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 ⌀ |
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
API vs Local setup for research? | 5 | Hi guys, been lurking for a couple weeks now, and genuinely really impressed with all the happenings in this sub even though I understand maybe a 1/4 of everything I read - like how ERP def is about enterprise resource planing.
Right now I’m working on a project to model the degree of online parasocial relationships ... | 2024-01-08T09:58:20 | https://www.reddit.com/r/LocalLLaMA/comments/191hrjq/api_vs_local_setup_for_research/ | GeeBrain | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 191hrjq | false | null | t3_191hrjq | /r/LocalLLaMA/comments/191hrjq/api_vs_local_setup_for_research/ | false | false | self | 5 | null |
Model recommendation - Browser copilot | 1 | Hello
I'm looking for a model ( 13\~b ) that would be a good fit for a browser extension that we want to use to predict what text may come after.
An example usage would be writing this exact same reddit post, the model would get some context on the active tab, the current input text ( before and after the current cur... | 2024-01-08T09:47:02 | https://www.reddit.com/r/LocalLLaMA/comments/191hluc/model_recommendation_browser_copilot/ | ithanlara1 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 191hluc | false | null | t3_191hluc | /r/LocalLLaMA/comments/191hluc/model_recommendation_browser_copilot/ | false | false | self | 1 | null |
Language Agent Tree Search Unifies Reasoning Acting and Planning in Language Models. LATS achieves 94.4% for programming on HumanEval with GPT-4 and an average score of 75.9 for web browsing on WebShop with GPT-3.5, demonstrating the effectiveness and generality of this method. | 1 | [removed] | 2024-01-08T09:42:57 | TysonUsykFury | i.redd.it | 1970-01-01T00:00:00 | 0 | {} | 191hjq6 | false | null | t3_191hjq6 | /r/LocalLLaMA/comments/191hjq6/language_agent_tree_search_unifies_reasoning/ | false | false | 1 | {'enabled': True, 'images': [{'id': 'w796KE4rqVxZkloaBGAx-IwUnYgunggwErNdZQ3cSfU', 'resolutions': [{'height': 162, 'url': 'https://preview.redd.it/lsik91e2t6bc1.png?width=108&crop=smart&auto=webp&s=ceaec92d9cea146f3e5a98743df692ec8489eea0', 'width': 108}, {'height': 325, 'url': 'https://preview.redd.it/lsik91e2t6bc1.pn... | ||
EC2 Instance, SageMaker or something better ? | 1 | [removed] | 2024-01-08T09:03:25 | https://www.reddit.com/r/LocalLLaMA/comments/191gz64/ec2_instance_sagemaker_or_something_better/ | Ornery_Researcher_ | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 191gz64 | false | null | t3_191gz64 | /r/LocalLLaMA/comments/191gz64/ec2_instance_sagemaker_or_something_better/ | false | false | self | 1 | null |
Best models for adult novels that can be run on Apple Silicon? | 1 | What are the best uncensored Apple-compatible models for spicy novels?
Thanks | 2024-01-08T08:46:38 | https://www.reddit.com/r/LocalLLaMA/comments/191gqjh/best_models_for_adult_novels_that_can_be_run_on/ | Cloudy-And-Sunny | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 191gqjh | false | null | t3_191gqjh | /r/LocalLLaMA/comments/191gqjh/best_models_for_adult_novels_that_can_be_run_on/ | false | false | self | 1 | null |
Llava on CPU? | 1 | Has anyone run Llava ([https://github.com/haotian-liu/LLaVA](https://github.com/haotian-liu/LLaVA)) model on CPU's without installing Intel Extention for Pytorch environment for inference? Any pointer will be really helpful | 2024-01-08T08:37:52 | https://www.reddit.com/r/LocalLLaMA/comments/191gm2q/llava_on_cpu/ | MLer-India | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 191gm2q | false | null | t3_191gm2q | /r/LocalLLaMA/comments/191gm2q/llava_on_cpu/ | false | false | self | 1 | {'enabled': False, 'images': [{'id': '6U37qjIXKQOAA8I73EjyXx_OErjVSduKDlTPrIoBlWE', 'resolutions': [{'height': 54, 'url': 'https://external-preview.redd.it/bH8ol9o4wom9RTIxdUSBuPHFCAzKRrshwnNhdZHMMJ4.jpg?width=108&crop=smart&auto=webp&s=6f55623724c5e41a5e8f5c095e53e9b8705e851d', 'width': 108}, {'height': 108, 'url': 'h... |
Fastest inference library for prod environment? | 12 | I'd like to deploy an open source models for a production use case. Users will be directly interfacing with the model so I need to minimize latency. I know vLLM is one option but are there any other libraries that would offer better performance in terms of inference speed and latency? | 2024-01-08T07:43:07 | https://www.reddit.com/r/LocalLLaMA/comments/191fsfp/fastest_inference_library_for_prod_environment/ | MonkeyMaster64 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 191fsfp | false | null | t3_191fsfp | /r/LocalLLaMA/comments/191fsfp/fastest_inference_library_for_prod_environment/ | false | false | self | 12 | null |
Sam Altman when GPT store launches | 7 | 2024-01-08T07:40:19 | TysonUsykFury | i.redd.it | 1970-01-01T00:00:00 | 0 | {} | 191fqvc | false | null | t3_191fqvc | /r/LocalLLaMA/comments/191fqvc/sam_altman_when_gpt_store_launches/ | false | false | 7 | {'enabled': True, 'images': [{'id': 'NdP4YW_XtjTu31Y53jYT7nUVU9wRM9dyHlRvMGZq4EM', 'resolutions': [{'height': 60, 'url': 'https://preview.redd.it/7mg1agp676bc1.jpeg?width=108&crop=smart&auto=webp&s=133e76059ce4b877ecacb96239a3e2f652001b8a', 'width': 108}, {'height': 120, 'url': 'https://preview.redd.it/7mg1agp676bc1.jp... | |||
Local TTS that can read a whole book | 1 | I use whisper a lot and it’s very good. However, there is word limit. Is there an app that can TTS a whole pdf or epub? | 2024-01-08T06:31:42 | https://www.reddit.com/r/LocalLLaMA/comments/191eo1b/local_tts_that_can_read_a_whole_book/ | IpadWriter | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 191eo1b | false | null | t3_191eo1b | /r/LocalLLaMA/comments/191eo1b/local_tts_that_can_read_a_whole_book/ | false | false | self | 1 | null |
Should SOTA performance also be measured by efficiency? If we don't know the size (parameter count) of either Gemini Ultra or GPT 4, can this not become an unfair comparison? Why is Google and OpenAI so scared of openness in testing? | 1 | 2024-01-08T06:30:05 | https://www.reddit.com/gallery/191en13 | TysonUsykFury | reddit.com | 1970-01-01T00:00:00 | 0 | {} | 191en13 | false | null | t3_191en13 | /r/LocalLLaMA/comments/191en13/should_sota_performance_also_be_measured_by/ | false | false | 1 | null | ||
Multi language Translation Local GPT | 1 | Is there a local gpt that can translate a whole pdf or epub file? Tired of manually copying page after page into ChatGPT | 2024-01-08T06:28:01 | https://www.reddit.com/r/LocalLLaMA/comments/191elv2/multi_language_translation_local_gpt/ | IpadWriter | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 191elv2 | false | null | t3_191elv2 | /r/LocalLLaMA/comments/191elv2/multi_language_translation_local_gpt/ | false | false | self | 1 | null |
llm struggles to interpret the context in response synthesis | 1 | Suppose we have a bunch of documents embedded in the vector db. And the user query is asking for an article mentioning "not driving a truck." RAG is retrieving the right documents, as it retrieves the documents mentioning both "not driving a truck" and "not driving a car." gpt4 only uses the phrases from the documents... | 2024-01-08T06:20:58 | https://www.reddit.com/r/LocalLLaMA/comments/191ehsf/llm_struggles_to_interpret_the_context_in/ | Lumpy-Breakfast3295 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 191ehsf | false | null | t3_191ehsf | /r/LocalLLaMA/comments/191ehsf/llm_struggles_to_interpret_the_context_in/ | false | false | self | 1 | null |
Decent LLMs on a Pi5. | 1 | [removed] | 2024-01-08T05:16:11 | https://www.reddit.com/r/LocalLLaMA/comments/191dczs/decent_llms_on_a_pi5/ | Sad_Preference2457 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 191dczs | false | null | t3_191dczs | /r/LocalLLaMA/comments/191dczs/decent_llms_on_a_pi5/ | false | false | self | 1 | {'enabled': False, 'images': [{'id': 'zAtW-iYarik5cBzFtk4y-cvIi7TsbZHVI2v20SZr5Qo', 'resolutions': [{'height': 81, 'url': 'https://external-preview.redd.it/zZovr0aPf7jGFN1QpgwvYGi6pTkunYUWBoT3MpOkKKQ.jpg?width=108&crop=smart&auto=webp&s=c9a2a403df7fc9c87c718581a7dfdb8f3ef2ac71', 'width': 108}, {'height': 162, 'url': 'h... |
Does anyone know a good model to make NSFW characters? | 1 | [removed] | 2024-01-08T04:57:22 | https://www.reddit.com/r/LocalLLaMA/comments/191d0cw/does_anyone_know_a_good_model_to_make_nsfw/ | bimibio | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 191d0cw | false | null | t3_191d0cw | /r/LocalLLaMA/comments/191d0cw/does_anyone_know_a_good_model_to_make_nsfw/ | false | false | nsfw | 1 | null |
Confused about using custom formatting in Axolotl | 3 | Hi, is there anyone who uses Axolotl and knows how to properly structure the custom user prompt?
My dataset is in the json format and contains multi-turn conversations:
```
[
{
"Chat": [
{"Human":"Question 1"},
{"Assistant":"Answer to question 1"},
{"Human":"Follow-up t... | 2024-01-08T04:39:58 | https://www.reddit.com/r/LocalLLaMA/comments/191copo/confused_about_using_custom_formatting_in_axolotl/ | ArakiSatoshi | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 191copo | false | null | t3_191copo | /r/LocalLLaMA/comments/191copo/confused_about_using_custom_formatting_in_axolotl/ | false | false | self | 3 | null |
Mixtral Speed Question | 4 | So I am testing Mixtral 8x7b Instruct utilizing thebloke's Q5 Quant.
I am using it in tests with a corporate HR Chatbot, currently the client uses Claude. The way their bot works, the entire HR manual is in the context, and the agent just answers from the context.
Context size is just under 20k Tokens.
Currently I a... | 2024-01-08T04:22:43 | https://www.reddit.com/r/LocalLLaMA/comments/191cd0f/mixtral_speed_question/ | aallsbury | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 191cd0f | false | null | t3_191cd0f | /r/LocalLLaMA/comments/191cd0f/mixtral_speed_question/ | false | false | self | 4 | null |
Non-enterprise question: 4000 super series? | 1 | I gotta get a new computer. How do you guys think the new 4000 super series is shaping up? I’m reading the 4070ti has an upgraded bus and more vram.
Most recent posts have been talking 120b+ or mixtral, so I dunno if we’re talking about consumer stuff anymore :-) | 2024-01-08T04:22:35 | https://www.reddit.com/r/LocalLLaMA/comments/191ccwx/nonenterprise_question_4000_super_series/ | hmmqzaz | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 191ccwx | false | null | t3_191ccwx | /r/LocalLLaMA/comments/191ccwx/nonenterprise_question_4000_super_series/ | false | false | self | 1 | null |
What is Apple thinking? Why are they so radio silent about LLMs despite having the edge over Microsoft/Google to bring local LLMs to iDevices? | 50 | (detail in the comments) | 2024-01-08T04:21:06 | https://www.reddit.com/r/LocalLLaMA/comments/191cbwh/what_is_apple_thinking_why_are_they_so_radio/ | nderstand2grow | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 191cbwh | false | null | t3_191cbwh | /r/LocalLLaMA/comments/191cbwh/what_is_apple_thinking_why_are_they_so_radio/ | false | false | self | 50 | null |
Currently working on building a Worldbuild+RP dataset | 50 | So I scraped all the worldbuilding stackexchange Q's, with 5+ rep, which left me with 18000 Q's. Its going to be a good resource for world-building and world details, which would probably augment RP.
The Raw release of the 18000 Q's is out here:
https://huggingface.co/datasets/VatsaDev/worldbuild
This is Phase one, t... | 2024-01-08T03:55:51 | https://www.reddit.com/r/LocalLLaMA/comments/191bufg/currently_working_on_building_a_worldbuildrp/ | vatsadev | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 191bufg | false | null | t3_191bufg | /r/LocalLLaMA/comments/191bufg/currently_working_on_building_a_worldbuildrp/ | false | false | self | 50 | {'enabled': False, 'images': [{'id': 'vBihn1wz8RSBZNXbn0zgmsx8oVKVjL3krCRZbMWEdeQ', 'resolutions': [{'height': 58, 'url': 'https://external-preview.redd.it/gaXcNSW79WamwnRdc6rFlvbSOU8gYg1u0YReYiej-0o.jpg?width=108&crop=smart&auto=webp&s=62e0fcf4304aee343b4a1ecb9d261177d5a08c0f', 'width': 108}, {'height': 116, 'url': 'h... |
The hidden cost of all mostly data driven algorithmic efficiencies during pretraining the we are seeing in smaller models when Open source release their models or AI researchers publish their results is lack of larger models......... | 1 | If I was a big company and wanted to train a SOTA model,
Rather than training a new larger model now to compete with or beat GPT 4,
I would just wait for new information to come out that would make my model better during pretraining.
The problem is that this information is just accelerating, every week new informat... | 2024-01-08T03:31:55 | https://www.reddit.com/r/LocalLLaMA/comments/191bdqm/the_hidden_cost_of_all_mostly_data_driven/ | TysonUsykFury | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 191bdqm | false | null | t3_191bdqm | /r/LocalLLaMA/comments/191bdqm/the_hidden_cost_of_all_mostly_data_driven/ | false | false | self | 1 | null |
alts – 100% free, local & offline voice assistant with speech recognition | 1 | 2024-01-08T03:03:17 | https://github.com/alxpez/alts | alxpez | github.com | 1970-01-01T00:00:00 | 0 | {} | 191at7i | false | null | t3_191at7i | /r/LocalLLaMA/comments/191at7i/alts_100_free_local_offline_voice_assistant_with/ | false | false | 1 | {'enabled': False, 'images': [{'id': 'gfcNuCwl_A0rp-wXcPD6L-AUPD835kmMKr_iZQ9YOZQ', 'resolutions': [{'height': 108, 'url': 'https://external-preview.redd.it/iYtaWN_tUsnKrzbXA3HOVvEzotGD-qBdIGUgmrlULrI.jpg?width=108&crop=smart&auto=webp&s=53e6f524c83dca67e47c81a7101d93162c303bf8', 'width': 108}, {'height': 216, 'url': '... | ||
Is the "max RAM required" gpu ram or system ram? Can I just run on system ram? | 1 | [removed] | 2024-01-08T03:02:19 | https://www.reddit.com/r/LocalLLaMA/comments/191asid/is_the_max_ram_required_gpu_ram_or_system_ram_can/ | Original_Job6327 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 191asid | false | null | t3_191asid | /r/LocalLLaMA/comments/191asid/is_the_max_ram_required_gpu_ram_or_system_ram_can/ | false | false | 1 | null | |
P40 or rtx 3060 ? | 8 | Hello everyone I am building my first small llm workstation. I will probably need it for a project I am currently playing around and if I get lucky I will get to write my dr. About and have accesse to alot more horsepower. But that might take a while.
So until then I want to have my own system that can run some basic... | 2024-01-08T02:19:06 | https://www.reddit.com/r/LocalLLaMA/comments/1919wc9/p40_or_rtx_3060/ | Noxusequal | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 1919wc9 | false | null | t3_1919wc9 | /r/LocalLLaMA/comments/1919wc9/p40_or_rtx_3060/ | false | false | self | 8 | null |
Innovative Approach to Enhance LLMs: Specialized 1B Model Integration into a 70B Model | 20 | Given the significant computational demands and complexities involved in training immense models (like those requiring A100/H100 GPUs), I started thinking about a more resource-efficient strategy. My idea revolves around initially developing a specialized 1B-parameter model in a narrowly defined domain so that my RTX30... | 2024-01-08T02:10:15 | https://www.reddit.com/r/LocalLLaMA/comments/1919pg4/innovative_approach_to_enhance_llms_specialized/ | Own_Relationship8953 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 1919pg4 | false | null | t3_1919pg4 | /r/LocalLLaMA/comments/1919pg4/innovative_approach_to_enhance_llms_specialized/ | false | false | self | 20 | null |
AI to Analyze Logbook Realtime (not GenAI) | 1 | Hi, I know this may not be the right forum as the topic is now directly related to Generative AI. Any guidance appreciated!
I am investing some effort to plug in AI/LLM with Home Assistant (smart home self hosted open source solution). My initial goal is to make available the Logbook and other data generated by HA to ... | 2024-01-08T01:44:08 | https://www.reddit.com/r/LocalLLaMA/comments/19195c0/ai_to_analyze_logbook_realtime_not_genai/ | cfurini | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 19195c0 | false | null | t3_19195c0 | /r/LocalLLaMA/comments/19195c0/ai_to_analyze_logbook_realtime_not_genai/ | false | false | self | 1 | null |
I Ran Advanced LLMs on the Raspberry Pi 5! | 1 | 2024-01-08T01:42:43 | https://rb.gy/mc6dlp | tim_macgyver | rb.gy | 1970-01-01T00:00:00 | 0 | {} | 191948o | false | null | t3_191948o | /r/LocalLLaMA/comments/191948o/i_ran_advanced_llms_on_the_raspberry_pi_5/ | false | false | 1 | {'enabled': False, 'images': [{'id': 'iAGKKvfraWCYFq8sA-9BxpVmV-jbiItHck_-cRL6N-Q', 'resolutions': [{'height': 60, 'url': 'https://external-preview.redd.it/o0NtlsBlOLnV2A3grHb9O_UhPG3lh7mwQvAzhVP-jXc.jpg?width=108&crop=smart&auto=webp&s=7a11a22f756a5cdc28de62f5d43393f1de208f3d', 'width': 108}, {'height': 121, 'url': 'h... | ||
NVIDIA RTX 5880 48GB GDDR6 Ada Generation Graphics Card | 1 | It's coming.
The model parameters are getting smaller and the devices are getting bigger.
https://preview.redd.it/tm9bd1vs74bc1.png?width=868&format=png&auto=webp&s=efae675166b1f2e792a3974a4b07c76bbcc3c04c
[https://www.nvidia.com/en-us/design-visualization/rtx-5880/](https://www.nvidia.com/en-us/design-visualization... | 2024-01-08T01:04:33 | https://www.reddit.com/r/LocalLLaMA/comments/1918acu/nvidia_rtx_5880_48gb_gddr6_ada_generation/ | sapporonight | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 1918acu | false | null | t3_1918acu | /r/LocalLLaMA/comments/1918acu/nvidia_rtx_5880_48gb_gddr6_ada_generation/ | false | false | 1 | null | |
LLM that text messages like a teenager? | 1 | Has anyone tried any LLMs that can emulate text message conversations between teenagers? I’m specifically looking for shorter text output with little emphasis on grammar and punctuations. All models I’ve tried output larger text output. I’ve tried mentioning in prompt to never exceed ‘x’ number of words but it doesn’t ... | 2024-01-08T00:27:54 | https://www.reddit.com/r/LocalLLaMA/comments/1917gfm/llm_that_text_messages_like_a_teenager/ | RepresentativeOdd276 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 1917gfm | false | null | t3_1917gfm | /r/LocalLLaMA/comments/1917gfm/llm_that_text_messages_like_a_teenager/ | false | false | self | 1 | null |
Run an own model as personal assistant? | 5 | Hello everyone,
I love LLMs and what they can do but i don't want to give shady black box in a cloud all my private thoughts and data.
Is it possible to not only run a pretrained model locally but actually constantly fine tune / enhance this model?
I want a model that actually knows all my data and remembers all pre... | 2024-01-08T00:23:12 | https://www.reddit.com/r/LocalLLaMA/comments/1917co5/run_an_own_model_as_personal_assistant/ | Some-Thoughts | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 1917co5 | false | null | t3_1917co5 | /r/LocalLLaMA/comments/1917co5/run_an_own_model_as_personal_assistant/ | false | false | self | 5 | null |
Chat templates after model merging using SLERP | 1 | Hi guys, I am new to model merging and am trying to merge some models to see how the newer ones turn out. I am planning to merge two mistral 7b finetunes with different chat templates (like OpenHermes-2.5 and Mistral-Instruct). What should I use as the chat template for the final model? Will either of the chat template... | 2024-01-08T00:00:18 | https://www.reddit.com/r/LocalLLaMA/comments/1916thr/chat_templates_after_model_merging_using_slerp/ | WillingMood2319 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 1916thr | false | null | t3_1916thr | /r/LocalLLaMA/comments/1916thr/chat_templates_after_model_merging_using_slerp/ | false | false | self | 1 | null |
Would you like to build a multilingual model? We present TaCo 🌮 🌮 (Translation-Assisted Chain-of-Thought Processes) method along with Alpaca-52K, Dolly-15K, and the Vicuña Benchmark datasets, available in 132 languages | 1 | [removed] | 2024-01-07T23:55:03 | https://www.reddit.com/r/LocalLLaMA/comments/1916ozv/would_you_like_to_build_a_multilingual_model_we/ | bibek_LLMs | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 1916ozv | false | null | t3_1916ozv | /r/LocalLLaMA/comments/1916ozv/would_you_like_to_build_a_multilingual_model_we/ | false | false | 1 | null | |
🐺🐦⬛ LLM Comparison/Test: Confirm Leaderboard? Big News! (SOLAR+Bagle+Mixtral/Yi) | 227 | The Hugging Face Leaderboard has been taken over by first SOLAR, then Bagel, and now some Yi-based (incorrectly) Mixtral-named models - and I'm doing my best to keep up with all that and provide additional evaluations as usual!
Will my tests confirm or refute their rankings? Spoiler: There's some big news ahead!
So w... | 2024-01-07T23:34:42 | https://www.reddit.com/r/LocalLLaMA/comments/1916896/llm_comparisontest_confirm_leaderboard_big_news/ | WolframRavenwolf | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 1916896 | false | null | t3_1916896 | /r/LocalLLaMA/comments/1916896/llm_comparisontest_confirm_leaderboard_big_news/ | false | false | self | 227 | {'enabled': False, 'images': [{'id': 'bDW7jyCB5L7RKBwRUqrzWSn3bIb_Szu_GogYRebiCjw', 'resolutions': [{'height': 54, 'url': 'https://external-preview.redd.it/tj8OYAHtgushFKKBfbCCyLFmzL7PWZ-Wz8cbqYk-I9E.jpg?width=108&crop=smart&auto=webp&s=f076a50b0d594dc8ba3b2ee703d67664decf1cba', 'width': 108}, {'height': 108, 'url': 'h... |
Finishing out my vacation by releasing the website for my llama.cpp web tool Epistemology | 2 | 2024-01-07T22:58:17 | https://epistemology.dev/ | richardanaya | epistemology.dev | 1970-01-01T00:00:00 | 0 | {} | 1915cfp | false | null | t3_1915cfp | /r/LocalLLaMA/comments/1915cfp/finishing_out_my_vacation_by_releasing_the/ | false | false | 2 | {'enabled': False, 'images': [{'id': 'i4xb5XRw775M6iSuK95lZvLwxeUu2rp9q58t16xb0Lo', 'resolutions': [{'height': 56, 'url': 'https://external-preview.redd.it/ofnrnjdIaRRhGf_0DNFY_QsoT6LIml3wX0dZ-q_nliM.jpg?width=108&crop=smart&auto=webp&s=2a0af4c889c4ab63354c53966f5dbc713047808d', 'width': 108}, {'height': 113, 'url': 'h... | ||
How to fine tune Llama CPP | 0 | Hi, I'm quite a beginner in the llama cpp enviroment and I was wondering if there was any way of fine tunning this version CPU compiled version of llama. I'm currently working with llama-2-13b-chat.ggmlv3.q5\_1.bin from [https://huggingface.co/TheBloke](https://huggingface.co/TheBloke) and I dont know if these kind of ... | 2024-01-07T22:55:28 | https://www.reddit.com/r/LocalLLaMA/comments/19159z2/how_to_fine_tune_llama_cpp/ | Responsible-Sky8889 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 19159z2 | false | null | t3_19159z2 | /r/LocalLLaMA/comments/19159z2/how_to_fine_tune_llama_cpp/ | false | false | self | 0 | {'enabled': False, 'images': [{'id': 'lkhHJv8mdJqfRh1UwBmzWCTs0H4Inw2Ugpa0eeRnBck', 'resolutions': [{'height': 58, 'url': 'https://external-preview.redd.it/2XWjLZRgmp4gyRdh7UWJJdFGyHYAlWYL9Q-rEfrT1Zs.jpg?width=108&crop=smart&auto=webp&s=de723b6ad3db101dc616591260b08a417f299523', 'width': 108}, {'height': 116, 'url': 'h... |
Looking for beta testers for wiseone.ai | 100 | I'm launching an ai platform that i built on llama, called wiseone.ai. Basically, it's the only platform around that provides an affordable, holistic analysis for stocks and digital assets. Providing real-time signals for changes in the 3 pillars of price action (social, charting, and fundamentals). | 2024-01-07T22:48:00 | https://v.redd.it/inxbxwq7k3bc1 | 2ez4irl | v.redd.it | 1970-01-01T00:00:00 | 0 | {} | 191532w | false | {'reddit_video': {'bitrate_kbps': 2400, 'dash_url': 'https://v.redd.it/inxbxwq7k3bc1/DASHPlaylist.mpd?a=1707259696%2CNDhlYzA0ZDAyODNlYWQzZDRhNjU0ZjdiYWNkNmJlMTAwOGViMDYyYTI5NTBkNDQyZjhiNGIwNjJhMDc0N2JkNA%3D%3D&v=1&f=sd', 'duration': 38, 'fallback_url': 'https://v.redd.it/inxbxwq7k3bc1/DASH_720.mp4?source=fallback', 'ha... | t3_191532w | /r/LocalLLaMA/comments/191532w/looking_for_beta_testers_for_wiseoneai/ | false | false | 100 | {'enabled': False, 'images': [{'id': 'eml1eWFlbjdrM2JjMcZxIT-GEJ4Veh-mzFgzTTW_OyiCHUNS8HSdMzUXm7XZ', 'resolutions': [{'height': 111, 'url': 'https://external-preview.redd.it/eml1eWFlbjdrM2JjMcZxIT-GEJ4Veh-mzFgzTTW_OyiCHUNS8HSdMzUXm7XZ.png?width=108&crop=smart&format=pjpg&auto=webp&s=a67a74945828cba7ec8dad0f52b6a0b95ef9... | |
🚀 Completely Local RAG with Ollama Web UI, in Two Docker Commands! | 59 | Hey everyone!
We're back with some fantastic news! Following [your invaluable feedback on ollama-webui,](https://www.reddit.com/r/LocalLLaMA/comments/17edvbx/run_local_llms_with_a_userfriendly_web_ui_in_two/) we've supercharged our webui with new, powerful features, making it the ultimate choice for local LLM enthusi... | 2024-01-07T22:17:43 | https://www.reddit.com/r/LocalLLaMA/comments/1914cam/completely_local_rag_with_ollama_web_ui_in_two/ | tjrbk | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 1914cam | false | null | t3_1914cam | /r/LocalLLaMA/comments/1914cam/completely_local_rag_with_ollama_web_ui_in_two/ | false | false | 59 | {'enabled': False, 'images': [{'id': 'dhTlZh6SNGgRTcdqNn28yyk8s08fh45qFB9w-MvugLE', 'resolutions': [{'height': 54, 'url': 'https://external-preview.redd.it/DwiE0gsZon6vpLAZYNzK4qeabUX2fSE9h6XvRAY_ChM.jpg?width=108&crop=smart&auto=webp&s=f8d17ebe5c7b996e8ee1a5acf34a24847e1ca1ce', 'width': 108}, {'height': 108, 'url': 'h... | |
7b models long multiturn test 2: mixtrals, kunoichi, laser +more | 32 | long story short: most models score a little too well on benchmark and then underperform in real chatting. I needed a way to stack and rank tunes to find the best for my purposes. I built a fixed long twisting chat with 30+ messages and I'm scoring it with gpt, which is far from ideal, but it's at least something I can... | 2024-01-07T22:14:23 | https://www.reddit.com/r/LocalLLaMA/comments/19149av/7b_models_long_multiturn_test_2_mixtrals_kunoichi/ | LoSboccacc | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 19149av | false | null | t3_19149av | /r/LocalLLaMA/comments/19149av/7b_models_long_multiturn_test_2_mixtrals_kunoichi/ | false | false | self | 32 | null |
GPT 4 was released on 14th March 2023. GPT 4V was released on 25th September 2023. | 5 | If Google release Gemini Ultra which is fully multimodal In January 2024, they would not be that far behind OpenAI.
Even if OpenAI releases GPT 4.5 in January, rumors are that Gemini 2 is already in training and will compete with GPT 5. It may even be released before GPT 5.
Llama 3 will be released in February suppo... | 2024-01-07T22:09:06 | https://www.reddit.com/r/LocalLLaMA/comments/19144gp/gpt_4_was_released_on_14th_march_2023_gpt_4v_was/ | TysonUsykFury | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 19144gp | false | null | t3_19144gp | /r/LocalLLaMA/comments/19144gp/gpt_4_was_released_on_14th_march_2023_gpt_4v_was/ | false | false | self | 5 | null |
It only costs an arm, a leg and your firstborn’s college tuition | 1 | 2024-01-07T22:05:26 | ZABKA_TM | i.redd.it | 1970-01-01T00:00:00 | 0 | {} | 191415o | false | null | t3_191415o | /r/LocalLLaMA/comments/191415o/it_only_costs_an_arm_a_leg_and_your_firstborns/ | false | false | 1 | {'enabled': True, 'images': [{'id': 'CkUe7BDLCKRD6oE35WZWPXTcMiBJmgPwgz00E7xnY5I', 'resolutions': [{'height': 81, 'url': 'https://preview.redd.it/19y8eoikc3bc1.jpeg?width=108&crop=smart&auto=webp&s=2d7bc7a3ede79bf9b00beeefb9a1131a3ffcf933', 'width': 108}, {'height': 162, 'url': 'https://preview.redd.it/19y8eoikc3bc1.jp... | |||
GLAI (gguf llama ai) was updated to v0.1.1 ! | 3 | Hi, big updated for the glai project,
Updated to v0.1.1
Large refactor to move ModeDB to a separate package (which is done now).
More details on the new dedicated package here [https://www.reddit.com/r/LocalLLaMA/comments/190k9ps/a\_database\_to\_automatically\_handle\_gguf\_lama/?utm\_source=share&utm\_medium=w... | 2024-01-07T21:41:02 | https://www.reddit.com/r/LocalLLaMA/comments/1913fas/glai_gguf_llama_ai_was_updated_to_v011/ | --lael-- | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 1913fas | false | null | t3_1913fas | /r/LocalLLaMA/comments/1913fas/glai_gguf_llama_ai_was_updated_to_v011/ | false | false | self | 3 | null |
llama2:13b bug or a feature? | 1 | ​
Is the model really narrowed down to tech topics as it eventually answering non tech question?
​
https://preview.redd.it/gq7v5pk753bc1.png?width=635&format=png&auto=webp&s=66752e5ee345f85e612b2fed273d08d8da494d25 | 2024-01-07T21:26:34 | https://www.reddit.com/r/LocalLLaMA/comments/191328g/llama213b_bug_or_a_feature/ | speacexstarlink | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 191328g | false | null | t3_191328g | /r/LocalLLaMA/comments/191328g/llama213b_bug_or_a_feature/ | false | false | 1 | null | |
What are some SoTA settings for *fast* inference? | 3 | I'm running Mistral (tunes) and Mixtral, and trying to get more **tok/s**, even in batch mode, for the sake of generating synth datasets.
I'm interested in both CPU-only and GPU-only inference.
* The `unsloth` library claims 5-20x faster training via custom Triton kernels, does anything like this exist to help infere... | 2024-01-07T21:23:10 | https://www.reddit.com/r/LocalLLaMA/comments/1912z9v/what_are_some_sota_settings_for_fast_inference/ | BayesMind | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 1912z9v | false | null | t3_1912z9v | /r/LocalLLaMA/comments/1912z9v/what_are_some_sota_settings_for_fast_inference/ | false | false | self | 3 | null |
Ay r/LocalLLaMA got to 100k subs | 1 | [removed] | 2024-01-07T21:09:01 | https://www.reddit.com/r/LocalLLaMA/comments/1912mev/ay_rlocalllama_got_to_100k_subs/ | PopcaanFan | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 1912mev | false | null | t3_1912mev | /r/LocalLLaMA/comments/1912mev/ay_rlocalllama_got_to_100k_subs/ | false | false | self | 1 | null |
Mixtral won't stop mentioning the provided context in RAG use-case | 2 | Has anyone had success using Mixtral-Instruct for Retrieval Augmented Generation? I can't get it to stop mentioning the provided context in the answer (eg it will respond "Based on the provided context blah blah blah"). I've tried instructing it to not mention the provided context in both the system and user prompt wi... | 2024-01-07T20:58:52 | https://www.reddit.com/r/LocalLLaMA/comments/1912co3/mixtral_wont_stop_mentioning_the_provided_context/ | Preacher2013 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 1912co3 | false | null | t3_1912co3 | /r/LocalLLaMA/comments/1912co3/mixtral_wont_stop_mentioning_the_provided_context/ | false | false | self | 2 | null |
Different attacks on machine learning models | 6 | 2024-01-07T20:52:04 | https://rnikhil.com/2024/01/07/attacking-neural-networks.html | Excellent-Effect237 | rnikhil.com | 1970-01-01T00:00:00 | 0 | {} | 19126pu | false | null | t3_19126pu | /r/LocalLLaMA/comments/19126pu/different_attacks_on_machine_learning_models/ | false | false | default | 6 | null | |
Hey UI developers: Please include screenshots of your UI! | 65 | I've been UI shopping lately, since text-gen-webui is ugly, constantly has to be re-set up every restart, and crashes fully if GGUFs exceed VRAM limit. Exui is nice, but overly simplistic and you can't use GGUFs with it.
There are a couple dozen UIs out there that I know of, and for some reason, less than half of them... | 2024-01-07T20:46:13 | https://www.reddit.com/r/LocalLLaMA/comments/19121n4/hey_ui_developers_please_include_screenshots_of/ | Arcturus17 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 19121n4 | false | null | t3_19121n4 | /r/LocalLLaMA/comments/19121n4/hey_ui_developers_please_include_screenshots_of/ | false | false | self | 65 | null |
[Urgent] can I make a Llama2 based app which doesn't have to be run on PyTorch? | 1 | Where else can I run it on? | 2024-01-07T20:34:54 | https://www.reddit.com/r/LocalLLaMA/comments/1911riy/urgent_can_i_make_a_llama2_based_app_which_doesnt/ | Accomplished_Cod1099 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 1911riy | false | null | t3_1911riy | /r/LocalLLaMA/comments/1911riy/urgent_can_i_make_a_llama2_based_app_which_doesnt/ | false | false | self | 1 | null |
LM Studio - Dolphin 2.7 Mixtral: Stop Generating problem | 1 | Hello guys, I'm using LM studio.
I've tried Dolphin 2.7, as a potential upgrade in creativity, instead of Mixtral Instruct 0.1.
I have a problem, though. In Mixtral Instruct, I can press stop generating, then input another prompt and the LLM responds to it.
But in Dolphin, if I stop it from generating and put somet... | 2024-01-07T20:31:16 | https://www.reddit.com/r/LocalLLaMA/comments/1911oc1/lm_studio_dolphin_27_mixtral_stop_generating/ | PwanaZana | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 1911oc1 | false | null | t3_1911oc1 | /r/LocalLLaMA/comments/1911oc1/lm_studio_dolphin_27_mixtral_stop_generating/ | false | false | self | 1 | null |
LiteLlama-460M-1T has 460M parameters trained with 1T tokens | 14 | 2024-01-07T20:28:23 | https://huggingface.co/ahxt/LiteLlama-460M-1T | davidmezzetti | huggingface.co | 1970-01-01T00:00:00 | 0 | {} | 1911lol | false | null | t3_1911lol | /r/LocalLLaMA/comments/1911lol/litellama460m1t_has_460m_parameters_trained_with/ | false | false | 14 | {'enabled': False, 'images': [{'id': 'CfyzbUAmgYUP62Lw81UgnUe8zRwF7BdkrW-By2_ZIk4', 'resolutions': [{'height': 58, 'url': 'https://external-preview.redd.it/I5g8tjLEDWzCuTN1ZJkfoCVlXoy7weyFgDlHR9h-WVM.jpg?width=108&crop=smart&auto=webp&s=e846d3a16596d2fc2bdf5cbc075f282ea4afa5ba', 'width': 108}, {'height': 116, 'url': 'h... | ||
What are some good setups to learn about orchestrating model training / ML infrastructure in general? | 1 | Hello! I’m pretty new to this topic so apologies for any silly questions. I see alot of the topics here related to home setups usually revolve around hosting local models, but is the same type of setup necessary if I just want to learn about the infrastructure? For example, is model training on 3080s vs 4080s (random e... | 2024-01-07T20:10:43 | https://www.reddit.com/r/LocalLLaMA/comments/19115pm/what_are_some_good_setups_to_learn_about/ | ifjo | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 19115pm | false | null | t3_19115pm | /r/LocalLLaMA/comments/19115pm/what_are_some_good_setups_to_learn_about/ | false | false | self | 1 | null |
My first pipeline using Llama7b / llvm / Langchain / EasyOCR / TinyDB | 11 | I am really happy with the result so I feel the urge to share. Hope it matches the community interest.
I started exploring self hosted AI for a while now, I had a hard time finding out an architecture that had the following requirement:
- Have openai api compatibility, so that I can fallback to using openai if the... | 2024-01-07T20:01:36 | https://www.reddit.com/r/LocalLLaMA/comments/1910xpv/my_first_pipeline_using_llama7b_llvm_langchain/ | MoiSanh | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 1910xpv | false | null | t3_1910xpv | /r/LocalLLaMA/comments/1910xpv/my_first_pipeline_using_llama7b_llvm_langchain/ | false | false | self | 11 | null |
Added JSON generation and streaming with automatic GBNF grammars for JSON schemas to ModelFusion JS/TS client for llama.cpp server | 4 | 2024-01-07T19:46:38 | https://modelfusion.dev/integration/model-provider/llamacpp#generate-structure | lgrammel | modelfusion.dev | 1970-01-01T00:00:00 | 0 | {} | 1910krj | false | null | t3_1910krj | /r/LocalLLaMA/comments/1910krj/added_json_generation_and_streaming_with/ | false | false | 4 | {'enabled': False, 'images': [{'id': 'a-4ml4TxskRWZByl6AYAgCO7u-aGfpUrtD4m7IFAD0A', 'resolutions': [{'height': 45, 'url': 'https://external-preview.redd.it/dzyL6Wk_q-n0FVZ4QBrA9-TfzgiPEgKg32VhjehevuE.jpg?width=108&crop=smart&auto=webp&s=4d509c8940e445f9070b094b77ec7226a76ea9da', 'width': 108}, {'height': 90, 'url': 'ht... | ||
How did I miss this? During Q-star speculation drama, Yann LeCun said Sam Altman has a long track record of self delusion. Either Mr. LeCun is arrogant or he has a mole inside OpenAI who informed him that Q-Star is all hype, no breakthrough. | 1 | 2024-01-07T19:28:44 | https://www.reddit.com/gallery/19105lz | TysonUsykFury | reddit.com | 1970-01-01T00:00:00 | 0 | {} | 19105lz | false | null | t3_19105lz | /r/LocalLLaMA/comments/19105lz/how_did_i_miss_this_during_qstar_speculation/ | false | false | 1 | null | ||
Cpu with gpu offloading oobabooga | 1 | I have an amd ryzen 9 7940hs with an integrated graphics card which has 20gb of storage( vram i proposes) is it possible to use bith my cpu and integrated gpu? If yes how | 2024-01-07T19:23:25 | https://www.reddit.com/r/LocalLLaMA/comments/19100xc/cpu_with_gpu_offloading_oobabooga/ | Single-Cow-5163 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 19100xc | false | null | t3_19100xc | /r/LocalLLaMA/comments/19100xc/cpu_with_gpu_offloading_oobabooga/ | false | false | self | 1 | null |
It finally happened: lmsys Chat Arena is also gamed: Multiple <70B models ranked higher than Llama 2 70B. Example: Starling 7B suspiciously ranked above Llama 2 70B and Perplexity 70B. | 1 | 2024-01-07T19:15:45 | nderstand2grow | i.redd.it | 1970-01-01T00:00:00 | 0 | {} | 190zuix | false | null | t3_190zuix | /r/LocalLLaMA/comments/190zuix/it_finally_happened_lmsys_chat_arena_is_also/ | false | false | 1 | {'enabled': True, 'images': [{'id': 'upVxFz7emM-wkjAmejcvxSJI_nx03VjSNIGQszL3YAM', 'resolutions': [{'height': 61, 'url': 'https://preview.redd.it/zdl6om0bi2bc1.png?width=108&crop=smart&auto=webp&s=8db2f2694e388a517e6daa58958878f4ce56a4aa', 'width': 108}, {'height': 123, 'url': 'https://preview.redd.it/zdl6om0bi2bc1.png... | |||
Venus 120b v1.2 | 35 | https://huggingface.co/nsfwthrowitaway69/Venus-120b-v1.2
Hey everyone, this week I got around to creating another frankenmerge model in the "Venus" lineup. For this one I only used a single model: lzlv_70b. Out of all the 70b models I've used, this one overall has the best combination of instruction following and crea... | 2024-01-07T19:13:23 | https://www.reddit.com/r/LocalLLaMA/comments/190zsk1/venus_120b_v12/ | nsfw_throwitaway69 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 190zsk1 | false | null | t3_190zsk1 | /r/LocalLLaMA/comments/190zsk1/venus_120b_v12/ | false | false | self | 35 | null |
Tips for Following the Latest News and Finding Quality Content on LLMs without Doomscrolling? | 26 | I'm deeply interested in LLMs, and I'm looking to stay updated with the latest ideas, papers, and developments in this field. Platforms like Twitter, Reddit, and YouTube are rich in content, but I often find myself doomscrolling through endless feeds, which can be overwhelming and time-consuming.
I'd love to hear your... | 2024-01-07T19:04:44 | https://www.reddit.com/r/LocalLLaMA/comments/190zl85/tips_for_following_the_latest_news_and_finding/ | alpsencer | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 190zl85 | false | null | t3_190zl85 | /r/LocalLLaMA/comments/190zl85/tips_for_following_the_latest_news_and_finding/ | false | false | self | 26 | null |
Fine-tuning for Natural Language to SPARQL queries | 1 | I'm trying to fine-tune a LLM to generate SPARQL from natural language. I started with llama but I quickly ran out of credits on Google Colab. Now I'm waiting for my university to grant me access to their cloud resources. Until then what other models do you recommend? Currently I'm playing with Flan-T5, is it worth fin... | 2024-01-07T18:46:27 | https://www.reddit.com/r/LocalLLaMA/comments/190z57f/finetuning_for_natural_language_to_sparql_queries/ | Optimal_Fishing2072 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 190z57f | false | null | t3_190z57f | /r/LocalLLaMA/comments/190z57f/finetuning_for_natural_language_to_sparql_queries/ | false | false | self | 1 | null |
[SUGGESTION] Suggestion for an LLM API Server with document ingestion support | 1 | Hi everyone,
what open source LLM server do you suggest me with API support for chat, document ingestion and document querying?
​
What I want to achieve is to create a .NET client, possibly a Desktop Application, that can manage the server, therefore start and stop and can interact with it with an API that a... | 2024-01-07T18:24:36 | https://www.reddit.com/r/LocalLLaMA/comments/190ym9b/suggestion_suggestion_for_an_llm_api_server_with/ | darcome | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 190ym9b | false | null | t3_190ym9b | /r/LocalLLaMA/comments/190ym9b/suggestion_suggestion_for_an_llm_api_server_with/ | false | false | self | 1 | null |
I just now added a paragraph to the Wikipedia article on Generative AI regarding open-source, including mention of r/LocalLLaMA | 17 | 2024-01-07T17:48:59 | https://en.wikipedia.org/w/index.php?title=Generative_artificial_intelligence&diff=1194184338&oldid=1194158714 | michaelmalak | en.wikipedia.org | 1970-01-01T00:00:00 | 0 | {} | 190xrz1 | false | null | t3_190xrz1 | /r/LocalLLaMA/comments/190xrz1/i_just_now_added_a_paragraph_to_the_wikipedia/ | false | false | 17 | {'enabled': False, 'images': [{'id': 'rlzXjNiW5fnwpwzacq9hjZb6-rTg3zw5OzhBYt44w5k', 'resolutions': [{'height': 72, 'url': 'https://external-preview.redd.it/fKR_a9c_RY0cGt7_njxh2i6BrTeIrQx_hOJRF6zZfSU.jpg?width=108&crop=smart&auto=webp&s=fefb1e59ea2c639d8f10bc43a9ef243065d7f504', 'width': 108}, {'height': 144, 'url': 'h... | ||
Can a RAG in conjunction with an LLM create a simulated version of consciousness? | 1 | In this scenario, using a RAG setup to "save" memories or experiences from interactions involves storing them in a retrievable, vectorized database. The language model would then access these stored memories when relevant to a given situation, effectively using past interactions to inform its current responses.
The ch... | 2024-01-07T17:43:40 | https://www.reddit.com/r/LocalLLaMA/comments/190xnij/can_a_rag_in_conjunction_with_an_llm_create_a/ | ApprehensiveJob171 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 190xnij | false | null | t3_190xnij | /r/LocalLLaMA/comments/190xnij/can_a_rag_in_conjunction_with_an_llm_create_a/ | false | false | self | 1 | null |
Cant continue old chats | 3 | Am I the only one who cant continue chats after i close them with shorter chats its manageable but the more tokens the longer they take to load to the point where after like 2000 tokens they dont load anymore while rp there's no problem and im not maxing out my ram either. Im running in cpu only | 2024-01-07T17:42:09 | https://www.reddit.com/r/LocalLLaMA/comments/190xm5x/cant_continue_old_chats/ | Single-Cow-5163 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 190xm5x | false | null | t3_190xm5x | /r/LocalLLaMA/comments/190xm5x/cant_continue_old_chats/ | false | false | self | 3 | null |
Used GPT4ALL for the first time and wondering if I could somehow feed it (technical) PDFs and turn it into "sidekick" for embedded programming? | 5 | I've just encountered a YT video that talked about GPT4ALL and it got me really curious, as I've always liked Chat-GPT - until it got bad.
I'm doing some embedded programming on all kinds of hardware - like STM32 Nucleo boards and Intel based FPGAs, and every board I own comes with a huge technical PDF that specificie... | 2024-01-07T17:26:15 | https://www.reddit.com/r/LocalLLaMA/comments/190x884/used_gpt4all_for_the_first_time_and_wondering_if/ | SaarN | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 190x884 | false | null | t3_190x884 | /r/LocalLLaMA/comments/190x884/used_gpt4all_for_the_first_time_and_wondering_if/ | false | false | self | 5 | null |
Mixtral vs Mistral Medium | 2 | Does anyone have a viewpoint about which is best given that they have been out for some time now. | 2024-01-07T16:51:39 | https://www.reddit.com/r/LocalLLaMA/comments/190wfaf/mixtral_vs_mistral_medium/ | ComprehensiveWord477 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 190wfaf | false | null | t3_190wfaf | /r/LocalLLaMA/comments/190wfaf/mixtral_vs_mistral_medium/ | false | false | self | 2 | null |
RAG for RPG Rules and Years of Campaign Data - Feasibility and Limitations? | 13 | A friend asked me if it is possible to put all those data (mostly pdf, excel sheets and latex) into a llm and get useful information. I know RAG is one of the possible solutions, but i can not find good information on how large the data can be for single documents or in whole. also on how truthful all the answers will ... | 2024-01-07T16:51:06 | https://www.reddit.com/r/LocalLLaMA/comments/190wetc/rag_for_rpg_rules_and_years_of_campaign_data/ | _ralph_ | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 190wetc | false | null | t3_190wetc | /r/LocalLLaMA/comments/190wetc/rag_for_rpg_rules_and_years_of_campaign_data/ | false | false | self | 13 | null |
LLM + translate model vs Finetuning from scratch | 1 | [removed] | 2024-01-07T16:49:36 | https://www.reddit.com/r/LocalLLaMA/comments/190wdi8/llm_translate_model_vs_finetuning_from_scratch/ | maayon | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 190wdi8 | false | null | t3_190wdi8 | /r/LocalLLaMA/comments/190wdi8/llm_translate_model_vs_finetuning_from_scratch/ | false | false | self | 1 | {'enabled': False, 'images': [{'id': 'nMQgcA_y0RC4hgFePWX8SlBkPjhSXRjtB_ZiIK-2zK4', 'resolutions': [{'height': 54, 'url': 'https://external-preview.redd.it/WWZy1A3cELSjML621MsbIuDR9vvH8NMpjCuaHv_Cw_U.jpg?width=108&crop=smart&auto=webp&s=c441b9f66175340fee4d0c143cb9c89bca6d4cd5', 'width': 108}, {'height': 108, 'url': 'h... |
Thinks to look for in a PC build for AI | 3 | So I am thinking of building a new computer with a strong focus on being able to run models like llama 7b and mixtral 8x7b locally, and I was wondering what I should focus on. A while back I heard everyone saying a good GPU was important with a lot of vram. But now I feel like I hear a lot of people saying ram and cpu ... | 2024-01-07T16:48:40 | https://www.reddit.com/r/LocalLLaMA/comments/190wcsg/thinks_to_look_for_in_a_pc_build_for_ai/ | Schenk06 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 190wcsg | false | null | t3_190wcsg | /r/LocalLLaMA/comments/190wcsg/thinks_to_look_for_in_a_pc_build_for_ai/ | false | false | self | 3 | null |
My Codellama model (merge + additional FT) Quantized as AWQ & GGUF | 15 | I held off on posting this because there are some who seem to enjoy going around and bashing models just because, and there was that one post a few weeks ago going off the rails implying that anyone doing merging was basically just in it to scam people.
However, a bunch of cool people here recommended I go ahead and... | 2024-01-07T16:42:47 | https://www.reddit.com/r/LocalLLaMA/comments/190w80c/my_codellama_model_merge_additional_ft_quantized/ | q5sys | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 190w80c | false | null | t3_190w80c | /r/LocalLLaMA/comments/190w80c/my_codellama_model_merge_additional_ft_quantized/ | false | false | self | 15 | {'enabled': False, 'images': [{'id': 'oheqXgiJdUktp8kctkFMNFrEv65NeVHIs3GKemvHMXg', 'resolutions': [{'height': 58, 'url': 'https://external-preview.redd.it/_WWv7A9e_AZ8Dj-8Anf5ZaHeYHalb3skMhuNk3wzk-w.jpg?width=108&crop=smart&auto=webp&s=d9f80099aa4f003718191b7912c8626687a56aea', 'width': 108}, {'height': 116, 'url': 'h... |
Does the inference time increase with longer inputs? | 3 | Hey, does the inference time (ms per token) change depending on how long the input is?
Let's say I have a text and want the LLM to give me a summary of the text. Does the speed of the LLM decrease when the text it summarizes is longer? And if so, how big will the difference be?
For example text1 is 100 token long an... | 2024-01-07T16:39:53 | https://www.reddit.com/r/LocalLLaMA/comments/190w5or/does_the_inference_time_increase_with_longer/ | Bluhbaerie | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 190w5or | false | null | t3_190w5or | /r/LocalLLaMA/comments/190w5or/does_the_inference_time_increase_with_longer/ | false | false | self | 3 | null |
How do I use MedPrompt with GPT? | 3 | I am trying to do research where I input different case reports and see what GPTs output. However, how do I implement MedPrompt architecture with GPTs?
[https://www.microsoft.com/en-us/research/blog/the-power-of-prompting/](https://www.microsoft.com/en-us/research/blog/the-power-of-prompting/)
[https://github.com/mic... | 2024-01-07T15:57:20 | https://www.reddit.com/r/LocalLLaMA/comments/190v71b/how_do_i_use_medprompt_with_gpt/ | InDebt2Medicine | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 190v71b | false | null | t3_190v71b | /r/LocalLLaMA/comments/190v71b/how_do_i_use_medprompt_with_gpt/ | false | false | self | 3 | {'enabled': False, 'images': [{'id': 'L9Iu-YaJRBYICojgBF-pdkfscUg3ao4hmHKLsANIQdY', 'resolutions': [{'height': 56, 'url': 'https://external-preview.redd.it/mOGfZtwLuTHmCdccq5tx_8hm9uAQnsyHScz8Fz8_nn0.jpg?width=108&crop=smart&auto=webp&s=cb6eeb00a7ffb3a23e1eb5eeecf563516da0807e', 'width': 108}, {'height': 112, 'url': 'h... |
Tip for writing stories: Don't use the word "Story" in your prompt | 135 | I've had a lot of issues when using LLMs to assist in writing story generations. Constantly, there seems to be a strong predisposition to write a conclusion to each section, write some moral that the character took away, or write about how they would overcome the challenges facing them and become stronger for their exp... | 2024-01-07T15:56:37 | https://www.reddit.com/r/LocalLLaMA/comments/190v6iu/tip_for_writing_stories_dont_use_the_word_story/ | Stepfunction | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 190v6iu | false | null | t3_190v6iu | /r/LocalLLaMA/comments/190v6iu/tip_for_writing_stories_dont_use_the_word_story/ | false | false | self | 135 | null |
llama.cpp CPU optimization | 25 | I love llama.cpp, so don't take this as a criticism of the project, but why does it peg every core to 100% when it's often waiting on IO anyway?
I have a 32 thread / 16 core CPU (Ryzen 3950x) and I did a test which shows that assigning 32 threads to do model inference is a complete waste of electricity. In fact runnin... | 2024-01-07T15:53:19 | https://www.reddit.com/r/LocalLLaMA/comments/190v426/llamacpp_cpu_optimization/ | noiserr | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 190v426 | false | null | t3_190v426 | /r/LocalLLaMA/comments/190v426/llamacpp_cpu_optimization/ | false | false | self | 25 | null |
Deploy TinyLlama as an API endpoint | 1 | SLMs (Small Language Models) are going to be a lot more powerful in 2024. And there must be an easy way to deploy and consume them on-demand for building applications.
So I created a colab notebook that enables you to quickly deploy and access TinyLlama 1.1B model on MonsterAPI as an API endpoint. This model was tra... | 2024-01-07T15:49:38 | https://www.reddit.com/r/LocalLLaMA/comments/190v19e/deploy_tinyllama_as_an_api_endpoint/ | gvij | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 190v19e | false | null | t3_190v19e | /r/LocalLLaMA/comments/190v19e/deploy_tinyllama_as_an_api_endpoint/ | false | false | self | 1 | {'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': '... |
adding a second GPU - another 3090 or a 4090? | 1 | I'm going to buy a second GPU soon to get more VRAM. Right now I have an RTX 3090. I could afford a 4090, but I'm wondering if there are benefits to having a second 3090 and NVLink versus a 3090 and a 4090. Anyone have any insights? | 2024-01-07T15:19:09 | https://www.reddit.com/r/LocalLLaMA/comments/190udev/adding_a_second_gpu_another_3090_or_a_4090/ | FortunaVelutLuna | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 190udev | false | null | t3_190udev | /r/LocalLLaMA/comments/190udev/adding_a_second_gpu_another_3090_or_a_4090/ | false | false | self | 1 | null |
Transform medical and research papers into knowledge bases with paperetl | 1 | 2024-01-07T15:18:28 | https://github.com/neuml/paperetl | davidmezzetti | github.com | 1970-01-01T00:00:00 | 0 | {} | 190ucva | false | null | t3_190ucva | /r/LocalLLaMA/comments/190ucva/transform_medical_and_research_papers_into/ | false | false | 1 | {'enabled': False, 'images': [{'id': 'Y4NWBFjNP3Ste9Mj_gsQpmzbF9z64vda_DCDA6v7Uw0', 'resolutions': [{'height': 54, 'url': 'https://external-preview.redd.it/ACIAQhlEJQHfEMePku9DdfiCcfYRsbfDqu-rbsE5OZc.jpg?width=108&crop=smart&auto=webp&s=593de29ec4004625d11a17d8823eed57aedf57d4', 'width': 108}, {'height': 108, 'url': 'h... | ||
[Question] Any updates on Flash Attention 2 build on Windows (Jan 2024)? | 1 | Hi all. A while ago, there was a discussion on making [Flash Attention 2 built on Windows](https://www.reddit.com/r/LocalLLaMA/comments/16skcwm/any_way_to_get_flash_attention_2_working_on/). However, I found that the information is currently obsolete, even though it is only about a few months old. I tried to reconcile ... | 2024-01-07T14:39:06 | https://www.reddit.com/r/LocalLLaMA/comments/190tich/question_any_updates_on_flash_attention_2_build/ | epicrob | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 190tich | false | null | t3_190tich | /r/LocalLLaMA/comments/190tich/question_any_updates_on_flash_attention_2_build/ | false | false | self | 1 | null |
has anyone analyzed how LLMs select 'random' stuff? | 7 | I am curious if there is any info out there on how a LLM choses randomness.
\`\`\`
Pick a random word from here:
\- apple
\- john
\- smith
\- freak
\- lion
\`\`\`
Tested on LoneStriker\_bagel-34b-v0.2-8.0bpw-h8-exl2 (never picked smith out of 30 tries, most were lion)
Tested on LoneStriker\_SUS-Chat-34B-8... | 2024-01-07T14:37:45 | https://www.reddit.com/r/LocalLLaMA/comments/190thet/has_anyone_analyzed_how_llms_select_random_stuff/ | shaman-warrior | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 190thet | false | null | t3_190thet | /r/LocalLLaMA/comments/190thet/has_anyone_analyzed_how_llms_select_random_stuff/ | false | false | self | 7 | null |
Convert BLOOM based model to gguf with llama.cpp | 1 | [removed] | 2024-01-07T14:37:38 | https://www.reddit.com/r/LocalLLaMA/comments/190thcb/convert_bloom_based_model_to_gguf_with_llamacpp/ | Christ0ph_ | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 190thcb | false | null | t3_190thcb | /r/LocalLLaMA/comments/190thcb/convert_bloom_based_model_to_gguf_with_llamacpp/ | false | false | 1 | {'enabled': False, 'images': [{'id': 'EuSxoJsoDqwQ__gF6pGtvT0fN-kj2YqM2WJYa1kBkN4', 'resolutions': [{'height': 36, 'url': 'https://external-preview.redd.it/fx_wZ2-ohfyb5W_ahn6ZVW3qOYRao3KFBtfsa9FyNBI.jpg?width=108&crop=smart&auto=webp&s=196af3f352b41ecb6a0526cf8cd2c41dceacd29c', 'width': 108}, {'height': 72, 'url': 'ht... | |
This is a bold prediction from Ilya Sutskever. Next token prediction = capable of superhuman performance. My question: does he specifically mean transformers here when he says base neural net? | 34 | 2024-01-07T13:57:14 | https://v.redd.it/pb8z8jyhx0bc1 | TysonUsykFury | /r/LocalLLaMA/comments/190sono/this_is_a_bold_prediction_from_ilya_sutskever/ | 1970-01-01T00:00:00 | 0 | {} | 190sono | false | {'reddit_video': {'bitrate_kbps': 5000, 'dash_url': 'https://v.redd.it/pb8z8jyhx0bc1/DASHPlaylist.mpd?a=1707357449%2CMTA5YjMwNTBmMzE5ODcyMGFkYmZhZDc2MjZhMWYwYjZhMDdiNmNjYzM2YTE4OWQwYjAzNTcxYzdmNTQzZjU1ZA%3D%3D&v=1&f=sd', 'duration': 127, 'fallback_url': 'https://v.redd.it/pb8z8jyhx0bc1/DASH_1080.mp4?source=fallback', '... | t3_190sono | /r/LocalLLaMA/comments/190sono/this_is_a_bold_prediction_from_ilya_sutskever/ | false | false | 34 | {'enabled': False, 'images': [{'id': 'NHlua3E3cGh4MGJjMUJqrwP9xesw1XpAJvjrZJyTxHbb9Si1bsVxYmYIdaA9', 'resolutions': [{'height': 60, 'url': 'https://external-preview.redd.it/NHlua3E3cGh4MGJjMUJqrwP9xesw1XpAJvjrZJyTxHbb9Si1bsVxYmYIdaA9.png?width=108&crop=smart&format=pjpg&auto=webp&s=6907c1f76814a7199b9ac66566b04dcc3ec69... | ||
Can someone give an overview of prompting strategies like tree search and the like ? | 4 | I am currently getting in to the preparations for my doctor thesis. I am relatively new to llms. I need to run text evaluations to filter out specific information from the texts and was wondering how different agants/ prompting methods could be leveraged for soemthing like this.
And I was hoping someone would be sonk... | 2024-01-07T13:17:48 | https://www.reddit.com/r/LocalLLaMA/comments/190rykd/can_someone_give_an_overview_of_prompting/ | Noxusequal | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 190rykd | false | null | t3_190rykd | /r/LocalLLaMA/comments/190rykd/can_someone_give_an_overview_of_prompting/ | false | false | self | 4 | null |
phi-2-GGUF outputs garbage | 3 | I downloaded 8bit quantized model: [https://huggingface.co/TheBloke/phi-2-GGUF](https://huggingface.co/TheBloke/phi-2-GGUF)
But it outputs not even "bad answers", it outputs garbage:
> Hello, how do I fix the car?
>
>AI
>
>{type: simple\_qa}
>
><|question|>Solve: -2x-1 <= x+5.8
>
><|question\_end|>An... | 2024-01-07T12:45:18 | https://www.reddit.com/r/LocalLLaMA/comments/190rdj1/phi2gguf_outputs_garbage/ | uti24 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 190rdj1 | false | null | t3_190rdj1 | /r/LocalLLaMA/comments/190rdj1/phi2gguf_outputs_garbage/ | false | false | self | 3 | {'enabled': False, 'images': [{'id': 'tn1ckeqsrgkW9jW-8WsYD4NdP_SIK1Y4pfa3EDSxFek', 'resolutions': [{'height': 58, 'url': 'https://external-preview.redd.it/0Br4yRVWMR7O3MqEgYuFvKJox2nri8zNRzhse9Sd2Ws.jpg?width=108&crop=smart&auto=webp&s=e956afb3e244d6ed2d92dcc2d5912b1e5ff5ca99', 'width': 108}, {'height': 116, 'url': 'h... |
Pre-training Mistral | 1 | Is it possible to do pre-training on Mistral? If so are there any guides on how to do this? | 2024-01-07T12:36:49 | https://www.reddit.com/r/LocalLLaMA/comments/190r8io/pretraining_mistral/ | BukHunt | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 190r8io | false | null | t3_190r8io | /r/LocalLLaMA/comments/190r8io/pretraining_mistral/ | false | false | self | 1 | null |
Long Context Recall Pressure Test - Batch 2 | 65 | **Approach**: Using Gregory Kamradt's **"Needle In A Haystack"** analysis, I explored models with different context lengths.
\- Needle: "What's the most fun thing to do in San Francisco?"
\- Haystack: Essays by Paul Graham
**Video explanation** by Gregory - [https://www.youtube.com/watch?v=KwRRuiCCdmc](https://www.y... | 2024-01-07T12:31:05 | https://www.reddit.com/r/LocalLLaMA/comments/190r59u/long_context_recall_pressure_test_batch_2/ | ramprasad27 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 190r59u | false | {'oembed': {'author_name': 'Greg Kamradt (Data Indy)', 'author_url': 'https://www.youtube.com/@DataIndependent', 'height': 200, 'html': '<iframe width="356" height="200" src="https://www.youtube.com/embed/KwRRuiCCdmc?feature=oembed&enablejsapi=1" frameborder="0" allow="accelerometer; autoplay; clipboard-write; encrypte... | t3_190r59u | /r/LocalLLaMA/comments/190r59u/long_context_recall_pressure_test_batch_2/ | false | false | 65 | {'enabled': False, 'images': [{'id': 'OondSl4tj1KDXy8pkUsxQBZHwCiKekJ00sdXFeRLzns', 'resolutions': [{'height': 81, 'url': 'https://external-preview.redd.it/k9s_HDytdOH3hMxsYPFIXN-bvkyOM7NyMIrsfE7ys2A.jpg?width=108&crop=smart&auto=webp&s=867a03d49cf317f8ccd573a6cbf632592dcee0e9', 'width': 108}, {'height': 162, 'url': 'h... | |
which model I can launch with a powerful phone ? | 1 | I have a realme gt 5 with 24 GB of ram + 12 virtually with a snapdragon 8 gen 2 do you have an idea of the best models to use? and also how, I am open to new techniques rather than continuing to use llama.cpp with termux... | 2024-01-07T12:10:23 | Terrible_Vegetable4 | i.redd.it | 1970-01-01T00:00:00 | 0 | {} | 190qtng | false | null | t3_190qtng | /r/LocalLLaMA/comments/190qtng/which_model_i_can_launch_with_a_powerful_phone/ | false | false | 1 | {'enabled': True, 'images': [{'id': 'kK55OdTMW9KALcQ9InAUMEfBZWU4gQe55Lu9Td5NK4s', 'resolutions': [{'height': 110, 'url': 'https://preview.redd.it/5qzqaqmge0bc1.jpeg?width=108&crop=smart&auto=webp&s=a8f68f738fd035403555a04ba482160a99de1a66', 'width': 108}, {'height': 220, 'url': 'https://preview.redd.it/5qzqaqmge0bc1.j... | ||
Open_Gpt4_8x7B -> This close to GPT4 locally??? | 1 | I am just thoroughly impressed with this model! It is based on Mixtral, but finetuned really nicely!
It even gets the notorious:
>I have 4 apples today. I ate 3 apples yesterday. How many apples do I have today?
Correct!
[smart co0k1e](https://preview.redd.it/2gdf6fsqb0bc1.png?width=1336&format=png&auto=webp&s=3856... | 2024-01-07T11:59:09 | https://www.reddit.com/r/LocalLLaMA/comments/190qn4l/open_gpt4_8x7b_this_close_to_gpt4_locally/ | nodating | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 190qn4l | false | null | t3_190qn4l | /r/LocalLLaMA/comments/190qn4l/open_gpt4_8x7b_this_close_to_gpt4_locally/ | false | false | 1 | {'enabled': False, 'images': [{'id': 'tmCNFAyh3_qCRhWXfTfOjTbmFmMkClsPbrrWgL5Lgxo', 'resolutions': [{'height': 58, 'url': 'https://external-preview.redd.it/F6C_QAhR1lDqwQ7C9EyXXnLqGVoFc-KcdGtmb9uXO7Q.jpg?width=108&crop=smart&auto=webp&s=9b2b5d3d22dc2c6e7f53a8eca8a5d61df6b2e562', 'width': 108}, {'height': 116, 'url': 'h... | |
Ideas for a future AL/LLM startup? | 1 | There have been many exciting companies related to LLM that have come into existence in the past 1 year or so.
What are the current pain points which are yet to be addressed properly which a future startup can work on?
It can be both in terms of foundational or applied LLM. | 2024-01-07T11:57:35 | https://www.reddit.com/r/LocalLLaMA/comments/190qmba/ideas_for_a_future_alllm_startup/ | satyajitdass | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 190qmba | false | null | t3_190qmba | /r/LocalLLaMA/comments/190qmba/ideas_for_a_future_alllm_startup/ | false | false | self | 1 | null |
After scraping the data of every company on the internet, OpenAI suspended Bytedance for using GPT-4 generated data. Then they have the gall to say the reason is that their technology should be used for GOOD. If using GPT-4 generated data makes Bytedance malevolent, then why even provide API access? | 48 | https://nypost.com/2023/12/18/business/openai-suspends-bytedances-account-after-it-allegedly-used-gpt-to-build-rival-ai-product-report/ | 2024-01-07T11:44:03 | TysonUsykFury | i.redd.it | 1970-01-01T00:00:00 | 0 | {} | 190qf1y | false | null | t3_190qf1y | /r/LocalLLaMA/comments/190qf1y/after_scraping_the_data_of_every_company_on_the/ | false | false | 48 | {'enabled': True, 'images': [{'id': 'kU8GtmFIn4H3RNEOZXQHbqaIc0t9sPDmsTp9tiBROD4', 'resolutions': [{'height': 79, 'url': 'https://preview.redd.it/0n52l7er90bc1.png?width=108&crop=smart&auto=webp&s=1c71570599bb1251c797d70a52b25ddff5ed4bb7', 'width': 108}, {'height': 158, 'url': 'https://preview.redd.it/0n52l7er90bc1.png... | ||
What's the best model to use for websites to turn them into q and a ? | 2 | Hey guys,
So I was developing something like sitegpt but using open source models.
I am sorry i am totally a newbie into the field of AI.
but please try to point me in the right direction and i will do more research.
It's a SAAS product so multiple ecommerce websites have to be trained and the bot will answer questio... | 2024-01-07T11:39:32 | https://www.reddit.com/r/LocalLLaMA/comments/190qcnt/whats_the_best_model_to_use_for_websites_to_turn/ | AnabelBain | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 190qcnt | false | null | t3_190qcnt | /r/LocalLLaMA/comments/190qcnt/whats_the_best_model_to_use_for_websites_to_turn/ | false | false | self | 2 | null |
Real time Arxiv API + RAG at inference | 5 | Hi everyone,
I’m quite new to the space and as a first project, I’m attempting to create an arxiv chat bot. I’m aware that this kind of bot is something that’s been done many times but I haven’t seen anything with the approach.
Most approaches I came across involves querying the arxiv api and using mainly the abstra... | 2024-01-07T11:35:38 | https://www.reddit.com/r/LocalLLaMA/comments/190qaol/real_time_arxiv_api_rag_at_inference/ | Candlespeaker | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 190qaol | false | null | t3_190qaol | /r/LocalLLaMA/comments/190qaol/real_time_arxiv_api_rag_at_inference/ | false | false | self | 5 | null |
Can anybody confirm that this speed is normal? | 1 | I'm running koboldcpp with the following parameters for a 7b q8\_0 gguf model I tried:
--usecublas --quiet --threads 10 --gpulayers 999 --contextsize 2048
I'm getting 54t/s on a rtx 3090 but I've seen people pull off [155t/s on a 4080](https://github.com/ggerganov/llama.cpp/pull/4773). This seems weird to me, the... | 2024-01-07T11:31:35 | https://www.reddit.com/r/LocalLLaMA/comments/190q8lu/can_anybody_confirm_that_this_speed_is_normal/ | OuchieOnChin | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 190q8lu | false | null | t3_190q8lu | /r/LocalLLaMA/comments/190q8lu/can_anybody_confirm_that_this_speed_is_normal/ | false | false | self | 1 | {'enabled': False, 'images': [{'id': 'aEPQc_sb6LYdT-qn9qPfnIklsRQ3gZARWeTYh5VB62g', 'resolutions': [{'height': 54, 'url': 'https://external-preview.redd.it/nhzrW2NkjbrptAvo0AnWruzc-DkuDVdonC9pvD_9CBA.jpg?width=108&crop=smart&auto=webp&s=91d652f58c951d7a00ed55dd5777db4ecc4a9246', 'width': 108}, {'height': 108, 'url': 'h... |
My theory: Microsoft changed Phi-2's license to MIT so they could one up Google and their closed source Gemini Nano model. 🤣 Microsoft may not have the smartphone market but Google's competitors like Samsung, Huawei, Xiaomi and even Apple do and now they can use Phi-2. | 36 | 2024-01-07T10:57:51 | https://www.reddit.com/gallery/190pqi5 | TysonUsykFury | reddit.com | 1970-01-01T00:00:00 | 0 | {} | 190pqi5 | false | null | t3_190pqi5 | /r/LocalLLaMA/comments/190pqi5/my_theory_microsoft_changed_phi2s_license_to_mit/ | false | false | 36 | null | ||
Anybody want to test its viability on much larger models? | 21 | 2024-01-07T10:37:43 | https://twitter.com/sdand/status/1743695855545426362 | Snoo_64233 | twitter.com | 1970-01-01T00:00:00 | 0 | {} | 190pgcz | false | null | t3_190pgcz | /r/LocalLLaMA/comments/190pgcz/anybody_want_to_test_its_viability_on_much_larger/ | false | false | default | 21 | null | |
Solution to transcribe Arabic | 1 | Hey everyone,
I am trying to help a local event organizer in creating a solution that would transcribe Arabic and auto translate and display the translation on a screen. I saw whisper from OAI, but wondering if there is a lesser known other one in the wild that i skipped.
Appreciate insights and thoughts,
T... | 2024-01-07T10:34:25 | https://www.reddit.com/r/LocalLLaMA/comments/190per1/solution_to_transcribe_arabic/ | AmeenRoayan | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 190per1 | false | null | t3_190per1 | /r/LocalLLaMA/comments/190per1/solution_to_transcribe_arabic/ | false | false | self | 1 | null |
Training Loss goes from being in Quadrillions to Zero | 1 | I was recently trying to fine tune CodeLlama model for generating code from text. I tried to replicate the code of WizardCoder for this and just changed the model name (it uses starcoder as the base model ig) and some other tweaks.
When I trained the model, the validation loss always came as Nan and the training Loss ... | 2024-01-07T10:30:04 | https://www.reddit.com/r/LocalLLaMA/comments/190pcjq/training_loss_goes_from_being_in_quadrillions_to/ | aayusss21 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 190pcjq | false | null | t3_190pcjq | /r/LocalLLaMA/comments/190pcjq/training_loss_goes_from_being_in_quadrillions_to/ | false | false | self | 1 | null |
Shoutout to a great RP model | 58 | Howdy everyone! I’ve been lurking this sub for quite some time now, always checking recommendations and tests for the new models, especially interested in those which fare well in roleplaying.
I am that sad type of an individual who has a convoluted, long-ass narrative roleplay (over two thousand messages and still go... | 2024-01-07T10:28:36 | https://www.reddit.com/gallery/190pbtn | Meryiel | reddit.com | 1970-01-01T00:00:00 | 0 | {} | 190pbtn | false | null | t3_190pbtn | /r/LocalLLaMA/comments/190pbtn/shoutout_to_a_great_rp_model/ | false | false | 58 | null | |
Any recommendation framework for enterprise conversational ai solutions ik rasa has llm based CA other than this is there any opensource out there | 2 | Langchain, llamaindex, haystack these are all for research. Any open source for building Conversational AI for buisnesses | 2024-01-07T10:26:17 | https://www.reddit.com/r/LocalLLaMA/comments/190pan7/any_recommendation_framework_for_enterprise/ | mrripo | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 190pan7 | false | null | t3_190pan7 | /r/LocalLLaMA/comments/190pan7/any_recommendation_framework_for_enterprise/ | false | false | self | 2 | null |
Text To Speech model that can handle special chars and numbers | 1 | Hello. I am experimenting with text to speech synthesis by following this article on Huggingface [https://huggingface.co/docs/transformers/main/en/tasks/text-to-speech](https://huggingface.co/docs/transformers/main/en/tasks/text-to-speech). I am using "Matthijs/cmu-arctic-xvectors" embeddings dataset for speaker embedd... | 2024-01-07T09:49:17 | https://www.reddit.com/r/LocalLLaMA/comments/190oryh/text_to_speech_model_that_can_handle_special/ | These-Butterfly8819 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 190oryh | false | null | t3_190oryh | /r/LocalLLaMA/comments/190oryh/text_to_speech_model_that_can_handle_special/ | false | false | self | 1 | {'enabled': False, 'images': [{'id': 'jfeVG47nZdEkz9kXfW1CcS-Sy8l4DXGb9JErx6bLKfU', 'resolutions': [{'height': 58, 'url': 'https://external-preview.redd.it/IfMbJOxNUMUzsY1dCStb5zfgtucewbklqG7kssYhOLc.jpg?width=108&crop=smart&auto=webp&s=6c2099a4a9a69e9793ac03aec2e167bf75ab3eae', 'width': 108}, {'height': 116, 'url': 'h... |
llama.cpp might soon get real 2bit quants | 111 | 2024-01-07T09:33:07 | https://github.com/ggerganov/llama.cpp/pull/4773 | cztomsik | github.com | 1970-01-01T00:00:00 | 0 | {} | 190ojju | false | null | t3_190ojju | /r/LocalLLaMA/comments/190ojju/llamacpp_might_soon_get_real_2bit_quants/ | false | false | 111 | {'enabled': False, 'images': [{'id': 'aEPQc_sb6LYdT-qn9qPfnIklsRQ3gZARWeTYh5VB62g', 'resolutions': [{'height': 54, 'url': 'https://external-preview.redd.it/nhzrW2NkjbrptAvo0AnWruzc-DkuDVdonC9pvD_9CBA.jpg?width=108&crop=smart&auto=webp&s=91d652f58c951d7a00ed55dd5777db4ecc4a9246', 'width': 108}, {'height': 108, 'url': 'h... | ||
7b vs 13b vs 33b for basic tasks + fine tuning (which one to choose) | 13 | I recently got started with local llms and i'm looking to use them for just one basic task (for now) : writing (all kinds, from product descriptions to poetry).
I'm not expecting models to perform the way i want them right out of the box - so i'm ready to do some fine tuning - already started with mistral 7b and the f... | 2024-01-07T09:19:11 | https://www.reddit.com/r/LocalLLaMA/comments/190ocf9/7b_vs_13b_vs_33b_for_basic_tasks_fine_tuning/ | yupignome | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 190ocf9 | false | null | t3_190ocf9 | /r/LocalLLaMA/comments/190ocf9/7b_vs_13b_vs_33b_for_basic_tasks_fine_tuning/ | false | false | self | 13 | null |
Has anyone tried using AI Agents to use browser dev tools and troubleshoot or work on CSS or JS? | 1 | [removed] | 2024-01-07T08:53:50 | https://www.reddit.com/r/LocalLLaMA/comments/190nzk4/has_anyone_tried_using_ai_agents_to_use_browser/ | TheTwelveYearOld | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 190nzk4 | false | null | t3_190nzk4 | /r/LocalLLaMA/comments/190nzk4/has_anyone_tried_using_ai_agents_to_use_browser/ | false | false | 1 | null |
Subsets and Splits
No community queries yet
The top public SQL queries from the community will appear here once available.