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 ⌀ |
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
How to deal with loss for SFT for CausalLM | 1 | I'm currently trying to finetune Llama2 chat model.
The task is causal language modeling and I'm exploiting custom dataset, consisting of domain specific prompts and corresponding answers.
I'm currently using SFT trainer([https://huggingface.co/docs/trl/sft\_trainer](https://huggingface.co/docs/trl/sft_trainer))and u... | 2023-12-10T17:28:30 | https://www.reddit.com/r/LocalLLaMA/comments/18f8ju4/how_to_deal_with_loss_for_sft_for_causallm/ | __given__ | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 18f8ju4 | false | null | t3_18f8ju4 | /r/LocalLLaMA/comments/18f8ju4/how_to_deal_with_loss_for_sft_for_causallm/ | false | false | 1 | null | |
Forcing AI to Follow a Specific Answer Pattern Using GBNF Grammar | 18 | Hi everyone!
I'm currently working on a project where I'm trying to force an AI to reply with a particular structure. I've written a GBNF grammar file for this purpose, but I'm facing some challenges in getting the AI to strictly adhere to the pattern I need.
Here's the pattern I want the AI to follow:
The logic... | 2023-12-10T17:10:52 | https://www.reddit.com/r/LocalLLaMA/comments/18f861a/forcing_ai_to_follow_a_specific_answer_pattern/ | Toni_rider | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 18f861a | false | null | t3_18f861a | /r/LocalLLaMA/comments/18f861a/forcing_ai_to_follow_a_specific_answer_pattern/ | false | false | self | 18 | null |
Has anyone tried striped hyena 7b chat from from together ai? | 1 | [removed] | 2023-12-10T16:25:50 | https://www.reddit.com/r/LocalLLaMA/comments/18f76h2/has_anyone_tried_striped_hyena_7b_chat_from_from/ | Conscious-Mixture-69 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 18f76h2 | false | null | t3_18f76h2 | /r/LocalLLaMA/comments/18f76h2/has_anyone_tried_striped_hyena_7b_chat_from_from/ | false | false | self | 1 | null |
Gpt4all can't discover starcoder-q4_0.gguf model | 2 | Hello,
I'm a beginner at this and don't know what's the issue hope you can help me with it.
I installed gpt4all on Windows and then downloaded this model **starcoder-q4\_0.gguf** to the correct location in settings but the app doesn't recognize the model.
What could be the issue and how to fix it?
Thanks
​ | 2023-12-10T16:24:32 | https://www.reddit.com/r/LocalLLaMA/comments/18f75gq/gpt4all_cant_discover_starcoderq4_0gguf_model/ | yassersharaf | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 18f75gq | false | null | t3_18f75gq | /r/LocalLLaMA/comments/18f75gq/gpt4all_cant_discover_starcoderq4_0gguf_model/ | false | false | self | 2 | null |
Got myself a 4way rtx 4090 rig for local LLM | 670 | 2023-12-10T16:07:13 | VectorD | i.redd.it | 1970-01-01T00:00:00 | 0 | {} | 18f6sae | false | null | t3_18f6sae | /r/LocalLLaMA/comments/18f6sae/got_myself_a_4way_rtx_4090_rig_for_local_llm/ | false | false | 670 | {'enabled': True, 'images': [{'id': '2gxzG1dtyI2H2UhZMEvZ4bKoy2f3c-a5jEXt_XhpatM', 'resolutions': [{'height': 216, 'url': 'https://preview.redd.it/abxkvuy1rh5c1.jpeg?width=108&crop=smart&auto=webp&s=b8e19e8c31690669dc5f20e3fe52e83d061b8484', 'width': 108}, {'height': 432, 'url': 'https://preview.redd.it/abxkvuy1rh5c1.j... | |||
Fail to reproduce the same evaluation metrics score during inference. | 3 | Hi,
I have fine-tuned LLAMA-2-7b using QLora for multi-label classification on 6k context using RoPE scaling. After training the model for 2 epochs I get F1 macro 0.51 and micro 0.65 on the evaluation dataset. However, I tried to reproduce these scores in the inference pipeline on the same evaluation dataset but fa... | 2023-12-10T15:28:03 | https://www.reddit.com/r/LocalLLaMA/comments/18f5z8z/fail_to_reproduce_the_same_evaluation_metrics/ | ali0100u | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 18f5z8z | false | null | t3_18f5z8z | /r/LocalLLaMA/comments/18f5z8z/fail_to_reproduce_the_same_evaluation_metrics/ | false | false | self | 3 | {'enabled': False, 'images': [{'id': 'Xzza6MaeNH9Rnq_891iBBVcMQM_HZSO6VjT5Q7fv8Bw', 'resolutions': [{'height': 54, 'url': 'https://external-preview.redd.it/QlMGkXTXgf4R7c_uQEwyYWqH0BQqZvMc8CBDYt-HvYc.jpg?width=108&crop=smart&auto=webp&s=5ea645d5ddc9c2ebb7f53494285860739fcacaf2', 'width': 108}, {'height': 108, 'url': 'h... |
Mixtral 7B MoE beats LLaMA2 70B in MMLU | 100 | 2023-12-10T15:15:37 | https://twitter.com/Francis_YAO_/status/1733686003687112983 | iDoAiStuffFr | twitter.com | 1970-01-01T00:00:00 | 0 | {} | 18f5q44 | false | {'oembed': {'author_name': 'Yao Fu', 'author_url': 'https://twitter.com/Francis_YAO_', 'cache_age': 3153600000, 'height': None, 'html': '<blockquote class="twitter-video"><p lang="en" dir="ltr">Feel the power of MoE <a href="https://t.co/JgwKJNOXCC">pic.twitter.com/JgwKJNOXCC</a></p>— Yao Fu (@Francis_YAO_) <a hr... | t3_18f5q44 | /r/LocalLLaMA/comments/18f5q44/mixtral_7b_moe_beats_llama2_70b_in_mmlu/ | false | false | 100 | {'enabled': False, 'images': [{'id': 'I9sTJGsHBuWQv7xtm4bF3_5q9TfGhO4geGjazaC6FeE', 'resolutions': [{'height': 45, 'url': 'https://external-preview.redd.it/47qG6rrCTpmkKn9claOEr7lg2Ashj4u6Z8XdpyK7ygI.jpg?width=108&crop=smart&auto=webp&s=759d95c744e29caa668db6a99fa4050fc0c7b930', 'width': 108}], 'source': {'height': 59,... | ||
Mixtral 7B MoE beats LLaMA2 in MMLU | 1 | [deleted] | 2023-12-10T15:14:47 | https://twitter.com/Francis_YAO_/status/1733686003687112983 | iDoAiStuffFr | twitter.com | 1970-01-01T00:00:00 | 0 | {} | 18f5pi3 | false | {'oembed': {'author_name': 'Yao Fu', 'author_url': 'https://twitter.com/Francis_YAO_', 'cache_age': 3153600000, 'height': None, 'html': '<blockquote class="twitter-video"><p lang="en" dir="ltr">Feel the power of MoE <a href="https://t.co/JgwKJNOXCC">pic.twitter.com/JgwKJNOXCC</a></p>— Yao Fu (@Francis_YAO_) <a hr... | t3_18f5pi3 | /r/LocalLLaMA/comments/18f5pi3/mixtral_7b_moe_beats_llama2_in_mmlu/ | false | false | 1 | {'enabled': False, 'images': [{'id': 'I9sTJGsHBuWQv7xtm4bF3_5q9TfGhO4geGjazaC6FeE', 'resolutions': [{'height': 45, 'url': 'https://external-preview.redd.it/47qG6rrCTpmkKn9claOEr7lg2Ashj4u6Z8XdpyK7ygI.jpg?width=108&crop=smart&auto=webp&s=759d95c744e29caa668db6a99fa4050fc0c7b930', 'width': 108}], 'source': {'height': 59,... | |
Why are there no exllamav2 or GPTQ quatschen for llamqfied Qwen 72b chat? | 1 | The details of the model seem to be pretty good and with a context window of 32k, as well as multi language capabilities this model could really be a choice when it comes to a multi tool, that performs on a broad range of tasks.
Usually, it does not take much time for ppl like TheBloke or LoneStriker to drop quants, b... | 2023-12-10T14:47:56 | https://www.reddit.com/r/LocalLLaMA/comments/18f55er/why_are_there_no_exllamav2_or_gptq_quatschen_for/ | Rutabaga-Agitated | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 18f55er | false | null | t3_18f55er | /r/LocalLLaMA/comments/18f55er/why_are_there_no_exllamav2_or_gptq_quatschen_for/ | false | false | self | 1 | null |
Using LLaVA for content moderation | 1 | [removed] | 2023-12-10T14:05:54 | https://www.reddit.com/r/LocalLLaMA/comments/18f4br8/using_llava_for_content_moderation/ | adpq | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 18f4br8 | false | null | t3_18f4br8 | /r/LocalLLaMA/comments/18f4br8/using_llava_for_content_moderation/ | false | false | self | 1 | null |
Are there any good papers or learning resources about system prompts? | 7 | To me it seems like people are just toying around with these randomly even though they are one of the biggest factors in output quality.
For example, this is the recommended system prompt for the excellent OpenHermes-2.5-Mistral-7B:
`"""<|im_start|>system`
`You are a sentient, superintelligent artificial general i... | 2023-12-10T14:02:23 | https://www.reddit.com/r/LocalLLaMA/comments/18f49e2/are_there_any_good_papers_or_learning_resources/ | Dogeboja | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 18f49e2 | false | null | t3_18f49e2 | /r/LocalLLaMA/comments/18f49e2/are_there_any_good_papers_or_learning_resources/ | false | false | self | 7 | null |
Mixtral finetune by fireworks.ai on Poe | 24 | 2023-12-10T13:56:32 | https://poe.com/Mixtral-8x7B-Chat | WaterdanceAC | poe.com | 1970-01-01T00:00:00 | 0 | {} | 18f4583 | false | null | t3_18f4583 | /r/LocalLLaMA/comments/18f4583/mixtral_finetune_by_fireworksai_on_poe/ | false | false | default | 24 | null | |
What are you guys using local LLMs for? | 88 | Just wondering what you guys are doing with these things, is it merely academical? I am a noob in this space trying to learn more.
My main interest in this space atm is with WebLLM, running LLMs on the browser so as to improve UI and maybe even eventually make LLM use free and accessible for everyone. What are you gu... | 2023-12-10T13:55:06 | https://www.reddit.com/r/LocalLLaMA/comments/18f448c/what_are_you_guys_using_local_llms_for/ | C12H16N | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 18f448c | false | null | t3_18f448c | /r/LocalLLaMA/comments/18f448c/what_are_you_guys_using_local_llms_for/ | false | false | self | 88 | null |
help me build my local machine with a 4060ti | 1 | hi guys im building a pc mostly for running llms locally.
first i decided for a gpu since its the most important thing.
gpu: 4060ti 16 gb
whats missing or as to where i dont know what a good addition is is the following :
-motherboard: i prefer one where i could at at least add another card or 4. and where i could ad... | 2023-12-10T13:51:31 | https://www.reddit.com/r/LocalLLaMA/comments/18f41v7/help_me_build_my_local_machine_with_a_4060ti/ | thefunnyape | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 18f41v7 | false | null | t3_18f41v7 | /r/LocalLLaMA/comments/18f41v7/help_me_build_my_local_machine_with_a_4060ti/ | false | false | self | 1 | null |
At this point we don’t necessarily need higher context windows. We need better truncation. | 58 | In a longer discussion, between a LLM and an average user, a 4k context window that manages to retain important details while truncating will be more effective than an 8k context window truncating the entire past discussion.
We need a system that determines what information is important enough to keep within context, ... | 2023-12-10T13:30:52 | https://www.reddit.com/r/LocalLLaMA/comments/18f3o08/at_this_point_we_dont_necessarily_need_higher/ | ZABKA_TM | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 18f3o08 | false | null | t3_18f3o08 | /r/LocalLLaMA/comments/18f3o08/at_this_point_we_dont_necessarily_need_higher/ | false | false | self | 58 | null |
GitHub - Krisseck/php-rag: An AI assistant built with PHP, Solr and LLM backend of choice | 1 | 2023-12-10T13:30:12 | https://github.com/Krisseck/php-rag | Risse | github.com | 1970-01-01T00:00:00 | 0 | {} | 18f3nk1 | false | null | t3_18f3nk1 | /r/LocalLLaMA/comments/18f3nk1/github_krisseckphprag_an_ai_assistant_built_with/ | false | false | 1 | {'enabled': False, 'images': [{'id': '_YWuBjUV8avKlIIPZcGoerc0hK_PvddCRNYRslw3GMA', 'resolutions': [{'height': 54, 'url': 'https://external-preview.redd.it/aVDcfzJ7_Oc-OEU7YPFGL9o31Ko69CIXa1pAC5r3uBQ.jpg?width=108&crop=smart&auto=webp&s=4b18a6c7f338e3f67ca2c5ff1fb1eb78ee986700', 'width': 108}, {'height': 108, 'url': 'h... | ||
So now 7b are better then 70b? | 10 | Now that Mistral 7b and the relative finetunes are the go-to for most of us I'm wondering if there is any 34b@4bit or 70b@ 2.4bpw that it's actually better then those mistral finetune.
Are the available 7b mistral really better then anything else now for 24gb vram?
I have a 4090 and I feel like I'm not pushing it a... | 2023-12-10T11:26:29 | https://www.reddit.com/r/LocalLLaMA/comments/18f1l7g/so_now_7b_are_better_then_70b/ | Lorian0x7 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 18f1l7g | false | null | t3_18f1l7g | /r/LocalLLaMA/comments/18f1l7g/so_now_7b_are_better_then_70b/ | false | false | self | 10 | null |
StrippedHyena | 27 | https://www.together.ai/blog/stripedhyena-7b
Thoughts ?! | 2023-12-10T10:48:36 | https://www.reddit.com/r/LocalLLaMA/comments/18f10i6/strippedhyena/ | True_Giraffe_7712 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 18f10i6 | false | null | t3_18f10i6 | /r/LocalLLaMA/comments/18f10i6/strippedhyena/ | false | false | self | 27 | {'enabled': False, 'images': [{'id': 'BZO-ySPJOe3ai2VIr8zBFqqikgdLZOfIKThn_0kEVcg', 'resolutions': [{'height': 108, 'url': 'https://external-preview.redd.it/L3yyMI1izgGt1JJcrpcieg6JFTv2ruZYrlytjw1rUrM.jpg?width=108&crop=smart&auto=webp&s=300e405f9097d5f047e47ae58121c9408e1299f3', 'width': 108}, {'height': 216, 'url': '... |
PSA: new ExLlamaV2 quant method makes 70Bs perform much better at low bpw quants | 162 | If you have a single 3090 or 4090, chances are you have tried to run a 2.4b-2.65bpw quant of 70B models only to be disappointed by how unstable they tend to be due to their high perplexity.
Good news: Turbo, the author of ExLlamaV2, has made a new quant method that decreases the perplexity of low bpw quants, improving... | 2023-12-10T07:42:21 | https://www.reddit.com/r/LocalLLaMA/comments/18eyf39/psa_new_exllamav2_quant_method_makes_70bs_perform/ | brobruh211 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 18eyf39 | false | null | t3_18eyf39 | /r/LocalLLaMA/comments/18eyf39/psa_new_exllamav2_quant_method_makes_70bs_perform/ | false | false | self | 162 | {'enabled': False, 'images': [{'id': '_rEX1xvwdv17x6NFAWQpYFNONQ0BKA5Qw0Eo0JX0zWU', 'resolutions': [{'height': 58, 'url': 'https://external-preview.redd.it/OFWu5qxCY4R2hQfI_vzWYgK2ON5meupO-ZR0eRPmsP8.jpg?width=108&crop=smart&auto=webp&s=4bc231a80d79babe4e6cddf7b4c71dcb0aa8f8ff', 'width': 108}, {'height': 116, 'url': 'h... |
PSA: new ExLlamaV2 quant method makes 70Bs perform much better on 24GB VRAM | 1 | [removed] | 2023-12-10T07:17:39 | https://www.reddit.com/r/LocalLLaMA/comments/18ey2ox/psa_new_exllamav2_quant_method_makes_70bs_perform/ | MyOrangeApples | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 18ey2ox | false | null | t3_18ey2ox | /r/LocalLLaMA/comments/18ey2ox/psa_new_exllamav2_quant_method_makes_70bs_perform/ | false | false | self | 1 | {'enabled': False, 'images': [{'id': '_rEX1xvwdv17x6NFAWQpYFNONQ0BKA5Qw0Eo0JX0zWU', 'resolutions': [{'height': 58, 'url': 'https://external-preview.redd.it/OFWu5qxCY4R2hQfI_vzWYgK2ON5meupO-ZR0eRPmsP8.jpg?width=108&crop=smart&auto=webp&s=4bc231a80d79babe4e6cddf7b4c71dcb0aa8f8ff', 'width': 108}, {'height': 116, 'url': 'h... |
Is there a glossary of LLM terms? | 13 | Below are some of the terms I have come across while looking at LLM projects and blogs. I am sure there are more. Is there a glossary of these terms or maybe you can list more that I have missed:
Rank
Alpha
Beam search
top-p
top-k
ggml
gguf
lora
gptq | 2023-12-10T06:54:43 | https://www.reddit.com/r/LocalLLaMA/comments/18exqgv/is_there_a_glossary_of_llm_terms/ | soham1996 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 18exqgv | false | null | t3_18exqgv | /r/LocalLLaMA/comments/18exqgv/is_there_a_glossary_of_llm_terms/ | false | false | self | 13 | null |
LLMS4Rec through RAG? | 5 | I recently came across [LLM4Rec-Awesome](https://github.com/WLiK/LLM4Rec-Awesome-Papers) and felt inspired to build something small based on some of those papers-- essentially, it will be a RAG-powered, recommendation engine for games (and eventually much more).
The approach focuses heavily on input standardization--... | 2023-12-10T05:36:22 | https://www.reddit.com/r/LocalLLaMA/comments/18ewk5b/llms4rec_through_rag/ | LyPreto | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 18ewk5b | false | null | t3_18ewk5b | /r/LocalLLaMA/comments/18ewk5b/llms4rec_through_rag/ | false | false | self | 5 | {'enabled': False, 'images': [{'id': '8WYCF9fd1fbmi6X0ClqQlR4UqNJcJ68gufyc3-XqTN0', 'resolutions': [{'height': 54, 'url': 'https://external-preview.redd.it/8dpTYyrh8TZawgwwd6Ve4U1_aubVLvsS96GhLn8PXsc.jpg?width=108&crop=smart&auto=webp&s=168a93dc5170ea25e6f5f8aa4c0bbbb038772d3e', 'width': 108}, {'height': 108, 'url': 'h... |
Need urgent help: Lllama-2-7b-chat llamacpp finetuning | 1 | I used this command:
llama.cpp/finetune \\
\--model-base $model\_path \\
\--train-data $datadir \\
\--lora-out $new\_model\_path \\
\--save-every 0 \\
\--threads 40 \\
\--ctx 4096 \\
\--rope-freq-base 10000 \\
\--rope-freq-scale 1.0 \\
\--batch 1 \\
\--grad-acc 1 \\
\--adam-iter 3099 \\... | 2023-12-10T04:53:00 | https://www.reddit.com/r/LocalLLaMA/comments/18evutu/need_urgent_help_lllama27bchat_llamacpp_finetuning/ | Key_Arugula_721 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 18evutu | false | null | t3_18evutu | /r/LocalLLaMA/comments/18evutu/need_urgent_help_lllama27bchat_llamacpp_finetuning/ | false | false | self | 1 | null |
shinning the spotlight on CogVLM | 31 | I was casually sifting through the [llama.cpp discussions](https://github.com/ggerganov/llama.cpp/discussions/categories/general) when i found a particularly interesting [conversation](https://github.com/ggerganov/llama.cpp/discussions/4350).
\--------
**TL;DR (if you don't want to sift through the conversation):**
... | 2023-12-10T04:50:36 | https://www.reddit.com/r/LocalLLaMA/comments/18evtgp/shinning_the_spotlight_on_cogvlm/ | LyPreto | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 18evtgp | false | null | t3_18evtgp | /r/LocalLLaMA/comments/18evtgp/shinning_the_spotlight_on_cogvlm/ | false | false | self | 31 | {'enabled': False, 'images': [{'id': 'DJPqvteONpGwVVw6LzaG6b8vlDa2rv2hETCaqe0z57s', 'resolutions': [{'height': 54, 'url': 'https://external-preview.redd.it/wyCM1fHzTa-IIqHgS1QTxdSYNXn668elDj0WmYMPf_k.jpg?width=108&crop=smart&auto=webp&s=d6fa197328d583bcae7a764b40fd1214265b6852', 'width': 108}, {'height': 108, 'url': 'h... |
Anyone playing around with the Starling 7B fine tune model or dataset? | 9 | It seems (based on chatbot arena Elo and MT bench scores) like an intriguing (if stodgy) fine tune and dataset. Having seven AI scored answers to over 100K prompts in the dataset seems like it would give the model a pretty clear idea of what GPT-4 thinks is the best answer to a wide variety of prompts. Any experimenter... | 2023-12-10T04:29:39 | https://www.reddit.com/r/LocalLLaMA/comments/18evhb2/anyone_playing_around_with_the_starling_7b_fine/ | WaterdanceAC | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 18evhb2 | false | null | t3_18evhb2 | /r/LocalLLaMA/comments/18evhb2/anyone_playing_around_with_the_starling_7b_fine/ | false | false | self | 9 | {'enabled': False, 'images': [{'id': 'MkPeBvU3WVFIry5Ow6_NGccUwNW-5VNr5a9-aLl22oE', 'resolutions': [{'height': 58, 'url': 'https://external-preview.redd.it/s0XUwHQwrVUYWPx2yMh-TgB49PUYfXtuc1NY9XKN_oY.jpg?width=108&crop=smart&auto=webp&s=e3b1bb2daa788a68756f939b39227b6698f780a5', 'width': 108}, {'height': 116, 'url': 'h... |
Do you run your LLM on your hardware or in a VM? | 4 | Is it always faster on hardware rather than in a VM? But didn't clog up the OS when runs in a VM? Any suggestions? | 2023-12-10T04:05:42 | https://www.reddit.com/r/LocalLLaMA/comments/18ev34i/do_you_run_your_llm_on_your_hardware_or_in_a_vm/ | DuckFormer | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 18ev34i | false | null | t3_18ev34i | /r/LocalLLaMA/comments/18ev34i/do_you_run_your_llm_on_your_hardware_or_in_a_vm/ | false | false | self | 4 | null |
SuperDuperDB - how to use it to talk to your documents locally using llama 7B or Mistral 7B? | 1 | https://github.com/SuperDuperDB/superduperdb
This has just been released few days ago and trending in github for LLM/AI category.
Would like to ask if anyone tried to use it to perform inferencing on your documents? Say 10 pages of text. How did it go? I'm planning to use LLAMA 2 7B or mistral 7B for it? | 2023-12-10T03:47:58 | https://www.reddit.com/r/LocalLLaMA/comments/18eusc8/superduperdb_how_to_use_it_to_talk_to_your/ | vlodia | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 18eusc8 | false | null | t3_18eusc8 | /r/LocalLLaMA/comments/18eusc8/superduperdb_how_to_use_it_to_talk_to_your/ | false | false | self | 1 | {'enabled': False, 'images': [{'id': 'Dm5OzYBAS-qzFRjPkJ4vzFTkoenLemIsEb4OJX6z6FQ', 'resolutions': [{'height': 54, 'url': 'https://external-preview.redd.it/6QlF-fcns_8JEM8aqZb1K110slWxYPXDHSs7GvEpDvQ.jpg?width=108&crop=smart&auto=webp&s=fe78d32a43569da51807866133ba782442e90225', 'width': 108}, {'height': 108, 'url': 'h... |
A fun experiment running concurrent inference in multiple MacBook Pro's to evaluate model and hardware performance. M2 Max 64GB (34B model) vs M3 Max 128GB (67B model) | 12 | I setup a feature to run concurrent inference workflows against multiple hosts. The UI only supports two for now but I will be scaling this as the project matures. This is just a fun experiment to evaluate the responses from different models in real time. I am actually surprised at how the M3 running a model twice the ... | 2023-12-10T03:09:48 | https://www.reddit.com/r/LocalLLaMA/comments/18eu5f1/a_fun_experiment_running_concurrent_inference_in/ | LocoMod | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 18eu5f1 | false | null | t3_18eu5f1 | /r/LocalLLaMA/comments/18eu5f1/a_fun_experiment_running_concurrent_inference_in/ | false | false | self | 12 | null |
Inference and Evaluation of Mistral AI's MoE model(Mixtral-8x7b-32kseqlen) | 31 | \- Inference and evaluation code of Mistral MoE(Mixtral-8x7b-32kseqlen)
[https://github.com/open-compass/MixtralKit](https://github.com/open-compass/MixtralKit)
​
\- Evaluation performance will updated soon. | 2023-12-10T03:03:28 | https://www.reddit.com/r/LocalLLaMA/comments/18eu1kb/inference_and_evaluation_of_mistral_ais_moe/ | No_Competition_7372 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 18eu1kb | false | null | t3_18eu1kb | /r/LocalLLaMA/comments/18eu1kb/inference_and_evaluation_of_mistral_ais_moe/ | false | false | self | 31 | {'enabled': False, 'images': [{'id': 'N-TaxDA82QwjJPSKD3xjtb6Sgr7qALGw-OrZYpo-9Ng', 'resolutions': [{'height': 54, 'url': 'https://external-preview.redd.it/R9e5lQq4rzsA56w55vbJDETNkSf9qtp6FzhLrtNjfj4.jpg?width=108&crop=smart&auto=webp&s=54640d3a14b650402ef364bbe07f03cefae379b4', 'width': 108}, {'height': 108, 'url': 'h... |
Why llama, yi, qwen, their official chat worse than its base in benchmarks, and some fine-tune stuff are better? is meta dumb? | 3 | is align tax a huge lie? | 2023-12-10T02:59:49 | https://www.reddit.com/r/LocalLLaMA/comments/18etz15/why_llama_yi_qwen_their_official_chat_worse_than/ | No-Link-2778 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 18etz15 | false | null | t3_18etz15 | /r/LocalLLaMA/comments/18etz15/why_llama_yi_qwen_their_official_chat_worse_than/ | false | false | self | 3 | null |
Question about models from newbie. | 3 | I was using dolphin-2.2.1-mistral-7b.Q5\_K\_S.gguf and it was not really bad, but I wanted better. I have tried a couple of 13B models like Wizard-Vicuna-13B-Uncensored.Q5\_K\_S.gguf and amethyst-13b-mistral.Q3\_K\_L.gguf, and result is honestly just worse. Worse quality, longer generation. I was thinking about upgradi... | 2023-12-10T02:22:07 | https://www.reddit.com/r/LocalLLaMA/comments/18etbqi/question_about_models_from_newbie/ | Deep-Yoghurt878 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 18etbqi | false | null | t3_18etbqi | /r/LocalLLaMA/comments/18etbqi/question_about_models_from_newbie/ | false | false | self | 3 | null |
Good models to run on a GTX 1660 with Ryzen 2950 Threadripper? | 1 | By “good” I mean practical, like you can ask it to do stuff and it gives useful answers instead of hot 🗑 | 2023-12-10T02:19:54 | https://www.reddit.com/r/LocalLLaMA/comments/18eta8x/good_models_to_run_on_a_gtx_1660_with_ryzen_2950/ | LeastWest9991 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 18eta8x | false | null | t3_18eta8x | /r/LocalLLaMA/comments/18eta8x/good_models_to_run_on_a_gtx_1660_with_ryzen_2950/ | false | false | self | 1 | null |
What is going on with Mistral 7b finetunes? (Equal to Qwen 72b) | 30 | Lately, every day there has been a new 7b finetune of Mistral that has beaten the last by a noticeable amount on the open LLM leaderboard. The top finetune went from 'Starling' to 'NeuralHermes-2.5' to 'OpenHermes-2.5-neural-chat' to 'DPOpenHermes' to 'MetaMath-Cybertron-Starling', and now 'go-bruins', which has a near... | 2023-12-10T02:15:39 | https://www.reddit.com/r/LocalLLaMA/comments/18et7h9/what_is_going_on_with_mistral_7b_finetunes_equal/ | DontPlanToEnd | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 18et7h9 | false | null | t3_18et7h9 | /r/LocalLLaMA/comments/18et7h9/what_is_going_on_with_mistral_7b_finetunes_equal/ | false | false | self | 30 | null |
RAG example with llama.cpp, LiteLLM and Mamba Chat | 26 | 2023-12-10T02:07:39 | https://neuml.hashnode.dev/integrate-llm-frameworks | davidmezzetti | neuml.hashnode.dev | 1970-01-01T00:00:00 | 0 | {} | 18et2be | false | null | t3_18et2be | /r/LocalLLaMA/comments/18et2be/rag_example_with_llamacpp_litellm_and_mamba_chat/ | false | false | 26 | {'enabled': False, 'images': [{'id': '7M0dwTYeAupbhUnTCO3MtN3YeIjFrAZaTyazieQoUJg', 'resolutions': [{'height': 56, 'url': 'https://external-preview.redd.it/KKgwERriw_FiuVuLRPiiIiItfIHuz7dUrQy9AV0JhZY.jpg?width=108&crop=smart&auto=webp&s=8332196eac0d18da2c083b3a8ef1de2a1a62bfbe', 'width': 108}, {'height': 113, 'url': 'h... | ||
What is your motive for running open-source models, instead of just using a ready-made solution like GPT-4? | 98 | Is it curiosity? A desire for privacy? Greater customizability and control?
I am new to this space and curious about the reasons to use open-source LLMs. | 2023-12-10T01:05:42 | https://www.reddit.com/r/LocalLLaMA/comments/18erxfd/what_is_your_motive_for_running_opensource_models/ | LeastWest9991 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 18erxfd | false | null | t3_18erxfd | /r/LocalLLaMA/comments/18erxfd/what_is_your_motive_for_running_opensource_models/ | false | false | self | 98 | null |
I have a 3080 and just bought a 3090 - is it worth me keeping both? | 2 | So I've been running LLMs on my 10GB 3080 for a while but I keep hitting memory limits so I thought it's finally time to bite the bullet and get a 3090, which I got a good deal with on a used one on ebay.
I was planning on selling the 3080 to cover some of that cost, but now I'm wondering is there anything I can do wi... | 2023-12-10T00:58:19 | https://www.reddit.com/r/LocalLLaMA/comments/18ersaj/i_have_a_3080_and_just_bought_a_3090_is_it_worth/ | CrasHthe2nd | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 18ersaj | false | null | t3_18ersaj | /r/LocalLLaMA/comments/18ersaj/i_have_a_3080_and_just_bought_a_3090_is_it_worth/ | false | false | self | 2 | null |
Finetunes and datasets to add onto mixture-of-expert models? | 2 | Mixture or collection of experts, whatever you want to call it.
This might be a challenge to make universal datasets to train and finetune with since the number of experts might vary, and their specialties might vary too.
Anyone who wants to have a universal dataset to throw on every multi-expert model might have to ... | 2023-12-10T00:41:56 | https://www.reddit.com/r/LocalLLaMA/comments/18erh83/finetunes_and_datasets_to_add_onto/ | -Automaticity | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 18erh83 | false | null | t3_18erh83 | /r/LocalLLaMA/comments/18erh83/finetunes_and_datasets_to_add_onto/ | false | false | self | 2 | null |
Aurelian: 70B 32K story-writing (and more) [Alpha] | 42 | A while ago, I posted about [ways of training 70B 32K LORAs on Llama-2](https://www.reddit.com/r/LocalLLaMA/comments/16euhw5/training_long_context_32k_70b_llama/), and some people seemed interested in an actual 32K 70B fine-tune.
**This is an alpha release for testing & feedback, there are known issues** (see known is... | 2023-12-09T23:48:34 | https://www.reddit.com/r/LocalLLaMA/comments/18eqfqd/aurelian_70b_32k_storywriting_and_more_alpha/ | Grimulkan | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 18eqfqd | false | null | t3_18eqfqd | /r/LocalLLaMA/comments/18eqfqd/aurelian_70b_32k_storywriting_and_more_alpha/ | false | false | self | 42 | {'enabled': False, 'images': [{'id': 'MCalqV1HoBH4FiM21SoIO1zmo1rxabGTtYiIG6z6kb8', 'resolutions': [{'height': 58, 'url': 'https://external-preview.redd.it/fjdJI20wZWeLaGoZI92qXakf5wHbS1sxCDfcogGIEVY.jpg?width=108&crop=smart&auto=webp&s=4a1b4c5ab08a12413dc526402ff94dcd7b014072', 'width': 108}, {'height': 116, 'url': 'h... |
Overview of OS-LLM architecture and how to take things to the next level | 19 | Disclaimer: I've been studying this stuff for a while but I'm not an expert so please forgive any mistakes.
---
There are an awful lot of models out there, and an awful lot of innovations to implement and combine. I want to discuss the state of the art, what is possible with minimal work, what is possible with some ... | 2023-12-09T22:19:46 | https://www.reddit.com/r/LocalLLaMA/comments/18eome3/overview_of_osllm_architecture_and_how_to_take/ | EvokerTCG | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 18eome3 | false | null | t3_18eome3 | /r/LocalLLaMA/comments/18eome3/overview_of_osllm_architecture_and_how_to_take/ | false | false | self | 19 | null |
Is there any open source app to load a model and expose API like OpenAI? | 23 | 99% of my usage of local LLMs is via API.
I have created my own, but with all the advancement it is hard to keep up to date. I also use r/Oobabooga for quick demos.
I am wondering if there isn't some OS project that is entirely focused on exposing API to interact with an LLM. | 2023-12-09T22:09:33 | https://www.reddit.com/r/LocalLLaMA/comments/18eoeti/is_there_any_open_source_app_to_load_a_model_and/ | Ion_GPT | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 18eoeti | false | null | t3_18eoeti | /r/LocalLLaMA/comments/18eoeti/is_there_any_open_source_app_to_load_a_model_and/ | false | false | self | 23 | null |
RAG for image question answering | 5 | Hi,
Has anyone seen anything related to using a RAG based solution with a vision model to answer specific questions about an image? I’m looking to answer questions about the price of merchandise in an image of a store by using a price menu as the reference document.
Thanks! | 2023-12-09T21:12:03 | https://www.reddit.com/r/LocalLLaMA/comments/18en7pi/rag_for_image_question_answering/ | loslow34 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 18en7pi | false | null | t3_18en7pi | /r/LocalLLaMA/comments/18en7pi/rag_for_image_question_answering/ | false | false | self | 5 | null |
Yi Context Length | 3 | I’m looking at this list: https://ollama.ai/library/yi/tags
This may be a dumb questions but are the only versions capable of 200k context size the ones labeled as such? In which case, only the 6B versions have that?
I have the memory to run any of these. Trying to get summaries of docs 10,000-15,000 words long. | 2023-12-09T20:54:35 | https://www.reddit.com/r/LocalLLaMA/comments/18emuj7/yi_context_length/ | Hinged31 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 18emuj7 | false | null | t3_18emuj7 | /r/LocalLLaMA/comments/18emuj7/yi_context_length/ | false | false | self | 3 | {'enabled': False, 'images': [{'id': 'krjt_5uhqcaDfYjfO7lkezThehav9cAIRJgcK-OKAmM', 'resolutions': [{'height': 56, 'url': 'https://external-preview.redd.it/s0D7i4Rco0trWh9Bu1uEkgnoJJLA3UNKUA9vs57seII.jpg?width=108&crop=smart&auto=webp&s=53486800d92d75b19d59502534fa9ba2785c14b0', 'width': 108}, {'height': 113, 'url': 'h... |
TinyLlama - Any news? | 26 | Do any of you know what's up with the current TinyLlama checkpoint ( -intermediate-2T tokens)? It is now four days delayed.
Would be glad if someone could provide more info. I've also looked at the progress on w&b, but unfortunately I'm not getting any clearer and I can't quite understand this interim correction there... | 2023-12-09T20:23:20 | https://www.reddit.com/r/LocalLLaMA/comments/18em6r9/tinyllama_any_news/ | Evening_Ad6637 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 18em6r9 | false | null | t3_18em6r9 | /r/LocalLLaMA/comments/18em6r9/tinyllama_any_news/ | false | false | self | 26 | null |
LLMs in the middle: Content-aware browser filters for social media | 22 | 2023-12-09T20:05:03 | https://karimjedda.com/llms-in-the-middle-content-aware-client-side-filtering/ | kaiserk13 | karimjedda.com | 1970-01-01T00:00:00 | 0 | {} | 18elso2 | false | null | t3_18elso2 | /r/LocalLLaMA/comments/18elso2/llms_in_the_middle_contentaware_browser_filters/ | false | false | 22 | {'enabled': False, 'images': [{'id': 'es03BSmKZSqRZxBY60FeyYuBDIhNmpdTYsk8GdRCduw', 'resolutions': [{'height': 57, 'url': 'https://external-preview.redd.it/3XEnZR-45OLspj2MVH3b_oOGjkDMDfxx75rH3f2gDBg.jpg?width=108&crop=smart&auto=webp&s=4a5ffa408801bd323ab41379397c59ed82da07e6', 'width': 108}, {'height': 114, 'url': 'h... | ||
DIY converting safetensors format to GGUF on a Mac | 15 | I have a Mac Studio M2 128GB that I've been using with great results lately. It's been much faster than running models on my machine with a single 4090.
But lately, I've been wanting to try several new models that TheBloke hasn't gotten around to converting to GGUF yet.
As it turns out, I didn't have to wait.
### Re... | 2023-12-09T19:56:47 | https://www.reddit.com/r/LocalLLaMA/comments/18elm98/diy_converting_safetensors_format_to_gguf_on_a_mac/ | Sakedo | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 18elm98 | false | null | t3_18elm98 | /r/LocalLLaMA/comments/18elm98/diy_converting_safetensors_format_to_gguf_on_a_mac/ | false | false | self | 15 | {'enabled': False, 'images': [{'id': 'DJPqvteONpGwVVw6LzaG6b8vlDa2rv2hETCaqe0z57s', 'resolutions': [{'height': 54, 'url': 'https://external-preview.redd.it/wyCM1fHzTa-IIqHgS1QTxdSYNXn668elDj0WmYMPf_k.jpg?width=108&crop=smart&auto=webp&s=d6fa197328d583bcae7a764b40fd1214265b6852', 'width': 108}, {'height': 108, 'url': 'h... |
Open Inference Engine Comparison | Features and Functionality of TGI, vLLM, llama.cpp, and TensorRT-LLM | 19 | 2023-12-09T19:33:26 | https://github.com/lapp0/lm-inference-engines/ | andrewlapp | github.com | 1970-01-01T00:00:00 | 0 | {} | 18el4gn | false | null | t3_18el4gn | /r/LocalLLaMA/comments/18el4gn/open_inference_engine_comparison_features_and/ | false | false | 19 | {'enabled': False, 'images': [{'id': 'QcoAuD6nN6iY47Y1pZuMjDzBToFqRjSHiJ6b37CV1ic', 'resolutions': [{'height': 54, 'url': 'https://external-preview.redd.it/uLnQ96wmcwfC9lp72bR-0F2y6HPbhYWniv4U1LTpM5c.jpg?width=108&crop=smart&auto=webp&s=c4c8a7f0d8eda75a3f075cf940cbccc4a00af35b', 'width': 108}, {'height': 108, 'url': 'h... | ||
Estimate price-per-token / inference cost for locally deployed models accessible via API | 1 | [removed] | 2023-12-09T19:32:48 | https://www.reddit.com/r/LocalLLaMA/comments/18el3zd/estimate_pricepertoken_inference_cost_for_locally/ | Greg_Z_ | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 18el3zd | false | null | t3_18el3zd | /r/LocalLLaMA/comments/18el3zd/estimate_pricepertoken_inference_cost_for_locally/ | false | false | self | 1 | null |
Fine-tuned DiscoLM Mixtral model after only 24 hours! | 167 | 2023-12-09T19:18:52 | https://huggingface.co/DiscoResearch/DiscoLM-mixtral-8x7b-v2 | jd_3d | huggingface.co | 1970-01-01T00:00:00 | 0 | {} | 18ektd7 | false | null | t3_18ektd7 | /r/LocalLLaMA/comments/18ektd7/finetuned_discolm_mixtral_model_after_only_24/ | false | false | 167 | {'enabled': False, 'images': [{'id': 'oQNhmIAEIIxFvzbRgVH-KHgMxTIHGWfRZoPfHNwUcLs', 'resolutions': [{'height': 58, 'url': 'https://external-preview.redd.it/wcPMlqSjrue99vHhUC9DnoBHBnBuhMagJ57CXns24PI.jpg?width=108&crop=smart&auto=webp&s=c66c2ff5a8160be1e9c2b19dc70a468ce0aba03c', 'width': 108}, {'height': 116, 'url': 'h... | ||
What is fblgit/una Unified Neural Alignment? Looks like cheating on testset and overfitting. | 13 | Those UNA-\*models have high TruthfulQA and ARC, but hallucinating much worse than those normal models.
And fblgit, this guy is hiding something - "What is UNA? A formula & A technique to TAME models"
We have no idea what UNA is, and he preferred not to say.
​
>Funded by Cybertron's H100's with few hours tra... | 2023-12-09T18:36:34 | https://www.reddit.com/r/LocalLLaMA/comments/18ejwm1/what_is_fblgituna_unified_neural_alignment_looks/ | PuzzledTeam5961 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 18ejwm1 | false | null | t3_18ejwm1 | /r/LocalLLaMA/comments/18ejwm1/what_is_fblgituna_unified_neural_alignment_looks/ | false | false | self | 13 | {'enabled': False, 'images': [{'id': 'E52zxkgIQ4erLeto4AhQQwIDH-4S-D7pyYegSKhUC3Y', 'resolutions': [{'height': 58, 'url': 'https://external-preview.redd.it/pX1sM-1B5Q7cYzBztyqS3kCWYJKD4n6j9K-WJrDmC10.jpg?width=108&crop=smart&auto=webp&s=11874a81c84f6ac8d6af4cd02b91b763e5aa9e63', 'width': 108}, {'height': 116, 'url': 'h... |
Memory Requirements for Training Over Time | 1 | I’m generally aware of decreasing memory requirements overtime with the introduction of various quantization levels, or approaches such as LoRA. Does anyone know of a longitudinal measure of requirements? E.g. when llama first came out what was the card size required, versus now? My Google Fu is failing me on this. | 2023-12-09T18:26:27 | https://www.reddit.com/r/LocalLLaMA/comments/18ejoq4/memory_requirements_for_training_over_time/ | Mbando | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 18ejoq4 | false | null | t3_18ejoq4 | /r/LocalLLaMA/comments/18ejoq4/memory_requirements_for_training_over_time/ | false | false | self | 1 | null |
LLava 1.5 13b on LM studio | 1 | [removed] | 2023-12-09T17:06:36 | https://www.reddit.com/r/LocalLLaMA/comments/18ehzjk/llava_15_13b_on_lm_studio/ | danilo139hg | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 18ehzjk | false | null | t3_18ehzjk | /r/LocalLLaMA/comments/18ehzjk/llava_15_13b_on_lm_studio/ | false | false | 1 | null | |
People who've used RWKV, whats your wishlist for it? | 29 | Seeing the recent outburst of new ssms, thought I'd ask people what their wishlist for rwkv was.
Most of the releases bench against rwkv v4, therefore making themselves look better, but with rwkv5, its 3b matches mamba 3b, and its 7b matches striped hyena 7b base, but is worse than the special tek finetune. all the rw... | 2023-12-09T16:37:51 | https://www.reddit.com/r/LocalLLaMA/comments/18ehd9z/people_whove_used_rwkv_whats_your_wishlist_for_it/ | vatsadev | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 18ehd9z | false | null | t3_18ehd9z | /r/LocalLLaMA/comments/18ehd9z/people_whove_used_rwkv_whats_your_wishlist_for_it/ | false | false | self | 29 | null |
Metacall.io running inside of llama.cpp | 2 | [removed] | 2023-12-09T16:35:17 | introsp3ctor | i.redd.it | 1970-01-01T00:00:00 | 0 | {} | 18ehbc7 | false | null | t3_18ehbc7 | /r/LocalLLaMA/comments/18ehbc7/metacallio_running_inside_of_llamacpp/ | false | false | 2 | {'enabled': True, 'images': [{'id': 'vtqsnhZYj90YNMewztStAY-5MZMkAlGzRefb5V9afQU', 'resolutions': [{'height': 52, 'url': 'https://preview.redd.it/l3wk0jaara5c1.jpg?width=108&crop=smart&auto=webp&s=a3870b51f252416e6a63e6eee1e5d187b86c7c56', 'width': 108}, {'height': 104, 'url': 'https://preview.redd.it/l3wk0jaara5c1.jpg... | ||
Compare a 5 page document against a 20 page code of conduct? | 3 | I pay my lovely £20 ChatGPT fee for one singular purpose.
I have a GPT which contains maybe 10 PDFs at most. One is a code of conduct, one is what a “work document” should contain, a sort of checklist. And the rest are documents on different aspects of a topic. For example maybe one is a document that contains 20 pag... | 2023-12-09T16:21:54 | https://www.reddit.com/r/LocalLLaMA/comments/18eh12r/compare_a_5_page_document_against_a_20_page_code/ | michaelsgoneinsane | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 18eh12r | false | null | t3_18eh12r | /r/LocalLLaMA/comments/18eh12r/compare_a_5_page_document_against_a_20_page_code/ | false | false | self | 3 | null |
Mixtral: A Promising Model with Unforeseen Challenges | 166 | I was able to spend significant time yesterday testing Mistral in a plethora of ways. If you go into it with high hopes off the bat, you are going to be disappointed. Just putting that out there upfront. There are bugs with this model. Why are those bugs there though, and are they fixable? Possibly, possibly not. This ... | 2023-12-09T16:15:34 | https://www.reddit.com/r/LocalLLaMA/comments/18egw8i/mixtral_a_promising_model_with_unforeseen/ | Fantastic-Ninja3839 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 18egw8i | false | null | t3_18egw8i | /r/LocalLLaMA/comments/18egw8i/mixtral_a_promising_model_with_unforeseen/ | false | false | self | 166 | null |
Using Llama Guard to moderate user/agent interaction from ChatGPT | 1 | [removed] | 2023-12-09T16:03:44 | https://www.reddit.com/r/LocalLLaMA/comments/18egn91/using_llama_guard_to_moderate_useragent/ | InevitableSky2801 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 18egn91 | false | null | t3_18egn91 | /r/LocalLLaMA/comments/18egn91/using_llama_guard_to_moderate_useragent/ | false | false | self | 1 | {'enabled': False, 'images': [{'id': 'nkhh65ujo5BznFJFojoMPaKjGuLSpPj6KGhRov-ykOg', 'resolutions': [{'height': 108, 'url': 'https://external-preview.redd.it/0-fRWqjlLadVXj5pfYp4_Oe3xgBWE-_rdjVSn7hlohI.jpg?width=108&crop=smart&auto=webp&s=f34d2dfdbbfa7de0f1956f186fd8430ee96a1a55', 'width': 108}, {'height': 216, 'url': '... |
aphrodite (help) | 2 | i installed aphrodite engine and installed everything, what do i do now, do i write a command, because im stuck in the script.
​ | 2023-12-09T14:54:28 | https://www.reddit.com/r/LocalLLaMA/comments/18ef7z2/aphrodite_help/ | Oorage420 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 18ef7z2 | false | null | t3_18ef7z2 | /r/LocalLLaMA/comments/18ef7z2/aphrodite_help/ | false | false | self | 2 | null |
Looking for Paper about LLM Fine Tuning for specific topic / Alignment Paper | 2 | Hi, I am new to LLM and I am trying to fine tune a 7B model to understand about one specific topic only as chat assistant (pretty much like everyone is trying to do). All guide I can find is just to make a diverse. But how diverse is it, what kind of diverse?
Due to my limited knowledge, I could not find any paper/res... | 2023-12-09T14:50:52 | https://www.reddit.com/r/LocalLLaMA/comments/18ef5j9/looking_for_paper_about_llm_fine_tuning_for/ | nggakmakasih | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 18ef5j9 | false | null | t3_18ef5j9 | /r/LocalLLaMA/comments/18ef5j9/looking_for_paper_about_llm_fine_tuning_for/ | false | false | self | 2 | {'enabled': False, 'images': [{'id': 'q3evP6JeDpAC2MdSQHWYxnCYTqbJkElIQsLFqVSdkss', 'resolutions': [{'height': 63, 'url': 'https://external-preview.redd.it/izh8gZHY4FqZ1nwtU1N_TjtohUCNuvTyMn90toXda80.jpg?width=108&crop=smart&auto=webp&s=bc9575b410002edc2df3c5b5b0355fefedc7baa8', 'width': 108}, {'height': 126, 'url': 'h... |
Any recommendations for cloud services to host llms? | 2 | Could you recommend a service, where you can use all these models (preferably also image generation)? | 2023-12-09T14:01:44 | https://www.reddit.com/r/LocalLLaMA/comments/18ee823/any_recommendations_for_cloud_services_to_host/ | Wonderful-Eye-71 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 18ee823 | false | null | t3_18ee823 | /r/LocalLLaMA/comments/18ee823/any_recommendations_for_cloud_services_to_host/ | false | false | self | 2 | null |
Patiently Lurking from the Shadows | 12 | https://huggingface.co/TheBloke/mixtral-7B-8expert-GPTQ/tree/main
The title is an original masterpiece of my own wetware llm. | 2023-12-09T14:01:22 | https://www.reddit.com/r/LocalLLaMA/comments/18ee7ry/patiently_lurking_from_the_shadows/ | shaman-warrior | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 18ee7ry | false | null | t3_18ee7ry | /r/LocalLLaMA/comments/18ee7ry/patiently_lurking_from_the_shadows/ | false | false | self | 12 | {'enabled': False, 'images': [{'id': '1tbQJmXKdfQqef0fnT21qOI8R8AMpcfEwW28TVqiBhA', 'resolutions': [{'height': 58, 'url': 'https://external-preview.redd.it/OdYeu0QH8G23X2-o5Ro2fzTuiLHNRm8N57peTW4WrH8.jpg?width=108&crop=smart&auto=webp&s=a3fe267b9625e4f6261e67ef041e96dcbc2ed9e2', 'width': 108}, {'height': 116, 'url': 'h... |
Loquace-7B-Mistral - An Italian speaking LLM good at following instructions. | 31 | Hi Everyone,
I just released the new version of the Loquace Family model, a project that started in the beginning of 2023 with the aim of democratizing LLMs in Italy.
It's a 7B fine-tuned instruct version of Mistral with 2k of context. It's not intended to be used as a chatbot but performs pretty well in NLP tasks. I... | 2023-12-09T13:30:05 | https://www.reddit.com/r/LocalLLaMA/comments/18edn1w/loquace7bmistral_an_italian_speaking_llm_good_at/ | cosimoiaia | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 18edn1w | false | null | t3_18edn1w | /r/LocalLLaMA/comments/18edn1w/loquace7bmistral_an_italian_speaking_llm_good_at/ | false | false | self | 31 | {'enabled': False, 'images': [{'id': 'Cn8DKZUElxbYbUJ2gm-qzOxWVae7Apcn-QB2mtmsLu4', 'resolutions': [{'height': 58, 'url': 'https://external-preview.redd.it/bRZUhx1xYNQx6KAXrSfPPPgn-n2N4qVXvCkz2_4uZy4.jpg?width=108&crop=smart&auto=webp&s=09d44e2844fa091d14b06cda9224e39dc60e31aa', 'width': 108}, {'height': 116, 'url': 'h... |
Unit tests feedback loop | 2 | Have you setup a feedback loop system with your local llama?
like give prompt for creating code for a task, then automatically unit test the result from the model. If it is failed give the error back to the model ask to correct it.
And repeat the process until unit test successfull.
With langchain etc..? | 2023-12-09T13:16:01 | https://www.reddit.com/r/LocalLLaMA/comments/18ede3y/unit_tests_feedback_loop/ | troposfer | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 18ede3y | false | null | t3_18ede3y | /r/LocalLLaMA/comments/18ede3y/unit_tests_feedback_loop/ | false | false | self | 2 | null |
I see the term "State of the Art" thrown around a lot. In the context of LLMs (or related algorithms like quantization), does that mean anything specific, or is it more of a buzz word? | 15 | What are the criteria for something to be SOTA or not? Who decides this? Can it be tested? Do I have enough body text yet? | 2023-12-09T13:12:43 | https://www.reddit.com/r/LocalLLaMA/comments/18edc07/i_see_the_term_state_of_the_art_thrown_around_a/ | Misha_Vozduh | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 18edc07 | false | null | t3_18edc07 | /r/LocalLLaMA/comments/18edc07/i_see_the_term_state_of_the_art_thrown_around_a/ | false | false | self | 15 | null |
Freeing VRAM with ollama | 6 | Hi chaps,
I'm loving ollama, but am curious if theres anyway to free/unload a model after it has been loaded - otherwise I'm stuck in a state with 90% of my VRAM utilized. Do I need to shutdown the systemd service?
Would be nice if there was a way to do it from the CLI... | 2023-12-09T13:09:10 | https://www.reddit.com/r/LocalLLaMA/comments/18ed9tr/freeing_vram_with_ollama/ | tlonny | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 18ed9tr | false | null | t3_18ed9tr | /r/LocalLLaMA/comments/18ed9tr/freeing_vram_with_ollama/ | false | false | self | 6 | null |
webui similar to chatgpt | 1 | Does anyone knows if there is one similar and easy to use like chatgpt interface? | 2023-12-09T12:58:40 | https://www.reddit.com/r/LocalLLaMA/comments/18ed36i/webui_similar_to_chatgpt/ | Desire-Protection | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 18ed36i | false | null | t3_18ed36i | /r/LocalLLaMA/comments/18ed36i/webui_similar_to_chatgpt/ | false | false | self | 1 | null |
Which model will gives the fastest results (like turbo) ? | 9 | hi,
I'm having hard time to identify a comparison of the models performances based on completion speed. Do you know any benchmark?
Many thanks to the community. | 2023-12-09T12:20:44 | https://www.reddit.com/r/LocalLLaMA/comments/18ech8a/which_model_will_gives_the_fastest_results_like/ | rmsisme | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 18ech8a | false | null | t3_18ech8a | /r/LocalLLaMA/comments/18ech8a/which_model_will_gives_the_fastest_results_like/ | false | false | self | 9 | null |
Absolutely exceeded our expectations and we got so many compliments. | 1 | 2023-12-09T12:00:34 | Cute_Hovercraft_1436 | i.redd.it | 1970-01-01T00:00:00 | 0 | {} | 18ec5qp | false | null | t3_18ec5qp | /r/LocalLLaMA/comments/18ec5qp/absolutely_exceeded_our_expectations_and_we_got/ | false | false | 1 | {'enabled': True, 'images': [{'id': '6e6ALjheGVcciVcm8ik4xG_vS_MXDTSpUK8M-uv0xy8', 'resolutions': [{'height': 96, 'url': 'https://preview.redd.it/mid1zu59e95c1.png?width=108&crop=smart&auto=webp&s=8a45134565181ddc19c5abbe1b67100a863715e3', 'width': 108}, {'height': 193, 'url': 'https://preview.redd.it/mid1zu59e95c1.png... | |||
Tigerbot 70B v4 beats gpt4 | 1 | So the newest version of tigerbot 70B supposedly beats a 1.8T model.
My question is, how reliable are these benchmarks? How do we know that these new llms aren't being trained directly on the benchmark questions?
I'm new to llms and i'd like to understand how much I should trust these numbers.
Cheers.
[https://hugg... | 2023-12-09T11:58:39 | https://www.reddit.com/r/LocalLLaMA/comments/18ec4lt/tigerbot_70b_v4_beats_gpt4/ | Mr_Hills | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 18ec4lt | false | null | t3_18ec4lt | /r/LocalLLaMA/comments/18ec4lt/tigerbot_70b_v4_beats_gpt4/ | false | false | self | 1 | {'enabled': False, 'images': [{'id': 'EN0-abblERL52DxeoNzcxdkhvXEwLdZMJTS58Umjs64', 'resolutions': [{'height': 58, 'url': 'https://external-preview.redd.it/tSZUq9622TYSgtzH4foFlGwz9n9ixCJUAgev8O2x8jI.jpg?width=108&crop=smart&auto=webp&s=90f4efd1c1314faf5b0cd1c5eeb8d2835fe4a3ba', 'width': 108}, {'height': 116, 'url': 'h... |
Managing multiple models, their settings and use cases | 3 | I've been exploring local LLMs for a week now and it's been really fun so far. However, I'm struggling with managing all the details and settings of the different models, the modes (chat, instruct, etc) and so forth.
How are you managing all of that knowledge?
Ideally, there'd be website with all the models, their in... | 2023-12-09T11:58:35 | https://www.reddit.com/r/LocalLLaMA/comments/18ec4km/managing_multiple_models_their_settings_and_use/ | permutation | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 18ec4km | false | null | t3_18ec4km | /r/LocalLLaMA/comments/18ec4km/managing_multiple_models_their_settings_and_use/ | false | false | self | 3 | null |
drop some knowledge on me: ollama vs koboldcpp or other tools for power users on mac | 3 | I've been playing with small models using my M1 mini 16GB, but I have an M3 macbook coming with lots of memory, so I need to take things more seriously.
I'm currently using ollama + litellm to easily use local models with an OpenAI-like API, but I'm feeling like it's **too** simple.
I don't necessarily need a UI for ... | 2023-12-09T11:46:13 | https://www.reddit.com/r/LocalLLaMA/comments/18ebxtd/drop_some_knowledge_on_me_ollama_vs_koboldcpp_or/ | Madd0g | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 18ebxtd | false | null | t3_18ebxtd | /r/LocalLLaMA/comments/18ebxtd/drop_some_knowledge_on_me_ollama_vs_koboldcpp_or/ | false | false | self | 3 | null |
Google just shipped libggml from llama-cpp into its Android AICore | 189 | 2023-12-09T11:00:51 | https://twitter.com/tarantulae/status/1733263857617895558 | perone | twitter.com | 1970-01-01T00:00:00 | 0 | {} | 18eb8u0 | false | {'oembed': {'author_name': 'Christian S. Perone', 'author_url': 'https://twitter.com/tarantulae', 'cache_age': 3153600000, 'height': None, 'html': '<blockquote class="twitter-video"><p lang="en" dir="ltr">These are the libs being shipped no in AICore:<a href="https://t.co/WECzbjrMDg">https://t.co/WECzbjrMDg</a><br>libf... | t3_18eb8u0 | /r/LocalLLaMA/comments/18eb8u0/google_just_shipped_libggml_from_llamacpp_into/ | false | false | 189 | {'enabled': False, 'images': [{'id': 'hUctKOEb-yrHHGYq4bfrgAvFeR_29YPQhi4z8aEeH1M', 'resolutions': [{'height': 49, 'url': 'https://external-preview.redd.it/cUN9xPcGNTYijMcsLHhsotuypTv4t9IT5GOJ14cG7Yg.jpg?width=108&crop=smart&auto=webp&s=2755b23cc52c959ba1380cb52a99dd5bd8b1fee3', 'width': 108}], 'source': {'height': 64,... | ||
Best local model for story-writing? | 10 | Hey everyone!
I’m new to LLM’s and feel overwhelmed with all the options out there. I’m looking for a tool that I can use for writing stories preferably uncensored. I have a 3090 and plenty of space on my SSD. What do you think is the best model for me?
Thanks in advance! | 2023-12-09T10:16:04 | https://www.reddit.com/r/LocalLLaMA/comments/18eakw0/best_local_model_for_storywriting/ | FullOfVitaminC | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 18eakw0 | false | null | t3_18eakw0 | /r/LocalLLaMA/comments/18eakw0/best_local_model_for_storywriting/ | false | false | self | 10 | null |
What cpu, ram, motherboard, power supply are people using to support their 2x 4090s or 2x A6000s? | 22 | I can see a high quality motherboard being important, but I have a hard time seeing any reason to get above economy levels CPU and RAM when this machine will essentially be a GPU server.
Pretty similarly on the power supply, hit the spec you need and move on.
Any words of warning? I can spend the money on quality, ... | 2023-12-09T10:00:06 | https://www.reddit.com/r/LocalLLaMA/comments/18eac3x/what_cpu_ram_motherboard_power_supply_are_people/ | learning_hedonism | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 18eac3x | false | null | t3_18eac3x | /r/LocalLLaMA/comments/18eac3x/what_cpu_ram_motherboard_power_supply_are_people/ | false | false | self | 22 | null |
QuIP at 4 or 8 bits? | 3 | From my understanding, the newly implemented QuIP quantization greatly reduces info loss at 2 bits, making it a lot more viable.
The same method should also improve 4 and 8 bit quantizations as far as I can see, although the improvement may not be as dramatic. Has anyone tried this? | 2023-12-09T09:39:56 | https://www.reddit.com/r/LocalLLaMA/comments/18ea27c/quip_at_4_or_8_bits/ | EvokerTCG | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 18ea27c | false | null | t3_18ea27c | /r/LocalLLaMA/comments/18ea27c/quip_at_4_or_8_bits/ | false | false | self | 3 | null |
EU regulation implications ? | 33 | so which way does the recently announced EU regulation go .. there was a rumour that they'd have exemptions for opensource (pressured by the mistral team or something..) , but what actually got decided in the end ?
the biden executive order almost seemed to have the opposite intent, i.e. it was more hostile toward the... | 2023-12-09T09:06:10 | https://www.reddit.com/r/LocalLLaMA/comments/18e9llg/eu_regulation_implications/ | dobkeratops | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 18e9llg | false | null | t3_18e9llg | /r/LocalLLaMA/comments/18e9llg/eu_regulation_implications/ | false | false | self | 33 | null |
text generation web ui with a rented GPU on runpod ? | 1 | [removed] | 2023-12-09T09:04:16 | https://www.reddit.com/r/LocalLLaMA/comments/18e9kmz/text_generation_web_ui_with_a_rented_gpu_on_runpod/ | Independent-Bill-770 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 18e9kmz | false | null | t3_18e9kmz | /r/LocalLLaMA/comments/18e9kmz/text_generation_web_ui_with_a_rented_gpu_on_runpod/ | false | false | self | 1 | null |
Can we do similarity search with different embedding models? | 3 | I mean, let's say I create a chroma_db vector store using Openai embeddings but I want to use an offline embedding model like MiniLM4all or such for similarity search. Will it cause any problems or even work to begin with? | 2023-12-09T08:30:19 | https://www.reddit.com/r/LocalLLaMA/comments/18e93rw/can_we_do_similarity_search_with_different/ | Shoddy_Vegetable_115 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 18e93rw | false | null | t3_18e93rw | /r/LocalLLaMA/comments/18e93rw/can_we_do_similarity_search_with_different/ | false | false | self | 3 | null |
Prompt Engineering for 7b LLMs | 171 | After testing Mistral-Instruct and Zephyr, I decided to start figuring out more ways to integrate them in my workflow. Running some unit tests now, and noting down my observations over multiple iterations. Sharing my current list:
- give clean and specific instructions (in a direct, authoritative tone - - like "do th... | 2023-12-09T08:27:17 | https://www.reddit.com/r/LocalLLaMA/comments/18e929k/prompt_engineering_for_7b_llms/ | noellarkin | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 18e929k | false | null | t3_18e929k | /r/LocalLLaMA/comments/18e929k/prompt_engineering_for_7b_llms/ | false | false | self | 171 | null |
My open-source & cross-platform on-device LLMs app is now available on TestFlight & GitHub. Feedback & testers welcome. | 2 | 2023-12-09T08:18:43 | https://v.redd.it/gddtagfr985c1 | BrutalCoding | /r/LocalLLaMA/comments/18e8xvp/my_opensource_crossplatform_ondevice_llms_app_is/ | 1970-01-01T00:00:00 | 0 | {} | 18e8xvp | false | {'reddit_video': {'bitrate_kbps': 5000, 'dash_url': 'https://v.redd.it/gddtagfr985c1/DASHPlaylist.mpd?a=1704788327%2COGEwMjYxNjhmMmY3NTU2MGFjNTBkZjRjNThiZDgwNTAwMzE0Yzk1ZDgxM2JlYjZiOWE4NThhZDY2ZjM3NTYzOA%3D%3D&v=1&f=sd', 'duration': 60, 'fallback_url': 'https://v.redd.it/gddtagfr985c1/DASH_1080.mp4?source=fallback', 'h... | t3_18e8xvp | /r/LocalLLaMA/comments/18e8xvp/my_opensource_crossplatform_ondevice_llms_app_is/ | false | false | 2 | {'enabled': False, 'images': [{'id': 'YTBuM2Mxd29hODVjMfOEWshS1WnjFZjn1v9QghJf7iEf5PNr_9qbhZO3ZL3q', 'resolutions': [{'height': 108, 'url': 'https://external-preview.redd.it/YTBuM2Mxd29hODVjMfOEWshS1WnjFZjn1v9QghJf7iEf5PNr_9qbhZO3ZL3q.png?width=108&crop=smart&format=pjpg&auto=webp&s=ee468a8d607c6546e1bab84078792e004c57... | ||
mixtral-8x7b api for testing here. | 38 | tks [fireworks.ai](https://fireworks.ai).
i post for for someone testing.
[https://app.fireworks.ai/models/fireworks/mixtral-8x7b](https://app.fireworks.ai/models/fireworks/mixtral-8x7b).
sister test.
There are three sisters in a room. Anna is reading a book. Alice is playing a game of chess. What is the third s... | 2023-12-09T07:47:11 | https://www.reddit.com/r/LocalLLaMA/comments/18e8huk/mixtral8x7b_api_for_testing_here/ | Narrow-Painter-9623 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 18e8huk | false | null | t3_18e8huk | /r/LocalLLaMA/comments/18e8huk/mixtral8x7b_api_for_testing_here/ | false | false | self | 38 | null |
Mamba is a new neural network architecture proposed by Albert Gu and Tri Dao. (nice overview) | 1 | [removed] | 2023-12-09T06:32:37 | https://www.reddit.com/r/LocalLLaMA/comments/18e7fbj/mamba_is_a_new_neural_network_architecture/ | Easy_Butterfly2125 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 18e7fbj | false | null | t3_18e7fbj | /r/LocalLLaMA/comments/18e7fbj/mamba_is_a_new_neural_network_architecture/ | false | false | self | 1 | {'enabled': False, 'images': [{'id': 'LSsQihx365XIDDP3ttQkd0kHWsiRZW0cns5Vh1ALTrc', 'resolutions': [{'height': 81, 'url': 'https://external-preview.redd.it/E4dc0PpHSE8-RICrBaEL4raVv9n7XpVfN9oyMv4Zyig.jpg?width=108&crop=smart&auto=webp&s=88ae2183560b9470c1148637bac044e3b76cc69a', 'width': 108}, {'height': 162, 'url': 'h... |
Mixtral appreciation post | 18 | Look, look, I know, this sounds like a low effort post, but I really like the name Mixtral and I think everyone should too
I think the boys and gals nailed it on this one. It's really clever and I like it a lot. That's all. | 2023-12-09T04:45:44 | https://www.reddit.com/r/LocalLLaMA/comments/18e5q4s/mixtral_appreciation_post/ | Dany0 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 18e5q4s | false | null | t3_18e5q4s | /r/LocalLLaMA/comments/18e5q4s/mixtral_appreciation_post/ | false | false | self | 18 | null |
Is Meta using llama2 in any customer-facing production applications? | 6 | I'm just wondering if it is known if Meta itself is dog-fooding llama2 anywhere? I am working with a customer and finding latency a very difficult obstacle to economically overcome. So I wanted to see if I could find some llama2 success stories and thought I would start with Meta itself. | 2023-12-09T04:34:37 | https://www.reddit.com/r/LocalLLaMA/comments/18e5jbq/is_meta_using_llama2_in_any_customerfacing/ | codefinger | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 18e5jbq | false | null | t3_18e5jbq | /r/LocalLLaMA/comments/18e5jbq/is_meta_using_llama2_in_any_customerfacing/ | false | false | self | 6 | null |
Llamacpp | 5 | how many layers are there in total in llama 7B model , and how many layers can i offload to GPU if i have 32gb vram? | 2023-12-09T04:21:44 | https://www.reddit.com/r/LocalLLaMA/comments/18e5bka/llamacpp/ | happy_dreamer10 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 18e5bka | false | null | t3_18e5bka | /r/LocalLLaMA/comments/18e5bka/llamacpp/ | false | false | self | 5 | null |
Has any of you had disturbing or unsettling dreams after using the LLM? | 1 | Title. I was wondering because since using it I've had more unsettling dreams. I've been giving he AI a bunch of nonsense and watch as it hallucinates some sense into it. However, I think reading this stuff is causing me to have really weird dreams. The last dream I remember, kids were dislocating their jaw and pos... | 2023-12-09T03:27:54 | https://www.reddit.com/r/LocalLLaMA/comments/18e4e4b/has_any_of_you_had_disturbing_or_unsettling/ | Red_Redditor_Reddit | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 18e4e4b | false | null | t3_18e4e4b | /r/LocalLLaMA/comments/18e4e4b/has_any_of_you_had_disturbing_or_unsettling/ | false | false | default | 1 | null |
HF transformers-compatible Mixtral model | 29 | 2023-12-09T03:26:39 | https://huggingface.co/DiscoResearch/mixtral-7b-8expert | ninjasaid13 | huggingface.co | 1970-01-01T00:00:00 | 0 | {} | 18e4dcp | false | null | t3_18e4dcp | /r/LocalLLaMA/comments/18e4dcp/hf_transformerscompatible_mixtral_model/ | false | false | 29 | {'enabled': False, 'images': [{'id': 'iH74TfiZ0eTAjkuoJWlFRPPA0sWd87IMuqE2xz7DcMM', 'resolutions': [{'height': 58, 'url': 'https://external-preview.redd.it/fizOw-MpmWqkoA5UcFxFDS8Kq0mlxSKIU5zfmv3qSyA.jpg?width=108&crop=smart&auto=webp&s=c34833c0e94fea32e94b1276136bc559040fd1e0', 'width': 108}, {'height': 116, 'url': 'h... | ||
Prompting LLMs to constrain output | 8 | I just started using GBNF, this has been a lifesaver - - can't believe I was using so many tokens asking the model to respond in a specific format :) I'm using TextSynth for small models, and the API endpoint has support for GBNF.
I've also noticed that using markdown in my prompt (Eg: ## TASK DESCRIPTION) for heading... | 2023-12-09T03:21:02 | https://www.reddit.com/r/LocalLLaMA/comments/18e49oj/prompting_llms_to_constrain_output/ | noellarkin | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 18e49oj | false | null | t3_18e49oj | /r/LocalLLaMA/comments/18e49oj/prompting_llms_to_constrain_output/ | false | false | self | 8 | null |
Podcaster: turn your static site RSS feed into a podcast (XTTS-v2 + Modal.com) | 8 | 2023-12-09T03:10:51 | https://duarteocarmo.com/blog/you-can-now-listen-to-this-blog | iLikePortugueseTarts | duarteocarmo.com | 1970-01-01T00:00:00 | 0 | {} | 18e432d | false | null | t3_18e432d | /r/LocalLLaMA/comments/18e432d/podcaster_turn_your_static_site_rss_feed_into_a/ | false | false | 8 | {'enabled': False, 'images': [{'id': 'JilLN92RSpbFUQILrN1kqEhNeqS72rz6KVI4Fc45upM', 'resolutions': [{'height': 105, 'url': 'https://external-preview.redd.it/amhyGNEiNAv6ipvgvcrV0foGmPMKSKdJ-gyDgK_CfiQ.jpg?width=108&crop=smart&auto=webp&s=d3aa7c7d981f4a1f078cd94af96ff8276deffaa0', 'width': 108}, {'height': 211, 'url': '... | ||
Ryzen 7 7800X3D VS. i9-13900K for self-hosted AI? | 3 | Hi, I currently have a Ryzen 7 7800X3D, x670e motherboard, 4090, and 32gb of DDR5.
Would an i9-13900K, z790 motherboard, my 4090, and 32gb of DDR5 be better for self-hosted AI?
I'm using OobaBooga.
I know the GPU matters most. But I'm wondering if the i9/z790 are better since the Ryzen is mostly for gaming?
I pl... | 2023-12-09T02:59:32 | https://www.reddit.com/r/LocalLLaMA/comments/18e3vhx/ryzen_7_7800x3d_vs_i913900k_for_selfhosted_ai/ | kaszebe | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 18e3vhx | false | null | t3_18e3vhx | /r/LocalLLaMA/comments/18e3vhx/ryzen_7_7800x3d_vs_i913900k_for_selfhosted_ai/ | false | false | self | 3 | null |
QLORA vs. Traditional Fine-Tuning | 1 | [removed] | 2023-12-09T02:44:34 | https://www.reddit.com/r/LocalLLaMA/comments/18e3ltr/qlora_vs_traditional_finetuning/ | Demo-Demologist | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 18e3ltr | false | null | t3_18e3ltr | /r/LocalLLaMA/comments/18e3ltr/qlora_vs_traditional_finetuning/ | false | false | self | 1 | null |
Wat | 61 | 2023-12-09T01:59:26 | xadiant | i.redd.it | 1970-01-01T00:00:00 | 0 | {} | 18e2ria | false | null | t3_18e2ria | /r/LocalLLaMA/comments/18e2ria/wat/ | false | false | 61 | {'enabled': True, 'images': [{'id': 'NQOGoQW4C3roWK7tmoc-2CDGTPB_hZoipAfQPnjZmgU', 'resolutions': [{'height': 56, 'url': 'https://preview.redd.it/6ql585x0f65c1.png?width=108&crop=smart&auto=webp&s=19aee5b684f3838fe6ec3eed55e326d6f98430dd', 'width': 108}, {'height': 113, 'url': 'https://preview.redd.it/6ql585x0f65c1.png... | |||
Mistral 7b MOE on Huggingface | 15 | It can be found here: https://huggingface.co/DiscoResearch/mixtral-7b-8expert | 2023-12-09T01:40:47 | https://www.reddit.com/r/LocalLLaMA/comments/18e2eud/mistral_7b_moe_on_huggingface/ | nutcustard | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 18e2eud | false | null | t3_18e2eud | /r/LocalLLaMA/comments/18e2eud/mistral_7b_moe_on_huggingface/ | false | false | self | 15 | {'enabled': False, 'images': [{'id': 'iH74TfiZ0eTAjkuoJWlFRPPA0sWd87IMuqE2xz7DcMM', 'resolutions': [{'height': 58, 'url': 'https://external-preview.redd.it/fizOw-MpmWqkoA5UcFxFDS8Kq0mlxSKIU5zfmv3qSyA.jpg?width=108&crop=smart&auto=webp&s=c34833c0e94fea32e94b1276136bc559040fd1e0', 'width': 108}, {'height': 116, 'url': 'h... |
European Union agrees to regulate potentially harmful effects of artificial intelligence | 1 | 2023-12-09T01:25:51 | https://www.cnn.com/2023/12/08/business/european-union-regulate-ai/index.html | throwaway_ghast | cnn.com | 1970-01-01T00:00:00 | 0 | {} | 18e24fg | false | null | t3_18e24fg | /r/LocalLLaMA/comments/18e24fg/european_union_agrees_to_regulate_potentially/ | false | false | 1 | {'enabled': False, 'images': [{'id': 'HBjXE5Os9ehypurFKDIMNi53p24uYiGuyWMm5jojnXs', 'resolutions': [{'height': 60, 'url': 'https://external-preview.redd.it/cJ_ToQAsuYdtR6wX_5Slbn2yYe9O-5vWTXiD-_vHZDs.jpg?width=108&crop=smart&auto=webp&s=0454a74c754c8a9cc6d9ee630eda174cc0b2899d', 'width': 108}, {'height': 121, 'url': 'h... | ||
First results of the Mixtral 7b MoEx8: Humaneval 33.54% vs previous Mistral 7b 30.5% | 40 | [Author](https://x.com/abacaj/status/1733292527904592350?s=46&t=dUCVh9akIWxxNUIkrDJwJg). Whole [results.](https://gist.github.com/abacaj/17b987286a265f63f22f03b0323d1399) | 2023-12-09T01:15:02 | https://www.reddit.com/r/LocalLLaMA/comments/18e1wwa/first_results_of_the_mixtral_7b_moex8_humaneval/ | Shir_man | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 18e1wwa | false | null | t3_18e1wwa | /r/LocalLLaMA/comments/18e1wwa/first_results_of_the_mixtral_7b_moex8_humaneval/ | false | false | self | 40 | {'enabled': False, 'images': [{'id': 'i7lTrP4taO8voJySMDU8lBrpnPDUZaDdsQ8Kx2QunBo', 'resolutions': [{'height': 54, 'url': 'https://external-preview.redd.it/7SMIjjyaVadThhLVUtL5L4sfOQ6Mj4naXAVhrZDIbDo.jpg?width=108&crop=smart&auto=webp&s=4b62d8ae8225607ec179b2d1cc48010e12379db7', 'width': 108}, {'height': 108, 'url': 'h... |
near fp16 performance with 2 bit quantitization? | 1 | [deleted] | 2023-12-09T01:05:54 | https://x.com/tsengalb99/status/1733222467953422702?s=20 | ninjasaid13 | x.com | 1970-01-01T00:00:00 | 0 | {} | 18e1qna | false | null | t3_18e1qna | /r/LocalLLaMA/comments/18e1qna/near_fp16_performance_with_2_bit_quantitization/ | false | false | default | 1 | null |
Mixtral-8x7B-32K-q8_0-gguf 49.6GB on HuggingFace | 17 | 2023-12-09T00:51:48 | https://huggingface.co/lxe/mixtral-8x7b-32kseqlen-GGUF | chibop1 | huggingface.co | 1970-01-01T00:00:00 | 0 | {} | 18e1gej | false | null | t3_18e1gej | /r/LocalLLaMA/comments/18e1gej/mixtral8x7b32kq8_0gguf_496gb_on_huggingface/ | false | false | 17 | {'enabled': False, 'images': [{'id': 'ZE6aaAMADWgj1PEdrTmSFWpK6gIEiAZiPtJpPuhlAbE', 'resolutions': [{'height': 58, 'url': 'https://external-preview.redd.it/cyCZeSX4UYWtj6rELwXGG95hynzmKNbckashIZrAkV8.jpg?width=108&crop=smart&auto=webp&s=4052e1a70eaab0e0831d9fd360ab50d19bc93338', 'width': 108}, {'height': 116, 'url': 'h... | ||
Can LLMs self-fine-tune on narrow tasks? Reinforcement Learning with Self-Feedback | 15 | In many cases, evaluation of an LLM output is far easier than generation of that output. In such cases you can get the LLM to rank its own responses, thus replacing the human in RLHF. There's been experiments with RLAIF, but these are with *better* AI models replacing the human ranking step. I'm talking about the same ... | 2023-12-09T00:50:34 | https://www.reddit.com/r/LocalLLaMA/comments/18e1fjg/can_llms_selffinetune_on_narrow_tasks/ | xXReggieXx | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 18e1fjg | false | null | t3_18e1fjg | /r/LocalLLaMA/comments/18e1fjg/can_llms_selffinetune_on_narrow_tasks/ | false | false | self | 15 | null |
Llama.cpp Mixtral Progress | 1 | I know you're all as eager as I am to run the new Mixtral model.
The place to stay up to date is actually on the linked github issue. You'll be the first to know when it's runnable. *cough* u/the-bloke | 2023-12-09T00:49:25 | https://github.com/ggerganov/llama.cpp/issues/4381 | Sweet_Protection_163 | github.com | 1970-01-01T00:00:00 | 0 | {} | 18e1enr | false | null | t3_18e1enr | /r/LocalLLaMA/comments/18e1enr/llamacpp_mixtral_progress/ | false | false | 1 | {'enabled': False, 'images': [{'id': 'N8-N4cINqk5edyL0ftSgecTUiIYGPLrKDJBi76iMY0I', 'resolutions': [{'height': 54, 'url': 'https://external-preview.redd.it/OSlzaWA70wwGe1VI6_vspPMTCTotQEsvrW_Nx9NqxdQ.jpg?width=108&crop=smart&auto=webp&s=3c6956b8c7591a7dfd644533ee018348b388fc40', 'width': 108}, {'height': 108, 'url': 'h... | |
Coding LLM Discussion - December 2023 | 4 | I've run some local llms for uncensored fun, but I use GPT4 for Javascript and Laravel web dev and it works great (3.5 is good too but I don't mind paying the $20 for 4 because it pays for itself for its convenience). For those of you running local LLMs for coding, why and where do you see it progressing from the comme... | 2023-12-09T00:45:36 | https://www.reddit.com/r/LocalLLaMA/comments/18e1byk/coding_llm_discussion_december_2023/ | gelatinous_pellicle | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 18e1byk | false | null | t3_18e1byk | /r/LocalLLaMA/comments/18e1byk/coding_llm_discussion_december_2023/ | false | false | self | 4 | null |
Systematic Reviews: Harnessing Local Large Language Models | 2 | I am looking into using a local LLM to help with a systematic review. I have a large Zotero library of multiple PDFs organized by topic. I think ideally this could be triggered by a Zotero plugin.
I found this paper that mentions the possibility but I’m curious if I could get some guidance on actually implementing it ... | 2023-12-09T00:42:58 | https://www.ncbi.nlm.nih.gov/pmc/articles/PMC10478591/ | lincolnrules | ncbi.nlm.nih.gov | 1970-01-01T00:00:00 | 0 | {} | 18e1a6w | false | null | t3_18e1a6w | /r/LocalLLaMA/comments/18e1a6w/systematic_reviews_harnessing_local_large/ | false | false | 2 | {'enabled': False, 'images': [{'id': 'eFMa-V1uKt_0fEaeLyZatpb8QwmDWeu0cd35rQ-BtGk', 'resolutions': [{'height': 56, 'url': 'https://external-preview.redd.it/mdgLNJC-IP-f3g0_kXaAuK-s1qKbr7wKnPDYGvTl8Dw.jpg?width=108&crop=smart&auto=webp&s=6a41c00b160bc781c73dede4c59738bd43199f11', 'width': 108}, {'height': 112, 'url': 'h... |
Subsets and Splits
No community queries yet
The top public SQL queries from the community will appear here once available.