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 ⌀ |
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
What's the current best way to deal with memory management? | 3 | With long conversations or large documents to parse, what tools are currently being used to help manage memory, fetch&format relevant information, etc... so that you have the important information within the context limits.
I've heard that Microsoft is working on a GitHub Copilot for Docs which is supposed to be able ... | 2023-09-06T10:16:36 | https://www.reddit.com/r/LocalLLaMA/comments/16bgeoh/whats_the_current_best_way_to_deal_with_memory/ | Sixhaunt | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 16bgeoh | false | null | t3_16bgeoh | /r/LocalLLaMA/comments/16bgeoh/whats_the_current_best_way_to_deal_with_memory/ | false | false | self | 3 | null |
Was Joi from Blade Runner 2049 a local LLM? | 13 | Inspired by another discussion on personal LLMs, I was reminded of that movie. I know that when it came out in 2017, LLMs did not yet exist but as I think back on it, Joi fits the mold of a local LLM as we have them today perfectly and the movie seems to be oddly prophetic (some info from the Wiki rather than the movie... | 2023-09-06T09:43:20 | https://www.reddit.com/r/LocalLLaMA/comments/16bfu1n/was_joi_from_blade_runner_2049_a_local_llm/ | Herr_Drosselmeyer | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 16bfu1n | false | null | t3_16bfu1n | /r/LocalLLaMA/comments/16bfu1n/was_joi_from_blade_runner_2049_a_local_llm/ | false | false | self | 13 | null |
Looking for Affordable Alternatives to ChatGPT 4 API - Best LLM APIs Today? | 2 | I've been using ChatGPT 4 for a while now, and it's been a fantastic tool for various tasks especially through its API.
So, I'm on the hunt for LLM (Large Language Model) APIs that can offer a similar experience to ChatGPT 4 but at a more affordable price point for a quite big project.
​
Thank you! | 2023-09-06T09:31:23 | https://www.reddit.com/r/LocalLLaMA/comments/16bfms3/looking_for_affordable_alternatives_to_chatgpt_4/ | pacmanpill | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 16bfms3 | false | null | t3_16bfms3 | /r/LocalLLaMA/comments/16bfms3/looking_for_affordable_alternatives_to_chatgpt_4/ | false | false | self | 2 | null |
Weird loss curves when training for the LLM science exam - anyone seen anything similar? | 7 | I just finished reading this very interesting post from [fast.ai](https://fast.ai): [https://www.fast.ai/posts/2023-09-04-learning-jumps/](https://www.fast.ai/posts/2023-09-04-learning-jumps/)
Theyre training an LLM to answer science questions for a kaggle competition, the dataset is 6500 question-answer pairs. These ... | 2023-09-06T09:17:40 | https://www.reddit.com/r/LocalLLaMA/comments/16bferl/weird_loss_curves_when_training_for_the_llm/ | heisenbork4 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 16bferl | false | null | t3_16bferl | /r/LocalLLaMA/comments/16bferl/weird_loss_curves_when_training_for_the_llm/ | false | false | self | 7 | {'enabled': False, 'images': [{'id': 'E25NtJMen0qHD0SG4k9ae4JyjU3zsRRlY0XGd5ykMMk', 'resolutions': [{'height': 49, 'url': 'https://external-preview.redd.it/d9ocJ8clzyJgAzJNpbT8rl6Ck4fuuuGgtyVtLxqCEsw.jpg?width=108&crop=smart&auto=webp&s=3ff6cefde0542398c2dc99595a9f5b29e30a90d5', 'width': 108}, {'height': 99, 'url': 'ht... |
Understanding Retrieval Augmented Generation (RAG) | 1 | [removed] | 2023-09-06T08:41:34 | https://www.reddit.com/r/LocalLLaMA/comments/16beuqa/understanding_retrieval_augmented_generation_rag/ | Floatbot_Inc | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 16beuqa | false | null | t3_16beuqa | /r/LocalLLaMA/comments/16beuqa/understanding_retrieval_augmented_generation_rag/ | false | false | self | 1 | null |
Any good learning resources for fine-tuning, quantization, and LoRA? | 16 | Hey all, I have been working with GPT3 for like 2 years now, I have lots of experience using it in all sorts of python programs but my experience is mostly on the surface level, I have only fine-tuned a couple of times and that was using the openai API. Id like to take the next step and learn about running models local... | 2023-09-06T08:23:31 | https://www.reddit.com/r/LocalLLaMA/comments/16bekej/any_good_learning_resources_for_finetuning/ | Chance_Confection_37 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 16bekej | false | null | t3_16bekej | /r/LocalLLaMA/comments/16bekej/any_good_learning_resources_for_finetuning/ | false | false | self | 16 | null |
qlora fine-tuned codellama 34b model | 8 | I always thought the codellama was pretrained on 1/4 of the original llama2 34b, maybe it can be futher fine-tuned rather than just for coding. So I took the \`codellama/CodeLlama-34b-hf\` base model and fine-tuned it on \`timdettmers/openassistant-guanaco\` dataset.
Surprisingly, it has become a multilingual chat mo... | 2023-09-06T07:54:23 | https://www.reddit.com/r/LocalLLaMA/comments/16be2vc/qlora_finetuned_codellama_34b_model/ | mzbacd | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 16be2vc | false | null | t3_16be2vc | /r/LocalLLaMA/comments/16be2vc/qlora_finetuned_codellama_34b_model/ | false | false | self | 8 | {'enabled': False, 'images': [{'id': 'WdMUdOa1Y0Not51DEOCF2_l9TPzadfYPoCr9OD_hTb0', 'resolutions': [{'height': 58, 'url': 'https://external-preview.redd.it/3MeU-ZZ8c5QqQHGzpGk-uCJS0PIuyTdUIKs_1qYMUnc.jpg?width=108&crop=smart&auto=webp&s=d6617d92a951b966e84a74b0debc3ba3259ba1ad', 'width': 108}, {'height': 116, 'url': 'h... |
Which framework would you use to build a RAG using llama-2? | 1 | [removed] | 2023-09-06T07:33:23 | https://www.reddit.com/r/LocalLLaMA/comments/16bdqs0/which_framework_would_you_use_to_build_a_rag/ | front-equal | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 16bdqs0 | false | null | t3_16bdqs0 | /r/LocalLLaMA/comments/16bdqs0/which_framework_would_you_use_to_build_a_rag/ | false | false | self | 1 | null |
How can I load a local model and play with it? | 1 | [removed] | 2023-09-06T07:26:31 | https://www.reddit.com/r/LocalLLaMA/comments/16bdmmh/how_can_i_load_a_local_model_and_play_with_it/ | william_luckybob | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 16bdmmh | false | {'oembed': {'author_name': 'James Briggs', 'author_url': 'https://www.youtube.com/@jamesbriggs', 'height': 200, 'html': '<iframe width="356" height="200" src="https://www.youtube.com/embed/6iHVJyX2e50?feature=oembed&enablejsapi=1" frameborder="0" allow="accelerometer; autoplay; clipboard-write; encrypted-media; gyrosco... | t3_16bdmmh | /r/LocalLLaMA/comments/16bdmmh/how_can_i_load_a_local_model_and_play_with_it/ | false | false | 1 | {'enabled': False, 'images': [{'id': 'YciGqF6lm8xszzTBA-e2GH9xMEAXy2SADgKjOWd7OLc', 'resolutions': [{'height': 81, 'url': 'https://external-preview.redd.it/xIj5386wZ9s0e27dzMbFn2VI0pjC8-_FXNvxuxVIeAo.jpg?width=108&crop=smart&auto=webp&s=1cbdfc0fb58ac0aac17289e6064ca16f7ddc52b2', 'width': 108}, {'height': 162, 'url': 'h... | |
How does Llama-2 perform in sentiment analysis? | 8 | Hey guys, if you have explored using Llama-2 in doing sentiment analysis, just wanted to get your experience in how Llama-2 perform in this task?
I have tried using GPT and it’s pretty accurate.
If Llama-2 isn’t all that good in sentiment analysis, which other open LLM would you recommend?
Thank heaps! | 2023-09-06T06:30:25 | https://www.reddit.com/r/LocalLLaMA/comments/16bcpn1/how_does_llama2_perform_in_sentiment_analysis/ | --leockl-- | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 16bcpn1 | false | null | t3_16bcpn1 | /r/LocalLLaMA/comments/16bcpn1/how_does_llama2_perform_in_sentiment_analysis/ | false | false | self | 8 | null |
Someone managed to connect local LLM's to the Internet | 1 | [removed] | 2023-09-06T05:21:41 | https://www.reddit.com/r/LocalLLaMA/comments/16bbin2/someone_managed_to_connect_local_llms_to_the/ | No_Marionberry312 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 16bbin2 | false | null | t3_16bbin2 | /r/LocalLLaMA/comments/16bbin2/someone_managed_to_connect_local_llms_to_the/ | false | false | 1 | null | |
ChatGPT-4 has gotten better for me over time | 5 | First off, I know this is r/LocalLLaMA, but I see a lot of comments about ChatGPT worsening, whether it's due to OpenAI "making it worse", quantization hurting performance, etc.
But for me, it's gotten better at translations, coding tasks, math questions, and really just anything I throw at it. No hate towards opensou... | 2023-09-06T04:46:42 | https://www.reddit.com/r/LocalLLaMA/comments/16bav14/chatgpt4_has_gotten_better_for_me_over_time/ | JuicyStandoffishMan | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 16bav14 | false | null | t3_16bav14 | /r/LocalLLaMA/comments/16bav14/chatgpt4_has_gotten_better_for_me_over_time/ | false | false | self | 5 | null |
Is it better to continue pretrain LLM for a domain then do instruction fine-tune or do instruction fine-tune using question-answer pairs for that domain immediately? | 9 | Let's say for example, I want to create a chat bot that answer questions about cars. Should I first continue train the LLM on a corpus containing documents about cars then do instruction fine-tuning? Or I can do instruction fine-tuning on question answer pairs about cars immediately?
I think that the first method requ... | 2023-09-06T04:41:04 | https://www.reddit.com/r/LocalLLaMA/comments/16barbk/is_it_better_to_continue_pretrain_llm_for_a/ | scienceotaku68 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 16barbk | false | null | t3_16barbk | /r/LocalLLaMA/comments/16barbk/is_it_better_to_continue_pretrain_llm_for_a/ | false | false | self | 9 | null |
Can or doe's anyone use LLm's to provide feedback on fiction you write? | 1 | Also can it be trusted as honest and objective or will it always say good job? | 2023-09-06T02:55:41 | https://www.reddit.com/r/LocalLLaMA/comments/16b8o9a/can_or_does_anyone_use_llms_to_provide_feedback/ | poet3991 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 16b8o9a | false | null | t3_16b8o9a | /r/LocalLLaMA/comments/16b8o9a/can_or_does_anyone_use_llms_to_provide_feedback/ | false | false | self | 1 | null |
SQL analysis | 1 | What's the best open source LLM for building a query builder from text to sql, analyze it, and more querying from document ? I heard that llama 2 not so good at coding. And also can I use two different llms for different endpoint in my api ? Example for generate code I'm using gpt 3.5 and for querying document I'm usin... | 2023-09-06T02:32:44 | https://www.reddit.com/r/LocalLLaMA/comments/16b86ry/sql_analysis/ | laveriaroha | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 16b86ry | false | null | t3_16b86ry | /r/LocalLLaMA/comments/16b86ry/sql_analysis/ | false | false | self | 1 | null |
Can I replace ChatGPT with local models yet? | 5 | I'm not particularly literate on the topic of LLM metrics, so I'm here because I'm wondering if there are any local ChatGPT alternatives I can set up today that could largely substitute either GPT-3.5 or GPT-4. Note that I'm not talking about just LLaMA, I'm open to anything really. | 2023-09-06T02:29:35 | https://www.reddit.com/r/LocalLLaMA/comments/16b84b6/can_i_replace_chatgpt_with_local_models_yet/ | 88sSSSs88 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 16b84b6 | false | null | t3_16b84b6 | /r/LocalLLaMA/comments/16b84b6/can_i_replace_chatgpt_with_local_models_yet/ | false | false | self | 5 | null |
Inconsistency of carbon footprint in LLaMA 1 paper | 8 | When I was reading the LLaMA 1 paper, it mentioned their power consumption and carbon emitted:
This means that developing these models would have cost around 2,638 MWh under our assumptions, and a total emission of 1,015 tCO2eq.
However, Table 15 does not state the same information:
https://preview.redd.it/1b23zuy2p... | 2023-09-06T02:26:53 | https://www.reddit.com/r/LocalLLaMA/comments/16b829c/inconsistency_of_carbon_footprint_in_llama_1_paper/ | secsilm | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 16b829c | false | null | t3_16b829c | /r/LocalLLaMA/comments/16b829c/inconsistency_of_carbon_footprint_in_llama_1_paper/ | false | false | 8 | null | |
Eval mmlu result against various infer methods (HF_Causal, VLLM, AutoGPTQ, AutoGPTQ-exllama) | 5 | I modified declare-lab's instruct-eval scripts, add support to VLLM, AutoGPTQ (and new autoGPTQ support exllama now), and test the mmlu result. I also add support to fastllm (which can accelerate ChatGLM2-6b.
The code is here [https://github.com/declare-lab/instruct-eval](https://github.com/declare-lab/instruct-eval)... | 2023-09-06T02:12:07 | https://www.reddit.com/r/LocalLLaMA/comments/16b7qr1/eval_mmlu_result_against_various_infer_methods_hf/ | bash99Ben | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 16b7qr1 | false | null | t3_16b7qr1 | /r/LocalLLaMA/comments/16b7qr1/eval_mmlu_result_against_various_infer_methods_hf/ | false | false | 5 | {'enabled': False, 'images': [{'id': 'evpneWxD5awodnxHnoDwaty2jWBMEu9gPDFPExqpN6s', 'resolutions': [{'height': 54, 'url': 'https://external-preview.redd.it/pNvFkZHQgmonjE72eRiWdFT17dYj30GAq16lFaaNDxI.jpg?width=108&crop=smart&auto=webp&s=57d7328218559ecfa1273e7865a5151292dbb450', 'width': 108}, {'height': 108, 'url': 'h... | |
llama.cpp/Koboldcpp hipBLAS compile under Windows | 1 | Anyone able to compile llama.cpp or koboldcpp with hipBLAS enabled under Windows? I did get llama-python-cpp working with hipBLAS (ROCm) under linux and it works great but have not been able to get it to compile in Windows. Under linux at least, llama.cpp even splits the vram usage pretty much equally with dual cards... | 2023-09-06T01:27:12 | https://www.reddit.com/r/LocalLLaMA/comments/16b6r73/llamacppkoboldcpp_hipblas_compile_under_windows/ | ccbadd | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 16b6r73 | false | null | t3_16b6r73 | /r/LocalLLaMA/comments/16b6r73/llamacppkoboldcpp_hipblas_compile_under_windows/ | false | false | self | 1 | null |
Good low-key video Jerry Kaplan, Why Generative AI is Truly Revolutionary | 1 | [https://www.youtube.com/watch?v=h7AgTzWMhUc](https://www.youtube.com/watch?v=h7AgTzWMhUc)
ChatGPT summarize:
* Jerry Kaplan, a technology expert with a Ph.D. in computer science and a background in entrepreneurship, discusses generative AI in a YouTube conversation.
* Generative AI represents advanced artificia... | 2023-09-06T00:50:59 | https://www.reddit.com/r/LocalLLaMA/comments/16b5xay/good_lowkey_video_jerry_kaplan_why_generative_ai/ | FPham | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 16b5xay | false | null | t3_16b5xay | /r/LocalLLaMA/comments/16b5xay/good_lowkey_video_jerry_kaplan_why_generative_ai/ | false | false | self | 1 | {'enabled': False, 'images': [{'id': '5ibR4gyccUh40J0K6twf60h-aMSWtSm_YrTtqCyNgyw', 'resolutions': [{'height': 81, 'url': 'https://external-preview.redd.it/smTj6ha57uAKiBWPm-kKz3E8qKTck10dFpaTIWCC5nY.jpg?width=108&crop=smart&auto=webp&s=9e8924dd9a11ea782d460a5521960c8056d50d15', 'width': 108}, {'height': 162, 'url': 'h... |
[Request] Instructions on how to convert models to the GGUF format. | 1 | I need to process large prompts, and there's almost no support for large context size models. I haven't found any GUI frontend that supports more than 2K context, and llama.cpp requires the GGUF format, of which there's very few models, almost none for large contexts.
I tried using the provided converstion tool but it... | 2023-09-05T22:40:05 | https://www.reddit.com/r/LocalLLaMA/comments/16b2qou/request_instructions_on_how_to_convert_models_to/ | jungle | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 16b2qou | false | null | t3_16b2qou | /r/LocalLLaMA/comments/16b2qou/request_instructions_on_how_to_convert_models_to/ | false | false | self | 1 | null |
I built a very simple TPS (tokens per second) visualizer so that you don't have to | 81 | Hi all,
A key question I've often come across whilst researching what hardware I should procure for my home server, is how many tokens per second a given GPU combination is able to generate for a given model.
The acceptability of said TPS always seems to be subjective, so I wanted to have an easy way to visualize thi... | 2023-09-05T21:59:32 | https://www.reddit.com/r/LocalLLaMA/comments/16b1nvp/i_built_a_very_simple_tps_tokens_per_second/ | iBifteki | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 16b1nvp | false | null | t3_16b1nvp | /r/LocalLLaMA/comments/16b1nvp/i_built_a_very_simple_tps_tokens_per_second/ | false | false | self | 81 | null |
Inside Meta's AI Drama: internal feuds over compute power, and a rumor on Llama 3 | 197 | This exclusive comes from The Information, the same publication that has published other exclusive articles on Meta AI news like the formerly unknown releases of Llama 2 and Code Llama.
The [full article](https://www.theinformation.com/articles/inside-metas-ai-drama-internal-feuds-over-compute-power) is paywalled, but... | 2023-09-05T21:43:56 | https://www.reddit.com/r/LocalLLaMA/comments/16b18tj/inside_metas_ai_drama_internal_feuds_over_compute/ | llamaShill | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 16b18tj | false | null | t3_16b18tj | /r/LocalLLaMA/comments/16b18tj/inside_metas_ai_drama_internal_feuds_over_compute/ | false | false | self | 197 | {'enabled': False, 'images': [{'id': 'LpaR91r08St8Yr52aV2kbsZKrvhW8kNpMnxey-dg2oY', 'resolutions': [{'height': 60, 'url': 'https://external-preview.redd.it/mR-vEFiBD85lbvnnnbksbGl519DXC9qrIbWto7j0S6E.jpg?width=108&crop=smart&auto=webp&s=a7e3fa55bf1e8216fb0765df3242f8463718129b', 'width': 108}, {'height': 121, 'url': 'h... |
The more I write in the chat, the longer the robot thinks | 1 | Do I understand correctly that he is constantly thinking over previous messages in the dialog? Is their length adjusted somewhere? I am using Llama-2 under oobadoga WebUI | 2023-09-05T21:31:34 | https://www.reddit.com/r/LocalLLaMA/comments/16b0whd/the_more_i_write_in_the_chat_the_longer_the_robot/ | Hatred_grows | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 16b0whd | false | null | t3_16b0whd | /r/LocalLLaMA/comments/16b0whd/the_more_i_write_in_the_chat_the_longer_the_robot/ | false | false | self | 1 | null |
Anyone know how to get current version koboldcpp to use GPU on an M2 Mac? | 1 | [removed] | 2023-09-05T21:09:54 | https://www.reddit.com/r/LocalLLaMA/comments/16b0ajj/anyone_know_how_to_get_current_version_koboldcpp/ | Virtamancer | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 16b0ajj | false | null | t3_16b0ajj | /r/LocalLLaMA/comments/16b0ajj/anyone_know_how_to_get_current_version_koboldcpp/ | false | false | self | 1 | null |
Completely new to this but does anyone know how to configure this part if I have 10GBs of VRAM (RTX 3080) and 32GBs of RAM? I'm completely clueless and any help would be fantastic thank you | 2 | 2023-09-05T21:02:14 | Affectionate-Grab864 | i.redd.it | 1970-01-01T00:00:00 | 0 | {} | 16b02vs | false | null | t3_16b02vs | /r/LocalLLaMA/comments/16b02vs/completely_new_to_this_but_does_anyone_know_how/ | false | false | 2 | {'enabled': True, 'images': [{'id': '_sX8c0sr6X-rqHutp6jn0eOzN5e3Bneo3LFRd3RhX8U', 'resolutions': [{'height': 89, 'url': 'https://preview.redd.it/0dso4rd64imb1.png?width=108&crop=smart&auto=webp&s=ea1b168a5e4290ee154a406f60d16742cc8eb8f7', 'width': 108}, {'height': 178, 'url': 'https://preview.redd.it/0dso4rd64imb1.png... | |||
Streamlit launches LLM Hackathon 🧠 | 22 | Streamlit just launched its latest hackathon focused on large language models and AI 🚀
Awesome opportunity to build a Streamlit app using LangChain, LlamaIndex, AssemblyAI, Weaviate, or Clarifai, and win cool prizes (AirPods, Yeti microphone, mechanical keyboard, to name a few) – plus, the first 250 folks to enter ge... | 2023-09-05T20:06:47 | https://www.reddit.com/r/LocalLLaMA/comments/16ayk5z/streamlit_launches_llm_hackathon/ | carolinedfrasca | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 16ayk5z | false | null | t3_16ayk5z | /r/LocalLLaMA/comments/16ayk5z/streamlit_launches_llm_hackathon/ | false | false | 22 | {'enabled': False, 'images': [{'id': 'cOIsV8EFAdNgcu8QXWE034usjIzLh7xTucelMcLjcuQ', 'resolutions': [{'height': 56, 'url': 'https://external-preview.redd.it/qVImSBBedqbXz2tzudizmjsay9lLj8_wx490VAJdUBc.jpg?width=108&crop=smart&auto=webp&s=d81e665e134b57fd868afc6922b40ef38653eb31', 'width': 108}, {'height': 113, 'url': 'h... | |
Streamlit launches LLM Hackathon 🧠 | 1 | Streamlit just launched its [latest hackathon](https://hubs.la/Q020TdDj0) focused on large language models and AI 🚀
Awesome opportunity to build a Streamlit app using LangChain, LlamaIndex, AssemblyAI, Weaviate, or Clarifai, and win cool prizes (AirPods, Yeti microphone, mechanical keyboard, to name a few) – plus, th... | 2023-09-05T19:43:34 | https://www.reddit.com/r/LocalLLaMA/comments/16axxoh/streamlit_launches_llm_hackathon/ | carolinedfrasca | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 16axxoh | false | null | t3_16axxoh | /r/LocalLLaMA/comments/16axxoh/streamlit_launches_llm_hackathon/ | false | false | 1 | {'enabled': False, 'images': [{'id': 'cOIsV8EFAdNgcu8QXWE034usjIzLh7xTucelMcLjcuQ', 'resolutions': [{'height': 56, 'url': 'https://external-preview.redd.it/qVImSBBedqbXz2tzudizmjsay9lLj8_wx490VAJdUBc.jpg?width=108&crop=smart&auto=webp&s=d81e665e134b57fd868afc6922b40ef38653eb31', 'width': 108}, {'height': 113, 'url': 'h... | |
Affordable cloud to deploy a basic llm pipeline as API backend? | 1 | To narrow down the question, I'm particularly thinking of a quantized 13B model for a personal project that doesn't involve too many requests, so it doesn't matter if it's "slow". Put it in other words, it doesn't need to serve many users concurrently, it's not a chatbot use case, it's more of a summarization pipeline.... | 2023-09-05T19:17:12 | https://www.reddit.com/r/LocalLLaMA/comments/16ax8cu/affordable_cloud_to_deploy_a_basic_llm_pipeline/ | Responsible_Warning3 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 16ax8cu | false | null | t3_16ax8cu | /r/LocalLLaMA/comments/16ax8cu/affordable_cloud_to_deploy_a_basic_llm_pipeline/ | false | false | self | 1 | null |
A recursive transformer (just a wild idea) | 7 | I've read many times that models that a ton of weights in typical models do not much, and can benefit from more training, but there is a problem with overfitting and catastrofic forgetting.
Also, there is that infamous "stack more layers" paradigm which, as much as I understand, few agree HOW it actually works, but mor... | 2023-09-05T19:06:42 | https://www.reddit.com/r/LocalLLaMA/comments/16awyld/a_recursive_transformer_just_a_wild_idea/ | BalorNG | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 16awyld | false | null | t3_16awyld | /r/LocalLLaMA/comments/16awyld/a_recursive_transformer_just_a_wild_idea/ | false | false | self | 7 | null |
A couple of questions on using GGML/GGUF to maximise context length | 12 | Hello, firstly apologies if any of this has been asked before, I searched the subreddit and I couldn't find the answers I was after. I'm also a noob of 1 week, so I don't really understand how this technology works beyond a few FAQs I've seen floating around various subreddits.
I am currently running the GPTQ version... | 2023-09-05T19:01:25 | https://www.reddit.com/r/LocalLLaMA/comments/16awtiy/a_couple_of_questions_on_using_ggmlgguf_to/ | EeyoresM8 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 16awtiy | false | null | t3_16awtiy | /r/LocalLLaMA/comments/16awtiy/a_couple_of_questions_on_using_ggmlgguf_to/ | false | false | self | 12 | {'enabled': False, 'images': [{'id': '8xtjwwtcKerurGMhTFLFFArH0ZxmDESqopVHCKpKfxU', 'resolutions': [{'height': 54, 'url': 'https://external-preview.redd.it/l4xYfRJ9MJu2EVsIiQGGndv0eMRVGWcafH1AgtXUuXk.jpg?width=108&crop=smart&auto=webp&s=941c18c68662db8cebcab4705115e8b304d71510', 'width': 108}, {'height': 108, 'url': 'h... |
How would a 4090 laptop fair in the current state of LocalLLaMA? | 15 | Hello!
I've recently been given a chance to get a machine from my company to "explore applications of LLM" in our office, main goal is to basically trying to have a small LLM that can write small and basic programs quickly.
Unfortunately, my boss insisted it be a laptop. So, I'm wondering if the top-of-the-line 4090 l... | 2023-09-05T18:51:47 | https://www.reddit.com/r/LocalLLaMA/comments/16awkmo/how_would_a_4090_laptop_fair_in_the_current_state/ | rexyuan | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 16awkmo | false | null | t3_16awkmo | /r/LocalLLaMA/comments/16awkmo/how_would_a_4090_laptop_fair_in_the_current_state/ | false | false | self | 15 | null |
LlaMA 13B Setup for custom requirement | 1 | My day to day work can extensively be cut back on if I am able to use LLaMA 13B (34B would be better but 13B model works fine for me, tested on Poe). I am seriously considering, setting up a rig from scratch, what's the cheapest config that can handle the following:-
1. Run LLaMA at 10-15 tokens per second
2. Accept c... | 2023-09-05T18:17:00 | https://www.reddit.com/r/LocalLLaMA/comments/16avold/llama_13b_setup_for_custom_requirement/ | mohityadavx | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 16avold | false | null | t3_16avold | /r/LocalLLaMA/comments/16avold/llama_13b_setup_for_custom_requirement/ | false | false | self | 1 | null |
Multi part Model | 1 | I cant find any one part of the models, I also can't find any explanation on how to combine multipart models into one. What am I missing? | 2023-09-05T17:56:42 | https://www.reddit.com/r/LocalLLaMA/comments/16av5b8/multi_part_model/ | EagleNoes | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 16av5b8 | false | null | t3_16av5b8 | /r/LocalLLaMA/comments/16av5b8/multi_part_model/ | false | false | self | 1 | null |
KOR with Llama | 1 | Hey guys, so I have to extract certain named entities, specifically of the medical domain, from passages. Problem is we have very few examples of the names entity, for ex: drug code. So we decided to try KOR with Llama2. Any one have any experience with it? Because with my first try, outputs seem to be dire. Any altern... | 2023-09-05T17:35:18 | https://www.reddit.com/r/LocalLLaMA/comments/16aulek/kor_with_llama/ | Tinjar12 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 16aulek | false | null | t3_16aulek | /r/LocalLLaMA/comments/16aulek/kor_with_llama/ | false | false | self | 1 | null |
GPT4ALL pylama issues can't figure out! | 1 | I've been away from the AI world for the last few months. Was upset to find that my python program no longer works with the new quantized binary models. I had a look in the tutorial threads but can't put my finger on the issue.
This is my code:
def gpt4all(user_input):
global conversation
gptj = G... | 2023-09-05T17:26:09 | https://www.reddit.com/r/LocalLLaMA/comments/16auclq/gpt4all_pylama_issues_cant_figure_out/ | darkbluetwilight | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 16auclq | false | null | t3_16auclq | /r/LocalLLaMA/comments/16auclq/gpt4all_pylama_issues_cant_figure_out/ | false | false | self | 1 | null |
I'm convinced now that “personal LLMs” are going to be a huge thing | 319 | Hey all,
[I posted here](https://www.reddit.com/r/LocalLLaMA/comments/16954fj/what_do_you_use_your_local_llm_for/) over the weekend asking for feedback on how you all use your local deployments. The response rate and engagement was great, and it gave me a lot to chew on.
The way I see it, the users here are all early... | 2023-09-05T17:16:30 | https://www.reddit.com/r/LocalLLaMA/comments/16au3ga/im_convinced_now_that_personal_llms_are_going_to/ | docsoc1 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 16au3ga | false | null | t3_16au3ga | /r/LocalLLaMA/comments/16au3ga/im_convinced_now_that_personal_llms_are_going_to/ | false | false | self | 319 | {'enabled': False, 'images': [{'id': 'q3evP6JeDpAC2MdSQHWYxnCYTqbJkElIQsLFqVSdkss', 'resolutions': [{'height': 63, 'url': 'https://external-preview.redd.it/0HhwdU6MKIAKjL9Y8-B_iH374a3NiPTy0ib8lmloRzA.jpg?width=108&crop=smart&auto=webp&s=2711d572cfc6c713893cf24e8c4a7344d5ad8a4c', 'width': 108}, {'height': 126, 'url': 'h... |
GPTMe: A fancy CLI to interact with LLMs (GPT or Llama) in a Chat-style interface, with capabilities to execute code & commands on the local machine | 35 | 2023-09-05T16:57:52 | https://github.com/ErikBjare/gptme | ErikBjare | github.com | 1970-01-01T00:00:00 | 0 | {} | 16atlia | false | null | t3_16atlia | /r/LocalLLaMA/comments/16atlia/gptme_a_fancy_cli_to_interact_with_llms_gpt_or/ | false | false | 35 | {'enabled': False, 'images': [{'id': 'pl9qRx-8qE8tbw-ndu0ENMqJ9cc_GhFLbUmG3_LAtgs', 'resolutions': [{'height': 54, 'url': 'https://external-preview.redd.it/dnaVcvhIweTXxyEdOijnBUTV2XNlQwZ2qfBwQ1ERhVU.jpg?width=108&crop=smart&auto=webp&s=cdeb5d306a3b83803dd77147481b6047a1b66857', 'width': 108}, {'height': 108, 'url': 'h... | ||
In general, is training done on base models? | 3 | Take TheBloke/Carl-Llama-2-13B-GGUF for example.
The original model card says
> **Training:** Entire dataset was trained on Azure 4 x A100 80GB. For 3 epoch, training took 50 hours. DeepSpeed codebase was used for training purpose. This was trained on Llama-2 by Meta. GGML Quant models are converted by Kijana Mi... | 2023-09-05T16:50:02 | https://www.reddit.com/r/LocalLLaMA/comments/16atee3/in_general_is_training_done_on_base_models/ | multiverse_fan | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 16atee3 | false | null | t3_16atee3 | /r/LocalLLaMA/comments/16atee3/in_general_is_training_done_on_base_models/ | false | false | self | 3 | null |
I need some help or guidance on how to set up a locall LLM | 1 | Hello:
I would like to run this llama-2 70b on my computer like it: [https://huggingface.co/chat](https://huggingface.co/chat).
But I do not know how to achieve it, and also that it can search both in Internet and my own files.
I have tried GPT4ALL and Faraday, but both miss my requirements for searching Internet a... | 2023-09-05T16:37:16 | https://www.reddit.com/r/LocalLLaMA/comments/16at2gw/i_need_some_help_or_guidance_on_how_to_set_up_a/ | SnooWoofers780 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 16at2gw | false | null | t3_16at2gw | /r/LocalLLaMA/comments/16at2gw/i_need_some_help_or_guidance_on_how_to_set_up_a/ | false | false | self | 1 | {'enabled': False, 'images': [{'id': 'O4__VvuTP1zjgNXHpYgGtbNlwm8CyL1iGZRclIV-cFg', 'resolutions': [{'height': 58, 'url': 'https://external-preview.redd.it/5keZ3GZzk8vGrHDudxMqXr9Ja7Wko-SGl9RrNbjC6P4.jpg?width=108&crop=smart&auto=webp&s=c5c01ca386f7a26e8afeb5073e51c35d0d581de7', 'width': 108}, {'height': 116, 'url': 'h... |
Reasonable Graphics card for LLM AND Gaming | 7 | I'm currently in the market of building my first PC in over a decade. (Mac User)
Primary reason is gaming, however, if possible I would love to be able to also run some larger LLM's locally. Can anyone recommend a consumer card that would be good for both?
I came across these two cards on Amazon - would it make sense... | 2023-09-05T16:00:05 | https://www.reddit.com/r/LocalLLaMA/comments/16as386/reasonable_graphics_card_for_llm_and_gaming/ | MattBurnes | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 16as386 | false | null | t3_16as386 | /r/LocalLLaMA/comments/16as386/reasonable_graphics_card_for_llm_and_gaming/ | false | false | self | 7 | null |
The concern about LLM knowledge base and the possible solution | 1 | 2023-09-05T15:58:12 | https://medium.com/@SymeCloud/the-concern-about-llm-knowledge-base-and-the-possible-solution-7c212d2e8f99 | nalaginrut | medium.com | 1970-01-01T00:00:00 | 0 | {} | 16as1hn | false | null | t3_16as1hn | /r/LocalLLaMA/comments/16as1hn/the_concern_about_llm_knowledge_base_and_the/ | false | false | 1 | {'enabled': False, 'images': [{'id': 'PFmYKNDQ_Zy5lFGaemVZ37fWFCR4-AtF6QzH77dbqbc', 'resolutions': [{'height': 96, 'url': 'https://external-preview.redd.it/e1oMH0Qvy4ZtNAfaieyqpXQmaCVpIcgVH8TxE2u7xDk.jpg?width=108&crop=smart&auto=webp&s=966c9b0c3e9f903364cd249b2f358b08cf127498', 'width': 108}, {'height': 193, 'url': 'h... | ||
Errors loading Transformers, Llama models | 1 | Hi Everyone!
I'm trying to run these via oobabooga/texgen webui via WSL with a 3090 and 128GB RAM. I have double and triple-checked that all requirements have been updated, and that exllama has been installed, and continue to get these errors upon loading them.
Trying to load TheBloke\_Wizard-Vicuna-30B-Uncensored... | 2023-09-05T15:28:05 | https://www.reddit.com/r/LocalLLaMA/comments/16ar9sq/errors_loading_transformers_llama_models/ | drycounty | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 16ar9sq | false | null | t3_16ar9sq | /r/LocalLLaMA/comments/16ar9sq/errors_loading_transformers_llama_models/ | false | false | self | 1 | null |
Guide for begineers | 2 | I'm wondering if there's any step-by-step guide for beginners which desire to start learning about LLMs, maybe setting up and training LLaMA.
Any suggestions about where and how to start, the hardware needed or suggested etc...
Many thanks | 2023-09-05T15:26:05 | https://www.reddit.com/r/LocalLLaMA/comments/16ar7xs/guide_for_begineers/ | TheHypersonic | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 16ar7xs | false | null | t3_16ar7xs | /r/LocalLLaMA/comments/16ar7xs/guide_for_begineers/ | false | false | self | 2 | null |
Advice needed: Macbook pro M1 max 64G for local models, Should I get it? | 13 | Hey guys,
I need your experience/thoughts about this, I am currently running local models 7B on my Mac intel 16GB, works fine with decent speed, I can also run 13B but fairly slow. I have an option to replace that now with a M1 max 64GB with 32cores, my aim is to be able to run larger models or at least the 13B with e... | 2023-09-05T15:08:51 | https://www.reddit.com/r/LocalLLaMA/comments/16aqs51/advice_needed_macbook_pro_m1_max_64g_for_local/ | simplir | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 16aqs51 | false | null | t3_16aqs51 | /r/LocalLLaMA/comments/16aqs51/advice_needed_macbook_pro_m1_max_64g_for_local/ | false | false | self | 13 | null |
LLM Obsession | 107 | I am obsessed with LLM. Every day, I find myself repeatedly checking Hugging Face to see if there is a new model that is compatible with my laptop GPU of RAM for GGUF, and I try it out. I have accumulated 3 terabytes of models, and I cannot bring myself to delete them. Is this a cause for concern, doctor? | 2023-09-05T13:23:06 | https://www.reddit.com/r/LocalLLaMA/comments/16ao5pe/llm_obsession/ | GlobeTrekkerTV | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 16ao5pe | false | null | t3_16ao5pe | /r/LocalLLaMA/comments/16ao5pe/llm_obsession/ | false | false | self | 107 | null |
can we run gpqt models with cuda in windows ? | 1 | [removed] | 2023-09-05T11:17:05 | https://www.reddit.com/r/LocalLLaMA/comments/16alf2m/can_we_run_gpqt_models_with_cuda_in_windows/ | count_dracula14 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 16alf2m | false | null | t3_16alf2m | /r/LocalLLaMA/comments/16alf2m/can_we_run_gpqt_models_with_cuda_in_windows/ | false | false | self | 1 | null |
Model stop responding after few reply | 1 | This 13b 4bit mythomax, vicuna works good, but what if it stop replying after a few messages. I tried many settings but it doesn't help much. I don't know if the problem is in the pc and memory or what it is. I set temperature, top p, top k etc in different configurations. Anyone had the same? Maybe the ram is clogge... | 2023-09-05T10:24:30 | https://www.reddit.com/r/LocalLLaMA/comments/16akg99/model_stop_responding_after_few_reply/ | LonleyPaladin | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 16akg99 | false | null | t3_16akg99 | /r/LocalLLaMA/comments/16akg99/model_stop_responding_after_few_reply/ | false | false | self | 1 | null |
I cancelled my Chatgpt monthly membership because I'm tired of the constant censorship and the quality getting worse and worse. Does anyone know an alternative that I can go to? | 254 | Like chatgpt I'm willing to pay about $20 a month but I want an text generation AI that:
Remembers more than 8000 tokens
Doesn't have as much censorship
Can help write stories that I like to make
Those are the only three things I'm asking but Chatgpt refused to even hit those three. It's super ridiculous. I've trie... | 2023-09-05T10:15:05 | https://www.reddit.com/r/LocalLLaMA/comments/16ak9s2/i_cancelled_my_chatgpt_monthly_membership_because/ | SerpentEmperor | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 16ak9s2 | false | null | t3_16ak9s2 | /r/LocalLLaMA/comments/16ak9s2/i_cancelled_my_chatgpt_monthly_membership_because/ | false | false | self | 254 | null |
Biggest possible LLama2 model that can run on Ryzen 3950X with 128GB RAM + 24GB VRAM | 0 | Given that I have a system with 128GB of RAM, a 16-core Ryzen 3950X, and an RTX 4090 with 24GB of VRAM, what's the largest language model in terms of billions of parameters that I can feasibly run on my machine? I previously tried running a 70B parameter model on CPU and it crashed.
Are there any optimizations or tri... | 2023-09-05T10:14:56 | https://www.reddit.com/r/LocalLLaMA/comments/16ak9nh/biggest_possible_llama2_model_that_can_run_on/ | No_Wing133 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 16ak9nh | false | null | t3_16ak9nh | /r/LocalLLaMA/comments/16ak9nh/biggest_possible_llama2_model_that_can_run_on/ | false | false | default | 0 | null |
Need Guidance on Exposing Local API for My LLM Model | 6 | Hi everyone, I'm working with Vicuna, a local language model (LLM),
and I'm looking to expose it through an API from my local machine.
This would allow me to interact with the LLM from various environments, including chatbots, agents, or platforms like FlowiseAI.
Can anyone guide me or recommend a tutorial on how ... | 2023-09-05T10:13:17 | https://www.reddit.com/r/LocalLLaMA/comments/16ak8ip/need_guidance_on_exposing_local_api_for_my_llm/ | Dave86ch | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 16ak8ip | false | null | t3_16ak8ip | /r/LocalLLaMA/comments/16ak8ip/need_guidance_on_exposing_local_api_for_my_llm/ | false | false | self | 6 | null |
Feed LLM with local knowledge | 14 | Say I want to build a LLM for films and movie production, I have several data to feed in:
\- description of the movie production process
\- some facts about "what is a good film" extracted during interviews
\- some movie titles along with metadata (film director, rating, year release, ...)
In short, I have a lot of... | 2023-09-05T09:50:10 | https://www.reddit.com/r/LocalLLaMA/comments/16ajtl8/feed_llm_with_local_knowledge/ | front-equal | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 16ajtl8 | false | null | t3_16ajtl8 | /r/LocalLLaMA/comments/16ajtl8/feed_llm_with_local_knowledge/ | false | false | self | 14 | null |
Has anyone finetuned LLAMA models using TPUs? | 16 | I have received access to resources on GCP for my research and I am curious if I can use them to fine-tune LLAMA models using Peft. | 2023-09-05T08:55:24 | https://www.reddit.com/r/LocalLLaMA/comments/16aiw18/has_anyone_finetuned_llama_models_using_tpus/ | Marc_Marc_ | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 16aiw18 | false | null | t3_16aiw18 | /r/LocalLLaMA/comments/16aiw18/has_anyone_finetuned_llama_models_using_tpus/ | false | false | self | 16 | null |
GitHub Copilot vs CodeLlama & Co for Code productivity | 9 | Hi everyone,
I am currently benchmarking the different LLMs for code productivity for my company and trying to find the best one in terms of cost / performance / latency / privacy.
The current challengers I see are in three brackets:
\- GitHub Copilot
\- Local models like CodeLlama & Co
\- Other vendors for LLMs... | 2023-09-05T08:55:00 | https://www.reddit.com/r/LocalLLaMA/comments/16aivry/github_copilot_vs_codellama_co_for_code/ | Separate-Still3770 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 16aivry | false | null | t3_16aivry | /r/LocalLLaMA/comments/16aivry/github_copilot_vs_codellama_co_for_code/ | false | false | self | 9 | null |
Estimated cost of a 13b model on a server with H24 workflow/Concurrent users | 0 | Hey,
I was wondering what would be the cheapest way to get MythoMax 13b running on a server with enough power so that sometimes API queries can be made at the same time. The model would be running H24. What would be the way to go ? Is there a solution that can evolve with my needs if after some time I need more power?... | 2023-09-05T08:49:51 | https://www.reddit.com/r/LocalLLaMA/comments/16aisrp/estimated_cost_of_a_13b_model_on_a_server_with/ | Traditional_Hurry622 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 16aisrp | false | null | t3_16aisrp | /r/LocalLLaMA/comments/16aisrp/estimated_cost_of_a_13b_model_on_a_server_with/ | false | false | self | 0 | null |
Lora vs Embeddings (Vector DB?) Knowledge Training | 26 | Hi all,
So recently my company wanted to venture into LLMs, the use-case is a standard one, where we will inject company-specific knowledgebase and use it internally, it might possibly serve other headquarters across the globe as well. The plan is to try Llama 2, then Code-Llama.
I tried created a very simple csv (on... | 2023-09-05T08:46:46 | https://www.reddit.com/r/LocalLLaMA/comments/16aiqxo/lora_vs_embeddings_vector_db_knowledge_training/ | cringelord000222 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 16aiqxo | false | null | t3_16aiqxo | /r/LocalLLaMA/comments/16aiqxo/lora_vs_embeddings_vector_db_knowledge_training/ | false | false | self | 26 | null |
Running Llama 2 on a SLURM script | 1 | I am currently having issues with even getting a Llama2-7b to run on a HPC even though I have access to enough GPUs. I don’t believe there is an issue with my code but there easily could be. I have followed a typical huggingface guide to get it running on transformers. However it usually times out after a certain point... | 2023-09-05T08:38:29 | https://www.reddit.com/r/LocalLLaMA/comments/16ailwv/running_llama_2_on_a_slurm_script/ | Fooples | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 16ailwv | false | null | t3_16ailwv | /r/LocalLLaMA/comments/16ailwv/running_llama_2_on_a_slurm_script/ | false | false | self | 1 | null |
Advice Getting Started w/ an AI Model - First: Which One? | 0 | I'm looking for some advice. I'm going to build an AI and train it, but I would love it to be pre-trained as a functional LLM first. First: What model should I use? What most up-to-date? What do I find that?
Here's my hardware: I have an old 1st Generation Intel i7 desktop computer that I want to convert into a de... | 2023-09-05T08:23:38 | https://www.reddit.com/r/LocalLLaMA/comments/16aid7o/advice_getting_started_w_an_ai_model_first_which/ | FlowingFire | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 16aid7o | false | null | t3_16aid7o | /r/LocalLLaMA/comments/16aid7o/advice_getting_started_w_an_ai_model_first_which/ | false | false | self | 0 | null |
RTX 3080 Ti vs 4090 for QLoRa | 3 | I am a laptop user and want to get a new company laptop with the most amount of VRAM for model fine-tuning.
I can choose between the RTX 3080 Ti and the RTX 4099. Both have 16GB VRAM, (so enough for QLoRa on 13B?)
But what are the differences in terms of performance? What speedup can I expect from a 4090? | 2023-09-05T07:01:24 | https://www.reddit.com/r/LocalLLaMA/comments/16agzb9/rtx_3080_ti_vs_4090_for_qlora/ | Koliham | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 16agzb9 | false | null | t3_16agzb9 | /r/LocalLLaMA/comments/16agzb9/rtx_3080_ti_vs_4090_for_qlora/ | false | false | self | 3 | null |
Deploying a fine-tuned LLaMA 2 model | 15 | I have been following this tutorial: https://www.philschmid.de/sagemaker-llama2-qlora that details how to fine-tune a LLaMA model using AWS SageMaker. I have attempted to deploy it locally (retrieving the model from the S3 bucket onto my local PC) but loading the model gave a bunch of common bitsandbytes errors related... | 2023-09-05T06:16:20 | https://www.reddit.com/r/LocalLLaMA/comments/16ag6ux/deploying_a_finetuned_llama_2_model/ | arkeniwnl | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 16ag6ux | false | null | t3_16ag6ux | /r/LocalLLaMA/comments/16ag6ux/deploying_a_finetuned_llama_2_model/ | false | false | self | 15 | {'enabled': False, 'images': [{'id': 'a1hmOnL77g0KEwQYz1ospL2mdtWnUUs4gvIEoj1uaZQ', 'resolutions': [{'height': 66, 'url': 'https://external-preview.redd.it/oD1pkZuJzDIaMa8rqAkLr3IbeHQwt3g4JwPFjRIiQ7Y.jpg?width=108&crop=smart&auto=webp&s=51e5811563287b81728e9f1934f629170807ff4e', 'width': 108}, {'height': 133, 'url': 'h... |
Efficient tokenization of timestamps? | 1 | Good golly, timestamps tokenize poorly. I'm experimenting with adding timestamps as prefixes to chat messages, and finding that they take one character per token in some cases (such as below for the string `[9/4/23 11:51PM]`), based on the strftime `%-m/%-d/%y %-I:%M%p`)
When I toggle timestamps in my custom app, I g... | 2023-09-05T05:02:27 | https://www.reddit.com/r/LocalLLaMA/comments/16aeu3b/efficient_tokenization_of_timestamps/ | tronathan | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 16aeu3b | false | null | t3_16aeu3b | /r/LocalLLaMA/comments/16aeu3b/efficient_tokenization_of_timestamps/ | false | false | 1 | null | |
How can I use multiple computers to locally run LLM's with a API endpoint? | 9 | My plan is to have a few computers on the network to work together to run a (or multiple) models locally with API to use with a chat interface. Any idea as to how I can do this? | 2023-09-05T04:08:22 | https://www.reddit.com/r/LocalLLaMA/comments/16adse5/how_can_i_use_multiple_computers_to_locally_run/ | heyitsradin | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 16adse5 | false | null | t3_16adse5 | /r/LocalLLaMA/comments/16adse5/how_can_i_use_multiple_computers_to_locally_run/ | false | false | self | 9 | null |
How to fine-tuning LLM for a chat bot to answer about a website's functionalities? | 3 | Hello, so I’m fine-tuning a LLM to use as a chat bot for a website. My goal is to allow the bot to be able to answer questions about this website’s functionalities, e.g. how to change password, what are the payment methods available, how to download certain games etc…
Currently, my dataset consists of a list of users’... | 2023-09-05T03:49:53 | https://www.reddit.com/r/LocalLLaMA/comments/16adfar/how_to_finetuning_llm_for_a_chat_bot_to_answer/ | scienceotaku68 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 16adfar | false | null | t3_16adfar | /r/LocalLLaMA/comments/16adfar/how_to_finetuning_llm_for_a_chat_bot_to_answer/ | false | false | self | 3 | {'enabled': False, 'images': [{'id': 'BxNvUeMFd6obe78ihkAJrzGJFpOkQpmEJ7BbVi_larY', 'resolutions': [{'height': 60, 'url': 'https://external-preview.redd.it/2J07IKccOEu528Dr2WlyssuQYfjax6yT553dEfNzT00.jpg?width=108&crop=smart&auto=webp&s=93162f369263d5c2a9e1768260a77dbe05103f3e', 'width': 108}, {'height': 121, 'url': 'h... |
Looking for Llama model to run on Google Collab (either free or pro) | 1 | Hello, as the name says, I'm looking for a version of Llama that can run on Collab, and I'm willing to pay for higher GPU. I'm trying a quantized version now here: [https://github.com/MuhammadMoinFaisal/LargeLanguageModelsProjects/blob/main/Run%20Llama2%20Google%20Colab/Llama\_2.ipynb](https://github.com/MuhammadMoinFa... | 2023-09-05T02:19:54 | https://www.reddit.com/r/LocalLLaMA/comments/16abkaq/looking_for_llama_model_to_run_on_google_collab/ | M1x1ma | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 16abkaq | false | null | t3_16abkaq | /r/LocalLLaMA/comments/16abkaq/looking_for_llama_model_to_run_on_google_collab/ | false | false | self | 1 | {'enabled': False, 'images': [{'id': 'eKjsCg89liVZs8XOdObb8bG5Phv6NC5UPXepy7tAe9c', 'resolutions': [{'height': 54, 'url': 'https://external-preview.redd.it/aW7Vqh0303tpwdK67i-L4f6Y3WiLzyvCpoM9yIvLsOQ.jpg?width=108&crop=smart&auto=webp&s=00c1aa9eb551167bc15de42add005d453be9eef3', 'width': 108}, {'height': 108, 'url': 'h... |
Automated Routing of Tasks to Optimal Models: A PR for Semantic-Kernel | 8 | The need for efficient model routing has been a [point of discussion](https://twitter.com/Altimor/status/1696221744024142210) in the community. Addressing this, I've submitted a [pull request](https://github.com/microsoft/semantic-kernel/pull/2323) to Semantic-Kernel that introduces an automated multi-model connector.
... | 2023-09-04T23:40:53 | https://www.reddit.com/r/LocalLLaMA/comments/16a80j4/automated_routing_of_tasks_to_optimal_models_a_pr/ | Jessynoo | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 16a80j4 | false | null | t3_16a80j4 | /r/LocalLLaMA/comments/16a80j4/automated_routing_of_tasks_to_optimal_models_a_pr/ | false | false | self | 8 | {'enabled': False, 'images': [{'id': 'JEsRby0ymh-Lsg-o1hInETv2KYW9o55WVpsSQSVxEFk', 'resolutions': [{'height': 137, 'url': 'https://external-preview.redd.it/rLV5GfkPivMe22A0Kw7Y8OW3AAW6hjWXV9XXnnuAQ9A.jpg?width=108&crop=smart&auto=webp&s=29604d57b4f02de40372a1dbeb5fce4053eeaece', 'width': 108}, {'height': 275, 'url': '... |
Code Llama is Amazing! | 47 | phind-codellama-34b-v2.Q5\_K\_S.gguf works great, but I've actually only needed codellama-13b-oasst-sft-v10.Q4\_K\_S.gguf
This is what I've been waiting for. I'm not going to say it's as good as chatGPT 3.5, but for most of my purposes it is. I'm using KoboldCPP with a temperature setting of .1 and it passes all of... | 2023-09-04T23:08:02 | https://www.reddit.com/r/LocalLLaMA/comments/16a78bf/code_llama_is_amazing/ | ThePseudoMcCoy | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 16a78bf | false | null | t3_16a78bf | /r/LocalLLaMA/comments/16a78bf/code_llama_is_amazing/ | false | false | self | 47 | {'enabled': False, 'images': [{'id': 'OgFzGCIRw1ZxjMOSkfV1OiH-_nQiZl8rzSonmOAuhGs', 'resolutions': [{'height': 108, 'url': 'https://external-preview.redd.it/-WiKXADWH5lgU4gQv5fcDAQ9QKNBZTJ-D83BykIL2HA.jpg?width=108&crop=smart&auto=webp&s=df9c6a296446d05d873c629a30253398c4d29c1b', 'width': 108}], 'source': {'height': 15... |
docker wont work when trying to install Nous Hermes Llama 2 13B | 1 | [removed] | 2023-09-04T22:20:42 | https://www.reddit.com/r/LocalLLaMA/comments/16a61ca/docker_wont_work_when_trying_to_install_nous/ | TheFarisaurusRex | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 16a61ca | false | null | t3_16a61ca | /r/LocalLLaMA/comments/16a61ca/docker_wont_work_when_trying_to_install_nous/ | false | false | self | 1 | {'enabled': False, 'images': [{'id': 'EgxglN1oOrkKevE7sa6DylFeaX96Qyhel4McIlIaExc', 'resolutions': [{'height': 81, 'url': 'https://external-preview.redd.it/9NKrQ8iiWMltHEGCGEqcM5TbhnxHuY6oq0Yb4gvuvnQ.jpg?width=108&crop=smart&auto=webp&s=fd6eea8730d5aab3bf78c89a32c0af1c3b782d29', 'width': 108}, {'height': 162, 'url': 'h... |
Need Advice: I have 12 , RTX3070s and want to put them to work on an AI project… What are some ideas that I could enhance my work/life/financial situation ? | 2 | First time posting on here, been watching for awhile… very thankful for all of your contributions. It’s helped me understand a lot of very complex thoughts about this new world we live in.
So I have been exploring ideas and training myself in python on basic concepts such as installing packages and basic functions and... | 2023-09-04T20:49:04 | https://www.reddit.com/r/LocalLLaMA/comments/16a3l0l/need_advice_i_have_12_rtx3070s_and_want_to_put/ | Overall-Split8048 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 16a3l0l | false | null | t3_16a3l0l | /r/LocalLLaMA/comments/16a3l0l/need_advice_i_have_12_rtx3070s_and_want_to_put/ | false | false | self | 2 | null |
Finetuning a llama 2 model using Claude or Claude instant dataset. | 8 | Won't it be nice to finetune a LLaMA 2 model on a custom dataset crafted from Anthropic Claude models, particularly the Claude instant or Claude 2 models? Most finetuned models are based on messages generated using GPT-4, so it would be interesting to see a LLaMA 2 model finetuned on a jailbroken/uncensored Claude data... | 2023-09-04T20:34:59 | https://www.reddit.com/r/LocalLLaMA/comments/16a37eq/finetuning_a_llama_2_model_using_claude_or_claude/ | DannyBrownMz | self.LocalLLaMA | 2023-09-04T20:53:42 | 0 | {} | 16a37eq | false | null | t3_16a37eq | /r/LocalLLaMA/comments/16a37eq/finetuning_a_llama_2_model_using_claude_or_claude/ | false | false | self | 8 | null |
vllm reducing quality when loading local fine tuned llama2 model | 7 | Has anyone else encountered the issue that a model loaded with vllm generates low quality/gibberish output when using a local, fine tuned llama2 13B hf model?
Just using the standard inference method from the vllm blog:
`from vllm import LLM`
`prompts = ["Hello, my name is", "The capital of France is"]`
`llm = LLM(... | 2023-09-04T17:53:15 | https://www.reddit.com/r/LocalLLaMA/comments/169ytis/vllm_reducing_quality_when_loading_local_fine/ | DeanBlub | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 169ytis | false | null | t3_169ytis | /r/LocalLLaMA/comments/169ytis/vllm_reducing_quality_when_loading_local_fine/ | false | false | self | 7 | null |
🚀We trained a new 1.6B parameters code model that reaches 32% HumanEval and is SOTA for the size | 186 | We’ve finished training a new code model Refact LLM which took us about a month. The main use case is for blazing-fast code completion with fill-in-the-middle, additionally, the model could reply to chat prompts.
It has much better performance than all of the code models of similar size, and almost reaches the same Hu... | 2023-09-04T17:48:01 | https://www.reddit.com/r/LocalLLaMA/comments/169yonh/we_trained_a_new_16b_parameters_code_model_that/ | kateklink | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 169yonh | false | null | t3_169yonh | /r/LocalLLaMA/comments/169yonh/we_trained_a_new_16b_parameters_code_model_that/ | false | false | self | 186 | {'enabled': False, 'images': [{'id': '1_wks0LGL7qavGXNT_Z37zwFckag2ZQ7CPAL6tKcDAo', 'resolutions': [{'height': 66, 'url': 'https://external-preview.redd.it/n8v241FMHVkDSAuIqs1OnzTDATwrQoobgY3lRVuiavg.jpg?width=108&crop=smart&auto=webp&s=b3affacaf0b9cd81d36f7334d635b14396159d1f', 'width': 108}, {'height': 132, 'url': 'h... |
Method to split model matrices | 1 | [removed] | 2023-09-04T17:44:46 | https://www.reddit.com/r/LocalLLaMA/comments/169ylj0/method_to_split_model_matrices/ | FootballDoc | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 169ylj0 | false | null | t3_169ylj0 | /r/LocalLLaMA/comments/169ylj0/method_to_split_model_matrices/ | false | false | self | 1 | null |
Split model matrices | 1 | [removed] | 2023-09-04T17:43:35 | https://www.reddit.com/r/LocalLLaMA/comments/169ykh7/split_model_matrices/ | FootballDoc | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 169ykh7 | false | null | t3_169ykh7 | /r/LocalLLaMA/comments/169ykh7/split_model_matrices/ | false | false | self | 1 | null |
llama2 GPU speedup | 1 | How to use GPU to run LLAMA2 faster. Using CPU is too slow when I wish to do lot of repetitive summary on data. I have tried llama-cpp-python library and done all that I can find to use my 4gb gpu nvidia t1200 but is not working. Can ctransformer be good option ? is it fast? | 2023-09-04T17:34:50 | https://www.reddit.com/r/LocalLLaMA/comments/169yc3f/llama2_gpu_speedup/ | PhantomLord06 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 169yc3f | false | null | t3_169yc3f | /r/LocalLLaMA/comments/169yc3f/llama2_gpu_speedup/ | false | false | self | 1 | null |
4x3060 testing | 19 |
Tested today rig on vast.ai with 4x3060
I didn't have much time, so i have not played with gpu split properly to measure max context, but it seems that it's not spread evenly between gpus...
in eu you can get 4x3060 with 24 months guarantee for 1300$
2x3090, used, 6 months guarantee (not offical) will cost 1900$
1x... | 2023-09-04T17:07:20 | https://www.reddit.com/r/LocalLLaMA/comments/169xlzb/4x3060_testing/ | kpodkanowicz | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 169xlzb | false | null | t3_169xlzb | /r/LocalLLaMA/comments/169xlzb/4x3060_testing/ | false | false | self | 19 | null |
Building an agent using an open llm | 7 | Hi, I am trying to build a very simple agent as a POC with the end goal of summarizing a document gotten from the web (like a paper from arxiv). I have been using the react format (I think?) where it looks like:
Below is an instruction that describes a task, paired with an input that provides further context.... | 2023-09-04T16:46:07 | https://www.reddit.com/r/LocalLLaMA/comments/169x1ud/building_an_agent_using_an_open_llm/ | klop2031 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 169x1ud | false | null | t3_169x1ud | /r/LocalLLaMA/comments/169x1ud/building_an_agent_using_an_open_llm/ | false | false | self | 7 | null |
Since lot of people took interest in my project, So uploading a screenshot of llama 2 chat 13B running locally using google search to provide answers. | 0 | 2023-09-04T16:18:53 | akbbiswas | i.redd.it | 1970-01-01T00:00:00 | 0 | {} | 169wbto | false | null | t3_169wbto | /r/LocalLLaMA/comments/169wbto/since_lot_of_people_took_interest_in_my_project/ | false | false | 0 | {'enabled': True, 'images': [{'id': 'G7iJSL46kXKFJpX9Z3gb5dx_p9PdLNFBlVSX5sRZv_8', 'resolutions': [{'height': 113, 'url': 'https://preview.redd.it/fcgrjdjok9mb1.png?width=108&crop=smart&auto=webp&s=f19fb9bc0d6eba0f02ce780022f8345536853368', 'width': 108}, {'height': 227, 'url': 'https://preview.redd.it/fcgrjdjok9mb1.pn... | |||
Code interpreter/data analysis via open source LLM? | 1 | [removed] | 2023-09-04T15:43:17 | https://www.reddit.com/r/LocalLLaMA/comments/169vduc/code_interpreterdata_analysis_via_open_source_llm/ | alvintsoiwc | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 169vduc | false | null | t3_169vduc | /r/LocalLLaMA/comments/169vduc/code_interpreterdata_analysis_via_open_source_llm/ | false | false | self | 1 | null |
Multi-bot chat with fictional characters | 1 | [removed] | 2023-09-04T14:58:26 | https://www.reddit.com/r/LocalLLaMA/comments/169u7vi/multibot_chat_with_fictional_characters/ | justynasty | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 169u7vi | false | null | t3_169u7vi | /r/LocalLLaMA/comments/169u7vi/multibot_chat_with_fictional_characters/ | false | false | 1 | null | |
Running llama 2(any model) in nodejs? | 4 | I'm trying to run llama2 model by using node js but am constantly running into errors. The langchain documentation recommends some other npm package and there are some tutorials out there which are using a totally different npm package. I've tried everything(even moved the file to D) in order to make the path simple, b... | 2023-09-04T14:58:25 | ContributionFun3037 | i.redd.it | 1970-01-01T00:00:00 | 0 | {} | 169u7uy | false | null | t3_169u7uy | /r/LocalLLaMA/comments/169u7uy/running_llama_2any_model_in_nodejs/ | false | false | 4 | {'enabled': True, 'images': [{'id': 'iRLT8rdRwC5gQtd-UvcLOZxBTqino1NRhn9RgH-qsZg', 'resolutions': [{'height': 58, 'url': 'https://preview.redd.it/lbsexelh69mb1.jpg?width=108&crop=smart&auto=webp&s=da11e411f7bf367fe945f463eeb9eacc874668ba', 'width': 108}, {'height': 116, 'url': 'https://preview.redd.it/lbsexelh69mb1.jpg... | ||
Best plan on runpod.ai for running a model for rpg/storywriting (like mythomax) | 1 | I wanna run a really model on the cloud to use it for a rpg/solo play. I am wanna use a model with a high context memory and some nice parameters. I looked up runpod and the I'm not sure what plan to choose for the same (I do not have enough resources on my local). Can someone tell me which plan I should be using? or i... | 2023-09-04T14:17:58 | https://www.reddit.com/r/LocalLLaMA/comments/169t7g5/best_plan_on_runpodai_for_running_a_model_for/ | Mani_and_5_others | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 169t7g5 | false | null | t3_169t7g5 | /r/LocalLLaMA/comments/169t7g5/best_plan_on_runpodai_for_running_a_model_for/ | false | false | self | 1 | null |
WizardLM is writing replies from "User:" After it's Own Response! | 1 | Decided to try and run WizardLM "ehartford/WizardLM-7B-Uncensored" for fun - to see if I could get it to help me with a reverse engineering project that I am working on. Normal models don't help as they think I am a hacker.
The model loads, and I can prompt it, but many times, after it's response, it continues on with... | 2023-09-04T13:56:27 | https://www.reddit.com/r/LocalLLaMA/comments/169soe5/wizardlm_is_writing_replies_from_user_after_its/ | JustinPooDough | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 169soe5 | false | null | t3_169soe5 | /r/LocalLLaMA/comments/169soe5/wizardlm_is_writing_replies_from_user_after_its/ | false | false | self | 1 | null |
WizardLM is writing replies from "User:" After it's Own Response! | 4 | Decided to try and run WizardLM "ehartford/WizardLM-7B-Uncensored" for fun - to see if I could get it to help me with a reverse engineering project that I am working on. Normal models don't help as they think I am a hacker.
The model loads, and I can prompt it, but many times, after it's response, it continues on with... | 2023-09-04T13:56:27 | https://www.reddit.com/r/LocalLLaMA/comments/169soec/wizardlm_is_writing_replies_from_user_after_its/ | JustinPooDough | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 169soec | false | null | t3_169soec | /r/LocalLLaMA/comments/169soec/wizardlm_is_writing_replies_from_user_after_its/ | false | false | self | 4 | null |
Question: How do I post a job for someone with experience fine tuning and configuring a model? | 2 | We've got a couple of projects from clients that we originally pitched using gpt/palm, but I feel that we could we getting better performance (both cost and quality) with a finetune. In addition a potential client has a policy banning any model not on their own Infra and we are fully booked.
So I'm looking to hire so... | 2023-09-04T13:36:31 | https://www.reddit.com/r/LocalLLaMA/comments/169s7vs/question_how_do_i_post_a_job_for_someone_with/ | alexmrv | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 169s7vs | false | null | t3_169s7vs | /r/LocalLLaMA/comments/169s7vs/question_how_do_i_post_a_job_for_someone_with/ | false | false | self | 2 | null |
OTS Structured Document Segmentation Suggestions for RAG Pipeline | 1 | [removed] | 2023-09-04T13:24:57 | https://www.reddit.com/r/LocalLLaMA/comments/169ry7h/ots_structured_document_segmentation_suggestions/ | RedditAppSucksDicks | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 169ry7h | false | null | t3_169ry7h | /r/LocalLLaMA/comments/169ry7h/ots_structured_document_segmentation_suggestions/ | false | false | default | 1 | null |
Python LLama 2 on windows | 0 | Hello Guys,
I am looking for a way to run llama 2 on windows by python.
I have read that it is done by llama.cpp, but unfortunately it is not running for me...
My error: ModuleNotFoundError: No module named 'llama\_cpp'
But llama cpp is already installed
Is using llama\_cpp the only way to run llama 2?
I ne... | 2023-09-04T13:23:00 | https://www.reddit.com/r/LocalLLaMA/comments/169rwof/python_llama_2_on_windows/ | Enkay55 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 169rwof | false | null | t3_169rwof | /r/LocalLLaMA/comments/169rwof/python_llama_2_on_windows/ | false | false | self | 0 | null |
Tweaking the llama2 architecture | 1 | I want to tweak llama2-7b-hf model to include skip connections and layer norm in between certain layers. Is it possible to do this in pytorch and/or hugginface format? | 2023-09-04T13:04:02 | https://www.reddit.com/r/LocalLLaMA/comments/169rglv/tweaking_the_llama2_architecture/ | Ornery-Young-7346 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 169rglv | false | null | t3_169rglv | /r/LocalLLaMA/comments/169rglv/tweaking_the_llama2_architecture/ | false | false | self | 1 | null |
Story Telling workflow | 11 | I have recently found interest in generating stories with LLM models. But most of stories that I generate have very less actions or verbal things going on and most of the time gives me some kind of summary with no dialogues. In short I like things slow( if you know what I mean ).
But still I must say that my go to mo... | 2023-09-04T12:33:07 | https://www.reddit.com/r/LocalLLaMA/comments/169qt0o/story_telling_workflow/ | Darkmeme9 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 169qt0o | false | null | t3_169qt0o | /r/LocalLLaMA/comments/169qt0o/story_telling_workflow/ | false | false | self | 11 | null |
Using a Local LLM to Anonymize Prompts Before Routing Through a Commercial LLM via VPN? | 2 | Yeehaw, y’all 🤠
I’ve been mulling over an idea to use a commercial LLM for counseling in a private way.
This came to mind when I was exploring Claude.ai, which utilizes Claude-2 and allows access via VPN without the need for phone number registration, unlike ChatGPT. It’s an impressive LLM, but Anthropics privacy po... | 2023-09-04T12:14:38 | https://www.reddit.com/r/LocalLLaMA/comments/169qfdc/using_a_local_llm_to_anonymize_prompts_before/ | Prince-of-Privacy | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 169qfdc | false | null | t3_169qfdc | /r/LocalLLaMA/comments/169qfdc/using_a_local_llm_to_anonymize_prompts_before/ | false | false | self | 2 | null |
What are the difference types of quantization? I know about ggml, gptq, q4_0, q4_1,q5_0. What is the relationship between gptq and the q4_0 models | 4 | What is the relationship between gptq and the q4_0 models, is it of quantization for weight and quantization for inference? | 2023-09-04T11:57:50 | https://www.reddit.com/r/LocalLLaMA/comments/169q2xh/what_are_the_difference_types_of_quantization_i/ | Top_Window_1417 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 169q2xh | false | null | t3_169q2xh | /r/LocalLLaMA/comments/169q2xh/what_are_the_difference_types_of_quantization_i/ | false | false | self | 4 | null |
Why is Microsoft collaborating with Meta on Open Source Llama? | 61 | I am confused by this. MSFT own half of OpenAI and ChatGPT.
And yet:
>Jul 18, 2023 — *Microsoft* and *Meta* are expanding their longstanding partnership, with *Microsoft* as the preferred partner for *Llama* 2.
​
while Meta openly declares this as an effort to overthrow ChatGPT:
​
>Jul 18, 2023 ... | 2023-09-04T11:11:41 | https://www.reddit.com/r/LocalLLaMA/comments/169p86m/why_is_microsoft_collaborating_with_meta_on_open/ | Infinite100p | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 169p86m | false | null | t3_169p86m | /r/LocalLLaMA/comments/169p86m/why_is_microsoft_collaborating_with_meta_on_open/ | false | false | self | 61 | null |
Can anyone explain in simple words how speculative sampling works and how to use it? | 14 | Can anyone explain in simple words how speculative sampling(https://github.com/ggerganov/llama.cpp/pull/2926) works and how to use it? | 2023-09-04T11:03:40 | https://www.reddit.com/r/LocalLLaMA/comments/169p2w5/can_anyone_explain_in_simple_words_how/ | IonLin | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 169p2w5 | false | null | t3_169p2w5 | /r/LocalLLaMA/comments/169p2w5/can_anyone_explain_in_simple_words_how/ | false | false | self | 14 | {'enabled': False, 'images': [{'id': 'bdfkCq85S-98mc6-Ykf0KqRea1XNLmqNwOjwH93uviE', 'resolutions': [{'height': 54, 'url': 'https://external-preview.redd.it/lzKmiKH0pPoitA-pFSh6So8ZRAVWrDLnY2CJQrBE8Ug.jpg?width=108&crop=smart&auto=webp&s=d15b6505d4fefe7611b62812ea8bc0583db0fced', 'width': 108}, {'height': 108, 'url': 'h... |
MEE6 AI CHARACTER BOT | 0 | Just tested out the new Mee6 AI feature, and I gotta say, it's mind-blowing! Had a chat with Elon, and every response felt genuine, like something Elon himself would say. It even threw some attitude when I questioned his actions!
Anyone have insights on what's powering this AI in the background? I'm absolutely fasci... | 2023-09-04T10:53:48 | https://www.reddit.com/r/LocalLLaMA/comments/169owg8/mee6_ai_character_bot/ | sarimsak13 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 169owg8 | false | null | t3_169owg8 | /r/LocalLLaMA/comments/169owg8/mee6_ai_character_bot/ | false | false | 0 | null | |
Adapting CodeLlama to an unseen language during training and its technical reports | 4 | I want to experiment with CodeLlama on a F# which I assume is not seen during training. I have a lot of code, audit reports and documentation of projects built using this language.
My goal is to experiment with this model in order to:
* being able to help security researchers check a code base (<100k tokens) and get ... | 2023-09-04T10:29:40 | https://www.reddit.com/r/LocalLLaMA/comments/169ogzf/adapting_codellama_to_an_unseen_language_during/ | front-equal | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 169ogzf | false | null | t3_169ogzf | /r/LocalLLaMA/comments/169ogzf/adapting_codellama_to_an_unseen_language_during/ | false | false | self | 4 | null |
MYthomax: 0 token output for certain inputs | 1 |
I was experimenting with mythomax(alpaca with input) on ooba. And it started outputting nothing for certain inputs. And i tried certain inputs like:
\*hugs you\*, \*touches you\* and some other inputs.
If i change the input it works fine. I am using the default tab with raw responses on ooba and not chat.
Img:
... | 2023-09-04T10:08:46 | https://www.reddit.com/r/LocalLLaMA/comments/169o3qa/mythomax_0_token_output_for_certain_inputs/ | ll_Teto_ll | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 169o3qa | false | null | t3_169o3qa | /r/LocalLLaMA/comments/169o3qa/mythomax_0_token_output_for_certain_inputs/ | false | false | self | 1 | {'enabled': False, 'images': [{'id': 'RAUj-9XvfHjk-7GK11jfHpn_sa2GlhPDO-xkDka4XlE', 'resolutions': [{'height': 10, 'url': 'https://external-preview.redd.it/wvhsK3L4E-hXs8wtssZgcwR8ogXGocZJ8grEhT2cJXk.jpg?width=108&crop=smart&auto=webp&s=1fd67faa65177854918c3ed8057776eb14d2466e', 'width': 108}, {'height': 20, 'url': 'ht... |
Finetuning codellama34B | 10 | I've successfully finetuned llama1(7B, 13B, 34B) and llama2 (7B, 13B) GPTQ weights using johnsmith0031 but can't seem to get it to work with codellama34B with my custom dataset.
What are you guys using to finetune codellama34B? Thanks | 2023-09-04T10:03:50 | https://www.reddit.com/r/LocalLLaMA/comments/169o0fv/finetuning_codellama34b/ | 2muchnet42day | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 169o0fv | false | null | t3_169o0fv | /r/LocalLLaMA/comments/169o0fv/finetuning_codellama34b/ | false | false | self | 10 | null |
ggmlv3 llama.cpp | 1 | Hi 👋
Do you know if it's possible to use convert.py to convert a .pth llama file into ggmlv3?
​ | 2023-09-04T09:59:30 | https://www.reddit.com/r/LocalLLaMA/comments/169nxfm/ggmlv3_llamacpp/ | Savings_Scholar | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 169nxfm | false | null | t3_169nxfm | /r/LocalLLaMA/comments/169nxfm/ggmlv3_llamacpp/ | false | false | self | 1 | null |
Oh go suck on a lemon llama2 13B! | 17 | what percentage of men are taller than women?
It is not appropriate to make generalizations about the heights of individuals based on their gender. Both men and women can have a wide range of heights, and there is no inherent difference in height between the two genders. Additionally, it is important to recognize tha... | 2023-09-04T09:35:50 | https://www.reddit.com/r/LocalLLaMA/comments/169nj89/oh_go_suck_on_a_lemon_llama2_13b/ | LetsUploadOurBrains | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 169nj89 | false | null | t3_169nj89 | /r/LocalLLaMA/comments/169nj89/oh_go_suck_on_a_lemon_llama2_13b/ | false | false | self | 17 | null |
Seed data for LLM Alignment | 2 | Hello,
I went through some LLM Alignment papers (Self-Instruct, Orca, Backtranslation, ...), my question is: If I want to use one of them, do I have to have the same number of seed data ?
They are quite innovative, but seed instructions size isn't really explained (why 175 for self-instruct, why 3200 for Backtranslat... | 2023-09-04T09:30:28 | https://www.reddit.com/r/LocalLLaMA/comments/169nfzu/seed_data_for_llm_alignment/ | AhmedAl93 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 169nfzu | false | null | t3_169nfzu | /r/LocalLLaMA/comments/169nfzu/seed_data_for_llm_alignment/ | false | false | self | 2 | null |
If we know MOE is the future, why doesn't the opensource community have a "Mixer" model yet? | 3 | I do not know much about the MOE arch but I imagine this mixer model as the same as sentiment analysis models, you throw the prompt at it and it tells you which model you should use and then the pipeline picks a model based on the mixer's output and throws the same prompt at it.
If my assumptions are true, why don't w... | 2023-09-04T09:23:11 | https://www.reddit.com/r/LocalLLaMA/comments/169nblb/if_we_know_moe_is_the_future_why_doesnt_the/ | yehiaserag | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 169nblb | false | null | t3_169nblb | /r/LocalLLaMA/comments/169nblb/if_we_know_moe_is_the_future_why_doesnt_the/ | false | false | self | 3 | null |
Subsets and Splits
No community queries yet
The top public SQL queries from the community will appear here once available.