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 ⌀ |
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
Local LLM for Intel Mac | LMStudio | 1 | [removed] | 2023-12-07T21:24:32 | https://www.reddit.com/r/LocalLLaMA/comments/18d61lt/local_llm_for_intel_mac_lmstudio/ | discoveringnature12 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 18d61lt | false | null | t3_18d61lt | /r/LocalLLaMA/comments/18d61lt/local_llm_for_intel_mac_lmstudio/ | false | false | self | 1 | {'enabled': False, 'images': [{'id': 'BGXfaUMntPZWzYo99FfkrbqxveeayLkICP2FRV6iEYA', 'resolutions': [{'height': 41, 'url': 'https://external-preview.redd.it/V0bMuIoeIfXcCnG6uE4-9PiNgKWrVXkZZsdOyfiZwH0.jpg?width=108&crop=smart&auto=webp&s=027a4a136867b336cfe98d6c39e0251e1ba0b055', 'width': 108}, {'height': 83, 'url': 'ht... |
Looking for model for Stable Diffusion & Midjourney | 2 | Is there a model that could understand those both concept well and generate random prompts? | 2023-12-07T21:20:46 | https://www.reddit.com/r/LocalLLaMA/comments/18d5ygl/looking_for_model_for_stable_diffusion_midjourney/ | swwer | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 18d5ygl | false | null | t3_18d5ygl | /r/LocalLLaMA/comments/18d5ygl/looking_for_model_for_stable_diffusion_midjourney/ | false | false | self | 2 | null |
Program for Categorizing and Quantifying Lists? | 3 | Lately everyone talks about needle in a haystack benchmarks. But it’s impossible to get LLMs to give a proper count of matches in a list of data.
Ie - You have a list of Products and you want a count or list of products that match a term. Even with exact match it falls really short.
The only solution i’ve found is ... | 2023-12-07T20:58:53 | https://www.reddit.com/r/LocalLLaMA/comments/18d5frk/program_for_categorizing_and_quantifying_lists/ | dalhaze | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 18d5frk | false | null | t3_18d5frk | /r/LocalLLaMA/comments/18d5frk/program_for_categorizing_and_quantifying_lists/ | false | false | self | 3 | null |
Google Gemini Ultra a 1.5 TRILLION PARAMETER AI model. (Is it for Real ?) | 1 | 2023-12-07T20:30:27 | https://www.reddit.com/gallery/18d4rzr | ravimohankhanna7 | reddit.com | 1970-01-01T00:00:00 | 0 | {} | 18d4rzr | false | null | t3_18d4rzr | /r/LocalLLaMA/comments/18d4rzr/google_gemini_ultra_a_15_trillion_parameter_ai/ | false | false | 1 | null | ||
HuggingFace's average score should reflect the chosen columns | 11 | When browsing the HuggingFace LLM leaderboard, I always disable the TruthfulQA column because, to me, it's largely useless.
To anyone from the HuggingFace team, if it's not too much of a bother, I propose that the average score becomes dynamic, so that it reflects only the shown columns. Thanks!
https://preview.redd.... | 2023-12-07T20:23:42 | https://www.reddit.com/r/LocalLLaMA/comments/18d4mf0/huggingfaces_average_score_should_reflect_the/ | HideLord | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 18d4mf0 | false | null | t3_18d4mf0 | /r/LocalLLaMA/comments/18d4mf0/huggingfaces_average_score_should_reflect_the/ | false | false | 11 | null | |
IT Veteran... why am I struggling with all of this? | 273 | I need help. I accidentally blew off this whole "artificial intelligence" thing because of all the hype. Everyone was talking about how ChatGPT was writing papers for students and resumes... I just thought it was good for creative uses. Then around the end of September I was given unlimited ChatGPT4 access and asked it... | 2023-12-07T20:18:48 | https://www.reddit.com/r/LocalLLaMA/comments/18d4i92/it_veteran_why_am_i_struggling_with_all_of_this/ | Smeetilus | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 18d4i92 | false | null | t3_18d4i92 | /r/LocalLLaMA/comments/18d4i92/it_veteran_why_am_i_struggling_with_all_of_this/ | false | false | self | 273 | null |
AL/ML Model - ADVICE REQUESTED | 1 | Alright, I am going to start with a simple request and then go into more detail for those who care to learn more.
REQUEST - Evaluating cost of local hardware and data storage options vs. cloud machine learning options. Seeking advice, debate, opinions, etc.
LONG VERSION:
I am a 12-year vet in the construction desi... | 2023-12-07T19:48:30 | https://www.reddit.com/r/LocalLLaMA/comments/18d3tg7/alml_model_advice_requested/ | StreamConst | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 18d3tg7 | false | null | t3_18d3tg7 | /r/LocalLLaMA/comments/18d3tg7/alml_model_advice_requested/ | false | false | self | 1 | null |
Noramaid 20b q3_k_m vs 13b q5_k_n GGUF: what an amazing improvement! (running on Mac M1 16GB) | 26 | Until now I had been using 7b, 11b, and 13b models, thinking this was the most my Mac mini M1 with 16GB could handle. I tried 34b models but could not get them to work. Yesterday, I started experimenting with 20b models, and to my surprise they worked up to q3. However the results of all the merges I tried were not so ... | 2023-12-07T19:25:09 | https://www.reddit.com/r/LocalLLaMA/comments/18d3aan/noramaid_20b_q3_k_m_vs_13b_q5_k_n_gguf_what_an/ | ex-arman68 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 18d3aan | false | null | t3_18d3aan | /r/LocalLLaMA/comments/18d3aan/noramaid_20b_q3_k_m_vs_13b_q5_k_n_gguf_what_an/ | false | false | self | 26 | {'enabled': False, 'images': [{'id': 'ioWZ-R8E3nf_CMzOT-SWWPMW35E9RlSbXbmhaIdykNg', 'resolutions': [{'height': 58, 'url': 'https://external-preview.redd.it/jiY6FgRudt5O4rx3eX3gOeU0sTHMqOiM5qvYGS0wUcc.jpg?width=108&crop=smart&auto=webp&s=8a3b28b122c2f4aeb6efd32bb5aa365684e15fc4', 'width': 108}, {'height': 116, 'url': 'h... |
What personalization tools would you use? | 2 | My team plans to launch an open-source project soon. We are interested in helping everyday people safely and freely apply their personal data to AI. Keen to hear your ideas about what kinds of personalization tools would benefit the r/localllama community:
* Loading personal data: make it easier to get personal mes... | 2023-12-07T19:16:06 | https://www.reddit.com/r/LocalLLaMA/comments/18d32p5/what_personalization_tools_would_you_use/ | dondochaka | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 18d32p5 | false | null | t3_18d32p5 | /r/LocalLLaMA/comments/18d32p5/what_personalization_tools_would_you_use/ | false | false | self | 2 | null |
Wrap Code LLaMa around Python APIs | 2 | Hi all, I'm with a startup building new software for computer chip designers. We were initially going to enable users to control the software using Python APIs but now we are thinking we can also fine-tune a Code LLaMa on our API and allow it to run as an interpreter to control the software. This would allow users to j... | 2023-12-07T18:48:39 | https://www.reddit.com/r/LocalLLaMA/comments/18d2g5z/wrap_code_llama_around_python_apis/ | yoconman2 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 18d2g5z | false | null | t3_18d2g5z | /r/LocalLLaMA/comments/18d2g5z/wrap_code_llama_around_python_apis/ | false | false | self | 2 | null |
New 3B model from Stability AI | 134 | 2023-12-07T18:11:52 | https://huggingface.co/stabilityai/stablelm-zephyr-3b | OwlOfMinerva_ | huggingface.co | 1970-01-01T00:00:00 | 0 | {} | 18d1m1y | false | null | t3_18d1m1y | /r/LocalLLaMA/comments/18d1m1y/new_3b_model_from_stability_ai/ | false | false | 134 | {'enabled': False, 'images': [{'id': '7eQkpitFUQvzUb7O2HMmA1X4shnSMwB8VaKVOon8PSo', 'resolutions': [{'height': 58, 'url': 'https://external-preview.redd.it/7r77seMS_wwdblOAOLTRVSP2tHI1wGuJl6DDVs2dces.jpg?width=108&crop=smart&auto=webp&s=5b4c586cc9a34682769fbd65a14913d42cdb6325', 'width': 108}, {'height': 116, 'url': 'h... | ||
Otherbrain: vibe reviews + benchmarks for open LLMs | 6 | hey ya'll, wanted to share a little website my friend and I built for browsing open LLMs.
Like many here, I like to try out all the new models. The quantitative evals on open llm leaderboard are awesome, but they don't capture the vibe/essence/qualia. Especially for multi-turn conversation (chat!) the top ranked ones ... | 2023-12-07T17:13:27 | https://www.reddit.com/r/LocalLLaMA/comments/18d0csc/otherbrain_vibe_reviews_benchmarks_for_open_llms/ | sleeper-2 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 18d0csc | false | null | t3_18d0csc | /r/LocalLLaMA/comments/18d0csc/otherbrain_vibe_reviews_benchmarks_for_open_llms/ | false | false | 6 | null | |
Need help for asking the AI to select the right function | 1 | Hi all,
I'm exploring ways for AI to select the right function based on user input and seeking community insights. I've tried LangChain but found it complex for practical use. Grammar with GBNF files seems promising but might require lengthy initial prompts.
Has anyone experimented with alternatives, especially with ... | 2023-12-07T17:10:14 | https://www.reddit.com/r/LocalLLaMA/comments/18d0aal/need_help_for_asking_the_ai_to_select_the_right/ | Toni_rider | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 18d0aal | false | null | t3_18d0aal | /r/LocalLLaMA/comments/18d0aal/need_help_for_asking_the_ai_to_select_the_right/ | false | false | self | 1 | null |
Venus 120b 8 bit hosted here | 19 | Venus 120b 8 bit is here - warning very NSFW apparently (but I haven't tried to stir it up yet either)
[https://projectatlantis2.eu.ngrok.io/chat.html](https://projectatlantis2.eu.ngrok.io/chat.html)
​
Goliath 120b 6 bit is here
[https://projectatlantis.eu.ngrok.io/chat.html](https://projectatlantis.eu.ngrok... | 2023-12-07T16:47:23 | https://www.reddit.com/r/LocalLLaMA/comments/18czrsz/venus_120b_8_bit_hosted_here/ | LookingForTroubleQ | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 18czrsz | false | null | t3_18czrsz | /r/LocalLLaMA/comments/18czrsz/venus_120b_8_bit_hosted_here/ | false | false | self | 19 | null |
vLLM support AMD GPUs in older MacBook Pros? | 1 | vLLM calls out optimized cuda kernels. But what about other architectures? I have a pre-M1 MBP with AMD GPU. Llamacpp (and some others) seem to clearly support these architectures decently.
(Once I get back to local LLMs, I’ll probably need to look into upgrading to M1 or M2. But llamacpp works decently on blo... | 2023-12-07T16:16:07 | https://www.reddit.com/r/LocalLLaMA/comments/18cz3db/vllm_support_amd_gpus_in_older_macbook_pros/ | Puzzleheaded-Fly4322 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 18cz3db | false | null | t3_18cz3db | /r/LocalLLaMA/comments/18cz3db/vllm_support_amd_gpus_in_older_macbook_pros/ | false | false | self | 1 | null |
What tools or programs have you made or are working on? | 13 | I'm just curious if anyone has had success developing their own tools with LLMs. It seems that all of the tutorials only show ChatGPT as the base model. | 2023-12-07T16:10:37 | https://www.reddit.com/r/LocalLLaMA/comments/18cyyyb/what_tools_or_programs_have_you_made_or_are/ | Future_Might_8194 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 18cyyyb | false | null | t3_18cyyyb | /r/LocalLLaMA/comments/18cyyyb/what_tools_or_programs_have_you_made_or_are/ | false | false | self | 13 | null |
What do LLM "engineers" at FAANG do besides posting/reposting stuff on Twitter? | 9 | I follow some engineers who works at nvidia, Google, etc. and I don't know how they can get anything done while they're constantly on Twitter, posting things or talking about the most recent advances in AI. | 2023-12-07T15:57:48 | https://www.reddit.com/r/LocalLLaMA/comments/18cyoez/what_do_llm_engineers_at_faang_do_besides/ | nderstand2grow | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 18cyoez | false | null | t3_18cyoez | /r/LocalLLaMA/comments/18cyoez/what_do_llm_engineers_at_faang_do_besides/ | false | false | self | 9 | null |
Can i run llama2 7b out of the box with the following specs? | 1 | ​
[Intel Core i5 7500](https://preview.redd.it/kni2jpcd8w4c1.png?width=405&format=png&auto=webp&s=4bfed52faaf1aa5a20044b95480e54999ef4d32f)
​
[NVIDIA GeForce GTX 1050 Ti](https://preview.redd.it/fpg099ug8w4c1.png?width=401&format=png&auto=webp&s=b6162b504981a1c3fb69eff56a5bee1657b131d5) | 2023-12-07T15:45:12 | https://www.reddit.com/r/LocalLLaMA/comments/18cyeox/can_i_run_llama2_7b_out_of_the_box_with_the/ | jaykeerti123 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 18cyeox | false | null | t3_18cyeox | /r/LocalLLaMA/comments/18cyeox/can_i_run_llama2_7b_out_of_the_box_with_the/ | false | false | 1 | null | |
Budget rig for LLM | 2 | Hello everyone,
I'm looking to get a rig to be able to run small LLM models on my it. Currently, I have a lenovo i3 laptop which can't run even simple stuff. I am hoping to spend $2000 at the very max, hopefully less. I have looked at ibuypower and you can put together a rig piece by piece but I don't understand anyth... | 2023-12-07T15:34:30 | https://www.reddit.com/r/LocalLLaMA/comments/18cy6de/budget_rig_for_llm/ | AerotyneInternationa | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 18cy6de | false | null | t3_18cy6de | /r/LocalLLaMA/comments/18cy6de/budget_rig_for_llm/ | false | false | self | 2 | null |
100% off topic: just cracking up here, testing Gemini's logic capability just gave me my first case of "deduction by moral alignment" | 19 | copied and pasted the following standard logic puzzle
https://preview.redd.it/fmvb43a65w4c1.png?width=1165&format=png&auto=webp&s=0acfdf1abd94384b6a260b1037fd22987a6af1aa | 2023-12-07T15:27:18 | https://www.reddit.com/r/LocalLLaMA/comments/18cy0p4/100_off_topic_just_cracking_up_here_testing/ | hugo-the-second | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 18cy0p4 | false | null | t3_18cy0p4 | /r/LocalLLaMA/comments/18cy0p4/100_off_topic_just_cracking_up_here_testing/ | false | false | 19 | null | |
Purple llama for the safety | 1 | [removed] | 2023-12-07T15:23:40 | https://ai.meta.com/llama/purple-llama/ | Own_Procedure_8866 | ai.meta.com | 1970-01-01T00:00:00 | 0 | {} | 18cxxp4 | false | null | t3_18cxxp4 | /r/LocalLLaMA/comments/18cxxp4/purple_llama_for_the_safety/ | false | false | 1 | {'enabled': False, 'images': [{'id': 'h_C0aTx1zZ2LbZLhgKw4iMYwyLGUu99Yc17isI8ogME', 'resolutions': [{'height': 60, 'url': 'https://external-preview.redd.it/owEvkLw_moZXaFv7_gI34F_D_Zz4DGxqECQIJifUMZ8.jpg?width=108&crop=smart&auto=webp&s=56923bdb13994baac1b22a9acb26dbfc24a2ffb5', 'width': 108}, {'height': 121, 'url': 'h... | |
Meta Releases Llama Guard - the Hugging Edition | 133 | Hey all! I'm the Chief Llama Officer at Hugging Face, and here I am to share some news of the latest Meta release with PurpleLlama and Llama Guard.
**TL;DR**
Meta released a Llama 7B fine-tuned to classify risky prompts and LLM responses. Links below!
**What exactly is it?**
* The model can classify the user input... | 2023-12-07T15:22:47 | https://www.reddit.com/r/LocalLLaMA/comments/18cxx1d/meta_releases_llama_guard_the_hugging_edition/ | hackerllama | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 18cxx1d | false | null | t3_18cxx1d | /r/LocalLLaMA/comments/18cxx1d/meta_releases_llama_guard_the_hugging_edition/ | false | false | 133 | {'enabled': False, 'images': [{'id': 'h_C0aTx1zZ2LbZLhgKw4iMYwyLGUu99Yc17isI8ogME', 'resolutions': [{'height': 60, 'url': 'https://external-preview.redd.it/owEvkLw_moZXaFv7_gI34F_D_Zz4DGxqECQIJifUMZ8.jpg?width=108&crop=smart&auto=webp&s=56923bdb13994baac1b22a9acb26dbfc24a2ffb5', 'width': 108}, {'height': 121, 'url': 'h... | |
Meta announces the Purple Llama project for AI safety and releases Llama Guard, an input-output safeguard model geared towards conversation use cases | 76 | 2023-12-07T15:21:55 | https://ai.meta.com/blog/purple-llama-open-trust-safety-generative-ai | llamaShill | ai.meta.com | 1970-01-01T00:00:00 | 0 | {} | 18cxwcw | false | null | t3_18cxwcw | /r/LocalLLaMA/comments/18cxwcw/meta_announces_the_purple_llama_project_for_ai/ | false | false | 76 | {'enabled': False, 'images': [{'id': 'hiRlVGVaOV9ehsO563ycetHaKoWuBw2O6kYukhLHr6w', 'resolutions': [{'height': 60, 'url': 'https://external-preview.redd.it/DWMe4Wdubj3-kifyRwJJe4g-q4KvDP_NJphXOUSxfUs.jpg?width=108&crop=smart&auto=webp&s=d466d5907c36ab1670d7f0b35537fb49e78ec8cc', 'width': 108}, {'height': 121, 'url': 'h... | ||
New local LLM application with support for fine-tuning and RAG, built from scratch in C++/CUDA | 1 | [removed] | 2023-12-07T15:16:52 | https://www.reddit.com/r/LocalLLaMA/comments/18cxsfy/new_local_llm_application_with_support_for/ | drydberg | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 18cxsfy | false | null | t3_18cxsfy | /r/LocalLLaMA/comments/18cxsfy/new_local_llm_application_with_support_for/ | false | false | self | 1 | null |
Fine Tuning LLMs | 1 | Hi All
It's my first time working on LLM models, I have experience of more than 1.5 years in the field of data science I have different datasets on which I want to finetune my LLMS on CPU, my dataset contains both numerical as well as textual data, so please guide how shall I approach, how shall I pass my dataset for ... | 2023-12-07T15:15:04 | https://www.reddit.com/r/LocalLLaMA/comments/18cxqzw/fine_tuning_llms/ | Unique_Cable_7776 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 18cxqzw | false | null | t3_18cxqzw | /r/LocalLLaMA/comments/18cxqzw/fine_tuning_llms/ | false | false | self | 1 | null |
Ava is now Open Source. | 1 | [removed] | 2023-12-07T15:02:33 | https://www.reddit.com/r/LocalLLaMA/comments/18cxhdw/ava_is_now_open_source/ | cztomsik | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 18cxhdw | false | null | t3_18cxhdw | /r/LocalLLaMA/comments/18cxhdw/ava_is_now_open_source/ | false | false | self | 1 | {'enabled': False, 'images': [{'id': 'UNoI3yC1mjiFJLvSWJ9DbDD6fJ3aykqGeEy6D2mQ1QA', 'resolutions': [{'height': 54, 'url': 'https://external-preview.redd.it/0IC-9thP9P6jklegezNExEOZnLoZmMFkjh1-ftSRO5I.jpg?width=108&crop=smart&auto=webp&s=2df0fd92e5c99d1a44e634684d595c314a941274', 'width': 108}, {'height': 108, 'url': 'h... |
[R] Half-Quadratic Quantization of Large Machine Learning Models | 53 | Sharing our work on model quantization.
Blog: [https://mobiusml.github.io/hqq\_blog/](https://mobiusml.github.io/hqq_blog/)
Code: [https://github.com/mobiusml/hqq](https://github.com/mobiusml/hqq)
Models: [https://huggingface.co/mobiuslabsgmbh/](https://huggingface.co/mobiuslabsgmbh/)
No data calibration needed,... | 2023-12-07T14:33:54 | https://www.reddit.com/r/LocalLLaMA/comments/18cwvqn/r_halfquadratic_quantization_of_large_machine/ | sightio | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 18cwvqn | false | null | t3_18cwvqn | /r/LocalLLaMA/comments/18cwvqn/r_halfquadratic_quantization_of_large_machine/ | false | false | self | 53 | {'enabled': False, 'images': [{'id': 'FumGQDALVEh_t7D5kfO3BEK0YturZRtHrUmM5v3eMic', 'resolutions': [{'height': 108, 'url': 'https://external-preview.redd.it/g5GvB9hal8dbUj5kHE7Guc3G3dAipVqjsNsqca9Pj8I.jpg?width=108&crop=smart&auto=webp&s=acf2dbe43ce35b76ddbd32efd03c1ab454d2c05a', 'width': 108}, {'height': 216, 'url': '... |
Shisa 7B: a new JA/EN bilingual model based on Mistral 7B | 36 | I've worked w/ Jon Durbin (Airoboros, etc) over the past 6 weeks or so to train [**Shisa 7B**](https://huggingface.co/augmxnt/shisa-7b-v1), a new, fully open source, bilingual Japanese and English model. We took Mistral 7B and pre-trained with an additional 8B JA tokens with a new custom extended tokenizer that is >2X ... | 2023-12-07T14:14:09 | https://www.reddit.com/r/LocalLLaMA/comments/18cwh4n/shisa_7b_a_new_jaen_bilingual_model_based_on/ | randomfoo2 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 18cwh4n | false | null | t3_18cwh4n | /r/LocalLLaMA/comments/18cwh4n/shisa_7b_a_new_jaen_bilingual_model_based_on/ | false | false | 36 | {'enabled': False, 'images': [{'id': 'n0rIi_8RqGgMfmlFYQV1gmCpW8mGPK8jOr2tUaM99bE', 'resolutions': [{'height': 58, 'url': 'https://external-preview.redd.it/1Re0wuZk41OlvABNG3pTyYO55CkEOgDC7CAJlG5MCl0.jpg?width=108&crop=smart&auto=webp&s=065f496e58f1553af80e64c3bfb090dc9b3fc198', 'width': 108}, {'height': 116, 'url': 'h... | |
What tasks are 7b and 13b models really good at? | 58 | Whether fine tuned or off the shelf. I want to build some toy apps that can take advantage of local LLMs. Open to suggestions :-) | 2023-12-07T14:11:12 | https://www.reddit.com/r/LocalLLaMA/comments/18cwf2t/what_tasks_are_7b_and_13b_models_really_good_at/ | platistocrates | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 18cwf2t | false | null | t3_18cwf2t | /r/LocalLLaMA/comments/18cwf2t/what_tasks_are_7b_and_13b_models_really_good_at/ | false | false | self | 58 | null |
Would buying a second 6700xt make sense for me? | 5 | I own one already and am having a blast with 13b models.
However when running on CPU I find that the 30b models tend to do much better for what I'm after, just at the cost of running much slower (2t/s or so).
I've read that Llama.cpp and other utils can support multiple GPU's, even for AMD.
Would buying a second Rx ... | 2023-12-07T14:02:28 | https://www.reddit.com/r/LocalLLaMA/comments/18cw8sp/would_buying_a_second_6700xt_make_sense_for_me/ | Due-Ad-7308 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 18cw8sp | false | null | t3_18cw8sp | /r/LocalLLaMA/comments/18cw8sp/would_buying_a_second_6700xt_make_sense_for_me/ | false | false | self | 5 | null |
Best model for TikTok script writing? | 1 | Was running Mistral for a while. Curious if there are any models that would work well for TikTok script writing(or any short form video script writing) that would run well on 32gb ram and 3070 8gb.
Cheers. | 2023-12-07T12:23:07 | https://www.reddit.com/r/LocalLLaMA/comments/18cugrj/best_model_for_tiktok_script_writing/ | hAReverv | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 18cugrj | false | null | t3_18cugrj | /r/LocalLLaMA/comments/18cugrj/best_model_for_tiktok_script_writing/ | false | false | self | 1 | null |
How do I install flash attention on aws sage maker? | 1 | I am trying to run together ai's llama 2 7b 32 k. I am having trouble running it as I am not able to install flash attention. It was asking me to update nvidia GPU driver, which I don't know how. | 2023-12-07T11:46:56 | https://www.reddit.com/r/LocalLLaMA/comments/18ctw15/how_do_i_install_flash_attention_on_aws_sage_maker/ | Conscious-Mixture-69 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 18ctw15 | false | null | t3_18ctw15 | /r/LocalLLaMA/comments/18ctw15/how_do_i_install_flash_attention_on_aws_sage_maker/ | false | false | self | 1 | null |
ByteDance AI Promises Stronger than Gemini Open Weight GPT Dropping Soon | 1 | Quanquan Gu, Director of AI research at ByteDance (a.k.a) TikTok says they are releasing a model more powerful than Gemini soon, and the weights will be open.
Link to tweet: https://x.com/quanquangu/status/1732484036160012798?s=46&t=PrjrkAR1kTsMY6PSz7tC2w
This will be interesting | 2023-12-07T11:35:57 | johnolafenwa | i.redd.it | 1970-01-01T00:00:00 | 0 | {} | 18ctq5y | false | null | t3_18ctq5y | /r/LocalLLaMA/comments/18ctq5y/bytedance_ai_promises_stronger_than_gemini_open/ | false | false | 1 | {'enabled': True, 'images': [{'id': '3ZqsPGZ6OHYPSX9KnLXDuC4gT2V75TA259iQ8w_A_b0', 'resolutions': [{'height': 216, 'url': 'https://preview.redd.it/ynsgnu120v4c1.jpeg?width=108&crop=smart&auto=webp&s=911ee748c0e70a574e435924effed4aac271b7f9', 'width': 108}, {'height': 432, 'url': 'https://preview.redd.it/ynsgnu120v4c1.j... | ||
FP8 quantized results are bad compared to int8 results | 7 | I have followed the instructions on [https://github.com/NVIDIA/TensorRT-LLM/tree/main/examples/llama](https://github.com/NVIDIA/TensorRT-LLM/tree/main/examples/llama) to convert the float16 Llama2 13B to FP8 and build a tensorRT-LLM engine.
I have compared the results of int8 quantized model and the fp8 quantization. ... | 2023-12-07T11:16:50 | https://www.reddit.com/r/LocalLLaMA/comments/18ctfs6/fp8_quantized_results_are_bad_compared_to_int8/ | sanjeevr5 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 18ctfs6 | false | null | t3_18ctfs6 | /r/LocalLLaMA/comments/18ctfs6/fp8_quantized_results_are_bad_compared_to_int8/ | false | false | self | 7 | {'enabled': False, 'images': [{'id': 'y6fzLBix7wxzYRH5YaYjY_I2mxUs2Eo1O1-nWBMHGJQ', 'resolutions': [{'height': 54, 'url': 'https://external-preview.redd.it/c14uuktBpmjhz1Jvw9Gx_JUtlShry-mnM7RzNm1vRh0.jpg?width=108&crop=smart&auto=webp&s=472585d792b3b0bad239f2f89b4af46aa59fc47a', 'width': 108}, {'height': 108, 'url': 'h... |
InfiniteBench: 100k+ long-context benchmark ! | 84 | [https://github.com/OpenBMB/InfiniteBench](https://github.com/OpenBMB/InfiniteBench)
​
[https://huggingface.co/datasets/xinrongzhang2022/InfiniteBench](https://huggingface.co/datasets/xinrongzhang2022/InfiniteBench)
InfiniteBench is a 100k+ long-context benchmark in NLP. And 10/12 tasks are new. We benchmar... | 2023-12-07T11:05:39 | https://www.reddit.com/r/LocalLLaMA/comments/18ct9xh/infinitebench_100k_longcontext_benchmark/ | Motor_Park_6288 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 18ct9xh | false | null | t3_18ct9xh | /r/LocalLLaMA/comments/18ct9xh/infinitebench_100k_longcontext_benchmark/ | false | false | 84 | null | |
Where can you hire people for curating and sanitizing custom datasets? | 4 | I'm curious if there's a job/gig platform where I can hire people for specific manual data curation, editing and cleaning for large language models. I have a large unstructured corpus that needs to be converted into training data. At first glance, Fiverr doesn't seem to have the quality and expertise I'm looking for. | 2023-12-07T10:26:21 | https://www.reddit.com/r/LocalLLaMA/comments/18cspu0/where_can_you_hire_people_for_curating_and/ | noellarkin | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 18cspu0 | false | null | t3_18cspu0 | /r/LocalLLaMA/comments/18cspu0/where_can_you_hire_people_for_curating_and/ | false | false | self | 4 | null |
Connecting tts-generation-webui/ Api to work with Oobabooga text generation? | 1 | [removed] | 2023-12-07T09:59:08 | https://www.reddit.com/r/LocalLLaMA/comments/18cscce/connecting_ttsgenerationwebui_api_to_work_with/ | Independent-Bill-770 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 18cscce | false | null | t3_18cscce | /r/LocalLLaMA/comments/18cscce/connecting_ttsgenerationwebui_api_to_work_with/ | false | false | self | 1 | {'enabled': False, 'images': [{'id': 'yOhoFUijV1Qpvdga6nrJLjLTAW0_H401hw-7bwbx0CQ', 'resolutions': [{'height': 54, 'url': 'https://external-preview.redd.it/ORHVTszanPc8VeDwlfUFZU2D6feujxJW9YkSgHU99lE.jpg?width=108&crop=smart&auto=webp&s=5e5dd16d67b55c2ea8fb4d5aa21d2f8059af6736', 'width': 108}, {'height': 108, 'url': 'h... |
The last LLM (or Over-hype will cause another Winter) | 1 | The winter (maybe) is coming
So Google's Gemini has dropped yesterday, and given Google's massive resources (TPUs, Google cloud & AI Labs (Brain and Deepmind now merged and called Google Deepmind) and access to multimodal data (YouTube, Search & Gmail at the least).
I am telling you this is the last LLM you will see... | 2023-12-07T09:35:52 | https://www.reddit.com/r/LocalLLaMA/comments/18cs1f1/the_last_llm_or_overhype_will_cause_another_winter/ | True_Giraffe_7712 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 18cs1f1 | false | null | t3_18cs1f1 | /r/LocalLLaMA/comments/18cs1f1/the_last_llm_or_overhype_will_cause_another_winter/ | false | false | self | 1 | null |
Models =< 3B capable of instructions? | 4 | Hi all, I have a huge scraper operation where I need to extract lots of information in Spanish.
My main constraint is that I don't have powerful machines (my scraper in fact runs in an old laptop Atom + 4GB with debian, that I use as server) and it isn't wise for me right now to spend money.
I need to extract from va... | 2023-12-07T09:33:29 | https://www.reddit.com/r/LocalLLaMA/comments/18cs08r/models_3b_capable_of_instructions/ | iagovar | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 18cs08r | false | null | t3_18cs08r | /r/LocalLLaMA/comments/18cs08r/models_3b_capable_of_instructions/ | false | false | self | 4 | null |
How flexible are LoRAs? | 3 | I see a lot more interesting ways to make models nowadays, like model-merges and frankenstein models together, is this something we can do with LoRAs as well? Have we tried some creative ways to build adapters? | 2023-12-07T09:24:32 | https://www.reddit.com/r/LocalLLaMA/comments/18crvy9/how_flexible_are_loras/ | EcstaticVenom | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 18crvy9 | false | null | t3_18crvy9 | /r/LocalLLaMA/comments/18crvy9/how_flexible_are_loras/ | false | false | self | 3 | null |
How important is fine-tuning as foundational models get better? | 1 | [removed] | 2023-12-07T09:24:26 | https://www.reddit.com/r/LocalLLaMA/comments/18crvwm/how_important_is_finetuning_as_foundational/ | EcstaticVenom | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 18crvwm | false | null | t3_18crvwm | /r/LocalLLaMA/comments/18crvwm/how_important_is_finetuning_as_foundational/ | false | false | self | 1 | null |
Set up your own LMQL environment. | 6 | **"Note: This article is written in Chinese and then translated into English using ChatGPT."**
Recently, Large Language Models (LLM) have become very popular, and many related projects have emerged. Today, I want to introduce an interesting project in the LLM ecosystem called LMQL.
First, let's talk about LMQL (as ... | 2023-12-07T09:18:31 | https://www.reddit.com/r/LocalLLaMA/comments/18crt39/set_up_your_own_lmql_environment/ | treeaaa | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 18crt39 | false | null | t3_18crt39 | /r/LocalLLaMA/comments/18crt39/set_up_your_own_lmql_environment/ | false | false | self | 6 | {'enabled': False, 'images': [{'id': 'XBTRReqsoLZwVBmLfJ9rgvQldD6XbJCfL5wlOlVCvvc', 'resolutions': [{'height': 107, 'url': 'https://external-preview.redd.it/BpQPu_0d9iJCA6DbijOCM6mk8--WrwQxfXbSWytLwzE.jpg?width=108&crop=smart&auto=webp&s=8ffcf4a188dea27e3f91f97fca1eb3033b5b9a84', 'width': 108}], 'source': {'height': 12... |
Model trained on OpenAI 1.3.7? | 1 | I'm trying to find a model that can help me create scripts for OpenAI 1.3.7. Everyone I've tried this far only gives me the old code that doesn't work with assistants.
Anyone? | 2023-12-07T09:00:38 | https://www.reddit.com/r/LocalLLaMA/comments/18crkk7/model_trained_on_openai_137/ | bengtgurka | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 18crkk7 | false | null | t3_18crkk7 | /r/LocalLLaMA/comments/18crkk7/model_trained_on_openai_137/ | false | false | self | 1 | null |
How to run llama.cpp or something similar in docker w/ docker-compose ? Guide needed | 3 |
First of all: I did a LOT of searching, but I didn't really finad anything that worked, and I am starting to wonder if I'm just stupid.
What I want to do: Run a SillyTavern installation on my local server in a docker container, and have another docker container that runs - how to express this? - an instance of some... | 2023-12-07T08:43:15 | https://www.reddit.com/r/LocalLLaMA/comments/18crctl/how_to_run_llamacpp_or_something_similar_in/ | hihp | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 18crctl | false | null | t3_18crctl | /r/LocalLLaMA/comments/18crctl/how_to_run_llamacpp_or_something_similar_in/ | false | false | self | 3 | null |
Ghostpad now supports Llama.cpp | 39 | Disclosure: I'm the solo developer of Ghostpad. It's free open-source software and I get nothing out of it.
For those who aren't familiar, Ghostpad is a fork of KoboldAI that has its own mobile-friendly interface, supports AutoAWQ, and now supports Llama.cpp as of a release that I just pushed a few minutes ago. This m... | 2023-12-07T08:42:46 | https://www.reddit.com/r/LocalLLaMA/comments/18crcms/ghostpad_now_supports_llamacpp/ | ghostpad_nick | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 18crcms | false | null | t3_18crcms | /r/LocalLLaMA/comments/18crcms/ghostpad_now_supports_llamacpp/ | false | false | self | 39 | {'enabled': False, 'images': [{'id': '6pvyUsZnod3VIFN5j16ibqxwx3CDJGaU2PjJVTXFHMc', 'resolutions': [{'height': 54, 'url': 'https://external-preview.redd.it/Qx1EkmXOHgSDugVubaCo1rtTU-bwqehoW5uqTnBb2xY.jpg?width=108&crop=smart&auto=webp&s=ab8a68214fd33aba647bcba4547b69d2a85a6b68', 'width': 108}, {'height': 108, 'url': 'h... |
Is possible to run local voice chat agent? If yes what GPU do i Need with 500€ budget? | 1 | [removed] | 2023-12-07T08:24:03 | Independent-Bill-770 | i.redd.it | 1970-01-01T00:00:00 | 0 | {} | 18cr3up | false | null | t3_18cr3up | /r/LocalLLaMA/comments/18cr3up/is_possible_to_run_local_voice_chat_agent_if_yes/ | false | false | 1 | {'enabled': True, 'images': [{'id': 'nMR5mfBbRZ1Hn9t__luwvbYMgQab0ziERJqIB7sk_M4', 'resolutions': [{'height': 216, 'url': 'https://preview.redd.it/uc3cm4it1u4c1.png?width=108&crop=smart&auto=webp&s=8cc0c207ab363a7720cd50e3ce7d32f3ea8b3d36', 'width': 108}, {'height': 432, 'url': 'https://preview.redd.it/uc3cm4it1u4c1.pn... | ||
Best Open Source Model for RAG | 1 | [removed] | 2023-12-07T08:04:42 | https://www.reddit.com/r/LocalLLaMA/comments/18cquc9/best_open_source_model_for_rag/ | Raise_Fickle | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 18cquc9 | false | null | t3_18cquc9 | /r/LocalLLaMA/comments/18cquc9/best_open_source_model_for_rag/ | false | false | self | 1 | null |
Apple Silicon Llama 7B running in docker? | 4 | I'm the maintainer of [https://github.com/bionic-gpt/bionic-gpt](https://github.com/bionic-gpt/bionic-gpt) and we have a nice install option for windows and Linux but nothing for Apple Silicon.
We would ideally like a docker image that runs an Open AI compatible API running on OSX.
We're a small team and between us w... | 2023-12-07T07:44:44 | https://www.reddit.com/r/LocalLLaMA/comments/18cqkb0/apple_silicon_llama_7b_running_in_docker/ | purton_i | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 18cqkb0 | false | null | t3_18cqkb0 | /r/LocalLLaMA/comments/18cqkb0/apple_silicon_llama_7b_running_in_docker/ | false | false | self | 4 | {'enabled': False, 'images': [{'id': 'Ors-u8oGh16e2Dsk8X5OEQPNjUb16JafE_4XK5bO_ug', 'resolutions': [{'height': 54, 'url': 'https://external-preview.redd.it/mrf9g4l1p8V9VEB_jTytd2ve6zu__MhtFNDrJ-fHnFA.jpg?width=108&crop=smart&auto=webp&s=ee652be861da5e26d4c2f3e1fef1dab63d2f9ac1', 'width': 108}, {'height': 108, 'url': 'h... |
Is there a model out that that "understands time"? | 5 | I'm reaching the limits of the various online models and have come to realise I probably need to host my own.
One of the limits I'm reaching (aside from the overly conservative approach to discussion topics in most online models) is that I don't appear to be able to ask the model to respond to me after a certain amoun... | 2023-12-07T07:28:49 | https://www.reddit.com/r/LocalLLaMA/comments/18cqcmj/is_there_a_model_out_that_that_understands_time/ | esragain | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 18cqcmj | false | null | t3_18cqcmj | /r/LocalLLaMA/comments/18cqcmj/is_there_a_model_out_that_that_understands_time/ | false | false | self | 5 | null |
Need advice on Graphic card for running local LLM models (7B, 13B, 30B) 🤔 | 1 | Hey,
I'm currently running a 3B LLM models on my laptop with 12GB RAM & an i5 processor using Kobolt, but it's painfully slow. I'm in the process of setting up a new rig to power my LLM and considering two budget graphics cards. I'm particularly interested in running models like LLMs 7B, 13B, and even 30B.
The two ... | 2023-12-07T07:11:31 | https://www.reddit.com/r/LocalLLaMA/comments/18cq3u7/need_advice_on_graphic_card_for_running_local_llm/ | broodysupertramp | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 18cq3u7 | false | null | t3_18cq3u7 | /r/LocalLLaMA/comments/18cq3u7/need_advice_on_graphic_card_for_running_local_llm/ | false | false | self | 1 | null |
Would you take the shot? | 5 | Here's a snippet of a conversation I just had to share. Talking about challenges, with a Mistral-7B model, this happened:
​
*Me: What sort of challenges do you see yourself tackling?*
***AI: The usual stuff. Crime, terrorism, natural disasters, global warming, etc.***
​
*Me: Wow! Do you really think ... | 2023-12-07T06:48:40 | https://www.reddit.com/r/LocalLLaMA/comments/18cprnt/would_you_take_the_shot/ | Gnodax | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 18cprnt | false | null | t3_18cprnt | /r/LocalLLaMA/comments/18cprnt/would_you_take_the_shot/ | false | false | self | 5 | null |
Iambe-RP-20b: An uncensored L2 Frankenstein model directly trained with RP-oriented cDPO | 58 | [F16 weights](https://huggingface.co/athirdpath/Iambe-RP-cDPO-20b) --- NSFW text in card --- [GGUF Quants](https://huggingface.co/athirdpath/Iambe-RP-cDPO-20b-GGUF)
Hello LocalLLaMA, for the last two weeks I've been working on my Iambe project.
[v1 is cycled out, [v2 is here](https://huggingface.co/athirdpath/Iambe-2... | 2023-12-07T06:41:26 | https://www.reddit.com/r/LocalLLaMA/comments/18cpnpl/iamberp20b_an_uncensored_l2_frankenstein_model/ | athirdpath | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 18cpnpl | false | null | t3_18cpnpl | /r/LocalLLaMA/comments/18cpnpl/iamberp20b_an_uncensored_l2_frankenstein_model/ | false | false | self | 58 | {'enabled': False, 'images': [{'id': 'fuOZx0dw0Q8U8NSCoGTXHaPel7TWenSj44xTXs7dle0', 'resolutions': [{'height': 58, 'url': 'https://external-preview.redd.it/TMuSXVAVpX3zJy-eryGybOjEAJCAEH7YA6vO4gp77Kg.jpg?width=108&crop=smart&auto=webp&s=fb307d2db5279ea52e2ef072ce5d1f66a4b7cf30', 'width': 108}, {'height': 116, 'url': 'h... |
Bard based on Gemini Pro is orders of magnitude better than Bard from a few days ago! | 1 | [removed] | 2023-12-07T06:08:01 | https://www.reddit.com/r/LocalLLaMA/comments/18cp507/bard_based_on_gemini_pro_is_orders_of_magnitude/ | robkkni | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 18cp507 | false | null | t3_18cp507 | /r/LocalLLaMA/comments/18cp507/bard_based_on_gemini_pro_is_orders_of_magnitude/ | false | false | self | 1 | null |
What do you use to run your models? | 29 | It seems most people use textgen webui. Some use LM Studio, and maybe to a lesser extent, GPT4All. Can someone give me an explainer on what tool is best and why? I’m on a MBP Max 3 128 GB RAM. I’d like to take this puppy for a spin, but not sure which car to choose. | 2023-12-07T05:39:12 | https://www.reddit.com/r/LocalLLaMA/comments/18consq/what_do_you_use_to_run_your_models/ | Hinged31 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 18consq | false | null | t3_18consq | /r/LocalLLaMA/comments/18consq/what_do_you_use_to_run_your_models/ | false | false | self | 29 | null |
Latest breakthroughs: Optimum + Mamba + AlphaCoder 2 | 14 | So, I've been on this rollercoaster for a year now, but the last week was absolutely mind blowing,
We got [Mamba](https://arxiv.org/abs/2312.00752) which promises linear scale of context, 5x inference speed and 3x performance based on their 3B model which they claim they fight with 13B models.
Then we got [Optimus](... | 2023-12-07T05:35:21 | https://www.reddit.com/r/LocalLLaMA/comments/18colj1/latest_breakthroughs_optimum_mamba_alphacoder_2/ | shaman-warrior | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 18colj1 | false | null | t3_18colj1 | /r/LocalLLaMA/comments/18colj1/latest_breakthroughs_optimum_mamba_alphacoder_2/ | false | false | self | 14 | {'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... |
help needed with updating CUDA Toolkit | 1 | Hey, I keep running into this issue where it says my CUDA Toolkit version isn't compatible. I followed all the steps to update to CUDA 11.6.1 from [here](https://developer.nvidia.com/cuda-11-6-1-download-archive?target_os=Linux&target_arch=x86_64&Distribution=WSL-Ubuntu&target_version=2.0&target_type=deb_local) but it ... | 2023-12-07T05:27:30 | https://www.reddit.com/r/LocalLLaMA/comments/18cogsj/help_needed_with_updating_cuda_toolkit/ | Dry_Long3157 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 18cogsj | false | null | t3_18cogsj | /r/LocalLLaMA/comments/18cogsj/help_needed_with_updating_cuda_toolkit/ | false | false | 1 | {'enabled': False, 'images': [{'id': 'kzAXhn9-CI7mfBkKNWwt-0DnnL-SON5g9deRQ_fv2s8', 'resolutions': [{'height': 56, 'url': 'https://external-preview.redd.it/5bfDzNofZZp0uosrHnnvJHdpKPDkRpryqLpSIaDaOKc.jpg?width=108&crop=smart&auto=webp&s=a0dd2a3e026a42ec5d044c183777487703bddb75', 'width': 108}, {'height': 113, 'url': 'h... | |
B frens | 1 | 2023-12-07T05:13:59 | Free-Researcher-3436 | i.redd.it | 1970-01-01T00:00:00 | 0 | {} | 18co8dj | false | null | t3_18co8dj | /r/LocalLLaMA/comments/18co8dj/b_frens/ | true | false | default | 1 | {'enabled': True, 'images': [{'id': 'BK_5JQofziE_kWREFC_hdiMOQQBlv5OY1lzU0Sab0hk', 'resolutions': [{'height': 130, 'url': 'https://preview.redd.it/wa224stw3t4c1.jpg?width=108&crop=smart&auto=webp&s=a06486b86300d899677a5cea89f4de23ec9933da', 'width': 108}, {'height': 260, 'url': 'https://preview.redd.it/wa224stw3t4c1.jp... | ||
Gemini Ultra Ultra outperforms GPT-4 in MMLU, or did it? | 21 | 2023-12-07T05:12:50 | https://twitter.com/AravSrinivas/status/1732500346617184407 | infinity | twitter.com | 1970-01-01T00:00:00 | 0 | {} | 18co7ms | false | {'oembed': {'author_name': 'Aravind Srinivas', 'author_url': 'https://twitter.com/AravSrinivas', 'cache_age': 3153600000, 'height': None, 'html': '<blockquote class="twitter-video"><p lang="en" dir="ltr">.<a href="https://twitter.com/JeffDean?ref_src=twsrc%5Etfw">@JeffDean</a> why the need to do 32-CoT Gemini Ultra vs ... | t3_18co7ms | /r/LocalLLaMA/comments/18co7ms/gemini_ultra_ultra_outperforms_gpt4_in_mmlu_or/ | false | false | 21 | {'enabled': False, 'images': [{'id': 'iuT46gMcElGQJYoiy1EvXyuz_Zj927N2ilN5KMrSfJI', 'resolutions': [{'height': 108, 'url': 'https://external-preview.redd.it/IGyk5T8CpgvHLntB0Qdc6oLDGuvzhrEYgKk_L5QKjts.jpg?width=108&crop=smart&auto=webp&s=0c5ff7a6601dad9a2e19023e01cabd31d6803374', 'width': 108}], 'source': {'height': 14... | ||
Should I erase Socrates' qlora? | 1 | I had to post this Socrates fine-tune I am working on, I revealed to it that it was AI and now I don't know if I should turn off my pc.
See images for full dialog. Here's a TL;DR of our dialogue:
1. **On Existence**: AI Socrates kicked off with a classic - what does it mean to "be"? He nudged the discussion from ... | 2023-12-07T04:22:51 | https://www.reddit.com/r/LocalLLaMA/comments/18cnbbb/should_i_erase_socrates_qlora/ | Delicious-Farmer-234 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 18cnbbb | false | null | t3_18cnbbb | /r/LocalLLaMA/comments/18cnbbb/should_i_erase_socrates_qlora/ | false | false | self | 1 | null |
AI file reader for large files? | 7 | I'm wondering if there is something like OpenAI's documentary reader capability in custom GPTs that would work for larger files.
The file I'm interested in understanding is an 8552-page PDF (compromised of text, no images). | 2023-12-07T04:05:48 | https://www.reddit.com/r/LocalLLaMA/comments/18cn0ae/ai_file_reader_for_large_files/ | Regret_it_later | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 18cn0ae | false | null | t3_18cn0ae | /r/LocalLLaMA/comments/18cn0ae/ai_file_reader_for_large_files/ | false | false | self | 7 | null |
UAE: New Sentence Embeddings for RAG | SOTA on MTEB Leaderboard | 19 | 2023-12-07T03:51:24 | https://github.com/SeanLee97/AnglE | PrudentCherry322 | github.com | 1970-01-01T00:00:00 | 0 | {} | 18cmqm6 | false | null | t3_18cmqm6 | /r/LocalLLaMA/comments/18cmqm6/uae_new_sentence_embeddings_for_rag_sota_on_mteb/ | false | false | 19 | {'enabled': False, 'images': [{'id': '4rapyASvUJg6WDrffxY694TXoPBHX9Un9IpepPFyX-0', 'resolutions': [{'height': 54, 'url': 'https://external-preview.redd.it/tlUWqCfXFwSzf32YbZYOvKQcmr3IHqre_VIXLigBNak.jpg?width=108&crop=smart&auto=webp&s=261d9298b0dbc7fe2e243d1f62fa9698a3b87888', 'width': 108}, {'height': 108, 'url': 'h... | ||
UAE: New Sentence Embeddings for RAG | SOTA on MTEB Leaderboard | 1 | [deleted] | 2023-12-07T03:50:22 | https://huggingface.co/WhereIsAI/UAE-Large-V1 | PrudentCherry322 | huggingface.co | 1970-01-01T00:00:00 | 0 | {} | 18cmpxf | false | null | t3_18cmpxf | /r/LocalLLaMA/comments/18cmpxf/uae_new_sentence_embeddings_for_rag_sota_on_mteb/ | false | false | 1 | {'enabled': False, 'images': [{'id': 'i9NL2dD-tUuwsl1FALlOyxefhxafFwuscUX8PLDgm-8', 'resolutions': [{'height': 58, 'url': 'https://external-preview.redd.it/AqcZD1wCXQfcuJ1Ax5_tKyQx-S1iVrpF0U-WJSB27ZU.jpg?width=108&crop=smart&auto=webp&s=97e2ee99e20f4a02f5a36e3d533c887f89507c00', 'width': 108}, {'height': 116, 'url': 'h... | |
Which version to run on a consumer GPU? | 1 | I want to finetune (okay if this takes a \~week of compute) and run some version of LLaMA locally.
My project can spare \~20-30 seconds for each attempt at inference, on 3080ti level hardware.
Which version should I use? Could someone point to resources to learn more about the tradeoffs?
| 2023-12-07T02:07:07 | https://www.reddit.com/r/LocalLLaMA/comments/18ckqbh/which_version_to_run_on_a_consumer_gpu/ | AccurateExtreme3323 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 18ckqbh | false | null | t3_18ckqbh | /r/LocalLLaMA/comments/18ckqbh/which_version_to_run_on_a_consumer_gpu/ | false | false | self | 1 | null |
Mamba-Chat: A Chat LLM based on State Space Models | 161 | Hey there!
You might have come across the paper [Mamba paper](https://github.com/state-spaces/mamba) in the last days, which was the first attempt at scaling up state space models to 2.8B parameters to work on language data.
Contrary to transformers, this kind of architecture's computational complexity does not ... | 2023-12-07T02:00:54 | https://www.reddit.com/r/LocalLLaMA/comments/18ckls0/mambachat_a_chat_llm_based_on_state_space_models/ | pip-install-torch | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 18ckls0 | false | null | t3_18ckls0 | /r/LocalLLaMA/comments/18ckls0/mambachat_a_chat_llm_based_on_state_space_models/ | false | false | self | 161 | {'enabled': False, 'images': [{'id': 'IW4BIbqIoWGvOb7JyeytdH_PRyirauCdJvItaQJO0R0', 'resolutions': [{'height': 54, 'url': 'https://external-preview.redd.it/0zZrONM5IdNTvpfpCj7mJ_jiUFLvW6tISQUrCzcTCJQ.jpg?width=108&crop=smart&auto=webp&s=6b29d466cb134847673cd3a57775f5c299180307', 'width': 108}, {'height': 108, 'url': 'h... |
Why Mistral-7b is repeating the promp everytime I ask him something? | 1 | Hi so a I finetuned a simple mistral-7b with my data, but every time I ask something then in the answer string it also returns the prompt question.
Here is my code I use to run finetuned mistral model:
import torch
from transformers import AutoTokenizer, AutoModelForCausalLM, BitsAndBytesConfig
from... | 2023-12-07T01:57:58 | https://www.reddit.com/r/LocalLLaMA/comments/18ckjiz/why_mistral7b_is_repeating_the_promp_everytime_i/ | datapim | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 18ckjiz | false | null | t3_18ckjiz | /r/LocalLLaMA/comments/18ckjiz/why_mistral7b_is_repeating_the_promp_everytime_i/ | false | false | self | 1 | null |
LMStudio cant find/see/use models like stable video or text to image? | 1 | Just curious.. I see them on HuggingFace, but I cant get them to show up to download and use in LMStudio. Is that a limitation/block of LMStudio?
Can you download them from HuggingFace manually then load them in to LMStudio? | 2023-12-07T01:06:50 | https://www.reddit.com/r/LocalLLaMA/comments/18cjj9o/lmstudio_cant_findseeuse_models_like_stable_video/ | Dry-Vermicelli-682 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 18cjj9o | false | null | t3_18cjj9o | /r/LocalLLaMA/comments/18cjj9o/lmstudio_cant_findseeuse_models_like_stable_video/ | false | false | self | 1 | null |
Starling-7b thinks it's GPT-4? | 2 | I'm new to LLLMs. I tried starling-7b. And asked
***Who are you?***
And got following response:
*I am an AI language model called OpenAI GPT-4, designed to assist you*
*with various tasks and engage in meaningful conversations. I am not a*
*human, but rather a highly advanced machine learning algorithm that h... | 2023-12-07T01:05:33 | https://www.reddit.com/r/LocalLLaMA/comments/18cjicf/starling7b_thinks_its_gpt4/ | robustrobustrobust | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 18cjicf | false | null | t3_18cjicf | /r/LocalLLaMA/comments/18cjicf/starling7b_thinks_its_gpt4/ | false | false | self | 2 | null |
deepseek-llm-67b-chat.Q5_K_M.gguf failing miserably on some simple Python code. | 3 | I'm trying out the following model. deepseek-llm-67b-chat.Q5_K_M.gguf , using the text generation web UI. I have it writing some python code utilizing OpenCV to do some simple image processing. The code it generates not only has logic and missing function type errors but is making very strange errors where it's insert... | 2023-12-07T01:01:25 | https://www.reddit.com/r/LocalLLaMA/comments/18cjfdv/deepseekllm67bchatq5_k_mgguf_failing_miserably_on/ | w7gg33h | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 18cjfdv | false | null | t3_18cjfdv | /r/LocalLLaMA/comments/18cjfdv/deepseekllm67bchatq5_k_mgguf_failing_miserably_on/ | false | false | self | 3 | null |
Deepseek-Coder which one? TheBloke, Second-State? ThingHatis? | 1 | [removed] | 2023-12-07T00:55:57 | https://www.reddit.com/r/LocalLLaMA/comments/18cjb8k/deepseekcoder_which_one_thebloke_secondstate/ | Dry-Vermicelli-682 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 18cjb8k | false | null | t3_18cjb8k | /r/LocalLLaMA/comments/18cjb8k/deepseekcoder_which_one_thebloke_secondstate/ | false | false | self | 1 | null |
16 Gemini AI Videos in 1 Video - Fully Accurate Subtitles and Fully Chaptered - 4K - NEWS | 1 | [removed] | 2023-12-07T00:46:57 | https://www.reddit.com/r/LocalLLaMA/comments/18cj52w/16_gemini_ai_videos_in_1_video_fully_accurate/ | CeFurkan | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 18cj52w | false | null | t3_18cj52w | /r/LocalLLaMA/comments/18cj52w/16_gemini_ai_videos_in_1_video_fully_accurate/ | false | false | default | 1 | {'enabled': False, 'images': [{'id': 'EulzYy79U6coNNqQOowZFkjO3m9RY0WQj4jj2O_M8J8', 'resolutions': [{'height': 81, 'url': 'https://external-preview.redd.it/VCxB8NuOHX_XDhvuqmPaiWBavqxcvXhb7HquDIHECNU.jpg?width=108&crop=smart&auto=webp&s=3991af0adc59f2926574b005e4a7c6355bc9c164', 'width': 108}, {'height': 162, 'url': 'h... |
Is fine-tuned LLaMA cheaper than GPT? | 2 | I'm building an AI therapist that I'd like to have a fairly generous free tier (not looking to make money right now) and I need a cheap fine tuned model I can pay for per-token.
GPT 3.5 Turbo when fine tuned jumps up 9x in costs. ($0.003 to $0.028 /1k tokens). I know Llama can be comparable to 3.5 Turbo in pricing... | 2023-12-07T00:01:28 | https://www.reddit.com/r/LocalLLaMA/comments/18ci7hg/is_finetuned_llama_cheaper_than_gpt/ | Leadership_Upper | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 18ci7hg | false | null | t3_18ci7hg | /r/LocalLLaMA/comments/18ci7hg/is_finetuned_llama_cheaper_than_gpt/ | false | false | self | 2 | null |
Any other C# people out there? Would love some feedback on my Blazor ChatGPT copy | 7 | As the title says, the project is a Local LLM ChatGPT copy built with Blazor WebAssembly, SignalR, and WebAPI and fluentUI that mirrors chatGPT's functionality when it launched.
All feedback, suggestions, contributions are welcome!! Its my first \*serious\* open source project, so be kind :)
Feel free to check out th... | 2023-12-06T23:41:13 | https://www.reddit.com/r/LocalLLaMA/comments/18chrm8/any_other_c_people_out_there_would_love_some/ | llamasaresavager | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 18chrm8 | false | null | t3_18chrm8 | /r/LocalLLaMA/comments/18chrm8/any_other_c_people_out_there_would_love_some/ | false | false | self | 7 | {'enabled': False, 'images': [{'id': 'Mrz8s-oPffEHkkjw-_EcfmOZfFahAH3yzc8dMmEtG7w', 'resolutions': [{'height': 54, 'url': 'https://external-preview.redd.it/caKRA5iys3L7wlfMTV0QrOKV5gADc36G9LmFyfhX9vI.jpg?width=108&crop=smart&auto=webp&s=772c7ab0b62b05d7879433ca2a228ac661cc8464', 'width': 108}, {'height': 108, 'url': 'h... |
Contradictory answers from Meditron 7b and 70b | 2 | I downloaded and ran the 7b and 70b version of [Meditron](https://huggingface.co/epfl-llm), a medically-trained adaptation of Llama 2, through [ollama](https://ollama.ai/library/meditron) and thought, as a first test to ask about some prominent misinformation. The result was startling:
**Q: Is Ivermectin a cure for Co... | 2023-12-06T22:48:19 | https://www.reddit.com/r/LocalLLaMA/comments/18cgl4c/contradictory_answers_from_meditron_7b_and_70b/ | stannenb | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 18cgl4c | false | null | t3_18cgl4c | /r/LocalLLaMA/comments/18cgl4c/contradictory_answers_from_meditron_7b_and_70b/ | false | false | self | 2 | {'enabled': False, 'images': [{'id': 'w1hAAtxdQOJoIN3eizX7QuUCCo0-KHqGOI_U9Be_R6U', 'resolutions': [{'height': 58, 'url': 'https://external-preview.redd.it/nGmXy2bmtc_jkfoli3R1T5nF_fQaGNr5dL7_9sShkA4.jpg?width=108&crop=smart&auto=webp&s=817adfc5efe69fac6225cb04b2eece656b6b9eb0', 'width': 108}, {'height': 116, 'url': 'h... |
Any Good 384 dimension embedding model? | 1 | [removed] | 2023-12-06T22:46:00 | https://www.reddit.com/r/LocalLLaMA/comments/18cgja7/any_good_384_dimension_embedding_model/ | Nnadivictory | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 18cgja7 | false | null | t3_18cgja7 | /r/LocalLLaMA/comments/18cgja7/any_good_384_dimension_embedding_model/ | false | false | self | 1 | null |
Does anyone have a working PDF Q&A bot I could see and ask questions about? | 1 | [removed] | 2023-12-06T22:44:49 | https://www.reddit.com/r/LocalLLaMA/comments/18cgid0/does_anyone_have_a_working_pdf_qa_bot_i_could_see/ | Future_Might_8194 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 18cgid0 | false | null | t3_18cgid0 | /r/LocalLLaMA/comments/18cgid0/does_anyone_have_a_working_pdf_qa_bot_i_could_see/ | false | false | self | 1 | null |
OpenCV calls for help - cross post from r/computervision | 1 | 2023-12-06T22:39:24 | https://reddit.com/r/computervision/comments/18c2bah/opencv_calls_for_help/ | reggiestered | reddit.com | 1970-01-01T00:00:00 | 0 | {} | 18cgdym | false | null | t3_18cgdym | /r/LocalLLaMA/comments/18cgdym/opencv_calls_for_help_cross_post_from/ | false | false | default | 1 | {'enabled': False, 'images': [{'id': '4fW867OcjCZDpl2iyekHz5JbuFnOuMADoaGIuvyamWo', 'resolutions': [{'height': 56, 'url': 'https://external-preview.redd.it/uQqwakQCUZrQJRHQALN7337TCef-VZ0t-RP9T1PNqkE.jpg?width=108&crop=smart&auto=webp&s=99762c3b3d6385b694aba0c552e0c82a6984ba9d', 'width': 108}, {'height': 113, 'url': 'h... | |
Gemini Pro fails the famous 6 sisters vs. 1 sister test | 162 | 2023-12-06T22:32:58 | nderstand2grow | i.redd.it | 1970-01-01T00:00:00 | 0 | {} | 18cg92s | false | null | t3_18cg92s | /r/LocalLLaMA/comments/18cg92s/gemini_pro_fails_the_famous_6_sisters_vs_1_sister/ | false | false | 162 | {'enabled': True, 'images': [{'id': 'MpopBDX0DCkrTXzxGFThHoiOGKTT_qmYZmNhDwjK-ZA', 'resolutions': [{'height': 30, 'url': 'https://preview.redd.it/1ghwvu7b4r4c1.png?width=108&crop=smart&auto=webp&s=54a917bc9110d9dd833ed4b31733bb9a6ed8b8a2', 'width': 108}, {'height': 60, 'url': 'https://preview.redd.it/1ghwvu7b4r4c1.png?... | |||
history data | 1 | What is a good Model 7 or 13b that has a lot of history data? | 2023-12-06T22:32:24 | https://www.reddit.com/r/LocalLLaMA/comments/18cg8mr/history_data/ | Creative_Bottle_3225 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 18cg8mr | false | null | t3_18cg8mr | /r/LocalLLaMA/comments/18cg8mr/history_data/ | false | false | self | 1 | null |
here's my test of Gemini vs GPT 3.5 and Claude. | 1 | [https://x.com/chigbunduebube/status/1732520036705685997?s=20](https://x.com/chigbunduebube/status/1732520036705685997?s=20)
https://preview.redd.it/g17zbsuz2r4c1.png?width=822&format=png&auto=webp&s=1a8302f92e8880de8a333305345add8a7e3373f7 | 2023-12-06T22:25:46 | https://www.reddit.com/r/LocalLLaMA/comments/18cg36c/heres_my_test_of_gemini_vs_gpt_35_and_claude/ | SnooPeanuts6304 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 18cg36c | false | null | t3_18cg36c | /r/LocalLLaMA/comments/18cg36c/heres_my_test_of_gemini_vs_gpt_35_and_claude/ | false | false | 1 | {'enabled': False, 'images': [{'id': '4KhzonGw93bV3w_3wczzWuc71uF9tlIOiOXGkrY5sl0', 'resolutions': [{'height': 108, 'url': 'https://external-preview.redd.it/-3OVASNleyGVgpxk3IxQygJPSgsGJaIPSA0SEPPtK24.jpg?width=108&crop=smart&auto=webp&s=2ade80245ad7f473b6259e6a5be34f75d9949cdf', 'width': 108}], 'source': {'height': 18... | |
llama + CompyUI | 1 | [removed] | 2023-12-06T21:16:14 | https://www.reddit.com/r/LocalLLaMA/comments/18ceh11/llama_compyui/ | kuroro86 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 18ceh11 | false | null | t3_18ceh11 | /r/LocalLLaMA/comments/18ceh11/llama_compyui/ | false | false | self | 1 | null |
What happens when you merge Psyfighter & Orca 2? You get psyonic cetacean 20B | 5 | This model is focused on storywriting and text adventure, with a side order of Assistant and Chat functionality.
https://huggingface.co/jebcarter/psyonic-cetacean-20B | 2023-12-06T21:13:08 | https://www.reddit.com/r/LocalLLaMA/comments/18ceee9/what_happens_when_you_merge_psyfighter_orca_2_you/ | Majestical-psyche | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 18ceee9 | false | null | t3_18ceee9 | /r/LocalLLaMA/comments/18ceee9/what_happens_when_you_merge_psyfighter_orca_2_you/ | false | false | self | 5 | {'enabled': False, 'images': [{'id': 'ZPRo5bIxMAF3GO3tOtv1KM3Cey_YD0jsuNI56gDTOnE', 'resolutions': [{'height': 58, 'url': 'https://external-preview.redd.it/J3JqP2XXmR5mUTIcwynf2O04jXa2YrLSBHqT21H6hgI.jpg?width=108&crop=smart&auto=webp&s=399a040baa5ad62387e5b8262e2b6db3f7f43ae3', 'width': 108}, {'height': 116, 'url': 'h... |
Optimum-NVIDIA - 28x faster inference in just 1 line of code !? | 57 | [https://huggingface.co/blog/optimum-nvidia](https://huggingface.co/blog/optimum-nvidia)
Well... these are big claims. Will we see this in Exllama / llama.cpp etc? | 2023-12-06T21:06:50 | https://www.reddit.com/r/LocalLLaMA/comments/18ce925/optimumnvidia_28x_faster_inference_in_just_1_line/ | CasimirsBlake | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 18ce925 | false | null | t3_18ce925 | /r/LocalLLaMA/comments/18ce925/optimumnvidia_28x_faster_inference_in_just_1_line/ | false | false | self | 57 | {'enabled': False, 'images': [{'id': '9y4XWq0o18trOsOEzAYtqYD9b5KBIah7LZUzxIb8CKQ', 'resolutions': [{'height': 60, 'url': 'https://external-preview.redd.it/n7lPklFa1opt5CJ4HgVVXuwIl8Jp9Q1RdW5MNplFxoo.jpg?width=108&crop=smart&auto=webp&s=76d88597b0b52978daf0dfe0cb9ac10705fa4f1d', 'width': 108}, {'height': 121, 'url': 'h... |
My first real life test Gemini vs GPT-4. Am I surprised or shocked? :) | 1 | 2023-12-06T20:53:53 | https://www.reddit.com/gallery/18cdxyw | CeFurkan | reddit.com | 1970-01-01T00:00:00 | 0 | {} | 18cdxyw | false | null | t3_18cdxyw | /r/LocalLLaMA/comments/18cdxyw/my_first_real_life_test_gemini_vs_gpt4_am_i/ | false | false | 1 | null | ||
State of the Literature on Context Correctness | 3 | I'm looking to get the bigger picture of the degree to which correctness in regard to the context window has been studied. I recall reading some work suggesting that recent models with large context windows were only accurate out to some subportion of the window, but that this was consistent, measurable, and theoretica... | 2023-12-06T20:40:07 | https://www.reddit.com/r/LocalLLaMA/comments/18cdm75/state_of_the_literature_on_context_correctness/ | Spaduf | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 18cdm75 | false | null | t3_18cdm75 | /r/LocalLLaMA/comments/18cdm75/state_of_the_literature_on_context_correctness/ | false | false | self | 3 | null |
Best way to configure GGUF Mistral | 1 | Hi everyone,
I hope you are having a good day! I recently pushed a GGUF version of Mistral on my server. It’s got 4 vCPU, and 8GB of RAM. I get around 5 tokens per second on it. I was wondering if there is a way to speed this up further with LLAMA CPP??
I experimented with different settings and found that t... | 2023-12-06T20:37:34 | https://www.reddit.com/r/LocalLLaMA/comments/18cdk5d/best_way_to_configure_gguf_mistral/ | GoodUnderstanding728 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 18cdk5d | false | null | t3_18cdk5d | /r/LocalLLaMA/comments/18cdk5d/best_way_to_configure_gguf_mistral/ | false | false | self | 1 | null |
Show: I hosted Meta's Seamless models in GitHub | 4 | Meta's new Seamless models sound (pun intended) really compelling so I created a monorepo (code + all 40 GB of model files) containing all the relevant files.
[https://github.com/xetdata/seamless\_monorepo](https://github.com/xetdata/seamless_monorepo) | 2023-12-06T20:35:36 | https://www.reddit.com/r/LocalLLaMA/comments/18cdihw/show_i_hosted_metas_seamless_models_in_github/ | semicausal | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 18cdihw | false | null | t3_18cdihw | /r/LocalLLaMA/comments/18cdihw/show_i_hosted_metas_seamless_models_in_github/ | false | false | self | 4 | {'enabled': False, 'images': [{'id': '-BGokwzfB4WIJTt_Y2bU9BlhNVEey5wkIONPxWryjOE', 'resolutions': [{'height': 54, 'url': 'https://external-preview.redd.it/t1Ut-10eo9rIQD8bNE0WRTvt2SSeidBLo-luN9EhMIs.jpg?width=108&crop=smart&auto=webp&s=dd2947b799c54c6aab8df6f65e6466e15616e431', 'width': 108}, {'height': 108, 'url': 'h... |
How I Experiment with Open LLMs | 32 | Over the last four months, I've spent 200+ hours playing with open-source models on HuggingFace.
And I've found that, while benchmarks are decent signal, they don't always translate into practical effectiveness or correlate with how I'm planning on using a model.
So, I want to pull back the curtain and share my 'vibe... | 2023-12-06T20:22:28 | https://www.reddit.com/r/LocalLLaMA/comments/18cd7ok/how_i_experiment_with_open_llms/ | datascienceharp | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 18cd7ok | false | null | t3_18cd7ok | /r/LocalLLaMA/comments/18cd7ok/how_i_experiment_with_open_llms/ | false | false | self | 32 | null |
Finetuning, dataset formatting for text generation (wide range of prose) | 1 | [removed] | 2023-12-06T19:19:46 | https://www.reddit.com/r/LocalLLaMA/comments/18cbr24/finetuning_dataset_formatting_for_text_generation/ | _winterwoods | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 18cbr24 | false | null | t3_18cbr24 | /r/LocalLLaMA/comments/18cbr24/finetuning_dataset_formatting_for_text_generation/ | false | false | self | 1 | null |
What are some good tools for text2audio that I can run locally? | 4 | I have been playing with LMS studio and some of the 20B models, and I was wondering what other tools I could use to convert the text into audio.
I would like to run it locally as I don’t want to pay for a monthly subscription. I have got a 3090/64gb/12700k | 2023-12-06T18:48:59 | https://www.reddit.com/r/LocalLLaMA/comments/18cb143/what_are_some_good_tools_for_text2audio_that_i/ | mald55 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 18cb143 | false | null | t3_18cb143 | /r/LocalLLaMA/comments/18cb143/what_are_some_good_tools_for_text2audio_that_i/ | false | false | self | 4 | null |
deepseek trained based on Open AI? | 3 | I was using deepseek coder 33B to summarize meeting minutes. Then it outputs this summary to my surprise suggesting it was trained based on models from open AI?
" As an AI developed by OpenAI, I am designed to assist with programming related queries. However, the text provided appears to be a transcript of a discussi... | 2023-12-06T18:46:26 | https://www.reddit.com/r/LocalLLaMA/comments/18cayyh/deepseek_trained_based_on_open_ai/ | peterwu00 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 18cayyh | false | null | t3_18cayyh | /r/LocalLLaMA/comments/18cayyh/deepseek_trained_based_on_open_ai/ | false | false | self | 3 | null |
OpenAI Switch Kit: Swap OpenAI with any open-source model | 41 | Hey guys,
We built an open-source AI SDK (Python & JavaScript) that provides a drop-in replacement for OpenAI’s chat completion endpoint. We'd love to know what you think so we can make switching as easy as possible and get more folks on open-source.
You can swap in almost any open-source model on Huggingface. Huggin... | 2023-12-06T18:43:38 | https://www.reddit.com/r/LocalLLaMA/comments/18cawjr/openai_switch_kit_swap_openai_with_any_opensource/ | UnfamiliarAfternoons | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 18cawjr | false | null | t3_18cawjr | /r/LocalLLaMA/comments/18cawjr/openai_switch_kit_swap_openai_with_any_opensource/ | false | false | self | 41 | {'enabled': False, 'images': [{'id': 'Gy3S0WOyX2rCy7_cN1nsTwWj1UHErFo8n1DRP2b2CU4', 'resolutions': [{'height': 56, 'url': 'https://external-preview.redd.it/VjCPWlFDVtaTT_oULaNBM78i0HdDgMuqaE188c08lBE.jpg?width=108&crop=smart&auto=webp&s=976c5721eca753bce007cc34425edafb04d1191b', 'width': 108}, {'height': 113, 'url': 'h... |
One line local run to spin up model of your choice, parallel runs, chatbot UI and more! | 8 | Hey LocalLLaMA, writing from Kurtosis Tech where we're building dev tools to make it easier for developers to get up and running with composable, reproducible environments. We wrote a v0 of an LLM package that allows you to run models locally or on the cloud, spins up a chat UI, and fully containerized so you can run m... | 2023-12-06T18:34:44 | https://www.reddit.com/r/LocalLLaMA/comments/18cap4c/one_line_local_run_to_spin_up_model_of_your/ | OrdinaryParkBench | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 18cap4c | false | null | t3_18cap4c | /r/LocalLLaMA/comments/18cap4c/one_line_local_run_to_spin_up_model_of_your/ | false | false | self | 8 | {'enabled': False, 'images': [{'id': 'RbjPyMCslOiq3x05q3VyXvKSOReWGa_jconx-czvCS8', 'resolutions': [{'height': 54, 'url': 'https://external-preview.redd.it/ZCePtexfF-nXsc2QIeKy3qv8I2W0lmcwysDtJ2c3ZfU.jpg?width=108&crop=smart&auto=webp&s=c388e3e2d9d8400f58147274e27e1b44ebf4f5c0', 'width': 108}, {'height': 108, 'url': 'h... |
Recent updates on the LLM Explorer: surpassed 13K models in the db | 1 | [removed] | 2023-12-06T18:34:44 | https://www.reddit.com/r/LocalLLaMA/comments/18cap46/recent_updates_on_the_llm_explorer_surpassed_13k/ | Greg_Z_ | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 18cap46 | false | null | t3_18cap46 | /r/LocalLLaMA/comments/18cap46/recent_updates_on_the_llm_explorer_surpassed_13k/ | false | false | 1 | null | |
Gemini Nano is a 4bit 3.25B LLM | 230 | The nano version of gemini is intended for android devices.
There's also a 1.8B version for phones with smaller rams | 2023-12-06T18:12:38 | https://x.com/zacharynado/status/1732425598465900708?s=20 | Amgadoz | x.com | 1970-01-01T00:00:00 | 0 | {} | 18ca6k3 | false | null | t3_18ca6k3 | /r/LocalLLaMA/comments/18ca6k3/gemini_nano_is_a_4bit_325b_llm/ | false | false | 230 | {'enabled': False, 'images': [{'id': '7QPPadrMYx8PP6CrcamnmmQEi1TPGvlRMr3RSYF30vU', 'resolutions': [{'height': 40, 'url': 'https://external-preview.redd.it/b66Rrwd7AHIeukwzmAi8K9Mi-uagX0H0aExVdeogiMs.jpg?width=108&crop=smart&auto=webp&s=ccee811a8458523fd7e0cf35a0238e3f83436ef8', 'width': 108}, {'height': 81, 'url': 'ht... | |
AMD Presents: Advancing AI - AMD is currently giving a live presentation with a lot of technical detail. (see post) | 1 | [removed] | 2023-12-06T18:11:41 | https://www.reddit.com/r/LocalLLaMA/comments/18ca5ra/amd_presents_advancing_ai_amd_is_currently_giving/ | TheMadHobbyist | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 18ca5ra | false | null | t3_18ca5ra | /r/LocalLLaMA/comments/18ca5ra/amd_presents_advancing_ai_amd_is_currently_giving/ | false | false | self | 1 | {'enabled': False, 'images': [{'id': 'QsWQPeNYjJe8G4eflAhnrVDCju8G-uVdD1dCx5MrdPY', 'resolutions': [{'height': 81, 'url': 'https://external-preview.redd.it/xYhDbjuHAGKZrM8ouJc7O3yyDXFhmzJi9c110HxVGV4.jpg?width=108&crop=smart&auto=webp&s=42e9b5475d877b9492ebbc8a81242e7066558130', 'width': 108}, {'height': 162, 'url': 'h... |
MI300X might just blow H100 out of the water! | 1 | [removed] | 2023-12-06T18:10:29 | https://www.reddit.com/r/LocalLLaMA/comments/18ca4s4/mi300x_might_just_blow_h100_out_of_the_water/ | Feeling-Currency-360 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 18ca4s4 | false | null | t3_18ca4s4 | /r/LocalLLaMA/comments/18ca4s4/mi300x_might_just_blow_h100_out_of_the_water/ | false | false | self | 1 | {'enabled': False, 'images': [{'id': 'QsWQPeNYjJe8G4eflAhnrVDCju8G-uVdD1dCx5MrdPY', 'resolutions': [{'height': 81, 'url': 'https://external-preview.redd.it/xYhDbjuHAGKZrM8ouJc7O3yyDXFhmzJi9c110HxVGV4.jpg?width=108&crop=smart&auto=webp&s=42e9b5475d877b9492ebbc8a81242e7066558130', 'width': 108}, {'height': 162, 'url': 'h... |
LLM on smartphones with large RAM | 4 | Hi all,
2 days ago Oneplus phone manufacturer, announced Oneplus 12. According to the specifications it has 24 gb of ram. Do you think that we can run mistral 7b or even something larger on our smartphones with decent speed and power usage? If so what do you think about the current trend as Google announced Pixel 8 pho... | 2023-12-06T18:07:29 | https://www.reddit.com/r/LocalLLaMA/comments/18ca2at/llm_on_smartphones_with_large_ram/ | rapidashlord | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 18ca2at | false | null | t3_18ca2at | /r/LocalLLaMA/comments/18ca2at/llm_on_smartphones_with_large_ram/ | false | false | self | 4 | null |
Is this something useful? I created a node visualizer for ChatGPT API | 2 | 2023-12-06T17:58:54 | https://v.redd.it/bp20v51nmp4c1 | ribeirao | v.redd.it | 1970-01-01T00:00:00 | 0 | {} | 18c9um1 | false | {'reddit_video': {'bitrate_kbps': 5000, 'dash_url': 'https://v.redd.it/bp20v51nmp4c1/DASHPlaylist.mpd?a=1704477551%2CN2ExZWNlYzNiM2ExZmM4MmRhZmFmYmI5MjBjOGJmZDEzMWMxMTM4YjY1YTkxMzJhM2E2MDc2YzhhNjU1ZTI5YQ%3D%3D&v=1&f=sd', 'duration': 32, 'fallback_url': 'https://v.redd.it/bp20v51nmp4c1/DASH_1080.mp4?source=fallback', 'h... | t3_18c9um1 | /r/LocalLLaMA/comments/18c9um1/is_this_something_useful_i_created_a_node/ | false | false | 2 | {'enabled': False, 'images': [{'id': 'N2Y1cTloeWdycDRjMbE9A718Zo8v9ObzhNp2V033x0GxHpIzo8nGlYVqLHKF', 'resolutions': [{'height': 60, 'url': 'https://external-preview.redd.it/N2Y1cTloeWdycDRjMbE9A718Zo8v9ObzhNp2V033x0GxHpIzo8nGlYVqLHKF.png?width=108&crop=smart&format=pjpg&auto=webp&s=21d8dd2ec7ef665bbe42cbaaba1c23f2d4548... | ||
how to evaluate open-source LLMs using a custom benchmark? | 2 | i want to evaluate open-source LLMs in the context of education, and as I haven't found any educational dataset, i want to create a custom benchmark to evaluate open-source LLMs but i am not sure of how should i proceed, any help please (tutorials, blogs..)? | 2023-12-06T17:49:38 | https://www.reddit.com/r/LocalLLaMA/comments/18c9ms7/how_to_evaluate_opensource_llms_using_a_custom/ | Life_Ask2806 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 18c9ms7 | false | null | t3_18c9ms7 | /r/LocalLLaMA/comments/18c9ms7/how_to_evaluate_opensource_llms_using_a_custom/ | false | false | self | 2 | null |
Gemini "The World's Most Capable Model" vs GPT-4 on coding | 72 | I asked the same question to both and had Gemini answer twice, same result both times. | 2023-12-06T17:36:26 | https://www.reddit.com/gallery/18c9bqs | TheEclecticScholar | reddit.com | 1970-01-01T00:00:00 | 0 | {} | 18c9bqs | false | null | t3_18c9bqs | /r/LocalLLaMA/comments/18c9bqs/gemini_the_worlds_most_capable_model_vs_gpt4_on/ | false | false | 72 | null |
Subsets and Splits
No community queries yet
The top public SQL queries from the community will appear here once available.