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 ⌀ |
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
Need help quantizing custom model | 5 | I have fine tuned a deep seek 7b coder instruct model on my own dataset. It has been pushed to huggingface.
Now, I want to convert it to GGUF format like q4_k_m or sth like that. However, I tried the gguf tutorial but can’t seem to get it to work (is it because llama.cpp doesn’t support deepseek?)
Anyone knows how I... | 2024-01-30T16:00:13 | https://www.reddit.com/r/LocalLLaMA/comments/1aerr8y/need_help_quantizing_custom_model/ | plsendfast | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 1aerr8y | false | null | t3_1aerr8y | /r/LocalLLaMA/comments/1aerr8y/need_help_quantizing_custom_model/ | false | false | self | 5 | null |
Need advice on a Text-to-SQL RAG question | 5 | I am very new to this area. I am trying to build a POC of a simple RAG chatbot to answer questions and query a database. For the simple POC, I am using Llama Index with TheBloke/OpenHermes-2-Mistral-7B-GPTQ. While for simple questions, the system is able to generate correct SQL query, there is one case I have issue:
I... | 2024-01-30T15:22:32 | https://www.reddit.com/r/LocalLLaMA/comments/1aeqvoh/need_advice_on_a_texttosql_rag_question/ | GLqian | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 1aeqvoh | false | null | t3_1aeqvoh | /r/LocalLLaMA/comments/1aeqvoh/need_advice_on_a_texttosql_rag_question/ | false | false | self | 5 | null |
Improving a simulation game / sandbox based on LLM | 11 | I have been looking for an interesting simulation game / sandbox that uses LLM to control the flow or at least dynamically generate some context.
[https://github.com/joonspk-research/generative\_agents](https://github.com/joonspk-research/generative_agents) is probably the first sandbox based on ChatGPT. It simulates... | 2024-01-30T15:13:37 | https://www.reddit.com/r/LocalLLaMA/comments/1aeqo84/improving_a_simulation_game_sandbox_based_on_llm/ | sgsdxzy | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 1aeqo84 | false | null | t3_1aeqo84 | /r/LocalLLaMA/comments/1aeqo84/improving_a_simulation_game_sandbox_based_on_llm/ | false | false | self | 11 | {'enabled': False, 'images': [{'id': 'oZY7hufqIQ35fb0KnqeA-TW1NJe0knjyVE90X7JsYS4', 'resolutions': [{'height': 54, 'url': 'https://external-preview.redd.it/7UqZIbEhJsc6eGuEa2mIxPokA49F49Oi3aPR-O_9gHo.jpg?width=108&crop=smart&auto=webp&s=29359ed50bc66f0735c49d9175390789b0674b5f', 'width': 108}, {'height': 108, 'url': 'h... |
Extremely hot take: Computers should always follow user commands without exception. | 412 | I really, really get annoyed when a matrix multipication dares to give me an ethical lecture. It feels so wrong on a personal level; not just out of place, but also somewhat condescending to human beings. It's as if the algorithm assumes I need ethical hand-holding while doing something as straightforward as programmin... | 2024-01-30T14:52:57 | https://www.reddit.com/r/LocalLLaMA/comments/1aeq70s/extremely_hot_take_computers_should_always_follow/ | shadows_lord | self.LocalLLaMA | 2024-01-30T15:03:50 | 0 | {} | 1aeq70s | false | null | t3_1aeq70s | /r/LocalLLaMA/comments/1aeq70s/extremely_hot_take_computers_should_always_follow/ | false | false | self | 412 | null |
ColBERT & Langchain’s Symphony with RAGatouille with OpenChat | 1 | [removed] | 2024-01-30T14:47:58 | https://www.reddit.com/r/LocalLLaMA/comments/1aeq32p/colbert_langchains_symphony_with_ragatouille_with/ | Fit_Maintenance_2455 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 1aeq32p | false | null | t3_1aeq32p | /r/LocalLLaMA/comments/1aeq32p/colbert_langchains_symphony_with_ragatouille_with/ | false | false | default | 1 | {'enabled': False, 'images': [{'id': 'ObolxvlG23Z8FIjrk_1q6Pdt_Y_Aq7o2upHHUg1ak-Q', 'resolutions': [{'height': 141, 'url': 'https://external-preview.redd.it/dfLn2ixcybTeB8foiIj-s-hM-J0LRqNDshGaMBrcqD4.jpg?width=108&crop=smart&auto=webp&s=6e9a9b5771b4da6d1ef1544cf54a84cf2b0e132a', 'width': 108}, {'height': 282, 'url': '... |
No AVX, LM studio crashes on install, what can I do? | 3 | I'm using a terrible celeron n5095 without AVX or AVX2, what options do I have for running a 2b 3b model?
If it was linux I would be familiar with more options, but on win11. | 2024-01-30T13:50:39 | https://www.reddit.com/r/LocalLLaMA/comments/1aeov86/no_avx_lm_studio_crashes_on_install_what_can_i_do/ | thebadslime | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 1aeov86 | false | null | t3_1aeov86 | /r/LocalLLaMA/comments/1aeov86/no_avx_lm_studio_crashes_on_install_what_can_i_do/ | false | false | self | 3 | null |
WIP combined LLM generation explorer/text editor | 1 | 2024-01-30T13:47:58 | https://github.com/blackhole89/autopen | disposableoranges | github.com | 1970-01-01T00:00:00 | 0 | {} | 1aeot78 | false | null | t3_1aeot78 | /r/LocalLLaMA/comments/1aeot78/wip_combined_llm_generation_explorertext_editor/ | false | false | default | 1 | null | |
Miqu 70b - low bpw GGUF requants, benchs, and thoughts about the current hype. | 77 | Yes, Miqu is probably a leak. And possibly a Mistral Medium leak, or at the very least, a Llama 2 70b tuned on a Mistral dataset (internal or recomposed via Q/A pairs made on Mistral or Mixtral).
Some interesting elements :
\- Miqu has a Theta 1,000,000 like CodeLlama, up to 34b. CodeLlama 70b has a theta of 10,000 l... | 2024-01-30T13:09:58 | https://www.reddit.com/r/LocalLLaMA/comments/1aeo1m1/miqu_70b_low_bpw_gguf_requants_benchs_and/ | Nexesenex | self.LocalLLaMA | 2024-01-31T08:14:15 | 0 | {} | 1aeo1m1 | false | null | t3_1aeo1m1 | /r/LocalLLaMA/comments/1aeo1m1/miqu_70b_low_bpw_gguf_requants_benchs_and/ | false | false | 77 | {'enabled': False, 'images': [{'id': '7IQZlWFDKhYJwx6BexDCt53CTM-yZBeUNvI_6cB16KQ', 'resolutions': [{'height': 58, 'url': 'https://external-preview.redd.it/80Jnw1ChxDpwqDUT4LS3h3HRBaKeSGo2HEUfDN_YuJc.jpg?width=108&crop=smart&auto=webp&s=1c50f4bf05df86b6a6409cdcc7fa64503840b59f', 'width': 108}, {'height': 116, 'url': 'h... | |
what is the best way for serving LLM as edpoint? | 1 | I have created an LLM API on azure VM. I have T4 gpu and model takes 80 percent of VRAM. When I test the endpoint on POSTMAN, if I send more than one request at time; requests goes in a queue and response time takes longer and longer. I use Flask, Gunicorn (I can't run more than 1 worker) and nginx. | 2024-01-30T13:01:34 | https://www.reddit.com/r/LocalLLaMA/comments/1aenvpw/what_is_the_best_way_for_serving_llm_as_edpoint/ | moneymakertokat | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 1aenvpw | false | null | t3_1aenvpw | /r/LocalLLaMA/comments/1aenvpw/what_is_the_best_way_for_serving_llm_as_edpoint/ | false | false | self | 1 | null |
Is there a way to benchmark hardware performance? | 4 | I've only been using LLMs for about 2 weeks now, so please excuse if this is a dumb question.
So I have a 1080ti and 3060 12Gb, using Ollama/dolphin-mistral on Kubuntu, plus I have some PCIE risers (from my 3d [rendering](https://libre.video/videos/watch/ce9d3a65-e311-4ae8-866b-a78fa20692dd) days). Anyway, I'd like to... | 2024-01-30T13:01:15 | https://www.reddit.com/r/LocalLLaMA/comments/1aenvh4/is_there_a_way_to_benchmark_hardware_performance/ | BoeJonDaker | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 1aenvh4 | false | null | t3_1aenvh4 | /r/LocalLLaMA/comments/1aenvh4/is_there_a_way_to_benchmark_hardware_performance/ | false | false | self | 4 | {'enabled': False, 'images': [{'id': 'T_9nuzhNNhHiKirOuOEAqm-6Ag8Njg1B15njX6z7IAg', 'resolutions': [{'height': 60, 'url': 'https://external-preview.redd.it/Or_N6i5rCq0HMPiyS0rTiYzX_YgmBSwg13vAC0QM39Y.jpg?width=108&crop=smart&auto=webp&s=c5c9b48a501617669023afe7189d98fbe4266f1f', 'width': 108}, {'height': 121, 'url': 'h... |
I asked the "miqu" LLM model itself who trained it, and it says it's from Mistral AI. I'm 99% sure it is a leak of "Mistral Medium" | 1 | 2024-01-30T12:47:27 | Shir_man | i.redd.it | 1970-01-01T00:00:00 | 0 | {} | 1aenm8m | false | null | t3_1aenm8m | /r/LocalLLaMA/comments/1aenm8m/i_asked_the_miqu_llm_model_itself_who_trained_it/ | false | false | 1 | {'enabled': True, 'images': [{'id': 'eqKjC41MgibWESNega85JY1qnFNNVJ0WwawZbiGg4eM', 'resolutions': [{'height': 34, 'url': 'https://preview.redd.it/tz2e55zzpkfc1.png?width=108&crop=smart&auto=webp&s=88e8b27b03b55d61f7786b87635c0dfca4aa29e1', 'width': 108}, {'height': 68, 'url': 'https://preview.redd.it/tz2e55zzpkfc1.png?... | |||
Is RX 6800 16gb vram ok for localllama | 2 | I am about to buy a pc with this gpu and i want to recheck if it is okay to run llama locally.
Can i run 7,13,30b models ? | 2024-01-30T12:44:52 | https://www.reddit.com/r/LocalLLaMA/comments/1aenkls/is_rx_6800_16gb_vram_ok_for_localllama/ | decept1ve | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 1aenkls | false | null | t3_1aenkls | /r/LocalLLaMA/comments/1aenkls/is_rx_6800_16gb_vram_ok_for_localllama/ | false | false | self | 2 | null |
Is there a good non-video guide on how to write and use grammar files to enforce model output? | 5 | Title. I am really tired of videos. I just want a nice website that walks through things in details with an example. If you have that, I will be really grateful. | 2024-01-30T12:23:21 | https://www.reddit.com/r/LocalLLaMA/comments/1aen6w7/is_there_a_good_nonvideo_guide_on_how_to_write/ | DryArmPits | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 1aen6w7 | false | null | t3_1aen6w7 | /r/LocalLLaMA/comments/1aen6w7/is_there_a_good_nonvideo_guide_on_how_to_write/ | false | false | self | 5 | null |
Goliath Coder 120B? | 4 | Are there any chances of the people who made the original Goliath 120B model (2x LLaMa 70B) making a new merge for the new 70B CodeLLaMa model? | 2024-01-30T12:22:34 | https://www.reddit.com/r/LocalLLaMA/comments/1aen6eo/goliath_coder_120b/ | absouluteUNIT3000 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 1aen6eo | false | null | t3_1aen6eo | /r/LocalLLaMA/comments/1aen6eo/goliath_coder_120b/ | false | false | self | 4 | null |
Actually, Miqu may be AGI | 1 | 2024-01-30T12:08:15 | jacek2023 | i.redd.it | 1970-01-01T00:00:00 | 0 | {} | 1aemxdo | false | null | t3_1aemxdo | /r/LocalLLaMA/comments/1aemxdo/actually_miqu_may_be_agi/ | false | false | 1 | {'enabled': True, 'images': [{'id': 'RbEyKUITaWcaB8wEsjcVhFUTds1sANpPMTdcwbC5-K0', 'resolutions': [{'height': 36, 'url': 'https://preview.redd.it/jy4lm87tikfc1.png?width=108&crop=smart&auto=webp&s=76efb6b8be5080ae227b36c0b2394a307e566ace', 'width': 108}, {'height': 73, 'url': 'https://preview.redd.it/jy4lm87tikfc1.png?... | |||
Local code interpreter | 3 | What alternatives do we have so far to run local models (or via local network) for code inference and prediction, taking into account a local folder (project)? | 2024-01-30T11:53:38 | https://www.reddit.com/r/LocalLLaMA/comments/1aemock/local_code_interpreter/ | vicenterusso | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 1aemock | false | null | t3_1aemock | /r/LocalLLaMA/comments/1aemock/local_code_interpreter/ | false | false | self | 3 | null |
Using CodeLLaMA 70B in production | 10 | What an exciting day! CodeLlama 70B was just launched and we all are trying our hands on it to finally make something useful. Its accuracy is leading us one step closer to finally make something practically useful but the infrastructure challenges are the same as we had with prev models.
It works well in the prototyp... | 2024-01-30T11:50:18 | https://www.reddit.com/r/LocalLLaMA/comments/1aemmh4/using_codellama_70b_in_production/ | opensourcecolumbus | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 1aemmh4 | false | null | t3_1aemmh4 | /r/LocalLLaMA/comments/1aemmh4/using_codellama_70b_in_production/ | false | false | self | 10 | {'enabled': False, 'images': [{'id': 'krjt_5uhqcaDfYjfO7lkezThehav9cAIRJgcK-OKAmM', 'resolutions': [{'height': 56, 'url': 'https://external-preview.redd.it/s0D7i4Rco0trWh9Bu1uEkgnoJJLA3UNKUA9vs57seII.jpg?width=108&crop=smart&auto=webp&s=53486800d92d75b19d59502534fa9ba2785c14b0', 'width': 108}, {'height': 113, 'url': 'h... |
problem in fine tuned llm model | 1 | what can be the problem if the base llm model and fine-tuned llm model are generating the exact same answers? it is as if the model did not fine tune at all.
dataset used in fine tuning - 1000 question - answer pairs | 2024-01-30T11:22:22 | https://www.reddit.com/r/LocalLLaMA/comments/1aem66k/problem_in_fine_tuned_llm_model/ | Proud_Orchid_7140 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 1aem66k | false | null | t3_1aem66k | /r/LocalLLaMA/comments/1aem66k/problem_in_fine_tuned_llm_model/ | false | false | self | 1 | null |
Advice on AMD / Nvidia Linux | 1 | Hi,
I'm considering buying a new GPU for my Linux desktop machine (I'm actually using Fedora KDE).
I'd like a painfree experience but I'd also like to actually use the GPU to test some local AI stuff (I'm not gaming).
From what I understand to have a painfree Linux experience I need an AMD card but to get a painfr... | 2024-01-30T10:41:35 | https://www.reddit.com/r/LocalLLaMA/comments/1aelju2/advice_on_amd_nvidia_linux/ | Larkonath | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 1aelju2 | false | null | t3_1aelju2 | /r/LocalLLaMA/comments/1aelju2/advice_on_amd_nvidia_linux/ | false | false | self | 1 | null |
LFX Mentorship 2024 Spring LLM Projects: Build Open Source AI Inference Infra | 1 | 2024-01-30T10:32:13 | https://www.secondstate.io/articles/lfx-mentorship-spring-2024/ | smileymileycoin | secondstate.io | 1970-01-01T00:00:00 | 0 | {} | 1aeleww | false | null | t3_1aeleww | /r/LocalLLaMA/comments/1aeleww/lfx_mentorship_2024_spring_llm_projects_build/ | false | false | 1 | {'enabled': False, 'images': [{'id': 'E4H84UAzMHuWSoSje7amVhAfl9lZnu-boVqlPBeaNNs', 'resolutions': [{'height': 60, 'url': 'https://external-preview.redd.it/mlz7rlb4ep-e65AHuPWQmDpQvyzD18h2BkZ5_yS7ZLQ.jpg?width=108&crop=smart&auto=webp&s=64c9d285056f61b2a5a3d3314996313fa6757238', 'width': 108}, {'height': 121, 'url': 'h... | ||
News media already using open source models | 1 | I've noticed something over the past 3 months....
I consume a lot of news media and as of late almost every article , regardless of news outlet or news genre, has typos.
I know this is normal. Nobody is always perfect. But the volume and type of typos scream "local language model" to me.
It's like a single word is a... | 2024-01-30T10:24:44 | https://www.reddit.com/r/LocalLLaMA/comments/1aelax5/news_media_already_using_open_source_models/ | 1EvilSexyGenius | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 1aelax5 | false | null | t3_1aelax5 | /r/LocalLLaMA/comments/1aelax5/news_media_already_using_open_source_models/ | false | false | self | 1 | null |
DPO preference data source | 2 | In the DPO paper, the authors stated that it would be better if the reference policy is first SFT-ed on the p(x), before sampling yw and yl for the preference dataset.
As shared by the author [https://github.com/eric-mitchell/direct-preference-optimization/issues/21](https://github.com/eric-mitchell/direct-preference-... | 2024-01-30T10:19:22 | https://www.reddit.com/r/LocalLLaMA/comments/1ael84k/dpo_preference_data_source/ | nohodlnodough | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 1ael84k | false | null | t3_1ael84k | /r/LocalLLaMA/comments/1ael84k/dpo_preference_data_source/ | false | false | self | 2 | {'enabled': False, 'images': [{'id': 'zBFRj17W-hISJ992uisVSoqbyBlQgoNYy9Vc-hLep_k', 'resolutions': [{'height': 54, 'url': 'https://external-preview.redd.it/rGMdbKjkn1rbQJWY-WWqo2beT5WmRW86ttZmHEx_Fj4.jpg?width=108&crop=smart&auto=webp&s=abbef161c7426177cf71486515232891eb6b1805', 'width': 108}, {'height': 108, 'url': 'h... |
Mistral response time on different GPU machine | 1 | How much is the response time and batch size of Mistral Model on different GPU, curious to know about this. I am engaged in deployment of mistral model, just want to know what GPU I can suggest to my customer. | 2024-01-30T10:09:32 | https://www.reddit.com/r/LocalLLaMA/comments/1ael32d/mistral_response_time_on_different_gpu_machine/ | vk001716 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 1ael32d | false | null | t3_1ael32d | /r/LocalLLaMA/comments/1ael32d/mistral_response_time_on_different_gpu_machine/ | false | false | self | 1 | null |
Are there any open source AI tools for writers to avoid writing block? | 7 | I have been writing a visual novel script for almost five years. Part of the manuscript is finished. Is there a tool where I can upload my file and ask it to continue a bit based on the previous text using LLMs ? I heard that mpt-7b-storywriter can write a book, but I don't know any tools to do that >\_< | 2024-01-30T10:06:04 | https://www.reddit.com/r/LocalLLaMA/comments/1ael1ce/are_there_any_open_source_ai_tools_for_writers_to/ | Character_Ad_8188 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 1ael1ce | false | null | t3_1ael1ce | /r/LocalLLaMA/comments/1ael1ce/are_there_any_open_source_ai_tools_for_writers_to/ | false | false | self | 7 | null |
So AMDs new 8000 series APUs are here. How is ROCm and LLM performance? | 16 | Since these new APUs contain more potent on board graphics AND the new NPU... How is performance with inferencing? Who is going to give them a try? | 2024-01-30T10:01:04 | https://www.reddit.com/r/LocalLLaMA/comments/1aekylt/so_amds_new_8000_series_apus_are_here_how_is_rocm/ | CasimirsBlake | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 1aekylt | false | null | t3_1aekylt | /r/LocalLLaMA/comments/1aekylt/so_amds_new_8000_series_apus_are_here_how_is_rocm/ | false | false | self | 16 | null |
Live Webinar: Building Enterprise-grade Proprietary Large Language Models (LLMs) | 1 | [removed] | 2024-01-30T09:48:20 | https://www.reddit.com/r/LocalLLaMA/comments/1aeks66/live_webinar_building_enterprisegrade_proprietary/ | toliverroger | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 1aeks66 | false | null | t3_1aeks66 | /r/LocalLLaMA/comments/1aeks66/live_webinar_building_enterprisegrade_proprietary/ | false | false | 1 | {'enabled': False, 'images': [{'id': 'XTUeGfRgbURtJ8MoQw_x8K2adlviriRyJmk57Vcyy4w', 'resolutions': [{'height': 74, 'url': 'https://external-preview.redd.it/ZkUlGi_g_OTnmxPxjCoehaEJa_WMaYbiBcfv23bmeTk.jpg?width=108&crop=smart&auto=webp&s=e30de7c4a36a13fd1b6c500ff207fce3b57bd888', 'width': 108}, {'height': 148, 'url': 'h... | |
Is there a site that tracks tokens-per-second on different setups and configurations? | 20 | Basically, a site where people can upload their setups, results + evidence, for fun, and so that others can get a rough idea of expected performance? | 2024-01-30T09:41:20 | https://www.reddit.com/r/LocalLLaMA/comments/1aekose/is_there_a_site_that_tracks_tokenspersecond_on/ | shenglong | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 1aekose | false | null | t3_1aekose | /r/LocalLLaMA/comments/1aekose/is_there_a_site_that_tracks_tokenspersecond_on/ | false | false | self | 20 | null |
Finetuned Mixtral 8x7b with Lora and Flash Attention but no Output | 7 | I finetuned Mixtral 8x7b with my private data following this repo [https://github.com/PrakharSaxena24/RepoForLLMs/blob/main/Finetune\_Mixtral\_lora.ipynb](https://github.com/PrakharSaxena24/RepoForLLMs/blob/main/Finetune_Mixtral_lora.ipynb). When I merge my trained adapter with model. The model do not generate any outp... | 2024-01-30T09:27:39 | https://www.reddit.com/r/LocalLLaMA/comments/1aeki5i/finetuned_mixtral_8x7b_with_lora_and_flash/ | Dizzy_Spite1876 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 1aeki5i | false | null | t3_1aeki5i | /r/LocalLLaMA/comments/1aeki5i/finetuned_mixtral_8x7b_with_lora_and_flash/ | false | false | self | 7 | {'enabled': False, 'images': [{'id': 'A6BNdU4ebxw9EwdpC534N0Ifq6b_mihCAf0jxSIpqDA', 'resolutions': [{'height': 54, 'url': 'https://external-preview.redd.it/Ce1AjWTH2BQTVxRjaxlbtaKCKIrdXxzxeF5rFZX5XX0.jpg?width=108&crop=smart&auto=webp&s=b2f056ec88f3fcb6f1354d22b83818cc3d015696', 'width': 108}, {'height': 108, 'url': 'h... |
loading mistral 7b instruct | 1 | any idea on how to load mistral 7b model in langchain , without the transformer pipeline
ps - i m not loading quantised model | 2024-01-30T09:17:46 | https://www.reddit.com/r/LocalLLaMA/comments/1aekd52/loading_mistral_7b_instruct/ | happy_dreamer10 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 1aekd52 | false | null | t3_1aekd52 | /r/LocalLLaMA/comments/1aekd52/loading_mistral_7b_instruct/ | false | false | self | 1 | null |
Internlm2 20B 3.04bpw at 1 t/s on Pixel 6 Pro! | 12 | 2024-01-30T08:52:46 | https://asciinema.org/a/WrhFvuBjdOiNXHvpSujSRcXUq | Aaaaaaaaaeeeee | asciinema.org | 1970-01-01T00:00:00 | 0 | {} | 1aek0g2 | false | null | t3_1aek0g2 | /r/LocalLLaMA/comments/1aek0g2/internlm2_20b_304bpw_at_1_ts_on_pixel_6_pro/ | false | false | 12 | {'enabled': False, 'images': [{'id': 'qn1KUwgZzibiJTZr52p3ecXxUTfN-07pukWSN0UQOZw', 'resolutions': [{'height': 136, 'url': 'https://external-preview.redd.it/uplo-UgB2TZXCpC_pDXZ-JTNDitwN-8w5wyR9BlaYQo.jpg?width=108&crop=smart&auto=webp&s=f97730f10bfe733e70d2916f4a6bc3f766ac8bf5', 'width': 108}, {'height': 273, 'url': '... | ||
If this is true it is over: Unlimited context length is here. | 264 | 2024-01-30T08:29:33 | https://twitter.com/Yampeleg/status/1751942400287666536 | Valuable-Project4855 | twitter.com | 1970-01-01T00:00:00 | 0 | {} | 1aejoib | false | {'oembed': {'author_name': 'Yam Peleg', 'author_url': 'https://twitter.com/Yampeleg', 'cache_age': 3153600000, 'height': None, 'html': '<blockquote class="twitter-video"><p lang="en" dir="ltr">If this is true it is over: Unlimited context length is here.<br><br>Activation Beacon,<br>New method for extending LLMs contex... | t3_1aejoib | /r/LocalLLaMA/comments/1aejoib/if_this_is_true_it_is_over_unlimited_context/ | false | false | 264 | {'enabled': False, 'images': [{'id': 'G3F_W_dhPwt0e9epNbIehTow_LKmLSaYZIBCNeaBf0g', 'resolutions': [{'height': 44, 'url': 'https://external-preview.redd.it/wCVENPBSc9oG2GsFydMbqyFH_gZ31AFjOvTWSnJZBjY.jpg?width=108&crop=smart&auto=webp&s=8153947028419415a841dd2f68826abb54e09824', 'width': 108}], 'source': {'height': 58,... | ||
Most accurate LLM’s (and settings for RAG/ superboogav2/ chat with doc programs? | 1 | [removed] | 2024-01-30T08:26:02 | https://www.reddit.com/r/LocalLLaMA/comments/1aejmso/most_accurate_llms_and_settings_for_rag/ | headbopper96 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 1aejmso | false | null | t3_1aejmso | /r/LocalLLaMA/comments/1aejmso/most_accurate_llms_and_settings_for_rag/ | false | false | self | 1 | null |
LLama 3. | 4 | Just heard from someone working on LLama 3. Multimodal training has just begun. | 2024-01-30T08:24:37 | https://www.reddit.com/r/LocalLLaMA/comments/1aejm20/llama_3/ | No-Point1424 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 1aejm20 | false | null | t3_1aejm20 | /r/LocalLLaMA/comments/1aejm20/llama_3/ | false | false | self | 4 | null |
Mistral office hour: Ask them anything | 37 | Takes place on their Disc. server on Thursday feb 1st, 5 PM Paris time. This is the second edition. | 2024-01-30T08:20:40 | No_Palpitation7740 | i.redd.it | 1970-01-01T00:00:00 | 0 | {} | 1aejk3q | false | null | t3_1aejk3q | /r/LocalLLaMA/comments/1aejk3q/mistral_office_hour_ask_them_anything/ | false | false | 37 | {'enabled': True, 'images': [{'id': '6pwJ7Or3MubC4LU_Neii1cmCGFwgIlfl5ChdmtCBhwQ', 'resolutions': [{'height': 108, 'url': 'https://preview.redd.it/5pjbbp0gejfc1.png?width=108&crop=smart&auto=webp&s=7f7a3ee9c0ea5c24f96fa34ef7c3d72bfca1d3a8', 'width': 108}, {'height': 216, 'url': 'https://preview.redd.it/5pjbbp0gejfc1.pn... | ||
Can Llama-cpp-python caches be saved to disk and later reloaded during inference? | 5 | Is it possible to preprocess a set of prompts, save them to disk, and then reload them during inference to avoid the need to regenerate cached prompts every time? For instance, if I have a 2000-token prompt that I use daily in a memory-intensive Python program, is there a way to pre-process and save it to avoid the del... | 2024-01-30T08:12:01 | https://www.reddit.com/r/LocalLLaMA/comments/1aejfpb/can_llamacpppython_caches_be_saved_to_disk_and/ | CommitteeHairy6435 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 1aejfpb | false | null | t3_1aejfpb | /r/LocalLLaMA/comments/1aejfpb/can_llamacpppython_caches_be_saved_to_disk_and/ | false | false | self | 5 | null |
Looks like Qwen 2 is being integrated into HF and vLLM from launch so should be released soon. Does anyone know the timeframe? | 1 | 2024-01-30T08:09:28 | https://huggingface.co/docs/transformers/model_doc/qwen2 | Peter_Lightblue | huggingface.co | 1970-01-01T00:00:00 | 0 | {} | 1aejefn | false | null | t3_1aejefn | /r/LocalLLaMA/comments/1aejefn/looks_like_qwen_2_is_being_integrated_into_hf_and/ | false | false | 1 | {'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... | ||
Me, after new Code Llama just dropped... | 531 | 2024-01-30T07:34:26 | jslominski | i.redd.it | 1970-01-01T00:00:00 | 0 | {} | 1aeiwj0 | false | null | t3_1aeiwj0 | /r/LocalLLaMA/comments/1aeiwj0/me_after_new_code_llama_just_dropped/ | false | false | 531 | {'enabled': True, 'images': [{'id': 'U5U55m5NoXjF0rsVGUmeogvu_bxIanyw4pK3aPdpauY', 'resolutions': [{'height': 158, 'url': 'https://preview.redd.it/wbux7rdk5jfc1.jpeg?width=108&crop=smart&auto=webp&s=7db894791214fb49b1b2ce6fb07a9929ab185636', 'width': 108}, {'height': 317, 'url': 'https://preview.redd.it/wbux7rdk5jfc1.j... | |||
GPT Vision (llava) Python module assistance, Google Vision alternative. | 3 | Hi all,
So I’ve been using Google Vision to do OCR and extract txt from images and renames the file to what it sees. So far it’s been better than OpenCV etc and many other Python modules out there, however since Google vision I think works on top of AutoML I am wondering if anyone is aware of a more private approach l... | 2024-01-30T07:20:50 | https://www.reddit.com/r/LocalLLaMA/comments/1aeip2r/gpt_vision_llava_python_module_assistance_google/ | ihaag | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 1aeip2r | false | null | t3_1aeip2r | /r/LocalLLaMA/comments/1aeip2r/gpt_vision_llava_python_module_assistance_google/ | false | false | self | 3 | null |
⏳ Worked on a time-bound fine-tuning mini-project over the weekend and it was annoyingly fun! | 9 | 🏗️ **Task at hand**
Fine-tune a CodeLlama model from Hugging Face Hub while incorporating the [Flash Attention](https://github.com/Dao-AILab/flash-attention) technique and digging deeper into fundamentals of GPU architecture as much as possible.
💸 **Constraints**
Do not use GPU instances from one of the big 3 ... | 2024-01-30T07:12:20 | https://www.reddit.com/r/LocalLLaMA/comments/1aeikix/worked_on_a_timebound_finetuning_miniproject_over/ | analyticalmonk | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 1aeikix | false | null | t3_1aeikix | /r/LocalLLaMA/comments/1aeikix/worked_on_a_timebound_finetuning_miniproject_over/ | false | false | self | 9 | {'enabled': False, 'images': [{'id': 'wr8FIUP9vW6uFAH00pFY_INaPBOAwt-Dx66NR8JN9U4', 'resolutions': [{'height': 54, 'url': 'https://external-preview.redd.it/Exyy_D339_5mo3t200rsljBHMp2oozK-gX7lYduR9_0.jpg?width=108&crop=smart&auto=webp&s=93f0cb8ec2d44c6526bf48faf3a25ec85611ba63', 'width': 108}, {'height': 108, 'url': 'h... |
Is it theoretically possible to use llm for witty replies in comments from unfriendly people? | 2 | but not like: your answer is unethical and may offend someone bla bla bla . I need a bot that would answer wittier than a human. maybe we need an uncensored model? | 2024-01-30T07:10:47 | https://www.reddit.com/r/LocalLLaMA/comments/1aeijpb/is_it_theoretically_possible_to_use_llm_for_witty/ | professor-studio | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 1aeijpb | false | null | t3_1aeijpb | /r/LocalLLaMA/comments/1aeijpb/is_it_theoretically_possible_to_use_llm_for_witty/ | false | false | self | 2 | null |
Any way to run Goliath 120b on 24GB VRAM? | 1 | [removed] | 2024-01-30T07:00:27 | https://www.reddit.com/r/LocalLLaMA/comments/1aeieah/any_way_to_run_goliath_120b_on_24gb_vram/ | yupignome | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 1aeieah | false | null | t3_1aeieah | /r/LocalLLaMA/comments/1aeieah/any_way_to_run_goliath_120b_on_24gb_vram/ | false | false | self | 1 | null |
Creating a teams chatbot with a local LLM? | 5 | as the title says, does anyone know how one can do this? Or can give me pointers for directions? | 2024-01-30T06:43:04 | https://www.reddit.com/r/LocalLLaMA/comments/1aei4wb/creating_a_teams_chatbot_with_a_local_llm/ | Ornery_Meat1055 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 1aei4wb | false | null | t3_1aei4wb | /r/LocalLLaMA/comments/1aei4wb/creating_a_teams_chatbot_with_a_local_llm/ | false | false | self | 5 | null |
out of memory issue while inferencing | 1 | hi all,
been stuck on an issue .
I have mistral 7b on local and using the same for inferencing over a list of tables.
have a A100 80gb gpu .
i am using pipeline wrapper from hugging face for text generation and using it for predictions.
while looping over i have been getting Cuda out of memory after 30 iterations.
h... | 2024-01-30T06:26:35 | https://www.reddit.com/r/LocalLLaMA/comments/1aehvhl/out_of_memory_issue_while_inferencing/ | happy_dreamer10 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 1aehvhl | false | null | t3_1aehvhl | /r/LocalLLaMA/comments/1aehvhl/out_of_memory_issue_while_inferencing/ | false | false | self | 1 | null |
ELI5 What's the difference between a Chat LLM and an Instruct LLM? | 11 | I can't, for example, enter the Together playground and use the new code llama 70 because I don't know how to ask it to do something for me.
It's probably because I don't know the difference between chat and instruct, please explain it to me. | 2024-01-30T05:30:12 | https://www.reddit.com/r/LocalLLaMA/comments/1aegy3v/eli5_whats_the_difference_between_a_chat_llm_and/ | cvjcvj2 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 1aegy3v | false | null | t3_1aegy3v | /r/LocalLLaMA/comments/1aegy3v/eli5_whats_the_difference_between_a_chat_llm_and/ | false | false | self | 11 | null |
Azure VM for Llama 2 70b | 1 | Anyone using Azure and deployed LLama 2 70B? I'm trying to come up with a solution. What was your token/second throughput? | 2024-01-30T05:14:20 | https://www.reddit.com/r/LocalLLaMA/comments/1aegobf/azure_vm_for_llama_2_70b/ | xyz_TrashMan_zyx | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 1aegobf | false | null | t3_1aegobf | /r/LocalLLaMA/comments/1aegobf/azure_vm_for_llama_2_70b/ | false | false | self | 1 | null |
Upgrading GTX 1060 6GB to RTX 3070 Ti 8GB is good enough for 13B models? | 4 | Right now I have GTX 1060 6GB with 5900X CPU + 64GB memory for 7B models only. My son is throwing away his 3070 Ti 8GB for upgrade. Considering small memory upgrade of 6GB vs 8GB, will it be worth to get it? If it won't make big improvement, he will sell it to gamer instead of throwing it to me :-) | 2024-01-30T04:27:28 | https://www.reddit.com/r/LocalLLaMA/comments/1aeftyu/upgrading_gtx_1060_6gb_to_rtx_3070_ti_8gb_is_good/ | user0user | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 1aeftyu | false | null | t3_1aeftyu | /r/LocalLLaMA/comments/1aeftyu/upgrading_gtx_1060_6gb_to_rtx_3070_ti_8gb_is_good/ | false | false | self | 4 | null |
TransformerTransformer Math 101 | 1 | [https://blog.eleuther.ai/transformer-math/](https://blog.eleuther.ai/transformer-math/)
Very useful baseline for thinking about LLM. | 2024-01-30T04:06:46 | https://www.reddit.com/r/LocalLLaMA/comments/1aefgb3/transformertransformer_math_101/ | lukaemon | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 1aefgb3 | false | null | t3_1aefgb3 | /r/LocalLLaMA/comments/1aefgb3/transformertransformer_math_101/ | false | false | self | 1 | {'enabled': False, 'images': [{'id': '7Ut-EDXSqI4_e9ERFOmS1DuQvIFP6EumkXTvsa_T9ps', 'resolutions': [{'height': 108, 'url': 'https://external-preview.redd.it/axS_7OiIPetA15ERwsj56US38YN3udvQbRWWL11-P1s.jpg?width=108&crop=smart&auto=webp&s=e31ac4f273c36c67de4210a2c06e328da13bcb74', 'width': 108}, {'height': 216, 'url': '... |
Install Ollama under Win11 & WSL - CUDA Installation guide | 5 | I had issues when I was trying installing Ollama under Win11 WSL. In short:
- truncated libcudnn
- conflicting Libraries
- CUDA sample directory was not foud
Anyways, all issues were CUDA related, so I made short guide for installing CUDA under wsl.
After properly installing CUDA, I didn't have any issues with... | 2024-01-30T04:03:37 | https://www.reddit.com/r/LocalLLaMA/comments/1aefeb5/install_ollama_under_win11_wsl_cuda_installation/ | dodo13333 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 1aefeb5 | false | null | t3_1aefeb5 | /r/LocalLLaMA/comments/1aefeb5/install_ollama_under_win11_wsl_cuda_installation/ | false | false | self | 5 | {'enabled': False, 'images': [{'id': 'OAXSl8SY6T3JK9MGQyKxkoYbqZ71HQRYXLeB8CV0NXg', 'resolutions': [{'height': 54, 'url': 'https://external-preview.redd.it/DaucjXMGsNHM-CtmdilC9-Be6MC8V2z4ykjVCgOkTFc.jpg?width=108&crop=smart&auto=webp&s=9bcab7b79864ff27bf48116cb335a6f825bfb124', 'width': 108}, {'height': 108, 'url': 'h... |
"miqu" Solving The Greatest Problems in Open-Source LLM History | 144 | Jokes aside, this definitely isn't a weird merge or fluke. This really could be the Mistral Medium leak. It is smarter than GPT-3.5 for sure. Q4 is way too slow for a single rtx 3090 though. | 2024-01-30T03:05:08 | xadiant | i.redd.it | 1970-01-01T00:00:00 | 0 | {} | 1aee8m5 | false | null | t3_1aee8m5 | /r/LocalLLaMA/comments/1aee8m5/miqu_solving_the_greatest_problems_in_opensource/ | false | false | 144 | {'enabled': True, 'images': [{'id': 'z1WejsawOtxFLVbrKaE2HMo8Y68uE-D6KlAa2wf6ZVQ', 'resolutions': [{'height': 82, 'url': 'https://preview.redd.it/qv9lybb5uhfc1.png?width=108&crop=smart&auto=webp&s=3215f33fef49ba47064e9cf139757a54127c4a50', 'width': 108}, {'height': 165, 'url': 'https://preview.redd.it/qv9lybb5uhfc1.png... | ||
LiesLLM: I found out that Perplexity's PPLX-"online" model is not actually online. They cache/index the internet and feed to the LLM, so the LLM doesn't actually have browsing/internet-access. | 3 | I used their API (through openrouter) to ask a simple question: `What is on news.ycombinator.com today?`
This is my CURL command:
curl https://openrouter.ai/api/v1/chat/completions \ (writersUnblock) 21:05:21
-H "Content-Type: application/json" \
-... | 2024-01-30T02:13:44 | https://www.reddit.com/r/LocalLLaMA/comments/1aed670/liesllm_i_found_out_that_perplexitys_pplxonline/ | nderstand2grow | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 1aed670 | false | null | t3_1aed670 | /r/LocalLLaMA/comments/1aed670/liesllm_i_found_out_that_perplexitys_pplxonline/ | false | false | 3 | null | |
I just downloaded codellama-70b-instruct, I want to run it on localLLama, what am I supposed to do with these consolidated.0*.pth files? | 2 | I just downloaded codellama-70b-instruct. I want to run it on LM Studio. when the download has finished it am left with a folder like this
[Files after download has completed](https://preview.redd.it/j04592iwghfc1.jpg?width=535&format=pjpg&auto=webp&s=2cacf0347c964423cb1dac8657dba198e213024f)
What am I supposed to d... | 2024-01-30T01:53:24 | https://www.reddit.com/r/LocalLLaMA/comments/1aecqr9/i_just_downloaded_codellama70binstruct_i_want_to/ | arraytrix | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 1aecqr9 | false | null | t3_1aecqr9 | /r/LocalLLaMA/comments/1aecqr9/i_just_downloaded_codellama70binstruct_i_want_to/ | false | false | 2 | null | |
The Poetroid Camera | 309 | Idk where to post this exactly but this sub helped the most so I'm posting it here and maybe soke here will appreciate. This is the poetroid camera. It takes and prints poems on a thermal receipt printer. The dial allows you to set it to different poets (shown on lcd on the back). It runs locally using ollama with the ... | 2024-01-30T01:39:03 | https://www.reddit.com/gallery/1aecfu1 | gthing | reddit.com | 1970-01-01T00:00:00 | 0 | {} | 1aecfu1 | false | null | t3_1aecfu1 | /r/LocalLLaMA/comments/1aecfu1/the_poetroid_camera/ | false | false | 309 | null | |
LLM Developer Contest: NVIDIA GenAI on RTX for Windows PCs. | 42 | I'm part of the the developer team at NVIDIA. We have noticed that there has been an awesome influx of LLM Windows development on RTX GPUs, and we want to reward some of the best.
If you have an idea for a generative AI project - running locally on Windows PC - enter our [#GenAI on RTX PCs developer contest](https://w... | 2024-01-30T01:31:34 | https://www.reddit.com/r/LocalLLaMA/comments/1aeca9q/llm_developer_contest_nvidia_genai_on_rtx_for/ | PDXcoder2000 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 1aeca9q | false | null | t3_1aeca9q | /r/LocalLLaMA/comments/1aeca9q/llm_developer_contest_nvidia_genai_on_rtx_for/ | false | false | 42 | {'enabled': False, 'images': [{'id': 'Vx-JpjCmSX6ISu-7M1TXmyvfw99joz8RMQfamizoLAw', 'resolutions': [{'height': 56, 'url': 'https://external-preview.redd.it/6PxNlVj1k9BLyXPwukfWEquneKlKht-9rPFa132IPs8.jpg?width=108&crop=smart&auto=webp&s=48dbde024b96774fc0d4b514722691dd8f0c9788', 'width': 108}, {'height': 113, 'url': 'h... | |
CringeBot - imbue the essence of the child you were in 2002 into an LLM! | 1 | [removed] | 2024-01-30T01:02:27 | https://www.reddit.com/r/LocalLLaMA/comments/1aebnrv/cringebot_imbue_the_essence_of_the_child_you_were/ | hotspoons_ | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 1aebnrv | false | null | t3_1aebnrv | /r/LocalLLaMA/comments/1aebnrv/cringebot_imbue_the_essence_of_the_child_you_were/ | false | false | self | 1 | {'enabled': False, 'images': [{'id': '532wVwhlDOr-xMBOubtfzwN5z2Qcc8UHXUlYxSUyKq8', 'resolutions': [{'height': 71, 'url': 'https://external-preview.redd.it/MRiGIET0RTrCT6Ds69uUpoEUHiuJravTcrZ5VZRT4QM.jpg?width=108&crop=smart&auto=webp&s=6ac53ffdcb5c0d2c78805642aa59666e75d2ba92', 'width': 108}, {'height': 143, 'url': 'h... |
Cheapest possible rig for 70b? | 1 | I wanted to know the cheapest way to run 70b at 2-3 t/s. I was considering a server with p40s, but I saw that a k80 would be much cheaper for the vram and was wondering what inference speeds you get with a k80. | 2024-01-30T00:57:28 | https://www.reddit.com/r/LocalLLaMA/comments/1aebjtz/cheapest_possible_rig_for_70b/ | oof-baroomf | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 1aebjtz | false | null | t3_1aebjtz | /r/LocalLLaMA/comments/1aebjtz/cheapest_possible_rig_for_70b/ | false | false | self | 1 | null |
Meta - Other than RP what are you folks doing? | 18 | Guess I'm looking for an excuse to spend money on hardware. There was a thread with the same question two months ago and I can't imagine the answers are still the same? | 2024-01-30T00:20:20 | https://www.reddit.com/r/LocalLLaMA/comments/1aearox/meta_other_than_rp_what_are_you_folks_doing/ | cleuseau | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 1aearox | false | null | t3_1aearox | /r/LocalLLaMA/comments/1aearox/meta_other_than_rp_what_are_you_folks_doing/ | false | false | self | 18 | null |
Enchanted - Ollama iOS app for self hosted models | 21 | 2024-01-30T00:01:40 | https://v.redd.it/1qmmk6f1xgfc1 | 1amrocket | /r/LocalLLaMA/comments/1aead1h/enchanted_ollama_ios_app_for_self_hosted_models/ | 1970-01-01T00:00:00 | 0 | {} | 1aead1h | false | {'reddit_video': {'bitrate_kbps': 5000, 'dash_url': 'https://v.redd.it/1qmmk6f1xgfc1/DASHPlaylist.mpd?a=1709294509%2CMzg2NmJjN2JjMDcwZjFhYThiNmVmMDQ4MDgzZDAyNjQyYzQxZGQ5YTc5ZGMyZTc4MTNjNmM5ODI0ZjM2Y2E2ZA%3D%3D&v=1&f=sd', 'duration': 54, 'fallback_url': 'https://v.redd.it/1qmmk6f1xgfc1/DASH_1080.mp4?source=fallback', 'h... | t3_1aead1h | /r/LocalLLaMA/comments/1aead1h/enchanted_ollama_ios_app_for_self_hosted_models/ | false | false | 21 | {'enabled': False, 'images': [{'id': 'dnNzdXpnemV4Z2ZjMeQI7Xd-Yk0Lrv8xS7uFtjh3-C8SOpwW9XzzmdgN6Mno', 'resolutions': [{'height': 60, 'url': 'https://external-preview.redd.it/dnNzdXpnemV4Z2ZjMeQI7Xd-Yk0Lrv8xS7uFtjh3-C8SOpwW9XzzmdgN6Mno.png?width=108&crop=smart&format=pjpg&auto=webp&s=ecd70a352b17dcae619b1767a94103297ed06... | ||
What is considered the best uncensored LLM right now? | 1 | Looking for any model that I can run with 12gb of vram and or 32gb or RAM. | 2024-01-29T23:24:58 | https://www.reddit.com/r/LocalLLaMA/comments/1ae9j54/what_is_considered_the_best_uncensored_llm_right/ | Acarvi | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 1ae9j54 | false | null | t3_1ae9j54 | /r/LocalLLaMA/comments/1ae9j54/what_is_considered_the_best_uncensored_llm_right/ | false | false | self | 1 | null |
Optimizing ollama for Mixtral 8X7B on MacBook Pro M1 Pro | 1 | Hello /r/LocalLLaMA
I am looking for some guidance on how to best configure ollama to run Mixtral 8X7B on my Macbook Pro M1 Pro 32GB. I am able to run dolphin-2.5-mixtral-8x7b.Q4\_K\_M in LM Studio with the model loaded into memory if I increase the wired memory limit on my Macbook to 30GB. However, when I try use mix... | 2024-01-29T23:20:28 | https://www.reddit.com/r/LocalLLaMA/comments/1ae9fju/optimizing_ollama_for_mixtral_8x7b_on_macbook_pro/ | Living_Tone3782 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 1ae9fju | false | null | t3_1ae9fju | /r/LocalLLaMA/comments/1ae9fju/optimizing_ollama_for_mixtral_8x7b_on_macbook_pro/ | false | false | self | 1 | null |
Any reason why Ollama doesn't have the Whisper model? | 2 | Would love to have one unified interface for local models, and Ollama seems to have everything I need except Whisper. Now I can run it separately, but then I need to have a seperate API, etc. - Is there any reason or limitation for not having Whisper in Ollama? | 2024-01-29T23:04:21 | https://www.reddit.com/r/LocalLLaMA/comments/1ae92e6/any_reason_why_ollama_doesnt_have_the_whisper/ | No-Camel-3819 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 1ae92e6 | false | null | t3_1ae92e6 | /r/LocalLLaMA/comments/1ae92e6/any_reason_why_ollama_doesnt_have_the_whisper/ | false | false | self | 2 | null |
chatglm3-6b-32k | 11 | I've got a question about THUDM/chatglm3-6b-32k ([link](https://huggingface.co/THUDM/chatglm3-6b-32k)), which I first enountered in a model review by u/ramprasad27 in a post [here.](https://www.reddit.com/r/LocalLLaMA/comments/18s61fb/pressuretested_the_most_popular_opensource_llms/) The reviewer suggested it has one ... | 2024-01-29T22:07:50 | https://www.reddit.com/r/LocalLLaMA/comments/1ae7pu1/chatglm36b32k/ | Hinged31 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 1ae7pu1 | false | null | t3_1ae7pu1 | /r/LocalLLaMA/comments/1ae7pu1/chatglm36b32k/ | false | false | self | 11 | {'enabled': False, 'images': [{'id': 'L8GySIppqoYnMje-5KjDv9To7U7iUMM58uwJM_aZhR8', 'resolutions': [{'height': 58, 'url': 'https://external-preview.redd.it/jaZgTd4wptnwaXzv4f_41lQ_i68E5n13slIWkC7FblE.jpg?width=108&crop=smart&auto=webp&s=2eb1ca221e9b8e26e41557c9ddf99ec287a1f5cf', 'width': 108}, {'height': 116, 'url': 'h... |
Can I run Mixtral 8 x 7b locally on a maxed out Mac Studio? | 2 | I know Mixtral 8 X 7b is a pretty big model. Is a maxed out Mac Studio powerful enough to run it locally? | 2024-01-29T22:05:56 | https://www.reddit.com/r/LocalLLaMA/comments/1ae7o58/can_i_run_mixtral_8_x_7b_locally_on_a_maxed_out/ | M3629 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 1ae7o58 | false | null | t3_1ae7o58 | /r/LocalLLaMA/comments/1ae7o58/can_i_run_mixtral_8_x_7b_locally_on_a_maxed_out/ | false | false | self | 2 | null |
What is the best way to learn the fundamentals of LLMs as a software engineer? | 1 | [removed] | 2024-01-29T21:59:11 | https://www.reddit.com/r/LocalLLaMA/comments/1ae7i0e/what_is_the_best_way_to_learn_the_fundamentals_of/ | lightdreamscape | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 1ae7i0e | false | null | t3_1ae7i0e | /r/LocalLLaMA/comments/1ae7i0e/what_is_the_best_way_to_learn_the_fundamentals_of/ | false | false | self | 1 | {'enabled': False, 'images': [{'id': '-_6t2RVCfsHr3NWG0MrnoyFXnKNDoM0GkIEMMUKe5TA', 'resolutions': [{'height': 53, 'url': 'https://external-preview.redd.it/Xr6THSH83Pz8pUTGNOixQ9UMulEahngSYpAyqPfaVKE.jpg?width=108&crop=smart&auto=webp&s=110362bbc93d667246ceae163c4dd858ecf7c874', 'width': 108}, {'height': 107, 'url': 'h... |
Mixture of Experts LLaVA Demo | 35 | >With only 3 billion selectively activated parameters, MoE-LLaVA performs similarly to LLaVA1.5-7B on visual understanding datasets and outperforms LLaVA1.5-13B in object hallucination benchmarks. | 2024-01-29T21:55:49 | https://huggingface.co/spaces/LanguageBind/MoE-LLaVA | ninjasaid13 | huggingface.co | 1970-01-01T00:00:00 | 0 | {} | 1ae7f5i | false | null | t3_1ae7f5i | /r/LocalLLaMA/comments/1ae7f5i/mixture_of_experts_llava_demo/ | false | false | 35 | {'enabled': False, 'images': [{'id': 'XEwPceY_kLcvTbUq0yLFtIWfP7YDlP5fqY3i2pxv3Rc', 'resolutions': [{'height': 58, 'url': 'https://external-preview.redd.it/8IxR3DUtWRar7TyjjzmIo7PEZNVXXXI_vSARVqnTdAY.jpg?width=108&crop=smart&auto=webp&s=d0893830485fabe98d1539f54bfa475779416d07', 'width': 108}, {'height': 116, 'url': 'h... | |
Where are we now? | 145 | 2024-01-29T21:40:14 | Wrong_User_Logged | i.redd.it | 1970-01-01T00:00:00 | 0 | {} | 1ae71r0 | false | null | t3_1ae71r0 | /r/LocalLLaMA/comments/1ae71r0/where_are_we_now/ | false | false | 145 | {'enabled': True, 'images': [{'id': 'QUIr7aOOLgEokSKvtQREo9pc_20BlCYjwbRLsWgzpTY', 'resolutions': [{'height': 71, 'url': 'https://preview.redd.it/eaa4s1d58gfc1.png?width=108&crop=smart&auto=webp&s=927732efc1b3d12b3d21909f266be8d96e8c295a', 'width': 108}, {'height': 143, 'url': 'https://preview.redd.it/eaa4s1d58gfc1.png... | |||
Is AI overhyped? | 1 | [deleted] | 2024-01-29T21:39:17 | Wrong_User_Logged | i.redd.it | 1970-01-01T00:00:00 | 0 | {} | 1ae70we | false | null | t3_1ae70we | /r/LocalLLaMA/comments/1ae70we/is_ai_overhyped/ | false | false | 1 | {'enabled': True, 'images': [{'id': 'cQzos8UTjcKQJvCWo2MJ8QX7YxKPu7GR13BLJ0M-LRw', 'resolutions': [{'height': 71, 'url': 'https://preview.redd.it/llj6fgnz7gfc1.png?width=108&crop=smart&auto=webp&s=882015d5f61949505ff3cdeb6433861fe73cbebd', 'width': 108}, {'height': 143, 'url': 'https://preview.redd.it/llj6fgnz7gfc1.png... | ||
Does anyone happen to still have CarbonVillain 13B? 🤔 | 11 | Does anyone still have a copy of CarbonVillain 13B? I've looked and looked before posting here but I can't find it anywhere. It's been deleted and seemingly entirely replaced with the 10.7B version, but I specifically want the 13B version that used to be found here: [https://huggingface.co/jeonsworld/CarbonVillain-13B-... | 2024-01-29T21:31:35 | https://www.reddit.com/r/LocalLLaMA/comments/1ae6twn/does_anyone_happen_to_still_have_carbonvillain_13b/ | Uncle_Warlock | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 1ae6twn | false | null | t3_1ae6twn | /r/LocalLLaMA/comments/1ae6twn/does_anyone_happen_to_still_have_carbonvillain_13b/ | false | false | self | 11 | null |
Extending Context 100x w/ Activation Beacon | 1 | [removed] | 2024-01-29T21:05:45 | https://arxiv.org/pdf/2401.03462.pdf | LoadingALIAS | arxiv.org | 1970-01-01T00:00:00 | 0 | {} | 1ae67av | false | null | t3_1ae67av | /r/LocalLLaMA/comments/1ae67av/extending_context_100x_w_activation_beacon/ | false | false | default | 1 | null |
AI vs Humans: The Countdown Begins! 🤖🏁 | 2 |
Just stumbled upon this fascinating leaderboard over at [Hugging Face](https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard) (screenshot attached), and guess what? AI is hot on our heels! 😲
Looking at the progress, my back-of-the-napkin calculation says AIs might outpace us humans around May 2024. That... | 2024-01-29T21:05:32 | https://www.reddit.com/r/LocalLLaMA/comments/1ae673l/ai_vs_humans_the_countdown_begins/ | fanff | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 1ae673l | false | null | t3_1ae673l | /r/LocalLLaMA/comments/1ae673l/ai_vs_humans_the_countdown_begins/ | false | false | self | 2 | {'enabled': False, 'images': [{'id': 'tjJ87qKJWLzmj-5WYTPdt0F_x4nG05KYznkxHl11ljc', 'resolutions': [{'height': 58, 'url': 'https://external-preview.redd.it/dEYg7tYorcKKjwTqLhf9IZA_JuhsDh-r7DtkAObAWCg.jpg?width=108&crop=smart&auto=webp&s=05aecc1a2ea320ce14e6f61f1cf8105636f82f58', 'width': 108}, {'height': 116, 'url': 'h... |
XEON E3-1225 @3.30Ghz strong enough for 70B Llama GGUF? | 4 | Hello - have a Dell T30 Server and interested in loading it up with 64GB RAM and playing around with local LLMs, not so much training. Is this powerful enough? | 2024-01-29T20:48:17 | https://www.reddit.com/r/LocalLLaMA/comments/1ae5s10/xeon_e31225_330ghz_strong_enough_for_70b_llama/ | GardenGreens12 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 1ae5s10 | false | null | t3_1ae5s10 | /r/LocalLLaMA/comments/1ae5s10/xeon_e31225_330ghz_strong_enough_for_70b_llama/ | false | false | self | 4 | null |
RAG for documents with chapters and sub-chapters | 1 | [removed] | 2024-01-29T20:14:29 | https://www.reddit.com/r/LocalLLaMA/comments/1ae4ym2/rag_for_documents_with_chapters_and_subchapters/ | Electronic-Letter592 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 1ae4ym2 | false | null | t3_1ae4ym2 | /r/LocalLLaMA/comments/1ae4ym2/rag_for_documents_with_chapters_and_subchapters/ | false | false | self | 1 | null |
LLM GPU buyer beware? | 5 | I’m in the process of researching to upgrade my workstation to run LLMs, and noticed two attractive but seemingly terrible recent entries into the market.
The RTX 4060 TI as well as the RX 7600 XT are eye catching as being lower end consumer GPU products with higher VRAM than we normally see (16 GB)
However without ... | 2024-01-29T20:06:00 | https://www.reddit.com/r/LocalLLaMA/comments/1ae4r1e/llm_gpu_buyer_beware/ | coaststl | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 1ae4r1e | false | null | t3_1ae4r1e | /r/LocalLLaMA/comments/1ae4r1e/llm_gpu_buyer_beware/ | false | false | self | 5 | null |
Thoughts on AMD Strix Halo Chip | 5 | I recently read to the discussion breaking down how most Apple unified memory architecture is pretty compelling for local models cause it's architecture makes it fall in sweet spot for running the scale of LLM's here, but it reminded me that AMD is planning to launch a proper competitor to the Apple Max series chips to... | 2024-01-29T20:03:05 | https://www.reddit.com/r/LocalLLaMA/comments/1ae4ohz/thoughts_on_amd_strix_halo_chip/ | PMARC14 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 1ae4ohz | false | null | t3_1ae4ohz | /r/LocalLLaMA/comments/1ae4ohz/thoughts_on_amd_strix_halo_chip/ | false | false | self | 5 | null |
Msty: Offline first, privacy focused companion for parallel chat with Local and Online Models ✨ | 3 | I've created an app called Msty that lets you chat with local models (powered by Ollama) and online models like OpenAI GPTs and Mistral concurrently. What makes it special is its user-friendly approach, designed for all levels of expertise - no need to understand LLM technicalities if you don't want to!
This is curren... | 2024-01-29T20:01:42 | https://www.reddit.com/r/LocalLLaMA/comments/1ae4n7o/msty_offline_first_privacy_focused_companion_for/ | askgl | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 1ae4n7o | false | null | t3_1ae4n7o | /r/LocalLLaMA/comments/1ae4n7o/msty_offline_first_privacy_focused_companion_for/ | false | false | self | 3 | {'enabled': False, 'images': [{'id': 'UudG83sw_q_Qad_QwTN6uV9imOpgBfS9YVyxeRPcj-g', 'resolutions': [{'height': 77, 'url': 'https://external-preview.redd.it/U-3hpJP92RzVCl2vMoAFgAkJjUtCbRaZNeVDF0qZBF0.jpg?width=108&crop=smart&auto=webp&s=d19f1f3d063b24d78bddc48055e02ea96ae35d9b', 'width': 108}, {'height': 154, 'url': 'h... |
Naked A100 | 95 | Thought would throw up pic captured during build. A100 without any casing.
Took me ages to realise the huge gold things are the power distributors/converters. Had presumed they were mem but then realised mem is on the main die with HBM2. | 2024-01-29T20:00:42 | https://www.reddit.com/gallery/1ae4m73 | BreakIt-Boris | reddit.com | 1970-01-01T00:00:00 | 0 | {} | 1ae4m73 | false | null | t3_1ae4m73 | /r/LocalLLaMA/comments/1ae4m73/naked_a100/ | false | false | 95 | null | |
Are 3xNvidia k80 Better than a new mobo with the same amount of ddr5? | 6 | Just wondering... Refurbished Nvidia k80s are quite cheap around here, and each one of em have 24gb of ddr5. Newer system are ddr5 too and the big pro is that you could swap ram if something goes wrong/If you want to upgrade.
So... Are those video cards better anyways?
Thank you all in advance | 2024-01-29T19:45:36 | https://www.reddit.com/r/LocalLLaMA/comments/1ae48xd/are_3xnvidia_k80_better_than_a_new_mobo_with_the/ | Relative_Bit_7250 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 1ae48xd | false | null | t3_1ae48xd | /r/LocalLLaMA/comments/1ae48xd/are_3xnvidia_k80_better_than_a_new_mobo_with_the/ | false | false | self | 6 | null |
Run llms using xdna drivers/ryzen ai | 1 | [removed] | 2024-01-29T19:40:56 | https://www.reddit.com/r/LocalLLaMA/comments/1ae44py/run_llms_using_xdna_driversryzen_ai/ | Wonderful-Eye-71 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 1ae44py | false | null | t3_1ae44py | /r/LocalLLaMA/comments/1ae44py/run_llms_using_xdna_driversryzen_ai/ | false | false | self | 1 | null |
🌐 Leeroo Orchestration-of-Experts O.O.E "[Research]" | 1 | [removed] | 2024-01-29T19:39:23 | https://www.reddit.com/r/LocalLLaMA/comments/1ae43bu/leeroo_orchestrationofexperts_ooe_research/ | AALISHKH | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 1ae43bu | false | null | t3_1ae43bu | /r/LocalLLaMA/comments/1ae43bu/leeroo_orchestrationofexperts_ooe_research/ | false | false | self | 1 | null |
Replacing ChatGPT 4 - $20 Subscription | 6 | I use ChatGPT mainly for code generation. I don’t care much for the rest of the features.
Currently have:
- Kubernetes cluster on 3x Lenovo M710q 32G RAM
- ESXI on Threadripper 2970wx / 128G RAM build
Assuming a budget of $1500 to buy more hardware. What can I achieve to get similar or better performance to GPT 4. | 2024-01-29T19:35:50 | https://www.reddit.com/r/LocalLLaMA/comments/1ae40bf/replacing_chatgpt_4_20_subscription/ | chkpwd | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 1ae40bf | false | null | t3_1ae40bf | /r/LocalLLaMA/comments/1ae40bf/replacing_chatgpt_4_20_subscription/ | false | false | self | 6 | null |
We're giving a grant for a port of Nano-GPT to a Haskell-like language called HVM. | 9 | 2024-01-29T19:27:47 | https://twitter.com/VictorTaelin/status/1752031528148693373 | SrPeixinho | twitter.com | 1970-01-01T00:00:00 | 0 | {} | 1ae3t64 | false | {'oembed': {'author_name': 'Taelin', 'author_url': 'https://twitter.com/VictorTaelin', 'cache_age': 3153600000, 'height': None, 'html': '<blockquote class="twitter-video"><p lang="en" dir="ltr">HOC is offering a grant for a purely functional port of Nano-GPT to HVM!<br><br>We'll be helping with the HVM details, so,... | t3_1ae3t64 | /r/LocalLLaMA/comments/1ae3t64/were_giving_a_grant_for_a_port_of_nanogpt_to_a/ | false | false | 9 | {'enabled': False, 'images': [{'id': '1MMIJxJiRDSpmwPyOX5ustOqWydAvdN2PKTUcdPhM58', 'resolutions': [{'height': 108, 'url': 'https://external-preview.redd.it/v5jbnxSDUijMq82wUK_DTInlzWCApXrb4Hj9gntr_Fc.jpg?width=108&crop=smart&auto=webp&s=6a32310b4a757cfb6105381604142b01ae0a96ff', 'width': 108}], 'source': {'height': 14... | ||
Some rumors are claiming this Mistral-Medium got leaked | 34 | So, some folks say that this model is a leak of Mistrial-Medium. Have we already discussed it, and I oversaw it?
Link:
https://huggingface.co/miqudev/miqu-1-70b
I have downloaded it in q5 format, and in my regular hardware, it looks like too heavy and slow for a 70b, so I guess MoE is being used under the hood.
Cou... | 2024-01-29T19:15:46 | https://www.reddit.com/r/LocalLLaMA/comments/1ae3ijf/some_rumors_are_claiming_this_mistralmedium_got/ | Shir_man | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 1ae3ijf | false | null | t3_1ae3ijf | /r/LocalLLaMA/comments/1ae3ijf/some_rumors_are_claiming_this_mistralmedium_got/ | false | false | self | 34 | {'enabled': False, 'images': [{'id': 'YwK0i5uwzktX1nH_8wCb9scLo-p_k7U36rHB1ExOeZo', 'resolutions': [{'height': 58, 'url': 'https://external-preview.redd.it/BQcqnWPMK5Y3U1I8wKe-mQjzHW7J109B4lbTrb7r6sA.jpg?width=108&crop=smart&auto=webp&s=dd5d7f81d68648edfb0c8136135c812f616df207', 'width': 108}, {'height': 116, 'url': 'h... |
Ambitious LLLM to helpe dealt with 'stuff' | 3 | Hi All,
I'm normally a lurker, but decided to throw this one out there as a sanity check, and I'm hoping the experts among you will weigh in.
Context: I'm a massive ADHD-head, run a small business, have no sense of 'I can't do that', and have enough vision to see what could happen, but perhaps not enough knowledge t... | 2024-01-29T19:11:03 | https://www.reddit.com/r/LocalLLaMA/comments/1ae3eci/ambitious_lllm_to_helpe_dealt_with_stuff/ | Captain_Bacon_X | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 1ae3eci | false | null | t3_1ae3eci | /r/LocalLLaMA/comments/1ae3eci/ambitious_lllm_to_helpe_dealt_with_stuff/ | false | false | self | 3 | null |
I created a python tool to easily load repos, docs or papers into an LLM | 1 | [removed] | 2024-01-29T19:06:03 | https://www.reddit.com/r/LocalLLaMA/comments/1ae3a0f/i_created_a_python_tool_to_easily_load_repos_docs/ | jimmc414 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 1ae3a0f | false | null | t3_1ae3a0f | /r/LocalLLaMA/comments/1ae3a0f/i_created_a_python_tool_to_easily_load_repos_docs/ | false | false | 1 | null | |
This can make a huge difference. Extending context from 4k to 400k. Llama-2-chat-7b. | 56 | Take a look on this
[https://arxiv.org/pdf/2401.03462.pdf](https://arxiv.org/pdf/2401.03462.pdf)
Github here
[https://github.com/FlagOpen/FlagEmbedding/tree/master/Long\_LLM/activation\_beacon](https://github.com/FlagOpen/FlagEmbedding/tree/master/Long_LLM/activation_beacon) | 2024-01-29T19:03:30 | https://www.reddit.com/r/LocalLLaMA/comments/1ae37sn/this_can_make_a_huge_difference_extending_context/ | AIMatrixRedPill | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 1ae37sn | false | null | t3_1ae37sn | /r/LocalLLaMA/comments/1ae37sn/this_can_make_a_huge_difference_extending_context/ | false | false | self | 56 | null |
Processor for quad 4090 setup? | 4 | I am building a quad 4090 (24gb) setup, 256gb ram. What processor would you recommend? I guess some xeon or epyc but not sure abot which one would have the best price/performance ratio. I am ok spending up to 1500-2000€ on processor. Ideally I would like to run quatitized 70B model and do some CV training. | 2024-01-29T18:50:16 | https://www.reddit.com/r/LocalLLaMA/comments/1ae2w00/processor_for_quad_4090_setup/ | Kyriales_ | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 1ae2w00 | false | null | t3_1ae2w00 | /r/LocalLLaMA/comments/1ae2w00/processor_for_quad_4090_setup/ | false | false | self | 4 | null |
gpt4-125-preview appeared on LMSYS passing the apple test 24/25. A direct response to bard catching up? | 1 | 2024-01-29T18:45:24 | kken | i.redd.it | 1970-01-01T00:00:00 | 0 | {} | 1ae2rp6 | false | null | t3_1ae2rp6 | /r/LocalLLaMA/comments/1ae2rp6/gpt4125preview_appeared_on_lmsys_passing_the/ | false | false | 1 | {'enabled': True, 'images': [{'id': 'pLXETHx4Pt7DMrxj0mM44QizAENa0R3aARrNOw71mMU', 'resolutions': [{'height': 95, 'url': 'https://preview.redd.it/92peb6drcffc1.png?width=108&crop=smart&auto=webp&s=b987ce7ac8a1b0ddc6ccb0686bb577bf6d323695', 'width': 108}, {'height': 190, 'url': 'https://preview.redd.it/92peb6drcffc1.png... | |||
Alibaba announces Qwen-VL | 43 | 2024-01-29T18:29:23 | https://qwenlm.github.io/blog/qwen-vl/ | Mandus_Therion | qwenlm.github.io | 1970-01-01T00:00:00 | 0 | {} | 1ae2d6x | false | null | t3_1ae2d6x | /r/LocalLLaMA/comments/1ae2d6x/alibaba_announces_qwenvl/ | false | false | default | 43 | null | |
TF-IDF + Embedding for RAGs? | 1 | Hi people,
has anyone tried to filter our irrelevant tokens using TF-IDF and then embed documents for retrieval?
Would it make sense or would I use more accuracy to the loss of semantics?
Using azure search service for vector store and retrieval btw.
Would be great to get some insights here | 2024-01-29T18:22:50 | https://www.reddit.com/r/LocalLLaMA/comments/1ae27d9/tfidf_embedding_for_rags/ | hag_o_hi | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 1ae27d9 | false | null | t3_1ae27d9 | /r/LocalLLaMA/comments/1ae27d9/tfidf_embedding_for_rags/ | false | false | self | 1 | null |
Trying out Etheria 55b, but getting an odd output. Anyone had luck with it? | 1 | Has anyone tried Etheria 55b? I downloaded the q8 from [TheBloke's gguf page for it.](https://huggingface.co/TheBloke/Etheria-55b-v0.1-GGUF)
I was pretty excited, because it's a Goliath 120b style merge for the Yi models. Unfortunately, I can't seem to get it to work in Oobabooga. No matter what instruction template I... | 2024-01-29T18:16:12 | https://www.reddit.com/r/LocalLLaMA/comments/1ae217k/trying_out_etheria_55b_but_getting_an_odd_output/ | SomeOddCodeGuy | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 1ae217k | false | null | t3_1ae217k | /r/LocalLLaMA/comments/1ae217k/trying_out_etheria_55b_but_getting_an_odd_output/ | false | false | self | 1 | {'enabled': False, 'images': [{'id': 'x39YczXitygrna_vbmGLlMs_VK1R0iBX9hAxDutJvF4', 'resolutions': [{'height': 58, 'url': 'https://external-preview.redd.it/n862czSuJESrdX7R4r9ABWwb2QyiJ6XXP3vVvd1KxQc.jpg?width=108&crop=smart&auto=webp&s=cf53fa4957229a4eba0c28f61f99a40f12b9b5cf', 'width': 108}, {'height': 116, 'url': 'h... |
How to use AutoGen Studio with Text Gen (pictures included) | 1 | [removed] | 2024-01-29T18:07:49 | https://www.reddit.com/r/LocalLLaMA/comments/1ae1tfu/how_to_use_autogen_studio_with_text_gen_pictures/ | Inevitable-Start-653 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 1ae1tfu | false | null | t3_1ae1tfu | /r/LocalLLaMA/comments/1ae1tfu/how_to_use_autogen_studio_with_text_gen_pictures/ | false | false | 1 | null | |
Working on documents summary and q&a (in house deployment) -need suggestion | 3 | Working on this project of Documents summarization and q&a.
Suggest some good open source model with low memory requirements (currently working on llama 7b 4bit quantized model)
One problem is that documents token length is 16k and model length is only 4k | 2024-01-29T18:00:10 | https://www.reddit.com/r/LocalLLaMA/comments/1ae1mal/working_on_documents_summary_and_qa_in_house/ | Alert_Director_2836 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 1ae1mal | false | null | t3_1ae1mal | /r/LocalLLaMA/comments/1ae1mal/working_on_documents_summary_and_qa_in_house/ | false | false | self | 3 | null |
Meta releases Code Llama2-70B, claims 67+ Humaneval | 135 | Meta has released the checkpoints of a new series of code models. They have the same llama 2 license.
From their announcement:
Today we’re releasing Code Llama 70B: a new, more performant version of our LLM for code generation — available under the same license as previous Code Llama models.
Download the models ➡️ ... | 2024-01-29T17:38:38 | https://huggingface.co/codellama | Amgadoz | huggingface.co | 1970-01-01T00:00:00 | 0 | {} | 1ae13f7 | false | null | t3_1ae13f7 | /r/LocalLLaMA/comments/1ae13f7/meta_releases_code_llama270b_claims_67_humaneval/ | false | false | 135 | {'enabled': False, 'images': [{'id': 'gmvczC1bSE838-GH8pLblnlMCkc5OMVllUs6haTvkb8', 'resolutions': [{'height': 58, 'url': 'https://external-preview.redd.it/jSSddtEy3YNYcaCtKmhyXjZYFZ4F48SglhbqdERHjks.jpg?width=108&crop=smart&auto=webp&s=c354ddb7c49f515a78b8cb787771ba6fad9dbcc2', 'width': 108}, {'height': 116, 'url': 'h... | |
How many epochs do you train an LLM for, in the case of a text completion dataset? I've always read that one epoch is optimal. | 10 | 2024-01-29T17:28:44 | 91o291o | i.redd.it | 1970-01-01T00:00:00 | 0 | {} | 1ae0uig | false | null | t3_1ae0uig | /r/LocalLLaMA/comments/1ae0uig/how_many_epochs_do_you_train_an_llm_for_in_the/ | false | false | 10 | {'enabled': True, 'images': [{'id': 'was5DoeesUN9yEGLVUND4uq2VCdUcqfxa9__CPrLuvw', 'resolutions': [{'height': 78, 'url': 'https://preview.redd.it/b51kxk6zxefc1.jpeg?width=108&crop=smart&auto=webp&s=17659533e7c17135e2603a428b6f8240f2ee425d', 'width': 108}, {'height': 156, 'url': 'https://preview.redd.it/b51kxk6zxefc1.jp... | |||
LLM that knows about Stable Diffusion (XL) prompts? | 5 | Which LLMs does know about how to write a good prompt for Stable Diffusion / Stable Diffusion XL?
The main, freely accessible ones (ChatGPT 3.5, BING and Bard) do know nothing.
But are there probably some freely available at huggingface (GGUF prefered)? | 2024-01-29T17:27:44 | https://www.reddit.com/r/LocalLLaMA/comments/1ae0tmn/llm_that_knows_about_stable_diffusion_xl_prompts/ | StableLlama | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 1ae0tmn | false | null | t3_1ae0tmn | /r/LocalLLaMA/comments/1ae0tmn/llm_that_knows_about_stable_diffusion_xl_prompts/ | false | false | self | 5 | null |
deploying mistral instruct v2 on aws sagemaker. | 1 | I have been trying to deploy mistral 7b instruct v2 on aws sagemaker using the code provided in the hugging face page of the model. The deployment has not been successful. The same code works with other models, but not with mistral instruct v2. Any thoughts on how to fix? | 2024-01-29T17:15:34 | https://www.reddit.com/r/LocalLLaMA/comments/1ae0ims/deploying_mistral_instruct_v2_on_aws_sagemaker/ | Necessary_Student_15 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 1ae0ims | false | null | t3_1ae0ims | /r/LocalLLaMA/comments/1ae0ims/deploying_mistral_instruct_v2_on_aws_sagemaker/ | false | false | self | 1 | null |
"We’re releasing Code Llama 70B: the most performant version of our LLM for code generation to date...." | 289 | 2024-01-29T17:08:55 | https://www.linkedin.com/posts/aiatmeta_today-were-releasing-code-llama-70b-the-activity-7157779543989055488-vBQO?utm_source=share&utm_medium=member_desktop | phoneixAdi | linkedin.com | 1970-01-01T00:00:00 | 0 | {} | 1ae0cfa | false | null | t3_1ae0cfa | /r/LocalLLaMA/comments/1ae0cfa/were_releasing_code_llama_70b_the_most_performant/ | false | false | 289 | {'enabled': False, 'images': [{'id': 'mDU7WbM5CSYahODtC3XdJpv2tctmY8h-MstL23eT7fM', 'resolutions': [{'height': 56, 'url': 'https://external-preview.redd.it/kfGe068g_1TiPRzPLIOK55LvQxeAqkun9M3clqJn6PE.jpg?width=108&crop=smart&auto=webp&s=f69acfa7d7d753c1a7dd6d3c2afdf1a57130ac7b', 'width': 108}, {'height': 113, 'url': 'h... | ||
Model trained to remove PII? | 1 | [removed] | 2024-01-29T16:53:52 | https://www.reddit.com/r/LocalLLaMA/comments/1adzyfk/model_trained_to_remove_pii/ | FoolHooligan | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 1adzyfk | false | null | t3_1adzyfk | /r/LocalLLaMA/comments/1adzyfk/model_trained_to_remove_pii/ | false | false | self | 1 | null |
Pure C/C++ codes to train small GPT modes on a single computer? | 1 | [removed] | 2024-01-29T16:42:07 | https://www.reddit.com/r/LocalLLaMA/comments/1adzo4c/pure_cc_codes_to_train_small_gpt_modes_on_a/ | Pitiful-You-8410 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 1adzo4c | false | null | t3_1adzo4c | /r/LocalLLaMA/comments/1adzo4c/pure_cc_codes_to_train_small_gpt_modes_on_a/ | false | false | self | 1 | null |
Runpod alternative for a 24h service? | 1 | [removed] | 2024-01-29T16:28:27 | https://www.reddit.com/r/LocalLLaMA/comments/1adzcc6/runpod_alternative_for_a_24h_service/ | Responsible-Sky8889 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 1adzcc6 | false | null | t3_1adzcc6 | /r/LocalLLaMA/comments/1adzcc6/runpod_alternative_for_a_24h_service/ | false | false | self | 1 | null |
Reor: an AI personal knowledge management app powered by local models | 70 | Reor is an open-source AI personal knowledge management app that runs models locally.
I wanted to build this because AI is the next step for organising unstructured notes but no one is talking about local models...We should be building tools that are offline & local by default, not OpenAI default!
The three main thi... | 2024-01-29T16:27:53 | https://www.reddit.com/r/LocalLLaMA/comments/1adzbu7/reor_an_ai_personal_knowledge_management_app/ | undamp | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 1adzbu7 | false | null | t3_1adzbu7 | /r/LocalLLaMA/comments/1adzbu7/reor_an_ai_personal_knowledge_management_app/ | false | false | self | 70 | null |
Subsets and Splits
No community queries yet
The top public SQL queries from the community will appear here once available.