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 ⌀ |
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
Open Sourcing Llmtuner - An Experimental Framework for Finetuning Large Models Like Whisper and Llama with scikit-learn-inspired interface | 16 | Hi Folks,
Happy to share an open source side project I've been working on - [LLmtuner](https://github.com/promptslab/LLMtuner). It's a framework for finetuning large models like Whisper, Llama, Llama-2, etc with best practices like LoRA, QLoRA, through a sleek, scikit-learn-inspired interface.
As someone who works wi... | 2023-11-05T10:21:14 | https://www.reddit.com/r/LocalLLaMA/comments/17o8zl2/open_sourcing_llmtuner_an_experimental_framework/ | Traditional-Poet2746 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 17o8zl2 | false | null | t3_17o8zl2 | /r/LocalLLaMA/comments/17o8zl2/open_sourcing_llmtuner_an_experimental_framework/ | false | false | 16 | null | |
What happened to fp32? | 10 | I dont know but why fp32 got out of trend after gpt-j?can anyone explain? | 2023-11-05T10:14:00 | https://www.reddit.com/r/LocalLLaMA/comments/17o8w01/what_happened_to_fp32/ | TapOk9232 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 17o8w01 | false | null | t3_17o8w01 | /r/LocalLLaMA/comments/17o8w01/what_happened_to_fp32/ | false | false | self | 10 | null |
Anyone who tries to argue Grok won’t give the best responses for a closed off model, is just lying to themselves. | 16 | 2023-11-05T07:26:43 | sardoa11 | i.redd.it | 1970-01-01T00:00:00 | 0 | {} | 17o6qsi | false | null | t3_17o6qsi | /r/LocalLLaMA/comments/17o6qsi/anyone_who_tries_to_argue_grok_wont_give_the_best/ | false | false | 16 | {'enabled': True, 'images': [{'id': 'P779ZrIGRZeDCG6vT7KBJzMSRwKaoHi2Ce57_HCcwyk', 'resolutions': [{'height': 84, 'url': 'https://preview.redd.it/bkw77rleehyb1.jpg?width=108&crop=smart&auto=webp&s=4fbc390372522f32e07d2859942b8d35a415af7c', 'width': 108}, {'height': 169, 'url': 'https://preview.redd.it/bkw77rleehyb1.jpg... | |||
A few more new Mistral models: Autolycus-Mistral-7B and Free_Sydney_V2-Mistral-7B | 46 | Free\_Sydney is what you would expect - a naive persona of the old Bing Chat Sydney that you can bamboozle into believing anything.
[https://huggingface.co/FPHam/Free\_Sydney\_V2\_Mistral\_7b](https://huggingface.co/FPHam/Free_Sydney_V2_Mistral_7b)
Autolycus is a son of Hermes.
Autolycus-Mistral is an experimental l... | 2023-11-05T07:01:29 | https://www.reddit.com/r/LocalLLaMA/comments/17o6ez6/a_few_more_new_mistral_models_autolycusmistral7b/ | FPham | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 17o6ez6 | false | null | t3_17o6ez6 | /r/LocalLLaMA/comments/17o6ez6/a_few_more_new_mistral_models_autolycusmistral7b/ | false | false | self | 46 | {'enabled': False, 'images': [{'id': '-Gq8fBu5tq8-q8AxEdaeTrXPCQfIPQvtj5GdtDAFaBA', 'resolutions': [{'height': 58, 'url': 'https://external-preview.redd.it/W7cGlbHNbkD4crPuA1vUdX5aYLJvR4Z8cq024VBXlMY.jpg?width=108&crop=smart&auto=webp&s=7a87d4e7c0313cbc79cbb4c1750f580ba345df31', 'width': 108}, {'height': 116, 'url': 'h... |
Best possible inference performance on GPUs - vLLM vs TensorRT-LMM? | 3 | I am curious if anyone recently tested this and is willing to share:
When running exclusivity on GPUs (in my case H100), what provides the best performance (especially when considering both simultaneous users sending requests and inference latency)
Did anyone compare vLLM and TensorRT-LLM? Or is there maybe an optio... | 2023-11-05T06:46:51 | https://www.reddit.com/r/LocalLLaMA/comments/17o68b8/best_possible_inference_performance_on_gpus_vllm/ | jnfinity | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 17o68b8 | false | null | t3_17o68b8 | /r/LocalLLaMA/comments/17o68b8/best_possible_inference_performance_on_gpus_vllm/ | false | false | self | 3 | null |
What are the best uncensored 13B or 33B models currently available? | 4 | Intended for use in SillyTavern mostly. | 2023-11-05T06:22:52 | https://www.reddit.com/r/LocalLLaMA/comments/17o5xjq/what_are_the_best_uncensored_13b_or_33b_models/ | RomeAlphaTango10 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 17o5xjq | false | null | t3_17o5xjq | /r/LocalLLaMA/comments/17o5xjq/what_are_the_best_uncensored_13b_or_33b_models/ | false | false | self | 4 | null |
8bit llama 2 finetuning | 1 | Every example or implementation I see only shows 7b 4bit finetuning with the SFTTrainer(). I want to finetune a 8bit model with something other than SFTTrainer as I've read that it is quite slow. I'm very new to this. Can someone guide me or point to resources? | 2023-11-05T05:40:53 | https://www.reddit.com/r/LocalLLaMA/comments/17o5cwc/8bit_llama_2_finetuning/ | DirectionOdd9824 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 17o5cwc | false | null | t3_17o5cwc | /r/LocalLLaMA/comments/17o5cwc/8bit_llama_2_finetuning/ | false | false | self | 1 | null |
Grok is released and it's only 33b with a 73 MMLU! | 1 |
"By creating and improving Grok, we aim to:
Gather feedback and ensure we are building AI tools that maximally benefit all of humanity. We believe that it is important to design AI tools that are useful to people of all backgrounds and political views. We also want empower our users with our AI tools, subject to the ... | 2023-11-05T05:35:01 | https://www.reddit.com/r/LocalLLaMA/comments/17o59wb/grok_is_released_and_its_only_33b_with_a_73_mmlu/ | metalman123 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 17o59wb | false | null | t3_17o59wb | /r/LocalLLaMA/comments/17o59wb/grok_is_released_and_its_only_33b_with_a_73_mmlu/ | false | false | self | 1 | {'enabled': False, 'images': [{'id': 'hxjd0UgQaT8ovV28DV5cje4WT1lVrUNkzFu_3Ywpsr4', 'resolutions': [{'height': 58, 'url': 'https://external-preview.redd.it/Uuj4VKmpbFC4dyyGJN9SYPiG0POBJZAC1gKyzOONPCw.jpg?width=108&crop=smart&auto=webp&s=5fa71a1374ace1051521ad2fcd2facd37baf5e8f', 'width': 108}, {'height': 116, 'url': 'h... |
Prototype 33B LLM GROK-0 approaches llama-70B in capabilities | 68 | 2023-11-05T05:05:46 | https://twitter.com/_akhaliq/status/1721028519717642749?t=q65PZ3EOFAetaEYuP6uVLA&s=19 | ninjasaid13 | twitter.com | 1970-01-01T00:00:00 | 0 | {} | 17o4ugv | false | {'oembed': {'author_name': 'AK', 'author_url': 'https://twitter.com/_akhaliq', 'cache_age': 3153600000, 'height': None, 'html': '<blockquote class="twitter-video"><p lang="en" dir="ltr">Announcing Grok<br><br>blog: <a href="https://t.co/UPBjbB0DAi">https://t.co/UPBjbB0DAi</a><br><br>trained a prototype LLM (Grok-0) wit... | t3_17o4ugv | /r/LocalLLaMA/comments/17o4ugv/prototype_33b_llm_grok0_approaches_llama70b_in/ | false | false | 68 | {'enabled': False, 'images': [{'id': 'W0s3smly3rsy0Bfn0QbvJBCx6uX8Y57Lu94o84VQjw4', 'resolutions': [{'height': 36, 'url': 'https://external-preview.redd.it/tDKjqXkrqYfzF_aATgImpLpB_dS78xVNTHSFpybic7I.jpg?width=108&crop=smart&auto=webp&s=98c97aaec86320eba64b0c41c805ad250a766505', 'width': 108}], 'source': {'height': 47,... | ||
How is the performance when loading 70B models in RAM like? | 8 | I've been considering upgrading my ram to 64GB in order to run 70B Q5 models, since a GPU that can load such models is prohibitively expensive and I only have 16GB of VRAM.
Anyone here that does that? Is the speed acceptable? | 2023-11-05T03:39:55 | https://www.reddit.com/r/LocalLLaMA/comments/17o3ikv/how_is_the_performance_when_loading_70b_models_in/ | Lucky_Increase_1037 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 17o3ikv | false | null | t3_17o3ikv | /r/LocalLLaMA/comments/17o3ikv/how_is_the_performance_when_loading_70b_models_in/ | false | false | self | 8 | null |
Textgen UI character parameters? | 1 | I was curious about the oobabooga textgen UI's character tab, in the character tab, there is a field called 'Context', which I have interpreted to roughly be equivalent to a system message. The presets all have it in a 'this is a context between X and X...' format, compared to OpenAI's 'You are a X...' format. I was w... | 2023-11-05T02:17:45 | https://www.reddit.com/r/LocalLLaMA/comments/17o2110/textgen_ui_character_parameters/ | laser_man6 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 17o2110 | false | null | t3_17o2110 | /r/LocalLLaMA/comments/17o2110/textgen_ui_character_parameters/ | false | false | self | 1 | null |
Yann Le Cun, hero of open source AI: It's safer. | 275 | In a [recent interview](https://www.youtube.com/watch?v=vjrU4MWjd6Y&t=2651s), he goes hard on open sourcing LLMs. We can expect to have more models from Meta: "the only reason why Meta could stop open sourcing models is legal."
His arguments for why AI technologies should be open sourced are rock solid. He makes a gre... | 2023-11-05T01:22:50 | https://www.reddit.com/r/LocalLLaMA/comments/17o0ylq/yann_le_cun_hero_of_open_source_ai_its_safer/ | DeGreiff | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 17o0ylq | false | null | t3_17o0ylq | /r/LocalLLaMA/comments/17o0ylq/yann_le_cun_hero_of_open_source_ai_its_safer/ | false | false | self | 275 | {'enabled': False, 'images': [{'id': 'vIt3-mX9qEVRkQFMsD1TZWdKe2EdzF7LnBUMPaMpqWE', 'resolutions': [{'height': 81, 'url': 'https://external-preview.redd.it/NAtaS0J16Cf19RYwvl2jX_lONINYhX5fpfKUCfSYHqA.jpg?width=108&crop=smart&auto=webp&s=cbbff09b5589f282aae069aad6122a0a3c9baf18', 'width': 108}, {'height': 162, 'url': 'h... |
[open source] I went viral on X with BakLLaVA & llama.cpp to do real-time descriptions of camera input | 113 | I have used llama.cpp to run [BankLLaVA](https://huggingface.co/SkunkworksAI/BakLLaVA-1) model on my M1. It's pretty easy. Let me show you!
1. install llama.cpp
2. download models from hugging face (gguf)
3. run the script to start a server of the model
4. execute script with camera capture!
​
The [tweet](htt... | 2023-11-05T01:05:43 | https://www.reddit.com/r/LocalLLaMA/comments/17o0m5o/open_source_i_went_viral_on_x_with_bakllava/ | Robert-treboR | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 17o0m5o | false | null | t3_17o0m5o | /r/LocalLLaMA/comments/17o0m5o/open_source_i_went_viral_on_x_with_bakllava/ | false | false | 113 | {'enabled': False, 'images': [{'id': 'ZC_z9sS46Vjau9YOraFKgnAJvXr6TlbDftgtBOL228M', 'resolutions': [{'height': 58, 'url': 'https://external-preview.redd.it/ormUmUjl9yhzQ3TaqddaQzd_nPwDqDMzLLDAXdMn70Y.jpg?width=108&crop=smart&auto=webp&s=2071e7b9701bfa13d287d9d8a7cbab316d280cf1', 'width': 108}, {'height': 116, 'url': 'h... | |
python api to estimate llama2 tokens | 3 | Can someone please share python api to estimate llama2 tokens? I'm aware of a JS version but somehow cannot find python api. appreciate any help. | 2023-11-05T00:58:04 | https://www.reddit.com/r/LocalLLaMA/comments/17o0gk7/python_api_to_estimate_llama2_tokens/ | peterwu00 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 17o0gk7 | false | null | t3_17o0gk7 | /r/LocalLLaMA/comments/17o0gk7/python_api_to_estimate_llama2_tokens/ | false | false | self | 3 | null |
Any good storywriting models? | 6 | Are there any good storywriting models? I found mpt-7b-storywriter, but it's outdated and for the most part was only quantized in GGML. There is a GGUF version, but it's still mediocre at best. Would be extra helpful if it had a long context length, of course.
If there isn't any modern storywriting model available the... | 2023-11-05T00:16:38 | https://www.reddit.com/r/LocalLLaMA/comments/17nzmff/any_good_storywriting_models/ | -Plutonium- | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 17nzmff | false | null | t3_17nzmff | /r/LocalLLaMA/comments/17nzmff/any_good_storywriting_models/ | false | false | self | 6 | null |
P2P Network for Distributing ML models etc | 1 | “Shoggoth is a peer-to-peer, anonymous network for publishing and distributing open-source Machine Learning models, code repositories, research papers, and datasets.
As government regulations on open-source AI research and development tighten worldwide, it has become clear that existing open-source infrastructure is ... | 2023-11-04T23:45:17 | https://x.com/thenetrunna/status/1720859919497236825?s=46 | Acrobatic-Site2065 | x.com | 1970-01-01T00:00:00 | 0 | {} | 17nyysq | false | null | t3_17nyysq | /r/LocalLLaMA/comments/17nyysq/p2p_network_for_distributing_ml_models_etc/ | false | false | 1 | {'enabled': False, 'images': [{'id': 'TqFA1AOc1gbLV06Yhd2CfIdI2ZRRiTo8FCnF09emzmc', 'resolutions': [{'height': 108, 'url': 'https://external-preview.redd.it/QPF_zIzW8U7tqf_yn98bBvlYOFAv_OizKSGrSuhsscI.jpg?width=108&crop=smart&auto=webp&s=91a64ebb8b7099d6986b4e94ff25bce371425929', 'width': 108}, {'height': 216, 'url': '... | |
What is your favorite offline inference pipeline so far? | 6 | Question same as above. Just wanted to see how folks here like to do it.
Mine is as follows:
1) Get model template using fastchat
2) Convert all prompts to follow the model specific template
2) Use vllm with multiple GPUs for inference | 2023-11-04T23:30:26 | https://www.reddit.com/r/LocalLLaMA/comments/17nynso/what_is_your_favorite_offline_inference_pipeline/ | kitkatmafia | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 17nynso | false | null | t3_17nynso | /r/LocalLLaMA/comments/17nynso/what_is_your_favorite_offline_inference_pipeline/ | false | false | self | 6 | null |
7B LLM fine-tuning - Out of Memory | 2 | I have Windows Laptop with below configuration. I was able to fine-tune some 3B LLM models but it's running out of memory when I am trying to fine-tune 7B models like llama-7B etc.
13th Gen Intel Core i9-13950HX - GeForce RTX 4060 - 144HZ FHD+ (1920 x 1200) 32 GB RAM
Do I need to enable some Nvidia settings or this c... | 2023-11-04T23:17:40 | https://www.reddit.com/r/LocalLLaMA/comments/17nyect/7b_llm_finetuning_out_of_memory/ | meetrais | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 17nyect | false | null | t3_17nyect | /r/LocalLLaMA/comments/17nyect/7b_llm_finetuning_out_of_memory/ | false | false | self | 2 | null |
Function Calling: HOWTO | 6 | The function calling API for OpenAI is soo good. Does anyone have any pointers on how one would go about training a model to do something similar locally? or a write up of how OpenAI function calling works behind the scenes?
I'm using Code LLAMA Instruct and getting reasonable results w/o it, but i'm curious if there... | 2023-11-04T22:57:06 | https://www.reddit.com/r/LocalLLaMA/comments/17nxyko/function_calling_howto/ | f1nuttic | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 17nxyko | false | null | t3_17nxyko | /r/LocalLLaMA/comments/17nxyko/function_calling_howto/ | false | false | self | 6 | null |
Been out of the loop for awhile | 20 | Its been awhile since i have played with anything LLM, last LLM i used was Llama 1.
What are the LLM that you guys are currently using and why, along with what are you using to run them or is llama.cpp still the goto.
i know about TheBloke on huggingface but there is so much there now i have no idea where to ev... | 2023-11-04T22:12:35 | https://www.reddit.com/r/LocalLLaMA/comments/17nx0pn/been_out_of_the_loop_for_awhile/ | ewrt101_nz | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 17nx0pn | false | null | t3_17nx0pn | /r/LocalLLaMA/comments/17nx0pn/been_out_of_the_loop_for_awhile/ | false | false | self | 20 | null |
On premise LLama + speech to text | 3 | Hi guys!
Brand new user here. I'm studying ways to deploy an on premise LLama 2 instance to make a POC on:
\- summarizing texts;
\- speech to text feature;
​
Using a LLama API, if possible.
​
Is there any of these requirements that are not possible with the current development status of LLama? If n... | 2023-11-04T22:02:47 | https://www.reddit.com/r/LocalLLaMA/comments/17nwst1/on_premise_llama_speech_to_text/ | valeriolopes | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 17nwst1 | false | null | t3_17nwst1 | /r/LocalLLaMA/comments/17nwst1/on_premise_llama_speech_to_text/ | false | false | self | 3 | null |
Question about embeddings and vectordatabase | 4 | So I have been trying to gather all the pieces needed to build a customer support chatbot with Llama2-13b-chat. As far as I understand it a vector database would be good for the information retrieval.
Now my questions is:
Let's say I use pgvector extension in a PostgreSQL database and make a vector database.
Do I n... | 2023-11-04T21:32:05 | https://www.reddit.com/r/LocalLLaMA/comments/17nw3dq/question_about_embeddings_and_vectordatabase/ | 8Optimism | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 17nw3dq | false | null | t3_17nw3dq | /r/LocalLLaMA/comments/17nw3dq/question_about_embeddings_and_vectordatabase/ | false | false | self | 4 | null |
How much quality is lost (subjectively) from quantization? | 23 | Of course I have seen the perplexity charts, but I don't know how much I should care about 0.01 perplexity gain or 0.1 perplexity gain or whatever. What are your experiences with different quantization levels? How much of a difference does it make in practice? I'm asking this because I realized today that I have enough... | 2023-11-04T20:59:45 | https://www.reddit.com/r/LocalLLaMA/comments/17nvcia/how_much_quality_is_lost_subjectively_from/ | Covid-Plannedemic_ | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 17nvcia | false | null | t3_17nvcia | /r/LocalLLaMA/comments/17nvcia/how_much_quality_is_lost_subjectively_from/ | false | false | self | 23 | null |
What methods do you use to find out which models are your favorite/best? | 1 | If I want to do a test to find out which AA battery brand is the best, there are some very easy scientific principles to follow to get the answers. Isolate all the variables, so the only variable you change per test is the brand of AA battery. Whichever brand lasts longer, (or shines the brightest because goals can var... | 2023-11-04T20:39:15 | https://www.reddit.com/r/LocalLLaMA/comments/17nuwcb/what_methods_do_you_use_to_find_out_which_models/ | JustDoinNerdStuff | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 17nuwcb | false | null | t3_17nuwcb | /r/LocalLLaMA/comments/17nuwcb/what_methods_do_you_use_to_find_out_which_models/ | false | false | self | 1 | null |
Long context (16K+) 7B training on a single GPU? | 8 | I'm *extremely* impressed with the long context performance of Amazon's MistralLite:
https://huggingface.co/amazon/MistralLite/tree/main
There is nothing like it at 12K-32K... But even though it can pluck summarized detail out of a 20K story like magic, the logic and storytelling/dialogue could be much better, even w... | 2023-11-04T20:39:06 | https://www.reddit.com/r/LocalLLaMA/comments/17nuw86/long_context_16k_7b_training_on_a_single_gpu/ | mcmoose1900 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 17nuw86 | false | null | t3_17nuw86 | /r/LocalLLaMA/comments/17nuw86/long_context_16k_7b_training_on_a_single_gpu/ | false | false | self | 8 | {'enabled': False, 'images': [{'id': '9jYiJY8lgKiK3sA8dMGGl_poYgtYOT3qJROfc9cEw_o', 'resolutions': [{'height': 58, 'url': 'https://external-preview.redd.it/m-Qkc4922qQ0juqeOEBXLR92ObN3nyyR1KY9o9o_ZaE.jpg?width=108&crop=smart&auto=webp&s=8b1a07f53b4a13504e62f21571a46c7c9fb7783c', 'width': 108}, {'height': 116, 'url': 'h... |
DeepSpeed-FastGen: LLM serving framework with 2x throughput of vLLM | 44 | Microsoft announced a new LLM serving framework based in DeepSpeed framework. They claim double the throughput of vLLM on A100.
Current supported architectures are Llama2 and Mistral (and OPT)
Blog post:
https://github.com/microsoft/DeepSpeed/tree/master/blogs/deepspeed-fastgen
Getting started code:
```
# pip inst... | 2023-11-04T20:32:30 | https://www.reddit.com/r/LocalLLaMA/comments/17nuqs3/deepspeedfastgen_llm_serving_framework_with_2x/ | Amgadoz | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 17nuqs3 | false | null | t3_17nuqs3 | /r/LocalLLaMA/comments/17nuqs3/deepspeedfastgen_llm_serving_framework_with_2x/ | false | false | self | 44 | {'enabled': False, 'images': [{'id': '2AkKWK_TpVxeNiYXCMkLQJAFHbGm8uIvmaW_4nvJpP4', 'resolutions': [{'height': 54, 'url': 'https://external-preview.redd.it/io1JhvXVnG6Lp9tfZjzW_WiGzSbUz9Hlw4tU8IsKf3w.jpg?width=108&crop=smart&auto=webp&s=c2b7a8e9f9e33da692ed8b32ff5d8a4de77a6722', 'width': 108}, {'height': 108, 'url': 'h... |
Pleb to Local AI needing step by step | 1 | Can anyone link me to a local install "get up and running" tut if it exists. I'm open to any RTFMs i may need to do. Looking to set this up on a Debian A6000 rig or MacOS M2 testing. Thanks in advance. | 2023-11-04T20:26:58 | https://www.reddit.com/r/LocalLLaMA/comments/17num43/pleb_to_local_ai_needing_step_by_step/ | coinCram | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 17num43 | false | null | t3_17num43 | /r/LocalLLaMA/comments/17num43/pleb_to_local_ai_needing_step_by_step/ | false | false | self | 1 | null |
Microsoft researchers present LLaVA-Interactive: a demo for image chat, segmentation, generation, and editing | 28 | ​
https://preview.redd.it/tne9qo1srdyb1.png?width=2452&format=png&auto=webp&s=0d2b6696af3a646766c74630a387f8ccdd061599
Abstract
>LLaVA-Interactive is a research prototype for multimodal human-AI interaction. The system can have multi-turn dialogues with human users by taking multimodal user inputs and generat... | 2023-11-04T19:19:50 | https://www.reddit.com/r/LocalLLaMA/comments/17nt2a7/microsoft_researchers_present_llavainteractive_a/ | llamaShill | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 17nt2a7 | false | null | t3_17nt2a7 | /r/LocalLLaMA/comments/17nt2a7/microsoft_researchers_present_llavainteractive_a/ | false | false | 28 | null | |
6-month-old LLM startup Mistral into a $2 billion unicorn, sources say | 281 | 2023-11-04T19:14:46 | https://www.businessinsider.com/mistral-in-talks-to-raise-funding-at-2-billion-valuation-2023-11 | metalman123 | businessinsider.com | 1970-01-01T00:00:00 | 0 | {} | 17nsy9d | false | null | t3_17nsy9d | /r/LocalLLaMA/comments/17nsy9d/6monthold_llm_startup_mistral_into_a_2_billion/ | false | false | 281 | {'enabled': False, 'images': [{'id': 'WwUwo0YNAqhnu0k7Hs0aeDjOz1-HT-kjr9ATtnYe4gc', 'resolutions': [{'height': 54, 'url': 'https://external-preview.redd.it/ivg4Yzdan9xTJJNfilLRuqawRoR7Tlrn5f1LKSxb2CM.jpg?width=108&crop=smart&auto=webp&s=ae58e77ff6d994e702f7a97a4183bddfa2452e73', 'width': 108}, {'height': 108, 'url': 'h... | ||
Made a github tool to check how many token/s you can get for any LLM | 3 | 2023-11-04T19:14:43 | https://github.com/RahulSChand/gpu_poor | ExploreExploit400 | github.com | 1970-01-01T00:00:00 | 0 | {} | 17nsy7m | false | null | t3_17nsy7m | /r/LocalLLaMA/comments/17nsy7m/made_a_github_tool_to_check_how_many_tokens_you/ | false | false | 3 | {'enabled': False, 'images': [{'id': 'BtsPd9rxkbpbhhKRo1YTv6jhVzhI5uwh2ggFwmrj-Y0', 'resolutions': [{'height': 54, 'url': 'https://external-preview.redd.it/u8PWZ3Sx7caizaQgstmCy1h_jjVUwnzLP8Rz6yYmxtk.jpg?width=108&crop=smart&auto=webp&s=d66b27cf8217a5d3fa5306280780915781d020fc', 'width': 108}, {'height': 108, 'url': 'h... | ||
How to quantize DeepSeek 33B model | 8 | The 6.7B model seems excellent and from my experiments, it's very close to what I would expect from much larger models. I am excited to try the 33B model but I'm not sure how I should go about performing GPTQ or AWQ quantization.
TIA. | 2023-11-04T18:38:38 | https://www.reddit.com/r/LocalLLaMA/comments/17ns4hk/how_to_quantize_deepseek_33b_model/ | Dry_Long3157 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 17ns4hk | false | null | t3_17ns4hk | /r/LocalLLaMA/comments/17ns4hk/how_to_quantize_deepseek_33b_model/ | false | false | self | 8 | null |
How many token/s can I get? A simple GitHub tool to see token/s u can get for a LLM | 1 | 2023-11-04T18:36:38 | https://github.com/RahulSChand/gpu_poor | ExploreExploit400 | github.com | 1970-01-01T00:00:00 | 0 | {} | 17ns2w9 | false | null | t3_17ns2w9 | /r/LocalLLaMA/comments/17ns2w9/how_many_tokens_can_i_get_a_simple_github_tool_to/ | false | false | default | 1 | null | |
How is your experience with code llama on your code repo? | 7 | Would love to hear about the experience. Starting a new post as I couldn’t find one in recent posts.
Which programming language(s) was the repo in?
How large the code was?
Were you running it on a Mac? What is the machine config?
Any other information would be helpful.
If you installed on Macbook pro, please share the... | 2023-11-04T18:22:32 | https://www.reddit.com/r/LocalLLaMA/comments/17nrrd7/how_is_your_experience_with_code_llama_on_your/ | Crisreddit1 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 17nrrd7 | false | null | t3_17nrrd7 | /r/LocalLLaMA/comments/17nrrd7/how_is_your_experience_with_code_llama_on_your/ | false | false | self | 7 | null |
(working) 180B airoboros gguf | 15 | 2023-11-04T18:18:56 | https://huggingface.co/imi2/airoboros-180b-2.2.1-gguf | Aaaaaaaaaeeeee | huggingface.co | 1970-01-01T00:00:00 | 0 | {} | 17nroc9 | false | null | t3_17nroc9 | /r/LocalLLaMA/comments/17nroc9/working_180b_airoboros_gguf/ | false | false | 15 | {'enabled': False, 'images': [{'id': '_xrW2JLfKIv7HdYcd9fz2gOS9vrU8ig1hPsOoRxvLZk', 'resolutions': [{'height': 58, 'url': 'https://external-preview.redd.it/kaq9zQAy6NQvp_oz99lCxphpfXBRxS4iyriBHEGtoBc.jpg?width=108&crop=smart&auto=webp&s=3182d812967d4ffd71e2e688a1c965ab8b579721', 'width': 108}, {'height': 116, 'url': 'h... | ||
How to get Mistral-7b to put END after each line in an conversation | 1 | I want to create a chatbot, and for easy seperation between speakers I would like the format to be:
Speaker 1: blah blah <END>
Speaker 2: blah blah <END>
​
How do you get Mistral-7b to do this? | 2023-11-04T18:13:13 | https://www.reddit.com/r/LocalLLaMA/comments/17nrjoe/how_to_get_mistral7b_to_put_end_after_each_line/ | ExaminationNo8522 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 17nrjoe | false | null | t3_17nrjoe | /r/LocalLLaMA/comments/17nrjoe/how_to_get_mistral7b_to_put_end_after_each_line/ | false | false | self | 1 | null |
Which framework supports the most amount LLama based models for inference? | 1 | I'm currently using vllm for my inference however it doesn't support Wizard-lm 7 or 13b. Wondering which model best supports unquantized llama based models? if quantized model perform better than wazard lm -13b for instruction based prompts - which model would you suggest to use? | 2023-11-04T17:59:36 | https://www.reddit.com/r/LocalLLaMA/comments/17nr8gv/which_framework_supports_the_most_amount_llama/ | kitkatmafia | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 17nr8gv | false | null | t3_17nr8gv | /r/LocalLLaMA/comments/17nr8gv/which_framework_supports_the_most_amount_llama/ | false | false | self | 1 | null |
How can I remotely access my LLM? | 16 | First I want to give you guys a heads up in that I have not even started yet. My concern is about building a local LLM that's about 300 miles away from me. How do I get started and how do I access it?
I have about 10 3090s, 5 mobos, and a 4090 | 2023-11-04T17:56:09 | https://www.reddit.com/r/LocalLLaMA/comments/17nr5vu/how_can_i_remotely_access_my_llm/ | Inevitable-Syrup8232 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 17nr5vu | false | null | t3_17nr5vu | /r/LocalLLaMA/comments/17nr5vu/how_can_i_remotely_access_my_llm/ | false | false | self | 16 | null |
Great analysis of the foundation model landscape | 5 | [https://twitter.com/GavinSBaker/status/1720819375517716610](https://twitter.com/GavinSBaker/status/1720819375517716610)
Investing in Llama would be a great move.
My takeaways:
1. buy NVDA, TSLA, GOOGL, MSFT and META. At least one will breakout big for sure
2. do not train your own model, that's a race to t... | 2023-11-04T17:30:07 | https://www.reddit.com/r/LocalLLaMA/comments/17nqmub/great_analysis_of_the_foundation_model_landscape/ | hadiazzouni | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 17nqmub | false | null | t3_17nqmub | /r/LocalLLaMA/comments/17nqmub/great_analysis_of_the_foundation_model_landscape/ | false | false | self | 5 | {'enabled': False, 'images': [{'id': 'trdRJm1G5NJXjj7HmlEQ9vpKHNohBhrJPHdGP3a-0oM', 'resolutions': [{'height': 108, 'url': 'https://external-preview.redd.it/0ocDgwAFR-hiRmNxZvtly7q70UL7NkmoFqtRHxTIEoY.jpg?width=108&crop=smart&auto=webp&s=7ad9b31ce159d2be6e18c06446b266436d41827d', 'width': 108}], 'source': {'height': 14... |
How to solve AI alignment | 1 | 1. Hire people to try to use AI to do scary stuff. (hacking, weapons, drugs)
2. If AI successfully aids the white hatters, "patch" the bug IRL: make the stuff they bought less accessible, or fix the bug the AI exploited, making humanity more robust over time.
The only alternative is to ban open source.
I don't see an... | 2023-11-04T17:03:08 | https://www.reddit.com/r/LocalLLaMA/comments/17nq2kc/how_to_solve_ai_alignment/ | bist12 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 17nq2kc | false | null | t3_17nq2kc | /r/LocalLLaMA/comments/17nq2kc/how_to_solve_ai_alignment/ | false | false | self | 1 | null |
Tunctation length issue with staying true to the character file | 2 | How is it that if i put the tunctation length at for example 2000 it drifts away from its character file, and in censored mode.
While when i turn it down to 500, it stays perfectly true to its character file, but it has 0 context size, each response is just new, not taking context into consideration.
Is there any w... | 2023-11-04T16:37:17 | https://www.reddit.com/r/LocalLLaMA/comments/17npiv4/tunctation_length_issue_with_staying_true_to_the/ | Gablediuk | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 17npiv4 | false | null | t3_17npiv4 | /r/LocalLLaMA/comments/17npiv4/tunctation_length_issue_with_staying_true_to_the/ | false | false | self | 2 | null |
New 1.5T token checkpoint of TinyLLaMa got released! | 72 | Hey, I just wanted to share that the TinyLLaMa project released the 1.5T token threshold checkpoint.
https://github.com/jzhang38/TinyLlama
I'm not affiliated with the project, just love following it.
Anyone had a chance to test it yet? | 2023-11-04T16:22:16 | https://www.reddit.com/r/LocalLLaMA/comments/17np7dm/new_15t_token_checkpoint_of_tinyllama_got_released/ | Combinatorilliance | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 17np7dm | false | null | t3_17np7dm | /r/LocalLLaMA/comments/17np7dm/new_15t_token_checkpoint_of_tinyllama_got_released/ | false | false | self | 72 | {'enabled': False, 'images': [{'id': 'hQ_1hwOCkdS4940txkrt_Xr40Uml28FsCfhg2AJoaC0', 'resolutions': [{'height': 54, 'url': 'https://external-preview.redd.it/4fEtUuJ2iozPeIlkfgOKZ_pSqvSJXvLxrDgHGtSqmxo.jpg?width=108&crop=smart&auto=webp&s=865bc69f7ab7d109f97327ecd446cbe5012efe1b', 'width': 108}, {'height': 108, 'url': 'h... |
Recommended Requirements and Cost of local setup | 2 | I want to build my own setup. I seem to not be able to run even the smallest models on my local machine. I've heard people mention ExaFLOP of processing. I'm just wanting a machine that can run most mid level models so they can respond in under 1 second.
Sorry if this isn't the place. didn't see a wiki/FaQ | 2023-11-04T15:56:27 | https://www.reddit.com/r/LocalLLaMA/comments/17non61/recommended_requirements_and_cost_of_local_setup/ | InternalEmergency480 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 17non61 | false | null | t3_17non61 | /r/LocalLLaMA/comments/17non61/recommended_requirements_and_cost_of_local_setup/ | false | false | self | 2 | null |
LM Studio vs Kobold CPP, what to use? | 1 | [removed] | 2023-11-04T15:27:05 | https://www.reddit.com/r/LocalLLaMA/comments/17no0xw/lm_studio_vs_kobold_cpp_what_to_use/ | derpgod123 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 17no0xw | false | null | t3_17no0xw | /r/LocalLLaMA/comments/17no0xw/lm_studio_vs_kobold_cpp_what_to_use/ | false | false | self | 1 | null |
LM Studio vs Llamma CPP, what do you use? | 1 | [removed] | 2023-11-04T15:24:08 | https://www.reddit.com/r/LocalLLaMA/comments/17nnyq4/lm_studio_vs_llamma_cpp_what_do_you_use/ | derpgod123 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 17nnyq4 | false | null | t3_17nnyq4 | /r/LocalLLaMA/comments/17nnyq4/lm_studio_vs_llamma_cpp_what_do_you_use/ | false | false | self | 1 | null |
Text-gen-webui + RAG | 3 | Hi all,
Hopefully you can help me with some pointers about the following:
I like to be able to use oobabooga’s text-generation-webui but feed it with documents, so that the model is able to read and understand these documents, and to make it possible to ask about the contents of those documents. Just like a RAG setup... | 2023-11-04T15:18:32 | https://www.reddit.com/r/LocalLLaMA/comments/17nnui1/textgenwebui_rag/ | e-nigmaNL | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 17nnui1 | false | null | t3_17nnui1 | /r/LocalLLaMA/comments/17nnui1/textgenwebui_rag/ | false | false | self | 3 | null |
Hey guys, can anyone recommend a home rig setup with a 4090 RTX? | 1 | It's been a long time since I was into building PCs every few years... still running with my old 5-6 PC with an 1080ti which has been doing well.
But I'm struggling with running local LLMs and want to join the fray, runpod is great... but I think it'll offer more practicality to run locally if possible, especially wit... | 2023-11-04T14:55:45 | https://www.reddit.com/r/LocalLLaMA/comments/17nncyz/hey_guys_can_anyone_recommend_a_home_rig_setup/ | babanz | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 17nncyz | false | null | t3_17nncyz | /r/LocalLLaMA/comments/17nncyz/hey_guys_can_anyone_recommend_a_home_rig_setup/ | false | false | self | 1 | null |
I've realized that I honestly don't know WHAT the Mac Studio's bottleneck is... | 45 | Ok, bear with me on the wall of text, but I'm seriously confused so I want to give full context.
So I have an M2 Ultra Mac Studio, and over the past few months I've seen several folks post their inference numbers from their Mac Studios as well; each time I've compared their tokens per second to mine, and each time the... | 2023-11-04T14:52:32 | https://www.reddit.com/r/LocalLLaMA/comments/17nnapj/ive_realized_that_i_honestly_dont_know_what_the/ | SomeOddCodeGuy | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 17nnapj | false | null | t3_17nnapj | /r/LocalLLaMA/comments/17nnapj/ive_realized_that_i_honestly_dont_know_what_the/ | false | false | self | 45 | null |
Language Agent Tree Search method bumped GPT-4's HumanEval Pass@1 score from 80.1 to 94.4, GPT-3.5's score from 72.5 to 86.9, can we use this approach with local coding models? | 43 | [This question was already asked a week ago but that thread didn't get much attention, so I wanted to repeat it.](https://www.reddit.com/r/LocalLLaMA/comments/17i7ua4/is_language_agent_tree_search_possible_for_local/)
[Here is the leaderboard for humaneval benchmark.]
(https://paperswithcode.com/sota/code-generation-o... | 2023-11-04T14:41:09 | https://www.reddit.com/r/LocalLLaMA/comments/17nn2va/language_agent_tree_search_method_bumped_gpt4s/ | OnurCetinkaya | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 17nn2va | false | null | t3_17nn2va | /r/LocalLLaMA/comments/17nn2va/language_agent_tree_search_method_bumped_gpt4s/ | false | false | self | 43 | {'enabled': False, 'images': [{'id': 'wr0scn8Z-BK3yLw7Z4N8Xd2w64gnVr3fRXMaL7lV6Lk', 'resolutions': [{'height': 57, 'url': 'https://external-preview.redd.it/KTfNZvG_sH4F5u55Wnt8joya00o9xQ0zxTg2g4zejSo.jpg?width=108&crop=smart&auto=webp&s=11b896a5cbd48fa69d31a438be0a644edb988118', 'width': 108}, {'height': 114, 'url': 'h... |
Talk-LLaMa | 17 | 2023-11-04T14:40:59 | https://github.com/ggerganov/whisper.cpp/tree/master/examples/talk-llama | azurisme | github.com | 1970-01-01T00:00:00 | 0 | {} | 17nn2qr | false | null | t3_17nn2qr | /r/LocalLLaMA/comments/17nn2qr/talkllama/ | false | false | 17 | {'enabled': False, 'images': [{'id': 'xakWJimd33OFeE8FWiBtxQS91zTgXEV6RUNxWdzm62Y', 'resolutions': [{'height': 54, 'url': 'https://external-preview.redd.it/MnlnNO1j_5bv5TAC7lTjiCkmmkBFYOpH0cfI5V_na2M.jpg?width=108&crop=smart&auto=webp&s=9f1a3c72bb85d28ca748578929e813c616ca047f', 'width': 108}, {'height': 108, 'url': 'h... | ||
The new version of koboldcpp is a game changer - instant replies thanks to context shifting | 87 | I'm blown away by the new feature in koboldcpp! Basically, instead of reprocessing a whole lot of the prompt each time you type your answer, it only processes the tokens that changed, e.g. your user message.
Even with full GPU offloading in llama.cpp, it takes a short while (around 5 seconds for me) to reprocess the ... | 2023-11-04T13:47:43 | https://www.reddit.com/r/LocalLLaMA/comments/17nm18r/the_new_version_of_koboldcpp_is_a_game_changer/ | dampflokfreund | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 17nm18r | false | null | t3_17nm18r | /r/LocalLLaMA/comments/17nm18r/the_new_version_of_koboldcpp_is_a_game_changer/ | false | false | self | 87 | null |
OpenHermes 2.5 is on another level conversationally | 143 | I've been using 70b models exclusively and yesterday I gave OpenHermes 2.5 a try.
I'm not going to say it's the best 7b model but from my perspective it is the best overall conversational.
What do you guys think? | 2023-11-04T13:43:07 | https://www.reddit.com/r/LocalLLaMA/comments/17nly6q/openhermes_25_is_on_another_level_conversationally/ | yehiaserag | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 17nly6q | false | null | t3_17nly6q | /r/LocalLLaMA/comments/17nly6q/openhermes_25_is_on_another_level_conversationally/ | false | false | self | 143 | null |
180b model on a big retail PC | 4 | If i build a PC with rtx3090, rtx4090, 192 ddr5 ram, 2x 2tb M2 can i run a 180b model? | 2023-11-04T12:27:00 | https://www.reddit.com/r/LocalLLaMA/comments/17nkllw/180b_model_on_a_big_retail_pc/ | StatusWeekly4719 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 17nkllw | false | null | t3_17nkllw | /r/LocalLLaMA/comments/17nkllw/180b_model_on_a_big_retail_pc/ | false | false | self | 4 | null |
180b on a big tetail pv | 1 | If i build a PC with rtx3090, rtx4090, 192 ddr5 ram, 2x 2tb M2 can i run a 180b model? | 2023-11-04T12:12:14 | https://www.reddit.com/r/LocalLLaMA/comments/17nkcqv/180b_on_a_big_tetail_pv/ | StatusWeekly4719 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 17nkcqv | false | null | t3_17nkcqv | /r/LocalLLaMA/comments/17nkcqv/180b_on_a_big_tetail_pv/ | false | false | self | 1 | null |
SATA vs NVMe SSD for boot drive | 1 | Is there a meaningful difference between running on SATA vs NVMe drives in terms of loading time or running speeds?
I have a spare SATA SSD lying around that I want to use to dual boot Linux, but I don't know if I should get another nvme drive instead. | 2023-11-04T12:04:08 | https://www.reddit.com/r/LocalLLaMA/comments/17nk7u7/sata_vs_nvme_ssd_for_boot_drive/ | tobychung08 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 17nk7u7 | false | null | t3_17nk7u7 | /r/LocalLLaMA/comments/17nk7u7/sata_vs_nvme_ssd_for_boot_drive/ | false | false | self | 1 | null |
How to calculate hardware required for training a model? | 2 | We're looking into establishing an on-premise LLM lab for some R&D. We've found some potential investors and they've asked us to give them a rough estimate on how much hardware (e.g. nVidia A-100 model) is required to train. Let's say 100B input tokens for training a Llama 14-B.
I would appreciate if someone could poi... | 2023-11-04T11:48:06 | https://www.reddit.com/r/LocalLLaMA/comments/17njynv/how_to_calculate_hardware_required_for_training_a/ | aLuViAn87 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 17njynv | false | null | t3_17njynv | /r/LocalLLaMA/comments/17njynv/how_to_calculate_hardware_required_for_training_a/ | false | false | self | 2 | null |
Prompts to fine-tune a story-writing model? | 1 | [removed] | 2023-11-04T10:46:43 | https://www.reddit.com/r/LocalLLaMA/comments/17nj1zo/prompts_to_finetune_a_storywriting_model/ | Guakatiko | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 17nj1zo | false | null | t3_17nj1zo | /r/LocalLLaMA/comments/17nj1zo/prompts_to_finetune_a_storywriting_model/ | false | false | self | 1 | null |
Fast and Portable Llama2 Inference on the Heterogeneous Edge | 1 | 2023-11-04T10:24:27 | https://blog.stackademic.com/fast-and-portable-llama2-inference-on-the-heterogeneous-edge-a62508e82359 | smileymileycoin | blog.stackademic.com | 1970-01-01T00:00:00 | 0 | {} | 17niqri | false | null | t3_17niqri | /r/LocalLLaMA/comments/17niqri/fast_and_portable_llama2_inference_on_the/ | false | false | 1 | {'enabled': False, 'images': [{'id': 'D0NQesOavmG4zCUlQFm3le3sd36uK6qgJKgCLspomkA', 'resolutions': [{'height': 108, 'url': 'https://external-preview.redd.it/04BKhMsyze1fz6egn3bnpllOr2PJO946c8SAjMRaCZY.jpg?width=108&crop=smart&auto=webp&s=7daf35241cf6074c1e5101f62f553c08513b612c', 'width': 108}, {'height': 216, 'url': '... | ||
Koyha_SS for LLM finetuning | 1 | Is there a repo like koyha for llm finetunning? I cant get my code to work do to some cuda 12.3 and bitsandbites compatibitly issue and now want the easy way out lol | 2023-11-04T10:21:27 | https://www.reddit.com/r/LocalLLaMA/comments/17nipbm/koyha_ss_for_llm_finetuning/ | Outside_Ad3038 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 17nipbm | false | null | t3_17nipbm | /r/LocalLLaMA/comments/17nipbm/koyha_ss_for_llm_finetuning/ | false | false | self | 1 | null |
Dolphin's consistency reduced my question to absurdity -.- | 35 | To be clear, I'm talking about Dolphin-2.2.1-Mistral-7B-Q4\_K\_M.gguf
As backend I used pure llama.cpp (server) with gpu-offloading
I have a template with quick questions that I like to use when I want to test new models and make a compromise between 'I don't have time for large-scale benchmarks etc' and 'I want ... | 2023-11-04T10:01:12 | https://www.reddit.com/r/LocalLLaMA/comments/17nif05/dolphins_consistency_reduced_my_question_to/ | Evening_Ad6637 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 17nif05 | false | null | t3_17nif05 | /r/LocalLLaMA/comments/17nif05/dolphins_consistency_reduced_my_question_to/ | false | false | self | 35 | null |
xAI megathread [not LLaMA] | 4 | ​
https://preview.redd.it/wkfdw5yt0byb1.jpg?width=680&format=pjpg&auto=webp&s=6aef45953a418b33db545425eb130796bc011795 | 2023-11-04T09:59:54 | https://www.reddit.com/r/LocalLLaMA/comments/17nie85/xai_megathread_not_llama/ | ambient_temp_xeno | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 17nie85 | false | null | t3_17nie85 | /r/LocalLLaMA/comments/17nie85/xai_megathread_not_llama/ | false | false | 4 | null | |
KoboldCpp v1.48 Context Shifting - Massively Reduced Prompt Reprocessing | 71 | This is huge! What a boon for large model accessibility! Normally it takes me almost 7 minutes to process a full 4K context with a 70b. Now all subsequent responses start after processing a small bit of prompt. I do wonder if it would be feasible for chat clients to put lorebook information toward the end of the prompt... | 2023-11-04T09:39:00 | https://www.reddit.com/r/LocalLLaMA/comments/17ni4hm/koboldcpp_v148_context_shifting_massively_reduced/ | Susp-icious_-31User | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 17ni4hm | false | null | t3_17ni4hm | /r/LocalLLaMA/comments/17ni4hm/koboldcpp_v148_context_shifting_massively_reduced/ | false | false | self | 71 | {'enabled': False, 'images': [{'id': 'iqHLTKimoM-j5TVbxW818h1OKH121oD_EZSlTrRlAqQ', 'resolutions': [{'height': 54, 'url': 'https://external-preview.redd.it/i8e9XW-Eex0LTmnjStaCJ1gL_XkCJHdpK-ZoU6azE1w.jpg?width=108&crop=smart&auto=webp&s=4b340cdcee0886673b6c0d2ada2e3709a2883c5f', 'width': 108}, {'height': 108, 'url': 'h... |
How to handle dependencies between text changes in RAG | 7 | Hello all,
I am working on RAG on certain pdf and I couldn't find resources that were able to handle cases that require multiple chunks (texts after splitting the document).
For example, I have this question: What are the obstacles in calculating labor cost per item?
If u look into the image attached, it has the ... | 2023-11-04T08:25:54 | https://www.reddit.com/r/LocalLLaMA/comments/17nh5sp/how_to_handle_dependencies_between_text_changes/ | vile_proxima | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 17nh5sp | false | null | t3_17nh5sp | /r/LocalLLaMA/comments/17nh5sp/how_to_handle_dependencies_between_text_changes/ | false | false | 7 | {'enabled': False, 'images': [{'id': 'FSgJkox8XXw25qhcPwMofZsbppstcYIZMXIyv1U1L-w', 'resolutions': [{'height': 58, 'url': 'https://external-preview.redd.it/NQJVRKi7omWn_fdODxaAlKoD9vcaQ7zoHGSRfPDnRUg.jpg?width=108&crop=smart&auto=webp&s=2dc8d7a24774f5309f8ec5ca70f4e028ea873609', 'width': 108}, {'height': 116, 'url': 'h... | |
MacBook Pro M3 opinions | 6 | Hey guys,
I’m planning on fine tuning a LLAMA2 model. Since I need a new MacBook anyway (mine is still from 2015) I thought I might aim for the new MP3 M3.
My plan is mainly to do the training on servers. But since I’m planning on using the machine also for some years I thought I’d go for the M3 Pro chip with 18 GB R... | 2023-11-04T08:21:03 | https://www.reddit.com/r/LocalLLaMA/comments/17nh3ou/macbook_pro_m3_opinions/ | Willing_Flatworm5419 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 17nh3ou | false | null | t3_17nh3ou | /r/LocalLLaMA/comments/17nh3ou/macbook_pro_m3_opinions/ | false | false | self | 6 | null |
How to make your companion bot more engaging ? | 18 | I'm looking for ways to make my companion bot more engaging and interesting to talk to. It's currently pretty basic, but I'd like to give it more personality and make it feel more like a real friend. Any tips? | 2023-11-04T07:54:08 | https://www.reddit.com/r/LocalLLaMA/comments/17ngqki/how_to_make_your_companion_bot_more_engaging/ | Zumcddo | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 17ngqki | false | null | t3_17ngqki | /r/LocalLLaMA/comments/17ngqki/how_to_make_your_companion_bot_more_engaging/ | false | false | self | 18 | null |
Why don't the indie modelers upload quantized models? | 7 | The average joe doesn't care who made a model, they care about the final result they're gonna use. The name they'll remember is not who trained the model but the last name they see on their way to use it, the fellow uploading quantized models
They give their $$$ to this fellow. So if the smart folks training models wa... | 2023-11-04T07:52:54 | https://www.reddit.com/r/LocalLLaMA/comments/17ngq1e/why_dont_the_indie_modelers_upload_quantized/ | SavingsAd287 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 17ngq1e | false | null | t3_17ngq1e | /r/LocalLLaMA/comments/17ngq1e/why_dont_the_indie_modelers_upload_quantized/ | false | false | self | 7 | null |
Guys I want to get into LLM use. | 1 | I used to study ML(informally) from 2012-2016 and did mostly NLP, I have been updating my theoretical knowledge for a few months now but I want to find some resources to just jump into playing with some LLMs. Eventually I'd like to create an LLM but the cost is prohibitive right now I have only a VM with 2 80gb A100 an... | 2023-11-04T07:21:52 | https://www.reddit.com/r/LocalLLaMA/comments/17ngc4t/guys_i_want_to_get_into_llm_use/ | ZoltorGack | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 17ngc4t | false | null | t3_17ngc4t | /r/LocalLLaMA/comments/17ngc4t/guys_i_want_to_get_into_llm_use/ | false | false | self | 1 | null |
Pc build Q’s | 1 | Hey,
I am trying to build a pc to run local llama modules, Example: 70b with 4-6bit quantized(I know its optimistic 😢 since it’s probably gonna be slow)and 30-65b (didn’t decide which quantization for the 65b).
Uses of the AI: i want to fine tune a module for my need in giving it books\research papers\articles in c... | 2023-11-04T07:16:42 | https://www.reddit.com/r/LocalLLaMA/comments/17ng9rg/pc_build_qs/ | No-Vermicelli5327 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 17ng9rg | false | null | t3_17ng9rg | /r/LocalLLaMA/comments/17ng9rg/pc_build_qs/ | false | false | self | 1 | null |
My favorite 4090 LLM for role-play and story telling. | 10 |
I’ve tried quite a few models, but this one tops them all.
- TheBloke/Nethena-MLewd-Xwin-23B-GGUF
I’m using Q5_K_M, At 4k context, with Kobold.CPP
https://huggingface.co/TheBloke/Nethena-MLewd-Xwin-23B-GGUF/tree/main?not-for-all-audiences=true | 2023-11-04T06:27:47 | https://www.reddit.com/r/LocalLLaMA/comments/17nfm3a/my_favorite_4090_llm_for_roleplay_and_story/ | Majestical-psyche | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 17nfm3a | false | null | t3_17nfm3a | /r/LocalLLaMA/comments/17nfm3a/my_favorite_4090_llm_for_roleplay_and_story/ | false | false | self | 10 | {'enabled': False, 'images': [{'id': 'A17L_oG0DJ6L2F20dyvpOM-qG3mgj6qu29ysP8src5c', 'resolutions': [{'height': 58, 'url': 'https://external-preview.redd.it/h9SQq0bN0enZPNfuhUmn-GWcCKBqvcRAkV5TFB_Pf9M.jpg?width=108&crop=smart&auto=webp&s=6dd16f99741e38065d39f6deb2e09cb0b82eb931', 'width': 108}, {'height': 116, 'url': 'h... |
Exchange Lora Lorax | 1 | Hello
Do uou know any open source to make an lora exchange model between weights ? | 2023-11-04T05:56:42 | https://www.reddit.com/r/LocalLLaMA/comments/17nf6rm/exchange_lora_lorax/ | bacocololo | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 17nf6rm | false | null | t3_17nf6rm | /r/LocalLLaMA/comments/17nf6rm/exchange_lora_lorax/ | false | false | self | 1 | null |
LLAMA 2 & GPT MoE ? | 1 | I want an application that can translate natural language to SQL and also analyze if the result contains any anomalies based on the document metadata I'll provide. Is there any method to use different LLM models (LLAMA and GPT) for natural language to SQL and checking for anomalies? is moe needed here or langchain is ... | 2023-11-04T05:45:45 | https://www.reddit.com/r/LocalLLaMA/comments/17nf1jq/llama_2_gpt_moe/ | laveriaroha | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 17nf1jq | false | null | t3_17nf1jq | /r/LocalLLaMA/comments/17nf1jq/llama_2_gpt_moe/ | false | false | self | 1 | null |
Large (70b) models responding with $$$$$ - What can cause this with LM Studio? | 1 | I recently got a pretty beefy machine and thought I'd try out some 70b models (I usually use 30b\~) but all the ones I've tried seem to respond with either $$$$$$ (repeating a random about of times) or glitchy looking block charachters.
I've tried Synthia 70b (q5km), llama 2 chat uncensored (q5km) and a few others usi... | 2023-11-04T05:32:58 | https://www.reddit.com/r/LocalLLaMA/comments/17nev89/large_70b_models_responding_with_what_can_cause/ | sammcj | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 17nev89 | false | null | t3_17nev89 | /r/LocalLLaMA/comments/17nev89/large_70b_models_responding_with_what_can_cause/ | false | false | 1 | null | |
What models can I run on a 4070 TI | 1 | I recently got a new graphics card and wanted to try running some Local ML models.
I got access to llama from [the meta site](https://ai.meta.com/resources/models-and-libraries/llama-downloads/) and tried to run it locally.
However, I'm running into an error whenever I execute the example provided in the github ... | 2023-11-04T04:16:57 | https://www.reddit.com/r/LocalLLaMA/comments/17ndp41/what_models_can_i_run_on_a_4070_ti/ | zzKillswitchzz | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 17ndp41 | false | null | t3_17ndp41 | /r/LocalLLaMA/comments/17ndp41/what_models_can_i_run_on_a_4070_ti/ | false | false | default | 1 | {'enabled': False, 'images': [{'id': 'ilC2qprzEOhvondbER2GPm9DXBMFQhdj6lShAI3fqUQ', 'resolutions': [{'height': 60, 'url': 'https://external-preview.redd.it/PWPq362pgpPGu5t830LBn-ulBHjrO1453X1VU_tZ130.jpg?width=108&crop=smart&auto=webp&s=23a0d0a4239d7b35988753076153b1495f2e93dd', 'width': 108}, {'height': 121, 'url': 'h... |
Suggestion for using model | 1 | [removed] | 2023-11-04T02:29:24 | https://www.reddit.com/r/LocalLLaMA/comments/17nbty1/suggestion_for_using_model/ | No_Cause_3396 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 17nbty1 | false | null | t3_17nbty1 | /r/LocalLLaMA/comments/17nbty1/suggestion_for_using_model/ | false | false | self | 1 | null |
Introducing HelixNet: An actor-critic-regenerator architecture with 3 x Mistral-7B's | 88 | It's been a big week for Open Source AI, and here's one more to cap the week off!
Introducing HelixNet.
HelixNet is a novel Deep Learning architecture consisting of 3 x Mistral-7B LLMs. It has an **actor**, a **critic**, and a **regenerator**. HelixNet is insprired from an actor-critic architecture most prominent in... | 2023-11-04T02:26:54 | https://www.reddit.com/r/LocalLLaMA/comments/17nbs72/introducing_helixnet_an_actorcriticregenerator/ | migtissera | self.LocalLLaMA | 2023-11-04T02:39:02 | 0 | {} | 17nbs72 | false | null | t3_17nbs72 | /r/LocalLLaMA/comments/17nbs72/introducing_helixnet_an_actorcriticregenerator/ | false | false | 88 | {'enabled': False, 'images': [{'id': '7gI7Tx8JVXaAhGgcXxEc_rYthznOxNDHEWZz3p9WhCY', 'resolutions': [{'height': 58, 'url': 'https://external-preview.redd.it/Nsy-J2A3XBStmvIiFZf83iq01iwhNaTOYtBI-zkbusA.jpg?width=108&crop=smart&auto=webp&s=3c390b86632f19da4cbcd0f884124a653ed4f7b8', 'width': 108}, {'height': 116, 'url': 'h... | |
I'm confused about embeddings | 10 | I understand that an embedding is a numerical representation of some text (or image, video, audio, etc, but I want to focus on text).
For example:
bird=[0.94,-0.3,...]
fish=[-0.01,0.12,...]
But who defines that the first dimension (0.94) will define the "capacity to fly" of the data. Is it the model itself? or the one... | 2023-11-04T00:59:43 | https://www.reddit.com/r/LocalLLaMA/comments/17na39t/im_confused_about_embeddings/ | julio_oa | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 17na39t | false | null | t3_17na39t | /r/LocalLLaMA/comments/17na39t/im_confused_about_embeddings/ | false | false | self | 10 | null |
HelixNet - Using 3 Mistral-7b models for better response gemneration | 132 | It seems to be quite an interesting approach if it works as advertised.
According to the original twitter post by @migtissera:
```
HelixNet is a novel Deep Learning architecture consisting of 3 x Mistral-7B LLMs. It has an actor, a critic, and a regenerator.
HelixNet regenerates very pleasing and accurate responses,... | 2023-11-04T00:42:12 | https://www.reddit.com/r/LocalLLaMA/comments/17n9r6k/helixnet_using_3_mistral7b_models_for_better/ | goatsdontlie | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 17n9r6k | false | null | t3_17n9r6k | /r/LocalLLaMA/comments/17n9r6k/helixnet_using_3_mistral7b_models_for_better/ | false | false | self | 132 | {'enabled': False, 'images': [{'id': '7gI7Tx8JVXaAhGgcXxEc_rYthznOxNDHEWZz3p9WhCY', 'resolutions': [{'height': 58, 'url': 'https://external-preview.redd.it/Nsy-J2A3XBStmvIiFZf83iq01iwhNaTOYtBI-zkbusA.jpg?width=108&crop=smart&auto=webp&s=3c390b86632f19da4cbcd0f884124a653ed4f7b8', 'width': 108}, {'height': 116, 'url': 'h... |
How to fine tune llama 2 13b using hugging & deepspeed without OOM issues | 3 | I've been trying to fine tune the llama 2 13b model not quantized on AWS g5.12x instance which has 4*24gb A10GPUs, and 192gb ram. I've been trying to fine-tune it with hugging face trainer along with deepspeed stage 3 because it could offload the parameters into the cpu, but I run into out of memory errors irrespective... | 2023-11-04T00:21:50 | https://www.reddit.com/r/LocalLLaMA/comments/17n9chh/how_to_fine_tune_llama_2_13b_using_hugging/ | IXMachina | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 17n9chh | false | null | t3_17n9chh | /r/LocalLLaMA/comments/17n9chh/how_to_fine_tune_llama_2_13b_using_hugging/ | false | false | self | 3 | null |
AI/ML Weekly Update - Newsletter | 1 | [removed] | 2023-11-04T00:14:34 | https://medium.com/@webtek.ai/navigating-the-neural-ai-ml-chronicles-of-the-week-10-30-11-03-398294311c85 | pinnapple-crush | medium.com | 1970-01-01T00:00:00 | 0 | {} | 17n96wt | false | null | t3_17n96wt | /r/LocalLLaMA/comments/17n96wt/aiml_weekly_update_newsletter/ | false | false | 1 | {'enabled': False, 'images': [{'id': 'epNryes8g21Sfk2C_huDQcZfjMI5aI0kpi5ubR_B3RQ', 'resolutions': [{'height': 108, 'url': 'https://external-preview.redd.it/AwR5KMz2LIkadl5UUj-zSjFLmlUCsv9On_jgyLlrSiA.jpg?width=108&crop=smart&auto=webp&s=894566271679722a0f0d049d309d433e4952b841', 'width': 108}, {'height': 216, 'url': '... | |
Let's discuss how technology and society would change with high-end, low-power LLMs | 57 | I can't be the only one thinking about this. Would like other people's thoughts.
Let's say it's 2026 and we are seeing the first foundational models for consumer hardware coming out, with the following specs:
* As intelligent as GPT-4
* Open source MIT license
* Runs under 4GB of RAM
* Runs on high-end CPUs
* Outputs... | 2023-11-03T23:29:17 | https://www.reddit.com/r/LocalLLaMA/comments/17n88ij/lets_discuss_how_technology_and_society_would/ | platistocrates | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 17n88ij | false | null | t3_17n88ij | /r/LocalLLaMA/comments/17n88ij/lets_discuss_how_technology_and_society_would/ | false | false | self | 57 | null |
Is gpt 4 or any open source llms are good at math | 1 | [removed] | 2023-11-03T23:22:43 | https://www.reddit.com/r/LocalLLaMA/comments/17n83hk/is_gpt_4_or_any_open_source_llms_are_good_at_math/ | Puzzleheaded_Acadia1 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 17n83hk | false | null | t3_17n83hk | /r/LocalLLaMA/comments/17n83hk/is_gpt_4_or_any_open_source_llms_are_good_at_math/ | false | false | self | 1 | null |
Forget ChatGPT, why Llama and open source AI win 2023 | 39 | 2023-11-03T23:05:58 | https://venturebeat.com/ai/forget-chatgpt-why-llama-and-open-source-ai-win-2023/ | emptyplate | venturebeat.com | 1970-01-01T00:00:00 | 0 | {} | 17n7qaf | false | null | t3_17n7qaf | /r/LocalLLaMA/comments/17n7qaf/forget_chatgpt_why_llama_and_open_source_ai_win/ | false | false | 39 | {'enabled': False, 'images': [{'id': 'vdlUv1tdJ_poyggEgJC_-7idcnkYyugtNDm4jaewWNE', 'resolutions': [{'height': 61, 'url': 'https://external-preview.redd.it/3d7Lg7vitUiIW8Nuwx-EgufFWel-q1z-lacJ0eXBMIs.jpg?width=108&crop=smart&auto=webp&s=0469b4184bcbd5acf9d7769fbe21270018226dba', 'width': 108}, {'height': 123, 'url': 'h... | ||
Need advice on running LLMs locally (dumb question) | 1 | [removed] | 2023-11-03T22:35:51 | https://www.reddit.com/r/LocalLLaMA/comments/17n72a9/need_advice_on_running_llms_locally_dumb_question/ | derpgod123 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 17n72a9 | false | null | t3_17n72a9 | /r/LocalLLaMA/comments/17n72a9/need_advice_on_running_llms_locally_dumb_question/ | false | false | self | 1 | null |
The White House - Executive Order on the Safe, Secure, and Trustworthy Development and Use of Artificial Intelligence | 5 | 2023-11-03T22:08:45 | Divniy | i.redd.it | 1970-01-01T00:00:00 | 0 | {} | 17n6h6s | false | null | t3_17n6h6s | /r/LocalLLaMA/comments/17n6h6s/the_white_house_executive_order_on_the_safe/ | false | false | 5 | {'enabled': True, 'images': [{'id': 'ExVe2SIAl92DCop7R4tlOfxPJoQu7752p6NKiv1Irl8', 'resolutions': [{'height': 157, 'url': 'https://preview.redd.it/gq1g2rvxh7yb1.png?width=108&crop=smart&auto=webp&s=7e14c613e482bde968bc05ad53d8f5cda8baac39', 'width': 108}, {'height': 315, 'url': 'https://preview.redd.it/gq1g2rvxh7yb1.pn... | |||
13B vs. 70B model comparison | 6 | I'm using llama2 model to summarize RAG results and just realized 13B model somehow gave me better results than 70B, which is surprising. here're the 2 models I used: llama2\_13b\_chat\_HF and TheBlokeLlama2\_70B\_chat\_GPTQ. Has anyone had similar experiences before? I used same prompt so not sure what else I did w... | 2023-11-03T21:54:45 | https://www.reddit.com/r/LocalLLaMA/comments/17n66ap/13b_vs_70b_model_comparison/ | peterwu00 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 17n66ap | false | null | t3_17n66ap | /r/LocalLLaMA/comments/17n66ap/13b_vs_70b_model_comparison/ | false | false | self | 6 | null |
What is the least chatty model? | 0 | I'm building a tool that I can use to query PDFs and automate the answers to be uploaded into a spreadsheet. Problem is that instead of just giving me concise responses with the info I need, every once in awhile the models will add things like "Sure! Here's your answer ..." To the response and that makes it a pain to c... | 2023-11-03T21:54:30 | https://www.reddit.com/r/LocalLLaMA/comments/17n662s/what_is_the_least_chatty_model/ | lilbronto | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 17n662s | false | null | t3_17n662s | /r/LocalLLaMA/comments/17n662s/what_is_the_least_chatty_model/ | false | false | self | 0 | null |
Multipurpose AI app for all your AI interests and services. | 1 | [removed] | 2023-11-03T21:33:03 | https://www.reddit.com/r/LocalLLaMA/comments/17n5p8u/multipurpose_ai_app_for_all_your_ai_interests_and/ | EtelsonRecomputing | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 17n5p8u | false | null | t3_17n5p8u | /r/LocalLLaMA/comments/17n5p8u/multipurpose_ai_app_for_all_your_ai_interests_and/ | false | false | self | 1 | {'enabled': False, 'images': [{'id': 'j9BOoAGSccutND6ogshNyb-xWVFtmdUvHV_lLdzYeVk', 'resolutions': [{'height': 56, 'url': 'https://external-preview.redd.it/V0FBs4ANBGpyFs_PZ9-yzcRHWxeq6OF-hv624Ti8Fs0.jpg?width=108&crop=smart&auto=webp&s=76adf9aa07171352e3727b8d8bde812b5eb0f7ab', 'width': 108}, {'height': 113, 'url': 'h... |
Yarn parameters on llama.cpp | 7 | Can anyone confirm the YARN parameters you would use to extend a non-finetuned llama2 model to 8192?
The PR states that non-fine tuned models can be extended to 2x without issues, but I'm getting garbage after a few thousand tokens
The discussion on the PR itself is a little confusing
Currently I'm attempting to us... | 2023-11-03T21:23:38 | https://www.reddit.com/r/LocalLLaMA/comments/17n5hrq/yarn_parameters_on_llamacpp/ | mrjackspade | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 17n5hrq | false | null | t3_17n5hrq | /r/LocalLLaMA/comments/17n5hrq/yarn_parameters_on_llamacpp/ | false | false | self | 7 | null |
Musk post on X | 1 | https://x.com/elonmusk/status/1720372289378590892?s=46&t=vKmhencp3-kHLHDLxzVYtw | 2023-11-03T21:02:33 | https://www.reddit.com/r/LocalLLaMA/comments/17n5063/musk_post_on_x/ | jeffwadsworth | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 17n5063 | false | null | t3_17n5063 | /r/LocalLLaMA/comments/17n5063/musk_post_on_x/ | false | false | self | 1 | {'enabled': False, 'images': [{'id': 'VD41x2eTwf3090Mdeh6MnypEdYddNddxU8tZSp4axIk', 'resolutions': [{'height': 108, 'url': 'https://external-preview.redd.it/9YsFFyZdxc-hZPkyQvesiYbYE4wWAm9eeUbdBY8TgsA.jpg?width=108&crop=smart&auto=webp&s=58328068d2591fec04c8d6e0e616981ea4bee9fa', 'width': 108}], 'source': {'height': 20... |
When LLM doesn’t fit into memory, how to make it work? | 5 | So I was playing with [MLC webllm](https://webllm.mlc.ai) locally.
I got my mistral 7B model installed and quantised. [Converted](https://github.com/mlc-ai/web-llm) it using mlc lib to metal package for Apple chips.
Now it takes only 3.5GB of memory
I run the MLC chat and I get out of memory error and it exits. It ge... | 2023-11-03T20:43:44 | https://www.reddit.com/r/LocalLLaMA/comments/17n4kv9/when_llm_doesnt_fit_into_memory_how_to_make_it/ | Robert-treboR | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 17n4kv9 | false | null | t3_17n4kv9 | /r/LocalLLaMA/comments/17n4kv9/when_llm_doesnt_fit_into_memory_how_to_make_it/ | false | false | self | 5 | null |
What's the go-to right now for a tuned sophisticated general intelligence model? | 2 | Something that is tuned and I can pick up and use right away without tinkering with it.
I have little experience with LLm's and don't know how fast the landscape changes. But I have a GPU server filled with 8 P40's with Ubuntu server and a llama cpp setup.
Something that doesn't require tuning like you would with a ... | 2023-11-03T20:00:42 | https://www.reddit.com/r/LocalLLaMA/comments/17n3m4d/whats_the_goto_right_now_for_a_tuned/ | CertainlyBright | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 17n3m4d | false | null | t3_17n3m4d | /r/LocalLLaMA/comments/17n3m4d/whats_the_goto_right_now_for_a_tuned/ | false | false | self | 2 | null |
FlashDecoding++: Faster Large Language Model Inference on GPUs | 26 | >As the Large Language Model (LLM) becomes increasingly important in various domains. However, the following challenges still remain unsolved in accelerating LLM inference: (1) Synchronized partial softmax update. The softmax operation requires a synchronized update operation among each partial softmax result, leading ... | 2023-11-03T19:12:12 | https://x.com/_akhaliq/status/1720447630084276329?t=WKhAHlrrPc8ckdFBaAnXRA&s=34 | ninjasaid13 | x.com | 1970-01-01T00:00:00 | 0 | {} | 17n2jys | false | null | t3_17n2jys | /r/LocalLLaMA/comments/17n2jys/flashdecoding_faster_large_language_model/ | false | false | 26 | {'enabled': False, 'images': [{'id': 'L6zWsuQ93Nhmym3w0fpVtkS_r5qRbJi7TG3bwYPugfY', 'resolutions': [{'height': 92, 'url': 'https://external-preview.redd.it/HxYXPDNmweuMREGVdKbPVn4Nl3NNvF5hYkG9bXT4y_g.jpg?width=108&crop=smart&auto=webp&s=b452e0a2d51eda87c8c409d01cb7f8a5e609479b', 'width': 108}, {'height': 185, 'url': 'h... | |
testing | 1 | [removed] | 2023-11-03T19:06:11 | https://www.reddit.com/r/LocalLLaMA/comments/17n2f5q/testing/ | MrEloi | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 17n2f5q | false | null | t3_17n2f5q | /r/LocalLLaMA/comments/17n2f5q/testing/ | false | false | self | 1 | null |
Kosmos-2 Demo | 14 | 2023-11-03T19:00:05 | https://x.com/mervenoyann/status/1720126908384366649?t=w33fpc-HUIe0eE9cXPWybw&s=34 | ninjasaid13 | x.com | 1970-01-01T00:00:00 | 0 | {} | 17n29zz | false | null | t3_17n29zz | /r/LocalLLaMA/comments/17n29zz/kosmos2_demo/ | false | false | 14 | {'enabled': False, 'images': [{'id': 'XE1_8mMyy1WtPRWQ5y5fWcohYgHxbQCmiSCkcH9qChg', 'resolutions': [{'height': 62, 'url': 'https://external-preview.redd.it/pKj9Fuyt-Nh097E8HM25_UmYkIWxd1j1wlJyPwOCTSQ.jpg?width=108&crop=smart&auto=webp&s=d0eeed48581b1e626566e346305df95d4c8bbbbc', 'width': 108}, {'height': 125, 'url': 'h... | ||
Troubleshooting Special Tokens in Transformer Language Model Training. | 1 | Hello, fellow CausalLM enthusiasts!
I’ve been developing a custom decoder-only transformer model in PyTorch for language generation, and I've encountered a perplexing issue during training.
The model’s objective is to generate text sequences in a specific language, and for this, I initially processed my input data... | 2023-11-03T18:50:57 | https://www.reddit.com/r/LocalLLaMA/comments/17n22vk/troubleshooting_special_tokens_in_transformer/ | alanrm01 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 17n22vk | false | null | t3_17n22vk | /r/LocalLLaMA/comments/17n22vk/troubleshooting_special_tokens_in_transformer/ | false | false | self | 1 | null |
Nvidia gives a shoutout to r/LocalLLaMA in a blog post on generative AI with their Jetson platform | 205 | 2023-11-03T18:31:29 | https://developer.nvidia.com/blog/bringing-generative-ai-to-life-with-jetson/ | Scary-Knowledgable | developer.nvidia.com | 1970-01-01T00:00:00 | 0 | {} | 17n1o1q | false | null | t3_17n1o1q | /r/LocalLLaMA/comments/17n1o1q/nvidia_gives_a_shoutout_to_rlocalllama_in_a_blog/ | false | false | 205 | {'enabled': False, 'images': [{'id': 'jdP6q1xx_oCIuC_kN69tUEk30RfFMzieeYbO1lM-8R8', 'resolutions': [{'height': 60, 'url': 'https://external-preview.redd.it/LI7759FS8kYOLhSFPgKnWZ3YvumC6N1FmUekiLv9_qc.jpg?width=108&crop=smart&auto=webp&s=0a18ce9e9af67b0b78d63509ebbba725fdea68e9', 'width': 108}, {'height': 121, 'url': 'h... | ||
Confusion over how to use Llama to generate reports | 1 | Hey y'all,
I wanted to ask about implementation of an idea I have - I feel like it's straightforward, but I haven't had any luck in my research and now feel more confused than ever on LLMs.
I want to create an chatbot that, given good samples of reports and the requirements for a new report, can write out the draft ... | 2023-11-03T18:12:45 | https://www.reddit.com/r/LocalLLaMA/comments/17n19kf/confusion_over_how_to_use_llama_to_generate/ | AdamantStudent | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 17n19kf | false | null | t3_17n19kf | /r/LocalLLaMA/comments/17n19kf/confusion_over_how_to_use_llama_to_generate/ | false | false | self | 1 | null |
Do you need resources for training large ML models ASAP? | 3 | Hello, everyone who deals with ML model training.
We have just opened access to Nebius AI — our AI-centric cloud platform. It's ready for intensive ML workloads, including LLM and Gen AI.We have a good number of NVIDIA® H100 Tensor Core GPUs that can be used on-demand or with reserved resources.
The platform provides... | 2023-11-03T17:41:44 | https://www.reddit.com/r/LocalLLaMA/comments/17n0lf3/do_you_need_resources_for_training_large_ml/ | nebius_com | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 17n0lf3 | false | null | t3_17n0lf3 | /r/LocalLLaMA/comments/17n0lf3/do_you_need_resources_for_training_large_ml/ | false | false | self | 3 | {'enabled': False, 'images': [{'id': 'T2fvizo3wg-f3jCSc9DLfMFhfqtqPZbCDK6w_nEUkd8', 'resolutions': [{'height': 54, 'url': 'https://external-preview.redd.it/UH0AdUJDNokmShFwaxO6pDADtVUcxqmNXUWCMRBj8WI.jpg?width=108&crop=smart&auto=webp&s=d925166771d4602029cbeb4687e187507dc4f17c', 'width': 108}, {'height': 108, 'url': 'h... |
Theoretically what's the largest LLAMA-based model you can run with 128GB M3 MacBook Pro? | 47 | Apologies if this has been asked before. I saw the new M3 lineup. While the higher end higher memory models seem super expensive, if you can potentially run larger Llama 2 models while being power efficient and portable, it might be worth it for some use cases. | 2023-11-03T17:34:08 | https://www.reddit.com/r/LocalLLaMA/comments/17n0fku/theoretically_whats_the_largest_llamabased_model/ | lanky_cowriter | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 17n0fku | false | null | t3_17n0fku | /r/LocalLLaMA/comments/17n0fku/theoretically_whats_the_largest_llamabased_model/ | false | false | self | 47 | null |
Merged mistral base plus lora performs poorly vs unmerged base plus lora | 5 | I have finetuned various loras that use mistralai/Mistral-7B-v0.1 as the base model, loaded in 4bit with bnb. The loras are targeting all available mistral target\_modules and use a private dataset with relatively straightforward summarisation-type tasks.
After finetuning, for each lora, I performed a baseline valida... | 2023-11-03T17:25:09 | https://www.reddit.com/r/LocalLLaMA/comments/17n08qc/merged_mistral_base_plus_lora_performs_poorly_vs/ | Hoblywobblesworth | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 17n08qc | false | null | t3_17n08qc | /r/LocalLLaMA/comments/17n08qc/merged_mistral_base_plus_lora_performs_poorly_vs/ | false | false | self | 5 | null |
is there an opensource version of Replit Ghostwriter | 2 | im looking to find something i can run locally that meets the features of replit ghostwriter ai. basically a code editor in the browser. the idea is to point it to a local llama model like mistral. | 2023-11-03T17:24:35 | https://www.reddit.com/r/LocalLLaMA/comments/17n08b4/is_there_an_opensource_version_of_replit/ | herozorro | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 17n08b4 | false | null | t3_17n08b4 | /r/LocalLLaMA/comments/17n08b4/is_there_an_opensource_version_of_replit/ | false | false | self | 2 | null |
Subsets and Splits
No community queries yet
The top public SQL queries from the community will appear here once available.