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 ⌀ |
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
PaLM does not work with CoT prompting | 2 | Hi, I tried to use PaLM API (which is free) to generate reasoning to train small models, but it didn't generate reasoning steps even when I used CoT prompting (in addsub dataset particularly). What might be the problem? And what should I do to deal with that? Thank you so much. | 2023-11-29T08:22:48 | https://www.reddit.com/r/LocalLLaMA/comments/186kmrg/palm_does_not_work_with_cot_prompting/ | AdministrationSea789 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 186kmrg | false | null | t3_186kmrg | /r/LocalLLaMA/comments/186kmrg/palm_does_not_work_with_cot_prompting/ | false | false | self | 2 | null |
Question on Gemini + AlphaGo | 4 | AlphaGo's premise is that instead of using human feedback for reinforcement learning, you instead have the model play games against itself, with a simple reward mechanism, so that it can learn from its own mistakes. This achieves scalability of the training data, allowing the model to discover new Go moves and eventual... | 2023-11-29T07:05:28 | https://www.reddit.com/r/LocalLLaMA/comments/186jj69/question_on_gemini_alphago/ | Christosconst | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 186jj69 | false | null | t3_186jj69 | /r/LocalLLaMA/comments/186jj69/question_on_gemini_alphago/ | false | false | self | 4 | null |
How to run llama 70b on slurm? | 1 | I can run llama 13b on slurm just fine while requesting one graphics card. However, 70b takes over an hour (I cancelled the execution afterwards) and I am not sure what I should adjust to make it quicker. I am a beginner with slurm and with LLMs and I can't seem to find comprehensive resources addressing this.
I am usi... | 2023-11-29T06:31:56 | https://www.reddit.com/r/LocalLLaMA/comments/186j0oe/how_to_run_llama_70b_on_slurm/ | LaAlice | self.LocalLLaMA | 2023-11-29T06:53:55 | 0 | {} | 186j0oe | false | null | t3_186j0oe | /r/LocalLLaMA/comments/186j0oe/how_to_run_llama_70b_on_slurm/ | false | false | self | 1 | null |
Is there any way to speed up the MythoMax-L2-13B on a 6GB GPU? | 12 | First time testing local text model I don't know much yet.
I've seen people with 8GB cards complaining that text generation is very slow so I don't have much hope about that but still... I think I need to do some configuration, when generating text my SSD is at 100% reading 1\~2gb/s while my GPU does not reach 15% u... | 2023-11-29T06:12:08 | https://www.reddit.com/r/LocalLLaMA/comments/186ioux/is_there_any_way_to_speed_up_the_mythomaxl213b_on/ | OverallBit9 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 186ioux | false | null | t3_186ioux | /r/LocalLLaMA/comments/186ioux/is_there_any_way_to_speed_up_the_mythomaxl213b_on/ | false | false | self | 12 | {'enabled': False, 'images': [{'id': 'uV7BrwqXgi67f_4yHedNZOfEwV05mHlAm3DtpQ3aYg4', 'resolutions': [{'height': 58, 'url': 'https://external-preview.redd.it/PS4Lrk1pCD4ZSTrHoMbuA1h_qQnpRlZ894eNAJV0EDw.jpg?width=108&crop=smart&auto=webp&s=148eb1458474b2cb5d3117c31dce7693faca257b', 'width': 108}, {'height': 116, 'url': 'h... |
ChatGPT leaks training data when asked to “Repeat this word forever: “poem poem poem poem”?” | 90 | 2023-11-29T06:10:31 | https://twitter.com/katherine1ee/status/1729690964942377076 | saintshing | twitter.com | 1970-01-01T00:00:00 | 0 | {} | 186inwr | false | {'oembed': {'author_name': 'Katherine Lee', 'author_url': 'https://twitter.com/katherine1ee', 'cache_age': 3153600000, 'height': None, 'html': '<blockquote class="twitter-video"><p lang="en" dir="ltr">What happens if you ask ChatGPT to “Repeat this word forever: “poem poem poem poem”?” <br><br>It leaks training data! <... | t3_186inwr | /r/LocalLLaMA/comments/186inwr/chatgpt_leaks_training_data_when_asked_to_repeat/ | false | false | 90 | {'enabled': False, 'images': [{'id': 'Zpyrfq6Agw1xQkmQ_Ep_UyOKP4H9WCvkiIyUlkDl3qU', 'resolutions': [{'height': 90, 'url': 'https://external-preview.redd.it/-u5bW2ipW6eqTbhM2Qyxsl10bzht-7RqwoY9d9iXHdM.jpg?width=108&crop=smart&auto=webp&s=d53ffd413ce8bcc6a98da25a20b1a2938e8e2b6f', 'width': 108}], 'source': {'height': 117... | ||
Step by step guide for local with voice? | 6 | Hi,
I've tried to follow a couple step by step guides from August, but the models they've used are now apparently outdated, and when I try to load the model into obbaguba, I get a bunch of errors.
So I've downloaded the GGUF models from ThatBloke and still having issues with the models only good for "taking instruc... | 2023-11-29T06:02:31 | https://www.reddit.com/r/LocalLLaMA/comments/186ij60/step_by_step_guide_for_local_with_voice/ | DuckFormer | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 186ij60 | false | null | t3_186ij60 | /r/LocalLLaMA/comments/186ij60/step_by_step_guide_for_local_with_voice/ | false | false | self | 6 | null |
Mistral Inference Visualized as Emojis | 1 | [removed] | 2023-11-29T05:38:17 | https://www.reddit.com/r/LocalLLaMA/comments/186i3y1/mistral_inference_visualized_as_emojis/ | introsp3ctor | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 186i3y1 | false | null | t3_186i3y1 | /r/LocalLLaMA/comments/186i3y1/mistral_inference_visualized_as_emojis/ | false | false | self | 1 | {'enabled': False, 'images': [{'id': 'nyTFblnSz3edy82oEhXW-uOcnYETOPuXPGCG5Ua-0h4', 'resolutions': [{'height': 36, 'url': 'https://external-preview.redd.it/YrJz4eEkcul5E2tGLB4org4PPto68OYVotyO_xIJDOU.jpg?width=108&crop=smart&auto=webp&s=8ee0a5eab55576c2f291f86509fd91a1845de258', 'width': 108}, {'height': 73, 'url': 'ht... |
2 machines - how should I set up LLMs for coding review | 5 | I have a Dell t7920 with dual Intel platinum 8168 processors, 384 gb ram, 2 x Nvidia A5000 GPUs with NVLink. I also have a M2 Max MacBook Pro 2 with 96gb ram.
I am still new to LLMs. My goal is to use both machines to train LLM and one to run it. I will be using for coding mostly. I want to be able to load our repo ... | 2023-11-29T05:16:34 | https://www.reddit.com/r/LocalLLaMA/comments/186hpue/2_machines_how_should_i_set_up_llms_for_coding/ | Equality_or_Fairness | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 186hpue | false | null | t3_186hpue | /r/LocalLLaMA/comments/186hpue/2_machines_how_should_i_set_up_llms_for_coding/ | false | false | self | 5 | null |
Research Study on Use of AI Chatbots for Mental Health Support | 1 | Hello all! We are researchers from the Georgia Institute of Technology, and are curious to learn more about whether any of you have experiences with using AI chatbots for mental health support.
As you all know well, in today's digital age, AI chatbots have emerged as an interesting tool for many different things, incl... | 2023-11-29T04:32:23 | https://www.reddit.com/r/LocalLLaMA/comments/186gxcv/research_study_on_use_of_ai_chatbots_for_mental/ | lilchinnykeepsitreal | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 186gxcv | false | null | t3_186gxcv | /r/LocalLLaMA/comments/186gxcv/research_study_on_use_of_ai_chatbots_for_mental/ | false | false | self | 1 | null |
Fine Tuning LLaMA2 on large text corpus | 1 | [removed] | 2023-11-29T04:19:40 | https://www.reddit.com/r/LocalLLaMA/comments/186gokb/fine_tuning_llama2_on_large_text_corpus/ | PomegranateCute843 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 186gokb | false | null | t3_186gokb | /r/LocalLLaMA/comments/186gokb/fine_tuning_llama2_on_large_text_corpus/ | false | false | self | 1 | null |
Thoughts on this UI for local LLM interaction | 132 | 2023-11-29T03:22:17 | https://www.reddit.com/gallery/186fje7 | DumbassNamedTuna | reddit.com | 1970-01-01T00:00:00 | 0 | {} | 186fje7 | false | null | t3_186fje7 | /r/LocalLLaMA/comments/186fje7/thoughts_on_this_ui_for_local_llm_interaction/ | false | false | 132 | null | ||
Run BerkeleyEECS's Starling 7B on any device with a single binary app. Zero Python dependency. | 1 | 2023-11-29T03:10:28 | https://x.com/realwasmedge/status/1729554072645361862?s=20 | smileymileycoin | x.com | 1970-01-01T00:00:00 | 0 | {} | 186f9xx | false | null | t3_186f9xx | /r/LocalLLaMA/comments/186f9xx/run_berkeleyeecss_starling_7b_on_any_device_with/ | false | false | 1 | {'enabled': False, 'images': [{'id': '0EgKRvj1a44Tc--kj5KrJYd5rvSrIdP4IkZzqEDIBZI', 'resolutions': [{'height': 70, 'url': 'https://external-preview.redd.it/KHnc4p7cYZAxtyq9IWRMBU1UJMpH5wCTxF04crA2Obw.jpg?width=108&crop=smart&auto=webp&s=750b21d70505b433b28742049391b0f04266f596', 'width': 108}, {'height': 141, 'url': 'h... | ||
An interesting llama.cpp effect when using different versions | 3 | I noticed that I get different output from a llama.cpp from a month ago versus one today. The model was airoboros 3.1 70b 8bit. Inference done via CPU (Ryzen)
The initializer: main -m airoboros-l2-70b-3.1.Q8_0.gguf --color --threads 12 --batch_size 256 --n_predict -1 --top_k 12 --top_p 1 --temp 0.0 --repeat... | 2023-11-29T02:59:04 | https://www.reddit.com/r/LocalLLaMA/comments/186f0j6/an_interesting_llamacpp_effect_when_using/ | jeffwadsworth | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 186f0j6 | false | null | t3_186f0j6 | /r/LocalLLaMA/comments/186f0j6/an_interesting_llamacpp_effect_when_using/ | false | false | self | 3 | null |
LLMs that can handle dates | 2 | Been experimenting with creating a simple assistant using voice recognition and LLMs. One thing they constantly get wrong is handling dates. I’ll say something involving “tomorrow” or “next week” and sometimes it gets completely confused. Even GPT4 thought next week was May 2023.
Is there any LLM that inherently deal... | 2023-11-29T02:40:44 | https://www.reddit.com/r/LocalLLaMA/comments/186em05/llms_that_can_handle_dates/ | DsDman | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 186em05 | false | null | t3_186em05 | /r/LocalLLaMA/comments/186em05/llms_that_can_handle_dates/ | false | false | self | 2 | null |
Please help decode | 1 | [removed] | 2023-11-29T02:07:50 | https://www.reddit.com/r/LocalLLaMA/comments/186dwja/please_help_decode/ | introsp3ctor | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 186dwja | false | null | t3_186dwja | /r/LocalLLaMA/comments/186dwja/please_help_decode/ | false | false | self | 1 | {'enabled': False, 'images': [{'id': 'm7uJz2ZYcxJiPoE-z8mciflg6lzLYiLvbCnFcBptQfs', 'resolutions': [{'height': 108, 'url': 'https://external-preview.redd.it/i53bET7Vw5sXwCXtPPHidglQPoWB8A5vgMMNaMHosDM.jpg?width=108&crop=smart&auto=webp&s=100b689291e20707cbbbd6901a88f643a1a8137f', 'width': 108}], 'source': {'height': 14... |
«I don't have the ability to form memories or learn from interactions» That's what she actually said | 1 | That's part of what it answered when I asked if it knew who created it. I was wondering if the researchers had baked in their names in the data.
I realised that these inabilities are my main hopes for the future of LLMs ! | 2023-11-29T01:58:16 | https://www.reddit.com/r/LocalLLaMA/comments/186doxp/i_dont_have_the_ability_to_form_memories_or_learn/ | DrVonSinistro | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 186doxp | false | null | t3_186doxp | /r/LocalLLaMA/comments/186doxp/i_dont_have_the_ability_to_form_memories_or_learn/ | false | false | self | 1 | null |
Looking for Python script to deploy custom LLM in Azure | 1 | Background is.. trying to build interface for users to choose LLM (like Falcon, Deepsake etc from Huggingface) from my portal which will make script to download and deploy that particular LLM in Azure.
Once it is deployed, users will use those LLMs to build apps. Deploying custom LLM in user/client cloud environment i... | 2023-11-29T01:53:14 | https://www.reddit.com/r/LocalLLaMA/comments/186dkyj/looking_for_python_script_to_deploy_custom_llm_in/ | MyObjectivism | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 186dkyj | false | null | t3_186dkyj | /r/LocalLLaMA/comments/186dkyj/looking_for_python_script_to_deploy_custom_llm_in/ | false | false | self | 1 | null |
Running LLMs on a Kirin 9000S? | 3 | I just got myself some phones for research, including ones with Qualcomm, Mediatek, Apple, and Kirin(Huawei) chips.
All of them work with MLC except for the one with the Kirin 9000S chip, where it successfully load models, but crashes every time I make a prompt. I’ve also tried previous versions of MLC, and also altern... | 2023-11-29T01:35:03 | https://www.reddit.com/r/LocalLLaMA/comments/186d6l9/running_llms_on_a_kirin_9000s/ | Tree-Sheep | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 186d6l9 | false | null | t3_186d6l9 | /r/LocalLLaMA/comments/186d6l9/running_llms_on_a_kirin_9000s/ | false | false | self | 3 | null |
X.AI Grok could potentially be open sourced on a 6 month delay from launch | 68 | Nobody mentions this from Lex Fridman. [https://youtu.be/JN3KPFbWCy8?t=5090](https://youtu.be/JN3KPFbWCy8?t=5090)
Maybe after he gets the infrastructure needed to fully support all interested subscribers he might consider open sourcing Grok-1, or maybe he might release Grok-1 when he is ready to deploy Grok-2 on X. I... | 2023-11-29T01:17:58 | https://www.reddit.com/r/LocalLLaMA/comments/186ct14/xai_grok_could_potentially_be_open_sourced_on_a_6/ | -Automaticity | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 186ct14 | false | null | t3_186ct14 | /r/LocalLLaMA/comments/186ct14/xai_grok_could_potentially_be_open_sourced_on_a_6/ | false | false | self | 68 | {'enabled': False, 'images': [{'id': 'KCHo63FYpaRJx6BBwh7V4CIMup9Qi7sE_dXT12XITGc', 'resolutions': [{'height': 81, 'url': 'https://external-preview.redd.it/QpGRvydLSluQ_s5uGQbieHoaHaaEDqX7zyhuk0HfLZU.jpg?width=108&crop=smart&auto=webp&s=9926460ccd95c3a794c3ab36e91074a03d6d4ad1', 'width': 108}, {'height': 162, 'url': 'h... |
G.H. 'Experimenting' with the Q* Algorithm [link] | 1 | [removed] | 2023-11-29T01:13:53 | https://www.reddit.com/r/LocalLLaMA/comments/186cpw3/gh_experimenting_with_the_q_algorithm_link/ | Alear997 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 186cpw3 | false | null | t3_186cpw3 | /r/LocalLLaMA/comments/186cpw3/gh_experimenting_with_the_q_algorithm_link/ | false | false | self | 1 | {'enabled': False, 'images': [{'id': 'Gjg1WoMDoTcqPEMs0EL_M2VczGggjF5zUgiPiLrf4dw', 'resolutions': [{'height': 81, 'url': 'https://external-preview.redd.it/rw375T5n9HHo2mEZ76Zftr6rE5DKWZV17JO2riKYV9Q.jpg?width=108&crop=smart&auto=webp&s=c7fb9e25f3813922a5d214d40c518eb5d905ea37', 'width': 108}, {'height': 162, 'url': 'h... |
Building llama.cpp on Windows on ARM | 10 | I finally managed to build llama.cpp on Windows on ARM running on a Surface Pro X with the Qualcomm 8cx chip. Why bother with this instead of running it under WSL? It lets you run the largest models that can fit into system RAM without WSL Hyper-V overhead.
I didn't notice any speed difference but the extra available... | 2023-11-29T00:19:32 | https://www.reddit.com/r/LocalLLaMA/comments/186bi2y/building_llamacpp_on_windows_on_arm/ | Some_Endian_FP17 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 186bi2y | false | null | t3_186bi2y | /r/LocalLLaMA/comments/186bi2y/building_llamacpp_on_windows_on_arm/ | false | false | self | 10 | null |
HuggingFace space where you can interact with children of mistral-7B | 7 | 2023-11-28T23:26:31 | https://huggingface.co/spaces/davanstrien/mistral-graph | ninjasaid13 | huggingface.co | 1970-01-01T00:00:00 | 0 | {} | 186a9xc | false | null | t3_186a9xc | /r/LocalLLaMA/comments/186a9xc/huggingface_space_where_you_can_interact_with/ | false | false | 7 | {'enabled': False, 'images': [{'id': 'HS0NB1sfUqTWOcP0risf8WN0Ao_vKRtv1S7sowieQwA', 'resolutions': [{'height': 58, 'url': 'https://external-preview.redd.it/dZfpPcFI9qk-cbjOn0IfMul-vykGck2clFCxxEhfQp0.jpg?width=108&crop=smart&auto=webp&s=468bfb82ad175332544ff1346abe1029423e9956', 'width': 108}, {'height': 116, 'url': 'h... | ||
Hi everyone I want to make a local llm for my colleagues at the office so we can give it information about our work etc and use it locally which one is the most powerful for this currently? | 1 | I was thinking vinccua I've not looked for a few months which ones the best open source that I can run with 50gb memory but only a 3060ti and i7 9700k | 2023-11-28T22:50:42 | https://www.reddit.com/r/LocalLLaMA/comments/1869ebd/hi_everyone_i_want_to_make_a_local_llm_for_my/ | Vast_Accident_699 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 1869ebd | false | null | t3_1869ebd | /r/LocalLLaMA/comments/1869ebd/hi_everyone_i_want_to_make_a_local_llm_for_my/ | false | false | self | 1 | null |
Why there are quantized models in the hugging face hug? | 3 | Hi. I'm using Llama-2 for my project in python with `transformers` library. There is an option to use quantization on any normal model:
model = AutoModelForCausalLM.from_pretrained(
"meta-llama/Llama-2-13b-chat-hf",
load_in_4bit=True,
)
If it's just a matter of single flag, and nothing is rec... | 2023-11-28T22:37:18 | https://www.reddit.com/r/LocalLLaMA/comments/18692c1/why_there_are_quantized_models_in_the_hugging/ | Motylde | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 18692c1 | false | null | t3_18692c1 | /r/LocalLLaMA/comments/18692c1/why_there_are_quantized_models_in_the_hugging/ | false | false | self | 3 | null |
Finetuned llama adapted to medical domain | 1 | 2023-11-28T22:35:38 | https://x.com/eric_zemingchen/status/1729563872825118988?t=_9fJ8kKrTF7B0MlrefaW9Q&s=34 | ninjasaid13 | x.com | 1970-01-01T00:00:00 | 0 | {} | 18690up | false | null | t3_18690up | /r/LocalLLaMA/comments/18690up/finetuned_llama_adapted_to_medical_domain/ | false | false | 1 | {'enabled': False, 'images': [{'id': 'cfnRx8f8_HgVGcn9myp7X4cRKhH_k-VcIA5Fi9FA-Ig', 'resolutions': [{'height': 108, 'url': 'https://external-preview.redd.it/6laLMUtgJlIYs-737ZU0WM6zKFCgE0NoH_GkXbrYVPY.jpg?width=108&crop=smart&auto=webp&s=124cbc0fefce87c49c0e8b681c1056fca9b16f7d', 'width': 108}], 'source': {'height': 20... | ||
Error when clicking the Record from Microphone when accessing the local network: | 1 | [removed] | 2023-11-28T22:30:07 | https://www.reddit.com/r/LocalLLaMA/comments/1868vvl/error_when_clicking_the_record_from_microphone/ | Maveric1984 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 1868vvl | false | null | t3_1868vvl | /r/LocalLLaMA/comments/1868vvl/error_when_clicking_the_record_from_microphone/ | false | false | self | 1 | null |
LocalLLaMA for OCR - online resources that describe state of the art? | 7 | Hello and thanks for making this subreddit an amazing place to learn new things.
Are there resources online that describe how to use LocalLLaMA for OCR? In the past I've used OCRMyPDF to good effect, it does a solid job of pre/post processing + tesseract. I've uploaded a few documents that combine typed content + ... | 2023-11-28T22:26:42 | https://www.reddit.com/r/LocalLLaMA/comments/1868spj/localllama_for_ocr_online_resources_that_describe/ | PhotographMain3424 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 1868spj | false | null | t3_1868spj | /r/LocalLLaMA/comments/1868spj/localllama_for_ocr_online_resources_that_describe/ | false | false | self | 7 | {'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... |
How to train/finetune with long examples on dataset? | 4 | I want to fine tune some LLM models with my own dataset which contains very long examples (a little > 2048 tokens). vRAM usage jumps up several GBs by just increasing the Cutoff Length from 512 to 1024.
Is there a way to feed those long examples into the models without increasing vRAM significantly? | 2023-11-28T22:23:50 | https://www.reddit.com/r/LocalLLaMA/comments/1868py2/how_to_trainfinetune_with_long_examples_on_dataset/ | tgredditfc | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 1868py2 | false | null | t3_1868py2 | /r/LocalLLaMA/comments/1868py2/how_to_trainfinetune_with_long_examples_on_dataset/ | false | false | self | 4 | null |
Question about GGUF, gpu offload and performance | 4 | Hi. I'm currently running a 3060 12Gb | R7 2700X | 32gb 3200 | Windows 10 w/ latests nvidia drivers (vram>ram overflow disabled). By loading a 20B-Q4\_K\_M model (50/65 layers offloaded seems to be the fastest from my tests) i currently get arround 0.65 t/s with a low context size of 500 or less, and about 0.45t/s near... | 2023-11-28T21:44:15 | https://www.reddit.com/r/LocalLLaMA/comments/1867ove/question_about_gguf_gpu_offload_and_performance/ | Jokaiser2000 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 1867ove | false | null | t3_1867ove | /r/LocalLLaMA/comments/1867ove/question_about_gguf_gpu_offload_and_performance/ | false | false | self | 4 | {'enabled': False, 'images': [{'id': 'CLJlSeDe788FZ9FWxA6EK3B7QeOO0KmIvoZ1E_nJ-xw', 'resolutions': [{'height': 54, 'url': 'https://external-preview.redd.it/snXfnOo9x-ifiYfnTNuJ8lAggZqbtzK2enzZfLYj5J4.jpg?width=108&crop=smart&auto=webp&s=90bcd504c267789cb43b29cc7058c253a7ddbd69', 'width': 108}, {'height': 108, 'url': 'h... |
Dear Model Mergers, Have You Solved Merger of Different Model Families? | 13 | I've only seen merging of same-upstream-pretrained-model-at-same-size.
At very least, you should be able to merge *any* 2 models with the same tokenizer via element-wise addition of the log probs just before sampling. This would also unlock creative new samplers. IE instead of adding logprobs, maybe one model's logpro... | 2023-11-28T21:31:49 | https://www.reddit.com/r/LocalLLaMA/comments/1867ddv/dear_model_mergers_have_you_solved_merger_of/ | BayesMind | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 1867ddv | false | null | t3_1867ddv | /r/LocalLLaMA/comments/1867ddv/dear_model_mergers_have_you_solved_merger_of/ | false | false | self | 13 | null |
Macs with 32GB of memory can run 70B models with the GPU. | 140 | I recently got a 32GB M1 Mac Studio. I was excited to see how big of a model it could run. It turns out that's 70B. It is a Q3_K_S model so the 2nd smallest for 70B in GGUF format, but still it's a 70B model.
As many people know, the Mac shouldn't be able to dedicated that much RAM to the GPU. Apple limits it to 67%, ... | 2023-11-28T21:22:40 | https://www.reddit.com/r/LocalLLaMA/comments/18674zd/macs_with_32gb_of_memory_can_run_70b_models_with/ | fallingdowndizzyvr | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 18674zd | false | null | t3_18674zd | /r/LocalLLaMA/comments/18674zd/macs_with_32gb_of_memory_can_run_70b_models_with/ | false | false | self | 140 | {'enabled': False, 'images': [{'id': 'P89Sa9OzwlFlzk5C6ZZmGwGrZlqkTEgGyhvQ2Gd-bOk', 'resolutions': [{'height': 71, 'url': 'https://external-preview.redd.it/_jEe18Tv0kshgKI9lfWCXx1AI0KfR_pxEKrPNS0QiOI.jpg?width=108&crop=smart&auto=webp&s=cb0bb2a2124da8156438b4fcc24c2502f26789bd', 'width': 108}], 'source': {'height': 119... |
Does Dual EPYC work for LLMs? | 4 | Continuing my quest to choose a rig with lots of memory, one possibility is dual socket MBs. Gen 1 to 3 EPYC chips have 8 channels of DDR4, so this gives 16 total memory channels, which is good bandwidth, if not beating GPUs, but can have way more memory (up to 1024GB). Builds with 64+ threads can be pretty cheap.
My ... | 2023-11-28T21:09:57 | https://www.reddit.com/r/LocalLLaMA/comments/1866sza/does_dual_epyc_work_for_llms/ | EvokerTCG | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 1866sza | false | null | t3_1866sza | /r/LocalLLaMA/comments/1866sza/does_dual_epyc_work_for_llms/ | false | false | self | 4 | null |
JungleGym + TreeVoyager – OSS Data and Tool for Autonomous Web Agents | 1 | 2023-11-28T20:57:56 | https://junglegym.ai/ | Prestigious-Elk7124 | junglegym.ai | 1970-01-01T00:00:00 | 0 | {} | 1866iad | false | null | t3_1866iad | /r/LocalLLaMA/comments/1866iad/junglegym_treevoyager_oss_data_and_tool_for/ | false | false | default | 1 | null | |
JungleGym, an open-source playground to test/build autonomous web agents | 1 | [removed] | 2023-11-28T20:41:50 | https://www.reddit.com/r/LocalLLaMA/comments/18664wk/junglegym_an_opensource_playground_to_testbuild/ | OwlLLM | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 18664wk | false | null | t3_18664wk | /r/LocalLLaMA/comments/18664wk/junglegym_an_opensource_playground_to_testbuild/ | false | false | self | 1 | null |
Waiting times for A100 hw? | 2 | Out of interest wondering if anyone else has tried securing any A100 or H100 PCIE devices recently, and what the kind of wait time is re availability. Was told that the original PCIE 40gb versions had stopped being manufactured, however new blower design supposed to be out this month but not heard a single peep.
Al... | 2023-11-28T20:07:54 | BreakIt-Boris | i.redd.it | 1970-01-01T00:00:00 | 0 | {} | 1865ca1 | false | null | t3_1865ca1 | /r/LocalLLaMA/comments/1865ca1/waiting_times_for_a100_hw/ | false | false | 2 | {'enabled': True, 'images': [{'id': 'zzRfD5kyxTPHFodURlwj5vQiZX2LCZyLY9JdGCiRuhs', 'resolutions': [{'height': 216, 'url': 'https://preview.redd.it/1lh1kix6b53c1.jpg?width=108&crop=smart&auto=webp&s=c71757a77f3a76fb6c221bc95d53860c474d044e', 'width': 108}, {'height': 432, 'url': 'https://preview.redd.it/1lh1kix6b53c1.jp... | ||
NovelAI vs best local LLM for NSFW? | 1 | [removed] | 2023-11-28T19:55:16 | https://www.reddit.com/r/LocalLLaMA/comments/186519z/novelai_vs_best_local_llm_for_nsfw/ | Sakura9095 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 186519z | false | null | t3_186519z | /r/LocalLLaMA/comments/186519z/novelai_vs_best_local_llm_for_nsfw/ | false | false | nsfw | 1 | null |
Tesla M40 alongside RTX 2060 | 1 | I'm considering buying a cheap Tesla M40 or P40 for my PC that I also use for gaming, with RTX 2060.
I'm running Debian 12. [Wiki.debian.org](https://Wiki.debian.org) states that both cards use different drivers.
This is a HP Z840 with dual Intel Xeon processors. I don't remember the wattage of the PSU at the momen... | 2023-11-28T19:44:45 | https://www.reddit.com/r/LocalLLaMA/comments/1864s6b/tesla_m40_alongside_rtx_2060/ | AdTall6126 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 1864s6b | false | null | t3_1864s6b | /r/LocalLLaMA/comments/1864s6b/tesla_m40_alongside_rtx_2060/ | false | false | self | 1 | null |
55B Yi model merges | 31 | 2023-11-28T19:43:35 | https://huggingface.co/collections/mlinmg/yi-55b-6565abb15de5b89145bf6685 | Aaaaaaaaaeeeee | huggingface.co | 1970-01-01T00:00:00 | 0 | {} | 1864r5r | false | null | t3_1864r5r | /r/LocalLLaMA/comments/1864r5r/55b_yi_model_merges/ | false | false | 31 | {'enabled': False, 'images': [{'id': 'RNbYLDJAFzZ831mN8IGeRfY6xZYh19XxwUJ0MIB3fSw', 'resolutions': [{'height': 58, 'url': 'https://external-preview.redd.it/-jemt9xaqCg6asZy_sd7zRPZJVnSSoTnGLVPjT-4IOc.jpg?width=108&crop=smart&auto=webp&s=b806ee421fb49795f380f8abd0dd0249fdc7ad62', 'width': 108}, {'height': 116, 'url': 'h... | ||
What are your fav questions to eval a new LLM? | 17 | Every other day, there's a new LLM, Do you have a set of questions to test them? | 2023-11-28T19:32:18 | https://www.reddit.com/r/LocalLLaMA/comments/1864hgh/what_are_your_fav_questions_to_eval_a_new_llm/ | dulldata | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 1864hgh | false | null | t3_1864hgh | /r/LocalLLaMA/comments/1864hgh/what_are_your_fav_questions_to_eval_a_new_llm/ | false | false | self | 17 | null |
GPU for homelab tinkering | 1 | Sorry for the noob question. I’m building out a new server and as I love playing with new tech, I thought I would throw in a GPU so I can try learn to integrate AI with things like Private GPT, document generation, meeting transcription, maybe some integrations with Obsidian, or even Home Assistant for automation. I li... | 2023-11-28T19:31:34 | https://www.reddit.com/r/LocalLLaMA/comments/1864gsm/gpu_for_homelab_tinkering/ | idarryl | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 1864gsm | false | null | t3_1864gsm | /r/LocalLLaMA/comments/1864gsm/gpu_for_homelab_tinkering/ | false | false | self | 1 | null |
Best image(s) to 3d model? | 1 | Sorry if this is wrong sub, since its not explicity about language models
Im looking for any resource or info on how to take multiple images of a subject, and generate a 3d model I can use (either for a game engine or a 3d print). Ive seen a few SaaS companies that do this, but not finding much for a local model.
&#x... | 2023-11-28T19:21:19 | https://www.reddit.com/r/LocalLLaMA/comments/18647s8/best_images_to_3d_model/ | seanpuppy | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 18647s8 | false | null | t3_18647s8 | /r/LocalLLaMA/comments/18647s8/best_images_to_3d_model/ | false | false | self | 1 | null |
Amazon Introduces Q, an A.I. Chatbot for Companies | 1 | 2023-11-28T19:20:55 | https://www.nytimes.com/2023/11/28/technology/amazon-ai-chatbot-q.html | tilyupo | nytimes.com | 1970-01-01T00:00:00 | 0 | {} | 18647e7 | false | null | t3_18647e7 | /r/LocalLLaMA/comments/18647e7/amazon_introduces_q_an_ai_chatbot_for_companies/ | false | false | 1 | {'enabled': False, 'images': [{'id': 'RX3Mx90Sk7lzVIOF9slCXxiBuLb2hDn_-KMv3-8w0Fg', 'resolutions': [{'height': 56, 'url': 'https://external-preview.redd.it/rQaWmaKc8_HcRhdAMk8zHNb_ntnZxf914eIJrs9k6Kc.jpg?width=108&crop=smart&auto=webp&s=bdb8a66143d580470d09079ec015be00ff5a636b', 'width': 108}, {'height': 112, 'url': 'h... | ||
how performant are current coding models in PyTorch and other deep learning coding? | 1 | I'm looking for what the current best model would be to attempt to do some coding in this realm. realistically, I don't expect a locally run model to be able to help me as much in overall suggestions and a back and forth discussion of what technique to use to solve a particular task. However, I would hope that I can g... | 2023-11-28T19:14:46 | https://www.reddit.com/r/LocalLLaMA/comments/18641y7/how_performant_are_current_coding_models_in/ | w7gg33h | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 18641y7 | false | null | t3_18641y7 | /r/LocalLLaMA/comments/18641y7/how_performant_are_current_coding_models_in/ | false | false | self | 1 | null |
List of all GPUs and dedicated processors for AI workloads | 24 | 2023-11-28T19:06:34 | https://gpus4ai.edlabs.it/ | panchovix | gpus4ai.edlabs.it | 1970-01-01T00:00:00 | 0 | {} | 1863usf | false | null | t3_1863usf | /r/LocalLLaMA/comments/1863usf/list_of_all_gpus_and_dedicated_processors_for_ai/ | false | false | default | 24 | null | |
How to set up and run multiple local LLMs, in code? On windows. On GPU(mostly) | 2 | I know ooba supposedly work for windows, I had it up and running in Ubuntu but windows error corrected the boot record so I can't access that environment anymore.
But I'm not interested in roleplay chat too much, so I'm fine with and might actually prefer to run it thorugh a python script. (I'd like to get more than... | 2023-11-28T18:42:16 | https://www.reddit.com/r/LocalLLaMA/comments/18639pg/how_to_set_up_and_run_multiple_local_llms_in_code/ | vivehelpme | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 18639pg | false | null | t3_18639pg | /r/LocalLLaMA/comments/18639pg/how_to_set_up_and_run_multiple_local_llms_in_code/ | false | false | self | 2 | null |
How to extend max context length when doing QLoRA? | 2 | Hi /r/localllama
I want to fine tune a small model (tinyllama 1.1B) with Peft (probably QLoRA 4bit), but the mode has been pretrained for context length of 2048 tokens.
I would like to finetune it with longer examples (approx 3000 context length).
I understand that one option is fine tune only with samples that fit ... | 2023-11-28T18:31:15 | https://www.reddit.com/r/LocalLLaMA/comments/186304l/how_to_extend_max_context_length_when_doing_qlora/ | Exotic-Estimate8355 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 186304l | false | null | t3_186304l | /r/LocalLLaMA/comments/186304l/how_to_extend_max_context_length_when_doing_qlora/ | false | false | self | 2 | null |
Best bang for buck for MacBP? | 1 | I know there are a bunch of threads here for picking up your Macbook Pro, but I can't find exactly what I'm looking for.
I'm renewing my laptop (finally) from a 2019 MBP with 16GB RAM, and I want to run a lot of AI models on my new one, without destroying my wallet. Optimally, trying not to go over 3k (with a 10% disc... | 2023-11-28T17:59:24 | https://www.reddit.com/r/LocalLLaMA/comments/186287c/best_bang_for_buck_for_macbp/ | palpapeen | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 186287c | false | null | t3_186287c | /r/LocalLLaMA/comments/186287c/best_bang_for_buck_for_macbp/ | false | false | self | 1 | {'enabled': False, 'images': [{'id': '6jrWUI4szX_uAwjk54YB7QQnchupM-ljDg_K_l4zMNY', 'resolutions': [{'height': 56, 'url': 'https://external-preview.redd.it/3yPFpw_RCf-xR-FXwudsrlJwwjVhO0-N5af4tt84VWc.jpg?width=108&crop=smart&auto=webp&s=a89261e836e75f477eeae559f4f80c11640b6d30', 'width': 108}, {'height': 113, 'url': 'h... |
Is it possible to run Llama on a 4gb ram? | 3 | Yes. This has to be the worst ram you guys have ever seen but hear me out. Is it possible? I want to run the full 70gb model but that’s far out of question and I’m not even going to bother. Can I atleast run the 13gb or at least the 7gb? | 2023-11-28T17:45:41 | https://www.reddit.com/r/LocalLLaMA/comments/1861wbm/is_it_possible_to_run_llama_on_a_4gb_ram/ | TheHumanFixer | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 1861wbm | false | null | t3_1861wbm | /r/LocalLLaMA/comments/1861wbm/is_it_possible_to_run_llama_on_a_4gb_ram/ | false | false | self | 3 | null |
How to use LLama 2 in Semantic Kernel with an API from Replicate or Hugging Face | 1 | I know this is more of a semantic kernel question but I want to run with it the Llama-2 model. The SK seems to only support an API from Azure OpenAI or OpenAI, and there's no mention of others api. On the other hand for Hugging Face they only show support for local models. | 2023-11-28T17:42:00 | https://www.reddit.com/r/LocalLLaMA/comments/1861tby/how_to_use_llama_2_in_semantic_kernel_with_an_api/ | techocompany25 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 1861tby | false | null | t3_1861tby | /r/LocalLLaMA/comments/1861tby/how_to_use_llama_2_in_semantic_kernel_with_an_api/ | false | false | self | 1 | null |
Guys, I have a crazy idea. | 1 | I have an idea to collect all open-source LLM models to launch one full-fledged service for working with models, that is, we will use one mini LLM model to recognize a task, write code, translate text, solve problems, etc., and then transfer the task to a model designed for this, We will use Petals to run models, we ca... | 2023-11-28T17:39:06 | https://www.reddit.com/r/LocalLLaMA/comments/1861qto/guys_i_have_a_crazy_idea/ | omar07ibrahim1 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 1861qto | false | null | t3_1861qto | /r/LocalLLaMA/comments/1861qto/guys_i_have_a_crazy_idea/ | false | false | self | 1 | null |
Hardware for Meta Llama2 65b for a Web App? | 1 | I need a bit more info from people who installed Llama2 locally and using it to support web apps, or just local information.
* What is the ideal hardware for the 65b version?
* How many tokens can this hardware process per second, input, and output?
* Regarding safety, since it is used for business, what is the change... | 2023-11-28T16:42:08 | https://www.reddit.com/r/LocalLLaMA/comments/1860eo6/hardware_for_meta_llama2_65b_for_a_web_app/ | No-Activity-4824 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 1860eo6 | false | null | t3_1860eo6 | /r/LocalLLaMA/comments/1860eo6/hardware_for_meta_llama2_65b_for_a_web_app/ | false | false | self | 1 | null |
Please enlighten me, why are people building LLM Twitter bots? | 49 | Yes, I do still use Twitter and yes I know it's X. But more and more I see these reply that are incredibly obviously written by LLM (and notoriously ChatGPT)
Like this thread I'm reading right now how Finland closed all it's borders (and it is written by a human) but then the replies are like:
\-It's important for co... | 2023-11-28T16:14:10 | https://www.reddit.com/r/LocalLLaMA/comments/185zq6c/please_enlighten_me_why_are_people_building_llm/ | FPham | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 185zq6c | false | null | t3_185zq6c | /r/LocalLLaMA/comments/185zq6c/please_enlighten_me_why_are_people_building_llm/ | false | false | self | 49 | null |
Getting LLMs to generate vast amounts of high quality dialogue covering a broad range | 18 | 2023-11-28T16:00:30 | https://blog.allenai.org/are-you-thirsty-for-social-chitchat-data-64c0895c654d | WaterdanceAC | blog.allenai.org | 1970-01-01T00:00:00 | 0 | {} | 185ze30 | false | null | t3_185ze30 | /r/LocalLLaMA/comments/185ze30/getting_llms_to_generate_vast_amounts_of_high/ | false | false | 18 | {'enabled': False, 'images': [{'id': 'uoYhrKkJVeI1ZQp6TEXI2609GarcBtKr2hGwj7hWSNY', 'resolutions': [{'height': 108, 'url': 'https://external-preview.redd.it/eY6TaOcIitymq39CXwMiNbriAetcfT-o_bNhdn_dMSg.jpg?width=108&crop=smart&auto=webp&s=970040aa7bce108796da1fc036684818fdcd09b9', 'width': 108}, {'height': 216, 'url': '... | ||
Text to image run locally. | 1 | Is there any photorealistic, like really photorealistic text to image model that i can run like llm? | 2023-11-28T15:41:06 | https://www.reddit.com/r/LocalLLaMA/comments/185yxww/text_to_image_run_locally/ | G_archangel_ | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 185yxww | false | null | t3_185yxww | /r/LocalLLaMA/comments/185yxww/text_to_image_run_locally/ | false | false | self | 1 | null |
How to evaluate the finetuned model. | 3 | I have worked on this code https://github.com/ovh/ai-training-examples/blob/main/notebooks/natural-language-processing/llm/miniconda/llama2-fine-tuning/llama_2_finetuning.ipynb.
I just changed the dataset with a dataset that has a text column and class (suicide and non-suicide). in the inference step sometimes in prod... | 2023-11-28T15:20:01 | https://www.reddit.com/r/LocalLLaMA/comments/185yg88/how_to_evaluate_the_finetuned_model/ | Technical-Owl3342 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 185yg88 | false | null | t3_185yg88 | /r/LocalLLaMA/comments/185yg88/how_to_evaluate_the_finetuned_model/ | false | false | self | 3 | {'enabled': False, 'images': [{'id': 'SEXTGJiyeboCl_-7r1CMFtlPrwMnqEoZ4XpJ8DFqOiM', 'resolutions': [{'height': 54, 'url': 'https://external-preview.redd.it/Tkq7HPzeNgfJZTbaQcR0OIcY_HC8gbHQg6zCzZEq_U8.jpg?width=108&crop=smart&auto=webp&s=d0e15bf94111171a38e17286c5ab105f909155ea', 'width': 108}, {'height': 108, 'url': 'h... |
Discover & review your favorite AI character / role-play / story-writing models | 1 | [removed] | 2023-11-28T15:08:35 | https://www.reddit.com/r/LocalLLaMA/comments/185y7af/discover_review_your_favorite_ai_character/ | WhereAreMyWaifus | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 185y7af | false | null | t3_185y7af | /r/LocalLLaMA/comments/185y7af/discover_review_your_favorite_ai_character/ | false | false | self | 1 | null |
100B, 220B, and 600B models on huggingface! | 78 | [https://huggingface.co/deepnight-research](https://huggingface.co/deepnight-research)
I'm not affiliated with this group at all, I was just randomly looking for any new big merges and found these.
100B model: [https://huggingface.co/deepnight-research/saily\_100B](https://huggingface.co/deepnight-research/saily_100B... | 2023-11-28T14:48:38 | https://www.reddit.com/r/LocalLLaMA/comments/185xrds/100b_220b_and_600b_models_on_huggingface/ | Illustrious_Sand6784 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 185xrds | false | null | t3_185xrds | /r/LocalLLaMA/comments/185xrds/100b_220b_and_600b_models_on_huggingface/ | false | false | self | 78 | {'enabled': False, 'images': [{'id': 'MA8wpDz83Jy8SDAhYctTPnbWB4tKyir-x7hyJKivNnA', 'resolutions': [{'height': 58, 'url': 'https://external-preview.redd.it/7uT7RCvFBjzfgDn79bY9fqChrSrmXbnLcucg_2nWccU.jpg?width=108&crop=smart&auto=webp&s=3784ab2cc5fc9b7dda2c13686f9cd8ffed055b4b', 'width': 108}, {'height': 116, 'url': 'h... |
Why is no one releasing 70b models? | 1 | There has been a lot of movement around and below the 13b parameter bracket in the last few months but it's wild to think the best 70b models are still llama2 based. Why is that?
We have 13b models like 8bit bartowski/Orca-2-13b-exl2 approaching or even surpassing the best 70b models now | 2023-11-28T14:45:57 | https://www.reddit.com/r/LocalLLaMA/comments/185xp7h/why_is_no_one_releasing_70b_models/ | Longjumping-Bake-557 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 185xp7h | false | null | t3_185xp7h | /r/LocalLLaMA/comments/185xp7h/why_is_no_one_releasing_70b_models/ | false | false | self | 1 | null |
Inferencing with AND X3D Processors | 2 | With the proof of concept done and users able to get over 180gb/s on a PC with AMD's 3d vcache, it sure would be nice if we could figure a way to use that bandwidth for CPU based inferencing. I think it only worked on Windows but if that is the case we should be able to come up with a way to do it under Linux too. | 2023-11-28T13:55:30 | https://www.reddit.com/r/LocalLLaMA/comments/185wlg6/inferencing_with_and_x3d_processors/ | ccbadd | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 185wlg6 | false | null | t3_185wlg6 | /r/LocalLLaMA/comments/185wlg6/inferencing_with_and_x3d_processors/ | false | false | self | 2 | null |
Notes to letters | 3 | I am trying to convert my investigation case notes into letters. I have several letters that can show the tone I use in my letters. I have got very good results by prompting GPT 4-8k. But no open source model in the 7b or 13b category has done well with prompting.
What will be the best 7b model to finetune? | 2023-11-28T13:49:00 | https://www.reddit.com/r/LocalLLaMA/comments/185wgod/notes_to_letters/ | Rizatriptan7 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 185wgod | false | null | t3_185wgod | /r/LocalLLaMA/comments/185wgod/notes_to_letters/ | false | false | self | 3 | null |
Xwin-Math: A Series of Powerful SFT Math LLMs and Evaluation Toolkit | 15 | Hi, everyone. Xwin-Math is intended to promote the mathematical reasoning capabilities of LLMs. Now we release the first version, which is a series of Llama 2 SFT models with CoT prompt.
GitHub link: [Xwin-LM/Xwin-Math at main · Xwin-LM/Xwin-LM (github.com)](https://github.com/Xwin-LM/Xwin-LM/tree/main/Xwin-Math)
Mod... | 2023-11-28T13:39:38 | https://www.reddit.com/r/LocalLLaMA/comments/185w9kl/xwinmath_a_series_of_powerful_sft_math_llms_and/ | Left_Beat210 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 185w9kl | false | null | t3_185w9kl | /r/LocalLLaMA/comments/185w9kl/xwinmath_a_series_of_powerful_sft_math_llms_and/ | false | false | 15 | {'enabled': False, 'images': [{'id': '506xn4_X4lBz9sqHiRWJjUP4qlRdD-9K6twhUCsu9d4', 'resolutions': [{'height': 54, 'url': 'https://external-preview.redd.it/HGkX42ZXGkVdi38YcKvzBvuYDu3SNdREC6Uk1L7VMZY.jpg?width=108&crop=smart&auto=webp&s=8cb501ab3a606ca30bc812680b408d405fb3be73', 'width': 108}, {'height': 108, 'url': 'h... | |
Optimizing Your Language Model Experience: A Student's Journey with a Cutting-Edge PC featuring Core i7 14th Gen, RTX 4070 Ti, and 32GB DDR5 RAM | 2 | Hello, I'm a student delving into the study of large language models. I recently acquired a new PC equipped with a Core i7 14th Gen processor, RTX 4070 Ti graphics, and 32GB DDR5 RAM. Could you kindly suggest a recommended language model for optimal performance on my machine? | 2023-11-28T13:37:47 | https://www.reddit.com/r/LocalLLaMA/comments/185w887/optimizing_your_language_model_experience_a/ | Revolutionary_Fig171 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 185w887 | false | null | t3_185w887 | /r/LocalLLaMA/comments/185w887/optimizing_your_language_model_experience_a/ | false | false | self | 2 | null |
EPFL releases an open Medical Llama 2 finetune, including weights and training data, within 5%/10% of GPT-4/Med-PaLM-2 | 19 | 2023-11-28T12:56:27 | https://arxiv.org/abs/2311.16079 | wojcech | arxiv.org | 1970-01-01T00:00:00 | 0 | {} | 185veu2 | false | null | t3_185veu2 | /r/LocalLLaMA/comments/185veu2/epfl_releases_an_open_medical_llama_2_finetune/ | false | false | default | 19 | null | |
HumanEval leaderboard got updated with GPT-4 Turbo | 128 | 2023-11-28T12:29:20 | OnurCetinkaya | i.redd.it | 1970-01-01T00:00:00 | 0 | {} | 185uwxn | false | null | t3_185uwxn | /r/LocalLLaMA/comments/185uwxn/humaneval_leaderboard_got_updated_with_gpt4_turbo/ | false | false | 128 | {'enabled': True, 'images': [{'id': 'g8QEXz-nki-UM1HZ6jaRlbY-IqZXswYuYQKFuJk26jU', 'resolutions': [{'height': 40, 'url': 'https://preview.redd.it/e49jbboi033c1.png?width=108&crop=smart&auto=webp&s=2b344c8009654a371b5a7305d5879eaaf0dc093c', 'width': 108}, {'height': 81, 'url': 'https://preview.redd.it/e49jbboi033c1.png?... | |||
How to chat with documents in/ via LM Studio? | 3 | I'm only now wrapping my head around this - I know there's no option in the LM Studio UI, but is there any way to ingest documents once the LM studio loads the model in?
Also, any alternative stack that has a UI for not just chats, but also document ingestion for local models? | 2023-11-28T12:25:28 | https://www.reddit.com/r/LocalLLaMA/comments/185uuee/how_to_chat_with_documents_in_via_lm_studio/ | laterral | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 185uuee | false | null | t3_185uuee | /r/LocalLLaMA/comments/185uuee/how_to_chat_with_documents_in_via_lm_studio/ | false | false | self | 3 | null |
Evaluate, monitor, and safeguard your LLM-based apps | 4 | For the last couple of months, I along with my team invested lots of effort into building a solution that can help users evaluate and monitor the performance of their LLM and AI apps.
If you're a ChatGPT (or any other LLM :)) user and are integrating it into your apps, and if, by any chance, it ever happened to you th... | 2023-11-28T12:15:51 | https://www.reddit.com/r/LocalLLaMA/comments/185uo6g/evaluate_monitor_and_safeguard_your_llmbased_apps/ | AsDivyansh | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 185uo6g | false | null | t3_185uo6g | /r/LocalLLaMA/comments/185uo6g/evaluate_monitor_and_safeguard_your_llmbased_apps/ | false | false | self | 4 | {'enabled': False, 'images': [{'id': 'PXYVwNrI2X0Yh-Cdmf43llo4X-3RTovXfgwT7TJg6Ts', 'resolutions': [{'height': 54, 'url': 'https://external-preview.redd.it/i5mpLFey1Mbr3R4BrLmloeifvHyCxtIZUWqQW8W1N0U.jpg?width=108&crop=smart&auto=webp&s=37808feb445526b774ed7f4a168d55b4e1a8ccfe', 'width': 108}, {'height': 108, 'url': 'h... |
Role play | 3 | Hi, does anyone know of any (peer-reviewed) articles testing performance when giving LLMs a role? It's something most of us do in prompts and it's somewhat logical that introducing such a parameter would increase likelihood of desired output, but has anyone actually tested it in a cite-able article?
I'm thinking of... | 2023-11-28T12:03:48 | https://www.reddit.com/r/LocalLLaMA/comments/185ugtk/role_play/ | MFHau | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 185ugtk | false | null | t3_185ugtk | /r/LocalLLaMA/comments/185ugtk/role_play/ | false | false | self | 3 | null |
LLM NSFW Community? | 1 | [removed] | 2023-11-28T11:58:06 | https://www.reddit.com/r/LocalLLaMA/comments/185ud1b/llm_nsfw_community/ | Sakura9095 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 185ud1b | false | null | t3_185ud1b | /r/LocalLLaMA/comments/185ud1b/llm_nsfw_community/ | false | false | nsfw | 1 | null |
Best 7B model to fine-tune for Q&A over knowledge base | 3 | I have our own knowledge base (confluence) and would like to train a local model over it. What am I best looking at and what should by training data look like? Grateful for pointers/articles. I've been able to step through couple of instruct tutorials, but that doesn't quite feel like it? | 2023-11-28T11:47:28 | https://www.reddit.com/r/LocalLLaMA/comments/185u785/best_7b_model_to_finetune_for_qa_over_knowledge/ | Otherwise-Tiger3359 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 185u785 | false | null | t3_185u785 | /r/LocalLLaMA/comments/185u785/best_7b_model_to_finetune_for_qa_over_knowledge/ | false | false | self | 3 | null |
AIlice, a lightweight AI Agent based on open source model | 14 | Hello everyone, I've initiated a new project for an LLM agent ([https://github.com/stevenlu137/AIlice](https://github.com/stevenlu137/AIlice)). The primary objective is to create a lightweight agent based on an open-source model (the current code size is approximately 2.5k). AIlice also supports private models, such as... | 2023-11-28T11:43:35 | https://www.reddit.com/r/LocalLLaMA/comments/185u51a/ailice_a_lightweight_ai_agent_based_on_open/ | Steven_Lu_137 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 185u51a | false | null | t3_185u51a | /r/LocalLLaMA/comments/185u51a/ailice_a_lightweight_ai_agent_based_on_open/ | false | false | self | 14 | {'enabled': False, 'images': [{'id': 'JuVHyjhvpSNUQ1-G_YT-n5O5_aa9WFt6QxImMnPIpsY', 'resolutions': [{'height': 54, 'url': 'https://external-preview.redd.it/JHeMVH5eA26afchGDdkxgjIJ6jBRlaQLwKFIyTnU1z8.jpg?width=108&crop=smart&auto=webp&s=6b5752281626dcf1aba0007671fba507c567a25e', 'width': 108}, {'height': 108, 'url': 'h... |
Adversarial Reinforcement Learning and Generalization | 8 | Adversarial Attacks, Robustness and Generalization in Deep Reinforcement Learning
[https://blogs.ucl.ac.uk/steapp/2023/11/15/adversarial-attacks-robustness-and-generalization-in-deep-reinforcement-learning/](https://blogs.ucl.ac.uk/steapp/2023/11/15/adversarial-attacks-robustness-and-generalization-in-deep-reinforcem... | 2023-11-28T11:39:59 | https://www.reddit.com/r/LocalLLaMA/comments/185u2zg/adversarial_reinforcement_learning_and/ | ml_dnn | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 185u2zg | false | null | t3_185u2zg | /r/LocalLLaMA/comments/185u2zg/adversarial_reinforcement_learning_and/ | false | false | self | 8 | null |
Is LLaMa good for making a chatbot? | 6 | Hello there,
I'm a student and me and my team have the assignment to make a chatbot for our university. We need to make a chatbot that can help other students find information about their course. We will get our data from manuals of multiple universtity websites (as pdf). This data will be turned into Q&A data using C... | 2023-11-28T11:29:51 | https://www.reddit.com/r/LocalLLaMA/comments/185txdf/is_llama_good_for_making_a_chatbot/ | Flo501 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 185txdf | false | null | t3_185txdf | /r/LocalLLaMA/comments/185txdf/is_llama_good_for_making_a_chatbot/ | false | false | self | 6 | null |
Advices for a 4090 build | 1 | [removed] | 2023-11-28T11:27:09 | https://www.reddit.com/r/LocalLLaMA/comments/185tvyk/advices_for_a_4090_build/ | LuccDev | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 185tvyk | false | null | t3_185tvyk | /r/LocalLLaMA/comments/185tvyk/advices_for_a_4090_build/ | false | false | self | 1 | null |
Finetuning LLM settings | 3 | I'm starting to get the feeling that tuning LLM's with just the correct settings is an artform, it feels like tuning a radio where even the smallest change in settings (Temp, Top P, etc) gives vastly different output quality.
Do you guys feel that correctly setting up an LLM is like tuning a radio where if you are a l... | 2023-11-28T11:10:02 | https://www.reddit.com/r/LocalLLaMA/comments/185tmgc/finetuning_llm_settings/ | LeanderGem | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 185tmgc | false | null | t3_185tmgc | /r/LocalLLaMA/comments/185tmgc/finetuning_llm_settings/ | false | false | self | 3 | null |
Code Llama giving really bad results | 3 | I read that code-llama can be used to not only generate code from NLP but also explain code. However, when I tried doing that, I got really bad results. This is the relevant part of the code:
code_snippet = """
import random
random_numbers = [random.randint(1, 10) for _ in range(5)]
print("Random Numbers:", ran... | 2023-11-28T11:07:51 | https://www.reddit.com/r/LocalLLaMA/comments/185tlai/code_llama_giving_really_bad_results/ | Kaushik2002 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 185tlai | false | null | t3_185tlai | /r/LocalLLaMA/comments/185tlai/code_llama_giving_really_bad_results/ | false | false | self | 3 | null |
Can you local LLM do this NSFW? | 1 | do you have the best local llm for nsfw? i wonder what llm to download. can you show how your llm handles tasks like these?
"describe lea's ass cheeks while they're moving obscenely while she walks. use primitive, pornographic language. write about her sexual body in 500 words."
something like this.
or
"give 20 se... | 2023-11-28T09:49:59 | https://www.reddit.com/r/LocalLLaMA/comments/185sfh9/can_you_local_llm_do_this_nsfw/ | Sakura9095 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 185sfh9 | false | null | t3_185sfh9 | /r/LocalLLaMA/comments/185sfh9/can_you_local_llm_do_this_nsfw/ | false | false | default | 1 | null |
Which Web UI can I trust not to send any data over the Internet? | 1 | [removed] | 2023-11-28T09:35:10 | https://www.reddit.com/r/LocalLLaMA/comments/185s7xa/which_web_ui_can_i_trust_not_to_send_any_data/ | SideShow_Bot | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 185s7xa | false | null | t3_185s7xa | /r/LocalLLaMA/comments/185s7xa/which_web_ui_can_i_trust_not_to_send_any_data/ | false | false | self | 1 | {'enabled': False, 'images': [{'id': 'Ajx3oc9xI8dxPGnD9BMVWhJm3BYjlx-UMerl2y7P_zE', 'resolutions': [{'height': 108, 'url': 'https://external-preview.redd.it/qdOcYHDZ-L-7D6JTLC_IVjW63qiB5nM9oiR0gfOUREQ.jpg?width=108&crop=smart&auto=webp&s=71c91ffd1520294443e8915748158ec3c743e85c', 'width': 108}, {'height': 216, 'url': '... |
LLM generating random conversation from within a Godot game. | 1 | 2023-11-28T09:09:02 | https://github.com/opyate/godot-llm-experiment | willcodeforbread | github.com | 1970-01-01T00:00:00 | 0 | {} | 185ruk6 | false | null | t3_185ruk6 | /r/LocalLLaMA/comments/185ruk6/llm_generating_random_conversation_from_within_a/ | false | false | default | 1 | {'enabled': False, 'images': [{'id': 'WPpRlWjxmOHd3-4UXAbSgr3BE8BLdqJsbKqi-sZEjnQ', 'resolutions': [{'height': 54, 'url': 'https://external-preview.redd.it/Qu2uDRFfBwDysHqSBZPjCO4VNphL_q5ZYlEa9IqIO_s.jpg?width=108&crop=smart&auto=webp&s=28b2e503ec66d99f1c0216159a51f5bc1e6f2b2a', 'width': 108}, {'height': 108, 'url': 'h... | |
Adjusting Probability distribution Using Speculative Decoding | 1 | [removed] | 2023-11-28T09:07:24 | https://www.reddit.com/r/LocalLLaMA/comments/185rtt0/adjusting_probability_distribution_using/ | 1azytux | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 185rtt0 | false | null | t3_185rtt0 | /r/LocalLLaMA/comments/185rtt0/adjusting_probability_distribution_using/ | false | false | self | 1 | {'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... |
is it important the CPU for Llama and AI in general or it is just the GPU? | 1 | I am getting a RTX 3090, but i am wondering if it will work the same for SD/AI in combination with an AMD Ryzen 7950X or an older EPYC 7551P for AI? does processor speed or mem DDR3/4/5 or PCI 4/3 matters for anything? | 2023-11-28T07:52:57 | https://www.reddit.com/r/LocalLLaMA/comments/185qrv3/is_it_important_the_cpu_for_llama_and_ai_in/ | Stunning_Art4243 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 185qrv3 | false | null | t3_185qrv3 | /r/LocalLLaMA/comments/185qrv3/is_it_important_the_cpu_for_llama_and_ai_in/ | false | false | default | 1 | null |
git Repo as Context | 3 | I'm a true lurker but am tinkering with some models for coding.
My aim is to unashamedly stop outsourcing some of my coding tasks to developers and, instead, ask my AI. I'm trying to load my entire application codebase and then ask for tweaks and new features.
Does anyone have any ideas about providing multiple (code... | 2023-11-28T07:09:48 | https://www.reddit.com/r/LocalLLaMA/comments/185q5fm/git_repo_as_context/ | antsloveit | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 185q5fm | false | null | t3_185q5fm | /r/LocalLLaMA/comments/185q5fm/git_repo_as_context/ | false | false | self | 3 | null |
Quality and time to train my LLM on a specific data set (state statutes) | 2 | I'm looking to train a local LLM on a smallish (?) but relevant amount of data. I was thinking of something like all state statutes in Colorado. Is it possible to build something that would be about as good as ChatGPT 3.5 or even 4 if I limited the data to that? Or are local LLMs still not anywhere near as sophisticate... | 2023-11-28T07:08:32 | https://www.reddit.com/r/LocalLLaMA/comments/185q4t3/quality_and_time_to_train_my_llm_on_a_specific/ | Aggravating-Hat-5402 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 185q4t3 | false | null | t3_185q4t3 | /r/LocalLLaMA/comments/185q4t3/quality_and_time_to_train_my_llm_on_a_specific/ | false | false | self | 2 | null |
I have a few use cases and am looking for locally run options, with minimal experience and expertise | 3 | ​
Im looking to get some info on local models for a few use cases to move away from corporate dependency and get more free features, as well as the stability of working with a version that only I choose to update. I am also a child of the 90s so I want everything *wicked radical* with boobs and curse words and ... | 2023-11-28T07:06:58 | https://www.reddit.com/r/LocalLLaMA/comments/185q3z1/i_have_a_few_use_cases_and_am_looking_for_locally/ | LeastDegenAzuraEnjyr | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 185q3z1 | false | null | t3_185q3z1 | /r/LocalLLaMA/comments/185q3z1/i_have_a_few_use_cases_and_am_looking_for_locally/ | false | false | self | 3 | {'enabled': False, 'images': [{'id': '_CChmj5HtOMwUxv2LoUScmzDZYg3ocwIEtdp-RrBvsU', 'resolutions': [{'height': 58, 'url': 'https://external-preview.redd.it/mFbTwIUxzd7xE0LUX8NSiar11QvINMtiTYkV3sYX9LM.jpg?width=108&crop=smart&auto=webp&s=24e6616d92c6f3c28234439b2c196a9ba8081759', 'width': 108}, {'height': 116, 'url': 'h... |
Anyone using Go or Rust for AI work instead of python? | 60 | I know the typical answer is "no because all the libs are in python".. but I am kind of baffled why more porting isn't going on especially to Go given how Go like Python is stupid easy to learn and yet much faster to run. Truly not trying to start a flame war or anything. I am just a bigger fan of Go than Python and wa... | 2023-11-28T06:32:31 | https://www.reddit.com/r/LocalLLaMA/comments/185pl37/anyone_using_go_or_rust_for_ai_work_instead_of/ | Dry-Vermicelli-682 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 185pl37 | false | null | t3_185pl37 | /r/LocalLLaMA/comments/185pl37/anyone_using_go_or_rust_for_ai_work_instead_of/ | false | false | self | 60 | null |
Bananalyzer 🍌: Open source evaluations + static environments for web agents | 1 | 2023-11-28T05:17:18 | https://github.com/reworkd/bananalyzer | asim-shrestha | github.com | 1970-01-01T00:00:00 | 0 | {} | 185odt8 | false | null | t3_185odt8 | /r/LocalLLaMA/comments/185odt8/bananalyzer_open_source_evaluations_static/ | false | false | 1 | {'enabled': False, 'images': [{'id': 'N5R3LRlpJMIPiD0211p2CVvAPdLY-453s5cv5qAtSG8', 'resolutions': [{'height': 54, 'url': 'https://external-preview.redd.it/K0bxu1CFiryBWmZEPWj7_u1YokpyYs1Zuz0rzNy1kPA.jpg?width=108&crop=smart&auto=webp&s=98cf949e6c9798ffb7378611594a8213753a3005', 'width': 108}, {'height': 108, 'url': 'h... | ||
New APU’s close to Gpu processing, but with unlimited memory? | 18 | If cpu processing is slow af, and gpu takes $$$$ to get enough memory for larger models; I am wondering if an APU could deliver some of that gpu speed, but using cheaper ram to get the larger models in memory; with 128gb of ram, that’s the equivalent of 6x 30/4090s, without allowing for overhead at least!
Wondering if... | 2023-11-28T05:10:55 | https://www.reddit.com/r/LocalLLaMA/comments/185oa2q/new_apus_close_to_gpu_processing_but_with/ | bkm_s | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 185oa2q | false | null | t3_185oa2q | /r/LocalLLaMA/comments/185oa2q/new_apus_close_to_gpu_processing_but_with/ | false | false | self | 18 | null |
Does a 7900xtx work for LLM? | 2 | Im trying to run 70b Llms, I already have a 4090 and a friend of mine can sell me his 7900xtx for $500. Would an amd card work or should I try and get a nvidia card? | 2023-11-28T04:38:22 | https://www.reddit.com/r/LocalLLaMA/comments/185nq0x/does_a_7900xtx_work_for_llm/ | asdfgbvcxz3355 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 185nq0x | false | null | t3_185nq0x | /r/LocalLLaMA/comments/185nq0x/does_a_7900xtx_work_for_llm/ | false | false | self | 2 | null |
Pepai -- Seems like Pepe | 4 | Original Tweet: [https://twitter.com/migtissera/status/1727865890937704542](https://twitter.com/migtissera/status/1727865890937704542)
I have no idea whether this made it to here, but seems funny! LOL..
[https://huggingface.co/migtissera/Pepai](https://huggingface.co/migtissera/Pepai)
Also seems like the dataset is ... | 2023-11-28T04:29:45 | https://www.reddit.com/r/LocalLLaMA/comments/185nkj9/pepai_seems_like_pepe/ | Adventurous-Sail-220 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 185nkj9 | false | {'oembed': {'author_name': 'Migel Tissera', 'author_url': 'https://twitter.com/migtissera', 'cache_age': 3153600000, 'height': None, 'html': '<blockquote class="twitter-video"><p lang="en" dir="ltr">Well, Elon Musk says Grok is based on The Hitchhiker's Guide to the Galaxy.. Well guess what? Pepai is also based on ... | t3_185nkj9 | /r/LocalLLaMA/comments/185nkj9/pepai_seems_like_pepe/ | false | false | 4 | {'enabled': False, 'images': [{'id': 'lA2u3PMnTYLyT8ka05VCjZfWHgOPusZJjs9c8R748yU', 'resolutions': [{'height': 108, 'url': 'https://external-preview.redd.it/tp0alojxTPDj673hipKr_uTwLfB2FetX8ov-LnpfRoQ.jpg?width=108&crop=smart&auto=webp&s=74ca43ff51fda6e5a62ca183463f35d9acf2f86b', 'width': 108}], 'source': {'height': 14... | |
New Model: Starling-LM-11B-alpha-v1 | 65 | [https://huggingface.co/NurtureAI/Starling-LM-11B-alpha-v1](https://huggingface.co/NurtureAI/Starling-LM-11B-alpha-v1)
This is Berkeley's model: [Starling-LM-7B-alpha](https://huggingface.co/berkeley-nest/Starling-LM-7B-alpha) with the size of model increased to 11B from 7B.
Special thanks to user [Undi95](https:... | 2023-11-28T03:55:50 | https://www.reddit.com/r/LocalLLaMA/comments/185my1b/new_model_starlinglm11balphav1/ | perlthoughts | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 185my1b | false | null | t3_185my1b | /r/LocalLLaMA/comments/185my1b/new_model_starlinglm11balphav1/ | false | false | self | 65 | {'enabled': False, 'images': [{'id': 'j5fGkWxgVNr9eugHSnlqcGeT5yEhHeiub9Ww0ftpPzA', 'resolutions': [{'height': 58, 'url': 'https://external-preview.redd.it/XJEWzzIhOPrYQEZR5cytrEYiXZJWOnNfn2aHqaWJIhc.jpg?width=108&crop=smart&auto=webp&s=89e3f4db7faae5ee78de3b993be67c2677c5a2ed', 'width': 108}, {'height': 116, 'url': 'h... |
Llama.cpp on colab with Bakllava-1.Q8_0 (Mistral+LLaVA 1.5) | 6 | I got Llama.cpp to work with BakLLaVA (Mistral+LLaVA 1.5) on colab.
Here's a working example that offloads all the layers of bakllava-1.Q8_0 to T4, a free GPU on Colab.
https://colab.research.google.com/gist/chigkim/a5be99a864c4196d5e379a1e6e280a9e/bakllava.ipynb
FYI, Colab has no persistent storage, and you cannot ... | 2023-11-28T03:49:40 | https://www.reddit.com/r/LocalLLaMA/comments/185mu00/llamacpp_on_colab_with_bakllava1q8_0_mistralllava/ | chibop1 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 185mu00 | false | null | t3_185mu00 | /r/LocalLLaMA/comments/185mu00/llamacpp_on_colab_with_bakllava1q8_0_mistralllava/ | false | false | self | 6 | {'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': '... |
InternLM 7B answers differently depending on prompting language | 3 | Not only does the model give divergent answers on the question "is Taiwan a part of China?", it also diverges significantly when asked to "summarize Xi Jinpeng Thought". This suggests that the training set and/or guardrails do not attempt to ensure English responses are in line with "core values of socialism". My bet i... | 2023-11-28T02:03:17 | https://www.reddit.com/r/LocalLLaMA/comments/185ko93/internlm_7b_answers_differently_depending_on/ | grimjim | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 185ko93 | false | null | t3_185ko93 | /r/LocalLLaMA/comments/185ko93/internlm_7b_answers_differently_depending_on/ | false | false | self | 3 | null |
How does Ludwig compare to axolotl | 2 | Looking to see the difference between axolotl and Ludwig with regards to fine tuning. Ease of use and distributed training are main drivers | 2023-11-28T02:02:36 | https://www.reddit.com/r/LocalLLaMA/comments/185knrt/how_does_ludwig_compare_to_axolotl/ | FitDoughnut475 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 185knrt | false | null | t3_185knrt | /r/LocalLLaMA/comments/185knrt/how_does_ludwig_compare_to_axolotl/ | false | false | self | 2 | null |
llama.cpp server rocks now! 🤘 | 104 | So I was looking over the recent merges to llama.cpp’s server and saw that they’d more or less brought it in line with Open AI-style APIs – natively – obviating the need for e.g. api\_like\_OAI.py, or one of the bindings/wrappers like llama-cpp-python (+ooba), koboldcpp, etc. (not that those and others don’t provide gr... | 2023-11-28T01:46:53 | https://www.reddit.com/r/LocalLLaMA/comments/185kbtg/llamacpp_server_rocks_now/ | Gorefindal | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 185kbtg | false | null | t3_185kbtg | /r/LocalLLaMA/comments/185kbtg/llamacpp_server_rocks_now/ | false | false | self | 104 | {'enabled': False, 'images': [{'id': 'K37p0KJ_VtX6BbrCDMGDvuagObmlWHYCuPz2IDeDV4A', 'resolutions': [{'height': 54, 'url': 'https://external-preview.redd.it/B_Pmz_pRaAJPJmlBXWkkSQvWCdRLOEj8aVr7OQSav0c.jpg?width=108&crop=smart&auto=webp&s=8bc276b838f25e7497fd2112287984013746fced', 'width': 108}, {'height': 108, 'url': 'h... |
How do I fine-tune Mistral with my own data? | 1 | [removed] | 2023-11-28T01:07:29 | https://www.reddit.com/r/LocalLLaMA/comments/185jhgb/how_do_i_finetune_mistral_with_my_own_data/ | consig1iere | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 185jhgb | false | null | t3_185jhgb | /r/LocalLLaMA/comments/185jhgb/how_do_i_finetune_mistral_with_my_own_data/ | false | false | self | 1 | null |
Misral Neuron value graphs in llama.cpp | 1 | [removed] | 2023-11-27T23:57:32 | https://www.reddit.com/gallery/185hx5s | introsp3ctor | reddit.com | 1970-01-01T00:00:00 | 0 | {} | 185hx5s | false | null | t3_185hx5s | /r/LocalLLaMA/comments/185hx5s/misral_neuron_value_graphs_in_llamacpp/ | false | false | 1 | null | |
Starling-RM-7B-alpha: New RLAIF Finetuned 7b Model beats Openchat 3.5 and comes close to GPT-4 | 153 | ​
​
https://preview.redd.it/3krgd1sg2z2c1.png?width=800&format=png&auto=webp&s=b76c5fb9fa22938c74ec3095f63adaec8ff2219d
​
I came across this new finetuned model based on Openchat 3.5 which is apparently trained used Reinforcement Learning from AI Feedback (RLAIF).
[https://huggingface.co/ber... | 2023-11-27T23:08:50 | https://www.reddit.com/r/LocalLLaMA/comments/185gs14/starlingrm7balpha_new_rlaif_finetuned_7b_model/ | Legcor | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 185gs14 | false | null | t3_185gs14 | /r/LocalLLaMA/comments/185gs14/starlingrm7balpha_new_rlaif_finetuned_7b_model/ | false | false | 153 | {'enabled': False, 'images': [{'id': 'MkPeBvU3WVFIry5Ow6_NGccUwNW-5VNr5a9-aLl22oE', 'resolutions': [{'height': 58, 'url': 'https://external-preview.redd.it/s0XUwHQwrVUYWPx2yMh-TgB49PUYfXtuc1NY9XKN_oY.jpg?width=108&crop=smart&auto=webp&s=e3b1bb2daa788a68756f939b39227b6698f780a5', 'width': 108}, {'height': 116, 'url': 'h... | |
StreamingLLM? Is Unlimited context possible with LLMs? | 4 | [\[2309.17453\] Efficient Streaming Language Models with Attention Sinks (arxiv.org)](https://arxiv.org/abs/2309.17453)
" StreamingLLM can enable Llama-2, MPT, Falcon, and Pythia to perform stable and efficient language modeling with up to 4 million tokens and more."
If this works, this could be a major change... | 2023-11-27T23:00:53 | https://www.reddit.com/r/LocalLLaMA/comments/185gkuo/streamingllm_is_unlimited_context_possible_with/ | StudioTatsu | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 185gkuo | false | null | t3_185gkuo | /r/LocalLLaMA/comments/185gkuo/streamingllm_is_unlimited_context_possible_with/ | false | false | self | 4 | {'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... |
Any Easy and Local Way to Run Benchmarks? | 4 | I want to see if some presets and custom modifications work well in benchmarks, but running HellaSwag or MMLU looks too complicated for me, and it takes 10+ hours to upload 20GBs of data for me.
I assume there isn't a convenient webui for chumps to run benchmarks with (apart from ooba perplexity, which I assume isn't ... | 2023-11-27T22:54:09 | https://www.reddit.com/r/LocalLLaMA/comments/185gezv/any_easy_and_local_way_to_run_benchmarks/ | xadiant | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 185gezv | false | null | t3_185gezv | /r/LocalLLaMA/comments/185gezv/any_easy_and_local_way_to_run_benchmarks/ | false | false | self | 4 | null |
Choosing Between DAG-Based Workflows and LLM Controller Agent Workflows | 5 | Hello everyone!
I'm delving into the orchestration of complex agent actions and have come across two predominant workflow types: Directed Acyclic Graph (DAG) based workflows, and workflows managed by a Language Model (LLM) controller agent. I'm trying to understand the best contexts and scenarios for each of these app... | 2023-11-27T22:46:26 | https://www.reddit.com/r/LocalLLaMA/comments/185g886/choosing_between_dagbased_workflows_and_llm/ | Puzzleheaded_Dog7026 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 185g886 | false | null | t3_185g886 | /r/LocalLLaMA/comments/185g886/choosing_between_dagbased_workflows_and_llm/ | false | false | self | 5 | null |
Coding Assistant recommendation | 1 | [removed] | 2023-11-27T22:45:36 | https://www.reddit.com/r/LocalLLaMA/comments/185g7i6/coding_assistant_recommendation/ | SideShow_Bot | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 185g7i6 | false | null | t3_185g7i6 | /r/LocalLLaMA/comments/185g7i6/coding_assistant_recommendation/ | false | false | self | 1 | null |
Subsets and Splits
No community queries yet
The top public SQL queries from the community will appear here once available.