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 ⌀ |
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
Train model to answer questions about large text corpus | 4 | I have a large corpus of text and I’m trying to figure out the best way to train a model to answer questions about it. Ideally being able to reference the file (or even section within) where the answer is based on.
I know this is a very hard problem to solve so just looking to brainstorm potential avenues here!
Thank... | 2023-10-07T10:15:15 | https://www.reddit.com/r/LocalLLaMA/comments/1722x86/train_model_to_answer_questions_about_large_text/ | joandadg | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 1722x86 | false | null | t3_1722x86 | /r/LocalLLaMA/comments/1722x86/train_model_to_answer_questions_about_large_text/ | false | false | self | 4 | null |
How to handle summarization of sub-topics using a document after chunking. | 1 | [removed] | 2023-10-07T09:53:16 | https://www.reddit.com/r/LocalLLaMA/comments/1722kq4/how_to_handle_summarization_of_subtopics_using_a/ | vile_proxima | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 1722kq4 | false | null | t3_1722kq4 | /r/LocalLLaMA/comments/1722kq4/how_to_handle_summarization_of_subtopics_using_a/ | false | false | self | 1 | null |
[SEEKING ADVICE] Looking for Existing Repos (Open-Source, VM-Hosted, & GPU-Compatible) | 5 | Greetings,
I'm on the hunt for an existing repositories that can fulfill that meets the following criteria:
1. Content Collection: Capability to read and extract text from multiple document formats, such as PDF and DOCX files.
2. Content Reformulation: After text extraction, the ability to rephrase the content in a s... | 2023-10-07T09:47:35 | https://www.reddit.com/r/LocalLLaMA/comments/1722hgl/seeking_advice_looking_for_existing_repos/ | SociallyF | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 1722hgl | false | null | t3_1722hgl | /r/LocalLLaMA/comments/1722hgl/seeking_advice_looking_for_existing_repos/ | false | false | self | 5 | {'enabled': False, 'images': [{'id': 'UdD1knbC4cRmQVFvN1DUIenSmYwGYd-d8pxwB2oW-Sw', 'resolutions': [{'height': 54, 'url': 'https://external-preview.redd.it/t0jojkb5dh-rbN5LghlrqUMm763fgwvjXXDfxLL5hJs.jpg?width=108&crop=smart&auto=webp&s=2b2457f92820df9f133e2ac03d365997ee326ec2', 'width': 108}, {'height': 108, 'url': 'h... |
Error using trained LoRAs in llamacpp | 5 | I used this command:
./finetune --model-base /Users/yuki/Downloads/models/pygmalion-2-7b.Q5\_K\_M.gguf --train-data /Users/yuki/Downloads/datasets/test.txt --threads 14 --lora-out lora.gguf --save-every 1 --sample-start "<s>" --include-sample-start --seed 1 --use-flash --lora-alpha 4 --lora-r 4 --adam-alpha 0.001 --ad... | 2023-10-07T06:38:30 | https://www.reddit.com/r/LocalLLaMA/comments/171zgpi/error_using_trained_loras_in_llamacpp/ | yukiarimo | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 171zgpi | false | null | t3_171zgpi | /r/LocalLLaMA/comments/171zgpi/error_using_trained_loras_in_llamacpp/ | false | false | self | 5 | null |
Phind 2 is seriously brain damanged or i am doing something wrong? | 1 | I saw phind as the best coding model before so i tried and results are really bad. cannot even answer simple git questions
```
ollama run phindq5
>>> I want to sort branches by latest commit. can you give me git command for that
?
To set up a Google Cloud Storage and interact with it via Python, follow ... | 2023-10-07T05:29:27 | https://www.reddit.com/r/LocalLLaMA/comments/171ybly/phind_2_is_seriously_brain_damanged_or_i_am_doing/ | 0xPark | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 171ybly | false | null | t3_171ybly | /r/LocalLLaMA/comments/171ybly/phind_2_is_seriously_brain_damanged_or_i_am_doing/ | false | false | self | 1 | null |
I made a custom webUI for tinyLlama! | 1 | [removed] | 2023-10-07T05:02:10 | https://www.reddit.com/r/LocalLLaMA/comments/171xvdk/i_made_a_custom_webui_for_tinyllama/ | vatsadev | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 171xvdk | false | null | t3_171xvdk | /r/LocalLLaMA/comments/171xvdk/i_made_a_custom_webui_for_tinyllama/ | false | false | self | 1 | null |
LLM Specialized Linux Distro | 1 | Is there any Linux distro which is ready for LLM inference, training, and fine tuning out of the box? Hope it just like HiveOS distro for crypto mining. Right after it installed on SSD it will ready to download models from Huggingface repo.. | 2023-10-07T04:48:28 | https://www.reddit.com/r/LocalLLaMA/comments/171xmon/llm_specialized_linux_distro/ | koesn | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 171xmon | false | null | t3_171xmon | /r/LocalLLaMA/comments/171xmon/llm_specialized_linux_distro/ | false | false | self | 1 | null |
Pandalyst Files | 2 | Can anyone provide the the files of pandalyst's github files. They may have made that repo private. | 2023-10-07T03:32:11 | https://www.reddit.com/r/LocalLLaMA/comments/171w9eq/pandalyst_files/ | Outside_Solid5371 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 171w9eq | false | null | t3_171w9eq | /r/LocalLLaMA/comments/171w9eq/pandalyst_files/ | false | false | self | 2 | null |
LLM Labeling UI: Open Source data labeling tool for LLM | 1 | [removed] | 2023-10-07T02:54:47 | https://www.reddit.com/r/LocalLLaMA/comments/171visj/llm_labeling_ui_open_source_data_labeling_tool/ | Disastrous_Expert_22 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 171visj | false | null | t3_171visj | /r/LocalLLaMA/comments/171visj/llm_labeling_ui_open_source_data_labeling_tool/ | false | false | self | 1 | {'enabled': False, 'images': [{'id': 'zDSkTyoJFOmpA67Fo5QqtLryAGDJOszH5cH86G3uFtU', 'resolutions': [{'height': 54, 'url': 'https://external-preview.redd.it/dzSddicP7WyXJEA6uWsc7jFFMzwgPpiv1fCbFIdCBPA.jpg?width=108&crop=smart&auto=webp&s=b8d91bc409cabcaefee339b3b48b72a84388ed06', 'width': 108}, {'height': 108, 'url': 'h... |
Release of AI Dataset STC230908 | 40 |
In exchange for the [taken down](https://torrentfreak.com/anti-piracy-group-takes-prominent-ai-training-dataset-books3-offline-230816/) dataset books3
, which was [used to train](https://torrentfreak.com/authors-accuse-openai-of-using-pirate-sites-to-train-chatgpt-230630/) major GPT models, we are releasing our own... | 2023-10-07T02:53:43 | https://www.reddit.com/r/LocalLLaMA/comments/171vi1b/release_of_ai_dataset_stc230908/ | imperiallearner | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 171vi1b | false | null | t3_171vi1b | /r/LocalLLaMA/comments/171vi1b/release_of_ai_dataset_stc230908/ | false | false | self | 40 | null |
Do you think Orca, Tora, and Phi-1.5 are all OpenAI's Experiments in making synthetic Data for GPT-5? | 67 | A lot of Papers Coming out of Microsoft right now, Show Models Destroying benchmarks or just being really powerful for their size, and all of them made large datasets of high quality, synthetic GPT-4 Data. Orca used the student-teacher format, showing that synthetic modeling can be good, and that models can get better ... | 2023-10-07T01:46:53 | https://www.reddit.com/r/LocalLLaMA/comments/171u5dm/do_you_think_orca_tora_and_phi15_are_all_openais/ | vatsadev | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 171u5dm | false | null | t3_171u5dm | /r/LocalLLaMA/comments/171u5dm/do_you_think_orca_tora_and_phi15_are_all_openais/ | false | false | self | 67 | null |
making LLM machine need tips on CPU cooling and RAM | 1 | My school asked me to help make a LLM
They want to make 3 separate ones, with 4 3060ti's in each one.
They have z490 motherboards.
I suggested 128GB of RAM for each, and i9-13900k CPUs.
I don't know what cooling system to get.
I read that AIO may be most suitable for this.
What are your thoughts on RAM? Will they... | 2023-10-07T01:29:20 | https://www.reddit.com/r/LocalLLaMA/comments/171ts2m/making_llm_machine_need_tips_on_cpu_cooling_and/ | AlienHandTenticleMan | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 171ts2m | false | null | t3_171ts2m | /r/LocalLLaMA/comments/171ts2m/making_llm_machine_need_tips_on_cpu_cooling_and/ | false | false | self | 1 | null |
Registers in transformer networks | 3 | Is this a known and formally defined thing already? The Vits needs registers paper, World model probing accuracy on periods is higher, Yam Peleg saying padding tokens increase performance in training. Think before you say doing the same.
So what is it? What functionality is that describing? Simply more time steps to ... | 2023-10-07T01:15:43 | https://www.reddit.com/r/LocalLLaMA/comments/171thwx/registers_in_transformer_networks/ | Leptok | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 171thwx | false | null | t3_171thwx | /r/LocalLLaMA/comments/171thwx/registers_in_transformer_networks/ | false | false | self | 3 | null |
Why is there no noticeable difference in performance when using llama.cpp with multiple GPUs and CPUs versus just one GPU and CPU? | 30 | When attempting to run a 70B model with a CPU (64GB RAM) and GPU (22GB), the runtime speed is approximately 0.8t/s. Adding an idle GPU to the setup, resulting in CPU (64GB RAM) + GPU (22GB) + GPU (8GB), properly distributed the workload across both GPUs. However, the speed remains unchanged at 0.8t/s. Why is there no ... | 2023-10-07T00:15:26 | https://www.reddit.com/r/LocalLLaMA/comments/171s8s8/why_is_there_no_noticeable_difference_in/ | Scared_Ninja912 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 171s8s8 | false | null | t3_171s8s8 | /r/LocalLLaMA/comments/171s8s8/why_is_there_no_noticeable_difference_in/ | false | false | self | 30 | null |
Jupyter disconnect cause llma2 folder deletion? | 2 | i'm running into a weird issue. i use langchain with llma2 to do inference on a linux server through Jupyter. occasionally i saw the Jupyter disconnected due to timeout and somehow the folder containing the ipynb file is gone. but then later on the folder reappeared after \~1hr. anyone has suggestions? thanks. | 2023-10-06T22:52:43 | https://www.reddit.com/r/LocalLLaMA/comments/171qcg0/jupyter_disconnect_cause_llma2_folder_deletion/ | peterwu00 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 171qcg0 | false | null | t3_171qcg0 | /r/LocalLLaMA/comments/171qcg0/jupyter_disconnect_cause_llma2_folder_deletion/ | false | false | self | 2 | null |
What are the most intelligent open source models in the 3B to 34B range? | 36 | What are the **most intelligent open source models in the 3B to 34B range** for the purpose of research assistance and playing around with ideas.
I prefer a low hallucination rate and more factual, though I know the technology cannot guarantee this yet. | 2023-10-06T22:31:01 | https://www.reddit.com/r/LocalLLaMA/comments/171ptpy/what_are_the_most_intelligent_open_source_models/ | JyggalagSheo | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 171ptpy | false | null | t3_171ptpy | /r/LocalLLaMA/comments/171ptpy/what_are_the_most_intelligent_open_source_models/ | false | false | self | 36 | null |
What are the most intelligent open source models in the 13B to 34B range? | 1 | What are the **most intelligent open source models in the 3B to 34B range** for the purpose of research assistance and playing around with ideas.
I prefer a low hallucination rate and more factual, though I know the technology cannot guarantee this yet. | 2023-10-06T22:28:43 | https://www.reddit.com/r/LocalLLaMA/comments/171prql/what_are_the_most_intelligent_open_source_models/ | JyggalagSheo | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 171prql | false | null | t3_171prql | /r/LocalLLaMA/comments/171prql/what_are_the_most_intelligent_open_source_models/ | false | false | self | 1 | null |
Reason behind removing lm_head in modules in QLoRA | 1 | [removed] | 2023-10-06T21:00:38 | https://www.reddit.com/r/LocalLLaMA/comments/171nlzm/reason_behind_removing_lm_head_in_modules_in_qlora/ | Ok_Pitch7985 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 171nlzm | false | null | t3_171nlzm | /r/LocalLLaMA/comments/171nlzm/reason_behind_removing_lm_head_in_modules_in_qlora/ | false | false | self | 1 | {'enabled': False, 'images': [{'id': 'HrB8HBAhY6wUJ0qirio_rZhOBwg6FWUWhIsuGQYIeoY', 'resolutions': [{'height': 54, 'url': 'https://external-preview.redd.it/qrdt5t3Fcl5sj83wgQONwle5hEM0UGW60KVRLzsJa18.jpg?width=108&crop=smart&auto=webp&s=5363c45f5cb9c3c0fbd47960ec4f2860aa52212b', 'width': 108}, {'height': 108, 'url': 'h... |
Downloading llama2 from huggingface vs from meta | 6 | I've observed that downloading llama2-70b-chat from meta the size on disk is \~192GB whereas downloading from hf the size on disk is \~257GB. What accounts for the difference? Is there any difference in memory requirements or any differences in inference results? Thanks in advance. | 2023-10-06T20:54:16 | https://www.reddit.com/r/LocalLLaMA/comments/171ngjm/downloading_llama2_from_huggingface_vs_from_meta/ | codefinger | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 171ngjm | false | null | t3_171ngjm | /r/LocalLLaMA/comments/171ngjm/downloading_llama2_from_huggingface_vs_from_meta/ | false | false | self | 6 | null |
Are there any Open source conversational and chat-based super Agents for LLAMA-2 or Mistral LLMs? | 2 | Does any one have any idea on how to use AutoGen or SuperAgents with open source models such as LLAMA-2 or Mistral. Most of the models are require OpenAI API key which is not ideal as you do not want to put money without knowing if the agents are good enough to build something.
TIA | 2023-10-06T20:34:45 | https://www.reddit.com/r/LocalLLaMA/comments/171mza6/are_there_any_open_source_conversational_and/ | AI_ML_preneur | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 171mza6 | false | null | t3_171mza6 | /r/LocalLLaMA/comments/171mza6/are_there_any_open_source_conversational_and/ | false | false | self | 2 | null |
How to use gguf models to retrieve information from a knowledge database? | 12 | I am currently using the llama-2-7b.Q5\_K\_M.gguf model, it's not GREAT with some questions but for now, it gets the job done.
The next step for me is to grab multiple documents and create a vector database so that the model can only access that DB and answer question specific to it.
My problem is that the thing I ... | 2023-10-06T18:10:50 | https://www.reddit.com/r/LocalLLaMA/comments/171jglp/how_to_use_gguf_models_to_retrieve_information/ | charbeld | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 171jglp | false | null | t3_171jglp | /r/LocalLLaMA/comments/171jglp/how_to_use_gguf_models_to_retrieve_information/ | false | false | self | 12 | null |
3 good models | 76 | I just want to mention 3 good models that I have encountered while testing a lot of models. The evaluation surely depends on the use cases but these seems to be quite good:
* Open-Orca/Mistral-7B-OpenOrca (I used q8 on LM Studio)
* Undi95/Amethyst-13B-Mistral-GGUF (q 5\_m)
* Sao10K/Mythical-Destroyer-L2-13B-GGUF (q 5\... | 2023-10-06T17:42:21 | https://www.reddit.com/r/LocalLLaMA/comments/171iq8w/3_good_models/ | Eduard_T | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 171iq8w | false | null | t3_171iq8w | /r/LocalLLaMA/comments/171iq8w/3_good_models/ | false | false | self | 76 | null |
I try to run the mistral 7B in an iphone | 61 | 2023-10-06T17:34:09 | https://www.reddit.com/gallery/171iiw3 | engkufizz | reddit.com | 1970-01-01T00:00:00 | 0 | {} | 171iiw3 | false | null | t3_171iiw3 | /r/LocalLLaMA/comments/171iiw3/i_try_to_run_the_mistral_7b_in_an_iphone/ | false | false | 61 | null | ||
I try to run the mistral 7B in an iphone | 1 | 2023-10-06T17:29:47 | https://www.reddit.com/gallery/171ieu8 | engkufizz | reddit.com | 1970-01-01T00:00:00 | 0 | {} | 171ieu8 | false | null | t3_171ieu8 | /r/LocalLLaMA/comments/171ieu8/i_try_to_run_the_mistral_7b_in_an_iphone/ | false | false | 1 | null | ||
Llama mis-tokenization | 9 | Hi guys. I just tried to check how does Llama Tokenizer work and saw that, for example, “Yuki” is splitting like “Y” and “uki” and many other words too.
So if I will train LoRA or Llama model, do I need to update tokenizer somehow or it will understand from the dataset that those 2 tokens are the name “Yuki” or not? A... | 2023-10-06T17:18:44 | https://www.reddit.com/r/LocalLLaMA/comments/171i4xh/llama_mistokenization/ | yukiarimo | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 171i4xh | false | null | t3_171i4xh | /r/LocalLLaMA/comments/171i4xh/llama_mistokenization/ | false | false | self | 9 | null |
Workflow video showing how to convert GGML Into GGUF | 1 | [removed] | 2023-10-06T17:12:32 | https://www.reddit.com/r/LocalLLaMA/comments/171hz9i/workflow_video_showing_how_to_convert_ggml_into/ | boricuapab | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 171hz9i | false | null | t3_171hz9i | /r/LocalLLaMA/comments/171hz9i/workflow_video_showing_how_to_convert_ggml_into/ | false | false | self | 1 | {'enabled': False, 'images': [{'id': 'T6jToJ97Li44m0P3DQqBREqmpAB6Fg2ia3qfeEQ5Y6A', 'resolutions': [{'height': 81, 'url': 'https://external-preview.redd.it/fe9u0RV_etPC38obKAHxoUx6p0NOqJvk87VuJ6WojVE.jpg?width=108&crop=smart&auto=webp&s=cb96aea12b1d9288be5e1c83e8b290e01a80678b', 'width': 108}, {'height': 162, 'url': 'h... |
Best ways to give back to localllama community? | 1 | [removed] | 2023-10-06T16:09:49 | https://www.reddit.com/r/LocalLLaMA/comments/171gd6b/best_ways_to_give_back_to_localllama_community/ | rockpool7 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 171gd6b | false | null | t3_171gd6b | /r/LocalLLaMA/comments/171gd6b/best_ways_to_give_back_to_localllama_community/ | false | false | self | 1 | null |
Prompt format for continuing text and instructions in storytelling | 10 | I'm having a little trouble figuring out the best way to format prompts for continuing text or working off an outline. Which happens a lot when trying to use the model interactively for storytelling, but it also comes up when trying to include RAG information in a prompt or have a chatbot continue a conversation with i... | 2023-10-06T15:23:30 | https://www.reddit.com/r/LocalLLaMA/comments/171f62r/prompt_format_for_continuing_text_and/ | AutomataManifold | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 171f62r | false | null | t3_171f62r | /r/LocalLLaMA/comments/171f62r/prompt_format_for_continuing_text_and/ | false | false | self | 10 | null |
Need some advice on putting together a "LLM-Powered Recommendation-Based Engine " | 2 | I've recently been granted some freedom at work to showcase and prototype a feature for our In-Flight Entertainment system & it incorporates AI in some way-- naturally I'm choosing LLMs.
Here's what I have so far and I would love some feedback on possible \[easier\] ways to accomplish this:
* A “What are you in the ... | 2023-10-06T15:05:22 | https://www.reddit.com/r/LocalLLaMA/comments/171ep6o/need_some_advice_on_putting_together_a_llmpowered/ | LyPreto | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 171ep6o | false | null | t3_171ep6o | /r/LocalLLaMA/comments/171ep6o/need_some_advice_on_putting_together_a_llmpowered/ | false | false | 2 | null | |
Is there a way to add layers to Lora fine tuning? | 9 | Let's say I use Lora fine tuning. How can I tell Lora to add a specific layer to the fine tuning task.
I am specifically interested in the layer "score" | 2023-10-06T14:42:32 | https://www.reddit.com/r/LocalLLaMA/comments/171e45e/is_there_a_way_to_add_layers_to_lora_fine_tuning/ | ComplexIt | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 171e45e | false | null | t3_171e45e | /r/LocalLLaMA/comments/171e45e/is_there_a_way_to_add_layers_to_lora_fine_tuning/ | false | false | self | 9 | null |
Have you ever encountered the following problem when using CodeLLama 13B? | 5 | I give the following prompt to codellama 13B
"How to parse all filenames from a long text that may contain many filenames? Write a test case."
but I got some unrelated cases
https://preview.redd.it/uy5rc021flsb1.png?width=2514&format=png&auto=webp&s=59405a9f8d5882e0e2b07eb101fb974edb748450 | 2023-10-06T14:36:00 | https://www.reddit.com/r/LocalLLaMA/comments/171dyct/have_you_ever_encountered_the_following_problem/ | More-Shop9383 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 171dyct | false | null | t3_171dyct | /r/LocalLLaMA/comments/171dyct/have_you_ever_encountered_the_following_problem/ | false | false | 5 | null | |
Problems using quantised llama models with cpu | 6 | I have been using llama.cpp quantised models (gguf) that I downloaded from [huggingface](https://huggingface.co/TheBloke/Firefly-Llama2-13B-v1.2-GGUF/blob/main/firefly-llama2-13b-v1.2.Q5_K_M.gguf). I can run it using my 32 core cpu (2 cpus in fact) with no problem, it generated awnser very quickly. However, when I atte... | 2023-10-06T13:36:38 | https://www.reddit.com/r/LocalLLaMA/comments/171cili/problems_using_quantised_llama_models_with_cpu/ | Spiritual-Ask-9766 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 171cili | false | null | t3_171cili | /r/LocalLLaMA/comments/171cili/problems_using_quantised_llama_models_with_cpu/ | false | false | self | 6 | {'enabled': False, 'images': [{'id': 'Nem_HlfKj23cY1AT0zT4OMxuVRi3CPsvAxbzC6NgoTY', 'resolutions': [{'height': 58, 'url': 'https://external-preview.redd.it/UWiOtr7zpcVlz6RPPfi575EQYbU11lbs0BVcsBucX_c.jpg?width=108&crop=smart&auto=webp&s=8f47d707d2b278726b8eb7d5816b90869b35edb4', 'width': 108}, {'height': 116, 'url': 'h... |
Reviewers here were before active members of r/wine and r/audiophile | 1 | [removed] | 2023-10-06T13:31:26 | [deleted] | 1970-01-01T00:00:00 | 0 | {} | 171cebd | false | null | t3_171cebd | /r/LocalLLaMA/comments/171cebd/reviewers_here_were_before_active_members_of/ | false | false | default | 1 | null | ||
How to do an empirical LLM finetuning cost calculation before renting GPUs? | 1 | [removed] | 2023-10-06T13:24:49 | https://www.reddit.com/r/LocalLLaMA/comments/171c8r8/how_to_do_an_empirical_llm_finetuning_cost/ | No-Street-3020 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 171c8r8 | false | null | t3_171c8r8 | /r/LocalLLaMA/comments/171c8r8/how_to_do_an_empirical_llm_finetuning_cost/ | false | false | self | 1 | null |
Every review here | 5 | 2023-10-06T12:52:30 | ultrapcb | i.redd.it | 1970-01-01T00:00:00 | 0 | {} | 171bj61 | false | null | t3_171bj61 | /r/LocalLLaMA/comments/171bj61/every_review_here/ | false | false | 5 | {'enabled': True, 'images': [{'id': 'trYfYDnUYpzbwcqbKaafF5-MGni30RML7z3jb7wPm9Y', 'resolutions': [{'height': 60, 'url': 'https://preview.redd.it/k8297o95xksb1.png?width=108&crop=smart&auto=webp&s=cd4859eeef7d8e673480723fd2ea8fe16786e6db', 'width': 108}, {'height': 121, 'url': 'https://preview.redd.it/k8297o95xksb1.png... | |||
Best TikTok and YouTubers doing LlaMa stuff? | 0 | Can you recommend anyone making content of them testing models and hardware? I mostly see AI news and more broad content. I’m curious if anyone is out there showing what a 13B GGUF model runs like on a 32GB sys-ram setup, stuff like that. | 2023-10-06T12:22:52 | https://www.reddit.com/r/LocalLLaMA/comments/171ax9f/best_tiktok_and_youtubers_doing_llama_stuff/ | Overall-Importance54 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 171ax9f | false | null | t3_171ax9f | /r/LocalLLaMA/comments/171ax9f/best_tiktok_and_youtubers_doing_llama_stuff/ | false | false | self | 0 | null |
Please explain, how was Mistral made? | 91 | I’m trying to understand how Mistral was created in a practical sense. Did the team just take a Llama-2 base model or some other and then just start fine-tuning it until it was better, or did they start from scratch? | 2023-10-06T12:14:32 | https://www.reddit.com/r/LocalLLaMA/comments/171ar0n/please_explain_how_was_mistral_made/ | Overall-Importance54 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 171ar0n | false | null | t3_171ar0n | /r/LocalLLaMA/comments/171ar0n/please_explain_how_was_mistral_made/ | false | false | self | 91 | null |
How is "grammar" achieved with LLMs? | 45 | So I just recently realised you can force a model to output in a certain format ("grammar") using specific files like described here: [https://github.com/ggerganov/llama.cpp/blob/master/grammars/README.md](https://github.com/ggerganov/llama.cpp/blob/master/grammars/README.md)
Can anybody explain to me how this is actu... | 2023-10-06T12:09:20 | https://www.reddit.com/r/LocalLLaMA/comments/171an9p/how_is_grammar_achieved_with_llms/ | psi-love | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 171an9p | false | null | t3_171an9p | /r/LocalLLaMA/comments/171an9p/how_is_grammar_achieved_with_llms/ | false | false | self | 45 | {'enabled': False, 'images': [{'id': 'DJPqvteONpGwVVw6LzaG6b8vlDa2rv2hETCaqe0z57s', 'resolutions': [{'height': 54, 'url': 'https://external-preview.redd.it/wyCM1fHzTa-IIqHgS1QTxdSYNXn668elDj0WmYMPf_k.jpg?width=108&crop=smart&auto=webp&s=d6fa197328d583bcae7a764b40fd1214265b6852', 'width': 108}, {'height': 108, 'url': 'h... |
Task Specific Alternative to GPT-4 | 5 | I'm creating different agents to complete various tasks, and one of which is to crawl through a website to find specific information. It was easiest to prove out the concept with GPT-4 since a lot of libraries (like Langchain) already create zero shot agent implementations for that model. Now that I have proved out the... | 2023-10-06T11:27:13 | https://www.reddit.com/r/LocalLLaMA/comments/1719t4m/task_specific_alternative_to_gpt4/ | not_the_godfather | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 1719t4m | false | null | t3_1719t4m | /r/LocalLLaMA/comments/1719t4m/task_specific_alternative_to_gpt4/ | false | false | self | 5 | null |
[Synthetic dataset generation] "textbook are all you need"... But how to choose the textbook writer? (gpt4, Claude, bizon, jurassic-2...) | 4 |
I'm looking for resources, papers, or experiences that compare the performance of large language models (LLMs). I'm trying to find a honest benchmark to compare the capabilities of the latest large models, while really intrested un those: GPT-3.5 Instruct, GPT-4, Claude 2, Claude Instant 100k, Palm2-Bizon, jurassic-2,... | 2023-10-06T11:20:10 | https://www.reddit.com/r/LocalLLaMA/comments/1719oeb/synthetic_dataset_generation_textbook_are_all_you/ | BXresearch | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 1719oeb | false | null | t3_1719oeb | /r/LocalLLaMA/comments/1719oeb/synthetic_dataset_generation_textbook_are_all_you/ | false | false | self | 4 | null |
How deterministic the result of inference is for the local LLMs? | 5 | It's common knowledge that ChatGPT inference is non-deterministic. Several queries will produce different outputs with temperature = 0 (mostly because of MoE architecture). It's crucial for me to have some guaranteed results in code generation. Does anyone deal with code generation using local models (codellama, starco... | 2023-10-06T10:54:08 | https://www.reddit.com/r/LocalLLaMA/comments/17197k1/how_deterministic_the_result_of_inference_is_for/ | Greg_Z_ | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 17197k1 | false | null | t3_17197k1 | /r/LocalLLaMA/comments/17197k1/how_deterministic_the_result_of_inference_is_for/ | false | false | self | 5 | null |
[German Language] Release of EM German with models based on Llama2, Mistral and LeoLM | 1 | 2023-10-06T10:26:20 | https://github.com/jphme/EM_German/blob/main/README.md | jphme | github.com | 1970-01-01T00:00:00 | 0 | {} | 1718qgh | false | null | t3_1718qgh | /r/LocalLLaMA/comments/1718qgh/german_language_release_of_em_german_with_models/ | false | false | 1 | {'enabled': False, 'images': [{'id': 'tTTfpP7bm29TY65B0VELyvMLMyOCM73087MrCMN_uvE', 'resolutions': [{'height': 54, 'url': 'https://external-preview.redd.it/FRchFCaoN1iX2bSrP3lnTtfaX6j7CBhWU4u0bdeYYeI.jpg?width=108&crop=smart&auto=webp&s=492cb78f8304666d7648f8408e2b5e80c951ecbb', 'width': 108}, {'height': 108, 'url': 'h... | ||
Cheapest option to run TheBloke/WizardLM-33B-V1.0-Uncensored | 1 | [removed] | 2023-10-06T10:20:10 | https://www.reddit.com/r/LocalLLaMA/comments/1718msh/cheapest_option_to_run/ | reddithotel | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 1718msh | false | null | t3_1718msh | /r/LocalLLaMA/comments/1718msh/cheapest_option_to_run/ | false | false | self | 1 | null |
What's your main interest in running a local LLM instead of using an existing API? | 62 |
[View Poll](https://www.reddit.com/poll/1718a9o) | 2023-10-06T09:58:10 | https://www.reddit.com/r/LocalLLaMA/comments/1718a9o/whats_your_main_interest_in_running_a_local_llm/ | gopietz | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 1718a9o | false | null | t3_1718a9o | /r/LocalLLaMA/comments/1718a9o/whats_your_main_interest_in_running_a_local_llm/ | false | false | self | 62 | null |
Has anyone created a llama monster? | 7 | I have a goal of creating a llama monster. For arguments sake, let's say it's a monster trained on the law (although medicine or history... anything is fair game). Money is no object. I can buy two A100's and fine tune them on case hold (or pile of law). I have numerous law school textbooks in PDF format that I could u... | 2023-10-06T08:22:24 | https://www.reddit.com/r/LocalLLaMA/comments/1716uqu/has_anyone_created_a_llama_monster/ | ATuring-314 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 1716uqu | false | null | t3_1716uqu | /r/LocalLLaMA/comments/1716uqu/has_anyone_created_a_llama_monster/ | false | false | self | 7 | null |
Does LM Studio have a sort of "memory/author's note" feature? | 1 | [removed] | 2023-10-06T07:04:14 | https://www.reddit.com/r/LocalLLaMA/comments/1715p4v/does_lm_studio_have_a_sort_of_memoryauthors_note/ | Gyramuur | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 1715p4v | false | null | t3_1715p4v | /r/LocalLLaMA/comments/1715p4v/does_lm_studio_have_a_sort_of_memoryauthors_note/ | false | false | self | 1 | null |
Run your local LLMs in a text editor | 28 | Hi,
Here's an extension for Neovim to invoke Ollama, it works reasonably well with Mistral. Video is in the description.
[https://github.com/David-Kunz/gen.nvim](https://github.com/David-Kunz/gen.nvim)
I would appreciate any comments or suggestions.
Thank you and best regards,
David | 2023-10-06T07:02:48 | https://www.reddit.com/r/LocalLLaMA/comments/1715oc6/run_your_local_llms_in_a_text_editor/ | David-Kunz | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 1715oc6 | false | null | t3_1715oc6 | /r/LocalLLaMA/comments/1715oc6/run_your_local_llms_in_a_text_editor/ | false | false | self | 28 | {'enabled': False, 'images': [{'id': 'G7d1n7bucTzsm5Bbc0J7JE-lKJ3BHprmv5VAcA7GrtE', 'resolutions': [{'height': 54, 'url': 'https://external-preview.redd.it/1TlYe3Te5BSmk1jWH9jI5v_0o7y5uyT8rWJE-E2VORY.jpg?width=108&crop=smart&auto=webp&s=9abbc99e1aac2fc03dd4cc0eb6670aa4654195cb', 'width': 108}, {'height': 108, 'url': 'h... |
Problem using llama-cpp-python on windows | 1 | I am trying to use mistral-openorca model by theBloke using llama-cpp-python. However, the inference speed is pretty slow, and I see that my nvidia gpu is not being used at all. I tried installing with cuBLAS and CLBLAST, but nothing seems to help. Can anybody please help me? | 2023-10-06T06:05:16 | https://www.reddit.com/r/LocalLLaMA/comments/1714rwt/problem_using_llamacpppython_on_windows/ | Blue_Dude3 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 1714rwt | false | null | t3_1714rwt | /r/LocalLLaMA/comments/1714rwt/problem_using_llamacpppython_on_windows/ | false | false | self | 1 | null |
Seeking Guidance on Using a Pre-trained Model for Medical Text Classification | 1 |
I'm working on a project where I need to classify medical texts into specific areas. For example, if I have a text like "Asthma is a chronic disease, and the drugs used are bronchodilators and corticosteroids," I want my model to return labels like ["pneumology", "asthma", "treatment"].
My question is, can a simple m... | 2023-10-06T05:42:21 | https://www.reddit.com/r/LocalLLaMA/comments/1714dxy/seeking_guidance_on_using_a_pretrained_model_for/ | koyo4ever | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 1714dxy | false | null | t3_1714dxy | /r/LocalLLaMA/comments/1714dxy/seeking_guidance_on_using_a_pretrained_model_for/ | false | false | self | 1 | null |
Enterprise Generative AI Pricing Estimator App | 3 | My name is Riya, a recent Computer Science graduate from Brown University and current first-year Master's student in Computer Science at Stanford University.
I built the [Enterprise Generative AI Pricing Estimator app](https://gen-ai-pricing-estimator.streamlit.app/) to help enterprise decision makers determine the ba... | 2023-10-06T05:23:08 | https://www.reddit.com/r/LocalLLaMA/comments/17142id/enterprise_generative_ai_pricing_estimator_app/ | ComfortableDaikon623 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 17142id | false | null | t3_17142id | /r/LocalLLaMA/comments/17142id/enterprise_generative_ai_pricing_estimator_app/ | false | false | self | 3 | {'enabled': False, 'images': [{'id': '6qqls60gKTiL0-yVyyCUcx6CGtbyKoQmvE6QXwE2Obs', 'resolutions': [{'height': 56, 'url': 'https://external-preview.redd.it/hnLO7KgRgpu8CLAmI8UppF2CpsuCVYGGGkudVro-kx4.jpg?width=108&crop=smart&auto=webp&s=5a13ffff5550b2dc235d6449f4c0c9768b220c86', 'width': 108}, {'height': 113, 'url': 'h... |
Are there large-sized companies that are using llama2 in prod? | 3 | This post is a part of my exploration I am doing between gpt and llama-2. In my last post, I did a cost comparison between gpt 3.5 and llama2, and llama2(with the compute I am using) turned out to be more expensive. Keeping the cost angle aside, I wanted to understand if anyone knows about companies using llama in prod... | 2023-10-06T05:02:15 | https://www.reddit.com/r/LocalLLaMA/comments/1713q1x/are_there_largesized_companies_that_are_using/ | todaysgamer | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 1713q1x | false | null | t3_1713q1x | /r/LocalLLaMA/comments/1713q1x/are_there_largesized_companies_that_are_using/ | false | false | self | 3 | null |
training 4bit quantized loras in ooba | 3 | this week i've been attempting some basic lora training in oobabooga. I have a single fairly large text file (64mb) and I'm training at default settings, popping off checkpoints every few hours.
I'm loading a llama2 descendant with Transformers in 4 bit (because gptq/gguf training is broken in ooba) and running this o... | 2023-10-06T00:14:20 | https://www.reddit.com/r/LocalLLaMA/comments/170xyeg/training_4bit_quantized_loras_in_ooba/ | __SlimeQ__ | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 170xyeg | false | null | t3_170xyeg | /r/LocalLLaMA/comments/170xyeg/training_4bit_quantized_loras_in_ooba/ | false | false | self | 3 | null |
Use LLM to convert anger level in text? | 1 | Is it possible to send text to an LLM and get it to convert it to be less / more angry, for example?
Ideally, I don't want any output except the converted text. It's similar to a model that translates and returns the output. I thought maybe I could make a character in ooba and give it some examples?
Any tips ap... | 2023-10-06T00:03:05 | https://www.reddit.com/r/LocalLLaMA/comments/170xpp1/use_llm_to_convert_anger_level_in_text/ | tuxedo0 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 170xpp1 | false | null | t3_170xpp1 | /r/LocalLLaMA/comments/170xpp1/use_llm_to_convert_anger_level_in_text/ | false | false | self | 1 | null |
[Synthetic data] Searching for honest comparison between LLM (gpt4, bizon, jurassic-2, Claude...) | 1 | [removed] | 2023-10-05T23:44:45 | https://www.reddit.com/r/LocalLLaMA/comments/170xana/synthetic_data_searching_for_honest_comparison/ | Distinct-Target7503 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 170xana | false | null | t3_170xana | /r/LocalLLaMA/comments/170xana/synthetic_data_searching_for_honest_comparison/ | false | false | self | 1 | null |
Nucleus.ai Founders Emerge From Stealth with 22b LLM (unconfirmed) | 56 | 2023-10-05T23:29:34 | https://www.businesswire.com/news/home/20231005112266/en/Nucleus.ai-Founders-Emerge-From-Stealth-and-Demonstrate-That-Big-Tech-Companies-Aren%E2%80%99t-the-Only-Ones-Building-Large-Language-Models | iLaurens | businesswire.com | 1970-01-01T00:00:00 | 0 | {} | 170wxz7 | false | null | t3_170wxz7 | /r/LocalLLaMA/comments/170wxz7/nucleusai_founders_emerge_from_stealth_with_22b/ | false | false | 56 | {'enabled': False, 'images': [{'id': 'wFC_FUUF00O0VBr0cI13RGrEYz2f5jco1BVu-7CREgA', 'resolutions': [{'height': 56, 'url': 'https://external-preview.redd.it/z_ZxLPqp6rJ6IfTuGzz9e65IvmcLVO9MH1IzBwui-Ds.jpg?width=108&crop=smart&auto=webp&s=a6c234041c69dc0f0ae76fbcd4dd97019ece6237', 'width': 108}, {'height': 112, 'url': 'h... | ||
Devs who use CodeLlama 34b- Which is the best current fine-tune (or not) to use? | 30 | Are any of you using it regularly, and if so which one is working best for you atm?
If you aren't using 34b, do you have one that's simply better? I really like the 100k context, but I'm really just looking for the best offline code assistant LLM. | 2023-10-05T23:11:28 | https://www.reddit.com/r/LocalLLaMA/comments/170wip7/devs_who_use_codellama_34b_which_is_the_best/ | LearningSomeCode | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 170wip7 | false | null | t3_170wip7 | /r/LocalLLaMA/comments/170wip7/devs_who_use_codellama_34b_which_is_the_best/ | false | false | self | 30 | null |
Are there a models that are really good at story writing like Claude 2? | 15 | I've been using Claude 2 to write stories of characters for a novel and it does a pretty good job in keeping track of some character details with the file upload feature. But it is terrible once any kind of conflict enters the picture and will refuse to draft a conversation between two characters that end on any kind o... | 2023-10-05T22:35:46 | https://www.reddit.com/r/LocalLLaMA/comments/170vnnh/are_there_a_models_that_are_really_good_at_story/ | Leyline266 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 170vnnh | false | null | t3_170vnnh | /r/LocalLLaMA/comments/170vnnh/are_there_a_models_that_are_really_good_at_story/ | false | false | self | 15 | null |
H2Oai GPT CPU | 1 | I am fairly new to LLMs and am having an issue implementing H2OGPT through CPU on windows. Not sure if this is allowed but would really appreciate it if someone could help me out. I’ve attached the link to the instructions I’ve followed on GitHub. When I get to the line of code:
# Required for CPU: LLaMa/GPT4All:
pi... | 2023-10-05T22:04:04 | https://github.com/h2oai/h2ogpt/blob/main/docs/README_WINDOWS.md | ComfortableFinancial | github.com | 1970-01-01T00:00:00 | 0 | {} | 170uuv5 | false | null | t3_170uuv5 | /r/LocalLLaMA/comments/170uuv5/h2oai_gpt_cpu/ | false | false | 1 | {'enabled': False, 'images': [{'id': 'eOBhSSaz8A1bMy1QEqMrqrkAJLULLOEdH6aiScvzh8M', 'resolutions': [{'height': 54, 'url': 'https://external-preview.redd.it/cDkyQn86bv25h0KdMLJVDkq41P7hhIqpXKZK2tp_5aY.jpg?width=108&crop=smart&auto=webp&s=b0397c9d5a46f3f5e09c919d5d08ace87ffecedd', 'width': 108}, {'height': 108, 'url': 'h... | |
Front ends for oobabooga that have Character AI's interface to regenerate/remember previous generations using arrow keys? | 5 | So when a character (the chatbot) generates a reply on C.AI, you can hit the right arrow to generate another, and the last generation moves to the left, like a big long tape that gets longer as you create more regenerations.
This is really nice, because you can easily use the left and right arrows to check through all... | 2023-10-05T22:00:05 | https://www.reddit.com/r/LocalLLaMA/comments/170uqzr/front_ends_for_oobabooga_that_have_character_ais/ | RottieCumGutter | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 170uqzr | false | null | t3_170uqzr | /r/LocalLLaMA/comments/170uqzr/front_ends_for_oobabooga_that_have_character_ais/ | false | false | self | 5 | {'enabled': False, 'images': [{'id': 'veE04iaMbgI4yLvLGj2IZNV7UQfnq3n_7BmxP28dCd8', 'resolutions': [{'height': 54, 'url': 'https://external-preview.redd.it/BGOGS7KdVHomyGu2FIFx85nsQDLp_fpWWBKXxvtudf4.jpg?width=108&crop=smart&auto=webp&s=0e594332595e82a5118e08d35a2cd140c18d7571', 'width': 108}, {'height': 108, 'url': 'h... |
Cant find guide anymore(need help, more inside) | 1 | All i see is link with list of models
So i was able to start with textwebui and load mistral-7b- was super easy
What i fail is how i load 33b model in 8-bit? I entered something in web and it downloaded fp16 model which is 66GB
And also if i load 70b model in 4-bit(once i fugure out how) would it be able to use two ... | 2023-10-05T21:45:07 | https://www.reddit.com/r/LocalLLaMA/comments/170ud34/cant_find_guide_anymoreneed_help_more_inside/ | chub0ka | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 170ud34 | false | null | t3_170ud34 | /r/LocalLLaMA/comments/170ud34/cant_find_guide_anymoreneed_help_more_inside/ | false | false | self | 1 | null |
Guide: Installing ROCm/hip for LLaMa.cpp on Linux for the 7900xtx | 54 | Hi all, I finally managed to get an upgrade to my GPU. I noticed there aren't a lot of complete guides out there on how to get LLaMa.cpp working with an AMD GPU, so here goes.
Note that this guide has not been revised super closely, there might be mistakes or unpredicted gotchas, general knowledge of Linux, LLaMa.cpp,... | 2023-10-05T21:09:49 | https://www.reddit.com/r/LocalLLaMA/comments/170tghx/guide_installing_rocmhip_for_llamacpp_on_linux/ | Combinatorilliance | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 170tghx | false | null | t3_170tghx | /r/LocalLLaMA/comments/170tghx/guide_installing_rocmhip_for_llamacpp_on_linux/ | false | false | self | 54 | null |
Problems finetuning Llama2 7B, tried SFTTrainer, autotrain and llama.cpp none worked. | 4 | Hello all,
I have been trying to finetune *llama2* for quite some time now, I encountered many problems in the process and after I finally manage to finetune it llama spit nothing but the usual nonsense base llama would split.
I would like to know if some of you have similar experience, here are some more details : ... | 2023-10-05T21:07:19 | https://www.reddit.com/r/LocalLLaMA/comments/170te70/problems_finetuning_llama2_7b_tried_sfttrainer/ | fawendeshuo | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 170te70 | false | null | t3_170te70 | /r/LocalLLaMA/comments/170te70/problems_finetuning_llama2_7b_tried_sfttrainer/ | false | false | self | 4 | null |
ROG or Fine Tuning for custom copilot. | 1 | Hey everyone,
I'm diving into a new project and could use some pointers. I've got a bunch of code in my repos, mostly in .NET and JavaScript. I'm trying to tweak this code based on what users ask, kind of like a custom Copilot. I'm thinking of using a single agent or maybe something like AutoGen.
With all the code fi... | 2023-10-05T21:00:10 | https://www.reddit.com/r/LocalLLaMA/comments/170t79i/rog_or_fine_tuning_for_custom_copilot/ | mcwin1 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 170t79i | false | null | t3_170t79i | /r/LocalLLaMA/comments/170t79i/rog_or_fine_tuning_for_custom_copilot/ | false | false | self | 1 | null |
How to do an empirical LLM finetuning cost calculation before renting GPUs? | 1 | [removed] | 2023-10-05T19:54:42 | https://www.reddit.com/r/LocalLLaMA/comments/170rkeu/how_to_do_an_empirical_llm_finetuning_cost/ | tensor64 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 170rkeu | false | null | t3_170rkeu | /r/LocalLLaMA/comments/170rkeu/how_to_do_an_empirical_llm_finetuning_cost/ | false | false | self | 1 | null |
How to run mistral-7b-openorca on Android phone? | 12 | So, I have my rooted android phone with 12 gb of ram, and i want to locally run mistral-7b-openorca on it. How can I do that? I assume I'll need quantized model, which one is possible to run on android, AWQ, GPTQ, or GGUF version?
Thank you guys! | 2023-10-05T19:47:41 | https://www.reddit.com/r/LocalLLaMA/comments/170re5q/how_to_run_mistral7bopenorca_on_android_phone/ | ZotD0t | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 170re5q | false | null | t3_170re5q | /r/LocalLLaMA/comments/170re5q/how_to_run_mistral7bopenorca_on_android_phone/ | false | false | self | 12 | null |
What LLMs would you hire for your Agent Corp? | 2 | ChatDev, AutoGen, and etc for teams of LLMs agents working together to complete complex and expanding tasks are progressing nicely.
Excited to see the likes integrated with txtai or similar.
Hoping this community can help research the best locally ran models available that can run on 24GB cards for the different t... | 2023-10-05T19:41:23 | https://www.reddit.com/r/LocalLLaMA/comments/170r8mb/what_llms_would_you_hire_for_your_agent_corp/ | MindOrbits | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 170r8mb | false | null | t3_170r8mb | /r/LocalLLaMA/comments/170r8mb/what_llms_would_you_hire_for_your_agent_corp/ | false | false | self | 2 | null |
Concerns about Data Security with LLaMa in the Cloud | 1 | Hey, fellow LLaMa enthusiasts,
I've been thinking a lot about the security implications of using LLaMa and other large language models. My primary concern is that LLaMa, like many LLMs, isn't designed to work with encrypted or coded data. When we input our information, there's a potential risk of exposure. Since the n... | 2023-10-05T19:29:56 | https://www.reddit.com/r/LocalLLaMA/comments/170qyao/concerns_about_data_security_with_llama_in_the/ | Few_Film8907 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 170qyao | false | null | t3_170qyao | /r/LocalLLaMA/comments/170qyao/concerns_about_data_security_with_llama_in_the/ | false | false | self | 1 | null |
Mistral vs Mistral finetunes vs 13B vs Llama-70B vs GPT-3.5 | 83 | I [did a comparison of Mistral-7B-0.1-GPTQ, its finetunes, some 13B models, Llama-70B-chat and the GPT-3.5.](https://low-tractor-1b9.notion.site/LLM-comparison-7B-13B-8abfda2142d24c14a9a5a35ed83a0f10)
No specific conclusions, it's up to you, but the Mistral looks great against the big models.
Only ChatGPT and Mira (c... | 2023-10-05T19:24:32 | https://www.reddit.com/r/LocalLLaMA/comments/170qtj3/mistral_vs_mistral_finetunes_vs_13b_vs_llama70b/ | domrique | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 170qtj3 | false | null | t3_170qtj3 | /r/LocalLLaMA/comments/170qtj3/mistral_vs_mistral_finetunes_vs_13b_vs_llama70b/ | false | false | self | 83 | null |
Finetuned models for function calling? | 17 | Hello. Are there finetuned LLaMa2 models that can reliably work for function calling yet? (Setting up agents in Langchain and such). Previous discussion is around 2 months old so I wonder if there has been some advances on this.
I have been trying to build a chatbot that can search on the internet and can be locally h... | 2023-10-05T18:29:13 | https://www.reddit.com/r/LocalLLaMA/comments/170pej3/finetuned_models_for_function_calling/ | RangerRocket09 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 170pej3 | false | null | t3_170pej3 | /r/LocalLLaMA/comments/170pej3/finetuned_models_for_function_calling/ | false | false | self | 17 | null |
Are instruction-tuning LORAs transferable? | 3 | Hey all, I am in the process of testing several models for fine-tuning and that question cropped up.
I am trying to emulate things [these guys did](https://www.stochastic.ai/blog/xfinance-vs-bloomberg-gpt), which is to use fine-tuning to add facts to a model (I know RAG is usually recommended, but there are reasons fo... | 2023-10-05T18:18:29 | https://www.reddit.com/r/LocalLLaMA/comments/170p4ru/are_instructiontuning_loras_transferable/ | keepthepace | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 170p4ru | false | null | t3_170p4ru | /r/LocalLLaMA/comments/170p4ru/are_instructiontuning_loras_transferable/ | false | false | self | 3 | null |
Tiny Language Models Thrive With GPT-4 as a Teacher | 24 | 2023-10-05T18:14:11 | https://www.quantamagazine.org/tiny-language-models-thrive-with-gpt-4-as-a-teacher-20231005 | emptyplate | quantamagazine.org | 1970-01-01T00:00:00 | 0 | {} | 170p0pn | false | null | t3_170p0pn | /r/LocalLLaMA/comments/170p0pn/tiny_language_models_thrive_with_gpt4_as_a_teacher/ | false | false | 24 | {'enabled': False, 'images': [{'id': 'eC9KQEgQY0d-VwV1At-uh_71amxHnDN70x5NQ58xRCg', 'resolutions': [{'height': 56, 'url': 'https://external-preview.redd.it/yDHt_GW3bvKpPsfucJKLg7_LQp2k7NcV-z6OcI7QSoI.jpg?width=108&crop=smart&auto=webp&s=9e36667ee58c2aa2ae2465b002b456b8a8b2376d', 'width': 108}, {'height': 113, 'url': 'h... | ||
Can anyone tell me the performance of LLaVA vs BLIP? | 10 | Can any tell me the performance of LLaVA vs Blip? Which one leads to higher quality captioning of images? Is there a benchmark somewhere of the various VLM for these kind of models? | 2023-10-05T17:53:40 | https://www.reddit.com/r/LocalLLaMA/comments/170oi1d/can_anyone_tell_me_the_performance_of_llava_vs/ | ninjasaid13 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 170oi1d | false | null | t3_170oi1d | /r/LocalLLaMA/comments/170oi1d/can_anyone_tell_me_the_performance_of_llava_vs/ | false | false | self | 10 | null |
LoRA training and Llama fine tuning scripts | 2 | I found 2 scripts:
https://github.com/ggerganov/llama.cpp/blob/45eba9369fbcbd7f677eba9a2d3e4ffcfdc81824/examples/finetune/README.md
https://github.com/ggerganov/llama.cpp/blob/45eba9369fbcbd7f677eba9a2d3e4ffcfdc81824/examples/export-lora/README.md
Fine tuning looks like this:
# get training data
wget https://raw.gi... | 2023-10-05T17:46:18 | https://www.reddit.com/r/LocalLLaMA/comments/170obia/lora_training_and_llama_fine_tuning_scripts/ | yukiarimo | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 170obia | false | null | t3_170obia | /r/LocalLLaMA/comments/170obia/lora_training_and_llama_fine_tuning_scripts/ | false | false | self | 2 | {'enabled': False, 'images': [{'id': 'DJPqvteONpGwVVw6LzaG6b8vlDa2rv2hETCaqe0z57s', 'resolutions': [{'height': 54, 'url': 'https://external-preview.redd.it/wyCM1fHzTa-IIqHgS1QTxdSYNXn668elDj0WmYMPf_k.jpg?width=108&crop=smart&auto=webp&s=d6fa197328d583bcae7a764b40fd1214265b6852', 'width': 108}, {'height': 108, 'url': 'h... |
Give our customers an LLM to talk to about their data | 9 | Hello guys, we are a small hosting, and we are testing langchain and llama2 llm locally. We want to be able to create a chatbot for our hosting customers so the llm can check out their hosting stats and our customers can ask questions such as "how much more space do I need if I want to add a new email account, create a... | 2023-10-05T17:21:44 | https://www.reddit.com/r/LocalLLaMA/comments/170npuw/give_our_customers_an_llm_to_talk_to_about_their/ | Background-Maybe-381 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 170npuw | false | null | t3_170npuw | /r/LocalLLaMA/comments/170npuw/give_our_customers_an_llm_to_talk_to_about_their/ | false | false | self | 9 | null |
Url scraping for llama | 6 | Hello, does anyone know an application or chrome extension that once we throw a URL at it, is able to scrap the text, clean it up, and possibly save it to some database? I am planning to build a personal logger for my everyday activity so I can use this as embeddings or use it to fine tune my local llama as my personal... | 2023-10-05T17:20:13 | https://www.reddit.com/r/LocalLLaMA/comments/170nodc/url_scraping_for_llama/ | ilt1 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 170nodc | false | null | t3_170nodc | /r/LocalLLaMA/comments/170nodc/url_scraping_for_llama/ | false | false | self | 6 | null |
How long till LLM characters can initiate a conversation? | 7 | Imagine setting up a text-based roleplaying game. You send warriors off to a new land and they prompt you when they need help (or whatever you want them to do really). It could even be in real time if you want, so maybe an "event" could happen every couple of hours.
Or maybe you set up a foreign character to teach you... | 2023-10-05T17:04:56 | https://www.reddit.com/r/LocalLLaMA/comments/170nagh/how_long_till_llm_characters_can_initiate_a/ | JebryyathHS | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 170nagh | false | null | t3_170nagh | /r/LocalLLaMA/comments/170nagh/how_long_till_llm_characters_can_initiate_a/ | false | false | self | 7 | null |
LLM Suggestions to fine tune on an NVIDIA 2080 Super | 2 | The title. Any popular large language models I can use to fine tune on the above GPU? My use case is to build a type of chatbot on custom text interactions. (Kinda leaning on hopefully the 7B llama that i can tune with qlora maybe…?)
I would also love dataset recommendations.
Ive listed out my specs below:
GPU: RTX... | 2023-10-05T16:55:55 | https://www.reddit.com/r/LocalLLaMA/comments/170n20m/llm_suggestions_to_fine_tune_on_an_nvidia_2080/ | laveshnk | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 170n20m | false | null | t3_170n20m | /r/LocalLLaMA/comments/170n20m/llm_suggestions_to_fine_tune_on_an_nvidia_2080/ | false | false | self | 2 | null |
Hi guys, I haven't been in the sub since llama 1... | 1 | [removed] | 2023-10-05T16:43:42 | https://www.reddit.com/r/LocalLLaMA/comments/170mqkh/hi_guys_i_havent_been_in_the_sub_since_llama_1/ | Norok_The_Diablo | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 170mqkh | false | null | t3_170mqkh | /r/LocalLLaMA/comments/170mqkh/hi_guys_i_havent_been_in_the_sub_since_llama_1/ | false | false | self | 1 | null |
Best free opensource model for chatbot? | 3 | Hello, i want to build chatbot for dating website with personality of girl. so can you guys suggest me a free best model ? | 2023-10-05T15:41:07 | https://www.reddit.com/r/LocalLLaMA/comments/170l6yd/best_free_opensource_model_for_chatbot/ | Medium-Ask-5384 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 170l6yd | false | null | t3_170l6yd | /r/LocalLLaMA/comments/170l6yd/best_free_opensource_model_for_chatbot/ | false | false | self | 3 | null |
Open-sourcing a simple automation/agent workflow builder | 30 | Hey /r/LocalLLaMA,
tl;dr: Open-sourcing a simple automation/agent workflow creator: [https://github.com/spyglass-search/talos](https://github.com/spyglass-search/talos)
We're open-sourcing a project that lets you build simple automations/agent workflows that use LLMs for different tasks. Kinda like Zapier or IFTTT b... | 2023-10-05T15:03:10 | https://www.reddit.com/r/LocalLLaMA/comments/170k91i/opensourcing_a_simple_automationagent_workflow/ | andyndino | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 170k91i | false | null | t3_170k91i | /r/LocalLLaMA/comments/170k91i/opensourcing_a_simple_automationagent_workflow/ | false | false | self | 30 | {'enabled': False, 'images': [{'id': 'qdXoAiUtJHNqkrhQ7hjDFXSGqDVImxGezDFvaf0z_iQ', 'resolutions': [{'height': 54, 'url': 'https://external-preview.redd.it/SUzaXg2XUDnB6EwT158_DSgIGojMmTlyBf9p3FQc6Hk.jpg?width=108&crop=smart&auto=webp&s=d33b709412d4646109ebd44c92a32fd03ee9cb4f', 'width': 108}, {'height': 108, 'url': 'h... |
training babyPhi on "Textbooks Are All You Need" type data | 29 | Hello everyone!
First and foremost, I'm deeply grateful for this community. I've learned and benefited immensely from all of you, and I'm now excited to collaborate with some of you on an interesting new project I'm starting.
I'm particularly impressed with the quality of data that u/docsoc1 produced using SciPhi. M... | 2023-10-05T13:59:46 | https://www.reddit.com/r/LocalLLaMA/comments/170iqkk/training_babyphi_on_textbooks_are_all_you_need/ | Dry_Long3157 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 170iqkk | false | null | t3_170iqkk | /r/LocalLLaMA/comments/170iqkk/training_babyphi_on_textbooks_are_all_you_need/ | false | false | self | 29 | {'enabled': False, 'images': [{'id': 'SRQqCJLLBWenZA-Vk4NmfhLIYoGP4qO_YhRZNcIHsgE', 'resolutions': [{'height': 58, 'url': 'https://external-preview.redd.it/TlN8fXuhzoMraEjoxJnMTjZpAcekJV--nUQanUj8-_8.jpg?width=108&crop=smart&auto=webp&s=5c63eeb0d15d3381f0bbadec162cca2f9ed72747', 'width': 108}, {'height': 116, 'url': 'h... |
How to create chat version of any llm like llama, qwen, etc | 0 | I want to create chat version of llm for custom data say for answering financial questions like you are talking to a bank manager. It should feel like a conversation having context of previous talks. Any guidance? It should be bit fast I have A10 for inference. | 2023-10-05T12:05:06 | https://www.reddit.com/r/LocalLLaMA/comments/170g8ga/how_to_create_chat_version_of_any_llm_like_llama/ | s1lv3rj1nx | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 170g8ga | false | null | t3_170g8ga | /r/LocalLLaMA/comments/170g8ga/how_to_create_chat_version_of_any_llm_like_llama/ | false | false | self | 0 | null |
Issue in Summarization using LLaMa2 | 8 | I am trying to Summarize documents of call transcripts using LLaMa2, now as the call transcript is long i processed the conversation into smaller chunks about 1500 words and summarized the smaller chunks. Then I concatenated the summaries of all the chunks to generate a final summary.
The response given by LLaMa2 in ... | 2023-10-05T12:00:44 | https://www.reddit.com/r/LocalLLaMA/comments/170g52i/issue_in_summarization_using_llama2/ | Bl4ze26 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 170g52i | false | null | t3_170g52i | /r/LocalLLaMA/comments/170g52i/issue_in_summarization_using_llama2/ | false | false | self | 8 | null |
Generate Alpaca format from plain text | 1 | Hi Guys,
What is the best method to generate a good alpaca dataset from plaintext?
If you recommend to use a model, which one you would recommend? | 2023-10-05T11:32:43 | https://www.reddit.com/r/LocalLLaMA/comments/170fls3/generate_alpaca_format_from_plain_text/ | Enkay55 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 170fls3 | false | null | t3_170fls3 | /r/LocalLLaMA/comments/170fls3/generate_alpaca_format_from_plain_text/ | false | false | self | 1 | null |
AWQ vs EXL2 | 48 | So, I notice /u/TheBloke, pillar of this community that he is, has been quantizing AWQ and skipping [EXL2](https://huggingface.co/models?search=exl2) entirely, while still producing GPTQs for some reason.
Seeing as I found EXL2 to be really fantastic (13b 6-bit or even 8-bit at blazing fast speeds on a 3090 with Exlla... | 2023-10-05T11:29:24 | https://www.reddit.com/r/LocalLLaMA/comments/170fjec/awq_vs_exl2/ | Dead_Internet_Theory | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 170fjec | false | null | t3_170fjec | /r/LocalLLaMA/comments/170fjec/awq_vs_exl2/ | false | false | self | 48 | {'enabled': False, 'images': [{'id': 'An0iJLapq-5CUQQlm3lWegevVWf7wlANjmn1iOwCTqk', 'resolutions': [{'height': 58, 'url': 'https://external-preview.redd.it/BOaSYNg6lhlngBhuDS68WpIBibLf88Q_KzjZVrFpgEc.jpg?width=108&crop=smart&auto=webp&s=2c0b032bdc9d0820b318f57def3af620afe60ee8', 'width': 108}, {'height': 116, 'url': 'h... |
Prompt wizard Coder with history | 1 | I want to prompt Wizard Coder model
The official doc from wizard team is [ModelCard](https://huggingface.co/WizardLM/WizardCoder-15B-V1.0)
`Below is an instruction that describes a task. Write a response that appropriately completes the request.`
`### Instruction:`
`{instruction}`
`### Response:`
But I want to ... | 2023-10-05T09:47:39 | https://www.reddit.com/r/LocalLLaMA/comments/170dsib/prompt_wizard_coder_with_history/ | Clear-Entry4618 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 170dsib | false | null | t3_170dsib | /r/LocalLLaMA/comments/170dsib/prompt_wizard_coder_with_history/ | false | false | self | 1 | {'enabled': False, 'images': [{'id': 'r0gcJabYq7dSCuNTMHKcWTTk1dVsFYAIdt95tBN68kw', 'resolutions': [{'height': 58, 'url': 'https://external-preview.redd.it/FUJZ3wTbHUTg4uMG0tWHjdrcVpb9YHtKLcqidUi_5Ng.jpg?width=108&crop=smart&auto=webp&s=6b1a72c5e005e68dd9fb4d90c1b46d64987d346f', 'width': 108}, {'height': 116, 'url': 'h... |
after being here one week | 757 | 2023-10-05T09:24:12 | upk27 | i.redd.it | 1970-01-01T00:00:00 | 0 | {} | 170dg70 | false | null | t3_170dg70 | /r/LocalLLaMA/comments/170dg70/after_being_here_one_week/ | false | false | 757 | {'enabled': True, 'images': [{'id': 'yY-PAFUKHxIb8Gc5AOVeQGJbklhmRAkna7vmUN_GKAk', 'resolutions': [{'height': 72, 'url': 'https://preview.redd.it/whsrfzh0rcsb1.png?width=108&crop=smart&auto=webp&s=456c5545d27c12659ee6591e8fbfde3cb595b6b7', 'width': 108}, {'height': 144, 'url': 'https://preview.redd.it/whsrfzh0rcsb1.png... | |||
Curated list of LLMs and services for RP chatbots, WebUIs, and Locally Hosted LLMs | 8 | I am making a curated list of LLMs and services for Role-Play chatbots, WebUIs, and Locally Hosted LLMs.
I have a long history and passion with chatbots, and the LLM boom sparked my interest even further. I would like to also share my knowledge and experience with the community, but there is only so much one can know... | 2023-10-05T08:29:32 | https://www.reddit.com/r/LocalLLaMA/comments/170cm19/curated_list_of_llms_and_services_for_rp_chatbots/ | starlightrobotics | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 170cm19 | false | null | t3_170cm19 | /r/LocalLLaMA/comments/170cm19/curated_list_of_llms_and_services_for_rp_chatbots/ | false | false | self | 8 | {'enabled': False, 'images': [{'id': 'pHpN1PiP3jn42TpQyFaUtAvfkVPgha_xl5tN61gtAhA', 'resolutions': [{'height': 54, 'url': 'https://external-preview.redd.it/of6uiUIKf6HSavWfn69Byc2Ca_8CksOLq9lFeqlZyWs.jpg?width=108&crop=smart&auto=webp&s=e48b26e088f1c8c53d4da7150e1d483851f99abc', 'width': 108}, {'height': 108, 'url': 'h... |
Elon Musk just unveiled a time-limited Bitcoin giveaway event. | 0 | 2023-10-05T08:05:32 | GiveTJaDollar | i.redd.it | 1970-01-01T00:00:00 | 0 | {} | 170c9ej | false | null | t3_170c9ej | /r/LocalLLaMA/comments/170c9ej/elon_musk_just_unveiled_a_timelimited_bitcoin/ | false | false | 0 | {'enabled': True, 'images': [{'id': 'RILuZx-d7o-dpozr7-CIZqokQNk48vlnFzrx794ocFo', 'resolutions': [{'height': 144, 'url': 'https://preview.redd.it/q78mblf2dcsb1.gif?width=108&crop=smart&format=png8&s=8ace100926f8778ab3ed9203a91fb41b470fdb05', 'width': 108}, {'height': 288, 'url': 'https://preview.redd.it/q78mblf2dcsb1.... | |||
What is the best open-source model for generating lesbian erotica? | 6 | Basically title for anybody with relevant experience, and as an extra you're welcome to expand on how to fine-tune the model accordingly. Thanks in advance. | 2023-10-05T07:54:53 | https://www.reddit.com/r/LocalLLaMA/comments/170c38u/what_is_the_best_opensource_model_for_generating/ | coumineol | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 170c38u | false | null | t3_170c38u | /r/LocalLLaMA/comments/170c38u/what_is_the_best_opensource_model_for_generating/ | false | false | self | 6 | null |
fine tune llama to generate text with citations | 3 | Hi, I am performing a continued pre training (unsupervised data) and then instruction fine tuning (SFT) to build a domain adaptive llm. Is there any way I can train llama with citations in the pre training stage? So that during inference, llama can generate the answer and also provide citations.
I am passing chunks o... | 2023-10-05T05:42:50 | https://www.reddit.com/r/LocalLLaMA/comments/1709zi9/fine_tune_llama_to_generate_text_with_citations/ | weedyuh | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 1709zi9 | false | null | t3_1709zi9 | /r/LocalLLaMA/comments/1709zi9/fine_tune_llama_to_generate_text_with_citations/ | false | false | self | 3 | null |
Best 13B coding language model to date? | 11 | What's the best coding llm out there as of today especially under 13B parameters? | 2023-10-05T04:54:29 | https://www.reddit.com/r/LocalLLaMA/comments/17095bu/best_13b_coding_language_model_to_date/ | Mrleibniz | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 17095bu | false | null | t3_17095bu | /r/LocalLLaMA/comments/17095bu/best_13b_coding_language_model_to_date/ | false | false | self | 11 | null |
The Progress on NanoPhi! Check out a textbook based, logical, uncensored AI in just 0.3B! | 99 | Hi everyone, Its me again, thanks for all the support last time, really helped the project gain some traction!
I took the feedback of those in the old post,
- couldn't use the GPT-4 tokenizer, spent hours trying to get it to work, but I'm finetuning, not pretraining, so I get a million issues
- Once some other goal... | 2023-10-05T04:14:08 | https://www.reddit.com/r/LocalLLaMA/comments/1708enq/the_progress_on_nanophi_check_out_a_textbook/ | vatsadev | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 1708enq | false | null | t3_1708enq | /r/LocalLLaMA/comments/1708enq/the_progress_on_nanophi_check_out_a_textbook/ | false | false | self | 99 | {'enabled': False, 'images': [{'id': 'YPjchsUHdEAk9LHUGLqV615eVebaMj4C3PoZXv0PaGA', 'resolutions': [{'height': 54, 'url': 'https://external-preview.redd.it/_MRreZAOhPOx3Mr2KXEadSPxCPMU7lV-nZe0osXXLt0.jpg?width=108&crop=smart&auto=webp&s=ddfd4c234be48e156c16a6801ad38cd475ac1ad1', 'width': 108}, {'height': 108, 'url': 'h... |
Does Mixed Precision training reduce memory usage when training the model? | 4 | According to this page [https://huggingface.co/docs/transformers/main/perf\_train\_gpu\_one](https://huggingface.co/docs/transformers/main/perf_train_gpu_one), mixed precision training does not optimize memory utilization, but they also add parentheses around "no".
Moreover, in this page [https://huggingface.co/docs/... | 2023-10-05T03:37:08 | https://www.reddit.com/r/LocalLLaMA/comments/1707p56/does_mixed_precision_training_reduce_memory_usage/ | scienceotaku68 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 1707p56 | false | null | t3_1707p56 | /r/LocalLLaMA/comments/1707p56/does_mixed_precision_training_reduce_memory_usage/ | false | false | self | 4 | {'enabled': False, 'images': [{'id': 'jfeVG47nZdEkz9kXfW1CcS-Sy8l4DXGb9JErx6bLKfU', 'resolutions': [{'height': 58, 'url': 'https://external-preview.redd.it/IfMbJOxNUMUzsY1dCStb5zfgtucewbklqG7kssYhOLc.jpg?width=108&crop=smart&auto=webp&s=6c2099a4a9a69e9793ac03aec2e167bf75ab3eae', 'width': 108}, {'height': 116, 'url': 'h... |
Tested: 24gb max context sizes with 70B exllamav2 | 57 | Recently, some people appear to be in the dark on the maximum context when using certain exllamav2 model, as well as some issues surrounding windows drivers skewing performance. Myself included.
I run desktop ubuntu, with a 3090 powering the graphics, consuming 0.7gb. These results are with text-gen-webui, which auto-... | 2023-10-05T03:27:35 | https://www.reddit.com/r/LocalLLaMA/comments/1707ico/tested_24gb_max_context_sizes_with_70b_exllamav2/ | Aaaaaaaaaeeeee | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 1707ico | false | null | t3_1707ico | /r/LocalLLaMA/comments/1707ico/tested_24gb_max_context_sizes_with_70b_exllamav2/ | false | false | self | 57 | null |
🇩🇪 A Demonstration of LeoLM's German Skills | 20 | Since some german speaking users have said that LeoLM generated gibberish, I am pretty sure it was caused by wrong hyperparameter settings and/or wrong prompt-style. I am really extremely impressed by how good it understands and generates german text.
​
Here is an example dialogue with \`leolm\_leo-hessianai-1... | 2023-10-05T02:52:06 | https://www.reddit.com/r/LocalLLaMA/comments/1706s4d/a_demonstration_of_leolms_german_skills/ | Evening_Ad6637 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 1706s4d | false | null | t3_1706s4d | /r/LocalLLaMA/comments/1706s4d/a_demonstration_of_leolms_german_skills/ | false | false | 20 | null | |
Has anyone benchmarked Llamav2 13B on RTX A6000 and A6000 Ada? | 2 | Looking for Llamav2 bechmarks for 7B and 13B in addition to 30 and 70B that's published. | 2023-10-05T01:37:21 | https://www.reddit.com/r/LocalLLaMA/comments/17055z1/has_anyone_benchmarked_llamav2_13b_on_rtx_a6000/ | ciphersolver007 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 17055z1 | false | null | t3_17055z1 | /r/LocalLLaMA/comments/17055z1/has_anyone_benchmarked_llamav2_13b_on_rtx_a6000/ | false | false | self | 2 | null |
should i keep or "upgrade" | 2 | I downloaded the classic llama-7b to 65b models back in march and i recently got back in the whole LLM shmuck and seeing all the amazing progress that has been made since by the community i ask myself, should i dump my old models in the trash and download some newer one? also turns out 300gb of models is bit much | 2023-10-05T00:35:30 | https://www.reddit.com/r/LocalLLaMA/comments/1703sr1/should_i_keep_or_upgrade/ | Key-Wait-3098 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 1703sr1 | false | null | t3_1703sr1 | /r/LocalLLaMA/comments/1703sr1/should_i_keep_or_upgrade/ | false | false | self | 2 | null |
ToRA: a tool-integrated reasoning agent for mathematical problem solving, surpassing prior open source models on 10 mathematical reasoning datasets | 50 | The ToRA and ToRA-Code model series are based on Llama 2 and Code Llama, respectively. They surpass [WizardMath](https://www.reddit.com/r/LocalLLaMA/comments/15ob1zh/introduce_the_newest_wizardmath_models_70b13b7b/) and [MAmmoTH](https://www.reddit.com/r/LocalLLaMA/comments/16pawuj/anyone_checks_mammoth_claims_sota_on/... | 2023-10-05T00:24:48 | https://www.reddit.com/r/LocalLLaMA/comments/1703k6d/tora_a_toolintegrated_reasoning_agent_for/ | llamaShill | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 1703k6d | false | null | t3_1703k6d | /r/LocalLLaMA/comments/1703k6d/tora_a_toolintegrated_reasoning_agent_for/ | false | false | 50 | {'enabled': False, 'images': [{'id': 'E_kcLQS5un2Wdq2pZXlQgJW19sVR9jxgqRGecliwShI', 'resolutions': [{'height': 54, 'url': 'https://external-preview.redd.it/90zV3ZTwe9J8WBEjbhr8-7Obo0le86EQRX97XNqoVOE.jpg?width=108&crop=smart&auto=webp&s=9d8e923083ba0a367ec4f679eb63ea11916d2ac8', 'width': 108}, {'height': 108, 'url': 'h... | |
Best Uncensored LLM w/ Free Google Colab | 0 | [removed] | 2023-10-05T00:11:56 | https://www.reddit.com/r/LocalLLaMA/comments/17039ok/best_uncensored_llm_w_free_google_colab/ | Suitable-Ad-8598 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 17039ok | false | null | t3_17039ok | /r/LocalLLaMA/comments/17039ok/best_uncensored_llm_w_free_google_colab/ | false | false | default | 0 | null |
Subsets and Splits
No community queries yet
The top public SQL queries from the community will appear here once available.