial video on Llama2 | 1 | [removed] | 2023-07-30T20:06:28 | https://www.reddit.com/r/LocalLLaMA/comments/15duz22/created_a_tutorial_video_on_llama2/ | aianytime | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 15duz22 | false | null | t3_15duz22 | /r/LocalLLaMA/comments/15duz22/created_a_tutorial_video_on_llama2/ | false | false | self | 1 | {'enabled': False, 'images': [{'id': 'UYAqLaReU4yUmCx_aeof61i3La6yak_kILnLBNYNDls', 'resolutions': [{'height': 81, 'url': 'https://external-preview.redd.it/bFs21RSq2m_PlCVAgvTZlb7zEsGtZogibW9pEoQ_VFk.jpg?width=108&crop=smart&auto=webp&s=06c7ac2fecf9e253fea577633e61ba2847314082', 'width': 108}, {'height': 162, 'url': 'h... |
If you're using Bing Chat. You're getting the worst possible answer from a supposed Search Assistant. Here's why? | 0 | # Here is a critique and rating of the different AI responses, showcasing which model performed the worst and best in different categories:
|Model|Accuracy|Clarity|Conciseness|Helpfulness|
|:-|:-|:-|:-|:-|
|Bing Chat|3|4|5|2|
|Perplexity AI|5|5|3|5|
|Bard|4|5|4|4|
|Huggingface|5|5|4|5|
**Evaluation:**
* Accuracy: Pe... | 2023-07-30T20:02:32 | https://www.reddit.com/r/LocalLLaMA/comments/15duvig/if_youre_using_bing_chat_youre_getting_the_worst/ | FHSenpai | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 15duvig | false | null | t3_15duvig | /r/LocalLLaMA/comments/15duvig/if_youre_using_bing_chat_youre_getting_the_worst/ | false | false | self | 0 | {'enabled': False, 'images': [{'id': 'awB4VuC4eKtbxFOwQFJ1hWN6Z8X7muUKyF0MogqqgV8', 'resolutions': [{'height': 162, 'url': 'https://external-preview.redd.it/P7XaoiBio1X2LadUCWFvHhD2aoiSHLpJyEYzkylrhIo.jpg?width=108&crop=smart&auto=webp&s=6a6bd8118dc8fde43fe6208f41e1de57e603cff3', 'width': 108}], 'source': {'height': 23... |
Trying to run StableBeluga-7B locally on AMD WSL | 2 | Hello, I've been following the installation guide as far as possible but I think I've gotten as far as I can without help. So:
- The oobabooga start_wsl.bat runs and I can connect, it does mention "bitsandbytes was compiled without GPU support" but I believe this relies on CUDA and therefore doesn't affect me trying t... | 2023-07-30T18:20:57 | https://www.reddit.com/r/LocalLLaMA/comments/15dsfbr/trying_to_run_stablebeluga7b_locally_on_amd_wsl/ | Hexaflex | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 15dsfbr | false | null | t3_15dsfbr | /r/LocalLLaMA/comments/15dsfbr/trying_to_run_stablebeluga7b_locally_on_amd_wsl/ | false | false | self | 2 | null |
why is rotary embedding applied at each layer in roformer/llama? | 1 | [removed] | 2023-07-30T18:07:05 | https://www.reddit.com/r/LocalLLaMA/comments/15ds3l4/why_is_rotary_embedding_applied_at_each_layer_in/ | hx129 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 15ds3l4 | false | null | t3_15ds3l4 | /r/LocalLLaMA/comments/15ds3l4/why_is_rotary_embedding_applied_at_each_layer_in/ | false | false | self | 1 | null |
[QUESTION] What prompt(s) to get results like Vectara and Perplexity? | 2 | Hi all,
I'm curious what prompt is or prompts are needed to get results like Vectara and Perplexity.
Example Vectara: [https://asknews.demo.vectara.com/?query=Should+AI+be+regulated%3F&filter=&language=eng](https://asknews.demo.vectara.com/?query=Should+AI+be+regulated%3F&filter=&language=eng)
Here you see a questio... | 2023-07-30T17:46:49 | https://www.reddit.com/r/LocalLLaMA/comments/15drlx8/question_what_prompts_to_get_results_like_vectara/ | VividFee | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 15drlx8 | false | null | t3_15drlx8 | /r/LocalLLaMA/comments/15drlx8/question_what_prompts_to_get_results_like_vectara/ | false | false | self | 2 | null |
Is there anyway to transfer reinforcement learning to newer foundation models? Suppose you train llama2 to play minecraft and then llama3 comes out. Perhaps a MOE architecture? | 13 | I've been fascinated by people training LLMs to play games with reinforcement learning, but it seems like there is no good way to avoid starting over every time a better foundation model comes out.
Suppose the model has undergone multiple rounds of actor-critic training or PPO or RLHF, perhaps playing games like mine... | 2023-07-30T17:08:44 | https://www.reddit.com/r/LocalLLaMA/comments/15dqp5f/is_there_anyway_to_transfer_reinforcement/ | 30299578815310 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 15dqp5f | false | null | t3_15dqp5f | /r/LocalLLaMA/comments/15dqp5f/is_there_anyway_to_transfer_reinforcement/ | false | false | self | 13 | null |
What's the best way to use a ChatAI to generate Stories? (a good storywriter) | 6 | Hey everyone!
I used ChatGPT a lot to write interesting and long Stories.
I gave ChatGPT instructions and told it what to write. After some Sentences, ChatGPT had written a little part of the story. Then I gave it more instructions on how to continue this story. This way, I wrote a pretty cool Story with three Chap... | 2023-07-30T16:57:26 | https://www.reddit.com/r/LocalLLaMA/comments/15dqfiy/whats_the_best_way_to_use_a_chatai_to_generate/ | ChrisX930 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 15dqfiy | false | null | t3_15dqfiy | /r/LocalLLaMA/comments/15dqfiy/whats_the_best_way_to_use_a_chatai_to_generate/ | false | false | self | 6 | null |
are there any finetuned chat models in the works? | 6 | not looking for roleplay, more like a more versatile model. a 13b model thats a mix of airoboros gpt4 1.4.1, guanaco, and nous hermes 2 but in a chat model | 2023-07-30T16:02:05 | https://www.reddit.com/r/LocalLLaMA/comments/15dp4kx/are_there_any_finetuned_chat_models_in_the_works/ | happydadinau | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 15dp4kx | false | null | t3_15dp4kx | /r/LocalLLaMA/comments/15dp4kx/are_there_any_finetuned_chat_models_in_the_works/ | false | false | self | 6 | null |
Can someone please clarify this to me: Are tools like LangChain interacting with the model (memory) directly, or it's all just prompting behind the scenes and filtering the results to only include the complete answer ? | 27 | **Context:** I'm playing with LLMs and I'm trying to implement stuff in pure CPP as much as possible.
I can't find a clear answer, and I lost hours going thorough source codes.
I know you can load embeddings with a model and it treats that as a part of it's model, but this does not make sense in case of dynamic data,... | 2023-07-30T15:32:58 | https://www.reddit.com/r/LocalLLaMA/comments/15dog1h/can_someone_please_clarify_this_to_me_are_tools/ | staviq | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 15dog1h | false | null | t3_15dog1h | /r/LocalLLaMA/comments/15dog1h/can_someone_please_clarify_this_to_me_are_tools/ | false | false | self | 27 | null |
An error occurred Model failed. Please try loading it again. | 1 | This often happens when giving a language model a longish prompt, getting a longish response and then briefly asking the AI to continue.
Why does this happen and how can we prevent this error? | 2023-07-30T15:26:53 | https://www.reddit.com/r/LocalLLaMA/comments/15doas2/an_error_occurred_model_failed_please_try_loading/ | innocuousAzureus | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 15doas2 | false | null | t3_15doas2 | /r/LocalLLaMA/comments/15doas2/an_error_occurred_model_failed_please_try_loading/ | false | false | self | 1 | null |
Newb with a PowerEdge R710, 32GB RAM, 12-core. Can I play, too? | 1 | I really want to learn, and so I'm just blindly jumping in like a derp. To the gurus, can I run the 33B LLaMA model on a PowerEdge R710 with 32GB RAM and 12-cores? | 2023-07-30T14:25:22 | https://www.reddit.com/r/LocalLLaMA/comments/15dmw1d/newb_with_a_poweredge_r710_32gb_ram_12core_can_i/ | Actual-Bad5029 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 15dmw1d | false | null | t3_15dmw1d | /r/LocalLLaMA/comments/15dmw1d/newb_with_a_poweredge_r710_32gb_ram_12core_can_i/ | false | false | self | 1 | null |
Seeking Advice on Using an LLM for Document Interaction - Need Input Based on My Knowledge Only! | 9 | Hi everyone! 📚🤖
I'm looking for some guidance on utilizing an LLM to interact with my documents effectively. However, I have a unique requirement – I want the LLM to respond solely based on my knowledge and not its own. 🤔
I'd greatly appreciate any suggestions or insights you have on how to achieve this! Whether i... | 2023-07-30T13:12:36 | https://www.reddit.com/r/LocalLLaMA/comments/15dlb1p/seeking_advice_on_using_an_llm_for_document/ | Tight_Promise8668 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 15dlb1p | false | null | t3_15dlb1p | /r/LocalLLaMA/comments/15dlb1p/seeking_advice_on_using_an_llm_for_document/ | false | false | self | 9 | null |
airo-llongma-2-13B-16k-GPTQ - 16K long context llama - works in 24GB VRAM | 73 | Just wanted to bring folks attention to this model that has just been posted on HF. I've been waiting for a GPTQ model that has high context llama 2 "out of the box" and this looks promising:
[https://huggingface.co/kingbri/airo-llongma-2-13B-16k-GPTQ](https://huggingface.co/kingbri/airo-llongma-2-13B-16k-GPTQ)
I'm a... | 2023-07-30T13:11:26 | https://www.reddit.com/r/LocalLLaMA/comments/15dla85/airollongma213b16kgptq_16k_long_context_llama/ | CasimirsBlake | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 15dla85 | false | null | t3_15dla85 | /r/LocalLLaMA/comments/15dla85/airollongma213b16kgptq_16k_long_context_llama/ | false | false | self | 73 | {'enabled': False, 'images': [{'id': 'J1diEqwjH_RYKuobQuOS5eeZnZ9TPU0aM4okJ60biDM', 'resolutions': [{'height': 58, 'url': 'https://external-preview.redd.it/ZtJWUJ5WnCcVtsI5dcFAXWjb9FFJ884GvXAqCVlesLw.jpg?width=108&crop=smart&auto=webp&s=434e9988ce6a28eb3af989323c79312e635e8656', 'width': 108}, {'height': 116, 'url': 'h... |
Windows PC a lot slower then MacBook Pro 14 ? | 10 | I am not sure if this is some configuration issue or if I do something wrong but my gaming PC seems a lot slower then my MacBook.
MacBook Pro 14 Inch M1 base model
Gaming PC:
\- AMD Rzyen 7 1700x
\- 32GB DDR4 3200 MHZ Ram
\- MSI GTX 1080
​
Could this be true, that my MacBook is a lot faster ? I tried the ... | 2023-07-30T11:23:11 | https://www.reddit.com/r/LocalLLaMA/comments/15dj894/windows_pc_a_lot_slower_then_macbook_pro_14/ | AntiqueSalamander310 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 15dj894 | false | null | t3_15dj894 | /r/LocalLLaMA/comments/15dj894/windows_pc_a_lot_slower_then_macbook_pro_14/ | false | false | self | 10 | null |
As LLM-Based app owners, how do you handle the combination of fixed monthly pricing for customers and the payment per tokens for external APIs (such as OpenAI)? | 8 | I'm working on my own AI-based app and started wondering, how do you guys keep your business profitable? I'm willing to charge my customers about $15-20 each month, but what if their usage in the app makes the token generation price higher than this original price they are paying?
Some solutions I've thought about are... | 2023-07-30T11:11:47 | https://www.reddit.com/r/LocalLLaMA/comments/15dj18g/as_llmbased_app_owners_how_do_you_handle_the/ | Motor-Performer-4967 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 15dj18g | false | null | t3_15dj18g | /r/LocalLLaMA/comments/15dj18g/as_llmbased_app_owners_how_do_you_handle_the/ | false | false | self | 8 | null |
Stop AI from replying to itself? | 12 | Running koboldcpp with airoboros 13b, connected to sillytavern and the AI keeps replying to itself and completely ignoring whatever I type in. Anyone know how to fix this?
I’ve searched online but I can’t find anything about it. | 2023-07-30T10:57:22 | https://www.reddit.com/r/LocalLLaMA/comments/15dirvv/stop_ai_from_replying_to_itself/ | hippithoppitboppit | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 15dirvv | false | null | t3_15dirvv | /r/LocalLLaMA/comments/15dirvv/stop_ai_from_replying_to_itself/ | false | false | self | 12 | null |
Domain Specific Fine Tuning of LLMS (Coding and Security Domain) -> Open source | 1 | [removed] | 2023-07-30T09:55:23 | https://www.reddit.com/r/LocalLLaMA/comments/15dhpd6/domain_specific_fine_tuning_of_llms_coding_and/ | ababeel1122 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 15dhpd6 | false | null | t3_15dhpd6 | /r/LocalLLaMA/comments/15dhpd6/domain_specific_fine_tuning_of_llms_coding_and/ | false | false | self | 1 | {'enabled': False, 'images': [{'id': 'QyV2S4rh-pMbnJML_R7bbJcWB2RH98giH_Z_P45_3vo', 'resolutions': [{'height': 58, 'url': 'https://external-preview.redd.it/svHHAck7dSjoulgoGopBQmcysvgwynJ3DcKwn8sX7Zc.jpg?width=108&crop=smart&auto=webp&s=a058206456911026ebb90e4a841787cd0c5c75ec', 'width': 108}, {'height': 116, 'url': 'h... |
Domain Specific Fine Tuning of LLMS (Coding and Security Domain) -> Open source | 1 | [removed] | 2023-07-30T09:55:23 | https://www.reddit.com/r/LocalLLaMA/comments/15dhpd0/domain_specific_fine_tuning_of_llms_coding_and/ | ababeel1122 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 15dhpd0 | false | null | t3_15dhpd0 | /r/LocalLLaMA/comments/15dhpd0/domain_specific_fine_tuning_of_llms_coding_and/ | false | false | self | 1 | {'enabled': False, 'images': [{'id': 'QyV2S4rh-pMbnJML_R7bbJcWB2RH98giH_Z_P45_3vo', 'resolutions': [{'height': 58, 'url': 'https://external-preview.redd.it/svHHAck7dSjoulgoGopBQmcysvgwynJ3DcKwn8sX7Zc.jpg?width=108&crop=smart&auto=webp&s=a058206456911026ebb90e4a841787cd0c5c75ec', 'width': 108}, {'height': 116, 'url': 'h... |
What's the best llm for translating japanese text into english | 15 | So i need to translate a game from japanese into english while chatgpt is really good at translating japanese i was wondering if there are any local llms that are good at translating japanese text. | 2023-07-30T09:20:21 | https://www.reddit.com/r/LocalLLaMA/comments/15dh4rg/whats_the_best_llm_for_translating_japanese_text/ | ghjlans | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 15dh4rg | false | null | t3_15dh4rg | /r/LocalLLaMA/comments/15dh4rg/whats_the_best_llm_for_translating_japanese_text/ | false | false | self | 15 | null |
how to make the models like airoboros-l2-70b-gpt4-1.4.1.ggmlv3.q8_0.bin more intelligent? Maybe some sort of "code interpreter"? | 4 | [https://paste.c-net.org/NightyLately](https://paste.c-net.org/NightyLately)
So far, this model is the closest LLM *(that is pubically available to download and run)* to correctly answering my puzzle. publically
\----
Is there something I can change (maybe the prompt) so it answers it correctly?
​
Also...
... | 2023-07-30T08:07:18 | https://www.reddit.com/r/LocalLLaMA/comments/15dfzag/how_to_make_the_models_like/ | dewijones92 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 15dfzag | false | null | t3_15dfzag | /r/LocalLLaMA/comments/15dfzag/how_to_make_the_models_like/ | false | false | self | 4 | null |
2070 Super for fine tuning | 5 | I have a 2070 Super on my linux rig that I'm currently running headless and I want to start getting into training my own LLMs. Is a 2070 Super 8gb enough for fine tuning a 7B or 13B quantized model?
I have a decent bit of cash but I don't know If i want to invest in a 3090 equivalent card yet. Will the 2070 super b... | 2023-07-30T08:05:41 | https://www.reddit.com/r/LocalLLaMA/comments/15dfydz/2070_super_for_fine_tuning/ | QuantumTyping33 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 15dfydz | false | null | t3_15dfydz | /r/LocalLLaMA/comments/15dfydz/2070_super_for_fine_tuning/ | false | false | self | 5 | null |
Is there any organization working on an open source 175B model? If not what is the extra compute required compared to current 70B models. | 56 | Most or the models and finetunes we get are based on Llama2 and Llama which is an excellent base model and the results we get are almost comparable to gpt 3.5 but with less than 50 percent of the parameters.
If we were actually able to increase the parameters to 175B or atleast a 100B will the results we get increase... | 2023-07-30T07:29:21 | https://www.reddit.com/r/LocalLLaMA/comments/15dfc8y/is_there_any_organization_working_on_an_open/ | timedacorn369 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 15dfc8y | false | null | t3_15dfc8y | /r/LocalLLaMA/comments/15dfc8y/is_there_any_organization_working_on_an_open/ | false | false | self | 56 | null |
i cant seem to get my ai to work on my pc | 1 | [removed] | 2023-07-30T07:11:52 | https://www.reddit.com/r/LocalLLaMA/comments/15df1yh/i_cant_seem_to_get_my_ai_to_work_on_my_pc/ | Limisap_ | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 15df1yh | false | {'oembed': {'author_name': 'TroubleChute', 'author_url': 'https://www.youtube.com/@TroubleChute', 'height': 200, 'html': '<iframe width="356" height="200" src="https://www.youtube.com/embed/7KFYtVVrAX4?start=15&feature=oembed&enablejsapi=1" frameborder="0" allow="accelerometer; autoplay; clipboard-write; encrypted-medi... | t3_15df1yh | /r/LocalLLaMA/comments/15df1yh/i_cant_seem_to_get_my_ai_to_work_on_my_pc/ | false | false | 1 | {'enabled': False, 'images': [{'id': 'c9UiwLTDf8-8SWpb59hwWnG41qJEaCq_y9DN_uQlt40', 'resolutions': [{'height': 81, 'url': 'https://external-preview.redd.it/XDgQaCCeWWEhRjROBHXH7krQlzoVgbBKW4Kw9bIfG3Y.jpg?width=108&crop=smart&auto=webp&s=bff699d4db86bcddfc67a9002557f9d3243f3a6a', 'width': 108}, {'height': 162, 'url': 'h... | |
Is it possible to run SFT after RLHF? What would happen? | 10 | Llama-2-chat is an RHLF model that works pretty well, but it doesn't have multilingual ability.
So I'm thinking if it is possible to run another round of SFT on Llama-2-chat with a multilingual dataset like [mlabonne/guanaco-llama2-1k](https://huggingface.co/datasets/mlabonne/guanaco-llama2-1k) to get a Llama-2-chat m... | 2023-07-30T06:26:37 | https://www.reddit.com/r/LocalLLaMA/comments/15deamj/is_it_possible_to_run_sft_after_rlhf_what_would/ | CORNMONSTER_2022 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 15deamj | false | null | t3_15deamj | /r/LocalLLaMA/comments/15deamj/is_it_possible_to_run_sft_after_rlhf_what_would/ | false | false | self | 10 | {'enabled': False, 'images': [{'id': 'VD8BNjZdlcrGoshtjvSCNv_Jy2CkUJ_W2ZwE77TM1G8', 'resolutions': [{'height': 58, 'url': 'https://external-preview.redd.it/z_dxK9BQsC9bpzByaAyQd7MuTs_IAxR0GoFKru19_Ig.jpg?width=108&crop=smart&auto=webp&s=c7d006087fc75bd0a185250300320f684047bf99', 'width': 108}, {'height': 116, 'url': 'h... |
What are some good open source projects using the Guidance prompting library? | 33 | I'm looking to learn from example. [link](https://github.com/microsoft/Guidance) to library for the curious | 2023-07-30T06:17:53 | https://www.reddit.com/r/LocalLLaMA/comments/15de570/what_are_some_good_open_source_projects_using_the/ | -Django | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 15de570 | false | null | t3_15de570 | /r/LocalLLaMA/comments/15de570/what_are_some_good_open_source_projects_using_the/ | false | false | self | 33 | {'enabled': False, 'images': [{'id': 'x3RWQbLa5164A1hTBcNJTSMH9O6Z5cihDtpb2hELFLQ', 'resolutions': [{'height': 54, 'url': 'https://external-preview.redd.it/qf_5DP_YtVv1xLndJ50nOZD21uriMVCj4JC8FvtsU-k.jpg?width=108&crop=smart&auto=webp&s=07bc6460f127663ba8438d1c6526331b76bbc55d', 'width': 108}, {'height': 108, 'url': 'h... |
Only able to output 1000 tokens total on ooba? is that normal? | 4 | Im new to local ai stuff and I have a 3060 12 gb which im running TheBloke\_airoboros-l2-13B-gpt4-1.4.1-GPTQ at 4096 tokens I know my gpu cant do 4096 fully but is it normal to only get 1000 tokens in length. I'm using text gen ui to write some short stories using a smallish 100 token prompt and wanted to see why it w... | 2023-07-30T04:25:32 | https://www.reddit.com/r/LocalLLaMA/comments/15dc3si/only_able_to_output_1000_tokens_total_on_ooba_is/ | Dramatic_Borger | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 15dc3si | false | null | t3_15dc3si | /r/LocalLLaMA/comments/15dc3si/only_able_to_output_1000_tokens_total_on_ooba_is/ | false | false | self | 4 | null |
A Review: Using Llama 2 to Chat with Notes on Consumer Hardware | 73 | We recently integrated Llama 2 into [Khoj](https://github.com/khoj-ai/khoj). I wanted to share a short real-world evaluation of using Llama 2 for the chat with docs use-cases and hear which models have worked best for you all. The standard benchmarks (ARC, HellaSwag, MMLU etc.) are not tuned for evaluating this
**Eval... | 2023-07-30T03:15:22 | https://www.reddit.com/r/LocalLLaMA/comments/15darr6/a_review_using_llama_2_to_chat_with_notes_on/ | hoperyto | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 15darr6 | false | null | t3_15darr6 | /r/LocalLLaMA/comments/15darr6/a_review_using_llama_2_to_chat_with_notes_on/ | false | false | 73 | {'enabled': False, 'images': [{'id': '0zJJqyaQQs6InWqjPXotRt7AKVso5slBY5DY4OMdlFI', 'resolutions': [{'height': 54, 'url': 'https://external-preview.redd.it/87Tmwe4abAxXATeZtfyxsYyf0amZvmYrIVyHbyu7Uqw.jpg?width=108&crop=smart&auto=webp&s=720a87a6ec4a11ebb863138d16e16db827af8315', 'width': 108}, {'height': 108, 'url': 'h... | |
Why you use others versions of Llama if we have the most powerful which is Llama 2 - 70B | 0 | I ask because i see everyone is working on different versions of it like 7B, 13B, 35B, etcetera.
If the most powerful is 70B, Why don't focus on it?
Honestly I'm not very clear in this, the most i think is to generate diversity on the application with the objective of being able to use it on phones.
This is the reas... | 2023-07-30T03:02:55 | https://www.reddit.com/r/LocalLLaMA/comments/15dajb7/why_you_use_others_versions_of_llama_if_we_have/ | HighWillord | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 15dajb7 | false | null | t3_15dajb7 | /r/LocalLLaMA/comments/15dajb7/why_you_use_others_versions_of_llama_if_we_have/ | false | false | self | 0 | null |
I copied the link from the Bloke and paste it in oobabooga and click download, oobabooga starts downloading all quantized variations of the model ! Do I just wait for it ALL to download, more then 100 GB !!!, or can I just create a folder and download what is needed, what files are needed ? | 1 | [removed] | 2023-07-30T02:58:11 | https://www.reddit.com/r/LocalLLaMA/comments/15dafpi/i_copied_the_link_from_the_bloke_and_paste_it_in/ | Vitamin_C_is_awesome | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 15dafpi | false | null | t3_15dafpi | /r/LocalLLaMA/comments/15dafpi/i_copied_the_link_from_the_bloke_and_paste_it_in/ | false | false | self | 1 | null |
Calling All Tech Heros: Help! I'm Trapped and Desperately Need a New GPU for Falcon 40B! Can Anyone Rescue Me? | 0 | Hello, I am new to Stable Defusion, AI models, LLMs, and new to GPUs too.
So I need some help with choosing the right GPU for my needs.
My needs: Like 1h/day of Stable Defusion, I need to run my own ChatGPT AKA LLM model (Specifically falcon 40b h2o.ai version) on my pc for 24h/day (instead of running it on a server... | 2023-07-30T01:15:37 | https://www.reddit.com/r/LocalLLaMA/comments/15d8fst/calling_all_tech_heros_help_im_trapped_and/ | SakamotoKyu | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 15d8fst | false | null | t3_15d8fst | /r/LocalLLaMA/comments/15d8fst/calling_all_tech_heros_help_im_trapped_and/ | false | false | self | 0 | null |
Is it possible to run LLaMA v2 locally with a 4G GTX960 and 16 Gb RAM on a desktop? | 45 | I want to try using new technology to help me with text writing, but my computer is a low-end device and cannot support running llama on GPU mode. I want to know if it’s possible to run llama locally on my desktop, and if yes, how to do it? | 2023-07-30T00:42:07 | https://www.reddit.com/r/LocalLLaMA/comments/15d7r8c/is_it_possible_to_run_llama_v2_locally_with_a_4g/ | Tony_Malloy | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 15d7r8c | false | null | t3_15d7r8c | /r/LocalLLaMA/comments/15d7r8c/is_it_possible_to_run_llama_v2_locally_with_a_4g/ | false | false | self | 45 | null |
Fully finetuning LLaMA 2-7B | 24 | I am trying to fully finetune LLaMA 2 7B using [this](https://github.com/hiyouga/LLaMA-Efficient-Tuning) repo via 8 A100 (40GB) GPUs but consistently getting OOM error. I am quite new to fine-tuning LLMs so not sure if this is normal. Any advice would be greatly appreciated. | 2023-07-29T23:01:46 | https://www.reddit.com/r/LocalLLaMA/comments/15d5lp7/fully_finetuning_llama_27b/ | Ornery-Young-7346 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 15d5lp7 | false | null | t3_15d5lp7 | /r/LocalLLaMA/comments/15d5lp7/fully_finetuning_llama_27b/ | false | false | self | 24 | {'enabled': False, 'images': [{'id': 'Nj2g5gVB5tKBNRVtk4uJV44WvMa2GCNq_nTsDEOfS7c', 'resolutions': [{'height': 54, 'url': 'https://external-preview.redd.it/c8YaawyIonmwmCC3lq0wJobSSPCxbxKWm8vljWr6hQo.jpg?width=108&crop=smart&auto=webp&s=934113308863ea9a8a05f9c69c287ab3228f7e55', 'width': 108}, {'height': 108, 'url': 'h... |
How to calculate tokens in LLaMA output? | 2 | Trying to compare the tok/sec result between LLaMa.cpp and Replicate and was wondering how we calculate the total tokens. Will it be the same as the result from tiktoken library? | 2023-07-29T21:59:08 | https://www.reddit.com/r/LocalLLaMA/comments/15d464y/how_to_calculate_tokens_in_llama_output/ | AmoghMishra2303 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 15d464y | false | null | t3_15d464y | /r/LocalLLaMA/comments/15d464y/how_to_calculate_tokens_in_llama_output/ | false | false | self | 2 | null |
Issues with System Prompt Following for finetuned Llama-2 models (e.g. airoboros-l2-70B-gpt4-1.4.1 and StableBeluga2) | 15 | This is only after playing a bit around with Llama-2 and finetuned models, so there's a big chance I'm doing something terribly wrong, but what I've found so far is that while Llama-2 seems to be able to follow the system prompt quite religiously, other models tend to kind of follow it or completely ignore it.
Please... | 2023-07-29T21:13:02 | https://www.reddit.com/r/LocalLLaMA/comments/15d32p1/issues_with_system_prompt_following_for_finetuned/ | nightlingo | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 15d32p1 | false | null | t3_15d32p1 | /r/LocalLLaMA/comments/15d32p1/issues_with_system_prompt_following_for_finetuned/ | false | false | self | 15 | null |
Get the following error when trying to load models locally? | 2 | I haven't been able to find a solution anywhere else. I am using ex llama 8k gptq models loaded with the exllama model loader. All of which have the same error message. Running on 3090 gpu. If anyone has solved this or know how to I would really appreciate any help. Thanks!
​
Traceback (most recent call last)... | 2023-07-29T21:07:26 | https://www.reddit.com/r/LocalLLaMA/comments/15d2y67/get_the_following_error_when_trying_to_load/ | StoryScapeStudios | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 15d2y67 | false | null | t3_15d2y67 | /r/LocalLLaMA/comments/15d2y67/get_the_following_error_when_trying_to_load/ | false | false | self | 2 | null |
How do you prevent your LLM from overgenerating? | 31 | I'm playing around with airoboros 33b and following a standard 'USER: ...' 'GIRLFRIEND: ...' format but the LLM occasionally goes of the rails and throws a response like this:
"Oh no, did I have another dream about us?" USER: haha yeah. but it's okay. we can go back to sleep if u want GIRLFRIEND: That sounds perfec... | 2023-07-29T21:02:50 | https://www.reddit.com/r/LocalLLaMA/comments/15d2u94/how_do_you_prevent_your_llm_from_overgenerating/ | lukeborgen | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 15d2u94 | false | null | t3_15d2u94 | /r/LocalLLaMA/comments/15d2u94/how_do_you_prevent_your_llm_from_overgenerating/ | false | false | self | 31 | null |
Pre-Training Artifacts in Falcon-40b | 1 | [removed] | 2023-07-29T21:00:17 | https://www.reddit.com/r/LocalLLaMA/comments/15d2rp7/pretraining_artifacts_in_falcon40b/ | Mbando | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 15d2rp7 | false | null | t3_15d2rp7 | /r/LocalLLaMA/comments/15d2rp7/pretraining_artifacts_in_falcon40b/ | false | false | self | 1 | null |
Subsets and Splits
No community queries yet
The top public SQL queries from the community will appear here once available.