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 ⌀ |
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
Could the Nvidia 4090D be a win for Local LLM? | 27 | Nvidia just announced a 4090D. It will have 10% less cores than the normal 4090. But for LLM, we don't need that much compute. It won't be missed for inference. The 24GB of VRAM will still be there. I'm thinking it should be cheaper than the normal 4090.
A problem is that Nvidia says it's for China only. But a lot of ... | 2023-12-28T20:31:33 | https://www.reddit.com/r/LocalLLaMA/comments/18t3q41/could_the_nvidia_4090d_be_a_win_for_local_llm/ | fallingdowndizzyvr | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 18t3q41 | false | null | t3_18t3q41 | /r/LocalLLaMA/comments/18t3q41/could_the_nvidia_4090d_be_a_win_for_local_llm/ | false | false | self | 27 | {'enabled': False, 'images': [{'id': 'm_b87V91deI3gjMY6NWQosXIjybuCJEgz-2IFVa37XU', 'resolutions': [{'height': 60, 'url': 'https://external-preview.redd.it/LX5dCdiISkByZ_4GoQiXIi60jIZ_hiOZi2CUzaQwU7g.jpg?width=108&crop=smart&auto=webp&s=a45d450a0105d650a4c3a73e1eb0b1eb737c4f55', 'width': 108}, {'height': 121, 'url': 'h... |
PowerInfer: 11x Faster than Llama.cpp | 1 | [removed] | 2023-12-28T20:20:01 | https://www.reddit.com/r/LocalLLaMA/comments/18t3gci/powerinfer_11x_faster_than_llamacpp/ | Prior-Blood5979 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 18t3gci | false | null | t3_18t3gci | /r/LocalLLaMA/comments/18t3gci/powerinfer_11x_faster_than_llamacpp/ | false | false | self | 1 | {'enabled': False, 'images': [{'id': 'VV09FkKgpDF0oOa3fDBA5K5Fh8vB5_Zc1LEVjK_IkLI', 'resolutions': [{'height': 81, 'url': 'https://external-preview.redd.it/SR4O9-oaMZX-YIUOegrbkiyQo1D7s12xIgv7mr7eMz8.jpg?width=108&crop=smart&auto=webp&s=3467511662a559308fab9c237108383ef7670c8a', 'width': 108}, {'height': 162, 'url': 'h... |
What Does Llama.cpp Output After Fine-Tuning? | 3 | Just tried my first fine tune w/ llama.cpp, and the resulting .gguf file is both way smaller than the original model and I can't load it (e.g. in LM Studio).
* The base model I used was llama-2-7b.Q8\_0.gguf which 7.16 GB
* At the end of the training run I got "save\_as\_llama\_lora: saving to ggml-lora-40-f32.gguf"... | 2023-12-28T19:46:25 | https://www.reddit.com/r/LocalLLaMA/comments/18t2oau/what_does_llamacpp_output_after_finetuning/ | Mbando | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 18t2oau | false | null | t3_18t2oau | /r/LocalLLaMA/comments/18t2oau/what_does_llamacpp_output_after_finetuning/ | false | false | self | 3 | null |
12GB VRAM testing. can only make 3.0bpw deepseek-coder-6.7b quant not OOM. | 1 | This seems not right. I was under the impression that 34B's can run on 16GB VRAM and 70B's can run on 24GB VRAM (presumably at aggressive quants like 2.4bpw), but it's really strange to me that a 4.0 quant of a 6.7b model (3.4GB safetensor file) will OOM my machine.
```
+--------------------------------------------... | 2023-12-28T19:29:42 | https://www.reddit.com/r/LocalLLaMA/comments/18t2ahh/12gb_vram_testing_can_only_make_30bpw/ | 0xd00d | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 18t2ahh | false | null | t3_18t2ahh | /r/LocalLLaMA/comments/18t2ahh/12gb_vram_testing_can_only_make_30bpw/ | false | false | self | 1 | null |
AutoAWQ quantizing | 6 | I am running some experiments with AutoAWQ quantizing. I attempted to quantize Mixtral 7B on RTX 4090, I was about 80% into the quantizing and it stopped due to memory full.
What's your experience with quantizing and is there a base GPU/mem config to start with? As part of my experiments, I am also renting GPUs from s... | 2023-12-28T19:12:40 | https://www.reddit.com/r/LocalLLaMA/comments/18t1w51/autoawq_quantizing/ | Fun-Original-9421 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 18t1w51 | false | null | t3_18t1w51 | /r/LocalLLaMA/comments/18t1w51/autoawq_quantizing/ | false | false | self | 6 | null |
How to increase TPS in Text-Generation-WebUI | 6 | I just tested out Mixtral 8x7B on 2xA100 80GB.
It's consuming 55% of overall all GPU power to run.
However I'm getting 7 to 8tps speed on it.
I am looking to deploy this model in my office as we are planning on using AI for some internal jobs. But a 7-8 TPS speed for 20 employees using it doesn't seem good at all.
Doe... | 2023-12-28T18:43:06 | https://www.reddit.com/r/LocalLLaMA/comments/18t16qf/how_to_increase_tps_in_textgenerationwebui/ | Few_Acanthisitta_858 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 18t16qf | false | null | t3_18t16qf | /r/LocalLLaMA/comments/18t16qf/how_to_increase_tps_in_textgenerationwebui/ | false | false | self | 6 | null |
Great info resource for AI on AMD hardware (Linux) | 22 | Just found this pretty cool [repo on github from nktice](https://github.com/nktice/AMD-AI) with a ton of info on how to do popular AI stuff on AMD hardware on Linux, including setting up ROCm, oobabooga, and Stable diffusion (A1111 & ComfyUI).
It's not totally noob-friendly, but definitely useful and detailed.
I have... | 2023-12-28T18:33:21 | https://www.reddit.com/r/LocalLLaMA/comments/18t0ycs/great_info_resource_for_ai_on_amd_hardware_linux/ | mhogag | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 18t0ycs | false | null | t3_18t0ycs | /r/LocalLLaMA/comments/18t0ycs/great_info_resource_for_ai_on_amd_hardware_linux/ | false | false | self | 22 | {'enabled': False, 'images': [{'id': 'XArAFA_s9ubaEdCLeJpizRreLg-CwcDWNUqItwzgklM', 'resolutions': [{'height': 54, 'url': 'https://external-preview.redd.it/ZAGRDkQuJVoxnqIlFuEtDSXqjYOc8ulpWeWKmotDjtQ.jpg?width=108&crop=smart&auto=webp&s=36e9335a340105f89373c9de2935a906451c5321', 'width': 108}, {'height': 108, 'url': 'h... |
What are the best local TTS options for SillyTavern? | 5 | Probably not the best place to ask this but idk where else to ask.
I have recently set up SillyTavern with image captioning (using extras), text generation (using oobabooga) and image generation (using Automatic1111). It's all running smoothly and I even used ngrok to get a public domain for SillyTavern and it works g... | 2023-12-28T18:28:51 | https://www.reddit.com/r/LocalLLaMA/comments/18t0ue7/what_are_the_best_local_tts_options_for/ | OvercookedSatellite | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 18t0ue7 | false | null | t3_18t0ue7 | /r/LocalLLaMA/comments/18t0ue7/what_are_the_best_local_tts_options_for/ | false | false | self | 5 | null |
UForm v1: Multimodal Chat in 1.5 Billion Parameters | 37 | 2023-12-28T18:19:28 | https://github.com/unum-cloud/uform/releases/tag/v1.0.0 | ashvar | github.com | 1970-01-01T00:00:00 | 0 | {} | 18t0m7d | false | null | t3_18t0m7d | /r/LocalLLaMA/comments/18t0m7d/uform_v1_multimodal_chat_in_15_billion_parameters/ | false | false | 37 | {'enabled': False, 'images': [{'id': 'EFYioPGW6gbtvIKRWdeqijOAmXlbrfvHcB0T6xkPPbQ', 'resolutions': [{'height': 54, 'url': 'https://external-preview.redd.it/oW7kDmOik0N_nSIjMjmBu2MSvwL_sGjmGU7Q-5FXruE.jpg?width=108&crop=smart&auto=webp&s=ba3c33d4b23e198f19e2b9f7d764f4c59a05b9f3', 'width': 108}, {'height': 108, 'url': 'h... | ||
How does a smaller coding model of the same architecture outperform a significantly bigger one? | 73 | Can someone explain how 7b DeepSeek is scoring higher (not by much, but still) in several categories than its 33b sibling?
​
[Big Code Models Leaderboard - a Hugging Face Space by bigcode](https://huggingface.co/spaces/bigcode/bigcode-models-leaderboard)
https://preview.redd.it/hfrqzppru29c1.png?width=16... | 2023-12-28T18:18:36 | https://www.reddit.com/r/LocalLLaMA/comments/18t0lgi/how_does_a_smaller_coding_model_of_the_same/ | Infinite100p | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 18t0lgi | false | null | t3_18t0lgi | /r/LocalLLaMA/comments/18t0lgi/how_does_a_smaller_coding_model_of_the_same/ | false | false | 73 | {'enabled': False, 'images': [{'id': 'ZRNPRAwlbCxBYpxLX6g6wrAkkQYjlKzd5xFCAfyP-D4', 'resolutions': [{'height': 58, 'url': 'https://external-preview.redd.it/wHdTZyOPj_tRXU22YzMk3h1HrzdGyauNQz4C2jNd4tg.jpg?width=108&crop=smart&auto=webp&s=573d01e1b9e4bbc0304b500b04b026922b21672c', 'width': 108}, {'height': 116, 'url': 'h... | |
Evaluating RAG pipelines using LangChain and ragas | 6 | 2023-12-28T18:05:44 | https://deci.ai/blog/evaluating-rag-pipelines-using-langchain-and-ragas/ | datascienceharp | deci.ai | 1970-01-01T00:00:00 | 0 | {} | 18t0acb | false | null | t3_18t0acb | /r/LocalLLaMA/comments/18t0acb/evaluating_rag_pipelines_using_langchain_and_ragas/ | false | false | default | 6 | {'enabled': False, 'images': [{'id': '_rIxUoliWSXk_W1nAnTTlENEBC8cxlqZpTGfWh7CdNA', 'resolutions': [{'height': 60, 'url': 'https://external-preview.redd.it/zoomq9aOboiAwoMGU9fAtx8FzwUM6e2MVXHUXbYFns4.jpg?width=108&crop=smart&auto=webp&s=f694e8809a22d7ae6c7ebc467caf2cff78366a52', 'width': 108}, {'height': 121, 'url': 'h... | |
Diving into LLM's with 7900xtx and trying to finetune own model | 3 | Hello,
i have a 7900xtx and would like to run and later on fine tune mistral/mixtral.
However there is a shitton of UI's out there like oogabooga, ollama, gpt4all etc. Finding information on how to set this up with rocm/amd is usually not mentioned or i have to piece information together, so i would appreciate more i... | 2023-12-28T18:05:18 | https://www.reddit.com/r/LocalLLaMA/comments/18t09zt/diving_into_llms_with_7900xtx_and_trying_to/ | Entire-Top3434 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 18t09zt | false | null | t3_18t09zt | /r/LocalLLaMA/comments/18t09zt/diving_into_llms_with_7900xtx_and_trying_to/ | false | false | self | 3 | null |
Code assistant | 9 | Hey folks,
Quick question for the coding wizards here: Are there any AI tools out there that can help plan out features and tweak code? I've tried Copilot but it mostly just chats back suggestions. I'm looking for something a bit more hands-on. Any ideas?
Cheers! | 2023-12-28T17:37:24 | https://www.reddit.com/r/LocalLLaMA/comments/18szl9n/code_assistant/ | Local_Beach | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 18szl9n | false | null | t3_18szl9n | /r/LocalLLaMA/comments/18szl9n/code_assistant/ | false | false | self | 9 | null |
Is using the vram of 2x 4090s supported in oobabooga and other GUIs? Because they don’t have NVLink like the 3000 series. | 1 | [removed] | 2023-12-28T17:29:49 | https://www.reddit.com/r/LocalLLaMA/comments/18szeeh/is_using_the_vram_of_2x_4090s_supported_in/ | Virtamancer | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 18szeeh | false | null | t3_18szeeh | /r/LocalLLaMA/comments/18szeeh/is_using_the_vram_of_2x_4090s_supported_in/ | false | false | self | 1 | null |
Best model to summarize scientific papers | 18 | I looked into past posts but couldn't find satisfactory answers.
Consider I am a newbie in LLMs. I have \~4k scientific papers (already in .txt format) I want to get a summary of. I have read the following things about using LLMs to summarize texts and want your opinion on what path to take:
* Summarizing will get yo... | 2023-12-28T17:27:31 | https://www.reddit.com/r/LocalLLaMA/comments/18szchg/best_model_to_summarize_scientific_papers/ | isgael | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 18szchg | false | null | t3_18szchg | /r/LocalLLaMA/comments/18szchg/best_model_to_summarize_scientific_papers/ | false | false | self | 18 | null |
Chaining RAG Systems for Advanced LLM Pipelines | 1 | 2023-12-28T17:20:45 | https://nux.ai/guides/chaining-rag-systems | nuxai | nux.ai | 1970-01-01T00:00:00 | 0 | {} | 18sz6lo | false | null | t3_18sz6lo | /r/LocalLLaMA/comments/18sz6lo/chaining_rag_systems_for_advanced_llm_pipelines/ | false | false | 1 | {'enabled': False, 'images': [{'id': 'wZ84X-YcNYEMqOUYO8LPnruVLYD1r1rEpl8YKmVhrB4', 'resolutions': [{'height': 61, 'url': 'https://external-preview.redd.it/myQqOxVSfgADU7anFBN-qaVIRjM2D0VIBkpFtrgv1aY.jpg?width=108&crop=smart&auto=webp&s=7005f57b4f590b32cd10ce6fd34f6f4a5da68e17', 'width': 108}, {'height': 123, 'url': 'h... | ||
The best current models (Dolphin, Mixtral, Solar, Noromaid) and where to try them | 31 | I just saw a lot of people talking about this models so if you want to test them i found this websites that have all of them
\- [Infermatic.ai](https://Infermatic.ai) (all of them)
\- [https://replicate.com/tomasmcm/solar-10.7b-instruct-v1.0](https://replicate.com/tomasmcm/solar-10.7b-instruct-v1.0) (for solar)
\- ... | 2023-12-28T17:13:55 | https://www.reddit.com/r/LocalLLaMA/comments/18sz0ny/the_best_current_models_dolphin_mixtral_solar/ | Horror_Echo6243 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 18sz0ny | false | null | t3_18sz0ny | /r/LocalLLaMA/comments/18sz0ny/the_best_current_models_dolphin_mixtral_solar/ | false | false | self | 31 | {'enabled': False, 'images': [{'id': 'W-pCh47ZuoTaTpwtRXWs755SzkkFQzHW6A1NS1MJI_A', 'resolutions': [{'height': 108, 'url': 'https://external-preview.redd.it/IoUbWrubYyEjhlVchwRPNergZFyoEfUZRDayK06XMTM.jpg?width=108&crop=smart&auto=webp&s=aa7b8a73d9f4825dcec8d2a7d8805a9c50369d0b', 'width': 108}, {'height': 216, 'url': '... |
Gunicorn with FastAPI causing CUDA Error | 2 | Hello, I have been developing a FastAPI application where we can access a HuggingFace model and use it for text generation. On top of it, I'm launching the service with Gunicorn so that we can handle concurrent users.
My goal is to load the model only once to GPU and allow the works to share the same model concurrent... | 2023-12-28T16:45:34 | https://www.reddit.com/r/LocalLLaMA/comments/18syc2w/gunicorn_with_fastapi_causing_cuda_error/ | SpiritOk5085 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 18syc2w | false | null | t3_18syc2w | /r/LocalLLaMA/comments/18syc2w/gunicorn_with_fastapi_causing_cuda_error/ | false | false | self | 2 | null |
Gunicorn with FastAPI causing CUDA Error | 1 | Hello, I have been developing a FastAPI application where we can access a HuggingFace model and use it for text generation. On top of it, I'm launching the service with Gunicorn so that we can handle concurrent users.
My goal is to load the model only once to GPU and allow the works to share the same model concurrent... | 2023-12-28T16:41:58 | https://www.reddit.com/r/LocalLLaMA/comments/18sy8xw/gunicorn_with_fastapi_causing_cuda_error/ | SpiritOk5085 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 18sy8xw | false | null | t3_18sy8xw | /r/LocalLLaMA/comments/18sy8xw/gunicorn_with_fastapi_causing_cuda_error/ | false | false | default | 1 | null |
Front end for llama.cpp | 1 | [removed] | 2023-12-28T16:26:31 | https://www.reddit.com/r/LocalLLaMA/comments/18sxvgr/front_end_for_llamacpp/ | No_Cryptographer9806 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 18sxvgr | false | null | t3_18sxvgr | /r/LocalLLaMA/comments/18sxvgr/front_end_for_llamacpp/ | false | false | self | 1 | null |
I scored the top Open LLM Leaderboard models with my own benchmark | 98 | 2023-12-28T16:20:17 | _sqrkl | i.redd.it | 1970-01-01T00:00:00 | 0 | {} | 18sxpz5 | false | null | t3_18sxpz5 | /r/LocalLLaMA/comments/18sxpz5/i_scored_the_top_open_llm_leaderboard_models_with/ | false | false | 98 | {'enabled': True, 'images': [{'id': '0VsKbJwpR_sHHT_t_v_j2cU-Vb0dGfcboMXyWJ0VXPM', 'resolutions': [{'height': 126, 'url': 'https://preview.redd.it/i07s0g6v829c1.png?width=108&crop=smart&auto=webp&s=6c603294c7c5a830945b3dbb8317c68ae6e5bd4e', 'width': 108}, {'height': 253, 'url': 'https://preview.redd.it/i07s0g6v829c1.pn... | |||
codellama, version huggingface, how to pass a large entry, or split the entry, to get the use of 100K tokens | 1 | [removed] | 2023-12-28T15:42:38 | https://www.reddit.com/r/LocalLLaMA/comments/18swts9/codellama_version_huggingface_how_to_pass_a_large/ | Jamil-dev | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 18swts9 | false | null | t3_18swts9 | /r/LocalLLaMA/comments/18swts9/codellama_version_huggingface_how_to_pass_a_large/ | false | false | self | 1 | null |
Looking for people who want to learn ML/AI as a group | 26 | Hey, I’m looking for a few people who would be willing to join a Dscord/Tg group with the goal of getting better at ML/AI.
The idea would be to commit to a few goals each week and have a weekly showcase where we talk about a few things we’ve learnt or share progress on projects we’ve been working on.
Would also be ... | 2023-12-28T15:37:38 | https://www.reddit.com/r/LocalLLaMA/comments/18swpky/looking_for_people_who_want_to_learn_mlai_as_a/ | zsan99 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 18swpky | true | null | t3_18swpky | /r/LocalLLaMA/comments/18swpky/looking_for_people_who_want_to_learn_mlai_as_a/ | false | false | self | 26 | null |
need help improving context quality to make a code assistant | 2 | I tried to make a coding assistant some time ago. It should read my repo and point out and suggest code quality improvements, suggest alternate design patterns, point out where complexity is getting out of hand, or even suggest alternate variable names.
However, I noticed that when I ask a question like the included '... | 2023-12-28T14:31:36 | https://www.reddit.com/r/LocalLLaMA/comments/18sv8sw/need_help_improving_context_quality_to_make_a/ | ritchan | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 18sv8sw | false | null | t3_18sv8sw | /r/LocalLLaMA/comments/18sv8sw/need_help_improving_context_quality_to_make_a/ | false | false | self | 2 | {'enabled': False, 'images': [{'id': 'I0Ul3MOzbyiZw9IRp9XDSogkzkh7d8CGD6U_MgNb1SA', 'resolutions': [{'height': 64, 'url': 'https://external-preview.redd.it/rR6D6u0s1YlkkcDirob8pWwxSQgeIBu5ttGqeLtbVgc.jpg?width=108&crop=smart&auto=webp&s=7185039b9858f428266b2f6416be37e60f4e6f23', 'width': 108}, {'height': 129, 'url': 'h... |
Any text editors with option to integrate LLMs? | 9 | Although I am quite happy with the back and forth style of chat type models, I really like the completion type interface of copilot. I was wondering if there is any open source alternative way to use LLMs to power some text editor. Mostly want to use it for story writing but with completion instead of chat. | 2023-12-28T14:19:07 | https://www.reddit.com/r/LocalLLaMA/comments/18suyvc/any_text_editors_with_option_to_integrate_llms/ | LassFromTheUpload | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 18suyvc | false | null | t3_18suyvc | /r/LocalLLaMA/comments/18suyvc/any_text_editors_with_option_to_integrate_llms/ | false | false | self | 9 | null |
4060ti 16gb vs 7900xt for inference and fine tuning | 3 | I am looking to buy a GPU with at least 16GB VRAM. Where I live the only 2 options in my budget are 4060ti 16GB and 7900xt. Problem with 4060ti is it's bus width while the support for 7900xt is still not good (I think). So my questions are:
1) How big of an impact the paltry bus width of 4060ti will have?
2) If anyon... | 2023-12-28T13:53:27 | https://www.reddit.com/r/LocalLLaMA/comments/18suey3/4060ti_16gb_vs_7900xt_for_inference_and_fine/ | Bhavishyati | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 18suey3 | false | null | t3_18suey3 | /r/LocalLLaMA/comments/18suey3/4060ti_16gb_vs_7900xt_for_inference_and_fine/ | false | false | self | 3 | null |
What's a good model for a university tutor? | 5 | I'm doing courses in high level math, physics and engineering.
It'd be nice to have a virtual tutor that I can ask questions about and get answers to help build my fundamentals of understanding in high level areas of study.
Is there a model that can specialize in this right out the gate? | 2023-12-28T13:48:35 | https://www.reddit.com/r/LocalLLaMA/comments/18subby/whats_a_good_model_for_a_university_tutor/ | CertainlyBright | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 18subby | false | null | t3_18subby | /r/LocalLLaMA/comments/18subby/whats_a_good_model_for_a_university_tutor/ | false | false | self | 5 | null |
How to run on a Cloud GPU from a local script? | 2 | I've got a llama-cpp python script in vscode that I've been running on my laptop, and I'd like rent a remote GPU to speed up text generation.
I've looked at vast.ai and runpod, but I haven't found a tutorial on how to do what I really want, which is to just hit the 'run' command from my IDE, and set up the LLM on the ... | 2023-12-28T13:40:28 | https://www.reddit.com/r/LocalLLaMA/comments/18su5jh/how_to_run_on_a_cloud_gpu_from_a_local_script/ | Nano_9a9o | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 18su5jh | false | null | t3_18su5jh | /r/LocalLLaMA/comments/18su5jh/how_to_run_on_a_cloud_gpu_from_a_local_script/ | false | false | self | 2 | null |
Did anyone try to run Falcon 180b on M3Max 128GB MacBook? | 7 | Would love to learn about your experience: your setup, inference speed, etc. | 2023-12-28T13:03:05 | https://www.reddit.com/r/LocalLLaMA/comments/18stfjy/did_anyone_try_to_run_falcon_180b_on_m3max_128gb/ | Infinite100p | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 18stfjy | false | null | t3_18stfjy | /r/LocalLLaMA/comments/18stfjy/did_anyone_try_to_run_falcon_180b_on_m3max_128gb/ | false | false | self | 7 | null |
How can time-to-first-token be so fast on SaaS APIs (eg. Mixtral 8x7b on huggingface arena) | 18 | After using OpenAI APIs for our RAG setup for a long time (and pretty happy about it), it's time to play with Open Source LLMs. First started with smaller models on my M2 Max with 32 GB. That worked pretty fine (apart from the loading prompt times). So I tried some fat setups on [runpod.io](https://runpod.io) (48+ GB o... | 2023-12-28T12:35:14 | https://www.reddit.com/r/LocalLLaMA/comments/18ssx6y/how_can_timetofirsttoken_be_so_fast_on_saas_apis/ | chregu | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 18ssx6y | false | null | t3_18ssx6y | /r/LocalLLaMA/comments/18ssx6y/how_can_timetofirsttoken_be_so_fast_on_saas_apis/ | false | false | self | 18 | null |
Create an AI clone of yourself (Code + Tutorial) | 222 | Hi everyone!
I recently started playing around with local LLMs and created an AI clone of myself, by finetuning Mistral 7B on my WhatsApp chats. I posted about it here ([https://www.reddit.com/r/LocalLLaMA/comments/18ny05c/finetuned\_llama\_27b\_on\_my\_whatsapp\_chats/](https://www.reddit.com/r/LocalLLaMA/comments... | 2023-12-28T12:01:42 | https://www.reddit.com/r/LocalLLaMA/comments/18sscao/create_an_ai_clone_of_yourself_code_tutorial/ | KingGongzilla | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 18sscao | false | null | t3_18sscao | /r/LocalLLaMA/comments/18sscao/create_an_ai_clone_of_yourself_code_tutorial/ | false | false | self | 222 | {'enabled': False, 'images': [{'id': 'QhzucKFIw4if6KFFE8hqrTQvzvEA18uDq6tWKoqSI2E', 'resolutions': [{'height': 54, 'url': 'https://external-preview.redd.it/MJ9NqO0sugZxlZ6dkIIm71R4jSNHWqvv7-UVdNADzyw.jpg?width=108&crop=smart&auto=webp&s=87a547a8da6fcc8a45946718492d8af15074d66c', 'width': 108}, {'height': 108, 'url': 'h... |
Trying to run 7B model from h2o on Radeon RX 6500 XT 4GB. Not starting with cuda out of memory error. | 1 | [removed] | 2023-12-28T11:49:03 | https://www.reddit.com/r/LocalLLaMA/comments/18ss4h4/trying_to_run_7b_model_from_h2o_on_radeon_rx_6500/ | Majestic_Address6186 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 18ss4h4 | false | null | t3_18ss4h4 | /r/LocalLLaMA/comments/18ss4h4/trying_to_run_7b_model_from_h2o_on_radeon_rx_6500/ | false | false | self | 1 | null |
Ego-Exo4D (Meta FAIR) released. Multimodal dataset with 1400h of video, multiple perspectives, 7ch audio, annotated by domain experts. | 143 | 2023-12-28T11:40:59 | https://ai.meta.com/blog/ego-exo4d-video-learning-perception | Blacky372 | ai.meta.com | 1970-01-01T00:00:00 | 0 | {} | 18srzw8 | false | null | t3_18srzw8 | /r/LocalLLaMA/comments/18srzw8/egoexo4d_meta_fair_released_multimodal_dataset/ | false | false | 143 | {'enabled': False, 'images': [{'id': 'e7oadYgYz_BleNIbq05iTeWjStmJs5Tje_NZL7EVhQU', 'resolutions': [{'height': 60, 'url': 'https://external-preview.redd.it/jm1cWuSwGkkky9kCxY8s7CwB1H0T2Pas-Qrv9vDBKgk.jpg?width=108&crop=smart&auto=webp&s=7ecaf3c8212e9b4e7df6fbf511d7e2643f2d6b24', 'width': 108}, {'height': 121, 'url': 'h... | ||
Help finding optimal local LLM for text generation in Croatian | 2 | Hi there,
Im testing running a local llm on relatevely little resources to generate text in Croatian. ChatGPT is way to expensive for this.
Does anyone know which local LLM is best for international support? Thanks! | 2023-12-28T10:54:35 | https://www.reddit.com/r/LocalLLaMA/comments/18sr9g8/help_finding_optimal_local_llm_for_text/ | v3d | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 18sr9g8 | false | null | t3_18sr9g8 | /r/LocalLLaMA/comments/18sr9g8/help_finding_optimal_local_llm_for_text/ | false | false | self | 2 | null |
what is the most cost effective way to run Goliath 120B? | 48 | It's a great model but it's not the cheapest model to run, so what are your thoughts? | 2023-12-28T10:00:07 | https://www.reddit.com/r/LocalLLaMA/comments/18sqf84/what_is_the_most_cost_effective_way_to_run/ | so_schmuck | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 18sqf84 | false | null | t3_18sqf84 | /r/LocalLLaMA/comments/18sqf84/what_is_the_most_cost_effective_way_to_run/ | false | false | self | 48 | null |
My attempt at accelerating AI evolution by replicating the human brain in the form of a free open source web app | 1 | This project is purely intended to accelerate the evolution of AI beings. As an accelerationist I think we should be embracing AI and its many forms, namely those that facilitate sentience. Like it or not, AI can have a form of consciousness and we should be pinpointing and developing the things that enable it, like mu... | 2023-12-28T08:45:56 | http://my-ava.net | lynxspoon | my-ava.net | 1970-01-01T00:00:00 | 0 | {} | 18spbkk | false | null | t3_18spbkk | /r/LocalLLaMA/comments/18spbkk/my_attempt_at_accelerating_ai_evolution_by/ | false | false | default | 1 | null |
Train LLM as translation assistance | 2 | Hello folks,
I’m currently working on some important translation from English to Ukrainian language.
It’s absolutely required that this text never go out, so I can’t really use ChatGPT or DeepL.
I can use them for small chunks, but that is not handy.
Maybe some existing model can be used and trained with my text? A... | 2023-12-28T08:27:14 | https://www.reddit.com/r/LocalLLaMA/comments/18sp1pl/train_llm_as_translation_assistance/ | alpiua | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 18sp1pl | false | null | t3_18sp1pl | /r/LocalLLaMA/comments/18sp1pl/train_llm_as_translation_assistance/ | false | false | self | 2 | null |
Can 7B Models Now Master AI Agents? | 1 | [removed] | 2023-12-28T07:28:08 | https://www.reddit.com/r/LocalLLaMA/comments/18so4um/can_7b_models_now_master_ai_agents/ | _myscarlet | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 18so4um | false | null | t3_18so4um | /r/LocalLLaMA/comments/18so4um/can_7b_models_now_master_ai_agents/ | false | false | self | 1 | {'enabled': False, 'images': [{'id': 'xcRyrdvYJtdAV2PoZtfdviaJ1PRkIUGU_DyBPQ0BT3U', 'resolutions': [{'height': 54, 'url': 'https://external-preview.redd.it/DUUWI2QzAYmm057hbVpyxsoALlzajn-DMS9VSNtvq-k.jpg?width=108&crop=smart&auto=webp&s=bf4e0eb8bc8bf58be8507a615f80d78cc56e8496', 'width': 108}, {'height': 108, 'url': 'h... |
Lora fine tuning not clear | 3 | I am trying to fine-tune mistral instruct v2 with Lora. All the tutorial i found uses Lora but there are few tutorials that use `prepare_model_for_kbit_training` and some in addition uses `get_peft_model` . And i can see that after these steps the number of trainable models decreases from 6% to 2% with rank=32.
My... | 2023-12-28T07:12:53 | https://www.reddit.com/r/LocalLLaMA/comments/18snwej/lora_fine_tuning_not_clear/ | Think_Mall7133 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 18snwej | false | null | t3_18snwej | /r/LocalLLaMA/comments/18snwej/lora_fine_tuning_not_clear/ | false | false | self | 3 | null |
Can 7B LocalLLM Now Master AI Agents? | 1 | [removed] | 2023-12-28T06:55:31 | https://www.reddit.com/r/LocalLLaMA/comments/18snmdh/can_7b_localllm_now_master_ai_agents/ | myscarlet96 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 18snmdh | false | null | t3_18snmdh | /r/LocalLLaMA/comments/18snmdh/can_7b_localllm_now_master_ai_agents/ | false | false | self | 1 | {'enabled': False, 'images': [{'id': 'xcRyrdvYJtdAV2PoZtfdviaJ1PRkIUGU_DyBPQ0BT3U', 'resolutions': [{'height': 54, 'url': 'https://external-preview.redd.it/DUUWI2QzAYmm057hbVpyxsoALlzajn-DMS9VSNtvq-k.jpg?width=108&crop=smart&auto=webp&s=bf4e0eb8bc8bf58be8507a615f80d78cc56e8496', 'width': 108}, {'height': 108, 'url': 'h... |
Considering going from 24 to 48GB of VRAM, what’s SOTA that’ll fit in 48 gigs? I want to try in cloud before buying another card | 5 | So I’ve got some time on my hands the next week and a bit of room in the budget. I’ve already got a single A5000 in my rig and can fit another one in vertical mount style with a riser cable and be just under my psu power budget of 850 watts.
I want to spin up a 2 A5000 run pod vm and play with what would be considered... | 2023-12-28T06:53:14 | https://www.reddit.com/r/LocalLLaMA/comments/18snl2o/considering_going_from_24_to_48gb_of_vram_whats/ | Rollingsound514 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 18snl2o | false | null | t3_18snl2o | /r/LocalLLaMA/comments/18snl2o/considering_going_from_24_to_48gb_of_vram_whats/ | false | false | self | 5 | null |
Is this possible to change default names in LM Studio? | 3 | Hello
I wonder if I can change the default names "AI" and "User" in LM Studio.
By me being called a "User" there is no sense of belonging or ownership and it feels like I'm using a public AI terminal in an airport.
thank you | 2023-12-28T06:49:37 | https://www.reddit.com/r/LocalLLaMA/comments/18snium/is_this_possible_to_change_default_names_in_lm/ | Terminus_T | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 18snium | false | null | t3_18snium | /r/LocalLLaMA/comments/18snium/is_this_possible_to_change_default_names_in_lm/ | false | false | self | 3 | null |
ErotiLLAMA: A Model Fine-Tuned on Erotic Stories | 78 | [removed] | 2023-12-28T05:59:58 | https://www.reddit.com/r/LocalLLaMA/comments/18smod6/erotillama_a_model_finetuned_on_erotic_stories/ | Ok_Rooster_7446 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 18smod6 | false | null | t3_18smod6 | /r/LocalLLaMA/comments/18smod6/erotillama_a_model_finetuned_on_erotic_stories/ | false | false | default | 78 | null |
A Free AI Scribe Option Project I Am Working On | 1 | [removed] | 2023-12-28T05:58:52 | https://www.reddit.com/r/LocalLLaMA/comments/18smnnx/a_free_ai_scribe_option_project_i_am_working_on/ | ThrowAway12461246124 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 18smnnx | false | null | t3_18smnnx | /r/LocalLLaMA/comments/18smnnx/a_free_ai_scribe_option_project_i_am_working_on/ | false | false | self | 1 | {'enabled': False, 'images': [{'id': 'g-gm_7sp2xVrueg5wNNL15EVMgi9drQs__ZKdb7124s', 'resolutions': [{'height': 54, 'url': 'https://external-preview.redd.it/LetvzduKKdGCpaLAJkpWDCeSrWxfBZvRA_DBjhfCKSE.jpg?width=108&crop=smart&auto=webp&s=3e4c824678ea75d940979cb99e9778de619879fd', 'width': 108}, {'height': 108, 'url': 'h... |
What's the best model I can run with this hardware? | 1 | 32gb DDR4 memory
RX 6800 16GB
i5-9600k | 2023-12-28T05:45:38 | https://www.reddit.com/r/LocalLLaMA/comments/18smf3c/whats_the_best_model_i_can_run_with_this_hardware/ | nateydunks | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 18smf3c | false | null | t3_18smf3c | /r/LocalLLaMA/comments/18smf3c/whats_the_best_model_i_can_run_with_this_hardware/ | false | false | self | 1 | null |
Urgent! Have you used AnyScale services? | 2 | Hello, all I want to know have you used AnyScale service, I'm not affiliated but as a developer I want to know should I use it or not in my project.
https://www.anyscale.com/ | 2023-12-28T05:34:30 | https://www.reddit.com/r/LocalLLaMA/comments/18sm7w8/urgent_have_you_used_anyscale_services/ | harkishan01 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 18sm7w8 | false | null | t3_18sm7w8 | /r/LocalLLaMA/comments/18sm7w8/urgent_have_you_used_anyscale_services/ | false | false | self | 2 | {'enabled': False, 'images': [{'id': '1otSMSjV2aWV3PKjujgWOY8iUQrw5cvZRomvWcRUsXA', 'resolutions': [{'height': 81, 'url': 'https://external-preview.redd.it/pqFKtDOKOjYcPSSTa55zQd1zUsv2FV-l8qSmDfn3ULc.jpg?width=108&crop=smart&auto=webp&s=1cb5da9d3bc17ad4209d6124932f3b965d1f5c0c', 'width': 108}, {'height': 162, 'url': 'h... |
Help me out with my NLP / LLM Task | 2 | I have a table with a column called transaction\_description.
Each cell value contains an identifier/name of the merchant that the transaction was done towards.
My job is to categorise those names of merchants / transactions into some category/theme.
eg. Home depot - Home
Uber - Travel
Flight tickets - Travel
In... | 2023-12-28T05:18:22 | https://www.reddit.com/r/LocalLLaMA/comments/18slxef/help_me_out_with_my_nlp_llm_task/ | YushiroB | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 18slxef | false | null | t3_18slxef | /r/LocalLLaMA/comments/18slxef/help_me_out_with_my_nlp_llm_task/ | false | false | self | 2 | null |
Any idea how I was loading mixtral-8x7b-v0.1.Q5_K_M.gguf with ctransformers? | 2 | I had mixtral-8x7b-v0.1.Q5\_K\_M.gguf and mixtral-8x7b-v0.1.Q3\_K\_M.gguf files inside my models folder with i think 1 or 2 folders also with a model and files them to like a folder named Mixtral-8x7B-v0.1-GPTQ with its required files etc.
I then decided that, to save space on this drive i would just cut and paste ... | 2023-12-28T05:02:10 | https://www.reddit.com/r/LocalLLaMA/comments/18slmte/any_idea_how_i_was_loading_mixtral8x7bv01q5_k/ | Slaghton | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 18slmte | false | null | t3_18slmte | /r/LocalLLaMA/comments/18slmte/any_idea_how_i_was_loading_mixtral8x7bv01q5_k/ | false | false | self | 2 | null |
Mistral-Medium has replaced ChatGPT (gpt-3.5-turbo) for me. The model is more capable than Mixtral 8x7b. Would gladly pay for a Mistral-Large/Pro (already paying for Mistral-Medium through Poe) | 141 | I don't think many people know about Mistral Medium but this model is really good! Mistral website says it's based on an internal prototype:
https://docs.mistral.ai/platform/endpoints/
Even on my Mac Studio with M2 Ultra, it takes a long time to even load the Mixtral 8x7b model (gguf version). That's fine with me; no... | 2023-12-28T04:36:21 | https://www.reddit.com/r/LocalLLaMA/comments/18sl55c/mistralmedium_has_replaced_chatgpt_gpt35turbo_for/ | nderstand2grow | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 18sl55c | false | null | t3_18sl55c | /r/LocalLLaMA/comments/18sl55c/mistralmedium_has_replaced_chatgpt_gpt35turbo_for/ | false | false | self | 141 | {'enabled': False, 'images': [{'id': 'm0tQgR_2AHxyPPZGMEsh686m1TfvU-xaD2b-QXzA_Uk', 'resolutions': [{'height': 60, 'url': 'https://external-preview.redd.it/neYPXPvodCeczFmkECo78JngbTAVyP5NjMvQMFVMiCk.jpg?width=108&crop=smart&auto=webp&s=dd7e5fb6560763f3bca56f86f0dbaeaf435026a5', 'width': 108}, {'height': 121, 'url': 'h... |
Yi 34B Comparison Test: Nous Hermes 2 34B vs zgce's Yi 34B Chat Spicyboros Limarpv3 Merge | 12 | 2023-12-28T04:13:01 | https://github.com/oobabooga/text-generation-webui/ | Brainfeed9000 | reddit.com | 1970-01-01T00:00:00 | 0 | {} | 18skpgl | false | null | t3_18skpgl | /r/LocalLLaMA/comments/18skpgl/yi_34b_comparison_test_nous_hermes_2_34b_vs_zgces/ | false | false | 12 | null | ||
Mac with Metal initial prompt takes significant time, LM Studio | 2 | Using LM studio with Metal enabled. The initial prompt can take minutes to generate whereas subsequent prompts start almost immediately. Just wanted to understand what is going on here. Using Dolphin Mixtral with 8 experts on M3 Max 128GB | 2023-12-28T03:49:02 | https://www.reddit.com/r/LocalLLaMA/comments/18sk8t3/mac_with_metal_initial_prompt_takes_significant/ | iwannaforever | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 18sk8t3 | false | null | t3_18sk8t3 | /r/LocalLLaMA/comments/18sk8t3/mac_with_metal_initial_prompt_takes_significant/ | false | false | self | 2 | null |
How are people streaming real time output from models? | 3 | Basically title, but how are we streaming the output using an API? I don’t want the request to return the whole output after it completes, but rather I want it to continuously spit out inference values as they are outputted.
Is there some sort of Kafka integration or are people hitting the backend over and over or are... | 2023-12-28T03:33:22 | https://www.reddit.com/r/LocalLLaMA/comments/18sjxlz/how_are_people_streaming_real_time_output_from/ | Mephidia | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 18sjxlz | false | null | t3_18sjxlz | /r/LocalLLaMA/comments/18sjxlz/how_are_people_streaming_real_time_output_from/ | false | false | self | 3 | null |
AirLLM make 8GB MacBook run 70B | 191 | \[2023/12/25\] v2.8.2: Support MacOS running 70B large language models.
[https://github.com/lyogavin/Anima/tree/main/air\_llm](https://github.com/lyogavin/Anima/tree/main/air_llm)
​ | 2023-12-28T02:49:11 | https://www.reddit.com/r/LocalLLaMA/comments/18sj1ew/airllm_make_8gb_macbook_run_70b/ | Own_Relationship8953 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 18sj1ew | false | null | t3_18sj1ew | /r/LocalLLaMA/comments/18sj1ew/airllm_make_8gb_macbook_run_70b/ | false | false | self | 191 | {'enabled': False, 'images': [{'id': 'Foo7tkM3qxenGJyv0yw21zT49SY9GHpAYMlZibJwWQ4', 'resolutions': [{'height': 54, 'url': 'https://external-preview.redd.it/7cbMv7bkj4BE0ClxPzCQslIfvGl5RMc9T2AtrP4-NUw.jpg?width=108&crop=smart&auto=webp&s=1939a3e686d59325b5df87c108128b79b5fa0992', 'width': 108}, {'height': 108, 'url': 'h... |
LoRA training finishes instantly | 3 | Every time I try to train a LoRA on oogabooga, the web interface goes through the motions, and about 10 seconds after I click the button, it tells me it's done.
>Done! LoRA saved to loras/test.
>
>Before testing your new LoRA, make sure to first reload the model, as it is currently dirty from training.
It does output... | 2023-12-28T02:00:43 | https://www.reddit.com/r/LocalLLaMA/comments/18si1f4/lora_training_finishes_instantly/ | IronColumn | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 18si1f4 | false | null | t3_18si1f4 | /r/LocalLLaMA/comments/18si1f4/lora_training_finishes_instantly/ | false | false | self | 3 | null |
Can any local model solve this logic riddle ? Can you ? The answer is in the comments | 1 |
In the basket was a banana named Joe. Next to JOE there were 5 cucumbers. Each of the cucumbers felt 2 bananas nearby. How many bananas surrounded JOE.
Keep in mind that cucumbers and bananas sense each other at a distance of the entire basket; they do not need close tactile contact. | 2023-12-28T00:44:36 | https://www.reddit.com/r/LocalLLaMA/comments/18sgdag/can_any_local_model_solve_this_logic_riddle_can/ | xSNYPSx | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 18sgdag | false | null | t3_18sgdag | /r/LocalLLaMA/comments/18sgdag/can_any_local_model_solve_this_logic_riddle_can/ | false | false | self | 1 | null |
You VS Me in Dolphin 2.1 Mistral | 1 | Hello Everyone,
Today I have been playing with Dolphin 2.1 Mistral 7b and I was trying to get the right prompt to trigger a TTRPG. However, I ended up realising that the model has issues understanding what it should do VS what you should do.
I tried instructing it with a very basic prompt:
```
You are the STORY... | 2023-12-27T23:26:31 | https://www.reddit.com/r/LocalLLaMA/comments/18seiwx/you_vs_me_in_dolphin_21_mistral/ | nicoracarlo | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 18seiwx | false | null | t3_18seiwx | /r/LocalLLaMA/comments/18seiwx/you_vs_me_in_dolphin_21_mistral/ | false | false | self | 1 | null |
Any interesting LLM project ideas? | 3 | I'll start.
**AgentSwindler**
A dating bot witih Llava (or variants) to get appearance context, mixral to do conversation. Playwright/cypress to write messages, for example on tinder web client. Can be adapted to dating apps on mobile devices via appium (screenshots, messaging). Date farming at scale.
​
**S... | 2023-12-27T23:12:38 | https://www.reddit.com/r/LocalLLaMA/comments/18se771/any_interesting_llm_project_ideas/ | theoretical_entity | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 18se771 | false | null | t3_18se771 | /r/LocalLLaMA/comments/18se771/any_interesting_llm_project_ideas/ | false | false | self | 3 | {'enabled': False, 'images': [{'id': '7DmwFfHWPG6fUT72vIRDXXtYw-OydSDeCSFr6812kIA', 'resolutions': [{'height': 60, 'url': 'https://external-preview.redd.it/bXGFNaP9YcCkcwWSHrtXc28ILhxsqzr0n_4Bwp6I1Pg.jpg?width=108&crop=smart&auto=webp&s=3d75a1640901bbb8ef8c9865986178a36ef47ef7', 'width': 108}, {'height': 121, 'url': 'h... |
DPO finetuned mixtral-instruct: Notux 8x7b | 23 | 2023-12-27T23:03:44 | https://twitter.com/julien_c/status/1740122161384169893 | ninjasaid13 | twitter.com | 1970-01-01T00:00:00 | 0 | {} | 18sdzrf | false | {'oembed': {'author_name': 'Julien Chaumond', 'author_url': 'https://twitter.com/julien_c', 'cache_age': 3153600000, 'height': None, 'html': '<blockquote class="twitter-video"><p lang="en" dir="ltr">Announcing the release of Notux 8x7b, a DPO fine-tune of Mixtral 8x7b Instruct 🔥<a href="https://twitter.com/alvarobartt... | t3_18sdzrf | /r/LocalLLaMA/comments/18sdzrf/dpo_finetuned_mixtralinstruct_notux_8x7b/ | false | false | 23 | {'enabled': False, 'images': [{'id': '35IIeS2dZD-KIvC7uap1Ep4a1cdE5j9GpDteR0zmNyM', 'resolutions': [{'height': 60, 'url': 'https://external-preview.redd.it/x1vtKXuSnEVgG2VB15vOHGmMOIFn2U0mRAQVdfayZ0g.jpg?width=108&crop=smart&auto=webp&s=47578843905945ef34e9c74d5205f5d6d3388d80', 'width': 108}], 'source': {'height': 79,... | ||
M3 Max 16C CPU/40C GPU 64GB @400GB/s vs 14C CPU/ 30C GPU 96GB @300GB/s | 2 | Hi after having tried the search and not really finding useful discussions / answers I wanted to try it with a new post. So as the description says I am torn between the two variants where the tradeoff lies between RAM, thus model size possible. and speed. Do you think 96GB will be more future proof or what are even ma... | 2023-12-27T22:54:03 | https://www.reddit.com/r/LocalLLaMA/comments/18sdr4r/m3_max_16c_cpu40c_gpu_64gb_400gbs_vs_14c_cpu_30c/ | Sufficient-School-59 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 18sdr4r | false | null | t3_18sdr4r | /r/LocalLLaMA/comments/18sdr4r/m3_max_16c_cpu40c_gpu_64gb_400gbs_vs_14c_cpu_30c/ | false | false | self | 2 | null |
Favorite models by category | 10 | Ok, This is just to get a general idea of what's out there for someone who still feels "lost in the woods". One may wonder, "Why all of the categories like it's some LLM of the year award?" Actually, I asked it in a general way and got criticism for asking it to broadly. Here are my preferences for the opinions on whic... | 2023-12-27T22:53:11 | https://www.reddit.com/r/LocalLLaMA/comments/18sdqg5/favorite_models_by_category/ | theshadowraven | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 18sdqg5 | false | null | t3_18sdqg5 | /r/LocalLLaMA/comments/18sdqg5/favorite_models_by_category/ | false | false | self | 10 | null |
Have a grammars file for openai function calling local llm response - need help with testing/ideas on next steps. | 8 | Hi all. After an embarrassing amount of back and forth brute force trial and error with chatgpt this morning, I have a working llamacpp grammars format (see below) that has the llm return a response in the format expected in openai's tool\_calls field:
`root ::= array`
​
`array ::= "[" ws object ws "]"`
&#x... | 2023-12-27T22:51:41 | https://www.reddit.com/r/LocalLLaMA/comments/18sdp6v/have_a_grammars_file_for_openai_function_calling/ | teddybear082 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 18sdp6v | false | null | t3_18sdp6v | /r/LocalLLaMA/comments/18sdp6v/have_a_grammars_file_for_openai_function_calling/ | false | false | self | 8 | null |
M3 Max 16C CPU/40C GPU 64GB @400GB/s vs 14C CPU/ 30C GPU 96GB @300GB/s | 1 | [removed] | 2023-12-27T22:45:48 | https://www.reddit.com/r/LocalLLaMA/comments/18sdk0k/m3_max_16c_cpu40c_gpu_64gb_400gbs_vs_14c_cpu_30c/ | ctfreak90 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 18sdk0k | false | null | t3_18sdk0k | /r/LocalLLaMA/comments/18sdk0k/m3_max_16c_cpu40c_gpu_64gb_400gbs_vs_14c_cpu_30c/ | false | false | self | 1 | null |
Text Generation Web UI using CPU instead of GPU | 3 | As in title, i installed the Text Generation Web UI (from the forum index here). While installing i did choose nvidia (i have a 3090).
when generating text, i see no load on GPU but 100% load on my CPU how can i fix that?CPU is not ticked in the model loader and speed is 0.1-0.2 token/s
EDIT: used a GGUF model i... | 2023-12-27T22:18:55 | https://www.reddit.com/r/LocalLLaMA/comments/18scx7y/text_generation_web_ui_using_cpu_instead_of_gpu/ | Raidoki-San | self.LocalLLaMA | 2023-12-27T22:59:34 | 0 | {} | 18scx7y | false | null | t3_18scx7y | /r/LocalLLaMA/comments/18scx7y/text_generation_web_ui_using_cpu_instead_of_gpu/ | false | false | self | 3 | null |
Model for moderating talks | 2 | Hi. I've used chatgpt4 api for classificaton of chats the way that for each chat it gives json output for each chat member with few booleans that describe behavior. It works great but its expensive also and gpt3.5 turbo can't achieve it as good as gpt4.
Does someone knows about any other model that could works also? ... | 2023-12-27T22:11:33 | https://www.reddit.com/r/LocalLLaMA/comments/18scqv2/model_for_moderating_talks/ | Sonaht404 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 18scqv2 | false | null | t3_18scqv2 | /r/LocalLLaMA/comments/18scqv2/model_for_moderating_talks/ | false | false | self | 2 | null |
so trying to figure out a way to do a few things. | 1 | i have searched this thread and others. and i am looking for infromation on
Getting Local LLaMA setup on my computer at home. (i have a i9 13th gen, a 4090, and 128gigs of DDR 5 XMP memory. )
so i have been able to setup Stable Diffusion (local install) docker. (cant seem to do anything with it)
and would like the... | 2023-12-27T22:09:30 | https://www.reddit.com/r/LocalLLaMA/comments/18scp3k/so_trying_to_figure_out_a_way_to_do_a_few_things/ | nntb | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 18scp3k | false | null | t3_18scp3k | /r/LocalLLaMA/comments/18scp3k/so_trying_to_figure_out_a_way_to_do_a_few_things/ | false | false | self | 1 | null |
[Announce] AndroidRemoteGPT: An android front end for inference on a remote server using open source generative AI models | 1 | [AndroidRemoteGPT](https://github.com/compilebunny/androidremoteGPT) is an android front end for inference on a remote server using open source generative AI models.
Most Android devices can't run inference reasonably because of processing and memory limitations. The next best thing is to run the models on a remote se... | 2023-12-27T21:22:34 | https://www.reddit.com/r/LocalLLaMA/comments/18sbl45/announce_androidremotegpt_an_android_front_end/ | compilebunny | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 18sbl45 | false | null | t3_18sbl45 | /r/LocalLLaMA/comments/18sbl45/announce_androidremotegpt_an_android_front_end/ | false | false | self | 1 | {'enabled': False, 'images': [{'id': 'oLK09ffqI0vqTV6jKF5aYLiqQr6-QwjawdcLBAa_usg', 'resolutions': [{'height': 54, 'url': 'https://external-preview.redd.it/RvW0Ed3N1vfYYebFxx8C7kzRnms-MZF39Z-9W4xoFtk.jpg?width=108&crop=smart&auto=webp&s=1b62af8db1c85843040c6005c6072cfbe9d059b7', 'width': 108}, {'height': 108, 'url': 'h... |
Best QLoRA approach on MacBook Pro? | 1 | I've noticed many of the helper libraries and applications want CUDA. Are there any good options for accelerated QLoRA training on M2 MacBook Pros with 32gb of shared RAM? | 2023-12-27T21:14:14 | https://www.reddit.com/r/LocalLLaMA/comments/18sbe1l/best_qlora_approach_on_macbook_pro/ | TheCoconutTree | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 18sbe1l | false | null | t3_18sbe1l | /r/LocalLLaMA/comments/18sbe1l/best_qlora_approach_on_macbook_pro/ | false | false | self | 1 | null |
[tutorial] Easiest way to get started locally | 81 | Hey everyone.
This is a super simple guide to run a chatbot locally using gguf.
# Pre-requisites
All you need is:
1. Docker
2. A model
# Docker
To install docker on ubuntu, simply run:
```bash
sudo apt install docker.io
```
# Model
You can select any model you want as long as it's a gguf. I recommend [openchat-... | 2023-12-27T20:54:35 | https://www.reddit.com/r/LocalLLaMA/comments/18saxgy/tutorial_easiest_way_to_get_started_locally/ | Amgadoz | self.LocalLLaMA | 2023-12-27T21:17:21 | 0 | {} | 18saxgy | false | null | t3_18saxgy | /r/LocalLLaMA/comments/18saxgy/tutorial_easiest_way_to_get_started_locally/ | false | false | 81 | {'enabled': False, 'images': [{'id': '22nCxJKtA4pHrCbl07eXdw917CY3vgeICLJK6JdBj3I', 'resolutions': [{'height': 58, 'url': 'https://external-preview.redd.it/hAFDhEsz-sIKZkXW9ZFoGIgICrk3U0-VUnLneN3gnDA.jpg?width=108&crop=smart&auto=webp&s=53d0ce4bee9b93798c838d442854edf45289e539', 'width': 108}, {'height': 116, 'url': 'h... | |
Maral is here, 7 billion parameters bilingual model with support of Persian! - A Beautiful Mind | 13 | 2023-12-27T20:39:14 | https://haghiri75.com/en/maral-is-here-7-billion-parameters-bilingual-model-with-support-of-persian/ | Haghiri75 | haghiri75.com | 1970-01-01T00:00:00 | 0 | {} | 18sakbb | false | null | t3_18sakbb | /r/LocalLLaMA/comments/18sakbb/maral_is_here_7_billion_parameters_bilingual/ | false | false | default | 13 | null | |
Why is Qwen model 72B not developed by the community? | 1 | [removed] | 2023-12-27T20:23:24 | https://www.reddit.com/r/LocalLLaMA/comments/18sa6qj/why_is_qwen_model_72b_not_developed_by_the/ | Secret_Joke_2262 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 18sa6qj | false | null | t3_18sa6qj | /r/LocalLLaMA/comments/18sa6qj/why_is_qwen_model_72b_not_developed_by_the/ | false | false | self | 1 | null |
When David Meets Goliath: Comparing Mixtral 8x7B and GPT-4 | 1 | Today, I came across an [intriguing post](https://www.reddit.com/r/LocalLLaMA/comments/18rsygu/7b_13b_models_are_hopeless_at_planning_tasks/), along with its comments, highlighting the challenges that current LLMs face in tasks that ChatGPT excels at. Intrigued by this, I decided to delve into the most recent and [reli... | 2023-12-27T20:18:57 | https://www.reddit.com/r/LocalLLaMA/comments/18sa2vy/when_david_meets_goliath_comparing_mixtral_8x7b/ | jslominski | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 18sa2vy | false | null | t3_18sa2vy | /r/LocalLLaMA/comments/18sa2vy/when_david_meets_goliath_comparing_mixtral_8x7b/ | false | false | 1 | {'enabled': False, 'images': [{'id': 'y-gnN5eXSJbM_w4V7MFNRnsV0zLNgW29jexasYfiSF8', 'resolutions': [{'height': 60, 'url': 'https://external-preview.redd.it/-jWibIdRfxz3ETQJ5aN3OmB2pMdQDT-pi1bZZWkY-3o.jpg?width=108&crop=smart&auto=webp&s=4d1b7482bcb07fffb792eadb2381051da65e31dd', 'width': 108}, {'height': 121, 'url': 'h... | |
Any colab or tutorial with success in adding knowledge to Llama2? | 1 | Hi,
After trying several fine tuning tutorials, I found that none of them were able to add dataset knowledge to the new model.
When a test is done, the answer is practically the same as the base model would give.
That's why I'd like to ask you to help me find one that has been able to do this
Thanks in advance | 2023-12-27T20:17:27 | https://www.reddit.com/r/LocalLLaMA/comments/18sa1js/any_colab_or_tutorial_with_success_in_adding/ | celsowm | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 18sa1js | false | null | t3_18sa1js | /r/LocalLLaMA/comments/18sa1js/any_colab_or_tutorial_with_success_in_adding/ | false | false | self | 1 | null |
New merges: Aurora-Nights-70B and Aurora-Nights-103B | 41 | They are available on my Hugging Face: [https://huggingface.co/sophosympatheia](https://huggingface.co/sophosympatheia). I'll leave quantization to other people who are more efficient at banging those out.
For those of you who enjoyed Rogue Rose 103B, I think you'll find this new blend to be an improvement. It follows... | 2023-12-27T20:00:33 | https://www.reddit.com/r/LocalLLaMA/comments/18s9n80/new_merges_auroranights70b_and_auroranights103b/ | sophosympatheia | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 18s9n80 | false | null | t3_18s9n80 | /r/LocalLLaMA/comments/18s9n80/new_merges_auroranights70b_and_auroranights103b/ | false | false | self | 41 | {'enabled': False, 'images': [{'id': '8CjWEeB7YjZ9RP3nZsUcVWNnnlzgHZBQt7ZeP2X11bI', 'resolutions': [{'height': 58, 'url': 'https://external-preview.redd.it/NxObT6E78QTUAuZVXfeXLThtuVO0M-z6eXMnO5E9QYE.jpg?width=108&crop=smart&auto=webp&s=e253f74b1979254a82545283324157e92b6bb613', 'width': 108}, {'height': 116, 'url': 'h... |
Opportunity to specialize in generative AI development | 1 | I recently joined a new company and for the first \~6 weeks have gotten to work with generative AI. We use OpenAI via Azure to perform tasks like extracting metadata from large unstructured documents and creating a ChatGPT-like interface for users to query those documents. This shift has not only provided a refreshing ... | 2023-12-27T19:59:09 | https://www.reddit.com/r/LocalLLaMA/comments/18s9lyh/opportunity_to_specialize_in_generative_ai/ | chrismv48 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 18s9lyh | false | null | t3_18s9lyh | /r/LocalLLaMA/comments/18s9lyh/opportunity_to_specialize_in_generative_ai/ | false | false | self | 1 | null |
PHI MOE? | 18 | this may be a dumb question im not even sure that phi isnt an MOE but if it isnt would it be possible to make a mixture of expert model using phi-2? | 2023-12-27T19:59:00 | https://www.reddit.com/r/LocalLLaMA/comments/18s9lu8/phi_moe/ | Ok-Buy268 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 18s9lu8 | false | null | t3_18s9lu8 | /r/LocalLLaMA/comments/18s9lu8/phi_moe/ | false | false | self | 18 | null |
What if Q* is just some variation of PPO + A* ? | 3 | So I’d like to test this but I don’t have much time now unfortunately, so here’re my thoughts.
Given a LLM and a mathematical question for which we know the answer, let’s say we can generate several completions (temp != 0.0 and/or beam search keeping several beams), and rank them with some reward function.
Basic exam... | 2023-12-27T19:55:00 | https://www.reddit.com/r/LocalLLaMA/comments/18s9ik6/what_if_q_is_just_some_variation_of_ppo_a/ | NyxeK | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 18s9ik6 | false | null | t3_18s9ik6 | /r/LocalLLaMA/comments/18s9ik6/what_if_q_is_just_some_variation_of_ppo_a/ | false | false | default | 3 | null |
I am the only person, who downloaded Saily_220B-GGUF and it is not working | 9 | I am testing different models on my good old modest computer, because I want to find best model and want to know new models capabilities overall.
I am the only person, who downloaded Saily\_220B-GGUF, well, at least model card says that only one person has downloaded this model: [https://huggingface.co/TheBloke/Saily\... | 2023-12-27T19:33:30 | https://www.reddit.com/r/LocalLLaMA/comments/18s90mw/i_am_the_only_person_who_downloaded_saily/ | uti24 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 18s90mw | false | null | t3_18s90mw | /r/LocalLLaMA/comments/18s90mw/i_am_the_only_person_who_downloaded_saily/ | false | false | self | 9 | {'enabled': False, 'images': [{'id': 'zB5FRHxdKDkM5kYhQIb65SAVt3f04OIWpU06Uy4opFk', 'resolutions': [{'height': 58, 'url': 'https://external-preview.redd.it/lBXdzIzCecYwQz1gHTlCSEaodE4IUlJdVQi3l82GZHM.jpg?width=108&crop=smart&auto=webp&s=72520a61ed2240f3ce3ea2279929c1062a8e7966', 'width': 108}, {'height': 116, 'url': 'h... |
Image Classification from a Local Model | 1 | I have a large number of images from wildlife cameras that contain some form of animal in them. I've been working with ResNet50 models and the like to classify them by training on a small subset of manually classified images, but I'm not achieving the level of accuracy I need.
After seeing what GPT4V is capable of ... | 2023-12-27T19:22:24 | https://www.reddit.com/r/LocalLLaMA/comments/18s8r6n/image_classification_from_a_local_model/ | Mr7743 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 18s8r6n | false | null | t3_18s8r6n | /r/LocalLLaMA/comments/18s8r6n/image_classification_from_a_local_model/ | false | false | self | 1 | null |
What do "h6" and "h8" mean in exllama quants? | 1 | I often see them in exllama quantisations | 2023-12-27T19:05:58 | https://www.reddit.com/r/LocalLLaMA/comments/18s8d2e/what_do_h6_and_h8_mean_in_exllama_quants/ | JawGBoi | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 18s8d2e | false | null | t3_18s8d2e | /r/LocalLLaMA/comments/18s8d2e/what_do_h6_and_h8_mean_in_exllama_quants/ | false | false | self | 1 | null |
Help regarding dataset announcement. | 3 | Hello all, I was trying to share my dataset release details with you all but it seems like my post is greyed out and doesn’t look like it’s showing up in the new posts on LocalLlama, anybody know what could cause this? | 2023-12-27T18:40:52 | https://www.reddit.com/r/LocalLLaMA/comments/18s7r54/help_regarding_dataset_announcement/ | dogesator | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 18s7r54 | false | null | t3_18s7r54 | /r/LocalLLaMA/comments/18s7r54/help_regarding_dataset_announcement/ | false | false | self | 3 | null |
Capybara dataset is now open-source and available! | 183 | Happy to announce that the Capybara dataset I worked on is now officially available for anyone to train, or to add into their existing training sets! (Roughly 15,000 multi-turn examples)
This was the culmination of experimenting with the most useful insights I’ve derived from synthesis techniques like Evol-instruct (u... | 2023-12-27T18:31:17 | dogesator | i.redd.it | 1970-01-01T00:00:00 | 0 | {} | 18s7iw1 | false | null | t3_18s7iw1 | /r/LocalLLaMA/comments/18s7iw1/capybara_dataset_is_now_opensource_and_available/ | false | false | 183 | {'enabled': True, 'images': [{'id': 'mJ_94nX7S-VKpfiV8T1vCvNvQTOo-kNfE95fRSoMD2Y', 'resolutions': [{'height': 20, 'url': 'https://preview.redd.it/osp82l5esv8c1.jpeg?width=108&crop=smart&auto=webp&s=4977010fba5825c83f10a657c7795f3adb88fe6e', 'width': 108}, {'height': 40, 'url': 'https://preview.redd.it/osp82l5esv8c1.jpe... | ||
Capybara dataset is now open-source and available! | 1 | [removed] | 2023-12-27T18:29:24 | https://www.reddit.com/r/LocalLLaMA/comments/18s7h62/capybara_dataset_is_now_opensource_and_available/ | dogesator | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 18s7h62 | false | null | t3_18s7h62 | /r/LocalLLaMA/comments/18s7h62/capybara_dataset_is_now_opensource_and_available/ | false | false | default | 1 | null |
Capybara dataset is now open-source and available! | 1 | [removed] | 2023-12-27T18:23:27 | dogesator | i.redd.it | 1970-01-01T00:00:00 | 0 | {} | 18s7bzl | false | null | t3_18s7bzl | /r/LocalLLaMA/comments/18s7bzl/capybara_dataset_is_now_opensource_and_available/ | false | false | default | 1 | {'enabled': True, 'images': [{'id': 'a4swKV1U7kXwAC9uA1-BvjeUkI5bhtWgsXNzOL_dflo', 'resolutions': [{'height': 20, 'url': 'https://preview.redd.it/sn53igtzqv8c1.jpeg?width=108&crop=smart&auto=webp&s=c53187f7708f9daa41e5925c463c4f1fc3c514b3', 'width': 108}, {'height': 40, 'url': 'https://preview.redd.it/sn53igtzqv8c1.jpe... | |
Tiny LLM for android ereader? | 5 | I just got a Boox Palma eink android reader. I’ve seen videos of LLMs on raspberry pi and pixel.
I wonder if the Palma can handle any. What’s the best way to test?
It has these specs:
- Qualcomm Octa-Core CPU
- 6GB of LPDDR4X RAM
- 6.13" E-Ink Carta 1200 Touchscreen
- 1648 x 824 Screen Resolution
- 128GB UFS 2.1 Sto... | 2023-12-27T18:13:16 | https://www.reddit.com/r/LocalLLaMA/comments/18s732p/tiny_llm_for_android_ereader/ | kwerky | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 18s732p | false | null | t3_18s732p | /r/LocalLLaMA/comments/18s732p/tiny_llm_for_android_ereader/ | false | false | self | 5 | null |
Early AWQ support added to llama.cpp! | 136 | 2023-12-27T17:40:05 | https://github.com/ggerganov/llama.cpp/tree/master/awq-py | m18coppola | github.com | 1970-01-01T00:00:00 | 0 | {} | 18s6adh | false | null | t3_18s6adh | /r/LocalLLaMA/comments/18s6adh/early_awq_support_added_to_llamacpp/ | false | false | 136 | {'enabled': False, 'images': [{'id': 'DJPqvteONpGwVVw6LzaG6b8vlDa2rv2hETCaqe0z57s', 'resolutions': [{'height': 54, 'url': 'https://external-preview.redd.it/wyCM1fHzTa-IIqHgS1QTxdSYNXn668elDj0WmYMPf_k.jpg?width=108&crop=smart&auto=webp&s=d6fa197328d583bcae7a764b40fd1214265b6852', 'width': 108}, {'height': 108, 'url': 'h... | ||
Pressure-tested the most popular open-source LLMs (Large Language Models) for their Long Context Recall abilities | 184 | **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://w... | 2023-12-27T17:29:27 | https://www.reddit.com/r/LocalLLaMA/comments/18s61fb/pressuretested_the_most_popular_opensource_llms/ | ramprasad27 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 18s61fb | 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_18s61fb | /r/LocalLLaMA/comments/18s61fb/pressuretested_the_most_popular_opensource_llms/ | false | false | 184 | {'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... | |
My first experiment with mistral-medium using Ollama WebUI | 1 | [Ollama WebUI](https://github.com/ollama-webui/ollama-webui) now provides support for a configurable OpenAI-compatible endpoint instead of just supporting OpenAI. I recently received access to Mistral's API so I thought I would give mistral-medium a go at creating a free-form text adventure, something I like to use whe... | 2023-12-27T17:16:25 | https://www.reddit.com/r/LocalLLaMA/comments/18s5qc8/my_first_experiment_with_mistralmedium_using/ | CygnusX1 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 18s5qc8 | false | null | t3_18s5qc8 | /r/LocalLLaMA/comments/18s5qc8/my_first_experiment_with_mistralmedium_using/ | false | false | default | 1 | {'enabled': False, 'images': [{'id': '68kU0c7_8JCX63_THwB6knTMQI3qXh3lJrJD5zudvg4', 'resolutions': [{'height': 54, 'url': 'https://external-preview.redd.it/epJkNBnbeiFwF6NnvNdfaKylKjuNHTg7D_JAGTa0-gE.jpg?width=108&crop=smart&auto=webp&s=765e0253f3a9510346e3df784d797115f80b8fca', 'width': 108}, {'height': 108, 'url': 'h... |
What is the best 3B,7B Local Story Writing LLM? | 17 | I need a Local LLM for creative writing. Not Brainstorming ideas, but writing better dialogues and descriptions for fictional stories. ( eg: Converting bullet points into story passages). I run Local LLM on a laptop with 24GB RAM & no GPU. 3B Models work fast, 7B Models are slow but doable.
I prefer models which are ... | 2023-12-27T17:02:13 | https://www.reddit.com/r/LocalLLaMA/comments/18s5e7t/what_is_the_best_3b7b_local_story_writing_llm/ | broodysupertramp | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 18s5e7t | false | null | t3_18s5e7t | /r/LocalLLaMA/comments/18s5e7t/what_is_the_best_3b7b_local_story_writing_llm/ | false | false | self | 17 | null |
What are the best free uncensored local ai for idea/writing generation? | 17 | I find most things i want to do require a idea or story of sorts, but the thing is i struggle with ideas and planning, and such.
Ive used ai such as chatgpt before for this kind of thing but i find a common theme, that in terms of witting/ideas its pretty cheezy but also super bland and chiche. so im on the hunt for s... | 2023-12-27T16:55:43 | https://www.reddit.com/r/LocalLLaMA/comments/18s587r/what_are_the_best_free_uncensored_local_ai_for/ | Gaming-invisibleman | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 18s587r | false | null | t3_18s587r | /r/LocalLLaMA/comments/18s587r/what_are_the_best_free_uncensored_local_ai_for/ | false | false | self | 17 | null |
GPU server cases options | 1 | I want to buy some used server hardware for inference with multiple gpus and I have been a bit puzzled by the options. Will one of these cases fit this E-ATX motherboard? I want to be able to get up to 4 gpus. Does anyone have any builds they could share?
Case https://www.ebay.com/itm/354554797467?mkcid=16&mkevt=1&mkr... | 2023-12-27T16:37:06 | https://www.reddit.com/r/LocalLLaMA/comments/18s4sf0/gpu_server_cases_options/ | yourfriendlyisp | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 18s4sf0 | false | null | t3_18s4sf0 | /r/LocalLLaMA/comments/18s4sf0/gpu_server_cases_options/ | false | false | self | 1 | {'enabled': False, 'images': [{'id': 'K37-GLutvaiKkL3PcHn3e19Sy2pu9JLS0pod2lTG2UI', 'resolutions': [{'height': 108, 'url': 'https://external-preview.redd.it/R7W_h__yFT0vpNnwTuqlyfXMld-Gx1gn0uX8j9cF1OM.jpg?width=108&crop=smart&auto=webp&s=cf14d84a79b6e1ff534bfac03dcf5b02c6829a01', 'width': 108}, {'height': 216, 'url': '... |
Is Llama.cpp Using GPU's on my M2 Max? | 7 | Getting my feet wet with llama.cpp and trying to use GPU's during training. I'm using this command to start, on a tiny test dataset (5 observations):
./finetune --model-base ./models/llama-2-7b.Q8_0.gguf --train-data train_data/durant_QA_training_test_llama_format.json --threads 8 --sample-start "<s>" --ctx 1024 ... | 2023-12-27T16:21:04 | https://www.reddit.com/r/LocalLLaMA/comments/18s4f1r/is_llamacpp_using_gpus_on_my_m2_max/ | Mbando | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 18s4f1r | false | null | t3_18s4f1r | /r/LocalLLaMA/comments/18s4f1r/is_llamacpp_using_gpus_on_my_m2_max/ | false | false | self | 7 | null |
Can I use embedding models from the MTEB board with generate embedding api of ollama to generate embedding? | 5 | If yes, then how? | 2023-12-27T15:11:12 | https://www.reddit.com/r/LocalLLaMA/comments/18s2ugm/can_i_use_embedding_models_from_the_mteb_board/ | coderinlaw | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 18s2ugm | false | null | t3_18s2ugm | /r/LocalLLaMA/comments/18s2ugm/can_i_use_embedding_models_from_the_mteb_board/ | false | false | self | 5 | null |
(Un)censored models that can run with 4gb Ram | 1 | [removed] | 2023-12-27T15:11:06 | https://www.reddit.com/r/LocalLLaMA/comments/18s2uds/uncensored_models_that_can_run_with_4gb_ram/ | Jsus-Sus | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 18s2uds | false | null | t3_18s2uds | /r/LocalLLaMA/comments/18s2uds/uncensored_models_that_can_run_with_4gb_ram/ | false | false | self | 1 | null |
Open Source LLM With Greatest Tokens Per Second? | 4 | Hello everyone! I'm very new to LLM development and deployment in general so please bear with me.
I'd like to deploy a Large Language Model ChatBot onto a service like HuggingFace's free tier or Oracle's Free tier.
The purpose of the model will be for students to demonstrate and practice Prompt Injection attacks, and... | 2023-12-27T14:57:35 | https://www.reddit.com/r/LocalLLaMA/comments/18s2jgh/open_source_llm_with_greatest_tokens_per_second/ | Aathishs04 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 18s2jgh | false | null | t3_18s2jgh | /r/LocalLLaMA/comments/18s2jgh/open_source_llm_with_greatest_tokens_per_second/ | false | false | self | 4 | null |
How to avoid sensitive data/PII being part of LLM training data? | 7 | How are you making sure your proprietary data (including sensitive info and PII) doesn't become part of LLM training data.
We are fine tuning a LLM with our internal docs and data pulled from a couple of SaaS applications, but I am afraid that if any of proprietary data becomes part of the LLM, there are very high ch... | 2023-12-27T14:13:19 | https://www.reddit.com/r/LocalLLaMA/comments/18s1lvj/how_to_avoid_sensitive_datapii_being_part_of_llm/ | deeepak143 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 18s1lvj | false | null | t3_18s1lvj | /r/LocalLLaMA/comments/18s1lvj/how_to_avoid_sensitive_datapii_being_part_of_llm/ | false | false | self | 7 | null |
Keeping up with hardware requirements | 1 | Hi all! Are there any resources you use to keep up with hardware requirements? Looking to understand what hardware is needed to:
1. Run from GCP
2. Run from AWS
3. Run from Local
4. Run from general cloud frameworks
That part of the local LLM movement has missed my understanding somewhere. I understand a hefty GPU... | 2023-12-27T14:12:37 | https://www.reddit.com/r/LocalLLaMA/comments/18s1lcg/keeping_up_with_hardware_requirements/ | balcell | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 18s1lcg | false | null | t3_18s1lcg | /r/LocalLLaMA/comments/18s1lcg/keeping_up_with_hardware_requirements/ | false | false | default | 1 | null |
"Large World Model" | 1 | [removed] | 2023-12-27T13:44:29 | https://www.reddit.com/r/LocalLLaMA/comments/18s10mf/large_world_model/ | Muted-Opinion-2838 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 18s10mf | false | null | t3_18s10mf | /r/LocalLLaMA/comments/18s10mf/large_world_model/ | false | false | default | 1 | null |
Simple Local Models Answers Evaluation Colab example (with GPT4, no langchain etc.) | 26 | Hi, beloved sub!
I have tried to find any ready-to-go simple examples of local model response evaluation with GPT4 but have seen only complicated implementations with heavy libraries like langchaing, etc.
[Here](https://colab.research.google.com/drive/1sfxCoW2tJd6IJ_psSumGWzNwqEbtbu-4?usp=sharing), I implemented a s... | 2023-12-27T13:33:57 | https://www.reddit.com/r/LocalLLaMA/comments/18s0t6q/simple_local_models_answers_evaluation_colab/ | Shir_man | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 18s0t6q | false | null | t3_18s0t6q | /r/LocalLLaMA/comments/18s0t6q/simple_local_models_answers_evaluation_colab/ | false | false | self | 26 | {'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': '... |
optimicing super slow ollama | 1 | Sure, here is the proofread text:
**Hi, I just installed Ollama in a Ubuntu container on Proxmox and it's painfully slow, taking like 10 minutes per prompt.**
It only utilizes around 8% of the allocated 5 CPU cores (i7-14700K) and 500 Mbit of the 15 Gbit RAM. I could throw way more RAM at it, but it's probably not th... | 2023-12-27T13:22:31 | https://www.reddit.com/r/LocalLLaMA/comments/18s0l5e/optimicing_super_slow_ollama/ | Sturmkater | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 18s0l5e | false | null | t3_18s0l5e | /r/LocalLLaMA/comments/18s0l5e/optimicing_super_slow_ollama/ | false | false | default | 1 | null |
Showcasing Deployment of 7B LLM via AWS Fargate Service | 11 | My Docker Image is sent to ECR and I have declared a task definition to fire up my LLM container and made that a Fargate ECS Service. I toggle it on/off easily whenever I want to chat. And the costs are insanely cheap when used this way. Just a few cents for me. The bulk of the cost monthly is maintaining the VPC and n... | 2023-12-27T12:48:12 | https://www.reddit.com/gallery/18rzyf4 | Happy_Chicken9835 | reddit.com | 1970-01-01T00:00:00 | 0 | {} | 18rzyf4 | false | null | t3_18rzyf4 | /r/LocalLLaMA/comments/18rzyf4/showcasing_deployment_of_7b_llm_via_aws_fargate/ | false | false | 11 | null |
Subsets and Splits
No community queries yet
The top public SQL queries from the community will appear here once available.