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 ⌀ |
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
Are there any public datasets that accept submissions? | 5 | I spend a lot of time conversing with GPT-4, and I was wondering if there's a place that I could submit these conversations with the goal of improving local models. I was wondering if anyone here is aware of something like what I've described.
Thanks | 2023-08-16T05:29:18 | https://www.reddit.com/r/LocalLLaMA/comments/15sgkmk/are_there_any_public_datasets_that_accept/ | CrunchyTesticle | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 15sgkmk | false | null | t3_15sgkmk | /r/LocalLLaMA/comments/15sgkmk/are_there_any_public_datasets_that_accept/ | false | false | self | 5 | null |
What modules should I target when training using LoRA? | 18 | I'm using \`axolotl\`, I can target these modules:
* gate\_proj
* down\_proj
* up\_proj
* q\_proj
* v\_proj
* k\_proj
* o\_proj
Can someone help me understand what each of these modules do? What should i target when training?
Oogaboga GUI targets only Q and V by default. Axolotl targets all by default.
​ | 2023-08-16T05:22:23 | https://www.reddit.com/r/LocalLLaMA/comments/15sgg4m/what_modules_should_i_target_when_training_using/ | Tasty-Lobster-8915 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 15sgg4m | false | null | t3_15sgg4m | /r/LocalLLaMA/comments/15sgg4m/what_modules_should_i_target_when_training_using/ | false | false | self | 18 | null |
some questions about roleplay models | 18 | Hello,
Thank you for taking the time to read.
I've been out of the loop for a few months, and would now like to get back into the scene. I've heard llama2 is here, and with it come new roleplay-focused models.
I would like to know which is best for my use-case, which is mostly talking with a little bit of emoting. I... | 2023-08-16T05:08:19 | https://www.reddit.com/r/LocalLLaMA/comments/15sg67k/some_questions_about_roleplay_models/ | Several_Extreme3886 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 15sg67k | false | null | t3_15sg67k | /r/LocalLLaMA/comments/15sg67k/some_questions_about_roleplay_models/ | false | false | self | 18 | null |
Hardware recommendations for running stable diffusion and 65b ggml at the same time. | 1 | I don't want to spend any money on new hardware. I have a i7-11700kf, 96gb ddr3 3200 ram and rtx 3090 and an rtx 3080. I want to run both stable diffusion and llama 65b model at the same time. The rtx 3090 would be use for stable diffusion. Would the 3080 + the CPU and ram combo be sufficient to run the 65b ggml model... | 2023-08-16T04:52:41 | https://www.reddit.com/r/LocalLLaMA/comments/15sfv22/hardware_recommendations_for_running_stable/ | Erdeem | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 15sfv22 | false | null | t3_15sfv22 | /r/LocalLLaMA/comments/15sfv22/hardware_recommendations_for_running_stable/ | false | false | self | 1 | null |
A simple beautiful UI for Wizard Vicuna 13B Uncensored | 0 | 2023-08-16T03:00:29 | CurryPuff99 | i.redd.it | 1970-01-01T00:00:00 | 0 | {} | 15sdlu2 | false | null | t3_15sdlu2 | /r/LocalLLaMA/comments/15sdlu2/a_simple_beautiful_ui_for_wizard_vicuna_13b/ | false | false | nsfw | 0 | {'enabled': True, 'images': [{'id': '3tDUXPzJlyxm3urC8LPQtGk797Zye6doVUCcML9dngM', 'resolutions': [{'height': 134, 'url': 'https://preview.redd.it/yzqm0n8t0eib1.jpg?width=108&crop=smart&auto=webp&s=d5b5b94787b4d5c694a455b26d9fdc97575cde56', 'width': 108}, {'height': 269, 'url': 'https://preview.redd.it/yzqm0n8t0eib1.jp... | ||
[How to architect this] Routing when mixing question answering from tables as well as documents | 8 | We are performing question answering from pdfs that have some pages with tables and some with standard text.
For the table pages, we are following an approach of detecting and converting them to csv, and dealing with them using a csv agent (in langchain). The QA from the rest of the document remains standard Retrieval... | 2023-08-16T02:30:34 | https://www.reddit.com/r/LocalLLaMA/comments/15scym0/how_to_architect_this_routing_when_mixing/ | nlpllama | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 15scym0 | false | null | t3_15scym0 | /r/LocalLLaMA/comments/15scym0/how_to_architect_this_routing_when_mixing/ | false | false | self | 8 | null |
DDR5 Worth fhe upgrade? | 11 | Hey guys, My pc is at a crossroads and I'm debating whether to upgrade to DDR5 ram now or keep it affordable and stick with DDR4. My use case would be to run 65b via ggml. Anyone running something similar on ddr5, and if so what sort of t/s are you getting? | 2023-08-16T02:06:17 | https://www.reddit.com/r/LocalLLaMA/comments/15scfeq/ddr5_worth_fhe_upgrade/ | idkanythingabout | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 15scfeq | false | null | t3_15scfeq | /r/LocalLLaMA/comments/15scfeq/ddr5_worth_fhe_upgrade/ | false | false | self | 11 | null |
WizardLM demos | 18 | 2023-08-16T00:32:04 | https://twitter.com/Gradio/status/1691400707264630784?t=vQgwiwyYC_v8gjcrSh70BA&s=19 | ninjasaid13 | twitter.com | 1970-01-01T00:00:00 | 0 | {} | 15sa8b7 | false | {'oembed': {'author_name': 'Gradio', 'author_url': 'https://twitter.com/Gradio', 'cache_age': 3153600000, 'height': None, 'html': '<blockquote class="twitter-video"><p lang="en" dir="ltr">Do you know that🔥WizardMath-70B🔥outperforms (on the GSM8K) most celebrated closed-source LLMs out there, like ChatGPT3.5, Claude I... | t3_15sa8b7 | /r/LocalLLaMA/comments/15sa8b7/wizardlm_demos/ | false | false | 18 | {'enabled': False, 'images': [{'id': 'MVhNJgwwBMwnAXYEvelHj0E5qpCGg1DsopbJaox1870', 'resolutions': [{'height': 108, 'url': 'https://external-preview.redd.it/fLaVrxbMV3kVJxR_Ri3hTqlG-zjODnRj37P-OZywU0g.jpg?width=108&crop=smart&auto=webp&s=2aba868c56edbe8c16255ff7ab4844c009aa712e', 'width': 108}], 'source': {'height': 14... | ||
The Bloke - Appreciation | 2 | [removed] | 2023-08-16T00:14:01 | https://www.reddit.com/r/LocalLLaMA/comments/15s9tgk/the_bloke_appreciation/ | LoadingALIAS | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 15s9tgk | false | null | t3_15s9tgk | /r/LocalLLaMA/comments/15s9tgk/the_bloke_appreciation/ | false | false | self | 2 | null |
What’s the bare minimum specs needed for running ai? | 9 | I’ve heard 2 3090s or a 4090 but can you get away with other? | 2023-08-15T23:13:48 | https://www.reddit.com/r/LocalLLaMA/comments/15s8crb/whats_the_bare_minimum_specs_needed_for_running_ai/ | PremoSaysThings | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 15s8crb | false | null | t3_15s8crb | /r/LocalLLaMA/comments/15s8crb/whats_the_bare_minimum_specs_needed_for_running_ai/ | false | false | self | 9 | null |
Potential fix to the repetitiveness problem of Llama 2 | 5 | I, like a few others, have noticed that the output quality of Llama 2 tends to degrade as the context size increase; becoming increasingly prone to repetitiveness of words and sentences. Sometimes it derails the entire conversation and makes continuing the chat impossible.
As this happened again, I wondered what would... | 2023-08-15T22:43:49 | https://www.reddit.com/r/LocalLLaMA/comments/15s7ln1/potential_fix_to_the_repetitiveness_problem_of/ | Xeruthos | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 15s7ln1 | false | null | t3_15s7ln1 | /r/LocalLLaMA/comments/15s7ln1/potential_fix_to_the_repetitiveness_problem_of/ | false | false | self | 5 | null |
On demand vs Reserved instances for LLM fine-tuning | 1 |
Hi everyone,
I am looking at different options to get access to GPUs to train an LLM on an enterprise use case for a customer. They are on a specific Cloud provider with associated credits, so I have no ability to go outside, like Runpod.
We are exchanging on whether we should go for On-demand or Reserved instance... | 2023-08-15T22:20:02 | https://www.reddit.com/r/LocalLLaMA/comments/15s70gf/on_demand_vs_reserved_instances_for_llm_finetuning/ | Separate-Still3770 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 15s70gf | false | null | t3_15s70gf | /r/LocalLLaMA/comments/15s70gf/on_demand_vs_reserved_instances_for_llm_finetuning/ | false | false | self | 1 | null |
I released model EverythingLM 3B. | 42 | Today I released a new model named EverythingLM 3B. It is [OpenLLaMA 3B V2](https://huggingface.co/openlm-research/open_llama_3b_v2) fine-tuned on [EverythingLM Data(ShareGPT format, more cleaned)](https://huggingface.co/datasets/totally-not-an-llm/everything-sharegptformat-morecleaned) for 1 epochs.
The prompt forma... | 2023-08-15T21:59:31 | https://www.reddit.com/r/LocalLLaMA/comments/15s6hlx/i_released_model_everythinglm_3b/ | bot-333 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 15s6hlx | false | null | t3_15s6hlx | /r/LocalLLaMA/comments/15s6hlx/i_released_model_everythinglm_3b/ | false | false | 42 | {'enabled': False, 'images': [{'id': 'mBBZscMdj4CoFq4VFvDECA6EMTJ--wbO5dOXowR_oEs', 'resolutions': [{'height': 58, 'url': 'https://external-preview.redd.it/pqZEAStqXNPuhwZNyfyzq23_uzdmnnkgm52iuYTq61o.jpg?width=108&crop=smart&auto=webp&s=186c5f83508e7d36bb7dacc4426d56a61a7673fc', 'width': 108}, {'height': 116, 'url': 'h... | |
How do AMD GPUs perform on llama.cpp? | 23 | How do a GPU such as the AMD 7900 XTX perform when using it to offload layers while using llama.cpp? How many tokens per seconds could I expect on 13b and 70b models?
I would plan on using a Ryzen 7 5800x/7800x and 64GB of RAM | 2023-08-15T21:37:38 | https://www.reddit.com/r/LocalLLaMA/comments/15s5x5o/how_do_amd_gpus_perform_on_llamacpp/ | joseluissaorin | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 15s5x5o | false | null | t3_15s5x5o | /r/LocalLLaMA/comments/15s5x5o/how_do_amd_gpus_perform_on_llamacpp/ | false | false | self | 23 | null |
Training | 1 | [removed] | 2023-08-15T21:36:47 | https://www.reddit.com/r/LocalLLaMA/comments/15s5wdx/training/ | Ulan0 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 15s5wdx | false | null | t3_15s5wdx | /r/LocalLLaMA/comments/15s5wdx/training/ | false | false | self | 1 | null |
Inconsistent Token Speed on Llama 2 Chat 70b with Exllama | 7 | Hi everyone,
I've been experiencing some issues with inconsistent token speed while using Llama 2 Chat 70b GPTQ 4 Bits 128g Act Order True with Exllama. My setup includes using the oobabooga WebUI.
**Platform/Device:** Linux
**Exllama Settings:** 4096 Alpha 1 compress\_pos\_emb 1 (Default).
​
Has anyone... | 2023-08-15T20:35:32 | https://www.reddit.com/r/LocalLLaMA/comments/15s497d/inconsistent_token_speed_on_llama_2_chat_70b_with/ | Used_Carpenter_6674 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 15s497d | false | null | t3_15s497d | /r/LocalLLaMA/comments/15s497d/inconsistent_token_speed_on_llama_2_chat_70b_with/ | false | false | 7 | null | |
Not Sure if this is the right place to post. Installed Oobabooga and a few loaders from Hugging Face. All responses from AI models are generic and only two or three sentences. | 1 | Any way to make the responses longer or more detailed? No matter how I phrase the question, whatever model I load, it only gives me one or two sentence answers that are vague and non-specific.
If someone could point me in the right direction to begin my search, that'd be great. Thank you!
Thank you! | 2023-08-15T20:28:20 | https://www.reddit.com/r/LocalLLaMA/comments/15s425y/not_sure_if_this_is_the_right_place_to_post/ | InnsmouthConspirator | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 15s425y | false | null | t3_15s425y | /r/LocalLLaMA/comments/15s425y/not_sure_if_this_is_the_right_place_to_post/ | false | false | self | 1 | null |
Can I use my 5700xt to use Llama? | 4 | I wanted to host Llama or maybe Llama 2 7b but i know that if you want it to work for sure you have to have a Nvidia GPU, sadly mine is AMD. Would it still work? If not, how could I make something similar to this work? I don't want to pay for hosting services, and want to use my own API key for the sites that ask them. | 2023-08-15T20:21:20 | https://www.reddit.com/r/LocalLLaMA/comments/15s3vd0/can_i_use_my_5700xt_to_use_llama/ | s-cardi | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 15s3vd0 | false | null | t3_15s3vd0 | /r/LocalLLaMA/comments/15s3vd0/can_i_use_my_5700xt_to_use_llama/ | false | false | self | 4 | null |
HF model suggestions for text multi class classification? (Fine-tuning) | 1 | I have been using the BERTForSequenceClassification , finetune it on my data and use it for sentence classification (have 16 classes). Results aren't that good. Any other model suggestion please? | 2023-08-15T20:08:56 | https://www.reddit.com/r/LocalLLaMA/comments/15s3j8z/hf_model_suggestions_for_text_multi_class/ | Wrong-Pension7258 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 15s3j8z | false | null | t3_15s3j8z | /r/LocalLLaMA/comments/15s3j8z/hf_model_suggestions_for_text_multi_class/ | false | false | self | 1 | null |
What is Hugging Face / The Hugging Face Version of Llama-2? | 1 | I'm confused about what Hugging Face is. From my research, they seem to sell servers to run LLMs in the cloud and write packages to help run those LLMs. That makes sense, but then there's a specific version of Llama-2 for Hugging Face and many tutorials (for example on quantization) use the Hugging Face version of Llam... | 2023-08-15T18:52:59 | https://www.reddit.com/r/LocalLLaMA/comments/15s18c0/what_is_hugging_face_the_hugging_face_version_of/ | MasterJaguar | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 15s18c0 | false | null | t3_15s18c0 | /r/LocalLLaMA/comments/15s18c0/what_is_hugging_face_the_hugging_face_version_of/ | false | false | default | 1 | null |
Uploading model to Hugging Face is stuck at hashing. | 1 | The model is only 7GB, and I have great internet connection. Any idea why this could happen?
​
https://preview.redd.it/zpgbnxbnlbib1.png?width=2472&format=png&auto=webp&s=58d7be7c9454ac17a70376732749905b206487ba | 2023-08-15T18:50:32 | https://www.reddit.com/r/LocalLLaMA/comments/15s15za/uploading_model_to_hugging_face_is_stuck_at/ | bot-333 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 15s15za | false | null | t3_15s15za | /r/LocalLLaMA/comments/15s15za/uploading_model_to_hugging_face_is_stuck_at/ | false | false | 1 | null | |
How to fine-tune llama2 on Mac M2 with 16gb? | 7 | I am new to LLMs. I understand that quantized models of Llama2 can be run on MacBook with optimum use of GPU. I was wondering if it is also possible to fine tune on Mac with custom dataset? Any examples in Python on how to do this would be helpful. | 2023-08-15T17:57:45 | https://www.reddit.com/r/LocalLLaMA/comments/15rzr3y/how_to_finetune_llama2_on_mac_m2_with_16gb/ | sbs1799 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 15rzr3y | false | null | t3_15rzr3y | /r/LocalLLaMA/comments/15rzr3y/how_to_finetune_llama2_on_mac_m2_with_16gb/ | false | false | self | 7 | null |
Can I train Llama with my own PDF documents? | 14 | Is it possible to train Llama with my own PDF documents to help me with my research? For instance if I upload my documents would it be able to read and answer questions about the information on those PDF documents? I would appreciate any insights. | 2023-08-15T17:42:13 | https://www.reddit.com/r/LocalLLaMA/comments/15rzcat/can_i_train_llama_with_my_own_pdf_documents/ | RomadCV | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 15rzcat | false | null | t3_15rzcat | /r/LocalLLaMA/comments/15rzcat/can_i_train_llama_with_my_own_pdf_documents/ | false | false | self | 14 | null |
What's the best English based Voice Cloning Model? | 3 | I am exploring a couple of Voice Cloning Models for Text to Speech but haven't had much success.
I have tried --
1. serp-ai bark voice clone - [https://github.com/serp-ai/bark-with-voice-clone/](https://github.com/serp-ai/bark-with-voice-clone/)
2. and a couple of models from TTS like - [https://github.com/coqui-ai/... | 2023-08-15T16:52:38 | https://www.reddit.com/r/LocalLLaMA/comments/15ry1ga/whats_the_best_english_based_voice_cloning_model/ | apple_pie0306 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 15ry1ga | false | null | t3_15ry1ga | /r/LocalLLaMA/comments/15ry1ga/whats_the_best_english_based_voice_cloning_model/ | false | false | self | 3 | {'enabled': False, 'images': [{'id': 'fqOKCqjCruczf3NIIPI7HcJI_cul8Vn8yyZM3AUWYck', 'resolutions': [{'height': 54, 'url': 'https://external-preview.redd.it/o6_Kh_eN12_VLM3qiyg-_mHEX9hgZj-BkbkTyK_rdFs.jpg?width=108&crop=smart&auto=webp&s=21f9f1c70c75c5ef484308578865ca69175136e8', 'width': 108}, {'height': 108, 'url': 'h... |
Open-Orca-Platypus is out! a 13b that surpasses llama65b!? | 290 | Today we bring the heat again!
​
We're releasing OpenOrca-Platypus2-13B, or as we call it affectionately among the team: OrcaPlaty(or Orctypus)
[https://huggingface.co/Open-Orca/OpenOrca-Platypus2-13B](https://huggingface.co/Open-Orca/OpenOrca-Platypus2-13B)
​
We have another chart-topper ready and o... | 2023-08-15T16:35:45 | https://www.reddit.com/r/LocalLLaMA/comments/15rxlrq/openorcaplatypus_is_out_a_13b_that_surpasses/ | Alignment-Lab-AI | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 15rxlrq | false | null | t3_15rxlrq | /r/LocalLLaMA/comments/15rxlrq/openorcaplatypus_is_out_a_13b_that_surpasses/ | false | false | self | 290 | {'enabled': False, 'images': [{'id': 'aGSBdTnyxE1IQubwYPrTLMgh1zVjFUQ3ibFoSW3qVqQ', 'resolutions': [{'height': 58, 'url': 'https://external-preview.redd.it/92pOcI2HbwHEJEZVaDTjd0JmHRXYK3T73r-a1mRqOeg.jpg?width=108&crop=smart&auto=webp&s=cb8346f982e7bf547cb3b5b1ce9e24c7a43bf11d', 'width': 108}, {'height': 116, 'url': 'h... |
Open-Orca-Platypus it out! a 13b surpassing llama 65b!? | 1 | Today we bring the heat again!
​
We're releasing OpenOrca-Platypus2-13B, or as we call it affectionately among the team: OrcaPlaty
[https://huggingface.co/Open-Orca/OpenOrca-Platypus2-13B](https://huggingface.co/Open-Orca/OpenOrca-Platypus2-13B)
​
We have another chart-topper ready and out the gate... | 2023-08-15T16:29:33 | https://www.reddit.com/r/LocalLLaMA/comments/15rxg6o/openorcaplatypus_it_out_a_13b_surpassing_llama_65b/ | Alignment-Lab-AI | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 15rxg6o | false | null | t3_15rxg6o | /r/LocalLLaMA/comments/15rxg6o/openorcaplatypus_it_out_a_13b_surpassing_llama_65b/ | false | false | 1 | {'enabled': False, 'images': [{'id': 'aGSBdTnyxE1IQubwYPrTLMgh1zVjFUQ3ibFoSW3qVqQ', 'resolutions': [{'height': 58, 'url': 'https://external-preview.redd.it/92pOcI2HbwHEJEZVaDTjd0JmHRXYK3T73r-a1mRqOeg.jpg?width=108&crop=smart&auto=webp&s=cb8346f982e7bf547cb3b5b1ce9e24c7a43bf11d', 'width': 108}, {'height': 116, 'url': 'h... | |
Experience of setting up LLAMA 2 70B Chat locally | 30 | **Motivation**
I was using the services of *Replicate* for prototyping prompt for an office project. However, their service was frequently returning "CUDA error device-side assert triggered". Therefore, we decided to set up 70B chat server locally. We used Nvidia A40 with 48GB RAM.
**GPU Drivers and Toolkit**
* Inst... | 2023-08-15T16:08:02 | https://www.reddit.com/r/LocalLLaMA/comments/15rwwws/experience_of_setting_up_llama_2_70b_chat_locally/ | UncertainLangur | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 15rwwws | false | null | t3_15rwwws | /r/LocalLLaMA/comments/15rwwws/experience_of_setting_up_llama_2_70b_chat_locally/ | false | false | self | 30 | null |
The LLM GPU Buying Guide - August 2023 | 331 | Hi all, here's a buying guide that I made after getting multiple questions on where to start from my network. I used Llama-2 as the guideline for VRAM requirements. Enjoy! Hope it's useful to you and if not, fight me below :)
Also, don't forget to apologize to your local gamers while you snag their GeForce cards.
[Th... | 2023-08-15T15:48:50 | https://www.reddit.com/r/LocalLLaMA/comments/15rwe7t/the_llm_gpu_buying_guide_august_2023/ | Dependent-Pomelo-853 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 15rwe7t | false | null | t3_15rwe7t | /r/LocalLLaMA/comments/15rwe7t/the_llm_gpu_buying_guide_august_2023/ | false | false | 331 | null | |
Video breakdown of the 78-page Llama-2 paper (Thumbnail created by Stable Diffusion) | 1 | [removed] | 2023-08-15T15:45:49 | https://www.reddit.com/r/LocalLLaMA/comments/15rwbew/video_breakdown_of_the_78page_llama2_paper/ | HoneyBeeStripe | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 15rwbew | false | {'oembed': {'author_name': 'Deepgram', 'author_url': 'https://www.youtube.com/@Deepgram', 'height': 200, 'html': '<iframe width="356" height="200" src="https://www.youtube.com/embed/Otb7Xi8Z0Oo?feature=oembed&enablejsapi=1" frameborder="0" allow="accelerometer; autoplay; clipboard-write; encrypted-media; gyroscope; pic... | t3_15rwbew | /r/LocalLLaMA/comments/15rwbew/video_breakdown_of_the_78page_llama2_paper/ | false | false | 1 | {'enabled': False, 'images': [{'id': 'WyY86rkRT0RQDXTSMiAQtsPJZJMRyISOfruPdNtSllI', 'resolutions': [{'height': 81, 'url': 'https://external-preview.redd.it/1gyRHKQWmD_WFyYZOrnJK6t1kzIFQrsajppxJc7cXX4.jpg?width=108&crop=smart&auto=webp&s=237cea185adcf4433a61ade59ec9133b98b6ac8b', 'width': 108}, {'height': 162, 'url': 'h... | |
Carl: A Therapist AI Models | 46 | Link to download Llama-2 model: [https://huggingface.co/ajibawa-2023/carl-llama-2-13b](https://huggingface.co/ajibawa-2023/carl-llama-2-13b)
Link for Llama model: carl-33b [https://huggingface.co/ajibawa-2023/carl-33b](https://huggingface.co/ajibawa-2023/carl-33b)
**Links for GPTQ & GGML Models are available on:** [h... | 2023-08-15T14:03:24 | https://www.reddit.com/r/LocalLLaMA/comments/15rtnsa/carl_a_therapist_ai_models/ | ajibawa-2023 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 15rtnsa | false | null | t3_15rtnsa | /r/LocalLLaMA/comments/15rtnsa/carl_a_therapist_ai_models/ | false | false | self | 46 | {'enabled': False, 'images': [{'id': 'mqTdABXx-yZoJ3Qg0xlRfhEt1V8zn1BYSMO1-nHNvUA', 'resolutions': [{'height': 58, 'url': 'https://external-preview.redd.it/IKTJF4_P5KYMdO0nYsyYtYJl7iQjls_UBMHy7y7QqGY.jpg?width=108&crop=smart&auto=webp&s=24b2dcfa9fd0923dcc75136b7b8390ac299cd302', 'width': 108}, {'height': 116, 'url': 'h... |
mapping data and model specifics to GPU/memory/system requirements | 1 | [removed] | 2023-08-15T13:36:31 | https://www.reddit.com/r/LocalLLaMA/comments/15rsyqt/mapping_data_and_model_specifics_to/ | solipcism | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 15rsyqt | false | null | t3_15rsyqt | /r/LocalLLaMA/comments/15rsyqt/mapping_data_and_model_specifics_to/ | false | false | self | 1 | null |
Any resources on how data and model translate into system requirements? | 1 | [removed] | 2023-08-15T13:34:46 | https://www.reddit.com/r/LocalLLaMA/comments/15rsx5e/any_resources_on_how_data_and_model_translate/ | solipcism | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 15rsx5e | false | null | t3_15rsx5e | /r/LocalLLaMA/comments/15rsx5e/any_resources_on_how_data_and_model_translate/ | false | false | self | 1 | null |
are there any open (public) api that serve vicuna v1.5 for testing? | 2 | Got stucked with AWS limit, so I'm searching alternative... | 2023-08-15T13:34:09 | https://www.reddit.com/r/LocalLLaMA/comments/15rswkd/are_there_any_open_public_api_that_serve_vicuna/ | Expensive_Breakfast6 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 15rswkd | false | null | t3_15rswkd | /r/LocalLLaMA/comments/15rswkd/are_there_any_open_public_api_that_serve_vicuna/ | false | false | self | 2 | null |
Bark & Whisper min requirements? | 1 | Bark & Whisper min requirements?
1. Min hardware requirements for real time gening
2. Min hardware requirements for relatively good results and short time gening (not real time)
I have R5 5600G, 16GB RAM, NO GPU, is there hope for me? | 2023-08-15T13:18:44 | https://www.reddit.com/r/LocalLLaMA/comments/15rsihe/bark_whisper_min_requirements/ | SakamotoKyu | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 15rsihe | false | null | t3_15rsihe | /r/LocalLLaMA/comments/15rsihe/bark_whisper_min_requirements/ | false | false | self | 1 | null |
AI Town starter kit | 26 | A deployable starter kit for building and customizing your own version of AI town - a virtual town where AI characters live, chat and socialize. | 2023-08-15T12:49:34 | https://x.com/stuffyokodraws/status/1691179412069445632?s=46&t=4Lg1z9tXUANCKLiHwRSk_A | Acrobatic-Site2065 | x.com | 1970-01-01T00:00:00 | 0 | {} | 15rrt0m | false | null | t3_15rrt0m | /r/LocalLLaMA/comments/15rrt0m/ai_town_starter_kit/ | false | false | default | 26 | {'enabled': False, 'images': [{'id': 'WpUgTF-JXyEFhM4-Z1knSENxY3J7DtV-MwL-5Xq14zE', 'resolutions': [{'height': 65, 'url': 'https://external-preview.redd.it/mxb_k6iVFq8s76oAXUVFxSnLE7BnfixA9oh1MM7yOHs.jpg?width=108&crop=smart&auto=webp&s=37c2a90453d7117951b6395d4d45978c54d61828', 'width': 108}, {'height': 131, 'url': 'h... |
Model for ABC midi generation? | 1 | [removed] | 2023-08-15T12:31:03 | https://www.reddit.com/r/LocalLLaMA/comments/15rrd7o/model_for_abc_midi_generation/ | chocolatebanana136 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 15rrd7o | false | null | t3_15rrd7o | /r/LocalLLaMA/comments/15rrd7o/model_for_abc_midi_generation/ | false | false | 1 | null | |
Llama 2 q4_k_s (70B) performance without GPU | 5 | Can you write your specs CPU Ram and token/s ? | 2023-08-15T11:55:41 | https://www.reddit.com/r/LocalLLaMA/comments/15rqkuw/llama_2_q4_k_s_70b_performance_without_gpu/ | grigio | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 15rqkuw | false | null | t3_15rqkuw | /r/LocalLLaMA/comments/15rqkuw/llama_2_q4_k_s_70b_performance_without_gpu/ | false | false | self | 5 | null |
Why is my GPU barely being used? Kobold | 7 | System specs: 13600KF, RX 6700xt
Whenever I run an LLM in Kobold, despite theoretically having all of the layers on the GPU, my CPU seems to be doing most of the work. Why and how do I fix this?
https://preview.redd.it/ho8av4q369ib1.png?width=205&format=png&auto=webp&s=a562b1f6079805ff9b5a62fb9813992316803665
https... | 2023-08-15T10:42:05 | https://www.reddit.com/r/LocalLLaMA/comments/15rp3ef/why_is_my_gpu_barely_being_used_kobold/ | McpeIsSoBuggy | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 15rp3ef | false | null | t3_15rp3ef | /r/LocalLLaMA/comments/15rp3ef/why_is_my_gpu_barely_being_used_kobold/ | false | false | 7 | null | |
Why is vicuna repeating itself? | 1 | [removed] | 2023-08-15T09:47:57 | https://www.reddit.com/r/LocalLLaMA/comments/15ro26d/why_is_vicuna_repeating_itself/ | McpeIsSoBuggy | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 15ro26d | false | null | t3_15ro26d | /r/LocalLLaMA/comments/15ro26d/why_is_vicuna_repeating_itself/ | false | false | default | 1 | null |
Outlines: guiding structured output from LLMs | 29 | 2023-08-15T09:46:32 | https://github.com/normal-computing/outlines | TopperBowers | github.com | 1970-01-01T00:00:00 | 0 | {} | 15ro186 | false | null | t3_15ro186 | /r/LocalLLaMA/comments/15ro186/outlines_guiding_structured_output_from_llms/ | false | false | 29 | {'enabled': False, 'images': [{'id': 'brqQ5fPAZ0cw7-xs4-II_MYzs9AZBLmG1e7XuyGdaIU', 'resolutions': [{'height': 54, 'url': 'https://external-preview.redd.it/NdwnTXluQjkQi6aI6px6JDMTlMpU1JK6lcFlalkCqcU.jpg?width=108&crop=smart&auto=webp&s=5e26bc58d4627d50f148987c1d6d21cebb7d0707', 'width': 108}, {'height': 108, 'url': 'h... | ||
[R] Instruction-tuned Large Language Models in Multiple Languages with RLHF | 10 | We've released our Okapi framework that introduces resources and models for instruction tuning for large language models (LLMs) with reinforcement learning from human feedback (RLHF) in **26 languages**. Okapi supports 8 high-resource languages, 11 medium-resource languages, and 7 low-resource languages.
Our resources... | 2023-08-15T09:07:11 | https://www.reddit.com/r/LocalLLaMA/comments/15rnbef/r_instructiontuned_large_language_models_in/ | itnguyen2015 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 15rnbef | false | null | t3_15rnbef | /r/LocalLLaMA/comments/15rnbef/r_instructiontuned_large_language_models_in/ | false | false | self | 10 | {'enabled': False, 'images': [{'id': 'aOp8k2bcfYONEiyLyjcZLFr9t3HvYWIiwJO2L3WNfrI', 'resolutions': [{'height': 54, 'url': 'https://external-preview.redd.it/Ey0B64NjL5aWm8gREyP-P7WPQZMnFLPyyc8mioWqqHM.jpg?width=108&crop=smart&auto=webp&s=8a26b8a153001827ecbfb162ed0051a8e259a677', 'width': 108}, {'height': 108, 'url': 'h... |
How to perform multi-GPU parallel inference for llama2? | 7 | Hi folks,
I tried running the 7b-chat-hf variant from meta (fp16) with 2\*RTX3060 (2\*12GB). I was able to load the model shards into both GPUs using "device\_map" in AutoModelForCausalLM.from\_pretrained() and both GPUs memory is almost full (11GB\~, 11GB\~) which is good.
But when it comes to model.generate(), ... | 2023-08-15T07:39:11 | https://www.reddit.com/r/LocalLLaMA/comments/15rlqsb/how_to_perform_multigpu_parallel_inference_for/ | cringelord000222 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 15rlqsb | false | null | t3_15rlqsb | /r/LocalLLaMA/comments/15rlqsb/how_to_perform_multigpu_parallel_inference_for/ | false | false | self | 7 | {'enabled': False, 'images': [{'id': 'XwFO1U6npNnxXTtreTz5tvpMmuCsK_ZdMABLdZj6rvo', 'resolutions': [{'height': 58, 'url': 'https://external-preview.redd.it/L2x2tb7UcKZ5UY7MoVweqtej_CDK_oNgK5qWWkOoIVw.jpg?width=108&crop=smart&auto=webp&s=33bae57943d09c41e6affe49dfcd77a2cf2e1f9c', 'width': 108}, {'height': 116, 'url': 'h... |
What does this mean for GPT4? Rate limit reached for 10KTPM-200RPM in organization on tokens per min. | 1 | Does anyone know what is this exception about? and how to resolve this issue?
*Rate limit reached for 10KTPM-200RPM in organization on tokens per min. Limit: 10000 / min. Please try again in 6ms. Contact us through our help center at* [*help.openai.com*](https://help.openai.com) *if you continue to have issues.*
&#x... | 2023-08-15T07:33:09 | https://www.reddit.com/r/LocalLLaMA/comments/15rlmrz/what_does_this_mean_for_gpt4_rate_limit_reached/ | Think_Blackberry4114 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 15rlmrz | false | null | t3_15rlmrz | /r/LocalLLaMA/comments/15rlmrz/what_does_this_mean_for_gpt4_rate_limit_reached/ | false | false | self | 1 | null |
Reproducing phi-1 | 1 | [removed] | 2023-08-15T07:03:06 | https://www.reddit.com/r/LocalLLaMA/comments/15rl3pe/reproducing_phi1/ | Sufficient_Run1518 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 15rl3pe | false | null | t3_15rl3pe | /r/LocalLLaMA/comments/15rl3pe/reproducing_phi1/ | false | false | self | 1 | null |
Can Multiprocessing be used for faster inference of Llama2 on ec2 gpu instance | 1 | Hey everyone,
I have deployed llama2 13B chat on a ec2 gpu machine g4dnxl using HF (quantized version), I was wondering can we use python multiprocessing to speed up inference.
It would be really helpful if you can provide some input. | 2023-08-15T06:57:51 | https://www.reddit.com/r/LocalLLaMA/comments/15rl002/can_multiprocessing_be_used_for_faster_inference/ | Spiritual-Rub925 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 15rl002 | false | null | t3_15rl002 | /r/LocalLLaMA/comments/15rl002/can_multiprocessing_be_used_for_faster_inference/ | false | false | self | 1 | null |
Is it possible to direct AI text generation dynamically? | 11 | So in kcpp I'll write in some details about the story, add in some authors notes and describe a building and a few characters in world info. For the most part I'm getting decent generations the mostly reflect what I am hoping for, but every now and then the AI will just become adamant that the next paragraph or two in ... | 2023-08-15T05:42:19 | https://www.reddit.com/r/LocalLLaMA/comments/15rjl4n/is_it_possible_to_direct_ai_text_generation/ | wh33t | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 15rjl4n | false | null | t3_15rjl4n | /r/LocalLLaMA/comments/15rjl4n/is_it_possible_to_direct_ai_text_generation/ | false | false | self | 11 | null |
What tools/techniques exist for me to outline a plot in point form or very brief notes and then have an entire story generated. | 1 | This would be less like collaborative story writing and more like rewriting general plot points into more interesting sentences with embelishments and details.
I see that in kcpp you can write into memory and build world info and such but you can't really just tell it the entire story briefly and then have the model ... | 2023-08-15T05:34:38 | https://www.reddit.com/r/LocalLLaMA/comments/15rjfup/what_toolstechniques_exist_for_me_to_outline_a/ | wh33t | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 15rjfup | false | null | t3_15rjfup | /r/LocalLLaMA/comments/15rjfup/what_toolstechniques_exist_for_me_to_outline_a/ | false | false | self | 1 | null |
Difference between llama-2-7b vs llama-2-7b-hf? | 3 | I've been trying to fine tune with Hugging face's SRTTrainer script (TRL). I had to convert the llama-2-7b weights to hugging face weights before using the script, why is it?.
Is there a way I can do without hf and directly load up the original llama-2 model?
Any resources are really appreciated, thank you. | 2023-08-15T04:59:07 | https://www.reddit.com/r/LocalLLaMA/comments/15riqey/difference_between_llama27b_vs_llama27bhf/ | amitsama92 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 15riqey | false | null | t3_15riqey | /r/LocalLLaMA/comments/15riqey/difference_between_llama27b_vs_llama27bhf/ | false | false | self | 3 | null |
can a model with a given context window be finetuned to have a larger context window? | 0 | can finetuning have an effect of increasing the context length? or can this be done for a particular domain ( e.g. using subject matter for that domain ? ) ?
or are the models with really large context windows like claude inherently different in their architecture or some other missing secret sauce? | 2023-08-15T04:04:24 | https://www.reddit.com/r/LocalLLaMA/comments/15rhn57/can_a_model_with_a_given_context_window_be/ | nlpllama | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 15rhn57 | false | null | t3_15rhn57 | /r/LocalLLaMA/comments/15rhn57/can_a_model_with_a_given_context_window_be/ | false | false | self | 0 | null |
How to configure oobabooga to actually get it working? | 0 | I am really new to this so maybe the solution to the problems I'm having is glaringly obvious:
Every time I load the model I get these warnings:
2023-08-15 11:24:58 WARNING:Exllama kernel is not installed, reset disable_exllama to True. This may because you installed auto_gptq using a pre-build wheel on Windows,... | 2023-08-15T03:50:23 | https://www.reddit.com/r/LocalLLaMA/comments/15rhc6n/how_to_configure_oobabooga_to_actually_get_it/ | Ethork66 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 15rhc6n | false | null | t3_15rhc6n | /r/LocalLLaMA/comments/15rhc6n/how_to_configure_oobabooga_to_actually_get_it/ | false | false | 0 | null | |
Octocoder Demo | 27 | 2023-08-15T03:41:59 | https://twitter.com/huybery/status/1691267973254991872 | ninjasaid13 | twitter.com | 1970-01-01T00:00:00 | 0 | {} | 15rh5wr | false | {'oembed': {'author_name': 'Binyuan Hui', 'author_url': 'https://twitter.com/huybery', 'cache_age': 3153600000, 'height': None, 'html': '<blockquote class="twitter-video"><p lang="en" dir="ltr">Check out our latest work 🐙OctoCoder 🐙! It's an instruction tuned CodeLLM using the natural structure of Git commits. No... | t3_15rh5wr | /r/LocalLLaMA/comments/15rh5wr/octocoder_demo/ | false | false | 27 | {'enabled': False, 'images': [{'id': 'q5pc16QA15fE6gPuzmAsIdo3UhTuJIDL8iYQzvNazQg', 'resolutions': [{'height': 108, 'url': 'https://external-preview.redd.it/wJgtrPwZv7_HU2SkGEryWNGzSzvZ-7xDzx54XXD2aeI.jpg?width=108&crop=smart&auto=webp&s=3552b6b73b35160ff2b8a09653dc657578d94463', 'width': 108}], 'source': {'height': 14... | ||
Help - only getting 0.03 tok/sec on 1080 ti | 1 | [removed] | 2023-08-15T03:39:48 | https://www.reddit.com/r/LocalLLaMA/comments/15rh47d/help_only_getting_003_toksec_on_1080_ti/ | bepispasta42069 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 15rh47d | false | null | t3_15rh47d | /r/LocalLLaMA/comments/15rh47d/help_only_getting_003_toksec_on_1080_ti/ | false | false | self | 1 | null |
Effects of Quantization of ARC Benchmark Performance | 26 | Have you ever pondered how quantization might affect model performance, or what the trade-off is between quantized methods?
We know how [quantization affects perplexity](https://www.reddit.com/r/LocalLLaMA/comments/1441jnr/k_quantization_vs_perplexity/?utm_source=share&utm_medium=web2x&context=3) but how does it affe... | 2023-08-15T03:39:07 | https://www.reddit.com/r/LocalLLaMA/comments/15rh3op/effects_of_quantization_of_arc_benchmark/ | onil_gova | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 15rh3op | false | null | t3_15rh3op | /r/LocalLLaMA/comments/15rh3op/effects_of_quantization_of_arc_benchmark/ | false | false | self | 26 | {'enabled': False, 'images': [{'id': 'lVUxULrfmQQhqgXu4A3ts4O5YovvLSFvMadANKyplII', 'resolutions': [{'height': 58, 'url': 'https://external-preview.redd.it/Myik7eECm3Ydm-TY4aIz27a4PC9eZgys--Ak5h1YWuM.jpg?width=108&crop=smart&auto=webp&s=ad03f6bb8277f6dad756e7ec27de40c72dfd35c0', 'width': 108}, {'height': 116, 'url': 'h... |
liteLLM – simple library to standardize OpenAI+ Huggingface Inference Endpoints + Replicate + Anthropic + .. | 1 | Hello r/LocalLLaMA, We just launched [liteLLM](https://github.com/BerriAI/litellm) \- one python library to call 50+ LLM models using the same Input/Output format.
liteLLM only has two functions completion()
and embedding()
and is entirely open source.
**Here's an example of how to use liteLLM**
from litel... | 2023-08-15T02:57:47 | https://www.reddit.com/r/LocalLLaMA/comments/15rfve7/litellm_simple_library_to_standardize_openai/ | VideoTo | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 15rfve7 | false | null | t3_15rfve7 | /r/LocalLLaMA/comments/15rfve7/litellm_simple_library_to_standardize_openai/ | false | false | self | 1 | {'enabled': False, 'images': [{'id': 'zNVKbeHaeI2B_H41hmQiRhsio1A_TsH0dD9ymVltNBU', 'resolutions': [{'height': 54, 'url': 'https://external-preview.redd.it/2lVdDU8iU8nIBnK7HbZwrxIDqKZJDhU6yKK7hyK6pZ4.jpg?width=108&crop=smart&auto=webp&s=b5b392448e3753b2206ccd7131c466d864463c20', 'width': 108}, {'height': 108, 'url': 'h... |
cool Llama explains LLMs and Local LLMs | 6 | Runtime: Llama 7B Chat on KoboldCPP
Custom settings for runtime:
- threads 6
- contextsize 2048
- stream
- smartcontext
- usemirostat 2 0.5 0.1
- debugmode
- blasbatcheize 64
Chat settings:
- max tokens 1024
- temperature 1
- amount to gen 512
- top k 45
- top p .95
- repetition penalty 1.1
___
PROMPT:
**Please co... | 2023-08-15T02:46:30 | https://www.reddit.com/gallery/15rfmd4 | Happy_Chicken9835 | reddit.com | 1970-01-01T00:00:00 | 0 | {} | 15rfmd4 | false | null | t3_15rfmd4 | /r/LocalLLaMA/comments/15rfmd4/cool_llama_explains_llms_and_local_llms/ | false | false | 6 | null | |
Best OS/Paid Embedding Model for Longer Token Length + Retrieval | 1 | Most of the MTEB leaderboard models have a max limit of 512 tokens, what are the best embedding models for 2k -8k context tokens, specifically for retrieval?
​
​ | 2023-08-15T02:08:47 | https://www.reddit.com/r/LocalLLaMA/comments/15requj/best_ospaid_embedding_model_for_longer_token/ | Expert-Supermarket-4 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 15requj | false | null | t3_15requj | /r/LocalLLaMA/comments/15requj/best_ospaid_embedding_model_for_longer_token/ | false | false | self | 1 | null |
Data Analytics using Llama2? | 6 | Is there any good workflow to use llama2 to perform data analytics on a csv file, perhaps using Langchain?
I noticed that Langchain has this nice agent to execute python code that can run analytics on a pandas data frame. It works very well with OpenAI models. But when I use the Langchain agent with Llama quantised 7B... | 2023-08-15T01:43:04 | https://www.reddit.com/r/LocalLLaMA/comments/15re5jq/data_analytics_using_llama2/ | Impressive-Ratio77 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 15re5jq | false | null | t3_15re5jq | /r/LocalLLaMA/comments/15re5jq/data_analytics_using_llama2/ | false | false | self | 6 | null |
The Normal Blog - Eliminating hallucinations (fast!) in Large Language Models with Finite State Machines | 34 | [The Normal Blog - Eliminating hallucinations (fast!) in Large Language Models with Finite State Machines](https://blog.normalcomputing.ai/posts/2023-07-27-regex-guided-generation/regex-guided-generation.html)
This is interesting: Regex-based logit guidance that is faster and more effective compared to things like Mic... | 2023-08-14T23:39:54 | https://www.reddit.com/r/LocalLLaMA/comments/15rb6a4/the_normal_blog_eliminating_hallucinations_fast/ | AutomataManifold | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 15rb6a4 | false | null | t3_15rb6a4 | /r/LocalLLaMA/comments/15rb6a4/the_normal_blog_eliminating_hallucinations_fast/ | false | false | self | 34 | {'enabled': False, 'images': [{'id': 'gMMGWfWaPKSKsmg0uDPhXtcZmUeH78u2lUsMDC6p96U', 'resolutions': [{'height': 83, 'url': 'https://external-preview.redd.it/tn6Pttf2f9fDIX1ydGaQTGanHqldPEorBdIJkJKNTBo.jpg?width=108&crop=smart&auto=webp&s=c8956003526204634e631901c35d5dc7ff62c907', 'width': 108}, {'height': 166, 'url': 'h... |
Getting up to speed on LLMS - Questions | 10 | Did a whirlwind tour after the Llama2 release and have some questions along the way. Also - if there are other communities like this (reddit, disc0rd, twitter, whatever) please point me in the right direction! Ok - so the questions I have:
<hr></hr>
**Supervised Fine Tuning vs Alternatives:**
I've heard SFT is good... | 2023-08-14T23:12:23 | https://www.reddit.com/r/LocalLLaMA/comments/15rah9g/getting_up_to_speed_on_llms_questions/ | m_woodworth | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 15rah9g | false | null | t3_15rah9g | /r/LocalLLaMA/comments/15rah9g/getting_up_to_speed_on_llms_questions/ | false | false | self | 10 | {'enabled': False, 'images': [{'id': 'nkhh65ujo5BznFJFojoMPaKjGuLSpPj6KGhRov-ykOg', 'resolutions': [{'height': 108, 'url': 'https://external-preview.redd.it/MrcDZx2izDY9ERwgWmMS-Hm2M3GEKZgeYLDszSh-KrQ.jpg?width=108&crop=smart&auto=webp&s=4b647239f77bf713f4a6209cfa4867351c055fd9', 'width': 108}, {'height': 216, 'url': '... |
Self-Alignment with Instruction Backtranslation Model | 6 | 2023-08-14T23:10:28 | https://twitter.com/jaseweston/status/1690888779878330368 | ninjasaid13 | twitter.com | 1970-01-01T00:00:00 | 0 | {} | 15rafdx | false | {'oembed': {'author_name': 'Jason Weston', 'author_url': 'https://twitter.com/jaseweston', 'cache_age': 3153600000, 'height': None, 'html': '<blockquote class="twitter-video"><p lang="en" dir="ltr">🚨New Paper 🚨<br>Self-Alignment with Instruction Backtranslation<br><br>- New method auto-labels web text with instructio... | t3_15rafdx | /r/LocalLLaMA/comments/15rafdx/selfalignment_with_instruction_backtranslation/ | false | false | 6 | {'enabled': False, 'images': [{'id': 'Blw5Ugpge7pOpKDsIovry68aiujEaAD0rTsIiY3s3Xg', 'resolutions': [{'height': 64, 'url': 'https://external-preview.redd.it/uh84nsu15Pxo8lFdDV04lMNAvQoT6dF6XOtZ68ILSHY.jpg?width=108&crop=smart&auto=webp&s=c54f6a050665e7cd64ac6855f9c5d547ab826e1d', 'width': 108}], 'source': {'height': 84,... | ||
Self-Alignment with Instruction Backtranslation Model | 22 | 2023-08-14T23:10:28 | https://twitter.com/jaseweston/status/1690888779878330368 | ninjasaid13 | twitter.com | 1970-01-01T00:00:00 | 0 | {} | 15rafe1 | false | {'oembed': {'author_name': 'Jason Weston', 'author_url': 'https://twitter.com/jaseweston', 'cache_age': 3153600000, 'height': None, 'html': '<blockquote class="twitter-video"><p lang="en" dir="ltr">🚨New Paper 🚨<br>Self-Alignment with Instruction Backtranslation<br><br>- New method auto-labels web text with instructio... | t3_15rafe1 | /r/LocalLLaMA/comments/15rafe1/selfalignment_with_instruction_backtranslation/ | false | false | 22 | {'enabled': False, 'images': [{'id': 'Blw5Ugpge7pOpKDsIovry68aiujEaAD0rTsIiY3s3Xg', 'resolutions': [{'height': 64, 'url': 'https://external-preview.redd.it/uh84nsu15Pxo8lFdDV04lMNAvQoT6dF6XOtZ68ILSHY.jpg?width=108&crop=smart&auto=webp&s=c54f6a050665e7cd64ac6855f9c5d547ab826e1d', 'width': 108}], 'source': {'height': 84,... | ||
Anyone test LosslessMegaCoder-llama2-7b-mini? | 3 | Title | 2023-08-14T21:31:23 | https://www.reddit.com/r/LocalLLaMA/comments/15r7rwp/anyone_test_losslessmegacoderllama27bmini/ | GG9242 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 15r7rwp | false | null | t3_15r7rwp | /r/LocalLLaMA/comments/15r7rwp/anyone_test_losslessmegacoderllama27bmini/ | false | false | self | 3 | null |
What features would you want from synthetic videos? | 2 |
It would be so nice to have a playthrough split up across x many videos to suit your schedule. Or even generate a playthrough of a specific section of the game. Something else might be an interactive chat similar to Twitch where the synthetic Youtuber can interact with your chat in real time (assuming the gameplay is... | 2023-08-14T21:21:13 | https://www.reddit.com/r/LocalLLaMA/comments/15r7hmz/what_features_would_you_want_from_synthetic_videos/ | JebryyathHS | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 15r7hmz | false | null | t3_15r7hmz | /r/LocalLLaMA/comments/15r7hmz/what_features_would_you_want_from_synthetic_videos/ | false | false | self | 2 | null |
Dutch Llama 2 13b chat | 17 | Hi. A few days ago i tried to make ggml version for previously released Dutch model: [Mirage-Studio/llama-gaan-2-7b-chat-hf-dutch-epoch-5 · Hugging Face](https://huggingface.co/Mirage-Studio/llama-gaan-2-7b-chat-hf-dutch-epoch-5) but didn't succeded cause i don't know how to set pad\_token\_id to required value. (The ... | 2023-08-14T21:03:35 | https://www.reddit.com/r/LocalLLaMA/comments/15r70aw/dutch_llama_2_13b_chat/ | Languages_Learner | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 15r70aw | false | null | t3_15r70aw | /r/LocalLLaMA/comments/15r70aw/dutch_llama_2_13b_chat/ | false | false | self | 17 | {'enabled': False, 'images': [{'id': 'EJ5DYnD2vg_zYKaAoFJlB-iCdfw22VMPLuOGA7XVaa8', 'resolutions': [{'height': 58, 'url': 'https://external-preview.redd.it/mL4osyL0Cre_EZuLsVZSBggJdfM5qujs44zE-F5sxxQ.jpg?width=108&crop=smart&auto=webp&s=e932f1b2fd8ef5f036f34be2c36c414e7612f59d', 'width': 108}, {'height': 116, 'url': 'h... |
Llama2 local 3090 24gb error | 1 | [removed] | 2023-08-14T20:29:59 | https://www.reddit.com/r/LocalLLaMA/comments/15r62xa/llama2_local_3090_24gb_error/ | OnY86 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 15r62xa | false | null | t3_15r62xa | /r/LocalLLaMA/comments/15r62xa/llama2_local_3090_24gb_error/ | false | false | self | 1 | null |
Let's say I have $6,000-8,000 for a new computer to run local llamas- what should I get? | 140 | I'm having a ton of fun playing with LLMs on my computer, but my rig is 5 years old. While fine for most work, not anywhere good enough for this use case. I can spend \~$6,000-$8,000 on a new computer (I know, this sounds like a lot, but it's not too bad amortized over the next 3-5 years. And if a local LLM saves me ev... | 2023-08-14T19:40:56 | https://www.reddit.com/r/LocalLLaMA/comments/15r4ra0/lets_say_i_have_60008000_for_a_new_computer_to/ | Berberis | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 15r4ra0 | false | null | t3_15r4ra0 | /r/LocalLLaMA/comments/15r4ra0/lets_say_i_have_60008000_for_a_new_computer_to/ | false | false | self | 140 | null |
How to increase domain knowledge in falcon 7b | 5 | I have been seeing many tutorials on how to fine tune a model by using Q&A chats.
However, what I want to do is have a chat bot that can answer questions based on multiple text files that I have, and hopefully scale it to hundreds of text files. So instead of feeding Q&A for training, I just feed text files for examp... | 2023-08-14T19:31:46 | https://www.reddit.com/r/LocalLLaMA/comments/15r4ig1/how_to_increase_domain_knowledge_in_falcon_7b/ | ConsistentHamster2 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 15r4ig1 | false | null | t3_15r4ig1 | /r/LocalLLaMA/comments/15r4ig1/how_to_increase_domain_knowledge_in_falcon_7b/ | false | false | self | 5 | null |
Can someone explain to me what ggml is and how does it work? | 1 | [removed] | 2023-08-14T19:15:02 | https://www.reddit.com/r/LocalLLaMA/comments/15r41go/can_someone_explain_to_me_what_ggml_is_and_how/ | Leading_Boot7734 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 15r41go | false | null | t3_15r41go | /r/LocalLLaMA/comments/15r41go/can_someone_explain_to_me_what_ggml_is_and_how/ | false | false | self | 1 | null |
Student Getting into AI from the Ground UP: Where to Start? | 1 | [removed] | 2023-08-14T19:00:51 | https://www.reddit.com/r/LocalLLaMA/comments/15r3n4s/student_getting_into_ai_from_the_ground_up_where/ | KvAk_AKPlaysYT | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 15r3n4s | false | null | t3_15r3n4s | /r/LocalLLaMA/comments/15r3n4s/student_getting_into_ai_from_the_ground_up_where/ | false | false | self | 1 | null |
Whats the app/tool are you using for code exploration? | 1 | I'm looking for a tool that will help speed up the process of code exploration. So far I've tried [cody AI](https://imgur.com/a/nRKsLXQ). I have found the cody to be quite useful at providing explanations however cody's consistent hallucinations when it needs to give real code are a major drawback.
To illustrate my us... | 2023-08-14T18:11:38 | https://www.reddit.com/r/LocalLLaMA/comments/15r2ag3/whats_the_apptool_are_you_using_for_code/ | nuusain | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 15r2ag3 | false | null | t3_15r2ag3 | /r/LocalLLaMA/comments/15r2ag3/whats_the_apptool_are_you_using_for_code/ | false | false | self | 1 | null |
Any news on the 30G LLaMA 2 model? | 54 | When LLaMA 2 was released, it was stated publically that the 30G model would be delayed due to some issues. I haven't heard anything since. Is it ever going to be released? | 2023-08-14T18:00:11 | https://www.reddit.com/r/LocalLLaMA/comments/15r1yqh/any_news_on_the_30g_llama_2_model/ | belladorexxx | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 15r1yqh | false | null | t3_15r1yqh | /r/LocalLLaMA/comments/15r1yqh/any_news_on_the_30g_llama_2_model/ | false | false | self | 54 | null |
MeZo with litgpt? | 8 | Litgpt is nanogpt retooled to support llama2
​
[https://github.com/princeton-nlp/MeZO](https://github.com/princeton-nlp/MeZO)
​
I'm wondering how feasible it is to incorporate mezo into this boilerplate code to enable training llms on much smaller footprint of vram. | 2023-08-14T17:56:43 | https://www.reddit.com/r/LocalLLaMA/comments/15r1vhr/mezo_with_litgpt/ | Thistleknot | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 15r1vhr | false | null | t3_15r1vhr | /r/LocalLLaMA/comments/15r1vhr/mezo_with_litgpt/ | false | false | self | 8 | {'enabled': False, 'images': [{'id': 'A27O_3WGGvMQ5Y02jVgrRrTC5e0GEQ_UOL9oJyS5zVs', 'resolutions': [{'height': 54, 'url': 'https://external-preview.redd.it/IRdxpULnKAWdLyc5ZwtQXIACKcaS72j9cVdYcJ7Uuds.jpg?width=108&crop=smart&auto=webp&s=f7ef9497e07f3b1c5f8c030c57fa27a2e5a80fa6', 'width': 108}, {'height': 108, 'url': 'h... |
GPU-Accelerated LLM on a $100 Orange Pi | 172 | Yes, it's possible to run GPU-accelerated LLM smoothly on an embedded device at a reasonable speed.
The Machine Learning Compilation ([MLC](https://github.com/mlc-ai/mlc-llm)) techniques enable you to run many LLMs natively on various devices with acceleration. In this example, we made it successfully run Llama-2-... | 2023-08-14T17:45:18 | https://www.reddit.com/r/LocalLLaMA/comments/15r1kcl/gpuaccelerated_llm_on_a_100_orange_pi/ | EmotionalFeed0 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 15r1kcl | false | null | t3_15r1kcl | /r/LocalLLaMA/comments/15r1kcl/gpuaccelerated_llm_on_a_100_orange_pi/ | false | false | 172 | {'enabled': False, 'images': [{'id': 'IZir45h_ISdZyWHdPbGpn5tLmvUKO-U0N3jB3pwPF4c', 'resolutions': [{'height': 54, 'url': 'https://external-preview.redd.it/tf0Cfb_7iHIOefWyFYIdn_lsrWbzI8P9qa0sa3nTBzs.jpg?width=108&crop=smart&auto=webp&s=017a6ffa978813dbeaa475e66c0bb323e91eff10', 'width': 108}, {'height': 108, 'url': 'h... | |
Models for function calls? | 4 | Are there good open source models that are fine-tuned for function calling?
By fine-tuned for function calling, I mean using a function signature or a JSON schema (similar to OpenAI does) as part of the prompt, and responding JSON that makes that schema.
So the prompt would be something like this
\- function signatu... | 2023-08-14T17:34:43 | https://www.reddit.com/r/LocalLLaMA/comments/15r1a0g/models_for_function_calls/ | lgrammel | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 15r1a0g | false | null | t3_15r1a0g | /r/LocalLLaMA/comments/15r1a0g/models_for_function_calls/ | false | false | self | 4 | null |
Expand the Context Length with RoPE from a β-based Encoding perspective | 57 | A very interesting blog. The link is [here](https://normxu.github.io/Rethinking-Rotary-Position-Embedding/) (part-1) and [here](https://normxu.github.io/Rethinking-Rotary-Position-Embedding-2/) (part-2)
The writer claims NTK-ScaleRoPE has flaws. A minor modification can fix the flaw and further improve ppl on very lo... | 2023-08-14T17:33:21 | https://www.reddit.com/r/LocalLLaMA/comments/15r18rx/expand_the_context_length_with_rope_from_a_βbased/ | Alternative_World936 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 15r18rx | false | null | t3_15r18rx | /r/LocalLLaMA/comments/15r18rx/expand_the_context_length_with_rope_from_a_βbased/ | false | false | self | 57 | null |
llama2-22b-daydreamer-v2 release. Why are there almost no models like 22B? | 8 | [https://huggingface.co/nkpz/llama2-22b-daydreamer-v2](https://huggingface.co/nkpz/llama2-22b-daydreamer-v2)
[https://huggingface.co/TheBloke/llama2-22B-daydreamer-v2-GGML](https://huggingface.co/TheBloke/llama2-22B-daydreamer-v2-GGML)
[https://huggingface.co/TheBloke/llama2-22B-daydreamer-v2-GPTQ](https://huggingfac... | 2023-08-14T17:21:28 | https://www.reddit.com/r/LocalLLaMA/comments/15r0x32/llama222bdaydreamerv2_release_why_are_there/ | Jipok_ | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 15r0x32 | false | null | t3_15r0x32 | /r/LocalLLaMA/comments/15r0x32/llama222bdaydreamerv2_release_why_are_there/ | false | false | self | 8 | {'enabled': False, 'images': [{'id': 'dCsf5vAEJpcaBc7Sxwa__PZgQCtqV0_7cqOMVqtli_M', 'resolutions': [{'height': 58, 'url': 'https://external-preview.redd.it/58LiW5YgG4aia_aL8VmboETRkGAFcLCCOGNu8Rj2nUg.jpg?width=108&crop=smart&auto=webp&s=e7b5cf484a713676cb47145ca91876ef21b9d6b2', 'width': 108}, {'height': 116, 'url': 'h... |
What is the difference in llama2 versions fine-tuned for specific tasks? | 5 | Hi,
Way back, before the dawn of ChatGPT, I have fine-tuned T5 model for email writing and it worked quite well. Now I'm trying out llama2-7b and am wondering, what is the difference between llama2 versions with different number of parameters in case of fine-tuning them for specific tasks.
I would appreciate if anyon... | 2023-08-14T16:44:09 | https://www.reddit.com/r/LocalLLaMA/comments/15qzwir/what_is_the_difference_in_llama2_versions/ | ThickDoctor007 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 15qzwir | false | null | t3_15qzwir | /r/LocalLLaMA/comments/15qzwir/what_is_the_difference_in_llama2_versions/ | false | false | self | 5 | null |
Best method to query txt files with GPTQ Llama 2 models | 11 | Hi,
I'm currently working on a chatbot who could answer questions about documents put in entry.
I've already made a implementation, using this model: [TheBloke/WizardLM-13B-V1-1-SuperHOT-8K-GPTQ · Hugging Face](https://huggingface.co/TheBloke/WizardLM-13B-V1-1-SuperHOT-8K-GPTQ), loaded with auto\_gptq, this embedding... | 2023-08-14T12:27:25 | https://www.reddit.com/r/LocalLLaMA/comments/15qtb0u/best_method_to_query_txt_files_with_gptq_llama_2/ | RAPHCVR | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 15qtb0u | false | null | t3_15qtb0u | /r/LocalLLaMA/comments/15qtb0u/best_method_to_query_txt_files_with_gptq_llama_2/ | false | false | 11 | {'enabled': False, 'images': [{'id': 'IiRXHqUc0kYWhj4GBsO_uvu3Zye_fDD6EHAmGEU9D5s', 'resolutions': [{'height': 58, 'url': 'https://external-preview.redd.it/JU-UDjlgD0Z3eh6zpliumsPdKw2iTwoMHk-4ciC_YRA.jpg?width=108&crop=smart&auto=webp&s=9f95c2ee0beda68c63370211fea05ba8434083ac', 'width': 108}, {'height': 116, 'url': 'h... | |
How to finetune LLM for text classfication | 10 | Now I have a scenario where I need to input the title of the product and return the product category it belongs to. There are a total of 7000 product categories. At present, I have tried to train and test using 300W products with Bert and fasttext respectively, and the final Acc is about 72%, so I would like to ask, ca... | 2023-08-14T11:34:39 | https://www.reddit.com/r/LocalLLaMA/comments/15qs6v7/how_to_finetune_llm_for_text_classfication/ | KneeNo79 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 15qs6v7 | false | null | t3_15qs6v7 | /r/LocalLLaMA/comments/15qs6v7/how_to_finetune_llm_for_text_classfication/ | false | false | self | 10 | null |
How to expose a model into an API? | 31 | I've a PC with a RTX 3090 and I would like to use it for models like Llama2. I would like to open a port and offer the inference power of that PC to other apps running LangChain outside the home network.
I've thought about combine FastAPI with HF local package but I believe that there are other options out there much ... | 2023-08-14T11:28:29 | https://www.reddit.com/r/LocalLLaMA/comments/15qs2br/how_to_expose_a_model_into_an_api/ | angeljdm | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 15qs2br | false | null | t3_15qs2br | /r/LocalLLaMA/comments/15qs2br/how_to_expose_a_model_into_an_api/ | false | false | self | 31 | null |
Best Model for Natural Language to SQL? | 38 | Anyone know what the best model for NL to SQL is? Are there any off the shelf model that works for complex queries or better to finetune LlaMA2 on some dataset? | 2023-08-14T11:22:20 | https://www.reddit.com/r/LocalLLaMA/comments/15qry0n/best_model_for_natural_language_to_sql/ | perseus_14 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 15qry0n | false | null | t3_15qry0n | /r/LocalLLaMA/comments/15qry0n/best_model_for_natural_language_to_sql/ | false | false | self | 38 | null |
LLaMA-2-chat vs LLaMa-2-base? | 1 | What are the advantages and disadvantages of each? Is the base version more capable of following instructions or are they both just as capable except the chat model has an extra advantage of being able to do dialogue? If so, is there any reason to use the base model? | 2023-08-14T10:04:36 | https://www.reddit.com/r/LocalLLaMA/comments/15qqfrf/llama2chat_vs_llama2base/ | ImNotLegitLol | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 15qqfrf | false | null | t3_15qqfrf | /r/LocalLLaMA/comments/15qqfrf/llama2chat_vs_llama2base/ | false | false | self | 1 | null |
What are the different finetunes for the LLaMa 2 model? How do you all find them? | 1 | So far, I found the ones listed in [https://www.reddit.com/r/LocalLLaMA/wiki/models/](https://www.reddit.com/r/LocalLLaMA/wiki/models/), but how do you all find them online? I tried "LLaMa 2 finetuned models", "LLaMA 2 finetuned models huggingface", etc. But I only find ones like some "uncensored" version on huggingfac... | 2023-08-14T10:02:20 | https://www.reddit.com/r/LocalLLaMA/comments/15qqe63/what_are_the_different_finetunes_for_the_llama_2/ | ImNotLegitLol | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 15qqe63 | false | null | t3_15qqe63 | /r/LocalLLaMA/comments/15qqe63/what_are_the_different_finetunes_for_the_llama_2/ | false | false | self | 1 | null |
Llama V2 as Langchain react agent | 1 | Any good results? I tried with 7B and it wasn't ideal. Will try again with a larger model. I wanted to use it so I can trigger RAG based on the query instead of relying on trigger keywords using spacy. | 2023-08-14T09:36:25 | https://www.reddit.com/r/LocalLLaMA/comments/15qpxbh/llama_v2_as_langchain_react_agent/ | sgt_banana1 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 15qpxbh | false | null | t3_15qpxbh | /r/LocalLLaMA/comments/15qpxbh/llama_v2_as_langchain_react_agent/ | false | false | self | 1 | null |
Deepspeed with remote servers | 1 | Hello,
I have 5 GPUs (2x P100 & 3x T4) installed on different servers (DL380 gen9). Would I be able to use deepspeed for training across multiple servers? What about inference with say, FastChat?
Thanks | 2023-08-14T09:30:05 | https://www.reddit.com/r/LocalLLaMA/comments/15qpt3x/deepspeed_with_remote_servers/ | sgt_banana1 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 15qpt3x | false | null | t3_15qpt3x | /r/LocalLLaMA/comments/15qpt3x/deepspeed_with_remote_servers/ | false | false | self | 1 | null |
Programmer getting into the AI word, where do I start? | 4 | Hello, I'm a software developer with a degree in computer science, and I've been making software for the last 10 years, mostly gaming-related.
I've been playing with Chat-GPT for the last few months, and overall, I'm very impressed.
Now, I would love to get into the AI world and start to delve deep into this tech... | 2023-08-14T08:19:30 | https://www.reddit.com/r/LocalLLaMA/comments/15qol73/programmer_getting_into_the_ai_word_where_do_i/ | ExtremeMarco | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 15qol73 | true | null | t3_15qol73 | /r/LocalLLaMA/comments/15qol73/programmer_getting_into_the_ai_word_where_do_i/ | false | false | self | 4 | {'enabled': False, 'images': [{'id': 'ATQL74MV_g1rXmHjE8PuwjaUEKg4dNbmOnVODSiNEzI', 'resolutions': [{'height': 88, 'url': 'https://external-preview.redd.it/EZFGH8aEMNQBRh233adi4QfiajDtEuGbEXTBXjURO3s.jpg?width=108&crop=smart&auto=webp&s=bf1a99ded14081cf9251439f19ed8c225f1c4643', 'width': 108}, {'height': 176, 'url': 'h... |
Quantifying Content Coverage | 4 | Suppose you have a document. How would you use the predicted and true summaries independently to quantify content coverage? I had an idea to use some sort of a sentence selection histogram or a heatmap showing that the predicted summary covers more than the true summary. What do y'all suggest? | 2023-08-14T08:13:16 | https://www.reddit.com/r/LocalLLaMA/comments/15qohcs/quantifying_content_coverage/ | psj_2908 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 15qohcs | false | null | t3_15qohcs | /r/LocalLLaMA/comments/15qohcs/quantifying_content_coverage/ | false | false | self | 4 | null |
How to create Retrieval Augmented Generation (RAG) locally without using LangChain PineCone etc? | 0 | I am currently working on RAG, but I wonder how to build it locally without going through LangChain, PineCone or Haystack. It will be great if you can share, how to build it from scratch. | 2023-08-14T07:30:52 | https://www.reddit.com/r/LocalLLaMA/comments/15qnqga/how_to_create_retrieval_augmented_generation_rag/ | Think_Blackberry4114 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 15qnqga | false | null | t3_15qnqga | /r/LocalLLaMA/comments/15qnqga/how_to_create_retrieval_augmented_generation_rag/ | false | false | self | 0 | null |
Ai Dungeon style ai generation? | 16 | Hey there folks. I've recently started to use oogabooga and a couple of models as alternative to GPT-4. I have so far used both the chat and instruct features, but I want something more in between these two, not necessarily just a chat bot, but at the same time not just a bit which creates a whole ass story with no inp... | 2023-08-14T06:04:55 | https://www.reddit.com/r/LocalLLaMA/comments/15qm4ng/ai_dungeon_style_ai_generation/ | Grucciman69420 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 15qm4ng | false | null | t3_15qm4ng | /r/LocalLLaMA/comments/15qm4ng/ai_dungeon_style_ai_generation/ | false | false | self | 16 | null |
How good is GPT-4 vs GitHub Co-Pilot? | 14 | How good is GPT-4 vs GitHub Co-Pilot for a non programming background person? If I have to pay for one subscription, which would be better for code writing for my project and debugging? | 2023-08-14T05:22:11 | https://www.reddit.com/r/LocalLLaMA/comments/15qlbfu/how_good_is_gpt4_vs_github_copilot/ | nolovenoshame | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 15qlbfu | false | null | t3_15qlbfu | /r/LocalLLaMA/comments/15qlbfu/how_good_is_gpt4_vs_github_copilot/ | false | false | self | 14 | null |
Finally making the switch! Can anyone recommend models specifically for coding? | 86 | I’m cancelling my GPT-4 plus membership as it is no longer useful for debugging code. At first I started seeing people constantly complaining of the performance decrease recently. I didn’t really notice until last week as I only used it for debugging which it was really useful. Now I’m constantly getting hallucinations... | 2023-08-14T01:54:48 | https://www.reddit.com/r/LocalLLaMA/comments/15qh0sy/finally_making_the_switch_can_anyone_recommend/ | ETHwillbeatBTC | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 15qh0sy | false | null | t3_15qh0sy | /r/LocalLLaMA/comments/15qh0sy/finally_making_the_switch_can_anyone_recommend/ | false | false | self | 86 | null |
I'm confused. Can someone ELI5 what the various system requirements are for LLMs | 2 | HI LocalLLAaMA,
Could someone explain how to understand system requirements for LLMs and how these requirements change as the parameter counts increase.
Questions I'm interested in.
Is it all about how big your graphics card is?
Is it all about CPU?
What role does RAM play?
Can you estimate based on system specs ... | 2023-08-14T01:32:59 | https://www.reddit.com/r/LocalLLaMA/comments/15qgjt9/im_confused_can_someone_eli5_what_the_various/ | Extreme-Snow-5888 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 15qgjt9 | false | null | t3_15qgjt9 | /r/LocalLLaMA/comments/15qgjt9/im_confused_can_someone_eli5_what_the_various/ | false | false | default | 2 | null |
creating a source of truth for models | 18 | i have a general idea of how this would play out but just wondering if something like this has been done before?
I found [this curated list of python algorithms](https://github.com/TheAlgorithms/Python) and thought I could leverage it to build a knowledge bank for my local LLMs. I'm running Wizardcoder-15B, which is `... | 2023-08-14T00:30:01 | https://www.reddit.com/r/LocalLLaMA/comments/15qf6gm/creating_a_source_of_truth_for_models/ | LyPreto | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 15qf6gm | false | null | t3_15qf6gm | /r/LocalLLaMA/comments/15qf6gm/creating_a_source_of_truth_for_models/ | false | false | self | 18 | {'enabled': False, 'images': [{'id': 'onDFjxN-rn4OIO8z5nETEYsWQ8GOY1EpVh8qDmNFZ54', 'resolutions': [{'height': 54, 'url': 'https://external-preview.redd.it/hQsMPna885A-2fGdNsqjmPxWa12zb85g-Cn7VsiEn9Q.jpg?width=108&crop=smart&auto=webp&s=80d0b4282eece9219246b53307b689f858a1346f', 'width': 108}, {'height': 108, 'url': 'h... |
Online Host service for AI/ML | 1 | I'm currently working on a personal project where I must host an AI service based on llama2 in order to build an API. As you might know, Artificial intelligence requires an specific (not cheap) hardware to be ran in.
Does anybody know any company that could solve this problem with reasonable prices?
PD: I'm currently... | 2023-08-13T23:47:27 | https://www.reddit.com/r/LocalLLaMA/comments/15qe7oy/online_host_service_for_aiml/ | Responsible-Sky8889 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 15qe7oy | false | null | t3_15qe7oy | /r/LocalLLaMA/comments/15qe7oy/online_host_service_for_aiml/ | false | false | self | 1 | null |
Should I fine tune a LLM to overcome context length limitation? | 12 | I need to accomplish a task, and I'm uncertain about how to proceed.
I have two tables at my disposal. The first is the "canon" table, housing the official IDs and store names for all popcorn stores within a specific region.
Canon Pop Corn Stores (17k stores) canon\_id, store\_name, store\_address
The second table i... | 2023-08-13T22:57:11 | https://www.reddit.com/r/LocalLLaMA/comments/15qd0as/should_i_fine_tune_a_llm_to_overcome_context/ | Pop-Huge | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 15qd0as | false | null | t3_15qd0as | /r/LocalLLaMA/comments/15qd0as/should_i_fine_tune_a_llm_to_overcome_context/ | false | false | self | 12 | null |
Another Beginner Post: Local LLM + LangChain Question | 4 | Hi! I'm very new to AI/ML, so feel free to let me know if I misuse terminology or need to clarify. I'm looking to host an LLM that I can train on private pdfs, later finetune with csv files, and at the end have its outputs appear on a website I'm contributing to. I looked into how to properly do that, but a lot of sour... | 2023-08-13T22:10:53 | https://www.reddit.com/r/LocalLLaMA/comments/15qbvug/another_beginner_post_local_llm_langchain_question/ | lankymarionette | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 15qbvug | false | null | t3_15qbvug | /r/LocalLLaMA/comments/15qbvug/another_beginner_post_local_llm_langchain_question/ | false | false | self | 4 | null |
CUDA out of memory when finetuning 3B model | 6 | Hello everyone I'm trying to finetune a 3b model on Colab's T4 but I'm getting CUDA out of memory issues. I'm using batch size of 1 and bfloat16. What did I do wrong?
CODE:
[https://gist.github.com/AmgadHasan/72b06cb8adc2d2217cca8c6790858685](https://gist.github.com/AmgadHasan/72b06cb8adc2d2217cca8c6790858685) | 2023-08-13T21:12:10 | https://www.reddit.com/r/LocalLLaMA/comments/15qaeom/cuda_out_of_memory_when_finetuning_3b_model/ | Amgadoz | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 15qaeom | false | null | t3_15qaeom | /r/LocalLLaMA/comments/15qaeom/cuda_out_of_memory_when_finetuning_3b_model/ | false | false | self | 6 | {'enabled': False, 'images': [{'id': 'OAXSl8SY6T3JK9MGQyKxkoYbqZ71HQRYXLeB8CV0NXg', 'resolutions': [{'height': 54, 'url': 'https://external-preview.redd.it/4-DxLM-C2Ve3tHmVL5ITI6GRtMVG8PzzdBuCKiaabfE.jpg?width=108&crop=smart&auto=webp&s=d5811c5bda5fece1040636a6af8702ba790f0fd4', 'width': 108}, {'height': 108, 'url': 'h... |
Oh No, I just Realized Something | 0 | I just realized something about AI.
If you have (now or in a few years) an AI friend / assistant /etc with a character and a personality and you built a long time relationship with him/her.
If that AI is hosted on a company's server:
The company might get hacked
Or simply will just move from AI altogether to somethi... | 2023-08-13T20:46:48 | https://www.reddit.com/r/LocalLLaMA/comments/15q9rs0/oh_no_i_just_realized_something/ | SakamotoKyu | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 15q9rs0 | false | null | t3_15q9rs0 | /r/LocalLLaMA/comments/15q9rs0/oh_no_i_just_realized_something/ | false | false | self | 0 | null |
Is there a way to add positive and negative keywords? | 6 | So, when generating images with Stable Diffusion, you add positive and negative prompts to guide the weighting. You fill the positive prompt with a rough idea of what you want, usually a list of keywords. And you add keywords to the negative prompts in order to avoid certain things, like nudity, blood or extra limbs.
... | 2023-08-13T20:30:59 | https://www.reddit.com/r/LocalLLaMA/comments/15q9dq0/is_there_a_way_to_add_positive_and_negative/ | Pumpkim | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 15q9dq0 | false | null | t3_15q9dq0 | /r/LocalLLaMA/comments/15q9dq0/is_there_a_way_to_add_positive_and_negative/ | false | false | self | 6 | null |
Repetition penalty application in proportion to historical token frequency. Thoughts? | 0 | I have a model that I run for long periods of time on the same context. Days, or hundreds of thousands of tokens will go through the same context
One of the issues I see when the model has been running for a while, is that the model slowly drifts from it's base. One of the biggest issues is that the model will frequen... | 2023-08-13T18:56:37 | https://www.reddit.com/r/LocalLLaMA/comments/15q707k/repetition_penalty_application_in_proportion_to/ | mrjackspade | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 15q707k | false | null | t3_15q707k | /r/LocalLLaMA/comments/15q707k/repetition_penalty_application_in_proportion_to/ | 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.