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 ⌀ |
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
Throughput problem | 1 | [removed] | 2023-12-13T10:29:58 | https://www.reddit.com/r/LocalLLaMA/comments/18hdwn4/throughput_problem/ | llm-questions | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 18hdwn4 | false | null | t3_18hdwn4 | /r/LocalLLaMA/comments/18hdwn4/throughput_problem/ | false | false | default | 1 | null |
Refresh of "GPUs4AI" (database of AI-capable GPUs) | 20 | Hi all. I updated my [web page on GPUs for AI workloads](https://gpus4ai.edlabs.it/) with some new visualization features, small fixes and new data.
I'm not confident about some choices (e.g. which sparsity/accumulation to indicate) and I'm also not too keen on manually keeping it up-to-date in the long term (e.g. cos... | 2023-12-13T10:21:53 | https://www.reddit.com/r/LocalLLaMA/comments/18hdsm1/refresh_of_gpus4ai_database_of_aicapable_gpus/ | digital_m0nk | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 18hdsm1 | false | null | t3_18hdsm1 | /r/LocalLLaMA/comments/18hdsm1/refresh_of_gpus4ai_database_of_aicapable_gpus/ | false | false | self | 20 | null |
What's the fastest solution to run an Llama on Mobile GPUs? | 1 | [removed] | 2023-12-13T09:58:39 | https://www.reddit.com/r/LocalLLaMA/comments/18hdgcu/whats_the_fastest_solution_to_run_an_llama_on/ | AwfulPoet_34 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 18hdgcu | false | null | t3_18hdgcu | /r/LocalLLaMA/comments/18hdgcu/whats_the_fastest_solution_to_run_an_llama_on/ | false | false | self | 1 | null |
Training llama | 1 | [removed] | 2023-12-13T09:54:49 | https://www.reddit.com/r/LocalLLaMA/comments/18hdei8/training_llama/ | vinay737 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 18hdei8 | false | null | t3_18hdei8 | /r/LocalLLaMA/comments/18hdei8/training_llama/ | false | false | self | 1 | null |
Beginner - Clarification on llama training | 1 | [removed] | 2023-12-13T09:52:24 | https://www.reddit.com/r/LocalLLaMA/comments/18hddcr/beginner_clarification_on_llama_training/ | vinay737 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 18hddcr | false | null | t3_18hddcr | /r/LocalLLaMA/comments/18hddcr/beginner_clarification_on_llama_training/ | false | false | self | 1 | null |
Is there a viable alternative to Apple Silicone in terms of memory bandwidth for CPU inference? | 6 | Afaik Apple Silicone has insane memory bandwidth due to their architecture, which is why it is viable to run arbitrarily large models as long as your RAM is big enough.
Are there viable alternatives with AMD or Intel? Maybe buying an old threadripper(or xeon) and packing it full of memory would work?
Thanks | 2023-12-13T09:22:30 | https://www.reddit.com/r/LocalLLaMA/comments/18hcz1g/is_there_a_viable_alternative_to_apple_silicone/ | king_of_jupyter | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 18hcz1g | false | null | t3_18hcz1g | /r/LocalLLaMA/comments/18hcz1g/is_there_a_viable_alternative_to_apple_silicone/ | false | false | self | 6 | null |
Prompt format for storytelling | 12 | **Is there any specific tips to write prompt for LLM for creating story based on specific characters and settings? Is longer better or specific format performed better?** I'm specifically asking for 20B and lower model. | 2023-12-13T09:14:19 | https://www.reddit.com/r/LocalLLaMA/comments/18hcv32/prompt_format_for_storytelling/ | Jeon_Mian | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 18hcv32 | false | null | t3_18hcv32 | /r/LocalLLaMA/comments/18hcv32/prompt_format_for_storytelling/ | false | false | self | 12 | null |
Is my Data safe when using trust_remote_code? | 4 | Hi,
I'm building a local RAG system for a company as a student and our data has to remain private. I've seen that the Jina Embeddings ([https://huggingface.co/jinaai/jina-embeddings-v2-base-en](https://huggingface.co/jinaai/jina-embeddings-v2-base-en)) achieve very good results, however to use them i need to activate ... | 2023-12-13T09:10:49 | https://www.reddit.com/r/LocalLLaMA/comments/18hctg6/is_my_data_safe_when_using_trust_remote_code/ | Purity1212 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 18hctg6 | false | null | t3_18hctg6 | /r/LocalLLaMA/comments/18hctg6/is_my_data_safe_when_using_trust_remote_code/ | false | false | self | 4 | {'enabled': False, 'images': [{'id': 'snAF5jXPdYeMuGFDDreOcJXMPKdC3FU0cDy07Fi6OUk', 'resolutions': [{'height': 58, 'url': 'https://external-preview.redd.it/uBUeoCCsQG_5YUxVmvPJ4pmv2PewycTnNw1zQozRwMg.jpg?width=108&crop=smart&auto=webp&s=e3a7e1d468af1af3670177ca9b0024ac5f4e862b', 'width': 108}, {'height': 116, 'url': 'h... |
Infra provider with Pyton API... Located in Europe? | 1 | [removed] | 2023-12-13T08:45:28 | https://www.reddit.com/r/LocalLLaMA/comments/18hchle/infra_provider_with_pyton_api_located_in_europe/ | illorca-verbi | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 18hchle | false | null | t3_18hchle | /r/LocalLLaMA/comments/18hchle/infra_provider_with_pyton_api_located_in_europe/ | false | false | self | 1 | null |
Do the LLMs of the future consume much less? | 4 | I would like to know if you think that in the future (say 2 years) we will have found techniques to compress LLMs enormously or make them consume much less, a world where a 3B model of the future would be equivalent to a 70B model of today or if we could make it work on a simple phone with 24GB RAM | 2023-12-13T08:32:20 | https://www.reddit.com/r/LocalLLaMA/comments/18hcbm9/do_the_llms_of_the_future_consume_much_less/ | Terrible_Vegetable4 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 18hcbm9 | false | null | t3_18hcbm9 | /r/LocalLLaMA/comments/18hcbm9/do_the_llms_of_the_future_consume_much_less/ | false | false | self | 4 | null |
Question about gpu’s | 4 | Hey, I’m running two tesla p40’s which I have had for some time. But both their compute architecture as their performance are a bit dated.
I was wondering if I could keep them both for their memory and add a powerful newer third gpu purely for compute? Any advice or information would be much appreciated. I tried goog... | 2023-12-13T08:31:38 | https://www.reddit.com/r/LocalLLaMA/comments/18hcb98/question_about_gpus/ | DucksAreCoolRightYes | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 18hcb98 | false | null | t3_18hcb98 | /r/LocalLLaMA/comments/18hcb98/question_about_gpus/ | false | false | self | 4 | null |
Can't feasibly run Mixtral. How's Mistral Instruct v2? | 1 | [removed] | 2023-12-13T08:28:09 | https://www.reddit.com/r/LocalLLaMA/comments/18hc9fq/cant_feasibly_run_mixtral_hows_mistral_instruct_v2/ | Future_Might_8194 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 18hc9fq | false | null | t3_18hc9fq | /r/LocalLLaMA/comments/18hc9fq/cant_feasibly_run_mixtral_hows_mistral_instruct_v2/ | false | false | self | 1 | null |
2.7B model that performs like Mistral 7B! | 1 | https://venturebeat.com/ai/microsoft-releases-phi-2-a-small-language-model-ai-that-outperforms-llama-2-mistral-7b/
Microsoft has released Phi-2, a 2.7B parameter model, that shows pretty good results in benchmarks. | 2023-12-13T08:03:56 | https://www.reddit.com/r/LocalLLaMA/comments/18hbxf8/27b_model_that_performs_like_mistral_7b/ | koehr | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 18hbxf8 | false | null | t3_18hbxf8 | /r/LocalLLaMA/comments/18hbxf8/27b_model_that_performs_like_mistral_7b/ | false | false | self | 1 | {'enabled': False, 'images': [{'id': 'HwZ3WFAjUW3eKQbpRdEvjl7sVLvf3icSgNMBnuc5SWo', 'resolutions': [{'height': 60, 'url': 'https://external-preview.redd.it/U-_AGmPtN0hnVR-qDWTHDBxG6Efj-k0KwUj87PZErJ0.jpg?width=108&crop=smart&auto=webp&s=6ae1395334a5fefb9c268e44c238370a6c90135b', 'width': 108}, {'height': 120, 'url': 'h... |
What is the "correct" way of serving a LLM as an API using FastAPI? | 5 | Hi, I've looked through some posts here and searched online. When it comes to deployment, there are many solutions and frameworks out there that offer a plethora of functionalities.
However, what I need is pretty simple. I just want to serve a custom Langchain agent using open source models (GGUF). There will be some... | 2023-12-13T06:29:47 | https://www.reddit.com/r/LocalLLaMA/comments/18hakev/what_is_the_correct_way_of_serving_a_llm_as_an/ | theonlyQuan | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 18hakev | false | null | t3_18hakev | /r/LocalLLaMA/comments/18hakev/what_is_the_correct_way_of_serving_a_llm_as_an/ | false | false | self | 5 | null |
Local LLM app for devs to work with AI easier (example is LLaVA) | 1 | 2023-12-13T06:26:57 | https://v.redd.it/eov72hap906c1 | NomadicRotator | v.redd.it | 1970-01-01T00:00:00 | 0 | {} | 18haiuu | false | {'reddit_video': {'bitrate_kbps': 1200, 'dash_url': 'https://v.redd.it/eov72hap906c1/DASHPlaylist.mpd?a=1705127222%2CZDI2OGI2YjlmNGNhZTdiY2YxZDRjN2Y0M2U3NDUzZjUzNGU4ZjVlN2U1OTIyMTMyYTE2NTcxYzllMzQ4ZjlkMQ%3D%3D&v=1&f=sd', 'duration': 12, 'fallback_url': 'https://v.redd.it/eov72hap906c1/DASH_480.mp4?source=fallback', 'ha... | t3_18haiuu | /r/LocalLLaMA/comments/18haiuu/local_llm_app_for_devs_to_work_with_ai_easier/ | false | false | default | 1 | {'enabled': False, 'images': [{'id': 'NzFsd3gyc3c5MDZjMR6BijiJSIiU_wvNJrLObQwDoyZxn1fzYdq35m-2U-Ls', 'resolutions': [{'height': 76, 'url': 'https://external-preview.redd.it/NzFsd3gyc3c5MDZjMR6BijiJSIiU_wvNJrLObQwDoyZxn1fzYdq35m-2U-Ls.png?width=108&crop=smart&format=pjpg&auto=webp&s=7769695a12e04a6cebad3eb48254d6227c517... | |
Integrate LLaMA2 with a webapp | 1 | Hello everyone,
I want to use LLaMA2 with langchain, for my final year project . Since there is a token price i want to avoid it by running it locally . How can i run LLaMA2 and than make it a part of my web app which will be in React.
Please help ! | 2023-12-13T06:07:19 | https://www.reddit.com/r/LocalLLaMA/comments/18ha84b/integrate_llama2_with_a_webapp/ | HeadMedical9064 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 18ha84b | false | null | t3_18ha84b | /r/LocalLLaMA/comments/18ha84b/integrate_llama2_with_a_webapp/ | false | false | self | 1 | null |
Nous Capybara 34B VS CaPlatTessDolXaBoros 34B | 6 | 1. Which one is overall smarter?
2. Which one is better for stories and roleplay?
Anyone have any experience with both of these?
CaPlatTessDolXaBoros-Yi-34B-200K-DARE-Ties-HighDensity
Merge:
Dolphin-2.2-yi-34b-200k,
Nous-Capybara-34B,
Tess-M-v1.4,
Airoboros-3_1-yi-34b-200k, PlatYi-34B-200K-Q,
Una-xaberius-34b-v... | 2023-12-13T05:56:45 | https://www.reddit.com/r/LocalLLaMA/comments/18ha1t6/nous_capybara_34b_vs_caplattessdolxaboros_34b/ | Majestical-psyche | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 18ha1t6 | false | null | t3_18ha1t6 | /r/LocalLLaMA/comments/18ha1t6/nous_capybara_34b_vs_caplattessdolxaboros_34b/ | false | false | self | 6 | {'enabled': False, 'images': [{'id': 'YIE5kc3E-w1ZbzsfeC2agfZWG8wlD7PFa7eyIFZ8wpA', 'resolutions': [{'height': 58, 'url': 'https://external-preview.redd.it/ZpF2mHEbKqAqtts2_9D56nHDDEuUFypNsjYAF_jYcPI.jpg?width=108&crop=smart&auto=webp&s=ace2f614fe47494a6dc8fab9a0a6df5044513c16', 'width': 108}, {'height': 116, 'url': 'h... |
Is it possible to run quantized llama 70b on multiple T4 GPU? | 2 | I see there’s example of multi-gpu with llama-70b but usually multiple a100. Is it possible to run llama-70b quantized on say 4 T4 GPU? | 2023-12-13T05:35:27 | https://www.reddit.com/r/LocalLLaMA/comments/18h9ph1/is_it_possible_to_run_quantized_llama_70b_on/ | defuyun | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 18h9ph1 | false | null | t3_18h9ph1 | /r/LocalLLaMA/comments/18h9ph1/is_it_possible_to_run_quantized_llama_70b_on/ | false | false | self | 2 | null |
Tesla p40s? | 5 | Ok I’m tired on only having 24 gigs of vram. I need more. Right now I’m using two 3060 12gigs. And I want to be able to run larger models and run multiple modules that need to utilize vram for other models. I was thinking about getting two Tesla p40s to run in my AI server. Does anyone have experience with it and will ... | 2023-12-13T05:35:22 | https://www.reddit.com/r/LocalLLaMA/comments/18h9pfd/tesla_p40s/ | opi098514 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 18h9pfd | false | null | t3_18h9pfd | /r/LocalLLaMA/comments/18h9pfd/tesla_p40s/ | false | false | self | 5 | null |
ELI5 why do we have weird LLM sizes like 3b, 7b, 13b, 33b, 70b? Who invented those sizes? | 102 | I understand it must be related to the way these LLMs and constructed. But I don't understand where such kind of numbers comer from? Take three 3B model, Why don't we add a few more layers and make it 4b for example? | 2023-12-13T05:34:55 | https://www.reddit.com/r/LocalLLaMA/comments/18h9p51/eli5_why_do_we_have_weird_llm_sizes_like_3b_7b/ | --dany-- | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 18h9p51 | false | null | t3_18h9p51 | /r/LocalLLaMA/comments/18h9p51/eli5_why_do_we_have_weird_llm_sizes_like_3b_7b/ | false | false | self | 102 | null |
BigDL versus Llamacpp/Ollama/etc | 3 | See https://github.com/intel-analytics/BigDL
Anybody got experience with BigDL? Pros/cons?
Recently it’s being presented on couple webinars, and another one coming up soon. | 2023-12-13T05:23:51 | https://www.reddit.com/r/LocalLLaMA/comments/18h9ijf/bigdl_versus_llamacppollamaetc/ | Puzzleheaded-Fly4322 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 18h9ijf | false | null | t3_18h9ijf | /r/LocalLLaMA/comments/18h9ijf/bigdl_versus_llamacppollamaetc/ | false | false | self | 3 | {'enabled': False, 'images': [{'id': 'kRS83Lv0fhrSlcb_rFOam6slTpBP-OL75GGC__HY9Oc', 'resolutions': [{'height': 54, 'url': 'https://external-preview.redd.it/4jL5ZH-HaT524qeJjz-7YmT3tyqauE5isobLPeuxLSQ.jpg?width=108&crop=smart&auto=webp&s=b0b86d5b49b9d6af665c58ac2ebf92da651ec053', 'width': 108}, {'height': 108, 'url': 'h... |
Which is the top 7B right now? | 5 | [deleted]
[View Poll](https://www.reddit.com/poll/18h9fei) | 2023-12-13T05:18:57 | https://www.reddit.com/r/LocalLLaMA/comments/18h9fei/which_is_the_top_7b_right_now/ | Future_Might_8194 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 18h9fei | false | null | t3_18h9fei | /r/LocalLLaMA/comments/18h9fei/which_is_the_top_7b_right_now/ | false | false | default | 5 | null |
Seeking Advice: Optimal Hardware Specs for 24/7 LLM Inference (RAG) with Scaling Requests - CPU, GPU, RAM, MOBO Considerations | 1 | Hello everyone. I've been researching on the costings of running LLMs but I am still very much confused.
Here is my use case :
1. 24/7 inference ( RAG )
2. Request per hour will go up in the future, now quite low ( < 100 req / hour )
3. NO training ( At least for now, RAG only seems to be OK )
4. Prefer up to 16K ... | 2023-12-13T05:10:19 | https://www.reddit.com/r/LocalLLaMA/comments/18h9a72/seeking_advice_optimal_hardware_specs_for_247_llm/ | Distinct_Maximum_760 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 18h9a72 | false | null | t3_18h9a72 | /r/LocalLLaMA/comments/18h9a72/seeking_advice_optimal_hardware_specs_for_247_llm/ | false | false | self | 1 | null |
Who came up with the idea of using these ugly and barely legible charts to compare LLMs, and can we agree as a community to never use them again? | 1 | 2023-12-13T03:52:04 | Covid-Plannedemic_ | i.redd.it | 1970-01-01T00:00:00 | 0 | {} | 18h7va4 | false | null | t3_18h7va4 | /r/LocalLLaMA/comments/18h7va4/who_came_up_with_the_idea_of_using_these_ugly_and/ | false | false | 1 | {'enabled': True, 'images': [{'id': 'FasYa2hKISlSrtXjEDHI-uz8njg_sdn-ulIXkVfblPs', 'resolutions': [{'height': 99, 'url': 'https://preview.redd.it/eymc8h1niz5c1.png?width=108&crop=smart&auto=webp&s=4c11129f331c56207c34e16fc63824c6e4f3b842', 'width': 108}, {'height': 199, 'url': 'https://preview.redd.it/eymc8h1niz5c1.png... | |||
Socrates Zephyr - Model and Database on Hugginface. What do you think? | 12 | Hi Everyone! I fine-tuned another model Zephyr mistral 7B on Socrates' persona, please check it and you can provide feedback so I can get better. I've used pre-trained models before and this one was a little different since it still retains the original zephyr fine-tune. I modified the database a little from previous ... | 2023-12-13T03:19:38 | https://www.reddit.com/r/LocalLLaMA/comments/18h790l/socrates_zephyr_model_and_database_on_hugginface/ | Delicious-Farmer-234 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 18h790l | false | null | t3_18h790l | /r/LocalLLaMA/comments/18h790l/socrates_zephyr_model_and_database_on_hugginface/ | false | false | 12 | {'enabled': False, 'images': [{'id': 'txhvg1aDWZFFZoN1ZGFR04Zq-kvY0u1jGITvU8hQjsQ', 'resolutions': [{'height': 58, 'url': 'https://external-preview.redd.it/YYMhBNAaAfAk0cjUTaR8Sj_jC3TTwcH9w1EGg7Z9IhA.jpg?width=108&crop=smart&auto=webp&s=aa94c7e2e815429699eaa14b0c834b7de9e0eb9c', 'width': 108}, {'height': 116, 'url': 'h... | |
Steering Llama 2 via Contrastive Activation Addition | 24 | 2023-12-13T03:19:28 | ninjasaid13 | i.redd.it | 1970-01-01T00:00:00 | 0 | {} | 18h78wz | false | null | t3_18h78wz | /r/LocalLLaMA/comments/18h78wz/steering_llama_2_via_contrastive_activation/ | false | false | 24 | {'enabled': True, 'images': [{'id': 'ANTSr6HYgr5Vc3fkGmRAQWCkY8ylvczONzfJFX6ef8A', 'resolutions': [{'height': 128, 'url': 'https://preview.redd.it/fgzli8hwcz5c1.jpg?width=108&crop=smart&auto=webp&s=db6cdb0e7192e9b8f4f332bf67bad9f4bce26a18', 'width': 108}, {'height': 256, 'url': 'https://preview.redd.it/fgzli8hwcz5c1.jp... | |||
End-to-End RAG Pipeline Development With MyScale and LlamaIndex | 1 | 2023-12-13T02:33:53 | https://myscale.com/blog/rag-pipeline-with-myscale-and-llamaindex/ | BellaHi | myscale.com | 1970-01-01T00:00:00 | 0 | {} | 18h6c1d | false | null | t3_18h6c1d | /r/LocalLLaMA/comments/18h6c1d/endtoend_rag_pipeline_development_with_myscale/ | false | false | 1 | {'enabled': False, 'images': [{'id': 'Jo2J3iEpwORaqKvyrDdIeX46vSga5QTrFSHqjsN1F7U', 'resolutions': [{'height': 108, 'url': 'https://external-preview.redd.it/Sjw5KUISBs3fWlzWbzf8RczrASlxKhBidT7QJ497htM.jpg?width=108&crop=smart&auto=webp&s=17443c8d608c8817453bb48ded7670b69b5756ca', 'width': 108}, {'height': 216, 'url': '... | ||
ArgalAI is now live on the Mac App Store | 5 | Two months ago I [posted](https://www.reddit.com/r/LocalLLaMA/comments/17agz01/im_building_a_macos_app_to_run_your_own_local/) about an app I was developing (back then I called it LoChat). It had pretty good reception so I decided to get it done and release it.
Well it has been two long months and it is now live on th... | 2023-12-13T02:33:21 | https://www.reddit.com/r/LocalLLaMA/comments/18h6bn6/argalai_is_now_live_on_the_mac_app_store/ | robert_ritz | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 18h6bn6 | false | null | t3_18h6bn6 | /r/LocalLLaMA/comments/18h6bn6/argalai_is_now_live_on_the_mac_app_store/ | false | false | self | 5 | {'enabled': False, 'images': [{'id': 'de_520tzKNULOT2x9oxmIUBejR5qJwjYaDzYqwH6tHQ', 'resolutions': [{'height': 108, 'url': 'https://external-preview.redd.it/DCyF7nyCJwFArAUc4lcbReINAmD1gZo3Ae8wuSfYr6c.jpg?width=108&crop=smart&auto=webp&s=9f5120a02980815482fab82b4ff7517f5a83684b', 'width': 108}, {'height': 216, 'url': '... |
Mixtral still works well when using 1 expert per token | 82 | The regular expected amount of experts that are routed per token is 2, for Mixtral's MoE setup.
But this is a hyperparameter that can be modified; someone in TheBloke's server changed it to route 1 expert per token by modifying and rebuilding llama.cpp.
The results were not bad at all, and this **doubled the prompt p... | 2023-12-13T02:09:46 | https://www.reddit.com/r/LocalLLaMA/comments/18h5p1v/mixtral_still_works_well_when_using_1_expert_per/ | kindacognizant | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 18h5p1v | false | null | t3_18h5p1v | /r/LocalLLaMA/comments/18h5p1v/mixtral_still_works_well_when_using_1_expert_per/ | false | false | 82 | {'enabled': False, 'images': [{'id': 'AVfRQZXGE39r4G8y5z0xPLili6Hi0paJ4FLnphIyVek', 'resolutions': [{'height': 54, 'url': 'https://external-preview.redd.it/kLI1LHaoe_ZBLHDKqm-8FsaATQAHaKk7WsoWnljAM48.jpg?width=108&crop=smart&auto=webp&s=2bda48053736afedbf460e0432ef53f02ffebecf', 'width': 108}, {'height': 108, 'url': 'h... | |
ArgalAI is now available on the Mac App Store. Dead simple way to use local LLMs. | 1 | 2023-12-13T02:01:55 | robert_ritz | i.redd.it | 1970-01-01T00:00:00 | 0 | {} | 18h5gvt | false | null | t3_18h5gvt | /r/LocalLLaMA/comments/18h5gvt/argalai_is_now_available_on_the_mac_app_store/ | false | false | default | 1 | null | ||
ArgalAI (formerly LoChat) is now live on the Mac App Store | 1 | 2023-12-13T01:59:01 | https://i.redd.it/5wdpu2ygyy5c1 | robert_ritz | i.redd.it | 1970-01-01T00:00:00 | 0 | {} | 18h5dnv | false | null | t3_18h5dnv | /r/LocalLLaMA/comments/18h5dnv/argalai_formerly_lochat_is_now_live_on_the_mac/ | false | false | default | 1 | null | |
Finetune to be better at RAG? | 10 | I want to use 13b or 34b Llama models for RAG purposes. The problem with the models that I have tried so far are these:
1. It does not just make use of the provided context, even though the prompt instructs it to
2. Some models capture the tone of the retrieved contexts and respond in a similar way. So the model appea... | 2023-12-13T01:51:26 | https://www.reddit.com/r/LocalLLaMA/comments/18h55is/finetune_to_be_better_at_rag/ | gptzerozero | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 18h55is | false | null | t3_18h55is | /r/LocalLLaMA/comments/18h55is/finetune_to_be_better_at_rag/ | false | false | self | 10 | null |
Well, at least it runs Mixtral 8x7b at 5Q 🤷♂️ | 12 | 2023-12-13T01:28:19 | https://i.redd.it/bl1453m2ty5c1 | SupplyChainNext | i.redd.it | 1970-01-01T00:00:00 | 0 | {} | 18h4g15 | false | null | t3_18h4g15 | /r/LocalLLaMA/comments/18h4g15/well_at_least_it_runs_mixtral_8x7b_at_5q/ | false | false | default | 12 | {'enabled': True, 'images': [{'id': 'MuNYf-BW7Oyfi9SLVTRTG9CLQXLzQWSGX__I2ccKzx0', 'resolutions': [{'height': 135, 'url': 'https://preview.redd.it/bl1453m2ty5c1.jpeg?width=108&crop=smart&auto=webp&s=b553321204a57797bd7b6695c1fa9b8da180bd62', 'width': 108}, {'height': 270, 'url': 'https://preview.redd.it/bl1453m2ty5c1.j... | |
mistral 7b Q5 K S on my fold 4. | 10 | so its had some self censorship but cant go 100% uncensored. https://i.postimg.cc/BvDKNVXf/20231213-T095747.jpg responce times are decent on my fold 4 | 2023-12-13T01:15:44 | https://www.reddit.com/r/LocalLLaMA/comments/18h41yz/mistral_7b_q5_k_s_on_my_fold_4/ | nntb | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 18h41yz | false | null | t3_18h41yz | /r/LocalLLaMA/comments/18h41yz/mistral_7b_q5_k_s_on_my_fold_4/ | false | false | self | 10 | {'enabled': False, 'images': [{'id': 'AGRduJwYt5g7VkD1E7KDbN6DtW88mTbIRU9zTZAMx58', 'resolutions': [{'height': 124, 'url': 'https://external-preview.redd.it/UoDxvCtBUL0sKon70Ae43rkqBC_vkMMxYpgVan7fFKI.jpg?width=108&crop=smart&auto=webp&s=3728d508b94b43ac8e321a1047bfb2d5a6a30d19', 'width': 108}, {'height': 249, 'url': '... |
Advice on running models on my hardware (4090 R9-3950x 128GB RAM) | 2 | Hello all you wonderful folk,
So I recently learnt about these local LLM models while self studying machine learning (still a beginner), I am honestly surprised how far the current technology is compared to the books printed just a few years ago, Anyways I have downloaded some 7b and 13b LLaMA GPTQ models from huggin... | 2023-12-13T01:07:25 | https://www.reddit.com/r/LocalLLaMA/comments/18h3sm4/advice_on_running_models_on_my_hardware_4090/ | ReAnimatedCell | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 18h3sm4 | false | null | t3_18h3sm4 | /r/LocalLLaMA/comments/18h3sm4/advice_on_running_models_on_my_hardware_4090/ | false | false | self | 2 | null |
Is there a Mixtral inference notebook for Kaggle? | 5 | Asking this so I don't waste my time making a new one. | 2023-12-13T01:03:43 | https://www.reddit.com/r/LocalLLaMA/comments/18h3og0/is_there_a_mixtral_inference_notebook_for_kaggle/ | bot-333 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 18h3og0 | false | null | t3_18h3og0 | /r/LocalLLaMA/comments/18h3og0/is_there_a_mixtral_inference_notebook_for_kaggle/ | false | false | self | 5 | null |
What locally runnable LLM has the best documentation? | 2 | Official or unofficial, and best to worst if you can give sich an opinion | 2023-12-13T00:46:43 | https://www.reddit.com/r/LocalLLaMA/comments/18h35f6/what_locally_runnable_llm_has_the_best/ | HotRepresentative325 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 18h35f6 | false | null | t3_18h35f6 | /r/LocalLLaMA/comments/18h35f6/what_locally_runnable_llm_has_the_best/ | false | false | self | 2 | null |
If you have issue running TheBloke/Mixtral-8x7B-Instruct-v0.1-GGUF | 13 | #Edit#
Already oudated.
Llama.cpp merge the Mixtral branch in the main branch already.
Part of the prompt issue was a mistake by TheBloke, we need to removed the <s> : https://github.com/ggerganov/llama.cpp/pull/4406#issuecomment-1853567132
I still have early code termination if i use GPU, so ill leave this up.
#-#... | 2023-12-13T00:37:52 | https://www.reddit.com/r/LocalLLaMA/comments/18h2vdj/if_you_have_issue_running/ | mantafloppy | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 18h2vdj | false | null | t3_18h2vdj | /r/LocalLLaMA/comments/18h2vdj/if_you_have_issue_running/ | false | false | self | 13 | {'enabled': False, 'images': [{'id': 'xGIgq5WHLtGSEAX_BThPt55UcCUz5VDbxJtIVG9bmp8', 'resolutions': [{'height': 54, 'url': 'https://external-preview.redd.it/dD5R8cPNrpba6tnVBdoRc9pMXABwvUsqfKOsYBqd6q8.jpg?width=108&crop=smart&auto=webp&s=c6f61c1605194b0c78b7b44868cba3c4b678fc4f', 'width': 108}, {'height': 108, 'url': 'h... |
Looking for Visual Studio c++ GUI example for llama.cpp to get me started | 3 | Anybody build a simple GUI chat for llama.dll in C++ that can share with me to get me started? Or found one on github? I work much better from code than from documentation...
I want to build a LLM plugin to a text editor - but this would help me to start so I don't have to reinvent the wheel.
​ | 2023-12-13T00:18:11 | https://www.reddit.com/r/LocalLLaMA/comments/18h28e0/looking_for_visual_studio_c_gui_example_for/ | FPham | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 18h28e0 | false | null | t3_18h28e0 | /r/LocalLLaMA/comments/18h28e0/looking_for_visual_studio_c_gui_example_for/ | false | false | self | 3 | null |
Phi2 vs Mistral Instruct V.02, which are you trying first? | 1 | [removed] | 2023-12-12T23:52:20 | https://www.reddit.com/r/LocalLLaMA/comments/18h1ei4/phi2_vs_mistral_instruct_v02_which_are_you_trying/ | Future_Might_8194 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 18h1ei4 | false | null | t3_18h1ei4 | /r/LocalLLaMA/comments/18h1ei4/phi2_vs_mistral_instruct_v02_which_are_you_trying/ | false | false | self | 1 | null |
Live Fine-tuning? | 2 | Is there a way to find tune a model while using it? Like be able to adjust the weights while it's running or shortly after? | 2023-12-12T23:17:19 | https://www.reddit.com/r/LocalLLaMA/comments/18h09ej/live_finetuning/ | ChildOf7Sins | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 18h09ej | false | null | t3_18h09ej | /r/LocalLLaMA/comments/18h09ej/live_finetuning/ | false | false | self | 2 | null |
Suggestions for benchmarking inferencing on PCs? | 2 | I've been noodling around with various ways of benchmarking upcoming PC processors (Intel Meteor Lake, Ryzen 8000, Qualcomm Snapdragon X Elite) and have some ideas. I'd like your input, though, as to what you'd use.
Most of the benchmarks I see are for mobile processors, and I'd like something that preferably runs on... | 2023-12-12T23:12:56 | https://www.reddit.com/r/LocalLLaMA/comments/18h04c7/suggestions_for_benchmarking_inferencing_on_pcs/ | markhachman | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 18h04c7 | false | null | t3_18h04c7 | /r/LocalLLaMA/comments/18h04c7/suggestions_for_benchmarking_inferencing_on_pcs/ | false | false | self | 2 | null |
🐺🐦⬛ LLM Comparison/Test: Mixtral-8x7B, Mistral, DeciLM, Synthia-MoE | 234 | With Mixtral's much-hyped (deservedly-so? let's find out!) release, I just had to drop what I was doing and do my usual in-depth tests and comparisons with this 8x7B mixture-of-experts model.
And since Mistral also released their updated 7B models, and there was already a Synthia (which is among my favorite models) Mo... | 2023-12-12T22:43:51 | https://www.reddit.com/r/LocalLLaMA/comments/18gz54r/llm_comparisontest_mixtral8x7b_mistral_decilm/ | WolframRavenwolf | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 18gz54r | false | null | t3_18gz54r | /r/LocalLLaMA/comments/18gz54r/llm_comparisontest_mixtral8x7b_mistral_decilm/ | false | false | self | 234 | {'enabled': False, 'images': [{'id': 'xU07sACUhuScPaN8BIMV0USMZkFwSMGcorjhvoKF4K0', 'resolutions': [{'height': 58, 'url': 'https://external-preview.redd.it/FRlvpc5SALNi_rYIzAsFALIzMXE1oc-Gkb2Yh1ZWGMM.jpg?width=108&crop=smart&auto=webp&s=9ad9ea4d991fae47edd6a09b5feb6d60eca474de', 'width': 108}, {'height': 116, 'url': 'h... |
Experimenting with Vicuna 13B | 2 | Howdy folks,
I am running Vicuna 13B and just wanted to share the very basic experiment I've been running: essentially I am trying to customize the chatbot with a bespoke system message. It is a pretty simple python script:
import json
import requests
url = 'http://fastchat.local/v1/completions'
sy... | 2023-12-12T22:22:31 | https://www.reddit.com/r/LocalLLaMA/comments/18gyfwx/experimenting_with_vicuna_13b/ | eom-dev | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 18gyfwx | false | null | t3_18gyfwx | /r/LocalLLaMA/comments/18gyfwx/experimenting_with_vicuna_13b/ | false | false | self | 2 | {'enabled': False, 'images': [{'id': 'q3evP6JeDpAC2MdSQHWYxnCYTqbJkElIQsLFqVSdkss', 'resolutions': [{'height': 63, 'url': 'https://external-preview.redd.it/izh8gZHY4FqZ1nwtU1N_TjtohUCNuvTyMn90toXda80.jpg?width=108&crop=smart&auto=webp&s=bc9575b410002edc2df3c5b5b0355fefedc7baa8', 'width': 108}, {'height': 126, 'url': 'h... |
I am really impressed with Mixtral 8x7 MoE | 27 | Now available on hugging chat. | 2023-12-12T22:03:05 | https://i.redd.it/rc607p5isx5c1 | AstrionX | i.redd.it | 1970-01-01T00:00:00 | 0 | {} | 18gxu17 | false | null | t3_18gxu17 | /r/LocalLLaMA/comments/18gxu17/i_am_really_impressed_with_mixtral_8x7_moe/ | false | false | default | 27 | {'enabled': True, 'images': [{'id': 'HIKt9oGMahB5R5U38rhMbpCgTlI-evTv6QBjFRgDfrQ', 'resolutions': [{'height': 216, 'url': 'https://preview.redd.it/rc607p5isx5c1.jpeg?width=108&crop=smart&auto=webp&s=1d4c271369286512d503ad68cc1226cf3d5f5d72', 'width': 108}, {'height': 432, 'url': 'https://preview.redd.it/rc607p5isx5c1.j... |
DeciLM-7B Instruct v Mistral-7B-Instruct-v01 on Chain of Thought | 7 | **Note:** I finished this notebook yesterday before learning about the news Mistral model. I will re-run this with the new Mistral instruct-tuned model later this week. If anyone from the community wants to re-run the notebook using the new Mistral model before then, please do.
📘 Check the notebook out [here](https:... | 2023-12-12T22:02:33 | https://www.reddit.com/r/LocalLLaMA/comments/18gxtey/decilm7b_instruct_v_mistral7binstructv01_on_chain/ | datascienceharp | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 18gxtey | false | null | t3_18gxtey | /r/LocalLLaMA/comments/18gxtey/decilm7b_instruct_v_mistral7binstructv01_on_chain/ | false | false | self | 7 | {'enabled': False, 'images': [{'id': 'nkhh65ujo5BznFJFojoMPaKjGuLSpPj6KGhRov-ykOg', 'resolutions': [{'height': 108, 'url': 'https://external-preview.redd.it/0-fRWqjlLadVXj5pfYp4_Oe3xgBWE-_rdjVSn7hlohI.jpg?width=108&crop=smart&auto=webp&s=f34d2dfdbbfa7de0f1956f186fd8430ee96a1a55', 'width': 108}, {'height': 216, 'url': '... |
Augmenting Local AI with Browser Data: Introducing MemoryCache | 33 | 2023-12-12T21:29:46 | https://future.mozilla.org/blog/introducing-memorycache/ | TinyApps_Org | future.mozilla.org | 1970-01-01T00:00:00 | 0 | {} | 18gwxuq | false | null | t3_18gwxuq | /r/LocalLLaMA/comments/18gwxuq/augmenting_local_ai_with_browser_data_introducing/ | false | false | default | 33 | null | |
AWS cloud pipeline mapping via LLM | 3 | I understand it probably couldn't fully be automated, but does anyone know of any service where I could connect to GitHub or put my code in and have it look through various source files for JavaScript and map out which pipelines need to be built and how on AWS. | 2023-12-12T21:22:34 | https://www.reddit.com/r/LocalLLaMA/comments/18gwrt1/aws_cloud_pipeline_mapping_via_llm/ | CuriousProgrammable | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 18gwrt1 | false | null | t3_18gwrt1 | /r/LocalLLaMA/comments/18gwrt1/aws_cloud_pipeline_mapping_via_llm/ | false | false | self | 3 | null |
Fine tuning Mixtral 8x7B | 11 | I'm having many issues fine tuning the Mixtral 8x7B - training throws errors between 30 minutes to 3 hours of training (4xL4 gpus). Using the same methods as running the Mistral 7b or Llama 13/70b models - anything different that I need to know when training an MoE model? | 2023-12-12T21:18:38 | https://www.reddit.com/r/LocalLLaMA/comments/18gwoke/fine_tuning_mixtral_8x7b/ | CuriosAligator | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 18gwoke | false | null | t3_18gwoke | /r/LocalLLaMA/comments/18gwoke/fine_tuning_mixtral_8x7b/ | false | false | self | 11 | null |
Noob Question : How are people able to run Mistral 8x-7b locally when platforms like replicate which are/were using A100s still take/took 52s to produce output? | 40 | I’m new to AI.
Just asking dumb questions for more clarity.
A simplified answer with a link to more detailed sources would be really helpful.
Thank you | 2023-12-12T21:16:52 | https://www.reddit.com/r/LocalLLaMA/comments/18gwn4y/noob_question_how_are_people_able_to_run_mistral/ | punit_palial | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 18gwn4y | false | null | t3_18gwn4y | /r/LocalLLaMA/comments/18gwn4y/noob_question_how_are_people_able_to_run_mistral/ | false | false | self | 40 | null |
Gemini wasn't released yet and was already "beaten" by MS... what a time to be alive! | 116 | ​
[Results reported by MS](https://preview.redd.it/1nczzysmix5c1.png?width=1210&format=png&auto=webp&s=9b3fec9b766cac0f268a0a17953956b62b42a6d3)
Source: [https://www.microsoft.com/en-us/research/blog/steering-at-the-frontier-extending-the-power-of-prompting/](https://www.microsoft.com/en-us/research/blog/steer... | 2023-12-12T21:08:13 | https://www.reddit.com/r/LocalLLaMA/comments/18gwg09/gemini_wasnt_released_yet_and_was_already_beaten/ | VertexMachine | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 18gwg09 | false | null | t3_18gwg09 | /r/LocalLLaMA/comments/18gwg09/gemini_wasnt_released_yet_and_was_already_beaten/ | false | false | 116 | {'enabled': False, 'images': [{'id': 'UMjqgM6AJ734iF5UWmQvuhyJAru2nIBB5TeAve7LQpw', 'resolutions': [{'height': 56, 'url': 'https://external-preview.redd.it/5ei1O03qVtMIWlN3BZXOAdiLq84LvNR6rRynnVcOsP0.jpg?width=108&crop=smart&auto=webp&s=20e2ad707e2012bb353a27cf842165113b49b249', 'width': 108}, {'height': 112, 'url': 'h... | |
Potentially outlandish question(s)/thoughts for hopefully someone with high expertise to answer? | 9 | Why wide and not deep? So LLM have relatively few layers, while layers are extremely wide. And that seems, lets say extremely suspicious. I know transformers are not what fasttext used, but... For some tasks some, almost decade ago I need text classifier, and fasttext seemed to fit the bill decently. Now default retrai... | 2023-12-12T21:05:55 | https://www.reddit.com/r/LocalLLaMA/comments/18gwe23/potentially_outlandish_questionsthoughts_for/ | morphles | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 18gwe23 | false | null | t3_18gwe23 | /r/LocalLLaMA/comments/18gwe23/potentially_outlandish_questionsthoughts_for/ | false | false | self | 9 | null |
I fine-tuned Llama to generate system diagrams for any repo | 86 | 2023-12-12T21:01:45 | https://v.redd.it/gsko5acpgx5c1 | TheMblabla | v.redd.it | 1970-01-01T00:00:00 | 0 | {} | 18gwah2 | false | {'reddit_video': {'bitrate_kbps': 5000, 'dash_url': 'https://v.redd.it/gsko5acpgx5c1/DASHPlaylist.mpd?a=1705006919%2CZGMzNDc3NzljZGQ5MWY5ZWM1OThhMGM3MjA1OGYwZmRhY2Y5MmJlN2M2OWQwY2E2MDVmNTVmNTc0ZGRkMzdkYg%3D%3D&v=1&f=sd', 'duration': 45, 'fallback_url': 'https://v.redd.it/gsko5acpgx5c1/DASH_1080.mp4?source=fallback', 'h... | t3_18gwah2 | /r/LocalLLaMA/comments/18gwah2/i_finetuned_llama_to_generate_system_diagrams_for/ | false | false | 86 | {'enabled': False, 'images': [{'id': 'N3BrcWtoOGtoeDVjMdOUIoYGV9-az7QVspxR7I-8jv3BrZE-LMhIuQAOnlvp', 'resolutions': [{'height': 64, 'url': 'https://external-preview.redd.it/N3BrcWtoOGtoeDVjMdOUIoYGV9-az7QVspxR7I-8jv3BrZE-LMhIuQAOnlvp.png?width=108&crop=smart&format=pjpg&auto=webp&s=6730cba4f79b020f0b92dfc36b3e3d1f7692b... | ||
Could you guys give me tips for my potential school project? | 2 | So my teacher and I were talking about LLMs and he brought up the idea of using a language model as a recommendation system.
The model should be small and its role would be to talk with the user and extract relevant information from them.
To keep the model's size small, it wouldn't not be trained on the books themsel... | 2023-12-12T20:53:10 | https://www.reddit.com/r/LocalLLaMA/comments/18gw39y/could_you_guys_give_me_tips_for_my_potential/ | HappyLove4691 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 18gw39y | false | null | t3_18gw39y | /r/LocalLLaMA/comments/18gw39y/could_you_guys_give_me_tips_for_my_potential/ | false | false | self | 2 | null |
Need clear google colab for fine tuning chat | 2 | Most of the tutorials I found focus on tuning instructions. It would be interesting to see lora’s implementation of training for chat. It also interesting to find out if there is a difference between learning through all the words and passing gradients only through the assistants answers (does it make diff). | 2023-12-12T20:48:47 | https://www.reddit.com/r/LocalLLaMA/comments/18gvznf/need_clear_google_colab_for_fine_tuning_chat/ | Due-Weather-3140 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 18gvznf | false | null | t3_18gvznf | /r/LocalLLaMA/comments/18gvznf/need_clear_google_colab_for_fine_tuning_chat/ | false | false | self | 2 | null |
My attempt at teaching Mixtral basic arithmetic | 3 | I asked Mixtral how many numbers are between 161 and 172, not counting "the borders".
I also asked it to give me a list.
It produced the correct list, but it claimed there were 20 numbers in between.
So I tried again, this time telling it to produce the list, add a counter, start with 1, and then "count on... | 2023-12-12T20:10:33 | https://www.reddit.com/r/LocalLLaMA/comments/18gv419/my_attempt_at_teaching_mixtral_basic_arithmetic/ | hugo-the-second | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 18gv419 | false | null | t3_18gv419 | /r/LocalLLaMA/comments/18gv419/my_attempt_at_teaching_mixtral_basic_arithmetic/ | false | false | 3 | null | |
LLMs and SQL | 6 | My goal is to create a LLM that will be able to execute SQL queries on my db with consistent accuracy. Some of the queries seem too advanced for llms right now.
I've tried many of the different ones out there but nothing is as good as chatgpt 4. But each API call is too expensive for what I'm doing.
I've provided the... | 2023-12-12T19:57:45 | https://www.reddit.com/r/LocalLLaMA/comments/18gut2v/llms_and_sql/ | sharpnation | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 18gut2v | false | null | t3_18gut2v | /r/LocalLLaMA/comments/18gut2v/llms_and_sql/ | false | false | self | 6 | null |
Mistral 7B v0.2 Q5_K_M | 16 | This GGUF works very well for smaller setups. with just 16GB M1 Pro it gets roughly ~10t/s and very good context length. | 2023-12-12T19:26:21 | https://www.reddit.com/r/LocalLLaMA/comments/18gu2cz/mistral_7b_v02_q5_k_m/ | cm8t | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 18gu2cz | false | null | t3_18gu2cz | /r/LocalLLaMA/comments/18gu2cz/mistral_7b_v02_q5_k_m/ | false | false | self | 16 | null |
How in the hell is this possible? | 1 | 2023-12-12T19:24:32 | HellIsParadise | i.redd.it | 1970-01-01T00:00:00 | 0 | {} | 18gu0wo | false | null | t3_18gu0wo | /r/LocalLLaMA/comments/18gu0wo/how_in_the_hell_is_this_possible/ | false | false | 1 | {'enabled': True, 'images': [{'id': 'mnDekcTiOC25mviLXP9_EVIHuGmQA4CDpzh-cIzGXUA', 'resolutions': [{'height': 64, 'url': 'https://preview.redd.it/joa6xz640x5c1.jpeg?width=108&crop=smart&auto=webp&s=787f60a80ea0864d04b9eecf73c93af015bcd7d3', 'width': 108}, {'height': 129, 'url': 'https://preview.redd.it/joa6xz640x5c1.jp... | |||
Mixtral 8x7b performance question | 8 | Everyone says that this custom model is more powerful than the Llama 70b. On what basis does it provide this power? If I understand correctly, only 2 models out of 8 available inside can function at the same time. Does the total number of parameters of all models mean something to the intelligence of the model? I use a... | 2023-12-12T19:23:35 | https://www.reddit.com/r/LocalLLaMA/comments/18gu05j/mixtral_8x7b_performance_question/ | Secret_Joke_2262 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 18gu05j | false | null | t3_18gu05j | /r/LocalLLaMA/comments/18gu05j/mixtral_8x7b_performance_question/ | false | false | self | 8 | null |
Help me get started | 2 | I have a laptop with a Ryzen 7 5700U, 16 GB ram, running Fedora 38 linux.
I'm looking to run a local uncensored LLM, I'd like to know what would be the best model and software to run it.
I'm currently running KoboldAI and Erebus 2.7b. It's okay in terms of speed, but I'm wondering if there's anything better out the... | 2023-12-12T18:59:12 | https://www.reddit.com/r/LocalLLaMA/comments/18gtf3m/help_me_get_started/ | agoodusername123456 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 18gtf3m | false | null | t3_18gtf3m | /r/LocalLLaMA/comments/18gtf3m/help_me_get_started/ | false | false | self | 2 | null |
Prolog language proposal for next Mixture of Experts model | 7 | Two days ago, I tried asking several language models on Poe.com, the [Wolf, Goat, and Cabbage problem](https://en.wikipedia.org/wiki/Wolf,_goat_and_cabbage_problem). When I asked them the problem in the original plain English form, none of them could get it right. Mixstral 7b actually went into an infinite loop when ... | 2023-12-12T18:36:32 | https://www.reddit.com/r/LocalLLaMA/comments/18gsvu0/prolog_language_proposal_for_next_mixture_of/ | petrus4 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 18gsvu0 | false | null | t3_18gsvu0 | /r/LocalLLaMA/comments/18gsvu0/prolog_language_proposal_for_next_mixture_of/ | false | false | self | 7 | null |
HF Leaderboard considered harmful (for chat)? | 78 | This has been bothering me lately.
Every benchmark used on the HF Leaderboard, as far as I know, **does not take the expected prompt format of the model into account.**
This isn't really news - we knew this already. And it goes without saying that this can cause misleading results. **But I think there's an even worse... | 2023-12-12T18:32:14 | https://www.reddit.com/r/LocalLLaMA/comments/18gss5q/hf_leaderboard_considered_harmful_for_chat/ | its_just_andy | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 18gss5q | false | null | t3_18gss5q | /r/LocalLLaMA/comments/18gss5q/hf_leaderboard_considered_harmful_for_chat/ | false | false | self | 78 | {'enabled': False, 'images': [{'id': 'f-Er2nh8Xt_YPyZ8le6GRHTfsR8EEtNIQE7W_Ea98Kw', 'resolutions': [{'height': 58, 'url': 'https://external-preview.redd.it/8cNFhKRvnMLhSF_I-JZvEn7pPt-P79iUIxKSuSYjwUQ.jpg?width=108&crop=smart&auto=webp&s=80a187ff989ccc5449f757c2e367667d58a885e6', 'width': 108}, {'height': 116, 'url': 'h... |
FastAI Jeremy Howard started a For Profit (Pro OS) R&D lab | 5 | 2023-12-12T18:28:46 | https://www.answer.ai/ | dulldata | answer.ai | 1970-01-01T00:00:00 | 0 | {} | 18gsp5h | false | null | t3_18gsp5h | /r/LocalLLaMA/comments/18gsp5h/fastai_jeremy_howard_started_a_for_profit_pro_os/ | false | false | 5 | {'enabled': False, 'images': [{'id': 'IxRN5t4FxciY24AQQblE2wZ0GjsgKY-0hcv89z_nc3U', 'resolutions': [{'height': 93, 'url': 'https://external-preview.redd.it/Jcj7cjQxb3IqOj4bP6My_XxFQz6ZW3AmZuxUQ1txJh4.jpg?width=108&crop=smart&auto=webp&s=4c84c216938a1b958c448fdd958a69e537816432', 'width': 108}, {'height': 186, 'url': 'h... | ||
Learning from using AutoGen (with fn calls) with Mistral 7B Finetunes | 6 | [removed] | 2023-12-12T18:27:59 | https://www.reddit.com/r/LocalLLaMA/comments/18gsoit/learning_from_using_autogen_with_fn_calls_with/ | YourTechBud | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 18gsoit | false | null | t3_18gsoit | /r/LocalLLaMA/comments/18gsoit/learning_from_using_autogen_with_fn_calls_with/ | false | false | default | 6 | {'enabled': False, 'images': [{'id': 'F00Hp_fn94hmZToVZeLnAW6-jVIURgxoiw1rN8IWMk4', 'resolutions': [{'height': 54, 'url': 'https://external-preview.redd.it/q_is5pemwqkWrp44IbXJD5na5aHaCPKNP6DdjGiLSgY.jpg?width=108&crop=smart&auto=webp&s=fbb145ad0a0a0c85339238d2107d22ece0fb316a', 'width': 108}, {'height': 108, 'url': 'h... |
Mixtral on 32GB MacBook | 3 | 2023-12-12T18:23:49 | https://www.linkedin.com/posts/srinivasbilla_just-over-a-year-ago-chatgpt-was-released-activity-7140394113215946753-SqsY?utm_source=share&utm_medium=member_android | Eastwindy123 | linkedin.com | 1970-01-01T00:00:00 | 0 | {} | 18gsl4r | false | null | t3_18gsl4r | /r/LocalLLaMA/comments/18gsl4r/mixtral_on_32gb_macbook/ | false | false | 3 | {'enabled': False, 'images': [{'id': 'tPht6daKXQSAVxAv1OJw4TjlxtoSAv4S0Z_HDWX8rro', 'resolutions': [{'height': 67, 'url': 'https://external-preview.redd.it/ukBbuf0Xue1X4mT4jF-AB-y9VSPsRxyuJ9E1pvEWdZA.jpg?width=108&crop=smart&auto=webp&s=44e142bb79c3612efeeacdecca8ce41368001005', 'width': 108}, {'height': 134, 'url': 'h... | ||
Mixtral on 32GB MacBook with LM Studio | 1 | https://www.linkedin.com/posts/srinivasbilla_just-over-a-year-ago-chatgpt-was-released-activity-7140394113215946753-SqsY?utm_source=share&utm_medium=member_android | 2023-12-12T18:23:01 | https://www.reddit.com/r/LocalLLaMA/comments/18gskej/mixtral_on_32gb_macbook_with_lm_studio/ | Eastwindy123 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 18gskej | false | null | t3_18gskej | /r/LocalLLaMA/comments/18gskej/mixtral_on_32gb_macbook_with_lm_studio/ | false | false | self | 1 | {'enabled': False, 'images': [{'id': 'tPht6daKXQSAVxAv1OJw4TjlxtoSAv4S0Z_HDWX8rro', 'resolutions': [{'height': 67, 'url': 'https://external-preview.redd.it/ukBbuf0Xue1X4mT4jF-AB-y9VSPsRxyuJ9E1pvEWdZA.jpg?width=108&crop=smart&auto=webp&s=44e142bb79c3612efeeacdecca8ce41368001005', 'width': 108}, {'height': 134, 'url': 'h... |
Llama2 13b vs 70b | 3 | Hey there, I'm currently in the process of building a website which uses LlamaAI to write a brief response to any question. Kind of like an AI search engine. I know Llama2 isn't really the most accurate AI, so I'm working on an internet connection and researching system for it. Ignoring that, since I'm currently using ... | 2023-12-12T18:21:08 | https://www.reddit.com/r/LocalLLaMA/comments/18gsitu/llama2_13b_vs_70b/ | kaiwestwood | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 18gsitu | false | null | t3_18gsitu | /r/LocalLLaMA/comments/18gsitu/llama2_13b_vs_70b/ | false | false | self | 3 | null |
Any 7xB gguf models for scientific enquiry | 4 | My system can run to 70 B model reasonably well but just wondering if there's any 7xB gguf models for scientific enquiry, Ie. Based on scientific papers. Thanks | 2023-12-12T18:15:13 | https://www.reddit.com/r/LocalLLaMA/comments/18gsduw/any_7xb_gguf_models_for_scientific_enquiry/ | Useful_Distance4325 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 18gsduw | false | null | t3_18gsduw | /r/LocalLLaMA/comments/18gsduw/any_7xb_gguf_models_for_scientific_enquiry/ | false | false | self | 4 | null |
Clinical RAG for Colonoscopy Detail Extraction? | 4 | I am trying to extract specific details about colonoscopy procedures from about 75k procedure notes. First I would like to use unstructured text to make sure the procedure was a colonoscopy. Colonoscopy could be stated in a number of different ways and combined with other procedures. Not able to do this with structure... | 2023-12-12T18:09:48 | https://www.reddit.com/r/LocalLLaMA/comments/18gs95t/clinical_rag_for_colonoscopy_detail_extraction/ | yelirkram | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 18gs95t | false | null | t3_18gs95t | /r/LocalLLaMA/comments/18gs95t/clinical_rag_for_colonoscopy_detail_extraction/ | false | false | self | 4 | null |
How to stop the fine-tuned Mistral 7B model from generating infinitely ? | 3 | It always generates to max\_tokens parameter, this results in sentence break, basically model doesn’t know when to stop. How to fix this? | 2023-12-12T18:04:09 | https://www.reddit.com/r/LocalLLaMA/comments/18gs4k5/how_to_stop_the_finetuned_mistral_7b_model_from/ | hi_there_bitch | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 18gs4k5 | false | null | t3_18gs4k5 | /r/LocalLLaMA/comments/18gs4k5/how_to_stop_the_finetuned_mistral_7b_model_from/ | false | false | self | 3 | null |
Does ctransformers have multi gpu support? | 2 | I know it works with a single gpu, but I am wondering if it is worth it to get another gpu for my box...or if i should switch my code over to use another backend? | 2023-12-12T17:44:34 | https://www.reddit.com/r/LocalLLaMA/comments/18gro4j/does_ctransformers_have_multi_gpu_support/ | natural_language_guy | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 18gro4j | false | null | t3_18gro4j | /r/LocalLLaMA/comments/18gro4j/does_ctransformers_have_multi_gpu_support/ | false | false | self | 2 | null |
Mistral-Medium coding a game got it on the first try | 41 | 2023-12-12T17:35:23 | https://twitter.com/skirano/status/1734612606055338383 | eunumseioquescrever | twitter.com | 1970-01-01T00:00:00 | 0 | {} | 18grg2k | false | {'oembed': {'author_name': 'Pietro Schirano', 'author_url': 'https://twitter.com/skirano', 'cache_age': 3153600000, 'height': None, 'html': '<blockquote class="twitter-video"><p lang="en" dir="ltr">Guys... Mistral-Medium is really good 😳 <br><br>It coded a functional game on the first try.<br><br>Sure, the game isn... | t3_18grg2k | /r/LocalLLaMA/comments/18grg2k/mistralmedium_coding_a_game_got_it_on_the_first/ | false | false | 41 | {'enabled': False, 'images': [{'id': 'tSkPubNoHFe9y6qTDLG6NzEyUcKj4lbV5St5pxpWrbU', 'resolutions': [{'height': 67, 'url': 'https://external-preview.redd.it/E2BSEO1wlx8L5zQ_HL2Zq37qP3TjbXC4EsiXi5rdEkk.jpg?width=108&crop=smart&auto=webp&s=79382d90a2e06d900ebb11d13e8f35255998eb8f', 'width': 108}], 'source': {'height': 88,... | ||
Phi-2: The surprising power of small language models | 197 | 2023-12-12T17:28:46 | https://www.microsoft.com/en-us/research/blog/phi-2-the-surprising-power-of-small-language-models/ | super-helper | microsoft.com | 1970-01-01T00:00:00 | 0 | {} | 18gra6c | false | null | t3_18gra6c | /r/LocalLLaMA/comments/18gra6c/phi2_the_surprising_power_of_small_language_models/ | false | false | 197 | {'enabled': False, 'images': [{'id': 'agPFP5kd4PBerXRDww4mkQus2VON_UqRYy51eqVhhcM', 'resolutions': [{'height': 56, 'url': 'https://external-preview.redd.it/dJvUxa2hjLA1MGRjIOLReL1zUoy_7_Yx3AfN-AfxIQg.jpg?width=108&crop=smart&auto=webp&s=bbc5a4a1f179de80f3befb3edd0853f230660078', 'width': 108}, {'height': 112, 'url': 'h... | ||
Easy highly reproducible way to try mixtral with llama.cpp using Linux without docker overhead | 6 | Just tried this out on a number of different nvidia machines and it works flawlessly. This is nvidia specific, but there are other versions IIRC:
1. Install Nix (See [here](https://zero-to-nix.com/start/install) for install information, alternate methods, supported systems, etc)
```
curl --proto '=https' --tlsv1.2 -... | 2023-12-12T17:27:07 | https://www.reddit.com/r/LocalLLaMA/comments/18gr8tk/easy_highly_reproducible_way_to_try_mixtral_with/ | paretoOptimalDev | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 18gr8tk | false | null | t3_18gr8tk | /r/LocalLLaMA/comments/18gr8tk/easy_highly_reproducible_way_to_try_mixtral_with/ | false | false | self | 6 | null |
Mixtral-Instruct now on Perplexity Labs | 18 | Perplexity Labs now serves Mixtral-Instruct. Check it out at http://labs.perplexity.ai. | 2023-12-12T16:47:09 | LankyZookeepergame76 | i.redd.it | 1970-01-01T00:00:00 | 0 | {} | 18gqa70 | false | null | t3_18gqa70 | /r/LocalLLaMA/comments/18gqa70/mixtralinstruct_now_on_perplexity_labs/ | false | false | 18 | {'enabled': True, 'images': [{'id': 'LZEF_yYI2TEn9UWJz6R1y5EQRaLBHoQ3Ihd6JQVgAgM', 'resolutions': [{'height': 166, 'url': 'https://preview.redd.it/15jfk5z48w5c1.jpeg?width=108&crop=smart&auto=webp&s=106d55acd2d9ff69fcce1777d4429c3b6b368737', 'width': 108}, {'height': 333, 'url': 'https://preview.redd.it/15jfk5z48w5c1.j... | ||
Marcoroni-7B-v3 is the best 7b model on the Open LLM Leaderboard - who is AIDC AI-Business? | 16 | 2023-12-12T16:44:14 | https://huggingface.co/AIDC-ai-business/Marcoroni-7B-v3 | niutech | huggingface.co | 1970-01-01T00:00:00 | 0 | {} | 18gq7t6 | false | null | t3_18gq7t6 | /r/LocalLLaMA/comments/18gq7t6/marcoroni7bv3_is_the_best_7b_model_on_the_open/ | false | false | 16 | {'enabled': False, 'images': [{'id': 'hmF-uKvVwMgW4ezY5tcRPLEXGqfZa8Sn3-MEkJqjrdY', 'resolutions': [{'height': 58, 'url': 'https://external-preview.redd.it/EnEA57oCplpMlDvQyFjUtFGbwKhseVUwuf9-i-JJ3nM.jpg?width=108&crop=smart&auto=webp&s=3e0c0116ae4ff6d4c77e96cab4719fbf30fc7799', 'width': 108}, {'height': 116, 'url': 'h... | ||
Upload a Lora on huggingface | 2 | Hi!
I've made a qLora of a mistral 7b finetune with oobabooga, is there a way to upload it on huggingface and deploy it to an endpoint?
When I click on the "new model" tab It seems like I can only choose between a base template or a stable-diffusion Lora template, but not a "llm lora".
Should I just ri-upload the w... | 2023-12-12T16:30:56 | https://www.reddit.com/r/LocalLLaMA/comments/18gpwpw/upload_a_lora_on_huggingface/ | C080 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 18gpwpw | false | null | t3_18gpwpw | /r/LocalLLaMA/comments/18gpwpw/upload_a_lora_on_huggingface/ | false | false | self | 2 | null |
Mixtral 4bit on ~28 GB VRAM | 7 | Just sharing this if anyone finds it useful to run mixtral on roughly 1/2 an A6000. Takes about 1-2 minutes to first token and is significantly slower (10 tokens/s vs >40 tokens/s) than 7b-instruct but still usable
[https://huggingface.co/mobiuslabsgmbh/Mixtral-8x7B-Instruct-v0.1-hf-4bit\_g64-HQQ](https://huggingfac... | 2023-12-12T16:02:13 | https://www.reddit.com/r/LocalLLaMA/comments/18gp8ay/mixtral_4bit_on_28_gb_vram/ | chris_myzel | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 18gp8ay | false | null | t3_18gp8ay | /r/LocalLLaMA/comments/18gp8ay/mixtral_4bit_on_28_gb_vram/ | false | false | self | 7 | {'enabled': False, 'images': [{'id': 'aIsLs6gqZTnGnTm_v_m1JaLpGwYnN0_l81U0PyQafV0', 'resolutions': [{'height': 58, 'url': 'https://external-preview.redd.it/uwZpKhNXch__-wbpPWuGoq4-TDw8n5TmpOwsc8No_U4.jpg?width=108&crop=smart&auto=webp&s=8e72e40bff733fd4806b03132c5ece4766342396', 'width': 108}, {'height': 116, 'url': 'h... |
Questions about merged 7b models | 6 | Hey! just a regular user of LLMs here
You probably seen this recently, a lot of 7B merged models getting very high scores and ranking higher than many 70B models in the leaderboard, I don't have a problem with that or the technical expertise to verify them thouroughly, but I have some questions.
* Does merging affect... | 2023-12-12T15:57:57 | https://www.reddit.com/r/LocalLLaMA/comments/18gp4gu/questions_about_merged_7b_models/ | benados | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 18gp4gu | false | null | t3_18gp4gu | /r/LocalLLaMA/comments/18gp4gu/questions_about_merged_7b_models/ | false | false | self | 6 | null |
Performance specsheet for different GPUs | 5 | ​
|GPU Model|Memory|Memory Bandwidth|Peak FP64|Peak FP32|Peak FP16 Tensor Core|Peak INT8 Tensor Core|
|:-|:-|:-|:-|:-|:-|:-|
|NVIDIA A100 (40GB)|40GB HBM2e|1,555 GB/s|9.7 TF|19.5 TF|312 TF|624 TOPS|
|NVIDIA A100 (80GB)|80GB HBM2e|2,039 GB/s|9.7 TF|19.5 TF|312 TF|624 TOPS|
|NVIDIA A10G|24GB GDDR6|600 GB/s|unknow... | 2023-12-12T15:45:18 | https://www.reddit.com/r/LocalLLaMA/comments/18gotzk/performance_specsheet_for_different_gpus/ | phoneixAdi | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 18gotzk | false | null | t3_18gotzk | /r/LocalLLaMA/comments/18gotzk/performance_specsheet_for_different_gpus/ | false | false | self | 5 | null |
Unable to access model through lmstudio | 1 | Hello everyone,
I am trying to use LMstudio, but I cannot download any model through LMstudio.
I have attached screenshots for reference.
The same thing happens when I search for a model. It says to check your internet connection. What am I missing?
https://preview.redd.it/qxdrexbavv5c1.png?width=1920&format=png... | 2023-12-12T15:37:02 | https://www.reddit.com/r/LocalLLaMA/comments/18gon4t/unable_to_access_model_through_lmstudio/ | kamranali406 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 18gon4t | false | null | t3_18gon4t | /r/LocalLLaMA/comments/18gon4t/unable_to_access_model_through_lmstudio/ | false | false | 1 | null | |
Unrestricted GPT! | 2 | HackAIGC's goal is to build the **Most Stable Unrestricted GPT,** unlocking the full potential of AI. If you encounter any situations where replies are denied during usage, feel free to provide feedback to us.
site:[https://www.hackaigc.com/](https://www.hackaigc.com/)
https://preview.redd.it/dxydnhdxuv5c1.png?width... | 2023-12-12T15:35:23 | https://www.reddit.com/r/LocalLLaMA/comments/18gols1/unrestricted_gpt/ | Capta1n_O | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 18gols1 | false | null | t3_18gols1 | /r/LocalLLaMA/comments/18gols1/unrestricted_gpt/ | false | false | 2 | null | |
gtx 1070 8gb for 7b models? | 1 | Dear all, I am considering an offer of a Zotac card GeForce 1070 8gb. My system is a i5-4460 with 16 gb ram. Board B85M. My system is very old, it is weak and I dont have much money. My goal is to speed up inferencing and the generation of content in 7b models. So far I've been working cpu only, but I want to includ... | 2023-12-12T15:31:27 | https://www.reddit.com/r/LocalLLaMA/comments/18goijj/gtx_1070_8gb_for_7b_models/ | Scared-Virus-3463 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 18goijj | false | null | t3_18goijj | /r/LocalLLaMA/comments/18goijj/gtx_1070_8gb_for_7b_models/ | false | false | self | 1 | null |
Variance calculator for LLMs | 2 | Even with very low temperature the response from LLMs(particularly for tasks demanding long outputs) is not deterministic. This can be tricky when you run the solution for critical tasks but get completely different output on re running it, but the difficulty lies when one of the responses is correct and the other is n... | 2023-12-12T15:15:43 | https://www.reddit.com/r/LocalLLaMA/comments/18go5tq/variance_calculator_for_llms/ | todaysgamer | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 18go5tq | false | null | t3_18go5tq | /r/LocalLLaMA/comments/18go5tq/variance_calculator_for_llms/ | false | false | self | 2 | null |
Huggingface now supports AMD ROCm! | 102 | For those like myself that have struggled to get AMD inference running locally on Windows, this may be your lucky day. Below is the git for the new transformers release.
https://github.com/huggingface/transformers/releases/tag/v4.36.0?utm_source=tldrai | 2023-12-12T15:09:54 | https://www.reddit.com/r/LocalLLaMA/comments/18go16o/huggingface_now_supports_amd_rocm/ | FlexMeta | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 18go16o | false | null | t3_18go16o | /r/LocalLLaMA/comments/18go16o/huggingface_now_supports_amd_rocm/ | false | false | self | 102 | {'enabled': False, 'images': [{'id': 'OFFfDuKCpuZC7hkinbJk9jLAz7slD03KmkSbhkQ8Iho', 'resolutions': [{'height': 54, 'url': 'https://external-preview.redd.it/xh0f8Js4NWEkpN7clx97dQ2BnXq33ylFZUcSbg154wc.jpg?width=108&crop=smart&auto=webp&s=7b4d52be75b9a9da3bf37b0dd87eef46b6e7f49c', 'width': 108}, {'height': 108, 'url': 'h... |
Running the newest Mistral model on RTX 4090? | 1 | I've heard a new model as good as GPT 3.5 and locally just came out? Can it run on a 4090? Is it available now? Where to download, and how? Do any of you have it? Is it unscensored? Is the 7b model, the new one with masters, or the instruct model? Need some help and clear up. | 2023-12-12T15:01:36 | https://www.reddit.com/r/LocalLLaMA/comments/18gnu9e/running_the_newest_mistral_model_on_rtx_4090/ | Sakura9095 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 18gnu9e | false | null | t3_18gnu9e | /r/LocalLLaMA/comments/18gnu9e/running_the_newest_mistral_model_on_rtx_4090/ | false | false | self | 1 | null |
Desktop APP that uses API | 2 | I have 2 linux servers hosting LLMs that I can access via their web interfaces with no issues currently. What I would like to find is desktop apps that can access those servers and provide useful features to my desktop environment. Things like Copilot from github, and an Outlook plugin that helps sorting and classify... | 2023-12-12T14:56:24 | https://www.reddit.com/r/LocalLLaMA/comments/18gnpxj/desktop_app_that_uses_api/ | ccbadd | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 18gnpxj | false | null | t3_18gnpxj | /r/LocalLLaMA/comments/18gnpxj/desktop_app_that_uses_api/ | false | false | self | 2 | null |
llama.cpp question: Am I starting my server right? | 4 | ./server -ngl 1 --threads 5 -m /path/to/neuralhermes-2.5-mistral-7b.Q8\_0.gguf -c 2048
I go to port 8080 and it loads the settings and I can start chats there. The responses are non-related to the prompt though. Thinking it was my settings, i tried using the api on sillytavern. It connects. When i send an input into ... | 2023-12-12T14:47:36 | https://www.reddit.com/r/LocalLLaMA/comments/18gnj11/llamacpp_question_am_i_starting_my_server_right/ | multiverse_fan | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 18gnj11 | false | null | t3_18gnj11 | /r/LocalLLaMA/comments/18gnj11/llamacpp_question_am_i_starting_my_server_right/ | false | false | self | 4 | null |
GT 730 - Any way to use it? | 1 | Hi, all,
I've been trying to use my GT 730 with a locally-hosted LLM in Windows. The card supports CUDA 9.1 with driver version 388.19. I tried adjusting requirements for text-generation-webui to try and use relevant versions ([https://download.pytorch.org/whl/cu91/torch/](https://download.pytorch.org/whl/cu91/torch/)... | 2023-12-12T14:46:26 | https://www.reddit.com/r/LocalLLaMA/comments/18gni27/gt_730_any_way_to_use_it/ | Upset_Acanthaceae_18 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 18gni27 | false | null | t3_18gni27 | /r/LocalLLaMA/comments/18gni27/gt_730_any_way_to_use_it/ | false | false | self | 1 | null |
I can't stand the AI not having its own opinion | 101 | It's just terribile, basically you can convince the AI of anything about every topic. I was able to change Bard opinion about the war in Ukraine how many times I wanted. Every AI I know it's just too condescending, I hate it. I want an AI that analyze the world and has its own idea even if it means creating a freaking ... | 2023-12-12T14:46:17 | https://www.reddit.com/r/LocalLLaMA/comments/18gnhy6/i_cant_stand_the_ai_not_having_its_own_opinion/ | Loxli | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 18gnhy6 | false | null | t3_18gnhy6 | /r/LocalLLaMA/comments/18gnhy6/i_cant_stand_the_ai_not_having_its_own_opinion/ | false | false | self | 101 | null |
the best LLm lodel that can work on rtx 3050 4gb vram | 3 | i have an rtx 3050 and i want an llm that can help with basic things like copywriting and summarization , also is there anyone test an llm on a 3050 | 2023-12-12T14:36:37 | https://www.reddit.com/r/LocalLLaMA/comments/18gnaba/the_best_llm_lodel_that_can_work_on_rtx_3050_4gb/ | mbakagi | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 18gnaba | false | null | t3_18gnaba | /r/LocalLLaMA/comments/18gnaba/the_best_llm_lodel_that_can_work_on_rtx_3050_4gb/ | false | false | self | 3 | null |
🤗 DeciLM-7b, the new 7b kid in town! 🤗 | 140 | Deci AI just released DeciLM-7b and DeciLM-7b-instruct.
It is up to 4.4x times faster than Mistral with Deci's inference engine (Infery LLM).
A live demo is available at [https://console.deci.ai/infery-llm-demo](https://console.deci.ai/infery-llm-demo)
Average accuracy: 63.19,
Throughput with Infery-LLM: 1,370 ... | 2023-12-12T14:33:14 | https://www.reddit.com/r/LocalLLaMA/comments/18gn7mo/decilm7b_the_new_7b_kid_in_town/ | cov_id19 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 18gn7mo | false | null | t3_18gn7mo | /r/LocalLLaMA/comments/18gn7mo/decilm7b_the_new_7b_kid_in_town/ | false | false | self | 140 | null |
Where do I start? - Leverage LLM to standardize report writing tone | 1 | My company writes expert reports. Those are written in specific and factual language. Multiple people can contribute to writing a report. Multiple different groups of people write reports.
We are actively trying to have a company tone. Currently, we have reviewers who rewrite and standardize the tone. I have years of ... | 2023-12-12T14:32:53 | https://www.reddit.com/r/LocalLLaMA/comments/18gn7cg/where_do_i_start_leverage_llm_to_standardize/ | theorize7044 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 18gn7cg | false | null | t3_18gn7cg | /r/LocalLLaMA/comments/18gn7cg/where_do_i_start_leverage_llm_to_standardize/ | false | false | self | 1 | null |
Deploy your own inference endpoint of Mistral 7B Instruct v0.1 - GGUF | 1 | 2023-12-12T14:29:06 | https://github.com/OutofAi/ChitChat | TerryCrewsHasacrew | github.com | 1970-01-01T00:00:00 | 0 | {} | 18gn47d | false | null | t3_18gn47d | /r/LocalLLaMA/comments/18gn47d/deploy_your_own_inference_endpoint_of_mistral_7b/ | false | false | 1 | {'enabled': False, 'images': [{'id': 'CusO7PGIhn3-0xNIP8g9L0DRleKbD-mtSVdctjdPGFk', 'resolutions': [{'height': 54, 'url': 'https://external-preview.redd.it/8MQ9N1GzGBY5vlJiOPvkcIwgVHm-fSxw6tIYlNk-M44.jpg?width=108&crop=smart&auto=webp&s=8bd94bb8425cc92696fbddd88cb72f6aee7127ef', 'width': 108}, {'height': 108, 'url': 'h... | ||
DeciLM-7b | 2 | 2023-12-12T14:28:02 | https://console.deci.ai/infery-llm-demo | cov_id19 | console.deci.ai | 1970-01-01T00:00:00 | 0 | {} | 18gn3dz | false | null | t3_18gn3dz | /r/LocalLLaMA/comments/18gn3dz/decilm7b/ | false | false | default | 2 | null | |
Mitral is not GPT 3.5 quality, contrary to popular belief it struggles. | 1 | 2023-12-12T14:22:04 | Bitcoin_100k | i.imgur.com | 1970-01-01T00:00:00 | 0 | {} | 18gmysl | false | null | t3_18gmysl | /r/LocalLLaMA/comments/18gmysl/mitral_is_not_gpt_35_quality_contrary_to_popular/ | false | false | 1 | {'enabled': True, 'images': [{'id': '5q5Rs62N0_HNwN8cVIJof7My1UHN68apc1JOlBpUfiU', 'resolutions': [{'height': 75, 'url': 'https://external-preview.redd.it/Xuyb8YByhsQcVn1glVPvukk7WlU5m9Mq1I_BKuVEcFc.jpg?width=108&crop=smart&auto=webp&s=747f6c4a4fa710dc21c5748c4352f3e6169c236c', 'width': 108}, {'height': 151, 'url': 'ht... | |||
NeurIPS | 1 | Do you know if it’s possible to watch the conference without pay vía streaming or YouTube?
If it’s possible. Recommendations of talks and tutorials/workshops?
Thanks | 2023-12-12T14:19:16 | https://www.reddit.com/r/LocalLLaMA/comments/18gmwm1/neurips/ | ComplexMarionberry27 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 18gmwm1 | false | null | t3_18gmwm1 | /r/LocalLLaMA/comments/18gmwm1/neurips/ | false | false | self | 1 | null |
Build on-premise LLM AI Model | 1 | Hello,
I need to make an estimate to build a local environment to run a model that different users can make requests to (max 20 p).
My problem arises when making an estimate because depending on the size of the model, if it’s 7B or 35B, different graphics cards are recommended. That is, I would like to have a just... | 2023-12-12T14:13:08 | https://www.reddit.com/r/LocalLLaMA/comments/18gms1x/build_onpremise_llm_ai_model/ | CarritosMaister | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 18gms1x | false | null | t3_18gms1x | /r/LocalLLaMA/comments/18gms1x/build_onpremise_llm_ai_model/ | false | false | self | 1 | null |
DeciLM-7B is here! | 66 | 2023-12-12T14:12:32 | https://v.redd.it/kbcv6u5fgv5c1 | datascienceharp | v.redd.it | 1970-01-01T00:00:00 | 0 | {} | 18gmrlz | false | {'reddit_video': {'bitrate_kbps': 5000, 'dash_url': 'https://v.redd.it/kbcv6u5fgv5c1/DASHPlaylist.mpd?a=1704982368%2CZDI1YjFjMzY5OWI0MWEyOTlkMmZkODgwYzBlMWUzNmRkYzk4MDZjZTNhNDU1NTQ2OGY5YThlZWQyMGE4OWVkMg%3D%3D&v=1&f=sd', 'duration': 49, 'fallback_url': 'https://v.redd.it/kbcv6u5fgv5c1/DASH_1080.mp4?source=fallback', 'h... | t3_18gmrlz | /r/LocalLLaMA/comments/18gmrlz/decilm7b_is_here/ | false | false | 66 | {'enabled': False, 'images': [{'id': 'c2t5a2FudmpndjVjMTPOgZYnOxdeutQ_ODagYGhxR8x_iUmuq2A_vOExibTu', 'resolutions': [{'height': 60, 'url': 'https://external-preview.redd.it/c2t5a2FudmpndjVjMTPOgZYnOxdeutQ_ODagYGhxR8x_iUmuq2A_vOExibTu.png?width=108&crop=smart&format=pjpg&auto=webp&s=6523d68217c466907b1ef89f71d30182a0192... |
Subsets and Splits
No community queries yet
The top public SQL queries from the community will appear here once available.