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 ⌀ |
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
Interactive tooling for local agents | 1 | Wouldn't it be awesome if an llm would interactively ask question and make suggestion while you write stuff?
I can see how far more granularity customized data could help people make their local setup more useful quicker. | 2023-09-28T16:26:12 | https://www.reddit.com/r/LocalLLaMA/comments/16ukipe/interactive_tooling_for_local_agents/ | ComplexRelevant2636 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 16ukipe | false | null | t3_16ukipe | /r/LocalLLaMA/comments/16ukipe/interactive_tooling_for_local_agents/ | false | false | self | 1 | null |
What type of Data Types do LLMs/LLaMa use? | 1 | When you look at the performance of a gpu it list FP64/FP32/FP16/Int8, etc.. What data types are we using when loader our quantized models, or even non quantized? I ask because looking at the performance on my machine I would think everything is being done with FP32 but thought LLM used FP16 most of the time? | 2023-09-28T15:55:13 | https://www.reddit.com/r/LocalLLaMA/comments/16ujppi/what_type_of_data_types_do_llmsllama_use/ | ccbadd | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 16ujppi | false | null | t3_16ujppi | /r/LocalLLaMA/comments/16ujppi/what_type_of_data_types_do_llmsllama_use/ | false | false | self | 1 | null |
Poor LoRA tools | 5 | I'd imagine we'd be getting far more out of the current models by being able to apply our own trained LoRAs to these LLMs to get them to work for our specific needs.
Right now we seem to be churning out more and more of the same Llama2 model with minor if any differences, while still having no LoRA creating tools tha... | 2023-09-28T15:46:46 | https://www.reddit.com/r/LocalLLaMA/comments/16uji7v/poor_lora_tools/ | AurrenTheWolf | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 16uji7v | false | null | t3_16uji7v | /r/LocalLLaMA/comments/16uji7v/poor_lora_tools/ | false | false | self | 5 | null |
List of Open Source UIs/Webapps for LLM Chatbots | 33 | Realized that many people are building their own chatbots from scratch which seems insane! So I compiled an "awesome list" of high-quality, plug-and-play chatbots, some of which support LLAMA/HF models out of the box.
[https://github.com/snowfort-ai/awesome-llm-webapps](https://github.com/snowfort-ai/awesome-llm-webap... | 2023-09-28T15:36:37 | https://www.reddit.com/r/LocalLLaMA/comments/16uj91r/list_of_open_source_uiswebapps_for_llm_chatbots/ | snowfort_guy | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 16uj91r | false | null | t3_16uj91r | /r/LocalLLaMA/comments/16uj91r/list_of_open_source_uiswebapps_for_llm_chatbots/ | false | false | self | 33 | {'enabled': False, 'images': [{'id': 'YN6cYQQpgQhjuCKbXGJmnwoW_ow-L2Ii2zsiopGeoeE', 'resolutions': [{'height': 54, 'url': 'https://external-preview.redd.it/P5lmE6yrt3YuuOKVwWocqsGS9cC6OK030_htsIpvBGw.jpg?width=108&crop=smart&auto=webp&s=a7d0b04f2896c14201ae050ab427cb2c2d8b5d31', 'width': 108}, {'height': 108, 'url': 'h... |
Cloud Options for testing LLM options (like Replicate, Together.ai, etc.) | 1 | [removed] | 2023-09-28T14:54:22 | https://www.reddit.com/r/LocalLLaMA/comments/16ui6ds/cloud_options_for_testing_llm_options_like/ | metsfan1025 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 16ui6ds | false | null | t3_16ui6ds | /r/LocalLLaMA/comments/16ui6ds/cloud_options_for_testing_llm_options_like/ | false | false | self | 1 | null |
Phi-1.5 finetunes and quantization's: Late September '23 edition | 1 | [removed] | 2023-09-28T14:19:50 | https://www.reddit.com/r/LocalLLaMA/comments/16uhbcy/phi15_finetunes_and_quantizations_late_september/ | Balance- | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 16uhbcy | false | null | t3_16uhbcy | /r/LocalLLaMA/comments/16uhbcy/phi15_finetunes_and_quantizations_late_september/ | false | false | self | 1 | {'enabled': False, 'images': [{'id': '3cxODlbih2qIQ-Qz9TOJSgByP2mgwayu1N0D8OG073s', 'resolutions': [{'height': 58, 'url': 'https://external-preview.redd.it/RCRgGANgOFhF64DNhHUMRz_K6LU58kyYmwvZUleyaVo.jpg?width=108&crop=smart&auto=webp&s=25176b92bb1e26f2c819378d495d619d06239a13', 'width': 108}, {'height': 116, 'url': 'h... |
Using LLAMA 2 for Document Sectioning in Medical Letters | 4 | Hello good people,
I'm curious if there's a method to use LLAMA 2 to split a document, like a medical letter, into sections like introduction, medications, summary, and so on? | 2023-09-28T14:16:57 | https://www.reddit.com/r/LocalLLaMA/comments/16uh8tr/using_llama_2_for_document_sectioning_in_medical/ | mohamednajdawi | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 16uh8tr | false | null | t3_16uh8tr | /r/LocalLLaMA/comments/16uh8tr/using_llama_2_for_document_sectioning_in_medical/ | false | false | self | 4 | null |
Swiss Army Llama: Do tons of useful stuff with local LLMs with a REST API | 54 | GitHub Repo: [https://github.com/Dicklesworthstone/swiss\_army\_llama](https://github.com/Dicklesworthstone/swiss_army_llama)
This project originally started out with a focus on easily generating embeddings from Llama2 and other llama\_cpp (gguf) models and storing them in a database, all exposed via a convenient REST... | 2023-09-28T14:12:03 | https://www.reddit.com/r/LocalLLaMA/comments/16uh4kr/swiss_army_llama_do_tons_of_useful_stuff_with/ | dicklesworth | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 16uh4kr | false | null | t3_16uh4kr | /r/LocalLLaMA/comments/16uh4kr/swiss_army_llama_do_tons_of_useful_stuff_with/ | false | false | self | 54 | {'enabled': False, 'images': [{'id': 'fCXOgyZ2W8tGxxw2efspDQHILZB0k-ShLk5hnm-Ln-Y', 'resolutions': [{'height': 54, 'url': 'https://external-preview.redd.it/c_KN-jhqxFfSSOkT6xTD1IVPczxPRqmHatKORfWiH2g.jpg?width=108&crop=smart&auto=webp&s=5268322afe636d271de4599f2a579ca2c22e61b2', 'width': 108}, {'height': 108, 'url': 'h... |
Need advice on Strategys for Local Hosting | 3 | I've been lurking for some time here and find the discussions interesting, but I have been hesitant to pull the trigger on jumping head first into a local hosting/training solution. Here are my concerns.
1. Local training is expensive both from a capital and operational cost perspective.
2. Maintaining data privacy ... | 2023-09-28T13:30:24 | https://www.reddit.com/r/LocalLLaMA/comments/16ug4z3/need_advice_on_strategys_for_local_hosting/ | The_Last_Monte | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 16ug4z3 | false | null | t3_16ug4z3 | /r/LocalLLaMA/comments/16ug4z3/need_advice_on_strategys_for_local_hosting/ | false | false | self | 3 | null |
General questions on LLMs and how to use them (post your own) | 5 | Now since I have a few questions myself, maybe we can use this thread for posting stuff that people will look up now and then, like some form of FAQ. If not, I hope at least my questions will be answered. :)
(I will create my questions as comments.) | 2023-09-28T12:59:29 | https://www.reddit.com/r/LocalLLaMA/comments/16ufefp/general_questions_on_llms_and_how_to_use_them/ | psi-love | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 16ufefp | false | null | t3_16ufefp | /r/LocalLLaMA/comments/16ufefp/general_questions_on_llms_and_how_to_use_them/ | false | false | self | 5 | null |
Small First Aid / survival LLM | 8 | Is there any LLM specifically well suited for first aid and/or survival? For situations without cell reception, such an LLM could be quite useful.
7B LLMs now run on high-end phones. Combined with satellite based emergency service this could make emergency situations in areas without cell receptions potentially a lot ... | 2023-09-28T12:57:47 | https://www.reddit.com/r/LocalLLaMA/comments/16ufczn/small_first_aid_survival_llm/ | Balance- | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 16ufczn | false | null | t3_16ufczn | /r/LocalLLaMA/comments/16ufczn/small_first_aid_survival_llm/ | false | false | self | 8 | {'enabled': False, 'images': [{'id': 'q3evP6JeDpAC2MdSQHWYxnCYTqbJkElIQsLFqVSdkss', 'resolutions': [{'height': 63, 'url': 'https://external-preview.redd.it/izh8gZHY4FqZ1nwtU1N_TjtohUCNuvTyMn90toXda80.jpg?width=108&crop=smart&auto=webp&s=bc9575b410002edc2df3c5b5b0355fefedc7baa8', 'width': 108}, {'height': 126, 'url': 'h... |
Is anyone interested in a prompt template converter? | 13 | Hi, llamers – after downloading a new model, I got stuck for a while by rewriting my local prompt files from one model template to another, which is just an unpleasant process.
From:
`<|prompter|>*your text here*<|endoftext|><|assistant|>`
To:
`USER: *your text here* ASSISTANT:`
Is anyone interested in a single... | 2023-09-28T12:34:24 | https://www.reddit.com/r/LocalLLaMA/comments/16ueu32/is_anyone_interested_in_a_prompt_template/ | Shir_man | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 16ueu32 | false | null | t3_16ueu32 | /r/LocalLLaMA/comments/16ueu32/is_anyone_interested_in_a_prompt_template/ | false | false | self | 13 | null |
Llama with HF Candle | 2 | Has anybody tried running llama with hf candle .
If yes, how better it is than running it on python | 2023-09-28T11:12:13 | https://www.reddit.com/r/LocalLLaMA/comments/16ud46p/llama_with_hf_candle/ | Spiritual-Rub925 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 16ud46p | false | null | t3_16ud46p | /r/LocalLLaMA/comments/16ud46p/llama_with_hf_candle/ | false | false | self | 2 | null |
is there a step by step guide for training loras? | 6 | i have an rtx 4080, i tried training loras but literally none of them worked, i tried many models as a base, tried to load them several ways, and even though i tried to keep settings default, they either won't start training, or i get all sorts of errors when i try to train, or i get an error a while after training has... | 2023-09-28T11:08:17 | https://www.reddit.com/r/LocalLLaMA/comments/16ud1dw/is_there_a_step_by_step_guide_for_training_loras/ | 3lirex | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 16ud1dw | false | null | t3_16ud1dw | /r/LocalLLaMA/comments/16ud1dw/is_there_a_step_by_step_guide_for_training_loras/ | false | false | self | 6 | null |
How to use a weaviate cluster in kubernetes for storing a vectorstore index? | 3 | Looking for an easy to follow tutorial for someone who doesn't have much experience with kubernetes.
I joined a new company a couple of weeks ago, and they use Rancher for kubernetes deployments, and I am totally unfamiliar with it. I have done a couple of kubernetes deployments with GKE in the past, but Rancher seems... | 2023-09-28T11:00:43 | https://www.reddit.com/r/LocalLLaMA/comments/16ucw1i/how_to_use_a_weaviate_cluster_in_kubernetes_for/ | ResearcherNo4728 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 16ucw1i | false | null | t3_16ucw1i | /r/LocalLLaMA/comments/16ucw1i/how_to_use_a_weaviate_cluster_in_kubernetes_for/ | false | false | self | 3 | {'enabled': False, 'images': [{'id': 'uCKgsARIVYHyputdKdO9ksztdsoTyZA0bbN34MOZOw0', 'resolutions': [{'height': 54, 'url': 'https://external-preview.redd.it/jGFU8U0oW4Cij03vKaJ4s_RJYDpKHF0Z9n_gm_rplvU.jpg?width=108&crop=smart&auto=webp&s=c09124bc959a674d36d5f534868065d24d87339b', 'width': 108}, {'height': 108, 'url': 'h... |
Pipeline for model evaluation in a batch | 4 | There are so many amazing models and fine-tunes being published on a daily basis that it's hard to keep track of everything and more often than not, the official benchmark numbers don't tell the full story on how well models will perform for my specific use-cases.
I have downloaded 20-30 models and most of the time, I... | 2023-09-28T10:54:06 | https://www.reddit.com/r/LocalLLaMA/comments/16ucrmx/pipeline_for_model_evaluation_in_a_batch/ | minecraft_simon | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 16ucrmx | false | null | t3_16ucrmx | /r/LocalLLaMA/comments/16ucrmx/pipeline_for_model_evaluation_in_a_batch/ | false | false | self | 4 | null |
Cost comparison of Llama 2 vs GPT? | 1 | Phil Schmid recently posted an article on huggingface regarding deployment costs of Llama on Sagemaker here: https://huggingface.co/blog/llama-sagemaker-benchmark
Here's pricing of ChatGPT API: https://openai.com/pricing
How is OpenAI API so cheap as compared to cloud deployment? What possibly could they be doing? | 2023-09-28T10:36:50 | https://www.reddit.com/r/LocalLLaMA/comments/16ucgex/cost_comparison_of_llama_2_vs_gpt/ | FolksyCobalt | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 16ucgex | false | null | t3_16ucgex | /r/LocalLLaMA/comments/16ucgex/cost_comparison_of_llama_2_vs_gpt/ | false | false | self | 1 | {'enabled': False, 'images': [{'id': '6GF5SFLQuxM57YUbXvvVb4a8VRrVD6a78kruPuKM9X8', 'resolutions': [{'height': 56, 'url': 'https://external-preview.redd.it/7zTJ9OP4lj9WWoZtUPBIhWhZmPUxjsSDv04A1lyPr_o.jpg?width=108&crop=smart&auto=webp&s=972c49520410737c4c5e358d2f062e2585ddb49b', 'width': 108}, {'height': 112, 'url': 'h... |
How to select sampling parameters and decoding strategies? | 5 | I have a rough understanding of how greedy search/ beam search works and how nucleus and mirostat sampling work. I'm not sure what is the best way to select the parameters. Are there some best practices/ presets for different tasks which I could use as a starting point? Also, beam search is quite slow. Do any of the ot... | 2023-09-28T10:03:21 | https://www.reddit.com/r/LocalLLaMA/comments/16ubuqz/how_to_select_sampling_parameters_and_decoding/ | LiquidGunay | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 16ubuqz | false | null | t3_16ubuqz | /r/LocalLLaMA/comments/16ubuqz/how_to_select_sampling_parameters_and_decoding/ | false | false | self | 5 | null |
But where is the llama source code | 1 | where is the source code that made the 'llama 2' | 2023-09-28T09:55:42 | https://www.reddit.com/r/LocalLLaMA/comments/16ubpwv/but_where_is_the_llama_source_code/ | qwertykeyboard_1 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 16ubpwv | false | null | t3_16ubpwv | /r/LocalLLaMA/comments/16ubpwv/but_where_is_the_llama_source_code/ | false | false | self | 1 | null |
NVLink bridge worth it for dual RTX 3090? | 37 | I recently got hold of two RTX 3090 GPUs specifically for LLM inference and training.
Everything seems to work well and I can finally fit a 70B model into the VRAM with 4 bit quantization.
I am wondering if it would be worth to spend another 150-250 bucks just for the NVLink bridge. Does anyone have experience with t... | 2023-09-28T09:47:22 | https://www.reddit.com/r/LocalLLaMA/comments/16ubkyq/nvlink_bridge_worth_it_for_dual_rtx_3090/ | minecraft_simon | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 16ubkyq | false | null | t3_16ubkyq | /r/LocalLLaMA/comments/16ubkyq/nvlink_bridge_worth_it_for_dual_rtx_3090/ | false | false | self | 37 | null |
Fine-tuning legal chatbot | 1 | [removed] | 2023-09-28T08:23:51 | https://www.reddit.com/r/LocalLLaMA/comments/16ua9nn/finetuning_legal_chatbot/ | Tejasw__ | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 16ua9nn | false | null | t3_16ua9nn | /r/LocalLLaMA/comments/16ua9nn/finetuning_legal_chatbot/ | false | false | self | 1 | {'enabled': False, 'images': [{'id': 'kiTAa4bFkOmLLNa4kjtv8fpFOwInbsnAb5RZFo9RdHQ', 'resolutions': [{'height': 58, 'url': 'https://external-preview.redd.it/FmdpgwbYoVmg9A56OpSQIS6-8ynaErevnIifbsY1Szk.jpg?width=108&crop=smart&auto=webp&s=a8bd49fbc84528679a589f37acd2c91da8d598c7', 'width': 108}, {'height': 116, 'url': 'h... |
Seeking Input on Local Model Alternatives for Complex Database Queries, Mapping | 4 | I am working on developing a conversational agent capable of answering complex questions about our database. Our goal is to empower users to make detailed inquiries about entity names, specialties, locations, and more. However, we've encountered some performance issues with the LLM 7B model in comparison to Chat GPT.
... | 2023-09-28T08:12:14 | https://www.reddit.com/r/LocalLLaMA/comments/16ua37d/seeking_input_on_local_model_alternatives_for/ | Alertt_53 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 16ua37d | false | null | t3_16ua37d | /r/LocalLLaMA/comments/16ua37d/seeking_input_on_local_model_alternatives_for/ | false | false | self | 4 | null |
LLama 2 jailbreak: Albert, at your service. (Genera-purpose AI jailbreak, similar to DAN) | 10 | 2023-09-28T07:45:42 | https://github.com/TheRook/Albert | AlternativeMath-1 | github.com | 1970-01-01T00:00:00 | 0 | {} | 16u9os8 | false | null | t3_16u9os8 | /r/LocalLLaMA/comments/16u9os8/llama_2_jailbreak_albert_at_your_service/ | false | false | 10 | {'enabled': False, 'images': [{'id': 'p-Cwi3wCM8en0xRnwKjEtDbTb0vH9zA63ZGI4si315E', 'resolutions': [{'height': 54, 'url': 'https://external-preview.redd.it/yzYdx6vntSo7F2stpeaCvYLxavgf7YTWQM-cwEQ7kD0.jpg?width=108&crop=smart&auto=webp&s=af01b1f5c43b4bb251ce3410acbdc1a01794e4ad', 'width': 108}, {'height': 108, 'url': 'h... | ||
Datasets | 2 | Hello does anybody know where to retrieve the datasets this repo mention?
[https://github.com/michaelnny/InstructLLaMA#download-and-prepare-datasets](https://github.com/michaelnny/InstructLLaMA#download-and-prepare-datasets)
Thanks :) | 2023-09-28T06:54:52 | https://www.reddit.com/r/LocalLLaMA/comments/16u8w86/datasets/ | Outrageous_Ad8520 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 16u8w86 | false | null | t3_16u8w86 | /r/LocalLLaMA/comments/16u8w86/datasets/ | false | false | default | 2 | {'enabled': False, 'images': [{'id': '_uBOlIAElkGfXpi6nut69VlzuMo7jX9pnk8VUysIhPY', 'resolutions': [{'height': 54, 'url': 'https://external-preview.redd.it/HfrtF0n7lH5b92RxyqyyEMvF85ULVZn1GuiW49RIy3Y.jpg?width=108&crop=smart&auto=webp&s=c95252233228b73477831e58329ae34e1bd1cdbd', 'width': 108}, {'height': 108, 'url': 'h... |
error when using a lora i trained | 2 | i'm new to local text generation, i just installed text generation web ui yesterday, everything works, but as soon as i try to apply the lora i trained (and retrained) i get this error:
Traceback (most recent call last):
File "C:\\Users\\sa\\Desktop\\textw\\text-generation-webui\\modules\\[callbacks.py](https://cal... | 2023-09-28T06:47:20 | https://www.reddit.com/r/LocalLLaMA/comments/16u8rve/error_when_using_a_lora_i_trained/ | 3lirex | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 16u8rve | false | null | t3_16u8rve | /r/LocalLLaMA/comments/16u8rve/error_when_using_a_lora_i_trained/ | false | false | self | 2 | null |
LM Studio models repetition issue | 9 | I've noticed this a few times now wiht a few different models. Whenever the LLM finishes a response and cuts it off, if i hit continue, it just repeats itself again.
Using wizardlm lama2 13b q8 or mythalion 13b q6 or any of hte other "prose" type LLMs, they always seem to repeat on continue instead of actually contin... | 2023-09-28T05:58:26 | https://www.reddit.com/r/LocalLLaMA/comments/16u7xzz/lm_studio_models_repetition_issue/ | count023 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 16u7xzz | false | null | t3_16u7xzz | /r/LocalLLaMA/comments/16u7xzz/lm_studio_models_repetition_issue/ | false | false | self | 9 | null |
Ebony_FicWriter GGUF (writing model for amusement) | 20 | 2023-09-28T05:33:49 | FPham | i.redd.it | 1970-01-01T00:00:00 | 0 | {} | 16u7iav | false | null | t3_16u7iav | /r/LocalLLaMA/comments/16u7iav/ebony_ficwriter_gguf_writing_model_for_amusement/ | false | false | 20 | {'enabled': True, 'images': [{'id': 'J76VAjToUtSDtkJJ0HpUjDE4EQUvbJEVL-uzu7hap0Q', 'resolutions': [{'height': 176, 'url': 'https://preview.redd.it/4kekkl4lnxqb1.jpg?width=108&crop=smart&auto=webp&s=6f2ab5dda54316867599c0db5c6eda9e55489676', 'width': 108}, {'height': 352, 'url': 'https://preview.redd.it/4kekkl4lnxqb1.jp... | |||
Apple restocked their certified refurbished Macs today. | 26 | Many models have already sold out. To give you an example of what the prices are like, a new M2 Ultra 76 core GPU is $6600. The refurbished one was $5600. But it's OOS.
A more midling model, M1 Ultra 48 core GPU 128GB was $3600.
These are the machines with the smallest drives possible. The configs with bigger drives ... | 2023-09-28T05:03:13 | https://www.reddit.com/r/LocalLLaMA/comments/16u6yok/apple_restocked_their_certified_refurbished_macs/ | fallingdowndizzyvr | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 16u6yok | false | null | t3_16u6yok | /r/LocalLLaMA/comments/16u6yok/apple_restocked_their_certified_refurbished_macs/ | false | false | self | 26 | null |
Deploy LLama v2 on A100 GPU locally (Not Cloud) ? | 1 | [removed] | 2023-09-28T04:29:08 | https://www.reddit.com/r/LocalLLaMA/comments/16u6c5p/deploy_llama_v2_on_a100_gpu_locally_not_cloud/ | Vi_ai | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 16u6c5p | false | null | t3_16u6c5p | /r/LocalLLaMA/comments/16u6c5p/deploy_llama_v2_on_a100_gpu_locally_not_cloud/ | false | false | self | 1 | {'enabled': False, 'images': [{'id': 'xgo0oMh2KAomuWljORL66cEJv_S-BospQ9FT4djWnVw', 'resolutions': [{'height': 106, 'url': 'https://external-preview.redd.it/V5d6lnYUvRlN2IdUXCLbyOOS5k_3A53UEb6ju9nFwWc.jpg?width=108&crop=smart&auto=webp&s=0d292e698bd96c3149d36629eab50ad7de1b783e', 'width': 108}, {'height': 212, 'url': '... |
How to Deploy Llama v2 on local A100 GPU ? | 1 | I was able to deploy llama v2 on A100 on my local server and inference from it following this tutorial (https://medium.com/@im_jatintyagi/deploy-your-llm-api-on-cpu-d350e38a7dbd) its basically loading the model and accessing it through fastAPI and tunnelling through ngrok. I would like to use this public url with groun... | 2023-09-28T02:31:18 | https://www.reddit.com/r/LocalLLaMA/comments/16u40fp/how_to_deploy_llama_v2_on_local_a100_gpu/ | Vi_ai | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 16u40fp | false | null | t3_16u40fp | /r/LocalLLaMA/comments/16u40fp/how_to_deploy_llama_v2_on_local_a100_gpu/ | false | false | self | 1 | {'enabled': False, 'images': [{'id': 'xgo0oMh2KAomuWljORL66cEJv_S-BospQ9FT4djWnVw', 'resolutions': [{'height': 106, 'url': 'https://external-preview.redd.it/V5d6lnYUvRlN2IdUXCLbyOOS5k_3A53UEb6ju9nFwWc.jpg?width=108&crop=smart&auto=webp&s=0d292e698bd96c3149d36629eab50ad7de1b783e', 'width': 108}, {'height': 212, 'url': '... |
Is an RTX4070, 12GB VRAM, 64GB RAM and an AMD 7 3700X good for a 70B? | 6 | Title ( Check my comment as well ) | 2023-09-28T02:25:18 | https://www.reddit.com/r/LocalLLaMA/comments/16u3vp3/is_an_rtx4070_12gb_vram_64gb_ram_and_an_amd_7/ | Belze_WasTaken | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 16u3vp3 | false | null | t3_16u3vp3 | /r/LocalLLaMA/comments/16u3vp3/is_an_rtx4070_12gb_vram_64gb_ram_and_an_amd_7/ | false | false | self | 6 | null |
Mistral 7B Beats Llama 2 13B on All Benchmarks | 1 | [removed] | 2023-09-28T02:17:27 | https://www.reddit.com/r/LocalLLaMA/comments/16u3pbv/mistral_7b_beats_llama_2_13b_on_all_benchmarks/ | trulyfurqan | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 16u3pbv | false | null | t3_16u3pbv | /r/LocalLLaMA/comments/16u3pbv/mistral_7b_beats_llama_2_13b_on_all_benchmarks/ | false | false | self | 1 | {'enabled': False, 'images': [{'id': 'g7n_1Jb14Y8BXFCnH7wC1zkld0ODa1KmQ3lQbS-Ua4c', 'resolutions': [{'height': 54, 'url': 'https://external-preview.redd.it/3XdAqZORNkASFPifjeeOP24mmGFpPtfKiCtFqJDMtRI.jpg?width=108&crop=smart&auto=webp&s=4e69f45fce712cb52b68317a0a98bfdfa1cff294', 'width': 108}, {'height': 108, 'url': 'h... |
Two technical questions on censoring models. | 1 | [removed] | 2023-09-28T02:14:50 | https://www.reddit.com/r/LocalLLaMA/comments/16u3n2m/two_technical_questions_on_censoring_models/ | Guilty-History-9249 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 16u3n2m | false | null | t3_16u3n2m | /r/LocalLLaMA/comments/16u3n2m/two_technical_questions_on_censoring_models/ | false | false | self | 1 | null |
Llama2 on M1 Ultra 128gb mac studio | 1 | 2023-09-28T01:40:10 | SigM400 | i.redd.it | 1970-01-01T00:00:00 | 0 | {} | 16u2uaf | false | null | t3_16u2uaf | /r/LocalLLaMA/comments/16u2uaf/llama2_on_m1_ultra_128gb_mac_studio/ | false | false | 1 | {'enabled': True, 'images': [{'id': 's6mArq_tn-Vbs7v6GuJrip83f8hREi8DqJJsVAemQpE', 'resolutions': [{'height': 121, 'url': 'https://preview.redd.it/ebltz4exhwqb1.png?width=108&crop=smart&auto=webp&s=8f603b7dbc405b98162305c533dcb878a11f4171', 'width': 108}, {'height': 243, 'url': 'https://preview.redd.it/ebltz4exhwqb1.pn... | |||
Multi-Modal Vector Embeddings at Scale | 1 | Hey everyone, excited to announce the addition of image embeddings for semantic similarity search to VectorFlow, the only high volume open source embedding pipeline. Now you can embed a high volume of images quickly with minimal effort and search them using Vectorflow. This will empower a wide range of applications, fr... | 2023-09-27T23:32:22 | https://www.reddit.com/r/LocalLLaMA/comments/16tzvp9/multimodal_vector_embeddings_at_scale/ | Fast_Homework_3323 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 16tzvp9 | false | null | t3_16tzvp9 | /r/LocalLLaMA/comments/16tzvp9/multimodal_vector_embeddings_at_scale/ | false | false | self | 1 | {'enabled': False, 'images': [{'id': 'ihzaBOYBFOFvmz1TpFTKGK5GDTWIxDqGf83GqYavM9o', 'resolutions': [{'height': 54, 'url': 'https://external-preview.redd.it/gz9goWfmEhaWr8H0ySdzVZ1JGlfab0iYbz0wgLupVr4.jpg?width=108&crop=smart&auto=webp&s=12668e0c9df66f8a4e36e1bbfdaae95629eb179c', 'width': 108}, {'height': 108, 'url': 'h... |
What are the best evaluations benchmarks for testing common sense, reasoning, summarisation and instruction following | 10 | I am looking into different llm evaluation benchmarks. I found [this list](https://github.com/EleutherAI/lm-evaluation-harness/tree/big-refactor/lm_eval/tasks#v10-tasks) from [https://github.com/EleutherAI/lm-evaluation-harness](https://github.com/EleutherAI/lm-evaluation-harness), but there are so many there, I'm unsu... | 2023-09-27T22:02:45 | https://www.reddit.com/r/LocalLLaMA/comments/16txkg8/what_are_the_best_evaluations_benchmarks_for/ | Zyguard7777777 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 16txkg8 | false | null | t3_16txkg8 | /r/LocalLLaMA/comments/16txkg8/what_are_the_best_evaluations_benchmarks_for/ | false | false | self | 10 | {'enabled': False, 'images': [{'id': '_lhCRyGnoxKvBBwa39Y5RVal-3itN-Z20fzRsWoxzpU', 'resolutions': [{'height': 54, 'url': 'https://external-preview.redd.it/DIauZmNVV_-CtiNIUPIhrM87Jcrs8iSx5iNLvxQsl6Y.jpg?width=108&crop=smart&auto=webp&s=8535f4d8dca7b24335aa0070d5b23eaa4b26e6e2', 'width': 108}, {'height': 108, 'url': 'h... |
Perplexity Testing Mac vs Windows Pt 2- Mac still 3x lower | 5 | [Part 1](https://www.reddit.com/r/LocalLLaMA/comments/16st2l5/getting_wildly_different_perplexity_test_results/)
So, after my last post seemed to have caused some consternation amongst folks, I thought I'd take another go at it and it do it properly this time, ensuring everything is absolutely identical between the tw... | 2023-09-27T21:54:53 | https://www.reddit.com/r/LocalLLaMA/comments/16txcqw/perplexity_testing_mac_vs_windows_pt_2_mac_still/ | LearningSomeCode | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 16txcqw | false | null | t3_16txcqw | /r/LocalLLaMA/comments/16txcqw/perplexity_testing_mac_vs_windows_pt_2_mac_still/ | false | false | self | 5 | null |
With Mistral 7B outperforming Llama 13B, how long will we wait for a 7B model to surpass today's GPT-4 | 136 | About 6-5 months ago, before the alpaca model was released, many doubted we'd see comparable results within 5 years. Yet now, Llama 2 approaches the original GPT-4's performance, and WizardCoder even surpasses it in coding tasks. With the recent announcement of Mistral 7B, it makes one wonder: how long before a 7B mode... | 2023-09-27T21:50:39 | https://www.reddit.com/r/LocalLLaMA/comments/16tx8qh/with_mistral_7b_outperforming_llama_13b_how_long/ | zazazakaria | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 16tx8qh | false | null | t3_16tx8qh | /r/LocalLLaMA/comments/16tx8qh/with_mistral_7b_outperforming_llama_13b_how_long/ | false | false | self | 136 | null |
LLM Chat/RP Comparison/Test: Mistral 7B Base + Instruct | 170 | Here's another LLM Chat/RP comparison/test of mine featuring today's newly released **[Mistral](https://twitter.com/MistralAI/status/1706877320844509405)** models!
Mistral seems to be trained on 32K context, but KoboldCpp doesn't go that high yet, and I only tested 4K context so far:
- **[Mistral-7B-Instruct-v0.1](ht... | 2023-09-27T21:34:39 | https://www.reddit.com/r/LocalLLaMA/comments/16twtfn/llm_chatrp_comparisontest_mistral_7b_base_instruct/ | WolframRavenwolf | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 16twtfn | false | null | t3_16twtfn | /r/LocalLLaMA/comments/16twtfn/llm_chatrp_comparisontest_mistral_7b_base_instruct/ | false | false | self | 170 | {'enabled': False, 'images': [{'id': 'CS0B1I30ZYj0ZX-zyY6FLZvd72xR9WPR7HDTGHV8oJU', 'resolutions': [{'height': 108, 'url': 'https://external-preview.redd.it/5sqkwEMzIqqPNtzrB1t5XsvpUZjwXad14Gcaj40q5TI.jpg?width=108&crop=smart&auto=webp&s=60a70155bda3574ef1569e82bff7884074c1b383', 'width': 108}], 'source': {'height': 14... |
Justice LLM? | 1 | Hello fellow local llamaers.
I pose this as a thought exercise.
If tuned LLM chat interfaces are going to be offering high quality services to consumers soon, would it not follow that as they become trusted and expected in all areas of life, that this technology would not be used within the judicial and justice sys... | 2023-09-27T21:33:58 | https://www.reddit.com/r/LocalLLaMA/comments/16twstp/justice_llm/ | Tridente | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 16twstp | false | null | t3_16twstp | /r/LocalLLaMA/comments/16twstp/justice_llm/ | false | false | self | 1 | null |
Autogen from Microsoft, Enable Next-Gen Large Language Model Applications | 24 | https://github.com/microsoft/autogen | 2023-09-27T21:32:09 | https://www.reddit.com/r/LocalLLaMA/comments/16twr5n/autogen_from_microsoft_enable_nextgen_large/ | Scary-Knowledgable | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 16twr5n | false | null | t3_16twr5n | /r/LocalLLaMA/comments/16twr5n/autogen_from_microsoft_enable_nextgen_large/ | false | false | self | 24 | {'enabled': False, 'images': [{'id': 'tkGpRIroBnVX9iGbNPf7rnLP4CiPBpvmpFE55FN1Sa4', 'resolutions': [{'height': 54, 'url': 'https://external-preview.redd.it/SXDS9sJC-1iIIJczkmH5iSJ8uowai6ICxPbpHADEJnk.jpg?width=108&crop=smart&auto=webp&s=024d798172180541a3031158f662b4a6c825e98f', 'width': 108}, {'height': 108, 'url': 'h... |
Running fp16 on Text Generation UI for Llama 2 13B chat | 1 | I am trying to run fp16 with llama.cpp and I am not sure if that's possible? I can't load the model with it for reference I used (TheBloke/Llama-2-13B-Chat-fp16). Can someone help me understand what you typically have to do to run fp16? I can run the quantized models with the gguf version easily.. | 2023-09-27T21:31:16 | https://www.reddit.com/r/LocalLLaMA/comments/16twqa3/running_fp16_on_text_generation_ui_for_llama_2/ | lifesucksandthenudie | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 16twqa3 | false | null | t3_16twqa3 | /r/LocalLLaMA/comments/16twqa3/running_fp16_on_text_generation_ui_for_llama_2/ | false | false | self | 1 | null |
Fine-tuned llama2-7b-lora vs chatGPT in a noble game of chess? | 15 | TL;DR I've experimented fine-tuning few llama2-7b models to play chess trying different datasets (regular move list in PGN format, board drawings, position analysis, etc.). Neither of them performed extremely well, however PGN is the way to go: can predict early moves, does ok vs ChatGPT-3.5 in some tasks, loses in che... | 2023-09-27T21:03:10 | https://www.reddit.com/r/LocalLLaMA/comments/16tvz7b/finetuned_llama27blora_vs_chatgpt_in_a_noble_game/ | Acceptable_Bed7015 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 16tvz7b | false | null | t3_16tvz7b | /r/LocalLLaMA/comments/16tvz7b/finetuned_llama27blora_vs_chatgpt_in_a_noble_game/ | false | false | 15 | null | |
I have finetuned LLAMA 7B on dialouge dataset, call it llamaxyz, the model is giving good results as now. Now, I also want to incorporate some static information (basically RAG), in same, do I use LLAMA index with my fine-tuned LLAMAXYZ model? or change the static information in conversational data, | 1 | [removed] | 2023-09-27T20:39:13 | https://www.reddit.com/r/LocalLLaMA/comments/16tvdab/i_have_finetuned_llama_7b_on_dialouge_dataset/ | Anu_Rag9704 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 16tvdab | false | null | t3_16tvdab | /r/LocalLLaMA/comments/16tvdab/i_have_finetuned_llama_7b_on_dialouge_dataset/ | false | false | self | 1 | null |
Opinion regarding the optimal model. | 3 | While I understand people have very cheap GPU's with 4 or 6 GB's of VRam the ultimate for a local LLM is a 4090 with a good CPU. I have a i9-13900K. People are creating various public local LLM's at different sizes but what about creating the highest quality LLM that uses every last bit of available VRam of a 4090. ... | 2023-09-27T20:13:25 | https://www.reddit.com/r/LocalLLaMA/comments/16tupcu/opinion_regarding_the_optimal_model/ | Guilty-History-9249 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 16tupcu | false | null | t3_16tupcu | /r/LocalLLaMA/comments/16tupcu/opinion_regarding_the_optimal_model/ | false | false | self | 3 | null |
Can I fine tune llama 2 using instructions instead of examples? | 2 | I have looked at a number of fine tuning examples, but it seems like they are always using examples input/output to fine tune.
I have a rather long and complex prompt that I use together with data to be processed by my normal (not fine tuned model) and I would like to not have to send the long set of instructions eve... | 2023-09-27T20:13:22 | https://www.reddit.com/r/LocalLLaMA/comments/16tupbc/can_i_fine_tune_llama_2_using_instructions/ | trollbrot | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 16tupbc | false | null | t3_16tupbc | /r/LocalLLaMA/comments/16tupbc/can_i_fine_tune_llama_2_using_instructions/ | false | false | self | 2 | null |
AI details from Meta Keynote Day 1. | 75 | Mark Zuckerberg;
New Image generation model from Meta called Emu
Meta version of ChatGPT, with internet access.
CharacterAI-like Agents, specifically mentions "entertainment", goes on to mention roleplaying, and a dungeon master bot.
AI Studio, a platform for creating AI like the official ones that Meta has made. M... | 2023-09-27T19:24:50 | https://www.reddit.com/r/LocalLLaMA/comments/16ttg6b/ai_details_from_meta_keynote_day_1/ | New_Hope3181 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 16ttg6b | false | null | t3_16ttg6b | /r/LocalLLaMA/comments/16ttg6b/ai_details_from_meta_keynote_day_1/ | false | false | self | 75 | null |
How to run ExLLama in python notebooks? | 3 | Currently I am making API calls to the huggingface llama-2 model for my project and am getting around 5t/s. I understand that it can be improved by using exllama but can't find any code samples on how to do that. The github repo simply mentions about the UI which uses exllama but how can I replace the huggingface trans... | 2023-09-27T18:12:51 | https://www.reddit.com/r/LocalLLaMA/comments/16trseo/how_to_run_exllama_in_python_notebooks/ | todaysgamer | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 16trseo | false | null | t3_16trseo | /r/LocalLLaMA/comments/16trseo/how_to_run_exllama_in_python_notebooks/ | false | false | self | 3 | null |
VideoDirectorGPT: Consistent multi-scene video generation that uses the knowledge of LLMs | 22 | 2023-09-27T17:52:48 | https://arxiv.org/abs/2309.15091 | ptitrainvaloin | arxiv.org | 1970-01-01T00:00:00 | 0 | {} | 16trbqs | false | null | t3_16trbqs | /r/LocalLLaMA/comments/16trbqs/videodirectorgpt_consistent_multiscene_video/ | false | false | default | 22 | null | |
OS 7B Mistral Model | 3 | 2023-09-27T17:27:53 | https://x.com/ClementDelangue/status/1707075741651804208?s=20 | ninjasaid13 | x.com | 1970-01-01T00:00:00 | 0 | {} | 16tqoqf | false | null | t3_16tqoqf | /r/LocalLLaMA/comments/16tqoqf/os_7b_mistral_model/ | false | false | 3 | {'enabled': False, 'images': [{'id': 'Ql6Uhi1ucq0p1LecKBaF2vKE6WhhgruMXNCZX_ebdrI', 'resolutions': [{'height': 108, 'url': 'https://external-preview.redd.it/iYL2KjzDqZ-uf7_-ABr5NIM1MXm3-PF5RUF_afgf814.jpg?width=108&crop=smart&auto=webp&s=e09562bcb08a7f0919dfd19796df158644359a47', 'width': 108}], 'source': {'height': 20... | ||
Model with unlimited finetuning resources but inference limitations? | 3 | I am planning on finetuning a llama-70b-chat model for my specific use case. For the finetuning stage I can rent AWS servers, but where I'm limited is inference, where I have 8xV100 gpus at my disposal. Basically, I need fast inference over sequence that never exceed \~2000 tokens, running multiple models at the same t... | 2023-09-27T16:45:03 | https://www.reddit.com/r/LocalLLaMA/comments/16tpkiq/model_with_unlimited_finetuning_resources_but/ | Mountain_Lobster5511 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 16tpkiq | false | null | t3_16tpkiq | /r/LocalLLaMA/comments/16tpkiq/model_with_unlimited_finetuning_resources_but/ | false | false | self | 3 | null |
9 Open Source LLMs and Agents to Watch | 1 | [removed] | 2023-09-27T16:13:08 | https://www.reddit.com/r/LocalLLaMA/comments/16toqno/9_open_source_llms_and_agents_to_watch/ | Data_Nerd1979 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 16toqno | false | null | t3_16toqno | /r/LocalLLaMA/comments/16toqno/9_open_source_llms_and_agents_to_watch/ | false | false | self | 1 | {'enabled': False, 'images': [{'id': 'ZH0Gz73guD-UAkjerWMHdpIjSueUYRLBGpyMGqN_iTk', 'resolutions': [{'height': 50, 'url': 'https://external-preview.redd.it/FN3hFG1-16k-KiKfARSQ6D0Xr9LLy2oCTnOXQ5YhbEo.jpg?width=108&crop=smart&auto=webp&s=743dad60ed61c37c1f7124e5482ee49a3011123e', 'width': 108}, {'height': 101, 'url': 'h... |
We built Beam: An ultrafast serverless GPU runtime | 1 | [removed] | 2023-09-27T15:55:26 | https://www.reddit.com/r/LocalLLaMA/comments/16to9rg/we_built_beam_an_ultrafast_serverless_gpu_runtime/ | velobro | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 16to9rg | false | null | t3_16to9rg | /r/LocalLLaMA/comments/16to9rg/we_built_beam_an_ultrafast_serverless_gpu_runtime/ | false | false | self | 1 | {'enabled': False, 'images': [{'id': 'TeeNqkrWBNh1JrFhPM2IXUB-2e8G2FFKKXkAMVEbKqA', 'resolutions': [{'height': 56, 'url': 'https://external-preview.redd.it/ZUXZni5hfI2l8JwI40R32J6ggHwz1wSuLe4KaSiLYn4.jpg?width=108&crop=smart&auto=webp&s=c3d57176345f8446cfe6b731a23ed08dfcf38837', 'width': 108}, {'height': 113, 'url': 'h... |
Need Feedback on Agent Framework | 1 | [removed] | 2023-09-27T15:38:52 | https://www.reddit.com/r/LocalLLaMA/comments/16tnus5/need_feedback_on_agent_framework/ | libraryofcelsus | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 16tnus5 | false | null | t3_16tnus5 | /r/LocalLLaMA/comments/16tnus5/need_feedback_on_agent_framework/ | false | false | self | 1 | {'enabled': False, 'images': [{'id': 'qePlJiYaje-kX_1e9KpN1e0EcevGzYtWWDh6vwyR3wk', 'resolutions': [{'height': 54, 'url': 'https://external-preview.redd.it/X5Ip_TJtZqfhQ4P6obMt9mUkShuRkV_wcEdXyvG28GI.jpg?width=108&crop=smart&auto=webp&s=8374e4e316ca0e8cd9a4946cfe56399475be7bdd', 'width': 108}, {'height': 108, 'url': 'h... |
Mistral 7B releases with claims of outperforming larger models | 262 | Claims as follows:
1. Outperforms Llama 2 13B on all benchmarks
2. Outperforms Llama 1 34B on many benchmarks
3. Approaches CodeLlama 7B performance on code, while remaining good at English tasks
https://mistral.ai/news/announcing-mistral-7b/ | 2023-09-27T15:35:35 | https://www.reddit.com/r/LocalLLaMA/comments/16tnrpm/mistral_7b_releases_with_claims_of_outperforming/ | abybaddi009 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 16tnrpm | false | null | t3_16tnrpm | /r/LocalLLaMA/comments/16tnrpm/mistral_7b_releases_with_claims_of_outperforming/ | false | false | self | 262 | null |
I fine-tuned a model but when running inference it just repeats the prompt for its output | 1 | [removed] | 2023-09-27T15:31:23 | https://www.reddit.com/r/LocalLLaMA/comments/16tnnvp/i_finetuned_a_model_but_when_running_inference_it/ | thinkingdots | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 16tnnvp | false | null | t3_16tnnvp | /r/LocalLLaMA/comments/16tnnvp/i_finetuned_a_model_but_when_running_inference_it/ | false | false | self | 1 | null |
Llama2 (original) vs llama2 (quantised) performance | 6 | Hi guys, i do not have GPUs and can work only on free version of google colab gpu (T4)
I just wanted to understand if is there any source where I came compare the performance in results for llama2 vs llama2 quantised models.
I can only try out 7B and 13 B (8/4/5 bits etc).
So how much is the trade off between real vs... | 2023-09-27T14:49:50 | https://www.reddit.com/r/LocalLLaMA/comments/16tmmcb/llama2_original_vs_llama2_quantised_performance/ | ianuvrat | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 16tmmcb | false | null | t3_16tmmcb | /r/LocalLLaMA/comments/16tmmcb/llama2_original_vs_llama2_quantised_performance/ | false | false | self | 6 | null |
Model trained on medical data | 7 | Is there any model besides medalpaca that is trained on medical data?
I tried thebloke's 13b Q5 quantized variant of medalpaca but for some reason I only get gibberish. | 2023-09-27T14:40:09 | https://www.reddit.com/r/LocalLLaMA/comments/16tmds6/model_trained_on_medical_data/ | Typical-Armadillo340 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 16tmds6 | false | null | t3_16tmds6 | /r/LocalLLaMA/comments/16tmds6/model_trained_on_medical_data/ | false | false | self | 7 | null |
How to Run LLM Models on GPU-enabled Local Servers and Use API Services to Access Them from CPU-only Computers in LAN | 5 | Is it possible to deploy an LLM model to a local computer (server) with RTX 4090 and provide API services, and then use a computer that only has CPU to access the server model? (Only python if possible, thanks.)🙂 | 2023-09-27T14:22:02 | https://www.reddit.com/r/LocalLLaMA/comments/16tlyc1/how_to_run_llm_models_on_gpuenabled_local_servers/ | Mochunnian | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 16tlyc1 | false | null | t3_16tlyc1 | /r/LocalLLaMA/comments/16tlyc1/how_to_run_llm_models_on_gpuenabled_local_servers/ | false | false | self | 5 | null |
Cannot load GGUF model - invalid magic number ? | 4 | Today I managed to build llama.cpp on Android with termux (F-Droid).
I tried out to run llama.cpp main executable now with the Xwin 7B (4-bit quantized) model, downloaded from
[https://huggingface.co/TheBloke/Xwin-LM-7B-V0.1-GGUF/blob/main/xwin-lm-7b-v0.1.Q4\_0.gguf](https://huggingface.co/TheBloke/Xwin-LM-7B-V0.1-... | 2023-09-27T14:03:07 | https://www.reddit.com/r/LocalLLaMA/comments/16tlhg7/cannot_load_gguf_model_invalid_magic_number/ | Fit_Check_919 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 16tlhg7 | false | null | t3_16tlhg7 | /r/LocalLLaMA/comments/16tlhg7/cannot_load_gguf_model_invalid_magic_number/ | false | false | 4 | {'enabled': False, 'images': [{'id': 'qHF6z0VgAPmgjD_377P7ukswa6IGLtI1a0ZGfZct0QI', 'resolutions': [{'height': 58, 'url': 'https://external-preview.redd.it/TkJNEnsQoMp8S5xgdv0d6Z33sX3SeSYLz5mMzjOXB3s.jpg?width=108&crop=smart&auto=webp&s=82150fe21ed44cef43a8d9fcb15cfd2fbcc0d0c8', 'width': 108}, {'height': 116, 'url': 'h... | |
What are the problems faced when an AI customer support chatbot is used by a SaaS business. | 2 | What exactly are all the problems/possible problems faced while using and incorporating an AI customer support chatbot by small to medium sized SaaS businesses in USA/Europe/etc.
Since am learning how to build AI chatbots and want to sell them to SaaS businesses. | 2023-09-27T12:22:12 | https://www.reddit.com/r/LocalLLaMA/comments/16tj40a/what_are_the_problems_faced_when_an_ai_customer/ | arxavsx | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 16tj40a | false | null | t3_16tj40a | /r/LocalLLaMA/comments/16tj40a/what_are_the_problems_faced_when_an_ai_customer/ | false | false | self | 2 | null |
Could merging finetunes be part of Chatgpt's secret sauce? | 14 | After the dramatic surprises of speechless-llama2-hermes-orca-platypus-wizardlm-13b
https://www.reddit.com/r/LocalLLaMA/comments/16s701v/this_is_one_of_the_best_13b_models_ive_tested_for/
In at least the whole Shakespearean sonnet writing area (and also general storytelling I feel) this model seems to punch so far a... | 2023-09-27T11:35:26 | https://www.reddit.com/r/LocalLLaMA/comments/16ti59p/could_merging_finetunes_be_part_of_chatgpts/ | ambient_temp_xeno | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 16ti59p | false | null | t3_16ti59p | /r/LocalLLaMA/comments/16ti59p/could_merging_finetunes_be_part_of_chatgpts/ | false | false | self | 14 | null |
Exllamav2 Performance With Different Quantization Levels | 24 | When we discuss quantization, we often only refer to it in terms of perplexity. I thought it would be interesting to explore the impact of quantization levels on an actual benchmark such as MMLU.
I quantized the model at 9 different levels for the 7b and 13b models using the exllamav2 quantizer. I also added theBloke/... | 2023-09-27T10:34:37 | https://www.reddit.com/r/LocalLLaMA/comments/16tgzzk/exllamav2_performance_with_different_quantization/ | a_slay_nub | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 16tgzzk | false | null | t3_16tgzzk | /r/LocalLLaMA/comments/16tgzzk/exllamav2_performance_with_different_quantization/ | false | false | self | 24 | {'enabled': False, 'images': [{'id': 'uE0hLPujxfcSKvFsxSzlOF_wtxb7x70gyELBHvLpNhs', 'resolutions': [{'height': 56, 'url': 'https://external-preview.redd.it/sXHbuwLgNM3yAEZAijHOlVvoIZGqQoxHidp15fzPY9A.jpg?width=108&crop=smart&auto=webp&s=2ed992105b4540a7774013bedebc92f5117ffaab', 'width': 108}, {'height': 113, 'url': 'h... |
Introducing QA-LoRA - Quantization-aware low-rank adaptation of LLMs | 102 | Fascinating new method from Qi Tian et al that combines parameter efficient fine-tuning (used in LoRAs) with parameter quantization in a new way with major efficiency gains - lower computation, faster inference, lower memory requirements.
[Paper page - QA-LoRA: Quantization-Aware Low-Rank Adaptation of Large Language ... | 2023-09-27T10:28:09 | https://www.reddit.com/r/LocalLLaMA/comments/16tgvtc/introducing_qalora_quantizationaware_lowrank/ | PookaMacPhellimen | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 16tgvtc | false | null | t3_16tgvtc | /r/LocalLLaMA/comments/16tgvtc/introducing_qalora_quantizationaware_lowrank/ | false | false | 102 | {'enabled': False, 'images': [{'id': '1GQs9IczKgKpajvf4Kpt_pWpRFCJ13n8AoJ92xkMtPo', 'resolutions': [{'height': 58, 'url': 'https://external-preview.redd.it/KvpQba2n4h-oBaOcbfnwSdmFyyFbIhXduBj9WTfEtZU.jpg?width=108&crop=smart&auto=webp&s=5de1aa1326e1adb90623a8fe46d23cdec07b3c20', 'width': 108}, {'height': 116, 'url': 'h... | |
ChatGPT fine-tuning vs Open LLM fine-tuning | 1 | Hi everyone,
I am especially interested in your experience of comparing ChatGPT fine-tuning with Open LLM fine-tuning
What are your experiences, advantages and bottlenecks for both technologies?
What could you achieve with one that you could not achieve with the other? Why did you decide for one technology in the e... | 2023-09-27T09:40:26 | https://www.reddit.com/r/LocalLLaMA/comments/16tg3v0/chatgpt_finetuning_vs_open_llm_finetuning/ | ComplexIt | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 16tg3v0 | false | null | t3_16tg3v0 | /r/LocalLLaMA/comments/16tg3v0/chatgpt_finetuning_vs_open_llm_finetuning/ | false | false | self | 1 | null |
How useful is ChatGPT Finetuning compared to Open LLM fine tuning | 1 | Hi everyone,
I am especially interested in your experience of comparing ChatGPT Finetuning with Open LLM fine tuning
What are your experiences, advantages and bottlenecks for both technologies? | 2023-09-27T09:38:07 | https://www.reddit.com/r/LocalLLaMA/comments/16tg2j9/how_useful_is_chatgpt_finetuning_compared_to_open/ | ComplexIt | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 16tg2j9 | false | null | t3_16tg2j9 | /r/LocalLLaMA/comments/16tg2j9/how_useful_is_chatgpt_finetuning_compared_to_open/ | false | false | self | 1 | null |
Looking for some guidance and get a basic knowledge regarding the branches in GPTQ models. | 5 | So I have a lot of questions. I am currently just using the quantized models by loading them, but now I want to know how exactly different branches are actually different. I see names like exllama, llama.cpp, Actorder, 128g etc. I do not know which one is suitable for me or what to use. I am not sure if 13B is actually... | 2023-09-27T09:13:58 | https://www.reddit.com/r/LocalLLaMA/comments/16tfp17/looking_for_some_guidance_and_get_a_basic/ | IamFuckinTomato | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 16tfp17 | false | null | t3_16tfp17 | /r/LocalLLaMA/comments/16tfp17/looking_for_some_guidance_and_get_a_basic/ | false | false | self | 5 | null |
MistralAI-0.1-7B, the first release from Mistral, dropped just like this on X (raw magnet link; use a torrent client) | 144 | 2023-09-27T08:37:41 | https://twitter.com/MistralAI/status/1706877320844509405 | Ilforte | twitter.com | 1970-01-01T00:00:00 | 0 | {} | 16tf4qn | false | {'oembed': {'author_name': 'Mistral AI', 'author_url': 'https://twitter.com/MistralAI', 'cache_age': 3153600000, 'height': None, 'html': '<blockquote class="twitter-video"><p lang="en" dir="ltr">magnet:?xt=urn:btih:208b101a0f51514ecf285885a8b0f6fb1a1e4d7d&dn=mistral-7B-v0.1&tr=udp%3A%2F%<a href="https://t.co/Od... | t3_16tf4qn | /r/LocalLLaMA/comments/16tf4qn/mistralai017b_the_first_release_from_mistral/ | false | false | 144 | {'enabled': False, 'images': [{'id': 'CS0B1I30ZYj0ZX-zyY6FLZvd72xR9WPR7HDTGHV8oJU', 'resolutions': [{'height': 108, 'url': 'https://external-preview.redd.it/5sqkwEMzIqqPNtzrB1t5XsvpUZjwXad14Gcaj40q5TI.jpg?width=108&crop=smart&auto=webp&s=60a70155bda3574ef1569e82bff7884074c1b383', 'width': 108}], 'source': {'height': 14... | ||
storage as ram | 1 | I don't have enough ram to run large models but I know there is an option to use storage as ram. Could it work even if it would just be much slower? | 2023-09-27T08:28:21 | https://www.reddit.com/r/LocalLLaMA/comments/16tezbu/storage_as_ram/ | Terrible_Vegetable4 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 16tezbu | false | null | t3_16tezbu | /r/LocalLLaMA/comments/16tezbu/storage_as_ram/ | false | false | self | 1 | null |
Another test to see if I can make top level posts yet | 1 | [removed] | 2023-09-27T08:24:34 | https://www.reddit.com/r/LocalLLaMA/comments/16texau/another_test_to_see_if_i_can_make_top_level_posts/ | MrEloi | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 16texau | false | null | t3_16texau | /r/LocalLLaMA/comments/16texau/another_test_to_see_if_i_can_make_top_level_posts/ | false | false | self | 1 | null |
Local llm agents eg local auto gpt a thing yet? | 0 | Question in the title basically. Haven't really been keeping up to date since April/may. Wondering if one can use llm agents locally in functions akin to auto gpt eg automatically | 2023-09-27T08:17:19 | https://www.reddit.com/r/LocalLLaMA/comments/16teta9/local_llm_agents_eg_local_auto_gpt_a_thing_yet/ | Maelstrom100 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 16teta9 | false | null | t3_16teta9 | /r/LocalLLaMA/comments/16teta9/local_llm_agents_eg_local_auto_gpt_a_thing_yet/ | false | false | self | 0 | null |
Why Weightdecay is set to zero when finetune LLM? | 6 | I found that all long context models are finetune with weightdecay equals zero. Anyone knows why?
[http://arxiv.org/abs/2309.12307](http://arxiv.org/abs/2309.12307)
[http://arxiv.org/abs/2309.00071](http://arxiv.org/abs/2309.00071) | 2023-09-27T08:03:08 | https://www.reddit.com/r/LocalLLaMA/comments/16telcc/why_weightdecay_is_set_to_zero_when_finetune_llm/ | Mountain-Run-5602 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 16telcc | false | null | t3_16telcc | /r/LocalLLaMA/comments/16telcc/why_weightdecay_is_set_to_zero_when_finetune_llm/ | false | false | self | 6 | {'enabled': False, 'images': [{'id': 'q3evP6JeDpAC2MdSQHWYxnCYTqbJkElIQsLFqVSdkss', 'resolutions': [{'height': 63, 'url': 'https://external-preview.redd.it/izh8gZHY4FqZ1nwtU1N_TjtohUCNuvTyMn90toXda80.jpg?width=108&crop=smart&auto=webp&s=bc9575b410002edc2df3c5b5b0355fefedc7baa8', 'width': 108}, {'height': 126, 'url': 'h... |
Loading LLaMA2-70B model | 8 | Hi All,
I'm trying to load LLaMA2-70B model, with following GPU specs:
https://pastebin.com/vjbWpP7C
Basically, I have two a40 machines, and was using this (https://discuss.huggingface.co/t/how-to-load-large-model-with-multiple-gpu-cards/18522/8) code to make it work,
```python
model = AutoModelForCausalLM.from_pret... | 2023-09-27T07:11:42 | https://www.reddit.com/r/LocalLLaMA/comments/16tdrot/loading_llama270b_model/ | 1azytux | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 16tdrot | false | null | t3_16tdrot | /r/LocalLLaMA/comments/16tdrot/loading_llama270b_model/ | false | false | self | 8 | {'enabled': False, 'images': [{'id': 'OgFzGCIRw1ZxjMOSkfV1OiH-_nQiZl8rzSonmOAuhGs', 'resolutions': [{'height': 108, 'url': 'https://external-preview.redd.it/P8lS0kk6BFe2IEo6TxCZd1LVwksc34IkzGTVx_SCc8w.jpg?width=108&crop=smart&auto=webp&s=3d74dbe4f1d67cc8b587db9aa01762f26e269bcf', 'width': 108}], 'source': {'height': 15... |
LlamaTor: A New Initiative for BitTorrent-Based AI Model Distribution | 1 | 2023-09-27T06:18:56 | https://github.com/Nondzu/LlamaTor | Nondzu | github.com | 1970-01-01T00:00:00 | 0 | {} | 16tcv1u | false | null | t3_16tcv1u | /r/LocalLLaMA/comments/16tcv1u/llamator_a_new_initiative_for_bittorrentbased_ai/ | false | false | 1 | {'enabled': False, 'images': [{'id': 'RjJWztBiFGWSiX83fH3_kau7edsk9G7G5e6O7I6Yv9o', 'resolutions': [{'height': 54, 'url': 'https://external-preview.redd.it/KMyRwkBosF8pXwu5XX6ZyCplk8kLcSgi8Tm3jyzE1OM.jpg?width=108&crop=smart&auto=webp&s=a1e94f2a1dde4342b077bc220e69f48c13683c9d', 'width': 108}, {'height': 108, 'url': 'h... | ||
Jetson nano 4gb | 1 | Any new optimized or new techniques to get models like LLama or Falcon on jetson nano 4gb ? 🥹😅 | 2023-09-27T04:35:15 | https://www.reddit.com/r/LocalLLaMA/comments/16tavjo/jetson_nano_4gb/ | Plane_Ad9568 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 16tavjo | false | null | t3_16tavjo | /r/LocalLLaMA/comments/16tavjo/jetson_nano_4gb/ | false | false | self | 1 | null |
What's your favorite RAG system and why? Langchain, LlamaIndex, etc? | 61 | Just trying to understand the latest landscape of RAGs out there.
Thanks! | 2023-09-27T04:28:09 | https://www.reddit.com/r/LocalLLaMA/comments/16taq8m/whats_your_favorite_rag_system_and_why_langchain/ | jl303 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 16taq8m | false | null | t3_16taq8m | /r/LocalLLaMA/comments/16taq8m/whats_your_favorite_rag_system_and_why_langchain/ | false | false | self | 61 | null |
Finetune Llm on amd gpu rx 580 | 2 | So i intend to finetune llama2 for a specific usecase i can already use koboldcpp and opencl to run it but hiw do i finetune it i literally cant find any info about this online | 2023-09-27T03:29:46 | https://www.reddit.com/r/LocalLLaMA/comments/16t9ihy/finetune_llm_on_amd_gpu_rx_580/ | GOD_HIMSELVES | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 16t9ihy | false | null | t3_16t9ihy | /r/LocalLLaMA/comments/16t9ihy/finetune_llm_on_amd_gpu_rx_580/ | false | false | self | 2 | null |
Fine tune LLaMa for code generation, seek suggestion. | 4 |
Hello, want to get an idea from you guys if this is a reasonable approach.
Problem statement: on daily basis, I need to create one code file and one unit test file. The code file follows a very specific format. And the unit test does the testing. Both files are in python. I want to use a fine tuned LLM to generate... | 2023-09-27T02:04:02 | https://www.reddit.com/r/LocalLLaMA/comments/16t7la1/fine_tune_llama_for_code_generation_seek/ | Renspire | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 16t7la1 | false | null | t3_16t7la1 | /r/LocalLLaMA/comments/16t7la1/fine_tune_llama_for_code_generation_seek/ | false | false | self | 4 | null |
Is 7900xtx ok to run llm | 1 | Would AMD gpu be a choice today? | 2023-09-27T00:55:00 | https://www.reddit.com/r/LocalLLaMA/comments/16t5xni/is_7900xtx_ok_to_run_llm/ | Willing_Citron_2894 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 16t5xni | false | null | t3_16t5xni | /r/LocalLLaMA/comments/16t5xni/is_7900xtx_ok_to_run_llm/ | false | false | self | 1 | null |
Tips for no GPU? | 13 | Does anyone have any tips and tricks for people trying to run Llama locally without a GPU?
What about a torrent solution like Petals? Please share your any insights and knowledge. | 2023-09-27T00:24:46 | https://www.reddit.com/r/LocalLLaMA/comments/16t57xn/tips_for_no_gpu/ | kecepa5669 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 16t57xn | false | null | t3_16t57xn | /r/LocalLLaMA/comments/16t57xn/tips_for_no_gpu/ | false | false | self | 13 | null |
A Quick Guide to Getting Started with LLMs | 1 | [removed] | 2023-09-26T23:39:31 | https://www.reddit.com/r/LocalLLaMA/comments/16t44bj/a_quick_guide_to_getting_started_with_llms/ | MrChristoCoder | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 16t44bj | false | null | t3_16t44bj | /r/LocalLLaMA/comments/16t44bj/a_quick_guide_to_getting_started_with_llms/ | false | false | self | 1 | {'enabled': False, 'images': [{'id': '_rEX1xvwdv17x6NFAWQpYFNONQ0BKA5Qw0Eo0JX0zWU', 'resolutions': [{'height': 58, 'url': 'https://external-preview.redd.it/OFWu5qxCY4R2hQfI_vzWYgK2ON5meupO-ZR0eRPmsP8.jpg?width=108&crop=smart&auto=webp&s=4bc231a80d79babe4e6cddf7b4c71dcb0aa8f8ff', 'width': 108}, {'height': 116, 'url': 'h... |
Need Feedback on Ai Agent Framework | 1 | [removed] | 2023-09-26T22:24:29 | https://www.reddit.com/r/LocalLLaMA/comments/16t2718/need_feedback_on_ai_agent_framework/ | libraryofcelsus | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 16t2718 | false | null | t3_16t2718 | /r/LocalLLaMA/comments/16t2718/need_feedback_on_ai_agent_framework/ | false | false | self | 1 | {'enabled': False, 'images': [{'id': 'C9eyCZK6YrjCI-CrNHdBphDEtLudNTehIWN5PDPU2mg', 'resolutions': [{'height': 54, 'url': 'https://external-preview.redd.it/rxT4qAuPjdxp8K89lzFYOsKff2k8Pl_J3OgAQHd8jwI.jpg?width=108&crop=smart&auto=webp&s=c38df96bf8dc53f1867f1673171a6f0c8fb14a99', 'width': 108}, {'height': 108, 'url': 'h... |
Experimenting with Humanizing ChatGPT text using LLama. | 1 | 2023-09-26T22:20:29 | FPham | i.redd.it | 1970-01-01T00:00:00 | 0 | {} | 16t22yb | false | null | t3_16t22yb | /r/LocalLLaMA/comments/16t22yb/experimenting_with_humanizing_chatgpt_text_using/ | false | false | 1 | {'enabled': True, 'images': [{'id': 'G3n-uYTnUJPSEvoLtZqFes63VS5lXLuxBc-gDUnBLOs', 'resolutions': [{'height': 49, 'url': 'https://preview.redd.it/ez24w5fadoqb1.jpg?width=108&crop=smart&auto=webp&s=7c46c851fc8b6882b569522852b7592c1c1518b1', 'width': 108}, {'height': 98, 'url': 'https://preview.redd.it/ez24w5fadoqb1.jpg?... | |||
What’s the best LLM for private Transcription of Audio files? | 1 | [removed] | 2023-09-26T21:35:02 | https://www.reddit.com/r/LocalLLaMA/comments/16t0t5l/whats_the_best_llm_for_private_transcription_of/ | NewportNerds | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 16t0t5l | false | null | t3_16t0t5l | /r/LocalLLaMA/comments/16t0t5l/whats_the_best_llm_for_private_transcription_of/ | false | false | self | 1 | null |
Best model to run locally on an Android phone? | 44 | 2023-09-26T21:27:17 | Ok-Recognition-3177 | i.redd.it | 1970-01-01T00:00:00 | 0 | {} | 16t0lbw | false | null | t3_16t0lbw | /r/LocalLLaMA/comments/16t0lbw/best_model_to_run_locally_on_an_android_phone/ | false | false | 44 | {'enabled': True, 'images': [{'id': '5LPNcYRwSIJ5sFAIhHUF9q0T84RqttMxOPYzzoLiSfU', 'resolutions': [{'height': 93, 'url': 'https://preview.redd.it/jp7pqlzr3oqb1.png?width=108&crop=smart&auto=webp&s=2d6b6ff43a98322a7fabbe0bd6cae840e70afbb8', 'width': 108}, {'height': 186, 'url': 'https://preview.redd.it/jp7pqlzr3oqb1.png... | |||
Comparing the Parallel AI Universes - Smallville vs AI Town | 2 | 2023-09-26T20:57:11 | https://querystar.io/blog/ai-town | DearWave | querystar.io | 1970-01-01T00:00:00 | 0 | {} | 16szr9j | false | null | t3_16szr9j | /r/LocalLLaMA/comments/16szr9j/comparing_the_parallel_ai_universes_smallville_vs/ | false | false | 2 | {'enabled': False, 'images': [{'id': '2LCPTOV_XM-6fq4aK28guSZ6TqS-ezgq9sv8E-5bK9w', 'resolutions': [{'height': 56, 'url': 'https://external-preview.redd.it/qvhjTB1qfbtmQPtBzEfSbt33UIXFByokUQ6FOZEDzDs.jpg?width=108&crop=smart&auto=webp&s=d6bfb8985581038455ece432af5767aecfc62f78', 'width': 108}, {'height': 113, 'url': 'h... | ||
I plan to run LLaMA on the browser, what vectordb should I use? | 4 | Hey! So I want to create a website where I'll run LLaMA, but I am not sure regarding which DB do I want to use to store the results and all the data.
Ideally it should be a tool to kinda store data without backend if this is even possible, lol. And be able to semantically search through it.
I am not really familiar ... | 2023-09-26T20:39:14 | https://www.reddit.com/r/LocalLLaMA/comments/16sza4f/i_plan_to_run_llama_on_the_browser_what_vectordb/ | Robert-treboR | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 16sza4f | false | null | t3_16sza4f | /r/LocalLLaMA/comments/16sza4f/i_plan_to_run_llama_on_the_browser_what_vectordb/ | false | false | self | 4 | null |
LaMini has been using AMD GPU in production for the past year | 22 | Sharon Zhou just shared this funny [revelation](https://twitter.com/realSharonZhou/status/1706708589837254946?t=UlkwBHI72r_1dZ-cw0blJA&s=19).
Seems like AMD is actually a thing for LLM in production. | 2023-09-26T19:55:53 | https://www.reddit.com/r/LocalLLaMA/comments/16sy3ic/lamini_has_been_using_amd_gpu_in_production_for/ | No_Palpitation7740 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 16sy3ic | false | null | t3_16sy3ic | /r/LocalLLaMA/comments/16sy3ic/lamini_has_been_using_amd_gpu_in_production_for/ | false | false | self | 22 | {'enabled': False, 'images': [{'id': 'I8vWJynmK66Chqg7a2jmStUeQiA5R0a6wrF-CkP2_n8', 'resolutions': [{'height': 192, 'url': 'https://external-preview.redd.it/BnPCwn7-9cGv-2zM2ODcOWUP6kpsIqCaivnFtta3B4g.jpg?width=108&crop=smart&auto=webp&s=f6152f999a92467a8e1c4b691fc9c2e1a8184b23', 'width': 108}, {'height': 384, 'url': '... |
Add new knowledge to LLama2 | 14 |
I am planning on building my personal assistant based on the LLama2 model. I want the model to know about my personal information, like hobbies, family, and close friends. So I created a dolly-format dataset full of conversations between me and the model. The result I got is that the model only correctly generates 6... | 2023-09-26T19:34:10 | https://www.reddit.com/r/LocalLLaMA/comments/16sxiop/add_new_knowledge_to_llama2/ | Capital_Birthday_654 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 16sxiop | false | null | t3_16sxiop | /r/LocalLLaMA/comments/16sxiop/add_new_knowledge_to_llama2/ | false | false | self | 14 | null |
How does The Bloke quantize models? | 1 | [removed] | 2023-09-26T19:33:04 | https://www.reddit.com/r/LocalLLaMA/comments/16sxhqq/how_does_the_bloke_quantize_models/ | Ender436 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 16sxhqq | false | null | t3_16sxhqq | /r/LocalLLaMA/comments/16sxhqq/how_does_the_bloke_quantize_models/ | false | false | self | 1 | null |
How is MMLU calculated? | 9 | I saw that exllamav2 had a MMLU calculation and wanted to know how the official MMLU was calculated. It seems like I'm supposed to go through all ~50 categories, calculate performance for each category, and then take the average the results?
Initially, I had left out 3 problems and just calculated the MMLU for all 14k... | 2023-09-26T18:54:21 | https://www.reddit.com/r/LocalLLaMA/comments/16swh0w/how_is_mmlu_calculated/ | a_slay_nub | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 16swh0w | false | null | t3_16swh0w | /r/LocalLLaMA/comments/16swh0w/how_is_mmlu_calculated/ | false | false | self | 9 | null |
Qwen is aligned just as you would expect | 56 | Or do you think it really doesn't know?
https://preview.redd.it/m880q6f6anqb1.png?width=1227&format=png&auto=webp&s=f28190b6fd61e312f6343b43220cf8140d8415f4 | 2023-09-26T18:41:22 | https://www.reddit.com/r/LocalLLaMA/comments/16sw4na/qwen_is_aligned_just_as_you_would_expect/ | random-string | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 16sw4na | false | null | t3_16sw4na | /r/LocalLLaMA/comments/16sw4na/qwen_is_aligned_just_as_you_would_expect/ | false | false | 56 | null | |
How to log train/val accuracy using SFT trainer? | 1 | Hi,
​
I'm using SFT trainer from HF to fine-tune a LLaMA model using PEFT. But SFT only gives me the loss and other performance-related (like timing) metrics. How can I get the training/val accuracy? I tried to use callbacks but not successful :( Could you please help me with this?
​
Here is my code:... | 2023-09-26T18:12:14 | https://www.reddit.com/r/LocalLLaMA/comments/16svcpz/how_to_log_trainval_accuracy_using_sft_trainer/ | Impossible-Froyo3412 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 16svcpz | false | null | t3_16svcpz | /r/LocalLLaMA/comments/16svcpz/how_to_log_trainval_accuracy_using_sft_trainer/ | false | false | self | 1 | null |
Local LLM that will search the Internet? | 72 | The great value in Bing Chat and Bard, over a plain chatbot, no matter how good is it, is that they're equipped with an Internet search tool that will search, then feed the AI so that it can predict a response with up-to-date, precise information it may not have been trained with. The problem is they're heavily censore... | 2023-09-26T18:01:51 | https://www.reddit.com/r/LocalLLaMA/comments/16sv2sh/local_llm_that_will_search_the_internet/ | A_for_Anonymous | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 16sv2sh | false | null | t3_16sv2sh | /r/LocalLLaMA/comments/16sv2sh/local_llm_that_will_search_the_internet/ | false | false | self | 72 | null |
I have a computer that is offline and accessible via USB. Any way to drop in the LLM? | 1 | WSL sounded good until I gave up hand copying .debs for make, gcc, gcc-12, and cpp..
Not sure what my options are. | 2023-09-26T17:46:12 | https://www.reddit.com/r/LocalLLaMA/comments/16sunag/i_have_a_computer_that_is_offline_and_accessible/ | pr1vacyn0eb | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 16sunag | false | null | t3_16sunag | /r/LocalLLaMA/comments/16sunag/i_have_a_computer_that_is_offline_and_accessible/ | false | false | self | 1 | null |
EasyEdit: An Easy-to-use Knowledge Editing Framework for LLMs. | 33 | 2023-09-26T17:44:48 | https://github.com/zjunlp/EasyEdit | AutomataManifold | github.com | 1970-01-01T00:00:00 | 0 | {} | 16sulqm | false | null | t3_16sulqm | /r/LocalLLaMA/comments/16sulqm/easyedit_an_easytouse_knowledge_editing_framework/ | false | false | 33 | {'enabled': False, 'images': [{'id': 'fhMHZVe6_o_Rka-ESuRRHmQkl8oug7pKcLUqNPLzvWM', 'resolutions': [{'height': 54, 'url': 'https://external-preview.redd.it/HXoTnWtvAS4kiNPChhrVCwvFvcYTlenWsfz5k0XtleI.jpg?width=108&crop=smart&auto=webp&s=1b9506e04db4e830584e54a5ff8199e2afb9de66', 'width': 108}, {'height': 108, 'url': 'h... | ||
Progress on Reproducing Phi-1/1.5 | 87 | Hey All,
Just wanted to share that I am churning out a large dataset that is meant to \~reproduce the synthetic textbook dataset that Microsoft used to train phi-1.5. I'm currently generating \~1bn tokens / day and will be continually streaming the results here - [https://huggingface.co/datasets/emrgnt-cmplxty/sciphi... | 2023-09-26T17:24:56 | https://www.reddit.com/r/LocalLLaMA/comments/16su32p/progress_on_reproducing_phi115/ | docsoc1 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 16su32p | false | null | t3_16su32p | /r/LocalLLaMA/comments/16su32p/progress_on_reproducing_phi115/ | false | false | self | 87 | {'enabled': False, 'images': [{'id': 'SRQqCJLLBWenZA-Vk4NmfhLIYoGP4qO_YhRZNcIHsgE', 'resolutions': [{'height': 58, 'url': 'https://external-preview.redd.it/TlN8fXuhzoMraEjoxJnMTjZpAcekJV--nUQanUj8-_8.jpg?width=108&crop=smart&auto=webp&s=5c63eeb0d15d3381f0bbadec162cca2f9ed72747', 'width': 108}, {'height': 116, 'url': 'h... |
How to Approach LLM Learning with Career Development in Mind? | 8 | Hey folks!
I'm a data scientist by trade, and I want to pivot my career towards LLM development for private companies in anticipation of that transition (with the understanding that this is still a very new field).
I've seen a few job postings, but there are obviously no certifications in this space yet.
Where shoul... | 2023-09-26T17:14:47 | https://www.reddit.com/r/LocalLLaMA/comments/16sttws/how_to_approach_llm_learning_with_career/ | DiamondBadge | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 16sttws | false | null | t3_16sttws | /r/LocalLLaMA/comments/16sttws/how_to_approach_llm_learning_with_career/ | false | false | self | 8 | null |
Making Food | 3 | Im hungry, there's a few random ingredients in the fridge..want to make some cheap Chinese American/Western food, and don't want to get food poisoning. Any good llms/datasets to toy with?
Do u find llama as a base model already has enough culinary information? | 2023-09-26T17:12:20 | https://www.reddit.com/r/LocalLLaMA/comments/16strqu/making_food/ | Aaaaaaaaaeeeee | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 16strqu | false | null | t3_16strqu | /r/LocalLLaMA/comments/16strqu/making_food/ | false | false | self | 3 | null |
Ollama - front-end for running local models, release v0.1.0 | 15 | 2023-09-26T17:07:59 | https://github.com/jmorganca/ollama/releases/tag/v0.1.0 | bandman614 | github.com | 1970-01-01T00:00:00 | 0 | {} | 16stnpn | false | null | t3_16stnpn | /r/LocalLLaMA/comments/16stnpn/ollama_frontend_for_running_local_models_release/ | false | false | 15 | {'enabled': False, 'images': [{'id': 'aI8JDBlabiZTdyh2CmhRcXkr-3TtsO28nAHtJiBtNpw', 'resolutions': [{'height': 54, 'url': 'https://external-preview.redd.it/0jCvrVt6I1m9dmD_mqXj2Y-BSTP6-kwaUM0E_n5XSzA.jpg?width=108&crop=smart&auto=webp&s=8f920dd8fb82a57b2d8d698d10ce34eeb60f2aa5', 'width': 108}, {'height': 108, 'url': 'h... |
Subsets and Splits
No community queries yet
The top public SQL queries from the community will appear here once available.