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 ⌀ |
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
Assessing Learning and Progress in Training with LoRa Method: A Case Study with llama2 | 3 | I am trying to overfit llama2 and understand if it's learning. To achieve this, I am training it using a single example and the LoRa method. I expect that it will learn from it—thus, the loss will decrease—and when I generate text, it will reproduce that example given only the beginning.
​
When I train the 13B... | 2023-08-09T20:37:53 | https://www.reddit.com/r/LocalLLaMA/comments/15mqrv6/assessing_learning_and_progress_in_training_with/ | GooD404 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 15mqrv6 | false | null | t3_15mqrv6 | /r/LocalLLaMA/comments/15mqrv6/assessing_learning_and_progress_in_training_with/ | false | false | self | 3 | {'enabled': False, 'images': [{'id': 'dSnK02WXdmgmsoIp5lR1xLca8kIYz6n7guVtLbmPaO0', 'resolutions': [{'height': 54, 'url': 'https://external-preview.redd.it/8n_7DTxnb5b6fTZT9_pZP9m3IYc-iFD0pokseeNBltY.jpg?width=108&crop=smart&auto=webp&s=2e732da77d05b2417646488bd3c5c0d657e11ef7', 'width': 108}, {'height': 108, 'url': 'h... |
What are the text chunking/splitting and embedding best practices for RAG applications? | 18 | I'm trying to make an LLM powered RAG application without LangChain that can answer questions about a document (pdf) and I want to know some of the strategies and libraries that you guys have used to transform your text for text embedding. I would also like to know which embedding model you used and how you dealt with ... | 2023-08-09T20:10:05 | https://www.reddit.com/r/LocalLLaMA/comments/15mq1ri/what_are_the_text_chunkingsplitting_and_embedding/ | malicious510 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 15mq1ri | false | null | t3_15mq1ri | /r/LocalLLaMA/comments/15mq1ri/what_are_the_text_chunkingsplitting_and_embedding/ | false | false | self | 18 | null |
Do LLMs take embeddings directly or is it converted to text for RAG? | 2 | Pretty much the title.
​
I want to know how LLMs answer questions based off embeddings retrieved from a vector database. To my understanding, text embeddings are just a list of numbers that represent the text's semantic meaning. How does an LLM understand these numbers if the embedding model is not the same a... | 2023-08-09T19:53:21 | https://www.reddit.com/r/LocalLLaMA/comments/15mpl6p/do_llms_take_embeddings_directly_or_is_it/ | malicious510 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 15mpl6p | false | null | t3_15mpl6p | /r/LocalLLaMA/comments/15mpl6p/do_llms_take_embeddings_directly_or_is_it/ | false | false | self | 2 | null |
Best model for text generation in low-end computers? | 10 | I need to implement text generation into a program that is already a bit VRAM heavy, in order to be usable for the maximum number of users, what would be some good performing small models that don't need much VRAM (maybe 2-4 GB) and respond decently fast? | 2023-08-09T19:06:07 | https://www.reddit.com/r/LocalLLaMA/comments/15moc8z/best_model_for_text_generation_in_lowend_computers/ | Valevergus | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 15moc8z | false | null | t3_15moc8z | /r/LocalLLaMA/comments/15moc8z/best_model_for_text_generation_in_lowend_computers/ | false | false | self | 10 | null |
Sharding LLMs | 3 | I have been wondering about this for a few days now and haven't been able to find much information on the how-to. I'm trying to fine-tune the Aguila HuggingFace model on the free version of Google Colab, but I haven't been able to locate a sharded version anywhere. I thought I might need to do it myself, but at the ... | 2023-08-09T18:52:05 | https://www.reddit.com/r/LocalLLaMA/comments/15mnysc/sharding_llms/ | Jaded-Armadillo8348 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 15mnysc | false | null | t3_15mnysc | /r/LocalLLaMA/comments/15mnysc/sharding_llms/ | false | false | self | 3 | null |
Train with custom knowledge | 3 | Hi, I have have ~100 XML files in a simple schema, these files contain logic and rules. At the moment these files are created manually. Is it possible to take for example the llama2 model and train it with this additional data, so that it could generate or modify these XML files by instructions? | 2023-08-09T18:08:02 | https://www.reddit.com/r/LocalLLaMA/comments/15mmsj6/train_with_custom_knowledge/ | FroyoAbject | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 15mmsj6 | false | null | t3_15mmsj6 | /r/LocalLLaMA/comments/15mmsj6/train_with_custom_knowledge/ | false | false | self | 3 | null |
[Project] Making AMD GPUs Competitive for LLM inference | 85 | ML compilation (MLC) techniques makes it possible to run LLM inference performantly. An AMD 7900xtx at $1k could deliver 80-85% performance of RTX 4090 at $1.6k, and 94% of RTX 3900Ti previously at $2k.
Most of the performant inference solutions are based on CUDA and optimized for NVIDIA GPUs nowadays. In the meantime... | 2023-08-09T18:01:21 | https://www.reddit.com/r/LocalLLaMA/comments/15mmlte/project_making_amd_gpus_competitive_for_llm/ | yzgysjr | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 15mmlte | false | null | t3_15mmlte | /r/LocalLLaMA/comments/15mmlte/project_making_amd_gpus_competitive_for_llm/ | false | false | self | 85 | null |
Documents on interfacing with local models | 0 | No i don’t mean existing UIs i mean creating a UI and interfacing with the local model. I’ve searched high and low and can’t find any existing documentation. I’ve spent the last few days going over multiple websites, looking at how to articles, and I’ve yet to find “here’s the code”. Hell i still can’t figure out if th... | 2023-08-09T17:49:34 | https://www.reddit.com/r/LocalLLaMA/comments/15mma90/documents_on_interfacing_with_local_models/ | tickleMyBigPoop | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 15mma90 | false | null | t3_15mma90 | /r/LocalLLaMA/comments/15mma90/documents_on_interfacing_with_local_models/ | false | false | self | 0 | null |
Why is this so strange? Can you change the system prompt and get it to be more uncensored? (Using Llama-2-13b) | 1 | 2023-08-09T17:40:32 | BetterProphet5585 | i.redd.it | 1970-01-01T00:00:00 | 0 | {} | 15mm1fg | false | null | t3_15mm1fg | /r/LocalLLaMA/comments/15mm1fg/why_is_this_so_strange_can_you_change_the_system/ | false | false | 1 | {'enabled': True, 'images': [{'id': 'G1pcZuWRUSCn62iMjroPQ1ZFPyMxDURHxagLUSDhZaA', 'resolutions': [{'height': 102, 'url': 'https://preview.redd.it/lam2k65pf4hb1.png?width=108&crop=smart&auto=webp&s=5b9855142578d231ece29f708c04c1f9aeb66d72', 'width': 108}, {'height': 205, 'url': 'https://preview.redd.it/lam2k65pf4hb1.pn... | |||
👨💻 An awesome and curated list of best code-LLM for research. | 20 | [https://github.com/huybery/Awesome-Code-LLM](https://github.com/huybery/Awesome-Code-LLM)
Letting LLMs help humans write code (named Code-LLMs) would be the best way to free up productivity, and we're collecting the research progress on this repo. If this resonates with you, please 🌟 star the repo on GitHub, contrib... | 2023-08-09T17:30:50 | https://www.reddit.com/r/LocalLLaMA/comments/15mlrt0/an_awesome_and_curated_list_of_best_codellm_for/ | huybery | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 15mlrt0 | false | null | t3_15mlrt0 | /r/LocalLLaMA/comments/15mlrt0/an_awesome_and_curated_list_of_best_codellm_for/ | false | false | self | 20 | {'enabled': False, 'images': [{'id': 'BsZMx6KFo0Ls1MX1YXO9BRz_V7c3QO-lr0wVkKQrzIc', 'resolutions': [{'height': 54, 'url': 'https://external-preview.redd.it/8AolF4KdkARFOYE2UPPcRcQlEj8KETjBymwVzK8yqh8.jpg?width=108&crop=smart&auto=webp&s=9209768234ed8ca24eb2f935493c9d2de0bdd74f', 'width': 108}, {'height': 108, 'url': 'h... |
Newbie needing some clarification in regards to koboldcpp, please and thank you. | 6 | Other than the selection of the model using the -model flag,
1. What options should I be using?
2. Is it always beneficial to put the maximum amount of layers on the GPU to use all available VRAM?
3. Do I need to specify how many threads the application should use? And do I always want to use all available threads?
... | 2023-08-09T17:09:48 | https://www.reddit.com/r/LocalLLaMA/comments/15ml757/newbie_needing_some_clarification_in_regards_to/ | wh33t | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 15ml757 | false | null | t3_15ml757 | /r/LocalLLaMA/comments/15ml757/newbie_needing_some_clarification_in_regards_to/ | false | false | self | 6 | null |
Can Llama convert English cue words into a Japanese sentences? | 7 | Apologies, but I'm a beginner. I want to convert few English words into Japanese sentences. The sentences would be easy so I don't think Llama would make a mistake there.
Is llama capable enough to do both of these tasks? I would appreciate if you can provide me some links that I can read and implement.
As of now, I... | 2023-08-09T15:52:49 | https://www.reddit.com/r/LocalLLaMA/comments/15mj4tm/can_llama_convert_english_cue_words_into_a/ | JapaniRobot | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 15mj4tm | false | null | t3_15mj4tm | /r/LocalLLaMA/comments/15mj4tm/can_llama_convert_english_cue_words_into_a/ | false | false | self | 7 | null |
What is the best embedding search? | 12 | I am working to a small personal project.
I plan to vectorise a lot of text using sBERT and then I would like to be able to search through this content by asking "natural" language questions.
I know that I need to tokenize the question and the use the tokens to run a similarity search through the vectors.
I am curr... | 2023-08-09T15:43:41 | https://www.reddit.com/r/LocalLLaMA/comments/15mivz5/what_is_the_best_embedding_search/ | aiworshipper | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 15mivz5 | false | null | t3_15mivz5 | /r/LocalLLaMA/comments/15mivz5/what_is_the_best_embedding_search/ | false | false | self | 12 | null |
Faster than OpenAI Api? | 3 | I am currently running a process where I have to analyse large chunks of texts by an LLM. I divide the texts into parts that fit the token window, but it still takes about an hour per text to run the prompt on everything and receive a reply for all chunks.
Can Llama be faster? I would probably connect to an Api provide... | 2023-08-09T15:13:56 | https://www.reddit.com/r/LocalLLaMA/comments/15mi446/faster_than_openai_api/ | ekevu456 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 15mi446 | false | null | t3_15mi446 | /r/LocalLLaMA/comments/15mi446/faster_than_openai_api/ | false | false | self | 3 | null |
Has anyone tried deploying GGML models in production? | 2 | Considering they’re not thread-safe, I’d be curious how you could deploy them behind a reliable API on AWS. Maybe use the LocalAI kubernetes config on EKS? | 2023-08-09T15:08:04 | https://www.reddit.com/r/LocalLLaMA/comments/15mhyk0/has_anyone_tried_deploying_ggml_models_in/ | bangarangguy | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 15mhyk0 | false | null | t3_15mhyk0 | /r/LocalLLaMA/comments/15mhyk0/has_anyone_tried_deploying_ggml_models_in/ | false | false | self | 2 | null |
EU Parliament approved the text of the AI Regulation Law (it is not applied yet, but we might be very near) - Which models should I hoard? Which are the best uncensored before the blackout? | 57 | I am overreacting a bit to this, but I still want to be prepared in case models and UIs will not be available in EU or if Open Source projects will have to obscure themselves before everyone understands and apply the transparency EU requires.
**I want to prepare to a possible AI winter in EU.**
---
This might ev... | 2023-08-09T14:46:55 | https://www.reddit.com/r/LocalLLaMA/comments/15mhebl/eu_parliament_approved_the_text_of_the_ai/ | BetterProphet5585 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 15mhebl | false | null | t3_15mhebl | /r/LocalLLaMA/comments/15mhebl/eu_parliament_approved_the_text_of_the_ai/ | false | false | self | 57 | null |
Introducing the newest WizardLM-70B V1.0 model! | 151 | Introducing the newest **WizardLM-70B V1.0** model !
1. WizardLM-70B V1.0 achieves a substantial and comprehensive improvement on **coding**, **mathematical reasoning** and **open-domain conversation** capacities.
2. This model is license friendly, and follows the same license with Meta Llama-2.
3. Next versi... | 2023-08-09T14:24:55 | https://www.reddit.com/r/LocalLLaMA/comments/15mgthr/introducing_the_newest_wizardlm70b_v10_model/ | cylaw01 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 15mgthr | false | null | t3_15mgthr | /r/LocalLLaMA/comments/15mgthr/introducing_the_newest_wizardlm70b_v10_model/ | false | false | 151 | {'enabled': False, 'images': [{'id': 'lOaLM5PtpNjrwQBaVnzypT1kCPzSVsujOefNAVhO5CQ', 'resolutions': [{'height': 58, 'url': 'https://external-preview.redd.it/XFh7NFmpmoin81UW6jgdBY3EwhyzfY1hVX4SA-fJ3SM.jpg?width=108&crop=smart&auto=webp&s=9e2bd842483d97a3a5070984e9c32b6df4165eb0', 'width': 108}, {'height': 116, 'url': 'h... | |
EU Parliament approved the text of the AI Regulation Law (it is not applied yet, but we might be very near) - Which models should I hoard? Which are the best unconsored before the blackout? | 1 | [removed] | 2023-08-09T14:15:54 | https://www.reddit.com/r/LocalLLaMA/comments/15mgl52/eu_parliament_approved_the_text_of_the_ai/ | PuzzledAd1197 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 15mgl52 | false | null | t3_15mgl52 | /r/LocalLLaMA/comments/15mgl52/eu_parliament_approved_the_text_of_the_ai/ | false | false | self | 1 | null |
Lost In Translation: LLMs Unleashed | 0 | You know those digital buddies we’ve come to rely on for a bit of tech magic? Well, they’ve decided to put on their cryptic cloaks and mess with our heads a bit. Buckle up, because we’re about to dive into a world where your AI assistant isn’t just your sidekick – it’s your partner in eerie shenanigans.
This: [https:/... | 2023-08-09T13:57:12 | https://www.reddit.com/r/LocalLLaMA/comments/15mg3g4/lost_in_translation_llms_unleashed/ | Powerful-Pumpkin-938 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 15mg3g4 | false | null | t3_15mg3g4 | /r/LocalLLaMA/comments/15mg3g4/lost_in_translation_llms_unleashed/ | false | false | self | 0 | {'enabled': False, 'images': [{'id': 'z-4lvjVtpSargyO33nCIO081kU4se1phI4FktUjpbSk', 'resolutions': [{'height': 108, 'url': 'https://external-preview.redd.it/drC0jbTnpopuKQDb-MNy1YcYpX7df0thDcmTqlmaM00.jpg?width=108&crop=smart&auto=webp&s=6e5e2d2bb460e4c25f694fb1e5b11b952566ed92', 'width': 108}, {'height': 216, 'url': '... |
Fine-tuning Llama 2 using spot instances across multiple clouds or Lambda Cloud | 2 | 2023-08-09T13:52:12 | https://dstack.ai/examples/finetuning-llama-2/ | cheptsov | dstack.ai | 1970-01-01T00:00:00 | 0 | {} | 15mfysb | false | null | t3_15mfysb | /r/LocalLLaMA/comments/15mfysb/finetuning_llama_2_using_spot_instances_across/ | false | false | 2 | {'enabled': False, 'images': [{'id': '1CJ80XE7TBliPhvCtW1XlPN9rEz_QAFB-YxQSDbhaKw', 'resolutions': [{'height': 56, 'url': 'https://external-preview.redd.it/d2ygPVR83FIieJANJ9_95HhWGCsLNy6kaV-7_NMpORA.jpg?width=108&crop=smart&auto=webp&s=34039547ea3d5e89dd33add5eff01d197aa2f659', 'width': 108}, {'height': 113, 'url': 'h... | ||
PC build for LLMs | 1 | [removed] | 2023-08-09T12:48:36 | https://www.reddit.com/r/LocalLLaMA/comments/15mednm/pc_build_for_llms/ | 04RR | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 15mednm | false | null | t3_15mednm | /r/LocalLLaMA/comments/15mednm/pc_build_for_llms/ | false | false | self | 1 | null |
Llama2 Embeddings FastAPI Service | 43 |
I just wanted a quick and easy way to easily submit strings to a REST API and get back the embedding vectors in JSON using Llama2 and other similar LLMs, so I put this together over the past couple days. It's very quick and easy to set up and totally self-contained and self-hosted. You can easily add new models to it... | 2023-08-09T12:37:34 | https://github.com/Dicklesworthstone/llama_embeddings_fastapi_service | dicklesworth | github.com | 1970-01-01T00:00:00 | 0 | {} | 15me4i9 | false | null | t3_15me4i9 | /r/LocalLLaMA/comments/15me4i9/llama2_embeddings_fastapi_service/ | false | false | default | 43 | {'enabled': False, 'images': [{'id': 'LIFpZZ97uHRTB2fR9xb2TOd2YvmaGyOm5rq7V0YRxTo', 'resolutions': [{'height': 54, 'url': 'https://external-preview.redd.it/weqXXUTkHKcprVLMpFtKxJW6yVKgvU5uxjJ0NyI-me8.jpg?width=108&crop=smart&auto=webp&s=32c0d6a94a728c1dc48428fae9ea4b7325f806d8', 'width': 108}, {'height': 108, 'url': 'h... |
Is there any hope at all for getting a 13B GPTQ model running entirely on an 8 GB GPU? | 22 | With the release of ExLlama and its incredible optimizations, I was hoping that I'd finally be able to load 13B models into my GPU, but unfortunately it's not quite there yet. While it OOMs with regular ExLlama, I can load it with ExLlama\_HF but it still OOMs upon inference.
I know that of course I can offload som... | 2023-08-09T12:32:46 | https://www.reddit.com/r/LocalLLaMA/comments/15me0oc/is_there_any_hope_at_all_for_getting_a_13b_gptq/ | Gyramuur | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 15me0oc | false | null | t3_15me0oc | /r/LocalLLaMA/comments/15me0oc/is_there_any_hope_at_all_for_getting_a_13b_gptq/ | false | false | self | 22 | null |
This dataset trains openai models but has no effect on llama2. Why? | 1 | [removed] | 2023-08-09T12:16:58 | https://www.reddit.com/r/LocalLLaMA/comments/15mdnq5/this_dataset_trains_openai_models_but_has_no/ | kielerrr | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 15mdnq5 | false | null | t3_15mdnq5 | /r/LocalLLaMA/comments/15mdnq5/this_dataset_trains_openai_models_but_has_no/ | false | false | default | 1 | {'enabled': False, 'images': [{'id': 'bWxZxCMhP9jfrcdBLdv9A8KMN-S-eA8s6v7OcxWVjKw', 'resolutions': [{'height': 58, 'url': 'https://external-preview.redd.it/JJXfYOqCYQgSnarrKjpjN3-vINMeVr8v0bKxiSeignE.jpg?width=108&crop=smart&auto=webp&s=4be6acec1540e26a5b8f50c6e781047d4bc6acdf', 'width': 108}, {'height': 116, 'url': 'h... |
This | 1 | [removed] | 2023-08-09T12:14:26 | https://www.reddit.com/r/LocalLLaMA/comments/15mdlnk/this/ | kielerrr | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 15mdlnk | false | null | t3_15mdlnk | /r/LocalLLaMA/comments/15mdlnk/this/ | false | false | self | 1 | {'enabled': False, 'images': [{'id': 'bWxZxCMhP9jfrcdBLdv9A8KMN-S-eA8s6v7OcxWVjKw', 'resolutions': [{'height': 58, 'url': 'https://external-preview.redd.it/JJXfYOqCYQgSnarrKjpjN3-vINMeVr8v0bKxiSeignE.jpg?width=108&crop=smart&auto=webp&s=4be6acec1540e26a5b8f50c6e781047d4bc6acdf', 'width': 108}, {'height': 116, 'url': 'h... |
What should be my expectations from models trained on a PC? | 7 | I'm considering making a serious upgrade to my PC so I could start playing around with AI. But before ponying up thousands of dollars in triple digit 5DDR RAM and thousand dollar GPUs, I want to know what I should expect from "PC AI" as most of the AI I am familiar with are billion dollar models like GPT4, trained by t... | 2023-08-09T11:48:29 | https://www.reddit.com/r/LocalLLaMA/comments/15md13z/what_should_be_my_expectations_from_models/ | BigBootyBear | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 15md13z | false | null | t3_15md13z | /r/LocalLLaMA/comments/15md13z/what_should_be_my_expectations_from_models/ | false | false | self | 7 | null |
My meta-llama/Llama-2-7b-hf fine-tuned model does not learn to use the additional special tokens | 21 | I am trying to fine-tune the meta-llama/Llama-2-7b-hf model on a recipe dataset using QLoRA and SFTTrainer. My dataset contains special tokens (such as <RECIPE\_TITLE>, <END\_TITLE>, , <END\_STEPS>, etc.) which helps with structuring the recipes. During fine-tuning I have added these additional tokens to the tokenizer:... | 2023-08-09T11:20:29 | https://www.reddit.com/r/LocalLLaMA/comments/15mcgjv/my_metallamallama27bhf_finetuned_model_does_not/ | rares13 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 15mcgjv | false | null | t3_15mcgjv | /r/LocalLLaMA/comments/15mcgjv/my_metallamallama27bhf_finetuned_model_does_not/ | false | false | self | 21 | null |
Fine-tune Llama 2 with DPO, has anyone tried? | 6 | 2023-08-09T11:15:57 | https://huggingface.co/blog/dpo-trl | Nondzu | huggingface.co | 1970-01-01T00:00:00 | 0 | {} | 15mcd1b | false | null | t3_15mcd1b | /r/LocalLLaMA/comments/15mcd1b/finetune_llama_2_with_dpo_has_anyone_tried/ | false | false | 6 | {'enabled': False, 'images': [{'id': 'AmQgpyNhIlUEj9zr9gG-RgzMA6CHeTDaZ7Q4LqqedT8', 'resolutions': [{'height': 52, 'url': 'https://external-preview.redd.it/gVC-CxRm2EPj2om6Rni76VF_RDOD7rroGVi0OohYP3k.jpg?width=108&crop=smart&auto=webp&s=74b9d4f0311999391894918231269f3bcd31e1d3', 'width': 108}, {'height': 105, 'url': 'h... | ||
Prompt Processing Times? (GGML CPU-only) | 32 | Tested with the following:
Prompt: 478 tokens
BLAS: 512
System: i3 9th Gen 4 cores/4 threads with 16GB DDR4 2400 RAM
-----------
LLaMA 7B Q2
Processing: 82ms/token
Generation: 206ms/token
-----------
LLaMA 7B Q4
Processing: 81ms/token
Generation: 258ms/token
-----------
LLaMA 13B Q2
Processing: 146ms/toke... | 2023-08-09T10:08:28 | https://www.reddit.com/r/LocalLLaMA/comments/15mb1f0/prompt_processing_times_ggml_cpuonly/ | noellarkin | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 15mb1f0 | false | null | t3_15mb1f0 | /r/LocalLLaMA/comments/15mb1f0/prompt_processing_times_ggml_cpuonly/ | false | false | self | 32 | null |
Lamma Context length is it max(4096) or can it be increased?? | 0 | I am running the model through replicate and i am getting error while i am testing on large input. is 4096 maximum that llama model can support or can i increase that ... if i try to pass in chunks will it give me same results because i am working on identifying the tone.
\---------------------------------------------... | 2023-08-09T09:12:18 | https://www.reddit.com/r/LocalLLaMA/comments/15m9zyo/lamma_context_length_is_it_max4096_or_can_it_be/ | Dry_Sink_597 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 15m9zyo | false | null | t3_15m9zyo | /r/LocalLLaMA/comments/15m9zyo/lamma_context_length_is_it_max4096_or_can_it_be/ | false | false | self | 0 | null |
Difference between meta-llama-2-7b and meta-llama-2-7b-hf | 1 | Was browsing through hugginfFace Llama's model card and came across the hf variant for all models. It says that it's pretrained on HuggingFace transformer. What exactly does it mean? | 2023-08-09T06:17:16 | https://www.reddit.com/r/LocalLLaMA/comments/15m6ulr/difference_between_metallama27b_and_metallama27bhf/ | IamFuckinTomato | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 15m6ulr | false | null | t3_15m6ulr | /r/LocalLLaMA/comments/15m6ulr/difference_between_metallama27b_and_metallama27bhf/ | false | false | self | 1 | null |
New version of Turbopilot released! | 38 | New: Refactored + Simplified: The source code has been improved to make it easier to extend and add new models to Turbopilot. The system now supports multiple flavours of model
New: Wizardcoder, Starcoder, Santacoder support - Turbopilot now supports state of the art local code completion models which provide more pro... | 2023-08-09T05:57:33 | https://github.com/ravenscroftj/turbopilot | Acrobatic-Site2065 | github.com | 1970-01-01T00:00:00 | 0 | {} | 15m6hn1 | false | null | t3_15m6hn1 | /r/LocalLLaMA/comments/15m6hn1/new_version_of_turbopilot_released/ | false | false | 38 | {'enabled': False, 'images': [{'id': 'VxeQvnvYGXg_A2HNdzuNBEzctgC1QlNp0_NATAQ2rS4', 'resolutions': [{'height': 54, 'url': 'https://external-preview.redd.it/I4qLsdbmDLeJLGhMJZD0EEYchn9LINPxBGd7FV3YamM.jpg?width=108&crop=smart&auto=webp&s=edee7eb2947e6e1dfe12ddd6ace311d562877a8b', 'width': 108}, {'height': 108, 'url': 'h... | |
GPT4All - Can LocalDocs plugin read HTML files? | 4 | Used Wget to mass download a wiki. Looking to train a model on the wiki. | 2023-08-09T05:24:12 | https://www.reddit.com/r/LocalLLaMA/comments/15m5v6s/gpt4all_can_localdocs_plugin_read_html_files/ | Rzablio | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 15m5v6s | false | null | t3_15m5v6s | /r/LocalLLaMA/comments/15m5v6s/gpt4all_can_localdocs_plugin_read_html_files/ | false | false | self | 4 | null |
Tried running llama-70b on 126GB of memory; memory overflow. How much memory is necessary ? | 95 | 2023-08-08T23:15:11 | MoiSanh | i.redd.it | 1970-01-01T00:00:00 | 0 | {} | 15lxscb | false | null | t3_15lxscb | /r/LocalLLaMA/comments/15lxscb/tried_running_llama70b_on_126gb_of_memory_memory/ | false | false | 95 | {'enabled': True, 'images': [{'id': 'xStm3HNsKGKSAHNnfzUUE0VN7YieO75cGhirAOOMSxo', 'resolutions': [{'height': 47, 'url': 'https://preview.redd.it/zjpv9w8dyygb1.png?width=108&crop=smart&auto=webp&s=510f4e7b7f7dfb795418e57cc2e407d279acca71', 'width': 108}, {'height': 94, 'url': 'https://preview.redd.it/zjpv9w8dyygb1.png?... | |||
Hi sub, i want to build my 2023 PC and i'm thinking in GPU for IA/LLAMA2... | 1 | [removed] | 2023-08-08T22:58:50 | https://www.reddit.com/r/LocalLLaMA/comments/15lxddr/hi_sub_i_want_to_build_my_2023_pc_and_im_thinking/ | Icy_Sun_4958 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 15lxddr | false | null | t3_15lxddr | /r/LocalLLaMA/comments/15lxddr/hi_sub_i_want_to_build_my_2023_pc_and_im_thinking/ | false | false | self | 1 | null |
For those running backends on W10/11 | 16 | So, I noticed that my W11 throttled token generation while terminal was running in the background.
I'm using kobold.cpp as my backend and noticed 40-50% drop in token generation, every time my browser was active instead of the terminal.
Apparently changing system power options to favor high performance solved it, at ... | 2023-08-08T22:58:27 | https://www.reddit.com/r/LocalLLaMA/comments/15lxd09/for_those_running_backends_on_w1011/ | nollataulu | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 15lxd09 | false | null | t3_15lxd09 | /r/LocalLLaMA/comments/15lxd09/for_those_running_backends_on_w1011/ | false | false | self | 16 | null |
Setting Up a Lightweight Local LLM, Fine-tuning, and Creating an API for Queries | 3 | Hey fellow Redditors,
I've been fascinated by large language models (LLMs) and their potential applications. I'm eager to dive into the world of LLMs by setting up a lightweight local version, fine-tuning it with my own data, and eventually creating an API to query it online. 🚀
However, I'm a bit unsure about the ... | 2023-08-08T22:44:03 | https://www.reddit.com/r/LocalLLaMA/comments/15lwzz5/setting_up_a_lightweight_local_llm_finetuning_and/ | aiCornStar | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 15lwzz5 | false | null | t3_15lwzz5 | /r/LocalLLaMA/comments/15lwzz5/setting_up_a_lightweight_local_llm_finetuning_and/ | false | false | self | 3 | null |
New SillyTavern Release - with proxy replacement! | 154 | There's a new major version of **[SillyTavern](https://github.com/SillyTavern/SillyTavern)**, my favorite LLM frontend, perfect for chat and roleplay!
The new feature I'm most excited about:
> **Added settings and instruct presets to imitate simple-proxy for local models**
Finally a replacement for the *simple-proxy... | 2023-08-08T22:36:26 | https://www.reddit.com/r/LocalLLaMA/comments/15lwtai/new_sillytavern_release_with_proxy_replacement/ | WolframRavenwolf | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 15lwtai | false | null | t3_15lwtai | /r/LocalLLaMA/comments/15lwtai/new_sillytavern_release_with_proxy_replacement/ | false | false | self | 154 | {'enabled': False, 'images': [{'id': 'bDW7jyCB5L7RKBwRUqrzWSn3bIb_Szu_GogYRebiCjw', 'resolutions': [{'height': 54, 'url': 'https://external-preview.redd.it/NFgRhAZ_cgs4xao5V1cOWNjptqU5JwIiGBtsvOdhlPU.jpg?width=108&crop=smart&auto=webp&s=22d2e1896c94ecebda58fed69478453d4b16fd4f', 'width': 108}, {'height': 108, 'url': 'h... |
Confused about the "custom URL provided will remain valid for model downloads for 24 hours to download each model up to 5 times" | 4 | Hello y'all, I just saw now the email from Meta I received 6 days ago granting me access to download their LLaMa v2 models. Though apparently, in 24 hours, I can download a model for only five times. I am just a little confused.
Does it mean like I can only download five times and have to fill out the form again?
I... | 2023-08-08T22:32:04 | https://www.reddit.com/r/LocalLLaMA/comments/15lwpej/confused_about_the_custom_url_provided_will/ | ImNotLegitLol | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 15lwpej | false | null | t3_15lwpej | /r/LocalLLaMA/comments/15lwpej/confused_about_the_custom_url_provided_will/ | false | false | self | 4 | null |
What is the best coding model to use directly with VS Code? | 12 | Is Wizard the best option to compete with CoPilot? | 2023-08-08T22:04:03 | https://www.reddit.com/r/LocalLLaMA/comments/15lvzfy/what_is_the_best_coding_model_to_use_directly/ | SillyLilBear | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 15lvzfy | false | null | t3_15lvzfy | /r/LocalLLaMA/comments/15lvzfy/what_is_the_best_coding_model_to_use_directly/ | false | false | self | 12 | null |
Have you all been guilty of being somewhat religious about specific models in the mist of all the local models coming up left and right ? [model fatigue] | 6 | Like for me, and I am probably not being objective here but the Nous-Hermes variant regardless of Llama1 or Llama2 is just...really a step above the rest.
I think it is just due to me experiencing model fatigue.
Do you all have a specific model you all are "religious" about ? | 2023-08-08T21:52:43 | https://www.reddit.com/r/LocalLLaMA/comments/15lvod0/have_you_all_been_guilty_of_being_somewhat/ | Vitamin_C_is_awesome | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 15lvod0 | false | null | t3_15lvod0 | /r/LocalLLaMA/comments/15lvod0/have_you_all_been_guilty_of_being_somewhat/ | false | false | self | 6 | null |
Local API and Apple shortcuts | 4 | One of the extensions in Generation Web UI allows for an api. Is it possible to run it locally so I can ask questions through apple shortcuts
https://preview.redd.it/cibdq93mjygb1.png?width=672&format=png&auto=webp&s=b1427cce433f8ea61495b3b9a78a19253a73d4e4 | 2023-08-08T21:51:57 | https://www.reddit.com/r/LocalLLaMA/comments/15lvnla/local_api_and_apple_shortcuts/ | LegendarySpy | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 15lvnla | false | null | t3_15lvnla | /r/LocalLLaMA/comments/15lvnla/local_api_and_apple_shortcuts/ | false | false | 4 | null | |
Exploring Local Multi-GPU Setup for AI: Harnessing AMD Radeon RX 580 8GB for Efficient AI Model | 17 | I'm a newcomer to the realm of AI for personal utilization. I happen to possess several AMD Radeon RX 580 8GB GPUs that are currently idle. Contemplating the idea of assembling a dedicated Linux-based system for LLMA localy, I'm curious whether it's feasible to locally deploy LLAMA with the support of multiple GPUs? If... | 2023-08-08T20:43:21 | https://www.reddit.com/r/LocalLLaMA/comments/15ltsj1/exploring_local_multigpu_setup_for_ai_harnessing/ | OfficialRakma | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 15ltsj1 | false | null | t3_15ltsj1 | /r/LocalLLaMA/comments/15ltsj1/exploring_local_multigpu_setup_for_ai_harnessing/ | false | false | self | 17 | null |
A beginner seeking for help | 1 | Hello everyone. I've been closely following all the work you're doing, and I'd like to start as well, setting up my own model, being able to fine-tune it, and maybe even gaining solid skills in the field. I have a good foundation in Python, and I'm persistent when I want to understand something, but right now I'm a bit... | 2023-08-08T20:36:51 | https://www.reddit.com/r/LocalLLaMA/comments/15ltm2z/a_beginner_seeking_for_help/ | Orfvr | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 15ltm2z | false | null | t3_15ltm2z | /r/LocalLLaMA/comments/15ltm2z/a_beginner_seeking_for_help/ | false | false | self | 1 | null |
Python LLaMa tokenizer with zero dependencies? | 1 | [removed] | 2023-08-08T19:10:24 | https://www.reddit.com/r/LocalLLaMA/comments/15lrarw/python_llama_tokenizer_with_zero_dependencies/ | GusPuffy | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 15lrarw | false | null | t3_15lrarw | /r/LocalLLaMA/comments/15lrarw/python_llama_tokenizer_with_zero_dependencies/ | false | false | self | 1 | {'enabled': False, 'images': [{'id': 'f85dH88dhYQPPafVGTNRvAc-A7RF-lmAfbRxl3qh294', 'resolutions': [{'height': 54, 'url': 'https://external-preview.redd.it/_yv1UpzqhYc7LSZY2PHM5KrMvXqJO0phh6CWPBW0TFc.jpg?width=108&crop=smart&auto=webp&s=e615a9bf00336f0a058df322754dac21e466b4e2', 'width': 108}, {'height': 108, 'url': 'h... |
Structured documentation for fine tuning | 2 | Hey guys !
I was wondering just like langchain has a good organised documentation on several ways to deal with LLMs , is there any similar documentation on how to fine tune and infer open-source LLMs , concepts like quantization , lora , qlora etc | 2023-08-08T19:01:48 | https://www.reddit.com/r/LocalLLaMA/comments/15lr2b0/structured_documentation_for_fine_tuning/ | Spiritual-Rub925 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 15lr2b0 | false | null | t3_15lr2b0 | /r/LocalLLaMA/comments/15lr2b0/structured_documentation_for_fine_tuning/ | false | false | self | 2 | null |
Can CPU llama.cpp get close to over 1t/s? | 7 | What might an Epyc rome or Milan 16core do with 200GB/s Memory bandwidth and lets say 256GB memory do token/sec?
Is Epyc Genoa with 12 channel ddr5 with 460GB/s needed for just 1 token/s? | 2023-08-08T18:55:30 | https://www.reddit.com/r/LocalLLaMA/comments/15lqw8n/can_cpu_llamacpp_get_close_to_over_1ts/ | HilLiedTroopsDied | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 15lqw8n | false | null | t3_15lqw8n | /r/LocalLLaMA/comments/15lqw8n/can_cpu_llamacpp_get_close_to_over_1ts/ | false | false | self | 7 | null |
has anyone tried Qwen-7B-Chat? | 9 | Came across this today and the benchmarks are really surprising-- [Qwen/Qwen-7B-Chat](https://huggingface.co/Qwen/Qwen-7B-Chat)
Especially the [tool usage](https://huggingface.co/Qwen/Qwen-7B-Chat#%E5%B7%A5%E5%85%B7%E4%BD%BF%E7%94%A8%E8%83%BD%E5%8A%9B%E7%9A%84%E8%AF%84%E6%B5%8B%EF%BC%88tool-usage%EF%BC%89) benchmark w... | 2023-08-08T18:20:20 | https://www.reddit.com/r/LocalLLaMA/comments/15lpyto/has_anyone_tried_qwen7bchat/ | LyPreto | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 15lpyto | false | null | t3_15lpyto | /r/LocalLLaMA/comments/15lpyto/has_anyone_tried_qwen7bchat/ | false | false | self | 9 | {'enabled': False, 'images': [{'id': 'Xj-CDOmBnVRen-RT9Mv5LhiNSsTyclH3JlnXqsFNCMY', 'resolutions': [{'height': 58, 'url': 'https://external-preview.redd.it/YH6Y7A8j_IK2zXrAcLgbhR5Gr1bxnbtlwSKuT1qOKHI.jpg?width=108&crop=smart&auto=webp&s=eccdbe9fd0b48f42a9ba66f6736fb7c7097d957d', 'width': 108}, {'height': 116, 'url': 'h... |
noob starting with llama2 | 0 | trying to use llama2 to create an offline chatbot (using m1 mac)read the getting started page and guide found that i can use llama.cpp and ggml models inorder to run this on cpu based machine. though the model list was too overwhelming, i decided for now to go forward with llama2-7b-chat by bloke.
can anyone give me a... | 2023-08-08T16:54:53 | https://www.reddit.com/r/LocalLLaMA/comments/15lnoib/noob_starting_with_llama2/ | HawkingRadiation42 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 15lnoib | false | null | t3_15lnoib | /r/LocalLLaMA/comments/15lnoib/noob_starting_with_llama2/ | false | false | self | 0 | null |
NVIDIA Unveils Next-Generation GH200 Grace Hopper Superchip | 70 | 2023-08-08T16:50:52 | https://nvidianews.nvidia.com/news/gh200-grace-hopper-superchip-with-hbm3e-memory | fallingdowndizzyvr | nvidianews.nvidia.com | 1970-01-01T00:00:00 | 0 | {} | 15lnktt | false | null | t3_15lnktt | /r/LocalLLaMA/comments/15lnktt/nvidia_unveils_nextgeneration_gh200_grace_hopper/ | false | false | 70 | {'enabled': False, 'images': [{'id': 'LNUxxo97U9-YS6WNrzJuSjRteeP8s-F1K2gN6F94lGg', 'resolutions': [{'height': 60, 'url': 'https://external-preview.redd.it/k92uNY7hMhdE2QVHzU6QBS2A6dldLUR1nL61W_KY1Cc.jpg?width=108&crop=smart&auto=webp&s=2a10af4e6dc90a754e0b90ea9d3d4f68136ad005', 'width': 108}, {'height': 121, 'url': 'h... | ||
Wizard Coder not Inserting Newlines | 11 | I'm using [Wizard Coder](https://huggingface.co/michaelfeil/ct2fast-WizardCoder-15B-V1.0) for code completion but I'm finding it regularly doesn't insert any new lines in the code it generates. For example:
"def power(x, y"
autocompletes with:
"): if y == 0: return 1 else: return x \* power(x, y-1) print(power(2,... | 2023-08-08T16:23:27 | https://www.reddit.com/r/LocalLLaMA/comments/15lmvbp/wizard_coder_not_inserting_newlines/ | kintrith | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 15lmvbp | false | null | t3_15lmvbp | /r/LocalLLaMA/comments/15lmvbp/wizard_coder_not_inserting_newlines/ | false | false | self | 11 | {'enabled': False, 'images': [{'id': 'zQBjqlzNyNQuSWeFUBZpTPHXCSbNON8vgpVhHD9WPm8', 'resolutions': [{'height': 58, 'url': 'https://external-preview.redd.it/ODozVdhO7r6t7RDP9GhT3aiYYude9LbRPFDlup4b5K4.jpg?width=108&crop=smart&auto=webp&s=8b2f2daec92b62d36a81d895339703f242dbd6f6', 'width': 108}, {'height': 116, 'url': 'h... |
New Code Generation Model from Stability AI with 16K context | 177 | “Stability AI has just announced the release of StableCode, its very first LLM generative AI product for coding. This product is designed to assist programmers with their daily work while also providing a great learning tool for new developers ready to take their skills to the next level.” | 2023-08-08T16:16:17 | https://twitter.com/stabilityai/status/1688931312122675200?s=46&t=4Lg1z9tXUANCKLiHwRSk_A | Acrobatic-Site2065 | twitter.com | 1970-01-01T00:00:00 | 0 | {} | 15lmojm | false | {'oembed': {'author_name': 'Stability AI', 'author_url': 'https://twitter.com/StabilityAI', 'cache_age': 3153600000, 'height': None, 'html': '<blockquote class="twitter-video"><p lang="en" dir="ltr">🚀Exciting news! Stability AI has launched StableCode, the revolutionary generative AI LLM for coding!<br><br>💡 Develope... | t3_15lmojm | /r/LocalLLaMA/comments/15lmojm/new_code_generation_model_from_stability_ai_with/ | false | false | 177 | {'enabled': False, 'images': [{'id': 'LaKRDKsNPue9HGl9OWKQdS_cFT1BV-KJj5nRYgR0qFI', 'resolutions': [{'height': 108, 'url': 'https://external-preview.redd.it/CbUSt5r8wlKyvA-VX34Doxh3vW4JmQzUb438c-p23U8.jpg?width=108&crop=smart&auto=webp&s=a6816300d23fc456382dc7a90c01c84fed6f8fda', 'width': 108}], 'source': {'height': 14... | |
Bright Eye: free mobile app that generates art and different forms of text (code, math answers, essays, games, ideas, and more)! | 0 |
Hi all. I’m the cofounder of a startup focused on developing the AI super app called “Bright Eye”, a multipurpose AI product that generates and analyzes content.
One of its interesting use cases is helping students study, people plan, and offering general advice.
As the title puts it, it’s capable of generating al... | 2023-08-08T16:10:31 | https://www.reddit.com/r/LocalLLaMA/comments/15lmiyk/bright_eye_free_mobile_app_that_generates_art_and/ | EtelsonRecomputing | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 15lmiyk | false | null | t3_15lmiyk | /r/LocalLLaMA/comments/15lmiyk/bright_eye_free_mobile_app_that_generates_art_and/ | false | false | self | 0 | {'enabled': False, 'images': [{'id': '5U3w0HRUOPA7NaUGZ4RL_8wjJYuCeus8Xsjl6SQQYik', 'resolutions': [{'height': 56, 'url': 'https://external-preview.redd.it/X0kpF-8iYyTAFvs0cIVB-TD9XiogQBV5hJAL_ZbkVI4.jpg?width=108&crop=smart&auto=webp&s=7db2cfa683e5720dee090d1f221bd54e8df0b627', 'width': 108}, {'height': 113, 'url': 'h... |
Prospects for future hardware releases | 6 | Is it likely that AMD or Intel will sense a market opportunity and start shipping affordable cards for those who wish to run local LLMs on a budget? Will future optimizations considerably reduce the requirements to run a model at a given performance level, or are we close to fundamental efficiency? Is there even a way ... | 2023-08-08T15:22:01 | https://www.reddit.com/r/LocalLLaMA/comments/15ll7or/prospects_for_future_hardware_releases/ | WarmCartoonist | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 15ll7or | false | null | t3_15ll7or | /r/LocalLLaMA/comments/15ll7or/prospects_for_future_hardware_releases/ | false | false | self | 6 | null |
Merging base Llama2 LoRA weights into Chat model | 3 | I have been playing around with LoRA as a way to get knowledge into Llama-2-7B, with some limited success. I was able to achieve some style transfer, but the model still tends to hallucinate. Interestingly enough, by merging base-model LoRA weights trained on a simple autoregressive objective into the Chat model, the l... | 2023-08-08T15:07:45 | https://www.reddit.com/r/LocalLLaMA/comments/15lkts4/merging_base_llama2_lora_weights_into_chat_model/ | Numerous_Current_298 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 15lkts4 | false | null | t3_15lkts4 | /r/LocalLLaMA/comments/15lkts4/merging_base_llama2_lora_weights_into_chat_model/ | false | false | self | 3 | null |
looking for a guide | 0 | Does anyone know a comprehensive guide to set up everything to run LocalLLama?
[Preferably on a steamdeck (Linux/SteamOs) 😂] | 2023-08-08T14:07:22 | https://www.reddit.com/r/LocalLLaMA/comments/15lj8vq/looking_for_a_guide/ | pussifricker1337 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 15lj8vq | false | null | t3_15lj8vq | /r/LocalLLaMA/comments/15lj8vq/looking_for_a_guide/ | false | false | self | 0 | null |
What is a good model for NER inference that fits into 12gb RAM of RTX 3060? | 6 | Any suggestions for a newbie wanting to try out llama2 on a limited GPU resource workstation? CPU RAM of 176 gb. | 2023-08-08T13:50:47 | https://www.reddit.com/r/LocalLLaMA/comments/15litek/what_is_a_good_model_for_ner_inference_that_fits/ | sbs1799 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 15litek | false | null | t3_15litek | /r/LocalLLaMA/comments/15litek/what_is_a_good_model_for_ner_inference_that_fits/ | false | false | self | 6 | null |
Big Model Comparison/Test (13 models tested) | 80 | Many interesting models have been released lately, and I tested most of them. Instead of keeping my observations to myself, I'm sharing my notes with you all.
Looking forward to your comments, especially if you have widely different experiences, so I may go back to retest some models with different settings. Here's ho... | 2023-08-08T13:37:51 | https://www.reddit.com/r/LocalLLaMA/comments/15lihmq/big_model_comparisontest_13_models_tested/ | WolframRavenwolf | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 15lihmq | false | null | t3_15lihmq | /r/LocalLLaMA/comments/15lihmq/big_model_comparisontest_13_models_tested/ | false | false | self | 80 | {'enabled': False, 'images': [{'id': 'bDW7jyCB5L7RKBwRUqrzWSn3bIb_Szu_GogYRebiCjw', 'resolutions': [{'height': 54, 'url': 'https://external-preview.redd.it/NFgRhAZ_cgs4xao5V1cOWNjptqU5JwIiGBtsvOdhlPU.jpg?width=108&crop=smart&auto=webp&s=22d2e1896c94ecebda58fed69478453d4b16fd4f', 'width': 108}, {'height': 108, 'url': 'h... |
There is an option to teach llama from github? | 1 | [removed] | 2023-08-08T13:07:57 | https://www.reddit.com/r/LocalLLaMA/comments/15lhqsi/there_is_an_option_to_teach_llama_from_github/ | Agreeable_Fun7280 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 15lhqsi | false | null | t3_15lhqsi | /r/LocalLLaMA/comments/15lhqsi/there_is_an_option_to_teach_llama_from_github/ | false | false | default | 1 | null |
Hosted nous hermes? | 1 | I know this is local llama, but sometimes you wanna move from local to hosted. Is there anywhere that these models can be hosted cheaply? | 2023-08-08T13:03:48 | https://www.reddit.com/r/LocalLLaMA/comments/15lhnol/hosted_nous_hermes/ | TopperBowers | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 15lhnol | false | null | t3_15lhnol | /r/LocalLLaMA/comments/15lhnol/hosted_nous_hermes/ | false | false | self | 1 | null |
ggml.js: Serverless AI Inference on browser with Web Assembly | 1 | [removed] | 2023-08-08T12:49:18 | https://www.reddit.com/r/LocalLLaMA/comments/15lhb0u/ggmljs_serverless_ai_inference_on_browser_with/ | AnonymousD3vil | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 15lhb0u | false | null | t3_15lhb0u | /r/LocalLLaMA/comments/15lhb0u/ggmljs_serverless_ai_inference_on_browser_with/ | false | false | self | 1 | {'enabled': False, 'images': [{'id': '4fC4vd6ed9N7BYtcZcg9XPJ6-FWYZfbxrXGLCVtQISQ', 'resolutions': [{'height': 54, 'url': 'https://external-preview.redd.it/iZahc4_iBp0yJhz_HToud8tCDstNjttaYz0KaDSTtwg.jpg?width=108&crop=smart&auto=webp&s=a99695e720ab200453487046768d233035ccb7d5', 'width': 108}, {'height': 108, 'url': 'h... |
Will training a LoRA help an AI emulate a specific writer's style? | 26 | I'm interested in creating LoRAs for specific authors so I can get an AI to emulate their style. Most immediately, I've been looking at Nabokov and Hemingway, specifically, because their writing styles are distinctive and immediately recognizable.
I've trained a LoRA on a dataset of three of Nabokov's books, and tried... | 2023-08-08T12:45:28 | https://www.reddit.com/r/LocalLLaMA/comments/15lh7wx/will_training_a_lora_help_an_ai_emulate_a/ | tenmileswide | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 15lh7wx | false | null | t3_15lh7wx | /r/LocalLLaMA/comments/15lh7wx/will_training_a_lora_help_an_ai_emulate_a/ | false | false | self | 26 | null |
Lora on top of lora-merged base model? | 6 | My intuition is that it should be technically trivial after the merge, but not sure if anyone actually tried it.
Has anyone tried lora- or qlora-ing on a previously lora-ed model?
Maybe it’s possible but not recommended? | 2023-08-08T12:33:40 | https://www.reddit.com/r/LocalLLaMA/comments/15lgy72/lora_on_top_of_loramerged_base_model/ | EntertainmentBroad43 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 15lgy72 | false | null | t3_15lgy72 | /r/LocalLLaMA/comments/15lgy72/lora_on_top_of_loramerged_base_model/ | false | false | self | 6 | null |
Teaching Llama to reason in another language help! | 2 | Hi r/LocalLLaMA,
​
I have been tinkering with Ooba and API calls for a while now, and have hit a bit of a wall.
My use case is corporate and not too out there: given transcripts of business calls, I should be able to answer questions and deliver summaries of the conversation. All easy with Langchain and ... | 2023-08-08T12:22:12 | https://www.reddit.com/r/LocalLLaMA/comments/15lgoo7/teaching_llama_to_reason_in_another_language_help/ | Puzzled_Chemist_279 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 15lgoo7 | false | null | t3_15lgoo7 | /r/LocalLLaMA/comments/15lgoo7/teaching_llama_to_reason_in_another_language_help/ | false | false | self | 2 | {'enabled': False, 'images': [{'id': 'h1WdwUjHD04AYItpD2-q7M_23Em4OEh1IeVUkIzKuOU', 'resolutions': [{'height': 54, 'url': 'https://external-preview.redd.it/i79qaNEIF-LEwnatW8R4IuTNz4GWElpPqvQp8KI8Oy0.jpg?width=108&crop=smart&auto=webp&s=2da3f5cd5c1f35bc9151f780f3047ed450916623', 'width': 108}, {'height': 108, 'url': 'h... |
I will help you set up Local LLama for Free. | 1 | A few of my friends asked me to set it up for them. I've documented the process for the setup so I can do this pretty fast for others as well.
I'm trying to gauge the market on whether consulting people on Llama might be a viable market. So, I get plenty out of it as well. If you're interested, you can comment or DM ... | 2023-08-08T12:07:54 | https://www.reddit.com/r/LocalLLaMA/comments/15lgcpf/i_will_help_you_set_up_local_llama_for_free/ | middlenameishardwork | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 15lgcpf | false | null | t3_15lgcpf | /r/LocalLLaMA/comments/15lgcpf/i_will_help_you_set_up_local_llama_for_free/ | false | false | self | 1 | null |
chronos-hermes-13b-v2-GPTQ - It's here, how is it? | 14 | Here it is folks:
[https://huggingface.co/Austism/chronos-hermes-13b-v2-GPTQ](https://huggingface.co/Austism/chronos-hermes-13b-v2-GPTQ)
or
[https://huggingface.co/TheBloke/Chronos-Hermes-13B-v2-GGML](https://huggingface.co/TheBloke/Chronos-Hermes-13B-v2-GGML)
How are people getting on with it for role play? I'm te... | 2023-08-08T11:11:15 | https://www.reddit.com/r/LocalLLaMA/comments/15lf4vo/chronoshermes13bv2gptq_its_here_how_is_it/ | CasimirsBlake | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 15lf4vo | false | null | t3_15lf4vo | /r/LocalLLaMA/comments/15lf4vo/chronoshermes13bv2gptq_its_here_how_is_it/ | false | false | self | 14 | {'enabled': False, 'images': [{'id': '5lq-vTKb8WPoIHJIEwLDWm-pYzECuhBMTlOVwcxpDrI', 'resolutions': [{'height': 58, 'url': 'https://external-preview.redd.it/7MHHoCMLXs6zPUkx4XnSTBQ9FtOA6uFtAMgStCY2Jws.jpg?width=108&crop=smart&auto=webp&s=cb46f17a656cf4e4df0ca8a270ea0958d90cd055', 'width': 108}, {'height': 116, 'url': 'h... |
Inference Speed for Llama 2 70b on A6000 with Exllama - Need Suggestions! | 12 | Hello everyone,I'm currently running Llama-2 70b on an A6000 GPU using Exllama, and I'm achieving an average inference speed of 10t/s, with peaks up to 13t/s.
I'm wondering if there's any way to further optimize this setup to increase the inference speed.Has anyone here had experience with this setup or similar config... | 2023-08-08T11:05:57 | https://www.reddit.com/r/LocalLLaMA/comments/15lf119/inference_speed_for_llama_2_70b_on_a6000_with/ | Used_Carpenter_6674 | self.LocalLLaMA | 2023-08-08T11:12:02 | 0 | {} | 15lf119 | false | null | t3_15lf119 | /r/LocalLLaMA/comments/15lf119/inference_speed_for_llama_2_70b_on_a6000_with/ | false | false | self | 12 | null |
Using HF Transformer APIs for local use of models like "TheBloke/Llama-2-7B-Chat-GGML" | 1 | [removed] | 2023-08-08T10:52:17 | https://www.reddit.com/r/LocalLLaMA/comments/15leqpa/using_hf_transformer_apis_for_local_use_of_models/ | m_k_johnson | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 15leqpa | false | null | t3_15leqpa | /r/LocalLLaMA/comments/15leqpa/using_hf_transformer_apis_for_local_use_of_models/ | false | false | self | 1 | {'enabled': False, 'images': [{'id': 'TS8j-IHmN8kpOvNSHQflSeOArGV9aYAaVmSnkggMS0U', 'resolutions': [{'height': 54, 'url': 'https://external-preview.redd.it/arhy915TK3EgvCgI0MmxciY1t5u4AHjz8DmH-myuWrA.jpg?width=108&crop=smart&auto=webp&s=48b677f91db4cbe41319e587f30b415ba58782d7', 'width': 108}, {'height': 108, 'url': 'h... |
What is the most effective language model for summarizing scientific text? | 6 | I've been working on abstractive summarization for scientific articles (mainly arXiV). Until now, I've fine-tuned a PEGASUS and a BART-large model and obtained okay-ish ROUGE values (\~40 ROUGE-1). What other models would you guys suggest that generate coherent summaries given a section of the research paper? Thank you... | 2023-08-08T10:10:06 | https://www.reddit.com/r/LocalLLaMA/comments/15ldw0w/what_is_the_most_effective_language_model_for/ | psj_2908 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 15ldw0w | false | null | t3_15ldw0w | /r/LocalLLaMA/comments/15ldw0w/what_is_the_most_effective_language_model_for/ | false | false | self | 6 | null |
Help: What sorcery do I use to figure out correct model loader? | 21 | I new to all of this stuff and am trying to load some new models, but I don't know how to determine the model loader information. How does one determine these parameters? Is it written up somewhere? Is it buried in the model card or does one have to write this themselves according to some information on a website? Pl... | 2023-08-08T09:35:23 | https://www.reddit.com/r/LocalLLaMA/comments/15ld8ld/help_what_sorcery_do_i_use_to_figure_out_correct/ | w7gg33h | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 15ld8ld | false | null | t3_15ld8ld | /r/LocalLLaMA/comments/15ld8ld/help_what_sorcery_do_i_use_to_figure_out_correct/ | false | false | self | 21 | null |
Pretty great reasoning from Nous Research Hermes LLama2 13B, q4. | 82 | 2023-08-08T09:16:23 | TopperBowers | i.redd.it | 1970-01-01T00:00:00 | 0 | {} | 15lcv2i | false | null | t3_15lcv2i | /r/LocalLLaMA/comments/15lcv2i/pretty_great_reasoning_from_nous_research_hermes/ | false | false | 82 | {'enabled': True, 'images': [{'id': 'MvcKsKpvWFfFarLhkDDllwYOXiC2Fici_u9m61spywM', 'resolutions': [{'height': 50, 'url': 'https://preview.redd.it/wj382l7rsugb1.png?width=108&crop=smart&auto=webp&s=25c6d83946dd24932bd6e15017e449f1cd8e971a', 'width': 108}, {'height': 100, 'url': 'https://preview.redd.it/wj382l7rsugb1.png... | |||
PyTorch and CUDA version mismatch | 1 | I am using this repo: [https://github.com/mzbac/qlora-fine-tune](https://github.com/mzbac/qlora-fine-tune) to fine tune a 7B 4bit quantized llama model. However, when trying to run setup\_cuda.py it says that my cuda and torch versions are mismatched.I tried building torch from source but it still only installs torch 2... | 2023-08-08T08:18:42 | https://www.reddit.com/r/LocalLLaMA/comments/15lbss9/pytorch_and_cuda_version_mismatch/ | QuantumTyping33 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 15lbss9 | false | null | t3_15lbss9 | /r/LocalLLaMA/comments/15lbss9/pytorch_and_cuda_version_mismatch/ | false | false | 1 | null | |
Video testing(for reference sake) with a bonafide trivial benchmark for the mountain of models that's forming on Huggingface. Suggestions welcomed. | 1 | [removed] | 2023-08-08T07:37:16 | https://www.reddit.com/r/LocalLLaMA/comments/15lb2g8/video_testingfor_reference_sake_with_a_bonafide/ | AI_Trenches | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 15lb2g8 | false | null | t3_15lb2g8 | /r/LocalLLaMA/comments/15lb2g8/video_testingfor_reference_sake_with_a_bonafide/ | false | false | self | 1 | {'enabled': False, 'images': [{'id': '4TdTL_e77QYjU7JKEsBZ1I1hqGryfWhbNyKTgp1CA-o', 'resolutions': [{'height': 108, 'url': 'https://external-preview.redd.it/vLMAfi65baIodwRaA35YSLasEjU7MJlhVKL_0YQIOWc.jpg?width=108&crop=smart&auto=webp&s=53e7b5f7e79788f23fd93f4792d90756633147d2', 'width': 108}, {'height': 216, 'url': '... |
Declarai - a game-changer for Python-based language model interactions! | 23 | Struggled with using LLMs in production? We've been there. That's why we created Declarai, an open-source gift to the engineering community.
What's Declarai?Simply put, it's declarative AI with Python. Keep developing as always, but supercharged with the power of LLMs.
With Declarai, you can:
🔥 Write Declarative Py... | 2023-08-08T07:31:28 | https://www.reddit.com/r/LocalLLaMA/comments/15laymb/declarai_a_gamechanger_for_pythonbased_language/ | matkley12 | self.LocalLLaMA | 2023-08-08T07:43:00 | 0 | {} | 15laymb | false | null | t3_15laymb | /r/LocalLLaMA/comments/15laymb/declarai_a_gamechanger_for_pythonbased_language/ | false | false | 23 | null | |
What llama 2 pay-on-demand API to use? | 13 | Hi all
I'd like to do some experiments with the 70B chat version of Llama 2. However, I don't have a good enough laptop to run it locally with reasonable speed. So I consider using some remote service, since it's mostly for experiments.
So my question: Do you have any recommendations for APIs I can use, where I just ... | 2023-08-08T06:08:30 | https://www.reddit.com/r/LocalLLaMA/comments/15l9eh7/what_llama_2_payondemand_api_to_use/ | silvanmelchior | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 15l9eh7 | false | null | t3_15l9eh7 | /r/LocalLLaMA/comments/15l9eh7/what_llama_2_payondemand_api_to_use/ | false | false | self | 13 | null |
Has anyone tried finetuning through ReLoRA? | 28 | Has anyone tried finetuning through [ReLoRA](https://github.com/Guitaricet/relora)?
It seems like a way of adding knowledge to models. | 2023-08-08T05:31:09 | https://www.reddit.com/r/LocalLLaMA/comments/15l8oyv/has_anyone_tried_finetuning_through_relora/ | ninjasaid13 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 15l8oyv | false | null | t3_15l8oyv | /r/LocalLLaMA/comments/15l8oyv/has_anyone_tried_finetuning_through_relora/ | false | false | self | 28 | {'enabled': False, 'images': [{'id': 'bqlZHX0DME6igHKbkudvkCpdRG3-_vFiv_J1JMc8-qw', 'resolutions': [{'height': 54, 'url': 'https://external-preview.redd.it/MR1Rdvi9CtLH50CgXROKE7njDcJNQZX5FmCbfjYzQ7Q.jpg?width=108&crop=smart&auto=webp&s=97168ba9e2c31c1c6c5aaf036d5e48c30a6c5780', 'width': 108}, {'height': 108, 'url': 'h... |
Baby 🦙 Code 🐍 Interpreter 🚀 (v.2) | 29 | [removed] | 2023-08-08T02:55:12 | https://www.reddit.com/r/LocalLLaMA/comments/15l5ivs/baby_code_interpreter_v2/ | LyPreto | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 15l5ivs | false | null | t3_15l5ivs | /r/LocalLLaMA/comments/15l5ivs/baby_code_interpreter_v2/ | false | false | 29 | {'enabled': False, 'images': [{'id': 'DJPqvteONpGwVVw6LzaG6b8vlDa2rv2hETCaqe0z57s', 'resolutions': [{'height': 54, 'url': 'https://external-preview.redd.it/ohwupr9MqnYXF974_2-gAgkZDuFxjDg48bFY3KdCQdc.jpg?width=108&crop=smart&auto=webp&s=b6caea286bbf31bdb473212eb5668f45376977be', 'width': 108}, {'height': 108, 'url': 'h... | |
Why can’t Lora fine tune add knowledge? | 57 | Whenever someone asks about fine tuning a Lora for a llama model to “add knowledge”, someone will suggest to do RAG instead.
What is the reason why Lora fine tune can’t do it, but the original full parameter pretraining can? | 2023-08-08T02:44:27 | https://www.reddit.com/r/LocalLLaMA/comments/15l5auj/why_cant_lora_fine_tune_add_knowledge/ | xynyxyn | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 15l5auj | false | null | t3_15l5auj | /r/LocalLLaMA/comments/15l5auj/why_cant_lora_fine_tune_add_knowledge/ | false | false | self | 57 | null |
Trying to fine-tune Starcoderbase 1B in rombodawg dataset(googlecolab) | 2 | So, I was trying to fine tune the smallest startcoder in the huge data set of rombodawg. However my PC is crap so I was trying to use google colab. I don't know if it is possible. I was able to load the model and but failed to load the database in a trainable way, I am inexperience and I am trying to adapt some google ... | 2023-08-08T02:35:36 | https://www.reddit.com/r/LocalLLaMA/comments/15l543h/trying_to_finetune_starcoderbase_1b_in_rombodawg/ | GG9242 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 15l543h | false | null | t3_15l543h | /r/LocalLLaMA/comments/15l543h/trying_to_finetune_starcoderbase_1b_in_rombodawg/ | false | false | self | 2 | null |
I can't run any LLM locally. I guess I know why. (AMD Phenom) | 1 | [removed] | 2023-08-07T23:55:08 | https://www.reddit.com/r/LocalLLaMA/comments/15l1g6a/i_cant_run_any_llm_locally_i_guess_i_know_why_amd/ | Wiktor1975 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 15l1g6a | false | null | t3_15l1g6a | /r/LocalLLaMA/comments/15l1g6a/i_cant_run_any_llm_locally_i_guess_i_know_why_amd/ | false | false | self | 1 | null |
I can't run any LLM locally (AMD Phenom) | 1 | [removed] | 2023-08-07T23:49:11 | https://www.reddit.com/r/LocalLLaMA/comments/15l1axo/i_cant_run_any_llm_locally_amd_phenom/ | Wiktor1975 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 15l1axo | false | null | t3_15l1axo | /r/LocalLLaMA/comments/15l1axo/i_cant_run_any_llm_locally_amd_phenom/ | false | false | self | 1 | null |
Stumbled across the negative CFG parameter today. Works as expected. ;) | 120 | 2023-08-07T23:46:24 | drwebb | i.redd.it | 1970-01-01T00:00:00 | 0 | {} | 15l18ka | false | null | t3_15l18ka | /r/LocalLLaMA/comments/15l18ka/stumbled_across_the_negative_cfg_parameter_today/ | false | false | nsfw | 120 | {'enabled': True, 'images': [{'id': 'McOocXcORNcXLBmchLQ4TMelke8R4H65dKlf2a6Uaaw', 'resolutions': [{'height': 62, 'url': 'https://preview.redd.it/h6mftk21zrgb1.png?width=108&crop=smart&auto=webp&s=e857a127d1b36d8cd5a8c89802dd9912a2801304', 'width': 108}, {'height': 125, 'url': 'https://preview.redd.it/h6mftk21zrgb1.png... | ||
What's similar to TheBloke_Llama-2-70B-Chat-GGML , but less censored? | 1 | [removed] | 2023-08-07T23:29:10 | https://www.reddit.com/r/LocalLLaMA/comments/15l0t5m/whats_similar_to_thebloke_llama270bchatggml_but/ | w7gg33h | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 15l0t5m | false | null | t3_15l0t5m | /r/LocalLLaMA/comments/15l0t5m/whats_similar_to_thebloke_llama270bchatggml_but/ | false | false | self | 1 | null |
3060 Ti or 4060 viable for 13B model | 8 | Hey there!
I want to know about 13B model tokens/s for 3060 Ti or 4060, basically 8GB cards.
I'm specifically interested in performance of GPTQ, GGML, Exllama, offloading, different sized contexts (2k, 4k, 8-16K) etc.
I'm also curious about the speed of the 30B models on offloading.
Any insights would be greatly ap... | 2023-08-07T21:58:16 | https://www.reddit.com/r/LocalLLaMA/comments/15kyhen/3060_ti_or_4060_viable_for_13b_model/ | Xhehab_ | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 15kyhen | false | null | t3_15kyhen | /r/LocalLLaMA/comments/15kyhen/3060_ti_or_4060_viable_for_13b_model/ | false | false | self | 8 | null |
I ran Llama2 on my Mac in < 5m | 1 | [removed] | 2023-08-07T21:11:24 | https://www.reddit.com/r/LocalLLaMA/comments/15kx8dg/i_ran_llama2_on_my_mac_in_5m/ | rajatarya | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 15kx8dg | false | null | t3_15kx8dg | /r/LocalLLaMA/comments/15kx8dg/i_ran_llama2_on_my_mac_in_5m/ | false | false | self | 1 | {'enabled': False, 'images': [{'id': '1ovRzCUs3oeIe_KXmpJSUSacS0FnNwwWmJEY_j6aBiw', 'resolutions': [{'height': 56, 'url': 'https://external-preview.redd.it/beiC5Rza84NRBokpxkagcjMOjlj5_57NpJn7MnyudPc.jpg?width=108&crop=smart&auto=webp&s=3bf3ae602824591e462b01ca1c63ce5490fe501e', 'width': 108}, {'height': 113, 'url': 'h... |
I'm just starting out and can't get the text generation to work. Any tips? | 0 | I'm using the bloke's models and they load right in. But when I type in the input box, it just pastes whatever I typed in the output box. Not sure what I'm doing wrong. Seems like I'm missing something simple but I don't know. | 2023-08-07T20:48:11 | https://www.reddit.com/r/LocalLLaMA/comments/15kwli7/im_just_starting_out_and_cant_get_the_text/ | nuupdog | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 15kwli7 | false | null | t3_15kwli7 | /r/LocalLLaMA/comments/15kwli7/im_just_starting_out_and_cant_get_the_text/ | false | false | self | 0 | null |
LLAMA 2 : Run this on internet | 0 | My llama2 (oogabooga) run perfect in local machine: (127.0.0:7860).
Now I want to put this accessible on the internet for others.
How to do this?
Thanks a lot.
C.G. | 2023-08-07T20:46:48 | https://www.reddit.com/r/LocalLLaMA/comments/15kwk3z/llama_2_run_this_on_internet/ | Embarrassed-Cicada94 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 15kwk3z | false | null | t3_15kwk3z | /r/LocalLLaMA/comments/15kwk3z/llama_2_run_this_on_internet/ | false | false | self | 0 | null |
need advice on how to build my own version of chatgpt code interpreter | 3 |
I am thinking of building a similar tool to chatgpt codeinterpreter using some opensource LLM.
I have only worked with the transformers library up untill now but this project might require some fine tuning or weight training and retrivel system. etc and i don't exactaly know how to do that can anyone please spare s... | 2023-08-07T20:11:22 | https://www.reddit.com/r/LocalLLaMA/comments/15kvlms/need_advice_on_how_to_build_my_own_version_of/ | Occupying-Mars | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 15kvlms | false | null | t3_15kvlms | /r/LocalLLaMA/comments/15kvlms/need_advice_on_how_to_build_my_own_version_of/ | false | false | self | 3 | null |
advice on building my own version of chatgpt code interpreter | 1 | [removed] | 2023-08-07T20:09:04 | https://www.reddit.com/r/LocalLLaMA/comments/15kvjcq/advice_on_building_my_own_version_of_chatgpt_code/ | neo-gen-evan | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 15kvjcq | false | null | t3_15kvjcq | /r/LocalLLaMA/comments/15kvjcq/advice_on_building_my_own_version_of_chatgpt_code/ | false | false | self | 1 | null |
What's currently the best model for a 12GB 3060? | 11 | Hey guys!
I am really happy about the open source community content pouring into huggingface.(thanks TheBloke!)
At the same time, I'm getting a little confused. I know I can run my own tests, and I will, but I'm also interested: what do you guys think, which one is the best model for a 12GB 3060 for sfw and nsfw ro... | 2023-08-07T20:03:43 | https://www.reddit.com/r/LocalLLaMA/comments/15kve2o/whats_currently_the_best_model_for_a_12gb_3060/ | dangernoodle01 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 15kve2o | false | null | t3_15kve2o | /r/LocalLLaMA/comments/15kve2o/whats_currently_the_best_model_for_a_12gb_3060/ | false | false | self | 11 | null |
Qwen 7B ggml and gptq versions | 14 | Hello, newby qwestion here: it has been a tremendous amount of time, in terms of how fast this community is moving, yet a model claiming to have capacity at 7B of all other models at 13B has no versions in ggml and gptq, the most popular versions used. What's going on? | 2023-08-07T19:37:08 | https://www.reddit.com/r/LocalLLaMA/comments/15kuoat/qwen_7b_ggml_and_gptq_versions/ | Eduard_T | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 15kuoat | false | null | t3_15kuoat | /r/LocalLLaMA/comments/15kuoat/qwen_7b_ggml_and_gptq_versions/ | false | false | self | 14 | null |
Finetuning for code generation | 13 | i want to fine tune any open source llm for code generation purpose with some of my code. any idea what model would be suitable? and any example of implementation? | 2023-08-07T19:30:48 | https://www.reddit.com/r/LocalLLaMA/comments/15kui8l/finetuning_for_code_generation/ | learner_beginner | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 15kui8l | false | null | t3_15kui8l | /r/LocalLLaMA/comments/15kui8l/finetuning_for_code_generation/ | false | false | self | 13 | null |
Introducing ggml.js: A JavaScript framework for ggml models | 1 | [removed] | 2023-08-07T19:22:01 | https://www.reddit.com/r/LocalLLaMA/comments/15ku9su/introducing_ggmljs_a_javascript_framework_for/ | AnonymousD3vil | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 15ku9su | false | null | t3_15ku9su | /r/LocalLLaMA/comments/15ku9su/introducing_ggmljs_a_javascript_framework_for/ | false | false | self | 1 | {'enabled': False, 'images': [{'id': 'mjAUxnYu0F8Er2K42CWPaaMaopQuUQmbwD2Ul2rf5Cg', 'resolutions': [{'height': 54, 'url': 'https://external-preview.redd.it/dHkAsG3bkpZkfZ_TQXaaepgRy4_TaKKUlUVWdmbgJh0.jpg?width=108&crop=smart&auto=webp&s=b5ac57e4a8476640074e3cdbd002dd99dd26c5c0', 'width': 108}, {'height': 108, 'url': 'h... |
Did you notice improvements in GGML models 7B, 13B, 30B, 70B vs q2, q3, q4, q5, q6, q8 ? | 33 | Because apart the RAM usage i didn't find improvements, i tried 7B, 13B, 30B at q2, maybe i'm doing something wrong | 2023-08-07T18:47:32 | https://www.reddit.com/r/LocalLLaMA/comments/15ktbo1/did_you_notice_improvements_in_ggml_models_7b_13b/ | grigio | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 15ktbo1 | false | null | t3_15ktbo1 | /r/LocalLLaMA/comments/15ktbo1/did_you_notice_improvements_in_ggml_models_7b_13b/ | false | false | self | 33 | null |
Making Micro-LLMs use tools | 1 | [removed] | 2023-08-07T17:26:48 | https://www.reddit.com/r/LocalLLaMA/comments/15kr3x5/making_microllms_use_tools/ | remyxai | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 15kr3x5 | false | null | t3_15kr3x5 | /r/LocalLLaMA/comments/15kr3x5/making_microllms_use_tools/ | false | false | self | 1 | {'enabled': False, 'images': [{'id': 'pDkuwj20mJP8FiHSJP1FHIROIiZrgpHvskQ5QxCSf1o', 'resolutions': [{'height': 58, 'url': 'https://external-preview.redd.it/mfw0F1zXG0ajLrzdRQEGvclpGKKCHfZdfkdStnXHuR0.jpg?width=108&crop=smart&auto=webp&s=1b298204f29d62fb8384cfaeb9101e5305fa9b1a', 'width': 108}, {'height': 116, 'url': 'h... |
Anyone here know enough Python/C++ to convert a function? [Llama.cpp/KoboldAI] | 2 | I was looking through the sample settings for Llama.cpp and I found a thread around the creation of the initial repetition samplers where someone comments that the Kobold repetition sampler has an option for a "slope" parameter. This causes tokens nearer to the end of the repetition window to be penalized more heavily ... | 2023-08-07T17:18:01 | https://www.reddit.com/r/LocalLLaMA/comments/15kqvlt/anyone_here_know_enough_pythonc_to_convert_a/ | mrjackspade | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 15kqvlt | false | null | t3_15kqvlt | /r/LocalLLaMA/comments/15kqvlt/anyone_here_know_enough_pythonc_to_convert_a/ | false | false | self | 2 | {'enabled': False, 'images': [{'id': 'ALrCA5sclUUfhY20UTCP1lRZyALg97qOas1UO-1EUW8', 'resolutions': [{'height': 54, 'url': 'https://external-preview.redd.it/xh9_E-d5uUFtTNfA0i95d8xpLrF-7c6exXdp9W3K3pg.jpg?width=108&crop=smart&auto=webp&s=d7476daeab0cb0c5ca4d19fb3ad9feadb0b3a568', 'width': 108}, {'height': 108, 'url': 'h... |
KoboldCPP v1.3.9, now has 16k context support. | 59 | KoboldCPP v1.3.9, now has 16k context support.
A new version of KoboldCPP supports up to 16k context. Here is the link to it, plus some 16k and 8k models. Have fun. :)
KoboldCPP 16k
https://github.com/LostRuins/koboldcpp/releases
Airoboros L1-33b 16k
https://huggingface.co/ycros/airoboros-33b-gpt4-1.4.1-lxctx-PI-... | 2023-08-07T16:01:27 | https://www.reddit.com/r/LocalLLaMA/comments/15kotbe/koboldcpp_v139_now_has_16k_context_support/ | Sabin_Stargem | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 15kotbe | false | null | t3_15kotbe | /r/LocalLLaMA/comments/15kotbe/koboldcpp_v139_now_has_16k_context_support/ | false | false | self | 59 | {'enabled': False, 'images': [{'id': 'naeM87qJQ77Rba8sJP8Noam3MXJbL0brGw3vtVlzFuU', 'resolutions': [{'height': 54, 'url': 'https://external-preview.redd.it/NB9mnqikSAgcernpMCXIFLnjY5FWZoLqdFnpaPJ1D3o.jpg?width=108&crop=smart&auto=webp&s=d077391e3fafa08e620f895eb65930d782d1fa2a', 'width': 108}, {'height': 108, 'url': 'h... |
I asked a simple riddle to 30+ models | 184 | I always found numbers-based benchmarks somewhat too abstract to evaluate models.
To get a better sense of how models reason, I got the idea to ask them this simple riddle:
>Question: **Sally (a girl) has 3 brothers. Each brother has 2 sisters. How many sisters does Sally have?**
>Answer:
With a temperature of 0 h... | 2023-08-07T15:25:07 | https://www.reddit.com/r/LocalLLaMA/comments/15kntrq/i_asked_a_simple_riddle_to_30_models/ | tim_toum | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 15kntrq | false | null | t3_15kntrq | /r/LocalLLaMA/comments/15kntrq/i_asked_a_simple_riddle_to_30_models/ | false | false | self | 184 | {'enabled': False, 'images': [{'id': 'Ef6e6fY_RVUqivW9t5ZLc8X0CfItOJmpVIgvesF-olY', 'resolutions': [{'height': 54, 'url': 'https://external-preview.redd.it/9pU1xKzDdhaFffz8kMKNPVry2-KUpbFgPgpzMdwzvDg.jpg?width=108&crop=smart&auto=webp&s=25a141e20ebcbac14bacfee3b920c52a5ab6060d', 'width': 108}, {'height': 108, 'url': 'h... |
Has anyone finetuned Galactica 120B | 11 | I know it's old, but I don't think I ever saw any fine tunes of it. I wonder how 120B preforms against the 70B models | 2023-08-07T14:22:31 | https://www.reddit.com/r/LocalLLaMA/comments/15km59b/has_anyone_finetuned_galactica_120b/ | FaustBargain | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 15km59b | false | null | t3_15km59b | /r/LocalLLaMA/comments/15km59b/has_anyone_finetuned_galactica_120b/ | false | false | self | 11 | null |
Anyone here use this yet | 0 | ? | 2023-08-07T13:50:18 | https://www.reddit.com/r/LocalLLaMA/comments/15klb2t/anyone_here_use_this_yet/ | LearnOnnReddit | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 15klb2t | false | null | t3_15klb2t | /r/LocalLLaMA/comments/15klb2t/anyone_here_use_this_yet/ | false | false | self | 0 | null |
Subsets and Splits
No community queries yet
The top public SQL queries from the community will appear here once available.