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 ⌀ |
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
Keeping the input embeddings entirely on CPU in PyTorch | 7 | I have a local model with a peculiar structure: the model itself is very small, outside the embedding matrices, which are massive. The sheer size massively slows and degrades training on my GPU, making borderline impossible to get anything useful out of it.
I'm wondering if it would be straightforward to keep the e... | 2024-01-11T18:29:14 | https://www.reddit.com/r/LocalLLaMA/comments/1948oq8/keeping_the_input_embeddings_entirely_on_cpu_in/ | mildresponse | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 1948oq8 | false | null | t3_1948oq8 | /r/LocalLLaMA/comments/1948oq8/keeping_the_input_embeddings_entirely_on_cpu_in/ | false | false | self | 7 | null |
Best Model for Code Analysis in C/C++? | 4 | I need a model for C/C++ code analysis, finding bug in the code, suggesting improvements, writing test cases etc.
Will WizardCoder for python can work for c/c++? Or is there any other better model out there? | 2024-01-11T18:25:14 | https://www.reddit.com/r/LocalLLaMA/comments/1948l9a/best_model_for_code_analysis_in_cc/ | GoodGalsSwallows | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 1948l9a | false | null | t3_1948l9a | /r/LocalLLaMA/comments/1948l9a/best_model_for_code_analysis_in_cc/ | false | false | self | 4 | null |
WhiteRabbitNeo-33B | 42 | In our commitment to developing offensive and defensive cybersecurity agents in the open, today we're open sourcing our larger model, WhiteRabbitNeo-33B-v1.0.
The model has been trained on a proprietary dataset containing custom Metasploit module development, Active Directory, red-teaming Windows, networking and API... | 2024-01-11T18:13:46 | https://www.reddit.com/r/LocalLLaMA/comments/1948bc5/whiterabbitneo33b/ | migtissera | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 1948bc5 | false | null | t3_1948bc5 | /r/LocalLLaMA/comments/1948bc5/whiterabbitneo33b/ | false | false | 42 | {'enabled': False, 'images': [{'id': 'NGYmN_uiLj1VOLCZVwTj9rn4b-3P5cXVR6Gce1fOFgE', 'resolutions': [{'height': 58, 'url': 'https://external-preview.redd.it/0ciQRdtB50MXrw4jyzVJZr3Z1skLfse3xjNARkEs9ko.jpg?width=108&crop=smart&auto=webp&s=2526be5775117da8c2b9d8d1d4b06fba5dd1e016', 'width': 108}, {'height': 116, 'url': 'h... | |
Any LLMs with ethically sourced training data? | 1 | I tried looking around, doing some searches on google, but couldn't find any LLMs with an open/ethically sourced training set.
​
Are there any that exist? | 2024-01-11T18:12:44 | https://www.reddit.com/r/LocalLLaMA/comments/1948adv/any_llms_with_ethically_sourced_training_data/ | Own-Candle-9993 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 1948adv | false | null | t3_1948adv | /r/LocalLLaMA/comments/1948adv/any_llms_with_ethically_sourced_training_data/ | false | false | self | 1 | null |
Taking your LLaMA app from prototype to production, what are we missing? | 1 | 2024-01-11T18:06:55 | https://nux.ai/guides/ai-apps-from-prototype-to-production | nuxai | nux.ai | 1970-01-01T00:00:00 | 0 | {} | 194858y | false | null | t3_194858y | /r/LocalLLaMA/comments/194858y/taking_your_llama_app_from_prototype_to/ | false | false | 1 | {'enabled': False, 'images': [{'id': '0C3cn9QRJU5TxUAO59YhbTRCjPGSKF1jxDuAhnbp_7c', 'resolutions': [{'height': 61, 'url': 'https://external-preview.redd.it/oBN0n4AfNDoOOj24TCfa0hji8RqQ3Wqv72XpokV8iJM.jpg?width=108&crop=smart&auto=webp&s=f99d941b35411f6ed29d6622865be29e30b599cf', 'width': 108}, {'height': 123, 'url': 'h... | ||
Building a new rig - enlighten me! | 1 | Hi,
As per the title, I'm currently in the midst of building a new rig to run my own LLMs locally.
I'll be using these LLM(s) to build my own personal assistant, and planning to integrate it with my own NodeJS/FastAPI api endpoints to connect to different services e.g. Notion, Todoist, the whole 9 yards.
Here's the... | 2024-01-11T17:56:37 | https://www.reddit.com/r/LocalLLaMA/comments/1947vvu/building_a_new_rig_enlighten_me/ | Kaldnite | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 1947vvu | false | null | t3_1947vvu | /r/LocalLLaMA/comments/1947vvu/building_a_new_rig_enlighten_me/ | false | false | self | 1 | null |
Meta Admits Use of ‘Pirated’ Book Dataset to Train AI | 187 | >*With AI initiatives developing at a rapid pace, copyright holders are on high alert. In addition to legislation, several currently ongoing lawsuits will help to define what's allowed and what isn't. Responding to a lawsuit from several authors, Meta now admits that it used portions of the Books3 dataset to train its ... | 2024-01-11T17:32:11 | https://www.reddit.com/r/LocalLLaMA/comments/19479qy/meta_admits_use_of_pirated_book_dataset_to_train/ | IntrovertedFL | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 19479qy | false | null | t3_19479qy | /r/LocalLLaMA/comments/19479qy/meta_admits_use_of_pirated_book_dataset_to_train/ | false | false | self | 187 | null |
Gemini pro seems better than ChatGPT at keepin' it real | 55 | 2024-01-11T17:30:31 | foazi | i.redd.it | 1970-01-01T00:00:00 | 0 | {} | 194787n | false | null | t3_194787n | /r/LocalLLaMA/comments/194787n/gemini_pro_seems_better_than_chatgpt_at_keepin_it/ | false | false | 55 | {'enabled': True, 'images': [{'id': 'a8N7DbCGWNc8rlvi280kA2OBQ4Baw6Rhn1db4c5fYWg', 'resolutions': [{'height': 55, 'url': 'https://preview.redd.it/tnlnv1s4jubc1.png?width=108&crop=smart&auto=webp&s=47e8a44ae0305d04f3e1b0b3ac4ff7b44006bffe', 'width': 108}, {'height': 111, 'url': 'https://preview.redd.it/tnlnv1s4jubc1.png... | |||
What is the fastest way to serve batch > 1 llm requests on a 4090? | 8 | I'm want to setup a friends and family server on my home 4090 with a yi 200k finetune. What's the most performant solution in terms of tokens/second? Is it still vllm or something else? | 2024-01-11T17:18:37 | https://www.reddit.com/r/LocalLLaMA/comments/1946xc8/what_is_the_fastest_way_to_serve_batch_1_llm/ | kerrygotten | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 1946xc8 | false | null | t3_1946xc8 | /r/LocalLLaMA/comments/1946xc8/what_is_the_fastest_way_to_serve_batch_1_llm/ | false | false | self | 8 | null |
Model MythoMax L2 13B available again | 1 | This model is proficient at both roleplaying and storywriting, so if you want to try it on the net before you run it local try [Infermatic.ai](https://infermatic.ai/) .
If you dont know what it is --> An improved, potentially even perfected variant of MythoMix, my [**MythoLogic-L2**](https://huggingface.co/Gryphe/Myth... | 2024-01-11T17:04:04 | https://www.reddit.com/r/LocalLLaMA/comments/1946kl0/model_mythomax_l2_13b_available_again/ | Horror_Echo6243 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 1946kl0 | false | null | t3_1946kl0 | /r/LocalLLaMA/comments/1946kl0/model_mythomax_l2_13b_available_again/ | false | false | self | 1 | {'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': '... |
How to enable cuBLAS in privateGPT | 2 | Hello everyone,
I experimenting with the privateGPT setup and I got everything working so far. I am using a runpod with Ububtu 20.4 x86. I can see a memory usage when I am uploading documents but the utilization is allways 0. Also when I am spinning it up the BLAS parameter is allways 0. CUDA and nvidia drivers are i... | 2024-01-11T16:35:26 | https://www.reddit.com/r/LocalLLaMA/comments/1945vga/how_to_enable_cublas_in_privategpt/ | Blax363 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 1945vga | false | null | t3_1945vga | /r/LocalLLaMA/comments/1945vga/how_to_enable_cublas_in_privategpt/ | false | false | self | 2 | null |
"Challenge LLMs to Reason About Reasoning: A Benchmark to Unveil Cognitive Depth in LLMs" (DiagGSM8K) | 38 | **Paper**: [https://arxiv.org/abs/2312.17080](https://arxiv.org/abs/2312.17080)
**Code**: [https://github.com/dvlab-research/DiagGSM8K](https://github.com/dvlab-research/DiagGSM8K)
**Dataset**: [https://huggingface.co/datasets/Randolphzeng/DiagGSM8K](https://huggingface.co/datasets/Randolphzeng/DiagGSM8K)
**Abstract... | 2024-01-11T16:33:10 | https://www.reddit.com/r/LocalLLaMA/comments/1945tfv/challenge_llms_to_reason_about_reasoning_a/ | APaperADay | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 1945tfv | false | null | t3_1945tfv | /r/LocalLLaMA/comments/1945tfv/challenge_llms_to_reason_about_reasoning_a/ | false | false | self | 38 | null |
How to make or code something locally with ai? | 1 | I have dolphin mistral 7b with kobold lite, and i was wondering what types of things can i make with ai code and if it could teach me something? Ive really been wanting to make games but can i use ai to help me and what languages/game engines is ai good at especially a 7b model? where would i share the final product at... | 2024-01-11T15:49:32 | https://www.reddit.com/r/LocalLLaMA/comments/1944spp/how_to_make_or_code_something_locally_with_ai/ | Gaming-invisibleman | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 1944spp | false | null | t3_1944spp | /r/LocalLLaMA/comments/1944spp/how_to_make_or_code_something_locally_with_ai/ | false | false | self | 1 | null |
Advice on fine-tuning? | 18 | So I'm finally getting a bit of free time in my personal life, and I've started to take the next step in my local AI journey - fine-tuning.
My primary rig has 6x3090's, with three NVLink's in place (GPUs 0-1, 2-3, and 4-5) for a total VRAM of 144GB.
I've created an alpaca format dataset that I'd like to use, but I'm ... | 2024-01-11T15:26:17 | https://www.reddit.com/r/LocalLLaMA/comments/1944993/advice_on_finetuning/ | Mass2018 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 1944993 | false | null | t3_1944993 | /r/LocalLLaMA/comments/1944993/advice_on_finetuning/ | false | false | self | 18 | null |
Phi-2 & Tiny LLama on Raspberry Pi 5 | 23 | Hi everyone,
I have done some tests using RPI5 8GB RAM. Here are the results:
1. TheBloke dolphin-2\_6-phi-2.Q4\_K\_M.gguf - 5 tokens/s
2. TheBloke tinyllama-1.1b-chat-v1.0.Q4\_K\_M.gguf - 10 tokens/s
Question was: "Hey can you give me some spaghetti recipe?"
Phi:
Of course! Here's a simple spaghetti recipe. Boil ... | 2024-01-11T15:20:30 | https://www.reddit.com/r/LocalLLaMA/comments/19444pu/phi2_tiny_llama_on_raspberry_pi_5/ | flopik | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 19444pu | false | null | t3_19444pu | /r/LocalLLaMA/comments/19444pu/phi2_tiny_llama_on_raspberry_pi_5/ | false | false | self | 23 | {'enabled': False, 'images': [{'id': 'mmSEhOO2Ya4Cjle-07d9l2l3p0K02gcnbjuYTcgYymE', 'resolutions': [{'height': 58, 'url': 'https://external-preview.redd.it/y7kZ5l3eN4uJnoeNp6fBiLE1B0DlXrgor7Ux1ilJt5k.jpg?width=108&crop=smart&auto=webp&s=c2033248ce0605f92a32f5c9fa9ac056a52d65bc', 'width': 108}, {'height': 116, 'url': 'h... |
Why such a drastic difference between EXL2 and GGUF of the same model? GGUF seems much better? | 38 | Hi all,
I've been using this model for a while now
https://huggingface.co/TheBloke/dolphin-2.5-mixtral-8x7b-GGUF
And decided to try the EXL2 by LoneStriker listed here
https://huggingface.co/LoneStriker/dolphin-2.5-mixtral-8x7b-3.5bpw-h6-exl2-2
Because I've heard the EXL2 format has a lot of benefits. I'm current... | 2024-01-11T15:15:01 | https://www.reddit.com/r/LocalLLaMA/comments/19440fy/why_such_a_drastic_difference_between_exl2_and/ | Some_guitarist | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 19440fy | false | null | t3_19440fy | /r/LocalLLaMA/comments/19440fy/why_such_a_drastic_difference_between_exl2_and/ | false | false | self | 38 | {'enabled': False, 'images': [{'id': 'Bfy8S1MwmvHWyvq3x1bCEzeTfWTZ5f6ChredIZbGrJk', 'resolutions': [{'height': 58, 'url': 'https://external-preview.redd.it/RCCYnWs6XiK7XvhWQVyugz8VLphXcECiWnO7WnySlWg.jpg?width=108&crop=smart&auto=webp&s=75a2ddbf4733f0554ee5ed67020a63bb8dfb8783', 'width': 108}, {'height': 116, 'url': 'h... |
Model Recommendations for Role Playing (Yi34B-based) | 8 | Hi, I'm looking for a good Yi 34B based model that is good in role-playing.
Do you have any suggestions?
Thanks and have a nice day! | 2024-01-11T15:06:03 | https://www.reddit.com/r/LocalLLaMA/comments/1943t4a/model_recommendations_for_role_playing_yi34bbased/ | Weyaxi | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 1943t4a | false | null | t3_1943t4a | /r/LocalLLaMA/comments/1943t4a/model_recommendations_for_role_playing_yi34bbased/ | false | false | self | 8 | null |
Local LLM laptop: MacBook vs NVIDIA GPU | 5 | As a laptop to run Local LLMs, would you recommend a MacBook Pro with a lot of unified memory or a laptop with a discrete NVIDIA GPU (with 8 GB of VRAM)? | 2024-01-11T15:04:28 | https://www.reddit.com/r/LocalLLaMA/comments/1943rst/local_llm_laptop_macbook_vs_nvidia_gpu/ | ekerazha | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 1943rst | false | null | t3_1943rst | /r/LocalLLaMA/comments/1943rst/local_llm_laptop_macbook_vs_nvidia_gpu/ | false | false | self | 5 | null |
Fine-tuning LLMs for classification tasks -> Windows malware api call logs | 1 |
Hello to the people on LocalLLama,
Im just trying to use LLMs such as codellama to classify input text, the input text is from api call logs of windows malware. I have 8 classes and around 80k documents/JSON files that I want to fine-tune the llm on, post which I want to get the llm to spit out a class for the inpu... | 2024-01-11T14:23:55 | https://www.reddit.com/r/LocalLLaMA/comments/1942vlj/finetuning_llms_for_classification_tasks_windows/ | Akimbo-fmg-9 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 1942vlj | false | null | t3_1942vlj | /r/LocalLLaMA/comments/1942vlj/finetuning_llms_for_classification_tasks_windows/ | false | false | self | 1 | null |
Transformers.js v2.14 adds in-browser Segment Anything w/ SlimSAM | 141 | 2024-01-11T13:58:39 | https://v.redd.it/wglfo5vkgtbc1 | xenovatech | v.redd.it | 1970-01-01T00:00:00 | 0 | {} | 1942bvt | false | {'reddit_video': {'bitrate_kbps': 1200, 'dash_url': 'https://v.redd.it/wglfo5vkgtbc1/DASHPlaylist.mpd?a=1707573532%2CMzYzMmM5YThjMDFhMGVjNDk1NThmODlkNGMyMjliNmE2MjRkYTRiMTJiNmEzNmU0Njc3MjA3MDgyNmUwN2Q0NA%3D%3D&v=1&f=sd', 'duration': 16, 'fallback_url': 'https://v.redd.it/wglfo5vkgtbc1/DASH_480.mp4?source=fallback', 'ha... | t3_1942bvt | /r/LocalLLaMA/comments/1942bvt/transformersjs_v214_adds_inbrowser_segment/ | false | false | 141 | {'enabled': False, 'images': [{'id': 'Yzc3ZHJ0MWZodGJjMVwpVUafglgPOgBEIAKsTPvBKLtNoSTYJ_-kg7_CxMgx', 'resolutions': [{'height': 93, 'url': 'https://external-preview.redd.it/Yzc3ZHJ0MWZodGJjMVwpVUafglgPOgBEIAKsTPvBKLtNoSTYJ_-kg7_CxMgx.png?width=108&crop=smart&format=pjpg&auto=webp&s=0d7a26ac96808a9c5c4a13b82c4df25466bbc... | ||
Quick overview of price/preformance for text generation on different GPUs | 162 | ​
|GPU|T/S|$/HR|T/$|WINNER|
|:-|:-|:-|:-|:-|
|RTX A6000|52.778275125799354|0.79|66.81|🏆|
|A40|45.17065873434471|0.79|57.18|✅|
|L40|56.87802678475367|1.14|49.89|✅|
|A100 SXM|61.965978844301496|2.29|27.06|❌|
|RTX4090|12.613347074703317|0.74|17.05|❌|
|H100|43.002703448927555|4.69|9.17|❌|
|RTX A5000|1.599260046273... | 2024-01-11T13:54:24 | https://www.reddit.com/r/LocalLLaMA/comments/19428v9/quick_overview_of_pricepreformance_for_text/ | MarksGG | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 19428v9 | false | null | t3_19428v9 | /r/LocalLLaMA/comments/19428v9/quick_overview_of_pricepreformance_for_text/ | false | false | self | 162 | {'enabled': False, 'images': [{'id': 'BgeV6m2P-1bGfzHkClsV6fGcuV9de1pTvejeuh-yOOw', 'resolutions': [{'height': 54, 'url': 'https://external-preview.redd.it/IbL7X3PcgfiQV-ujCMZdcU1PtR40UbzZrB-yBT1ZtWk.jpg?width=108&crop=smart&auto=webp&s=60ecec693f5b9f79b531d1a8d9b32d5ea026830e', 'width': 108}, {'height': 108, 'url': 'h... |
Multi-GPU setups | 1 | OK I have been badly infected with the LLM-madness
What are some good resources or advice for someone considering setting up multi GPU setup.
I am considering:
A) Some cheap server with slots for many cheap GPUs like 3060 12GB
B) Two (or three) GPU setup for my desktop | 2024-01-11T13:40:00 | https://www.reddit.com/r/LocalLLaMA/comments/1941y10/multigpu_setups/ | Full_Operation_9865 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 1941y10 | false | null | t3_1941y10 | /r/LocalLLaMA/comments/1941y10/multigpu_setups/ | false | false | self | 1 | null |
Fine-tune for specific writing style based on text samples | 1 | Looking for a tutorial on how to best fine-tune on a large sample of writing data for a specific use case i.e. writing social media posts based on a businesses past posts.
The tutorials I've seen on creating a dataset are all just prompt and output examples but I don't think that's exactly what I am looking for. | 2024-01-11T13:29:10 | https://www.reddit.com/r/LocalLLaMA/comments/1941q0t/finetune_for_specific_writing_style_based_on_text/ | DK_Tech | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 1941q0t | false | null | t3_1941q0t | /r/LocalLLaMA/comments/1941q0t/finetune_for_specific_writing_style_based_on_text/ | false | false | self | 1 | null |
Question re. roles of various tools | 1 | I'm struggling to understand the roles of different local llm tools, and hope someone can help.
My goal: Build a POC "chat with docs" system for a business with multiple users/teams, each with different datasets. Everything must run local, no internet.
My current mental model of two tools:
--Ollama: Hosts/connects... | 2024-01-11T13:20:44 | https://www.reddit.com/r/LocalLLaMA/comments/1941jyb/question_re_roles_of_various_tools/ | CapsFanHere | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 1941jyb | false | null | t3_1941jyb | /r/LocalLLaMA/comments/1941jyb/question_re_roles_of_various_tools/ | false | false | self | 1 | null |
Intel Core Ultra and LLMs | 1 | I need to buy a new laptop, where I expect to run a 7b model and, if possible, some fine tuning. I was just wondering if/how the new Intel Core Ultra with its NPU and GPU could fit. It will not compete with GPU and CUDA, but I was wondering how this compete with a Macbook Silicon (to me it looks like Macbook is better ... | 2024-01-11T13:15:25 | https://www.reddit.com/r/LocalLLaMA/comments/1941g99/intel_core_ultra_and_llms/ | IzzyHibbert | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 1941g99 | false | null | t3_1941g99 | /r/LocalLLaMA/comments/1941g99/intel_core_ultra_and_llms/ | false | false | self | 1 | null |
Why is llama.cpp still called 'llama.cpp' today? | 1 | Hi guys,
pls forgive me if you think what a dumb question - that appears to me as well :-)
I'm new to the whole stuff ML/LLM, trying to understand bit after another, so the name of the project llama.cpp confused me a lot at the first try. I though it is only re-implementation of LLaMA model in C++, no, now it can run... | 2024-01-11T13:14:27 | https://www.reddit.com/r/LocalLLaMA/comments/1941fj2/why_is_llamacpp_still_called_llamacpp_today/ | tunggad | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 1941fj2 | false | null | t3_1941fj2 | /r/LocalLLaMA/comments/1941fj2/why_is_llamacpp_still_called_llamacpp_today/ | false | false | self | 1 | null |
Creating your own embedding model to boost retrieval performance | 4 | I have RAG pipeline for medical documents. There are a lot specific features in the language only relevant to medicine. Someone suggested created a custom embeddings model, just wondering if anyone has done this, any direction on how to start if so? Did it help and how did you qualify the uplift in performance if it di... | 2024-01-11T13:06:12 | https://www.reddit.com/r/LocalLLaMA/comments/19419yg/creating_your_own_embedding_model_to_boost/ | drivenkey | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 19419yg | false | null | t3_19419yg | /r/LocalLLaMA/comments/19419yg/creating_your_own_embedding_model_to_boost/ | false | false | self | 4 | null |
Using DeepInfra's Custom LLM with Pandasai | 1 | Hello everyone, I'm not very good at python and I'm trying to use pandasai with custom LLM by deepinfra. I'm stuck at how can I use the custom endpoints along with one of the notebook that was shared in this forum. I'm sharing the code below, if someone can help that would be really helpful
`import pandas as pd`
... | 2024-01-11T12:52:51 | https://www.reddit.com/r/LocalLLaMA/comments/19410sj/using_deepinfras_custom_llm_with_pandasai/ | nishant299 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 19410sj | false | null | t3_19410sj | /r/LocalLLaMA/comments/19410sj/using_deepinfras_custom_llm_with_pandasai/ | false | false | self | 1 | {'enabled': False, 'images': [{'id': 'gdv5Bh89JWXxDpkAlTrk_zCb-qJxrREhAWY8_SsUogU', 'resolutions': [{'height': 108, 'url': 'https://external-preview.redd.it/9yZr3zHUmyWQtvbJofUKJroV_0PJzwp1lwBQ4qcwT7s.jpg?width=108&crop=smart&auto=webp&s=4e8ad5cdf82a75c71c4af7b04654daaa4f3a27a1', 'width': 108}, {'height': 216, 'url': '... |
Open source version of OpenAI assistants? | 2 | Hey guys so as the title suggests I'm curious to know if there are any open source alternatives to OpenAI assistants. I understand that function calling can be accomplished using grammars for instance and there are plenty of open source RAG (knowledge retrieval) solutions. However what I would like to find out is if th... | 2024-01-11T12:46:24 | https://www.reddit.com/r/LocalLLaMA/comments/1940wj0/open_source_version_of_openai_assistants/ | MonkeyMaster64 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 1940wj0 | false | null | t3_1940wj0 | /r/LocalLLaMA/comments/1940wj0/open_source_version_of_openai_assistants/ | false | false | self | 2 | null |
MegaDolphin- 120b released by Erick Hartford | 58 | Just saw that Eric Hartford have published a 120b model similar to Goliath but using dolphin-2.2-70b for the merge. here is the twitter post
https://x.com/erhartford/status/1745187763673276793?t=wtDpQ8G2b40OFK6Cq9Fh5w&s=09
And the huggingface link
https://huggingface.co/cognitivecomputations/MegaDolphin-120b/tree/main... | 2024-01-11T12:00:57 | https://www.reddit.com/r/LocalLLaMA/comments/194036l/megadolphin_120b_released_by_erick_hartford/ | m_mukhtar | self.LocalLLaMA | 2024-01-11T13:43:13 | 0 | {} | 194036l | false | null | t3_194036l | /r/LocalLLaMA/comments/194036l/megadolphin_120b_released_by_erick_hartford/ | false | false | self | 58 | {'enabled': False, 'images': [{'id': 'dkibOVShc_1z4JacNGblZJDqpuoj0VIJB_eeSubb1yY', 'resolutions': [{'height': 108, 'url': 'https://external-preview.redd.it/FNgq4Z7iPgrvEb29t89h9Z3tjSlfzw9JbZyl6czH9Zw.jpg?width=108&crop=smart&auto=webp&s=4fe4a0005b9d10261c67e939033e53c397e6cf54', 'width': 108}, {'height': 216, 'url': '... |
The secret to improve the performance of Mixtral MoE model | 7 | This is cloudyu, recently I focus on testing mixtral based models.
I found the parameter of num_experts_per_tok is very important.
Here I test hellaswag for
[cloudyu/Mixtral_7Bx4_MOE_24B](https://huggingface.co/cloudyu/Mixtral_7Bx4_MOE_24B) with different num_experts_per_tok
- num_experts_per_tok=2
hf (pretrained=/home... | 2024-01-11T11:41:35 | https://www.reddit.com/r/LocalLLaMA/comments/193zr7l/the_secret_to_improve_the_performance_of_mixtral/ | OkAcanthocephala3355 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 193zr7l | false | null | t3_193zr7l | /r/LocalLLaMA/comments/193zr7l/the_secret_to_improve_the_performance_of_mixtral/ | false | false | self | 7 | {'enabled': False, 'images': [{'id': 'UbhHHn_oYvdU2BRCY8XPutI5H59Gismm2pyVa9YL3f4', 'resolutions': [{'height': 58, 'url': 'https://external-preview.redd.it/d5-V5zsl6B-5_3p_aDeT1b1kbpIra4Dn1zz6u61l2F4.jpg?width=108&crop=smart&auto=webp&s=3fe3ec235277406b3ef2bdac29b5bcd21b0cf493', 'width': 108}, {'height': 116, 'url': 'h... |
API for dolphin mistral? | 1 | Is there any online api that would let me run dolphin mistral in a OpenAI api like system? | 2024-01-11T11:39:30 | https://www.reddit.com/r/LocalLLaMA/comments/193zpw3/api_for_dolphin_mistral/ | Responsible-Sky8889 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 193zpw3 | false | null | t3_193zpw3 | /r/LocalLLaMA/comments/193zpw3/api_for_dolphin_mistral/ | false | false | self | 1 | null |
Can you guys sanity check for me? | 1 | Would love for get feedback on how feasible this would be to setup, and get pointers on where to start!
I made a post about how sleazy OpenAI was after realizing they switched their data privacy/usage policy from opt-in to opt-out late last year without letting users know. Only those in the EU got a courtesy email cu... | 2024-01-11T11:21:55 | https://www.reddit.com/r/LocalLLaMA/comments/193zfiq/can_you_guys_sanity_check_for_me/ | GeeBrain | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 193zfiq | false | null | t3_193zfiq | /r/LocalLLaMA/comments/193zfiq/can_you_guys_sanity_check_for_me/ | false | false | self | 1 | null |
How do you discover tools/ideas that might help improve your LLM-based apps which are not RAG? | 16 | Hi!
I'm new to LLM-based applications and mainly just trying stuff for fun and learning to improve my skills and knowledge but I was wondering how do you discover ideas/tools that can help improve your way of interacting between data and LLMs in applications which are not RAG, for which I find there are a lot of resou... | 2024-01-11T10:53:49 | https://www.reddit.com/r/LocalLLaMA/comments/193yz5r/how_do_you_discover_toolsideas_that_might_help/ | Mean-Night6324 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 193yz5r | false | null | t3_193yz5r | /r/LocalLLaMA/comments/193yz5r/how_do_you_discover_toolsideas_that_might_help/ | false | false | self | 16 | null |
Axolotl training with instruct dataset | 2 | I am trying to create axolotl config that will work with dataset that has instructions defined in following format <s>\[INST\] {instruction} {question}\[/INST\] {answer}</s>.
Can someone please advise how dataset definition should be define in axolotl config.yaml file for it.
Thanx! | 2024-01-11T10:05:58 | https://www.reddit.com/r/LocalLLaMA/comments/193y9ic/axolotl_training_with_instruct_dataset/ | hrdingo | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 193y9ic | false | null | t3_193y9ic | /r/LocalLLaMA/comments/193y9ic/axolotl_training_with_instruct_dataset/ | false | false | default | 2 | null |
How good is Mistral 7b at Function calling? | 2 | I want to use function calling in openorca mistral 7b but I'm just not sure how good can it be. Are there any mistral 7b fine tuned models that are better for function calling?
​ | 2024-01-11T08:19:11 | https://www.reddit.com/r/LocalLLaMA/comments/193wqoi/how_good_is_mistral_7b_at_function_calling/ | NFCProdACR | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 193wqoi | false | null | t3_193wqoi | /r/LocalLLaMA/comments/193wqoi/how_good_is_mistral_7b_at_function_calling/ | false | false | self | 2 | null |
Free LLM APIs | 2 | I'm looking to categorize my images. So I want to write a simple Python program that takes the filename of a list of images and returns a list of tags for each filename.
Are there any free LLM APIs out there that I could use for a task like this?
I have a very basic computer, so running a local LLM is probably not po... | 2024-01-11T08:17:44 | https://www.reddit.com/r/LocalLLaMA/comments/193wpyj/free_llm_apis/ | vroemboem | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 193wpyj | false | null | t3_193wpyj | /r/LocalLLaMA/comments/193wpyj/free_llm_apis/ | false | false | self | 2 | null |
Any alternatives for H2O DataStudio ? | 9 | Hello i have seen H2O Datastudio [(ref)](https://docs.h2o.ai/h2o-llm-data-studio/) and i think such tool can be good for an amateur like me, as it covers multiple aspects of dataset creation. It seems that it is not an open source project so i couldnt install it and run locally. Does anybody knows any alternative?
To... | 2024-01-11T07:56:33 | https://www.reddit.com/r/LocalLLaMA/comments/193weeb/any_alternatives_for_h2o_datastudio/ | idesireawill | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 193weeb | false | null | t3_193weeb | /r/LocalLLaMA/comments/193weeb/any_alternatives_for_h2o_datastudio/ | false | false | self | 9 | null |
[Demo] NVIDIA Chat With RTX | Leveraging retrieval-augmented generation (RAG), TensorRT-LLM, and RTX acceleration, you can query a custom chatbot | 27 | 2024-01-11T07:55:41 | https://www.nvidia.com/en-us/ai-on-rtx/chat-with-rtx-generative-ai/ | Nunki08 | nvidia.com | 1970-01-01T00:00:00 | 0 | {} | 193we0e | false | null | t3_193we0e | /r/LocalLLaMA/comments/193we0e/demo_nvidia_chat_with_rtx_leveraging/ | false | false | 27 | {'enabled': False, 'images': [{'id': 'SAAks4rC6Og3LbqkpNqIIY1OPQrjAQsgx0UPGu6Vo5I', 'resolutions': [{'height': 24, 'url': 'https://external-preview.redd.it/d47SYF4-nEdaYG6sETbq_a2ATOg3LUbbAo_imVo58sE.jpg?width=108&crop=smart&auto=webp&s=283a208fabf90a832c132bd833d93ad7ab831009', 'width': 108}, {'height': 48, 'url': 'ht... | ||
Easy-to-use apps/SaaS/tools etc. for fine tune? | 5 | Is there any beginner-friendly apps/SaaS/tools etc. for fine tune if I don't want to jump in the rabbit hole of setting everything up on my laptop, or I don't have a powerful GPU for it?
Ideally, I can simply upload my data, specify a model on HuggingFace and click one button to fine tune the model. | 2024-01-11T07:49:12 | https://www.reddit.com/r/LocalLLaMA/comments/193wapk/easytouse_appssaastools_etc_for_fine_tune/ | felixding | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 193wapk | false | null | t3_193wapk | /r/LocalLLaMA/comments/193wapk/easytouse_appssaastools_etc_for_fine_tune/ | false | false | self | 5 | null |
Running Tinyllama on an Android phone locally no internet. | 1 | [removed] | 2024-01-11T06:11:13 | https://www.reddit.com/r/LocalLLaMA/comments/193us6u/running_tinyllama_on_an_android_phone_locally_no/ | CaptSpalding | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 193us6u | false | null | t3_193us6u | /r/LocalLLaMA/comments/193us6u/running_tinyllama_on_an_android_phone_locally_no/ | false | false | self | 1 | {'enabled': False, 'images': [{'id': 'thB1ECTDhAmAceVvm3UHMmOSs88oRrLCuKd9QyX-vh4', 'resolutions': [{'height': 81, 'url': 'https://external-preview.redd.it/TbEH56oX-ZOBDqgrE723tx8yikJrhQLlnFgXtfR2GAU.jpg?width=108&crop=smart&auto=webp&s=61cdb5163738fa0716d154053f9d42ed67db4923', 'width': 108}, {'height': 162, 'url': 'h... |
[RAG] [llama-index] How to execute multiple SQL queries with SQLTableRetrieverQueryEngine in NL2SQL project? | 1 | I am working on a project where user will ask natural language queries and this llama-index based engine will convert that natural language to sql query and execute it on my database and give answer in natural language to the user. Problem is it is only able to execute one query per question so comparison quetions are ... | 2024-01-11T06:05:59 | https://www.reddit.com/r/LocalLLaMA/comments/193uoti/rag_llamaindex_how_to_execute_multiple_sql/ | HappyDataGuy | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 193uoti | false | null | t3_193uoti | /r/LocalLLaMA/comments/193uoti/rag_llamaindex_how_to_execute_multiple_sql/ | false | false | default | 1 | null |
Easy to use "out of the box" LLM running programs for Macs? | 2 | on my main machine i love use kobold, and even ooba however after making the purchase of a Mac studio M2 192gb, ive come to learn that the environment is different than what i was used to on windows.
So i reverted back to using LM studio on the mac because it was literally just install and use. however i am having som... | 2024-01-11T05:41:15 | https://www.reddit.com/r/LocalLLaMA/comments/193u9c7/easy_to_use_out_of_the_box_llm_running_programs/ | DominicanGreg | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 193u9c7 | false | null | t3_193u9c7 | /r/LocalLLaMA/comments/193u9c7/easy_to_use_out_of_the_box_llm_running_programs/ | false | false | self | 2 | null |
DeepSeek just announced DeepSeek-MoE | 126 | 2024-01-11T05:33:16 | https://nitter.net/_akhaliq/status/1745306807931642055#m | ninjasaid13 | nitter.net | 1970-01-01T00:00:00 | 0 | {} | 193u4eq | false | null | t3_193u4eq | /r/LocalLLaMA/comments/193u4eq/deepseek_just_announced_deepseekmoe/ | false | false | default | 126 | null | |
Why is there a padding=max_length option when there is a padding=longest for hugging face tokenizer? | 1 | I was going through hugging face tokenizer and realised that there are two options for padding - 'longest length in the batch' and 'maximum length accepted by model'. All this while I thought padding meant the former only. Is there any advantage for the second option or in which case should we use it? The attention me... | 2024-01-11T05:29:28 | dire_wolf_cookie | i.redd.it | 1970-01-01T00:00:00 | 0 | {} | 193u203 | false | null | t3_193u203 | /r/LocalLLaMA/comments/193u203/why_is_there_a_paddingmax_length_option_when/ | false | false | 1 | {'enabled': True, 'images': [{'id': '_8POnxrmj2letnf6OakG8CMJCSxiwP9az7_lTv7em50', 'resolutions': [{'height': 54, 'url': 'https://preview.redd.it/9vbtkxtkyqbc1.png?width=108&crop=smart&auto=webp&s=9e42b636da1fef9ff5633b913c29cd4b47482c95', 'width': 108}, {'height': 108, 'url': 'https://preview.redd.it/9vbtkxtkyqbc1.png... | ||
Is data privacy a feature or a right? | 1 | [removed] | 2024-01-11T05:21:49 | https://www.reddit.com/r/LocalLLaMA/comments/193tx6x/is_data_privacy_a_feature_or_a_right/ | GeeBrain | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 193tx6x | false | null | t3_193tx6x | /r/LocalLLaMA/comments/193tx6x/is_data_privacy_a_feature_or_a_right/ | false | false | self | 1 | null |
Need some Advice / Help | 1 | Hello, I have been tasked to find a solution to deploy a fine tuned Mistral 7B model locally. If the solution was to scale to give around 100 people access (Similar to a much smaller Chat GPT), what would rougly be the GPU/CPU requirements to do so? can i chain multiple instances? | 2024-01-11T04:47:31 | https://www.reddit.com/r/LocalLLaMA/comments/193tas7/need_some_advice_help/ | Annukhz | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 193tas7 | false | null | t3_193tas7 | /r/LocalLLaMA/comments/193tas7/need_some_advice_help/ | false | false | self | 1 | null |
Is fine tuning QLoRA still state of the art? | 18 | If so, how are people doing it, what frameworks are we using and what hardware did you invest in? | 2024-01-11T04:27:18 | https://www.reddit.com/r/LocalLLaMA/comments/193sxbj/is_fine_tuning_qlora_still_state_of_the_art/ | HotRepresentative325 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 193sxbj | false | null | t3_193sxbj | /r/LocalLLaMA/comments/193sxbj/is_fine_tuning_qlora_still_state_of_the_art/ | false | false | self | 18 | null |
What are small models that work for you? What are the configs that you use for them? | 9 | When I quantize the OpenHermes model to q2\_k, it's around \~3GB. Has anyone had experience using a smaller quantized model with similar performance? just wondering. What configs do y'all use for your models? Currently, I have "use\_mlock", "n\_ctx: 2048", "n\_gpu\_layers: 0" (running on CPU). I'm not really sure how t... | 2024-01-11T04:24:02 | https://www.reddit.com/r/LocalLLaMA/comments/193sv21/what_are_small_models_that_work_for_you_what_are/ | Powerful-Cupcake-407 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 193sv21 | false | null | t3_193sv21 | /r/LocalLLaMA/comments/193sv21/what_are_small_models_that_work_for_you_what_are/ | false | false | self | 9 | null |
Could an MoE be made up of language and embedding models? | 1 | [removed] | 2024-01-11T04:04:32 | https://www.reddit.com/r/LocalLLaMA/comments/193shv4/could_an_moe_be_made_up_of_language_and_embedding/ | Future_Might_8194 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 193shv4 | false | null | t3_193shv4 | /r/LocalLLaMA/comments/193shv4/could_an_moe_be_made_up_of_language_and_embedding/ | false | false | self | 1 | null |
Templates/presets | 3 | Were can i find presets or templates(like shortwave)?
Is there a website were they are shared? I cant find these presets for the life of me. (From agnaistic) | 2024-01-11T04:03:30 | https://www.reddit.com/r/LocalLLaMA/comments/193sh55/templatespresets/ | darklink6446 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 193sh55 | false | null | t3_193sh55 | /r/LocalLLaMA/comments/193sh55/templatespresets/ | false | false | self | 3 | null |
Interpretation of learnt weight tensors | 4 | Nowadays model merging is rising popularity notably slerp and other interpolation method, I have a doubt how to interpret the weights tensors interpolation concept, I see learn weights of LLMs as high dimensional Dense vectors but I am having difficulty how these tensors orient or change themselves while merging with ... | 2024-01-11T03:50:53 | https://www.reddit.com/r/LocalLLaMA/comments/193s83u/interpretation_of_learnt_weight_tensors/ | MysticShadow427 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 193s83u | false | null | t3_193s83u | /r/LocalLLaMA/comments/193s83u/interpretation_of_learnt_weight_tensors/ | false | false | self | 4 | null |
Prompting strategies to use with LLMs and medical case descriptors? | 1 | I am working on a project where I input case report descriptors into an LLM (Mistral, GPT 4, etc.) I need some prompting strategies to give me better answers. Eventually, after the description, I ask what the diagnosis is and compare it to what is in the paper. I have an AI engineer working with me that will be able t... | 2024-01-11T03:16:13 | https://www.reddit.com/r/LocalLLaMA/comments/193rjln/prompting_strategies_to_use_with_llms_and_medical/ | InDebt2Medicine | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 193rjln | false | null | t3_193rjln | /r/LocalLLaMA/comments/193rjln/prompting_strategies_to_use_with_llms_and_medical/ | false | false | self | 1 | {'enabled': False, 'images': [{'id': '-UIKbvJLmDI5ngIkrN_zDqqQgf3a5RDS3IEOiocJWmg', 'resolutions': [{'height': 54, 'url': 'https://external-preview.redd.it/yFZRdbH0P041Nemxi4wCb983K5p3HSYJadSQ138g8_U.jpg?width=108&crop=smart&auto=webp&s=ce510ffff10f4a83fc33b66040a2d47a364b91a8', 'width': 108}, {'height': 108, 'url': 'h... |
Read any GIT folder and answer questions | 1 | Looking for developing an application to read a GIT folder and answer user questions on functionality and technical components. Also draw editable diagrams. Any suggestions on the approach. | 2024-01-11T02:16:36 | https://www.reddit.com/r/LocalLLaMA/comments/193qbeh/read_any_git_folder_and_answer_questions/ | Key-Air-1324 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 193qbeh | false | null | t3_193qbeh | /r/LocalLLaMA/comments/193qbeh/read_any_git_folder_and_answer_questions/ | false | false | self | 1 | null |
Looking for a music specialized LLAMA 2 finetune. | 1 | [removed] | 2024-01-11T01:50:45 | https://www.reddit.com/r/LocalLLaMA/comments/193prwx/looking_for_a_music_specialized_llama_2_finetune/ | chocolatebanana136 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 193prwx | false | null | t3_193prwx | /r/LocalLLaMA/comments/193prwx/looking_for_a_music_specialized_llama_2_finetune/ | false | false | self | 1 | null |
Local LLama vs other GPT local alternatives (like gpt4all) | 1 | I'm looking for some guidance here hopefully we can have a good discussion. All of this sea of information on Local AI's or just AI in general is greek to me but I'm trying to learn as I go. I'm trying to setup a local AI that interacts with sensitive information from PDF's for my local business in the education space.... | 2024-01-11T01:38:35 | https://www.reddit.com/r/LocalLLaMA/comments/193piuw/local_llama_vs_other_gpt_local_alternatives_like/ | acotwo | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 193piuw | false | null | t3_193piuw | /r/LocalLLaMA/comments/193piuw/local_llama_vs_other_gpt_local_alternatives_like/ | false | false | self | 1 | null |
best option for multi gpu inference ? | 2 | i dont have experience in muti-gpu inference, i actually have a 4090rtx with vllm and got a very fast t/s inference with awq 7b models, but i want to test larger models so in your experience whats is the best local inference setup for larger models ex: 70b and multi gpu
i can get some sli ready 3090 for around 550-50... | 2024-01-11T01:34:20 | https://www.reddit.com/r/LocalLLaMA/comments/193pfq5/best_option_for_multi_gpu_inference/ | prudant | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 193pfq5 | false | null | t3_193pfq5 | /r/LocalLLaMA/comments/193pfq5/best_option_for_multi_gpu_inference/ | false | false | self | 2 | null |
Recommendations for build targeting speed/efficiency | 3 | Hi, pretty new to the LLM world, but I'm trying to build something for my personal use.
I was searching around for a way to enable my own home automation software (home assistant) to make use of llms in order to control the devices. Right now I'm using OpenAI api, but this depends on cloud and I really don't like the ... | 2024-01-11T01:26:38 | https://www.reddit.com/r/LocalLLaMA/comments/193p9ru/recommendations_for_build_targeting/ | CappyT | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 193p9ru | false | null | t3_193p9ru | /r/LocalLLaMA/comments/193p9ru/recommendations_for_build_targeting/ | false | false | self | 3 | null |
Help to use pipeline conversational on mistral instruct v0.2 | 1 | I am trying to use the same code that works on zephyr and llama2:
from transformers import pipeline, AutoTokenizer, AutoModelForCausalLM, BitsAndBytesConfig
import torch
compute_dtype = getattr(torch, "float16")
quantization_config = BitsAndBytesConfig(
load_in_4bit=True,
bnb_4bit_... | 2024-01-11T01:26:03 | https://www.reddit.com/r/LocalLLaMA/comments/193p9c3/help_to_use_pipeline_conversational_on_mistral/ | celsowm | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 193p9c3 | false | null | t3_193p9c3 | /r/LocalLLaMA/comments/193p9c3/help_to_use_pipeline_conversational_on_mistral/ | false | false | self | 1 | null |
Help - Struggling to get valid JSON responses from Mixtral 8x7b | 4 | I've been primarily using GPT 3.5 and prompting it to respond JSON:
"
Instructions:
...
Output format:
Output the answer in the following JSON format:
{ question: string, options: string\[\]}
"
I expect it to return a singular JSON in string format, in which I parse. To provide for any potential additions... | 2024-01-11T01:23:05 | https://www.reddit.com/r/LocalLLaMA/comments/193p701/help_struggling_to_get_valid_json_responses_from/ | benjalim | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 193p701 | false | null | t3_193p701 | /r/LocalLLaMA/comments/193p701/help_struggling_to_get_valid_json_responses_from/ | false | false | self | 4 | null |
Stay up-to-date within the LLM space | 1 | Hi! With everything around LLMs moving at such a fast pace, papers, related frameworks, libraries, toolkits, open source models and more popping up every day, I found it much harder to stay on top of everything than before. How do you stay updated and effectively navigate this space. Any recommendations for blogs, comm... | 2024-01-11T01:18:56 | https://www.reddit.com/r/LocalLLaMA/comments/193p3r5/stay_uptodate_within_the_llm_space/ | Odd-Farmer-3121 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 193p3r5 | false | null | t3_193p3r5 | /r/LocalLLaMA/comments/193p3r5/stay_uptodate_within_the_llm_space/ | false | false | self | 1 | null |
4090s in stock at Best Buy for pick up. Rather they go to my LocalLLaMA family than scalpers. Good luck. | 42 | 2024-01-11T00:16:47 | https://www.bestbuy.com/site/pny-nvidia-geforce-rtx-4090-24gb-gddr6x-pci-express-4-0-graphics-card-with-triple-fan-and-dlss-3-black/6522679.p?skuId=6522679 | SeymourBits | bestbuy.com | 1970-01-01T00:00:00 | 0 | {} | 193nr4e | false | null | t3_193nr4e | /r/LocalLLaMA/comments/193nr4e/4090s_in_stock_at_best_buy_for_pick_up_rather/ | false | false | 42 | {'enabled': False, 'images': [{'id': 'T-15OBvm6H1Df7kNrhwbOoVjPzTcOLNnLL_vxJpMGEA', 'resolutions': [{'height': 108, 'url': 'https://external-preview.redd.it/i5AFOzzJUQHKv6dPePBvsk77zSWwoDcsukdQR9-sgNM.jpg?width=108&crop=smart&auto=webp&s=dd860919e0e6c91d87d79851dcdab3a9d2a8ce51', 'width': 108}, {'height': 216, 'url': '... | ||
Let's get GPTs to promote local LLMs | 1 | [removed] | 2024-01-10T23:24:07 | https://www.reddit.com/r/LocalLLaMA/comments/193mjfp/lets_get_gpts_to_promote_local_llms/ | ALocalLLaMA | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 193mjfp | false | null | t3_193mjfp | /r/LocalLLaMA/comments/193mjfp/lets_get_gpts_to_promote_local_llms/ | false | false | self | 1 | {'enabled': False, 'images': [{'id': '5ZmL7d2VZstdFqjn3Ip6GXNjx6NLEdZri5mcfZcSAKI', 'resolutions': [{'height': 108, 'url': 'https://external-preview.redd.it/GDs_bj0u5K43BtH1Ci5Qv3jIVB_IHBIVwl91-0Xqcgs.jpg?width=108&crop=smart&auto=webp&s=7db44306d92aefb317471040cfca8a7f7eef14aa', 'width': 108}, {'height': 216, 'url': '... |
Quite new to this, looking for suggestions for my powerful PC. | 1 | I have a quite powerful PC and am looking for suggestions and or I inspiration of what kinds of things would be interesting/enjoyable to run on my PC.
I have a 4090, a 13900k, 96 GB of DDR5 RAM, and 6 TB of m.2 drive space which I can expand further with another 2 available slots.
I am super eager and interested in... | 2024-01-10T23:19:35 | https://www.reddit.com/r/LocalLLaMA/comments/193mfor/quite_new_to_this_looking_for_suggestions_for_my/ | caidicus | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 193mfor | false | null | t3_193mfor | /r/LocalLLaMA/comments/193mfor/quite_new_to_this_looking_for_suggestions_for_my/ | false | false | self | 1 | null |
Titan RTX 2024 | 1 | https://www.tiktok.com/t/ZT8qd6yt8/
This is Dolphin Mixtral 2.5 8x 7B 4 bit running on my machine. Note the settings at the end. I’m an amateur here but when I tried to run this on my 4070, it crashed most of the time. I can work with this.
I asked multiple models to compare the RTX 3090 and they all said basically t... | 2024-01-10T23:17:44 | https://www.reddit.com/r/LocalLLaMA/comments/193me6f/titan_rtx_2024/ | stonedoubt | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 193me6f | false | null | t3_193me6f | /r/LocalLLaMA/comments/193me6f/titan_rtx_2024/ | false | false | self | 1 | {'enabled': False, 'images': [{'id': 'IFg7829quY-18QR4nbP48ZW2jUfEjDYctl_ojWuxzLE', 'resolutions': [{'height': 192, 'url': 'https://external-preview.redd.it/unqq89Z_TCMJyb_whAYn6YZ_mWpRTHvFHBnqiq764uE.jpg?width=108&crop=smart&auto=webp&s=75771d169ae48748903c527e713c2dc6cecb62c5', 'width': 108}, {'height': 384, 'url': '... |
Jan: an open-source alternative to LM Studio providing both a frontend and a backend for running local large language models | 263 | 2024-01-10T23:03:34 | https://jan.ai/ | CosmosisQ | jan.ai | 1970-01-01T00:00:00 | 0 | {} | 193m27u | false | null | t3_193m27u | /r/LocalLLaMA/comments/193m27u/jan_an_opensource_alternative_to_lm_studio/ | false | false | 263 | {'enabled': False, 'images': [{'id': '_clR5lo0uUzBmmOefgsOcrqCYpHgjkxrStKzWLzjtqg', 'resolutions': [{'height': 60, 'url': 'https://external-preview.redd.it/71HRL7bDHzSg5fARXgUVzQrb-ddlAEFhDMiNjCqLPcE.jpg?width=108&crop=smart&auto=webp&s=a34a9c017a9872303c87fdbe0bca0b95846bd110', 'width': 108}, {'height': 121, 'url': 'h... | ||
Qwen2 is coming! | 73 | 2024-01-10T22:47:02 | https://github.com/huggingface/transformers/pull/28436 | bratao | github.com | 1970-01-01T00:00:00 | 0 | {} | 193lnq5 | false | null | t3_193lnq5 | /r/LocalLLaMA/comments/193lnq5/qwen2_is_coming/ | false | false | 73 | {'enabled': False, 'images': [{'id': 'x4hmJK7t4R9WIQYYT2n8OiRxk2Rxf0K5K8PKm1lA510', 'resolutions': [{'height': 54, 'url': 'https://external-preview.redd.it/KZc4htiU1OQ2s5k_rP90XTDoIAUZgI2W5uqpXX9S71E.jpg?width=108&crop=smart&auto=webp&s=8059d320216e7dfcc51ecce1fa198ea99e760f2d', 'width': 108}, {'height': 108, 'url': 'h... | ||
New super model bagel-dpo-8x7b-v0.2 available | 1 | This new model it's been a promise, so if you want to try it on the net before you run it local try [Infermatic.ai](https://Infermatic.ai) .
If you dont know what it is --> An experimental fine-tune of [**mixtral-8x7b-v0.1**](https://huggingface.co/mistralai/Mixtral-8x7B-v0.1) using [**bagel**](https://github.com/jond... | 2024-01-10T22:23:59 | https://www.reddit.com/r/LocalLLaMA/comments/193l39e/new_super_model_bageldpo8x7bv02_available/ | Horror_Echo6243 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 193l39e | false | null | t3_193l39e | /r/LocalLLaMA/comments/193l39e/new_super_model_bageldpo8x7bv02_available/ | false | false | self | 1 | {'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': '... |
Fastest for hosting API | 1 | [removed] | 2024-01-10T22:21:54 | https://www.reddit.com/r/LocalLLaMA/comments/193l1h0/fastest_for_hosting_api/ | aallsbury | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 193l1h0 | false | null | t3_193l1h0 | /r/LocalLLaMA/comments/193l1h0/fastest_for_hosting_api/ | false | false | self | 1 | null |
Chat with Pixtral on Huggingface | 10 | 2024-01-10T22:12:39 | https://huggingface.co/spaces/mlabonne/phixtral-chat | ninjasaid13 | huggingface.co | 1970-01-01T00:00:00 | 0 | {} | 193ktim | false | null | t3_193ktim | /r/LocalLLaMA/comments/193ktim/chat_with_pixtral_on_huggingface/ | false | false | 10 | {'enabled': False, 'images': [{'id': 'J7YmoBKIcNHXxOrsGMFobFjePT65GI96Lx71BgeT3_I', 'resolutions': [{'height': 58, 'url': 'https://external-preview.redd.it/LQgvMxXwnEVsmzg5hFPdyuBmAysXGuWJ49dlqkWjmqw.jpg?width=108&crop=smart&auto=webp&s=5d8161904c2057d32d03397bcb0098e2cbc97a35', 'width': 108}, {'height': 116, 'url': 'h... | ||
Does anyone have non-quantized codellama models in GGUF format for llama.cpp? | 1 | I am trying to run non quantized models on an A100 via llama.cpp, and the bloke only has up to 8 bit quantized codellama 34b...but no 16 or 32bit | 2024-01-10T22:05:36 | https://www.reddit.com/r/LocalLLaMA/comments/193kn7s/does_anyone_have_nonquantized_codellama_models_in/ | natural_language_guy | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 193kn7s | false | null | t3_193kn7s | /r/LocalLLaMA/comments/193kn7s/does_anyone_have_nonquantized_codellama_models_in/ | false | false | self | 1 | null |
Is there any backend like vllm but for low end systems aka using llama.cpp and the like for cpu gou inference mix ? | 1 | I am looking into a task that needs high throughput above everything else.
And if somethinh like this exsits i can afford to try out alot more different sized models then with vllm. As far aa my understanding goes.
Do you guys know anything ? | 2024-01-10T21:21:23 | https://www.reddit.com/r/LocalLLaMA/comments/193jjow/is_there_any_backend_like_vllm_but_for_low_end/ | Noxusequal | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 193jjow | false | null | t3_193jjow | /r/LocalLLaMA/comments/193jjow/is_there_any_backend_like_vllm_but_for_low_end/ | false | false | self | 1 | null |
Upcoming APU Discussions (AMD, Intel, Qualcomm) | 19 | Hey guys. As you may know, there is a new lineup of APUs coming from AMD, Intel and Qualcomm.
What makes these interesting is that they all have some form of Neural Processing Unit that makes them really efficient for AI inferencing. The specification that these vendors are using to differentiate their AI capability ... | 2024-01-10T20:42:10 | https://www.reddit.com/r/LocalLLaMA/comments/193ikun/upcoming_apu_discussions_amd_intel_qualcomm/ | zippyfan | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 193ikun | false | null | t3_193ikun | /r/LocalLLaMA/comments/193ikun/upcoming_apu_discussions_amd_intel_qualcomm/ | false | false | self | 19 | {'enabled': False, 'images': [{'id': 'fFgRIBH6bKUwFFw1IRkgiKbGFEu23T6GbBMg_BYwbUc', 'resolutions': [{'height': 60, 'url': 'https://external-preview.redd.it/Z1Pq8kzFrOGW9oLn_TLgx6H-X6H--Ru-BYR08TXLMfw.jpg?width=108&crop=smart&auto=webp&s=7acb49c5c2a497e9d99fd0b23ee54e28b91fe960', 'width': 108}, {'height': 121, 'url': 'h... |
Huggingface AutoTrain params for long context models | 1 | In Huggingface AutoTrain ([https://huggingface.co/autotrain](https://huggingface.co/autotrain)) you can set some parameters for finetuning. My first question, however, would be about data format. As far as I understand, the "generic LLM" and "SFT" options only use the *text* field in the input CSV file ([https://huggin... | 2024-01-10T20:22:18 | https://www.reddit.com/r/LocalLLaMA/comments/193i308/huggingface_autotrain_params_for_long_context/ | Foxtr0t | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 193i308 | false | null | t3_193i308 | /r/LocalLLaMA/comments/193i308/huggingface_autotrain_params_for_long_context/ | false | false | self | 1 | {'enabled': False, 'images': [{'id': '8fmoOM73_P4nASRHhvACYVZ1TP8Mftfqe1pW4h9xU7Q', 'resolutions': [{'height': 58, 'url': 'https://external-preview.redd.it/ALGC6XWA8Kvu-HNmMhUkttfwUknHJRL7mfobrnubZT0.jpg?width=108&crop=smart&auto=webp&s=41a33a7fec6d54b6e024b2a0cf19faa6d116dc53', 'width': 108}, {'height': 116, 'url': 'h... |
QLoRa fine-tuning Mistral-7B-Instruct-v0.2 with 8GB RAM MacBook using MLX and MLXT | 22 | Hey all, inspired by previous posts on MLX fine-tuning [this](https://www.reddit.com/r/LocalLLaMA/comments/18ujt0n/using_gpus_on_a_mac_m2_max_via_mlx_update_on/), [this](https://www.reddit.com/r/LocalLLaMA/comments/18wabkc/lessons_learned_so_far_lora_fine_tuning_on/) and [this](https://www.reddit.com/r/LocalLLaMA/comme... | 2024-01-10T20:06:53 | https://www.reddit.com/r/LocalLLaMA/comments/193hp0s/qlora_finetuning_mistral7binstructv02_with_8gb/ | chenhunghan | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 193hp0s | false | null | t3_193hp0s | /r/LocalLLaMA/comments/193hp0s/qlora_finetuning_mistral7binstructv02_with_8gb/ | false | false | self | 22 | {'enabled': False, 'images': [{'id': 'OxIEja9CdlLIWGYqo8KFmtPb6euM2VXpSPyRhRvFKz0', 'resolutions': [{'height': 54, 'url': 'https://external-preview.redd.it/v1LpnxZdkHiPaeADz2fYMXoXP_Aj-AmUZr3ylVzKbn8.jpg?width=108&crop=smart&auto=webp&s=5775b56abd2ca15fef8a5df3ef2ea9308eacc603', 'width': 108}, {'height': 108, 'url': 'h... |
"Alien Text Object" prompting, any potential for super-intelligence? Like Japanese, LLMs may be able to pick up hidden meaning based on contextual use of weird symbols, and may intuitively understand some "hyperdense alien languages" optimized for reasoning | 1 | 2024-01-10T19:29:29 | https://www.reddit.com/gallery/193grlq | ryunuck | reddit.com | 1970-01-01T00:00:00 | 0 | {} | 193grlq | false | null | t3_193grlq | /r/LocalLLaMA/comments/193grlq/alien_text_object_prompting_any_potential_for/ | false | false | 1 | null | ||
How to download and use safetensors models? | 1 | [removed] | 2024-01-10T19:14:35 | https://www.reddit.com/r/LocalLLaMA/comments/193ged7/how_to_download_and_use_safetensors_models/ | yungfishstick | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 193ged7 | false | null | t3_193ged7 | /r/LocalLLaMA/comments/193ged7/how_to_download_and_use_safetensors_models/ | false | false | self | 1 | null |
RAG Dataset - 3.7M LA Times headlines and links (1914-2024) | 38 | Hey r/LocalLLaMA, I wrote a webscraper to assemble this data and I figured I'd save y'all the trouble of doing it yourself. The dataset's columns are \['title', 'link', 'month', 'year'\]. All headlines were collected from their sitemap yesterday, so it should be quite up to date. I'm also working on getting a full data... | 2024-01-10T18:52:49 | https://www.reddit.com/r/LocalLLaMA/comments/193fus0/rag_dataset_37m_la_times_headlines_and_links/ | metaprotium | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 193fus0 | false | null | t3_193fus0 | /r/LocalLLaMA/comments/193fus0/rag_dataset_37m_la_times_headlines_and_links/ | false | false | self | 38 | {'enabled': False, 'images': [{'id': 'NuAQ90kiUUX4kthd84B4t0ZEil1JR2PaZQ4MKiAf4Zw', 'resolutions': [{'height': 58, 'url': 'https://external-preview.redd.it/V6er3A0u_IkxkGNZIXQKZNswSexL5mPfdDL9qjUKSrI.jpg?width=108&crop=smart&auto=webp&s=4248bb7e6011b998c3822d584130ad508ae5c38b', 'width': 108}, {'height': 116, 'url': 'h... |
Python package for Ollama? | 1 | Is there a python package for ollama? I tried pip installing ollama, and it doesn't exist? I couldn't find anything on github, either. Section 4 on [this webpage](https://cheatsheet.md/llm-leaderboard/ollama) makes it sound like it can be done... Thank for any help! I have ollama running on my windows machine, and I'd ... | 2024-01-10T18:50:18 | https://www.reddit.com/r/LocalLLaMA/comments/193fsh6/python_package_for_ollama/ | dottie-dog | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 193fsh6 | false | null | t3_193fsh6 | /r/LocalLLaMA/comments/193fsh6/python_package_for_ollama/ | false | false | self | 1 | {'enabled': False, 'images': [{'id': 'qRb47zpOiYba0pKDqa0cposRogPk0DJmEboC9GecLNE', 'resolutions': [{'height': 61, 'url': 'https://external-preview.redd.it/to0AW-8pVdMBD4x2Mt7o4TSD_Fspsab719o3dAsh764.jpg?width=108&crop=smart&auto=webp&s=2a56f94d9cdbcbc6be1f06352311c36df2ed2dd2', 'width': 108}, {'height': 123, 'url': 'h... |
When you work with us, you can rest easy knowing you’re getting the quality you deserve; we only employ the most skilled technicians in the industry, and we hold them to higher standards of precision. | 1 | 2024-01-10T18:46:05 | unitedaxleofnm | i.redd.it | 1970-01-01T00:00:00 | 0 | {} | 193fooh | false | null | t3_193fooh | /r/LocalLLaMA/comments/193fooh/when_you_work_with_us_you_can_rest_easy_knowing/ | false | false | 1 | {'enabled': True, 'images': [{'id': 'qALC5EX8DuVP6TL1dubswwm8AYLKQlaNXPG_G2klUTg', 'resolutions': [{'height': 108, 'url': 'https://preview.redd.it/invdt3dqrnbc1.jpeg?width=108&crop=smart&auto=webp&s=51982163d6885ef8c9cf4f2f0edb22d152c61145', 'width': 108}, {'height': 216, 'url': 'https://preview.redd.it/invdt3dqrnbc1.j... | |||
Mistral Medium 4th on the updated LMSYS Leaderboard | 235 | 2024-01-10T18:42:50 | atgctg | i.redd.it | 1970-01-01T00:00:00 | 0 | {} | 193flvk | false | null | t3_193flvk | /r/LocalLLaMA/comments/193flvk/mistral_medium_4th_on_the_updated_lmsys/ | false | false | 235 | {'enabled': True, 'images': [{'id': 'ghjfBbVmWliZx5Lqu_Ep7JdShZYXvAYqo-n9SQ3e6WQ', 'resolutions': [{'height': 71, 'url': 'https://preview.redd.it/xzn442rvqnbc1.png?width=108&crop=smart&auto=webp&s=71ab466fd30d6f266980955ca3fe615f03c9dbea', 'width': 108}, {'height': 142, 'url': 'https://preview.redd.it/xzn442rvqnbc1.png... | |||
So far, mistral medium is the only model aside from GPT-4 that can correctly answer my riddle of the Sphinx trick question | 68 | 2024-01-10T18:36:29 | boring_pencil | i.redd.it | 1970-01-01T00:00:00 | 0 | {} | 193fgb6 | false | null | t3_193fgb6 | /r/LocalLLaMA/comments/193fgb6/so_far_mistral_medium_is_the_only_model_aside/ | false | false | 68 | {'enabled': True, 'images': [{'id': 'F48vd--hCcbXXlK00RlbFEpk-XaNY96DuOpPccMlNt8', 'resolutions': [{'height': 60, 'url': 'https://preview.redd.it/mkdlm8mwpnbc1.png?width=108&crop=smart&auto=webp&s=0d2793f05ba73bdf9d7d03c70b5b2eb2a47aa611', 'width': 108}, {'height': 120, 'url': 'https://preview.redd.it/mkdlm8mwpnbc1.png... | |||
What are the advantages of formats other than GGUF? | 67 | I was using RTX 2070 with 8GB VRAM and 16GB RAM for few weeks, today I upgraded to RTX 3090 with 24GB and 128GB RAM, finally I can use Mixtral and stuff.
I still use koboldcpp with GGUF. I put as many layers as possible in 24GB VRAM then I can put everything else in RAM.
What can I achieve with other formats? Are the... | 2024-01-10T18:33:21 | https://www.reddit.com/r/LocalLLaMA/comments/193fdfq/what_are_the_advantages_of_formats_other_than_gguf/ | jacek2023 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 193fdfq | false | null | t3_193fdfq | /r/LocalLLaMA/comments/193fdfq/what_are_the_advantages_of_formats_other_than_gguf/ | false | false | self | 67 | null |
How to merge safetensors models? | 1 | [removed] | 2024-01-10T18:07:07 | https://www.reddit.com/r/LocalLLaMA/comments/193epuj/how_to_merge_safetensors_models/ | yungfishstick | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 193epuj | false | null | t3_193epuj | /r/LocalLLaMA/comments/193epuj/how_to_merge_safetensors_models/ | false | false | self | 1 | null |
Avoid additional heavy-duty truck axle repair services by covering routine axle maintenance steps. After carefully inspecting, repairing, and testing your truck axle, we provide you with a recommended maintenance schedule for essential tasks. | 1 | 2024-01-10T17:56:07 | unitedaxleofnm | i.redd.it | 1970-01-01T00:00:00 | 0 | {} | 193efp9 | false | null | t3_193efp9 | /r/LocalLLaMA/comments/193efp9/avoid_additional_heavyduty_truck_axle_repair/ | false | false | 1 | {'enabled': True, 'images': [{'id': 'GuX_6IXdwomHrbu6_RkHNZ81xxmhPVm-CCfuOkZIhFk', 'resolutions': [{'height': 108, 'url': 'https://preview.redd.it/oywlvzbsinbc1.jpeg?width=108&crop=smart&auto=webp&s=f1fce21651e915185e581a6351316bfd51cb2e23', 'width': 108}, {'height': 216, 'url': 'https://preview.redd.it/oywlvzbsinbc1.j... | |||
How to chat with codebase | 8 | Hi, I'd like to somehow ask questions to my local medium sized python codebase (1000s of files). I've got 128GB of RAM so I can have a fairly large context, but some type of training isn't out of the question. Any projects I should investigate? Would preferrably like to stick with llama.cpp and mixstral if possible. | 2024-01-10T17:38:39 | https://www.reddit.com/r/LocalLLaMA/comments/193e00p/how_to_chat_with_codebase/ | 1ncehost | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 193e00p | false | null | t3_193e00p | /r/LocalLLaMA/comments/193e00p/how_to_chat_with_codebase/ | false | false | self | 8 | null |
🔥 I USED ARTIFICIAL INTELLIGENCE TO CREATE A STREAMER (VTUBE) THAT INTERACTS WITH YOU 🔥 | 1 | [removed] | 2024-01-10T17:17:26 | https://www.reddit.com/r/LocalLLaMA/comments/193dh7b/i_used_artificial_intelligence_to_create_a/ | cybermazinh0 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 193dh7b | false | null | t3_193dh7b | /r/LocalLLaMA/comments/193dh7b/i_used_artificial_intelligence_to_create_a/ | false | false | self | 1 | {'enabled': False, 'images': [{'id': 'ewwn6lUdf7KXGGAnpwqWm_Dibpolb3ZeA86LAnwbtTA', 'resolutions': [{'height': 81, 'url': 'https://external-preview.redd.it/FlKzpxC47dyBv4buiPgG4lFlrO8n5JJ3jzVqIsKoboE.jpg?width=108&crop=smart&auto=webp&s=e0e59add3926d174d17364c03a0a16a4dc9e212f', 'width': 108}, {'height': 162, 'url': 'h... |
how to reducing RAG chatbot response time? | 1 | does anybody have any idea as to how to reduce the prompt evaluation time and evaluation time in RAG chatbot (langchain).?
https://preview.redd.it/wyiayxfi9nbc1.png?width=1695&format=png&auto=webp&s=a2977cb09b41e1ac6d17183f7bb66d3d1340ce32 | 2024-01-10T17:05:28 | https://www.reddit.com/r/LocalLLaMA/comments/193d6mq/how_to_reducing_rag_chatbot_response_time/ | HV4U2001 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 193d6mq | false | null | t3_193d6mq | /r/LocalLLaMA/comments/193d6mq/how_to_reducing_rag_chatbot_response_time/ | false | false | 1 | null | |
Looking for recommendations on a new machine | 2 | Hey All,
Im planning on building out a new machine I can run an LLM on. I have a pretty decent budget, looking to cap at around $5k to $6k.
​
For the best performance, would you guys recommend running a server with multiple GPUs ? Gaming system with a couple of 4090s ? Or Possibly an apple platform M2 or M3 ... | 2024-01-10T17:03:12 | https://www.reddit.com/r/LocalLLaMA/comments/193d4mb/looking_for_recommendations_on_a_new_machine/ | Noack1 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 193d4mb | false | null | t3_193d4mb | /r/LocalLLaMA/comments/193d4mb/looking_for_recommendations_on_a_new_machine/ | false | false | self | 2 | null |
simplest way to integrate RAG into ooba for an assistant? | 2 | hoping to build a persistent assistant and want to fuss with it as little as possible after it's set up, would using an extension like this within ooba be the move to enable RAG? https://github.com/jason-brian-anderson/long_term_memory_with_qdrant
setting up docker seems like it would be a little annoying but fine | 2024-01-10T16:50:38 | https://www.reddit.com/r/LocalLLaMA/comments/193ctfr/simplest_way_to_integrate_rag_into_ooba_for_an/ | Dankmemexplorer | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 193ctfr | false | null | t3_193ctfr | /r/LocalLLaMA/comments/193ctfr/simplest_way_to_integrate_rag_into_ooba_for_an/ | false | false | self | 2 | {'enabled': False, 'images': [{'id': '-hLiGokqftfCFZgATMKR6egjzzJfZHTgZhU1NlFJKgc', 'resolutions': [{'height': 54, 'url': 'https://external-preview.redd.it/1vMj7kZjEzPBbfake4enQ0rtNRAFXhomrFi4bEJQ2aM.jpg?width=108&crop=smart&auto=webp&s=efa305219da3899a32aa2fcbdd442a6ea3982340', 'width': 108}, {'height': 108, 'url': 'h... |
single vs dual 3090 | 1 | Hi All,
I am considering upgrading my PC which currently has a rtx 2070. I am confused between getting a single vs dual 3090. My use cases are not properly defined yet in terms of size of model etc. The biggest model I have trained was about 120M params, but not sure if I will be doing that again. My aim is mostly to ... | 2024-01-10T16:16:19 | https://www.reddit.com/r/LocalLLaMA/comments/193bzmh/single_vs_dual_3090/ | not_a_user42 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 193bzmh | false | null | t3_193bzmh | /r/LocalLLaMA/comments/193bzmh/single_vs_dual_3090/ | false | false | self | 1 | null |
LongLM is now open source! This is an implementation of the paper: "LLM Maybe LongLM: Self-Extend LLM Context Window Without Tuning" | 130 | 2024-01-10T16:15:37 | https://github.com/datamllab/LongLM | CosmosisQ | github.com | 1970-01-01T00:00:00 | 0 | {} | 193bz3g | false | null | t3_193bz3g | /r/LocalLLaMA/comments/193bz3g/longlm_is_now_open_source_this_is_an/ | false | false | 130 | {'enabled': False, 'images': [{'id': 'Mb0bbqxunuDW3MgoEYAZ201azLFkM2JWOCOd4XbjSnA', 'resolutions': [{'height': 54, 'url': 'https://external-preview.redd.it/tKVkOdMb4LKX0L3CjuVbVak3SOgbQQmko1eIiOskS4s.jpg?width=108&crop=smart&auto=webp&s=d1f2fa51bc00708530f4f60748db857de54421d9', 'width': 108}, {'height': 108, 'url': 'h... | ||
Experimenting with new sampling in MLX | 19 | Hi folks. MLX is absolutely cool as it allows to quickly hack stuff. I'm playing with this sampling algorithm that is specifically designed for coherence and simple to tune parameters:
[https://x.com/antirez/status/1745051794743472502?s=20](https://x.com/antirez/status/1745051794743472502?s=20)
At the same time, I... | 2024-01-10T16:12:05 | https://www.reddit.com/r/LocalLLaMA/comments/193bw95/experimenting_with_new_sampling_in_mlx/ | antirez | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 193bw95 | false | null | t3_193bw95 | /r/LocalLLaMA/comments/193bw95/experimenting_with_new_sampling_in_mlx/ | false | false | self | 19 | {'enabled': False, 'images': [{'id': 'XOf47-Yd0aVe0cqjB0ptS1-eXnZ3pv4SQRX5PP4VO-I', 'resolutions': [{'height': 108, 'url': 'https://external-preview.redd.it/Fjpi7IcgdFRJRuGB8FUmDYuiRO2Ae957jovHQrDYmlA.jpg?width=108&crop=smart&auto=webp&s=ba46993a1d215f8522d91609135cab453821f051', 'width': 108}], 'source': {'height': 20... |
Mistral 7B instruct v0.2 is the probably the best instruct model I have ever tested till date! Not only it follows the instruction very well, its context based answering, logic and reasoning, it doesn't feel like I am running a 7B model!!! | 2 | 2024-01-10T16:01:16 | akbbiswas | i.redd.it | 1970-01-01T00:00:00 | 0 | {} | 193bmw7 | false | null | t3_193bmw7 | /r/LocalLLaMA/comments/193bmw7/mistral_7b_instruct_v02_is_the_probably_the_best/ | false | false | 2 | {'enabled': True, 'images': [{'id': '5pSraIlU29O7y6NRA5eNT8nyLTOTd0xGbcQ37ennQz8', 'resolutions': [{'height': 39, 'url': 'https://preview.redd.it/efqu3x2oxmbc1.png?width=108&crop=smart&auto=webp&s=728c313c86509cd150d501d532e1e35398ebaa87', 'width': 108}, {'height': 79, 'url': 'https://preview.redd.it/efqu3x2oxmbc1.png?... | |||
Newbie question: Model has expected data to answer my query, but doesn't answer. How to get it fixed? | 1 | I am totally newbie to LLama world (hardly a few days spent). I tried following in llama.cpp.
$ ./main -m ../llama-models/TheBloke/dolphin-2.5-mixtral-8x7b-GGUF/dolphin-2.5-mixtral-8x7b.Q4_K_M.gguf -n -1 --repeat_penalty 1.0 --color -i -r "User:" -f prompts/chat-with-bob.txt
Question 1:
User:What are the classic lan... | 2024-01-10T15:53:53 | https://www.reddit.com/r/LocalLLaMA/comments/193bgm7/newbie_question_model_has_expected_data_to_answer/ | user0user | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 193bgm7 | false | null | t3_193bgm7 | /r/LocalLLaMA/comments/193bgm7/newbie_question_model_has_expected_data_to_answer/ | false | false | self | 1 | null |
Getting started on M2 Mac 32GB | 1 | [removed] | 2024-01-10T15:53:12 | https://www.reddit.com/r/LocalLLaMA/comments/193bg11/getting_started_on_m2_mac_32gb/ | SnooBeans7516 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 193bg11 | false | null | t3_193bg11 | /r/LocalLLaMA/comments/193bg11/getting_started_on_m2_mac_32gb/ | false | false | self | 1 | null |
How much do you think a 32GB 5090 will cost at launch? | 14 | How much will you be willing to pay for it? I have a feeling that there will be a big price bump given how much 4090 is still selling for. | 2024-01-10T15:29:25 | https://www.reddit.com/r/LocalLLaMA/comments/193avwh/how_much_do_you_think_a_32gb_5090_will_cost_at/ | EasternBeyond | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 193avwh | false | null | t3_193avwh | /r/LocalLLaMA/comments/193avwh/how_much_do_you_think_a_32gb_5090_will_cost_at/ | false | false | self | 14 | null |
For those serving OpenSource models + apps? How do you distribute them? | 2 | I am working on a tool that makes it easier for you to put together distributed systems giving an entry point to a distributed system. Think of it as an "exe" to a distributed system and I am wondering if folks here feel any pain with distributing their OSS apps
We have had some success with people using our tooling f... | 2024-01-10T15:26:02 | https://www.reddit.com/r/LocalLLaMA/comments/193at5x/for_those_serving_opensource_models_apps_how_do/ | hopeirememberthisid | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 193at5x | false | null | t3_193at5x | /r/LocalLLaMA/comments/193at5x/for_those_serving_opensource_models_apps_how_do/ | false | false | self | 2 | null |
Any (legal) models trained on illegal images (example: child porn) | 1 | (Apologies if this is the wrong subreddit. If there is somewhere else that would make more sense for this question please let me know!)
Part of my job is parsing through user generated content and removing anything malicious. This includes viruses, spam, scams, phishing attempts, and of course child pornography.
For... | 2024-01-10T15:04:06 | https://www.reddit.com/r/LocalLLaMA/comments/193ab0m/any_legal_models_trained_on_illegal_images/ | yaazz | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 193ab0m | true | null | t3_193ab0m | /r/LocalLLaMA/comments/193ab0m/any_legal_models_trained_on_illegal_images/ | false | false | self | 1 | null |
Prompting Strategies I can use with Medical Data? | 1 | I am working on a project where I input case reports into an LLM (Mistral, GPT 4, etc.) I need some prompting strategies to give me better answers. Eventually, after the description, I ask what the diagnosis is and compare it to what is in the paper. I have an AI engineer working with me that will be able to implement ... | 2024-01-10T14:18:32 | https://www.reddit.com/r/LocalLLaMA/comments/1939aud/prompting_strategies_i_can_use_with_medical_data/ | InDebt2Medicine | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 1939aud | false | null | t3_1939aud | /r/LocalLLaMA/comments/1939aud/prompting_strategies_i_can_use_with_medical_data/ | false | false | self | 1 | {'enabled': False, 'images': [{'id': '-UIKbvJLmDI5ngIkrN_zDqqQgf3a5RDS3IEOiocJWmg', 'resolutions': [{'height': 54, 'url': 'https://external-preview.redd.it/yFZRdbH0P041Nemxi4wCb983K5p3HSYJadSQ138g8_U.jpg?width=108&crop=smart&auto=webp&s=ce510ffff10f4a83fc33b66040a2d47a364b91a8', 'width': 108}, {'height': 108, 'url': 'h... |
Subsets and Splits
No community queries yet
The top public SQL queries from the community will appear here once available.