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 ⌀ |
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
Does anyone know if any uncensored multilingual model exists? | 13 | I recently tried OpenBuddy and it was pretty decent as local model in Japanese language. At least it was better than any Japanese-focused model released by Japanese corporations. But when it comes to nsfw things it turns into chatgpt and refusing to response.
I also tried RWKV(raven and world models) but honestly it's ... | 2023-06-17T03:09:15 | https://www.reddit.com/r/LocalLLaMA/comments/14bfs6a/does_anyone_know_if_any_uncensored_multilingual/ | Beautiful-Ad2181 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 14bfs6a | false | null | t3_14bfs6a | /r/LocalLLaMA/comments/14bfs6a/does_anyone_know_if_any_uncensored_multilingual/ | false | false | self | 13 | null |
Meta reportedly wants to make LLaMA v2 available for commercial use | 168 | This comes from *The Information*, a subscription based publication made for tech executives. The [full article is paywalled](https://www.theinformation.com/articles/meta-wants-companies-to-make-money-off-its-open-source-ai-in-challenge-to-google) but here's the intro:
>Meta Platforms CEO Mark Zuckerberg and his deput... | 2023-06-17T03:05:58 | https://www.reddit.com/r/LocalLLaMA/comments/14bfpwi/meta_reportedly_wants_to_make_llama_v2_available/ | llamaShill | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 14bfpwi | false | null | t3_14bfpwi | /r/LocalLLaMA/comments/14bfpwi/meta_reportedly_wants_to_make_llama_v2_available/ | false | false | self | 168 | {'enabled': False, 'images': [{'id': 'K3mJS5QAvFPQp9UO9nCAh8cDZb2w0a_Va2a2L3IwnHs', 'resolutions': [{'height': 60, 'url': 'https://external-preview.redd.it/JIVlwx_zSZmSG1SFNAAHXhlJLBXZlBlBBpDwa0o3d1Y.jpg?width=108&crop=smart&auto=webp&s=232b13b494d16530c85a2400e9adad86d5830b11', 'width': 108}, {'height': 121, 'url': 'h... |
Base models are all uncensored right? | 5 | Such as the open llama 3b and 7B base models? | 2023-06-17T02:16:49 | https://www.reddit.com/r/LocalLLaMA/comments/14bere3/base_models_are_all_uncensored_right/ | Tasty-Lobster-8915 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 14bere3 | false | null | t3_14bere3 | /r/LocalLLaMA/comments/14bere3/base_models_are_all_uncensored_right/ | false | false | self | 5 | null |
EXLlama support added to oobabooga-text-generation-webui | 119 | 2023-06-17T00:13:43 | https://github.com/oobabooga/text-generation-webui/commit/9f40032d32165773337e6a6c60de39d3f3beb77d | panchovix | github.com | 1970-01-01T00:00:00 | 0 | {} | 14bc7ug | false | null | t3_14bc7ug | /r/LocalLLaMA/comments/14bc7ug/exllama_support_added_to/ | false | false | 119 | {'enabled': False, 'images': [{'id': 'K1Btc2tnb4mW5SaUKQuVDRHyun2UZv9I85wrDQolNBI', 'resolutions': [{'height': 54, 'url': 'https://external-preview.redd.it/WBwPr26ZKAbreRZsb7QXwzLHKL0dstUS3HCEcsV0yEw.jpg?width=108&crop=smart&auto=webp&s=509348a4936cd56dcb8065f19a1ad83851791644', 'width': 108}, {'height': 108, 'url': 'h... | ||
OK, since people here agreed decentralized AI training could be a powerful if possible. I'm opening r/BuildThisAI for intentional discussion on achieving this goal. This is directly inspired by a QnA I got to attend w/ Sam Altman (Info post): | 1 | [removed] | 2023-06-16T23:26:22 | [deleted] | 1970-01-01T00:00:00 | 0 | {} | 14bb5sm | false | null | t3_14bb5sm | /r/LocalLLaMA/comments/14bb5sm/ok_since_people_here_agreed_decentralized_ai/ | false | false | default | 1 | null | ||
Any model that can do basic reasoning? | 26 | \`\`\`Sally (a girl) has 3 brothers. Each brother has 2 sisters. How many sisters does sally have?\`\`\`
Is there any open model that can reliably answer this question and also offer the right explanations?
I've been playing a lot with these models, and while they can be extremely good for story-telling or embody a s... | 2023-06-16T23:19:40 | https://www.reddit.com/r/LocalLLaMA/comments/14bb08o/any_model_that_can_do_basic_reasoning/ | shaman-warrior | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 14bb08o | false | null | t3_14bb08o | /r/LocalLLaMA/comments/14bb08o/any_model_that_can_do_basic_reasoning/ | false | false | self | 26 | null |
What is the best VPS / cloud server to run LLMs on ? | 13 | For LLama 65B 8bit you require 74GB of RAM (from the wiki). For a few LLM runs, its probably cheaper to hire a cloud server instead of buying a huge machine to run it yourself.
What cloud providers are there that give this much RAM? Are there any free ones?
If you are going to buy your own machine, what are your opti... | 2023-06-16T22:51:22 | https://www.reddit.com/r/LocalLLaMA/comments/14bactj/what_is_the_best_vps_cloud_server_to_run_llms_on/ | [deleted] | self.LocalLLaMA | 2023-06-16T23:02:15 | 0 | {} | 14bactj | false | null | t3_14bactj | /r/LocalLLaMA/comments/14bactj/what_is_the_best_vps_cloud_server_to_run_llms_on/ | false | false | self | 13 | null |
[Feedback Request] Monitor LLM Hallucinations - with ChatGPT! | 4 | [removed] | 2023-06-16T21:37:17 | https://www.reddit.com/r/LocalLLaMA/comments/14b8n9t/feedback_request_monitor_llm_hallucinations_with/ | shurturgal19 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 14b8n9t | false | null | t3_14b8n9t | /r/LocalLLaMA/comments/14b8n9t/feedback_request_monitor_llm_hallucinations_with/ | false | false | default | 4 | null |
w7900 for llama | 3 | Hello everybody, AMD recently released the w7900, a graphics card with 48gb memory. The few tests that are available suggest that it is competitive from a price performance point of view to at least the older A6000 by Nvidia.
That said, no tests with LLMs were conducted (which does not surprise me tbh). Could this car... | 2023-06-16T20:21:07 | https://www.reddit.com/r/LocalLLaMA/comments/14b6z1e/w7900_for_llama/ | RabbitHole32 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 14b6z1e | false | null | t3_14b6z1e | /r/LocalLLaMA/comments/14b6z1e/w7900_for_llama/ | false | false | self | 3 | null |
What Can I Run | 1 | [removed] | 2023-06-16T20:18:49 | https://www.reddit.com/r/LocalLLaMA/comments/14b6wz7/what_can_i_run/ | Creative-Match7817 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 14b6wz7 | false | null | t3_14b6wz7 | /r/LocalLLaMA/comments/14b6wz7/what_can_i_run/ | false | false | default | 1 | null |
I created a site to share Opensource LLMs in chatbot and API form | 5 | [removed] | 2023-06-16T19:51:14 | https://www.reddit.com/r/LocalLLaMA/comments/14b68x6/i_created_a_site_to_share_opensource_llms_in/ | ortegaalfredo | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 14b68x6 | false | null | t3_14b68x6 | /r/LocalLLaMA/comments/14b68x6/i_created_a_site_to_share_opensource_llms_in/ | false | false | default | 5 | null |
Falcon 40B instruct tuned on Open Assistant data - model weights Open Source | 6 | 2023-06-16T19:46:09 | https://gpt-gm.h2o.ai/ | ricklamers | gpt-gm.h2o.ai | 1970-01-01T00:00:00 | 0 | {} | 14b64et | false | null | t3_14b64et | /r/LocalLLaMA/comments/14b64et/falcon_40b_instruct_tuned_on_open_assistant_data/ | false | false | default | 6 | null | |
Which Linux distro is best for AI stuff? | 1 | [removed] | 2023-06-16T19:43:31 | https://www.reddit.com/r/LocalLLaMA/comments/14b620d/which_linux_distro_is_best_for_ai_stuff/ | ThrowawayProgress99 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 14b620d | false | null | t3_14b620d | /r/LocalLLaMA/comments/14b620d/which_linux_distro_is_best_for_ai_stuff/ | false | false | default | 1 | null |
Robin V2 model reaches top of LLM leaderboard | 84 | 2023-06-16T17:38:39 | https://medium.com/@hkust.ml/robin-v2-launches-achieves-unparalleled-performance-on-openllm-4f6886e822c1 | yahma | medium.com | 1970-01-01T00:00:00 | 0 | {} | 14b2zdu | false | null | t3_14b2zdu | /r/LocalLLaMA/comments/14b2zdu/robin_v2_model_reaches_top_of_llm_leaderboard/ | false | false | 84 | {'enabled': False, 'images': [{'id': 'EyludQq-38PPetVGcAXonPPSk188ZNmvgsHWeGmH_WQ', 'resolutions': [{'height': 58, 'url': 'https://external-preview.redd.it/x2SFNUegVp-i28oXRjfOqovBU2vZhZhy6-tlntzSmPc.jpg?width=108&crop=smart&auto=webp&s=808b475e8072757887d221391905eba6ad61b722', 'width': 108}, {'height': 117, 'url': 'h... | ||
🦜🔗 Building Multi task AI agent with LangChain and using Aim to trace and visualize the executions.. Let's prompt the agent to: i. List 5 supernova facts, ii. Find the latest explosion, iii. Calculate years since the last explosion | 11 | 2023-06-16T17:28:12 | https://v.redd.it/w12wxtjfze6b1 | tatyanaaaaaa | v.redd.it | 1970-01-01T00:00:00 | 0 | {} | 14b2q6n | false | {'reddit_video': {'bitrate_kbps': 4800, 'dash_url': 'https://v.redd.it/w12wxtjfze6b1/DASHPlaylist.mpd?a=1695733629%2CYWI3N2RmYzVlZDVlZTgwZjMyMmZjYWZhNTA0Mjc2N2E3MmVlOWE2NzgwMjAxYTM0ZDM4NzkyOGVhY2E3ZmNlMA%3D%3D&v=1&f=sd', 'duration': 28, 'fallback_url': 'https://v.redd.it/w12wxtjfze6b1/DASH_1080.mp4?source=fallback', 'h... | t3_14b2q6n | /r/LocalLLaMA/comments/14b2q6n/building_multi_task_ai_agent_with_langchain_and/ | false | false | default | 11 | null | |
WizardCoder-15B-1.0 vs ChatGPT coding showdown: 4 webapps * 3 frameworks | 56 | Hello /r/LocalLLaMa!
With yesterday's release of WizardCoder-15B-1.0 (see [official thread](https://www.reddit.com/r/LocalLLaMA/comments/14ajglx/official_wizardcoder15bv10_released_can_achieve/) and [less official thread] (https://www.reddit.com/r/LocalLLaMA/comments/149ir49/new_model_just_dropped_wizardcoder15bv10_m... | 2023-06-16T16:50:36 | https://www.reddit.com/r/LocalLLaMA/comments/14b1tsw/wizardcoder15b10_vs_chatgpt_coding_showdown_4/ | kryptkpr | self.LocalLLaMA | 2023-06-16T17:31:50 | 0 | {} | 14b1tsw | false | null | t3_14b1tsw | /r/LocalLLaMA/comments/14b1tsw/wizardcoder15b10_vs_chatgpt_coding_showdown_4/ | false | false | self | 56 | {'enabled': False, 'images': [{'id': 'QyV2S4rh-pMbnJML_R7bbJcWB2RH98giH_Z_P45_3vo', 'resolutions': [{'height': 58, 'url': 'https://external-preview.redd.it/svHHAck7dSjoulgoGopBQmcysvgwynJ3DcKwn8sX7Zc.jpg?width=108&crop=smart&auto=webp&s=a058206456911026ebb90e4a841787cd0c5c75ec', 'width': 108}, {'height': 116, 'url': 'h... |
RWKV Pile+ seems to be training on far more tokens than any LLM ever has | 93 | Has anyone else noticed [this](https://huggingface.co/BlinkDL/rwkv-4-pileplus)? Seems to be in-progress
Apparently it's being *finetuned* on 1.7T tokens (RedPajama + subset of The Pile v2), *after* already training on the ~800GB of The Pile. As far as public knowledge goes, that's *far* more than any LLM has ever be... | 2023-06-16T16:21:22 | https://www.reddit.com/r/LocalLLaMA/comments/14b147o/rwkv_pile_seems_to_be_training_on_far_more_tokens/ | pedantic_pineapple | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 14b147o | false | null | t3_14b147o | /r/LocalLLaMA/comments/14b147o/rwkv_pile_seems_to_be_training_on_far_more_tokens/ | false | false | self | 93 | {'enabled': False, 'images': [{'id': '0gNI3KsG_0eps01yrutV_yvv3UTcmipaOX5BWN-oTVY', 'resolutions': [{'height': 58, 'url': 'https://external-preview.redd.it/EEw0WAaGvRm-5GaW4ew8WSjHJ45CBmjp2FsLB3IOPOQ.jpg?width=108&crop=smart&auto=webp&s=6fbcda1a2d2fc6cab365d0a844c26ef4274911ba', 'width': 108}, {'height': 116, 'url': 'h... |
Question on fine tuning with LORA | 8 | I tried to fine tune a 7B model using oogaboga text gui. It went well.
When I loaded it on my machine, I was using the quantised version of the model. Llama.cpp gave me a warning saying using Lora’s with quantised models may produce bad quality.
Does anyone know if this is significant? Should I use QLora to train on ... | 2023-06-16T16:06:03 | https://www.reddit.com/r/LocalLLaMA/comments/14b0qkt/question_on_fine_tuning_with_lora/ | Tasty-Lobster-8915 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 14b0qkt | false | null | t3_14b0qkt | /r/LocalLLaMA/comments/14b0qkt/question_on_fine_tuning_with_lora/ | false | false | self | 8 | null |
Why is there not as much cutting edge research into embeddings? | 35 | I know LLMs are flashier, but embeddings are in the same vein, and arguably have more established real world usages right now. Why is there not nearly as many embeddings models and research coming out? The SOTA is still `mpnet-base-v2` (correct me if I'm wrong) which is almost 2 years old now. | 2023-06-16T15:52:06 | https://www.reddit.com/r/LocalLLaMA/comments/14b0dta/why_is_there_not_as_much_cutting_edge_research/ | srvhfvakc | self.LocalLLaMA | 2023-06-16T15:56:19 | 0 | {} | 14b0dta | false | null | t3_14b0dta | /r/LocalLLaMA/comments/14b0dta/why_is_there_not_as_much_cutting_edge_research/ | false | false | self | 35 | null |
Issue Loading 13B Model in Ooba Booga on RTX 4070 with 12GB VRAM | 5 | Hello everyone,
I am currently encountering an issue with the Ooba Booga software on my Windows 10 PC. I'm running the program on a machine with an RTX 4070 GPU, which has 12GB of VRAM.
Whenever I'm trying to load any 13B LLaMA models, I am consistently receiving an error that seems to be related to memory allocatio... | 2023-06-16T15:35:46 | https://www.reddit.com/r/LocalLLaMA/comments/14azzij/issue_loading_13b_model_in_ooba_booga_on_rtx_4070/ | alexthai7 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 14azzij | false | null | t3_14azzij | /r/LocalLLaMA/comments/14azzij/issue_loading_13b_model_in_ooba_booga_on_rtx_4070/ | false | false | self | 5 | null |
PDF form parser with non-text inputs | 1 | [removed] | 2023-06-16T15:30:04 | https://www.reddit.com/r/LocalLLaMA/comments/14azuck/pdf_form_parser_with_nontext_inputs/ | harold__hadrada | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 14azuck | false | null | t3_14azuck | /r/LocalLLaMA/comments/14azuck/pdf_form_parser_with_nontext_inputs/ | false | false | default | 1 | null |
Could a model not be trained by a decentralized network? Like Seti @ home or kinda-sorta like bitcoin. Petals accomplishes this somewhat, but if raw computer power is the only barrier to open-source I'd be happy to try organizing decentalized computing efforts | 55 | Title. If enough people could be reached with a model that is trainable with decentralized computing, in theory, could this not create an (unlikely, but possible) avenue for an open-source model as powerful as Meta's or OpenAI's?
Sorry if this might be a naieve question | 2023-06-16T14:56:20 | https://www.reddit.com/r/LocalLLaMA/comments/14az00q/could_a_model_not_be_trained_by_a_decentralized/ | doublemint2202 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 14az00q | false | null | t3_14az00q | /r/LocalLLaMA/comments/14az00q/could_a_model_not_be_trained_by_a_decentralized/ | false | false | self | 55 | null |
NER but with LLM | 1 | [removed] | 2023-06-16T14:22:34 | https://www.reddit.com/r/LocalLLaMA/comments/14ay6bq/ner_but_with_llm/ | JollyAnteater5339 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 14ay6bq | false | null | t3_14ay6bq | /r/LocalLLaMA/comments/14ay6bq/ner_but_with_llm/ | false | false | default | 1 | null |
best Llama model for Mac M1? | 9 | I have a mac mini m1 256/ 8gb.
What is the best instruct llama model I can run smoothly on this machine without burning it? | 2023-06-16T13:51:01 | https://www.reddit.com/r/LocalLLaMA/comments/14axesy/best_llama_model_for_mac_m1/ | buxrmp | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 14axesy | false | null | t3_14axesy | /r/LocalLLaMA/comments/14axesy/best_llama_model_for_mac_m1/ | false | false | self | 9 | null |
which current LLM is most advanced/modern? which one will it be in next few months? | 15 | Not talking about size.
It can be a model which is small but uses different technologies. | 2023-06-16T12:49:28 | https://www.reddit.com/r/LocalLLaMA/comments/14aw0on/which_current_llm_is_most_advancedmodern_which/ | Sofronyami | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 14aw0on | false | null | t3_14aw0on | /r/LocalLLaMA/comments/14aw0on/which_current_llm_is_most_advancedmodern_which/ | false | false | self | 15 | null |
help with Oobaboga training please | 1 | [removed] | 2023-06-16T12:13:02 | https://www.reddit.com/r/LocalLLaMA/comments/14av8vf/help_with_oobaboga_training_please/ | Competitive_Fox7811 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 14av8vf | false | null | t3_14av8vf | /r/LocalLLaMA/comments/14av8vf/help_with_oobaboga_training_please/ | false | false | default | 1 | null |
Replace pinecone. | 28 | I am impressed with the service https://github.com/Mintplex-Labs/anything-llm but I don't want to use pinecone, as it makes me dependent on someone else's service. can I replace pinecone and if so, how do I do it? Thanks! | 2023-06-16T12:04:59 | https://www.reddit.com/r/LocalLLaMA/comments/14av30w/replace_pinecone/ | One_Creator_One | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 14av30w | false | null | t3_14av30w | /r/LocalLLaMA/comments/14av30w/replace_pinecone/ | false | false | self | 28 | {'enabled': False, 'images': [{'id': 'QESTWT5GMa_WkFsdEhn1_2EHGzZjQq2UCxpW6FKE-nw', 'resolutions': [{'height': 54, 'url': 'https://external-preview.redd.it/jy9XImdAfzUxWGr96OoUt8mk7x_pxHfh_tww131nMS4.jpg?width=108&crop=smart&auto=webp&s=2c0464c24f7a3fe17b534591bf843aa02de61175', 'width': 108}, {'height': 108, 'url': 'h... |
I was able to load WizardLM-30b onto my RTX 3090 | 22 | I am impressed, could load the model into vram, took 800s to load. But its really quick at inference. I gave it a few prompts such as summarizing a document, and writing me emails. Works well. But I wonder are there any better models? I saw the HF leaderboard, but seems like lots of models are missing.
Any models I s... | 2023-06-16T11:58:37 | https://www.reddit.com/r/LocalLLaMA/comments/14auy1z/i_was_able_to_load_wizardlm30b_onto_my_rtx_3090/ | klop2031 | self.LocalLLaMA | 2023-06-18T14:52:25 | 0 | {} | 14auy1z | false | null | t3_14auy1z | /r/LocalLLaMA/comments/14auy1z/i_was_able_to_load_wizardlm30b_onto_my_rtx_3090/ | false | false | self | 22 | {'enabled': False, 'images': [{'id': 'zgC8GKkQBGteVKfyG-suakesKihDSh27INw1Hgkj5Oo', 'resolutions': [{'height': 54, 'url': 'https://external-preview.redd.it/s9OVUUW_8RxZmj8qtV36Hr32p7FN4XKm4ZvErv2HZ28.jpg?width=108&crop=smart&auto=webp&s=b737df0e747f7673ec07665e18bb1c14197657ab', 'width': 108}, {'height': 108, 'url': 'h... |
How are all these models different from each other | 26 | Like what does Wizard do that vicuña couldn’t etc.
Also with so many different models can we have a section in the wiki explaining what specific thing each is good at | 2023-06-16T11:04:28 | https://www.reddit.com/r/LocalLLaMA/comments/14atx3q/how_are_all_these_models_different_from_each_other/ | [deleted] | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 14atx3q | false | null | t3_14atx3q | /r/LocalLLaMA/comments/14atx3q/how_are_all_these_models_different_from_each_other/ | false | false | self | 26 | null |
airoboros gpt4 v1.2 | 81 | Thanks for testing the last round and giving feedback, another one is ready to test:
* [https://huggingface.co/jondurbin/airoboros-65b-gpt4-1.2](https://huggingface.co/jondurbin/airoboros-65b-gpt4-1.2)
* [https://huggingface.co/jondurbin/airoboros-33b-gpt4-1.2](https://huggingface.co/jondurbin/airoboros-33b-gpt4-1.2)
... | 2023-06-16T10:34:27 | https://www.reddit.com/r/LocalLLaMA/comments/14atdex/airoboros_gpt4_v12/ | JonDurbin | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 14atdex | false | null | t3_14atdex | /r/LocalLLaMA/comments/14atdex/airoboros_gpt4_v12/ | false | false | 81 | {'enabled': False, 'images': [{'id': 'hjs5sZRSjODTAP9HiMGqQKQDjnjJ4XWJd-J-sPTJc_U', 'resolutions': [{'height': 58, 'url': 'https://external-preview.redd.it/b-2QeG40weNXA8RzcCwO3KY1CHaiARyicg2EW-2TgLQ.jpg?width=108&crop=smart&auto=webp&s=cdcd4cb494639aeab3bede204f6a48d1d99a67d1', 'width': 108}, {'height': 116, 'url': 'h... | |
The best model for content generation? | 2 | Hey, I wanted to know which model would you guys suggest is best for content generation. | 2023-06-16T10:07:17 | https://www.reddit.com/r/LocalLLaMA/comments/14asvzd/the_best_model_for_content_generation/ | TheArchivist314 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 14asvzd | false | null | t3_14asvzd | /r/LocalLLaMA/comments/14asvzd/the_best_model_for_content_generation/ | false | false | self | 2 | null |
Compiling Falcon.cpp on windows | 5 | Has anyone managed to compile this https://github.com/jploski/ggml/tree/falcon40b to an exe on windows?? No matter what I try I cannot get it to compile to main.exe.
Error output looks like this (much large but similar build issues) using cMake gui and chocolately’s make package for windows.
2>E:\ggml-falcon40b\exam... | 2023-06-16T09:51:36 | https://www.reddit.com/r/LocalLLaMA/comments/14aslu6/compiling_falconcpp_on_windows/ | ihaag | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 14aslu6 | false | null | t3_14aslu6 | /r/LocalLLaMA/comments/14aslu6/compiling_falconcpp_on_windows/ | false | false | self | 5 | {'enabled': False, 'images': [{'id': 'LhXGBGxcvevyJYiKZhH9d4c-Ry850cspL4r0h_gl7XQ', 'resolutions': [{'height': 54, 'url': 'https://external-preview.redd.it/ceGnPQ8D0MYLaZTrv8rOYBt5-sTGR_12n3r59PsHjWI.jpg?width=108&crop=smart&auto=webp&s=bc39ed4ae8e213f34a6c96ce101221a0368d3c68', 'width': 108}, {'height': 108, 'url': 'h... |
What do you think is the best llm to use as a teacher | 2 | [removed] | 2023-06-16T09:42:47 | https://www.reddit.com/r/LocalLLaMA/comments/14asgaa/what_do_you_think_is_the_best_llm_to_use_as_a/ | Redbeardybeard | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 14asgaa | false | null | t3_14asgaa | /r/LocalLLaMA/comments/14asgaa/what_do_you_think_is_the_best_llm_to_use_as_a/ | false | false | default | 2 | null |
Help me with this private gpt Error | 1 | [removed] | 2023-06-16T09:29:48 | Curious-Ninja150627 | i.redd.it | 1970-01-01T00:00:00 | 0 | {} | 14as7zd | false | null | t3_14as7zd | /r/LocalLLaMA/comments/14as7zd/help_me_with_this_private_gpt_error/ | false | false | default | 1 | null | |
Can anyone help me with this problem in private gpt | 1 | [removed] | 2023-06-16T09:26:36 | Curious-Ninja150627 | i.redd.it | 1970-01-01T00:00:00 | 0 | {} | 14as62r | false | null | t3_14as62r | /r/LocalLLaMA/comments/14as62r/can_anyone_help_me_with_this_problem_in_private/ | false | false | default | 1 | null | |
Can we evade LLM detection by using dynamic temperature across text? Most detectors pass your text through their LLM and check if the temperature is constant, and maybe look for other sampling artifacts. So making temperature vary, we make it harder to detect our text. | 25 | Can we evade LLM detection by using dynamic temperature across text? Most detectors pass your text through their LLM and check if the temperature is constant, and maybe look for other sampling artifacts. So making temperature vary, we make it harder to detect our text. | 2023-06-16T09:23:09 | https://www.reddit.com/r/LocalLLaMA/comments/14as3x3/can_we_evade_llm_detection_by_using_dynamic/ | NancyAurum | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 14as3x3 | false | null | t3_14as3x3 | /r/LocalLLaMA/comments/14as3x3/can_we_evade_llm_detection_by_using_dynamic/ | false | false | self | 25 | null |
LLM user support | 0 | [removed] | 2023-06-16T08:47:59 | https://www.reddit.com/r/LocalLLaMA/comments/14arivh/llm_user_support/ | One_Creator_One | self.LocalLLaMA | 2023-06-16T11:02:22 | 0 | {} | 14arivh | false | null | t3_14arivh | /r/LocalLLaMA/comments/14arivh/llm_user_support/ | false | false | default | 0 | null |
Best uncensored llm to run locally on free google colab? | 1 | [removed] | 2023-06-16T08:26:43 | https://www.reddit.com/r/LocalLLaMA/comments/14ar639/best_uncensored_llm_to_run_locally_on_free_google/ | Murky-Cheek-7554 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 14ar639 | false | null | t3_14ar639 | /r/LocalLLaMA/comments/14ar639/best_uncensored_llm_to_run_locally_on_free_google/ | false | false | default | 1 | null |
Is there a free local analogue of the text translator DeepL in the form of an LLM? | 16 |
1. To translate not literally by words, but in the context of a sentence (paragraph).
2. To be able to download databases for required languages only.
3. integrated with WebUI | 2023-06-16T08:09:01 | https://www.reddit.com/r/LocalLLaMA/comments/14aqvrw/is_there_a_free_local_analogue_of_the_text/ | nihnuhname | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 14aqvrw | false | null | t3_14aqvrw | /r/LocalLLaMA/comments/14aqvrw/is_there_a_free_local_analogue_of_the_text/ | false | false | self | 16 | null |
Prevent LLM from answering out of context questions | 3 | I am currently playing around with fastchat t5. I have a set of documents that is fed to the model based on the query through langchain. My current issue is that whenever there's an out of context question, fastchat is using it's pretrained knowledge to answer it whereas the expected output should be 'I don't know' or ... | 2023-06-16T06:58:55 | https://www.reddit.com/r/LocalLLaMA/comments/14apo7n/prevent_llm_from_answering_out_of_context/ | perseus_14 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 14apo7n | false | null | t3_14apo7n | /r/LocalLLaMA/comments/14apo7n/prevent_llm_from_answering_out_of_context/ | false | false | self | 3 | null |
Robin V2 Launches: Achieves Unparalleled Performance on OpenLLM! | 1 | 2023-06-16T06:20:36 | https://www.reddit.com/r/machinelearningnews/comments/14am06w/robin_v2_launches_achieves_unparalleled/ | saintshing | reddit.com | 1970-01-01T00:00:00 | 0 | {} | 14ap05c | false | null | t3_14ap05c | /r/LocalLLaMA/comments/14ap05c/robin_v2_launches_achieves_unparalleled/ | false | false | default | 1 | null | |
Could a llama lora be merged into OpenLLama? | 1 | If they are the same architecture & size, it should be possible, right? Because lora trained on base llama can be merged into finetunes. | 2023-06-16T05:48:07 | https://www.reddit.com/r/LocalLLaMA/comments/14aofh5/could_a_llama_lora_be_merged_into_openllama/ | pokeuser61 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 14aofh5 | false | null | t3_14aofh5 | /r/LocalLLaMA/comments/14aofh5/could_a_llama_lora_be_merged_into_openllama/ | false | false | self | 1 | null |
Do you wanna have a free Al agent? | 1 | [removed] | 2023-06-16T04:27:56 | [deleted] | 1970-01-01T00:00:00 | 0 | {} | 14amz6s | false | null | t3_14amz6s | /r/LocalLLaMA/comments/14amz6s/do_you_wanna_have_a_free_al_agent/ | false | false | default | 1 | null | ||
How is ExLlama so good? Can it be used with a more feature rich UI? | 46 | ExLlama uses way less memory and is much faster than AutoGPTQ or GPTQ-for-Llama, running on a 3090 at least. Does anyone know how to get it to work with Tavern or Kobold or Oobabooga? | 2023-06-16T02:01:51 | https://www.reddit.com/r/LocalLLaMA/comments/14ak4yg/how_is_exllama_so_good_can_it_be_used_with_a_more/ | Excessive_Etcetra | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 14ak4yg | false | null | t3_14ak4yg | /r/LocalLLaMA/comments/14ak4yg/how_is_exllama_so_good_can_it_be_used_with_a_more/ | false | false | self | 46 | null |
Official WizardCoder-15B-V1.0 Released! Can Achieve 59.8% Pass@1 on HumanEval! | 175 | * Today, the ***WizardLM Team*** has released their **Official** **WizardCoder-15B-V1.0** model trained with 78**k** evolved code instructions.
* *WizardLM Team* will ***open-source all the code, data, models, and algorithms recently!***
* Paper: [https://arxiv.org/abs/2306.08568](https://arxiv.org/abs/2306.08568)
* T... | 2023-06-16T01:27:49 | https://www.reddit.com/r/LocalLLaMA/comments/14ajglx/official_wizardcoder15bv10_released_can_achieve/ | cylaw01 | self.LocalLLaMA | 2023-06-17T13:01:14 | 0 | {} | 14ajglx | false | null | t3_14ajglx | /r/LocalLLaMA/comments/14ajglx/official_wizardcoder15bv10_released_can_achieve/ | false | false | 175 | {'enabled': False, 'images': [{'id': 'q3evP6JeDpAC2MdSQHWYxnCYTqbJkElIQsLFqVSdkss', 'resolutions': [{'height': 63, 'url': 'https://external-preview.redd.it/0HhwdU6MKIAKjL9Y8-B_iH374a3NiPTy0ib8lmloRzA.jpg?width=108&crop=smart&auto=webp&s=2711d572cfc6c713893cf24e8c4a7344d5ad8a4c', 'width': 108}, {'height': 126, 'url': 'h... | |
More intelligent Pdf parsers | 15 | Apologies of this is slightly off topic. I've been experimenting with Llama Index along with local models for context based question answering problem. One key issue I've been facing is Pdf parsing, especially tabular information formats.
Does anyone know of current state of the art (reproducible code, not just paper... | 2023-06-16T01:16:51 | https://www.reddit.com/r/LocalLLaMA/comments/14aj8pe/more_intelligent_pdf_parsers/ | darthstargazer | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 14aj8pe | false | null | t3_14aj8pe | /r/LocalLLaMA/comments/14aj8pe/more_intelligent_pdf_parsers/ | false | false | self | 15 | null |
Airoboros 65b GGML is really good! | 112 | [https://huggingface.co/TheBloke/airoboros-65B-gpt4-1.2-GGML](https://huggingface.co/TheBloke/airoboros-65B-gpt4-1.2-GGML)
Haven't seen people talk about this release from thebloke, but it did a solid job with the joke that has stumped pretty much every other open source LLM since the beginning of my testing:
USER:
... | 2023-06-16T00:48:33 | https://www.reddit.com/r/LocalLLaMA/comments/14ainpc/airoboros_65b_ggml_is_really_good/ | TheDreamSymphonic | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 14ainpc | false | null | t3_14ainpc | /r/LocalLLaMA/comments/14ainpc/airoboros_65b_ggml_is_really_good/ | false | false | self | 112 | {'enabled': False, 'images': [{'id': 'CtpzRLMS6GlQQnv1zcIL_IW4nH6Hb6XpVXFHAgeld0k', 'resolutions': [{'height': 58, 'url': 'https://external-preview.redd.it/R2NpRx8QV3Z0krq0lsqPaorFLEPDDb-NAzWXGKNi9QY.jpg?width=108&crop=smart&auto=webp&s=1a3a7ec11661e57b61ec3bdd14353a9b4fe71fda', 'width': 108}, {'height': 116, 'url': 'h... |
Langchain and self hosted LLaMA hosted API | 3 | What are the current best "no reinventing the wheel" approaches to have Langchain use an LLM through a locally hosted REST API, the likes of Oobabooga or [hyperonym/basaran](https://github.com/hyperonym/basaran) with streaming support for 4-bit GPTQ? | 2023-06-15T21:55:04 | https://www.reddit.com/r/LocalLLaMA/comments/14aeo8f/langchain_and_self_hosted_llama_hosted_api/ | 2muchnet42day | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 14aeo8f | false | null | t3_14aeo8f | /r/LocalLLaMA/comments/14aeo8f/langchain_and_self_hosted_llama_hosted_api/ | false | false | self | 3 | {'enabled': False, 'images': [{'id': 'gFHYjON9kBqne0o-foYmyiaBdqO1BkPF2DRj0ogoTxg', 'resolutions': [{'height': 54, 'url': 'https://external-preview.redd.it/VOlWMgzRN51j72aNawt6hTAKIaCcNWUEg_5PmWyYmX8.jpg?width=108&crop=smart&auto=webp&s=fea07ae3ab0bb62bc75b34910774a4c0619feecf', 'width': 108}, {'height': 108, 'url': 'h... |
Why are LLM benchmarks so absurdly correlated? | 20 | I've been looking at jubilantjerry's excellent 'Combined LLM benchmarks' work ([https://www.reddit.com/r/LocalLLaMA/comments/13qj07n/sharing\_my\_comparison\_methodology\_for\_llm\_models/](https://www.reddit.com/r/LocalLLaMA/comments/13qj07n/sharing_my_comparison_methodology_for_llm_models/)), and the most striking t... | 2023-06-15T21:31:54 | https://www.reddit.com/r/LocalLLaMA/comments/14ae2xv/why_are_llm_benchmarks_so_absurdly_correlated/ | ClayShirky | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 14ae2xv | false | null | t3_14ae2xv | /r/LocalLLaMA/comments/14ae2xv/why_are_llm_benchmarks_so_absurdly_correlated/ | false | false | self | 20 | null |
Preset Arena: 17,205 comparisons between 241 different presets. Vote on the best ones! | 125 | Everyone here has probably been through the question "What parameters should I use to get the best responses?". Temperature, top_k, top_p, repetition_penalty, typical_p... Finding the ideal combination is extremely difficult.
To tackle this problem, I have come up with the following experiment: comparing thousands of ... | 2023-06-15T21:06:55 | https://www.reddit.com/r/LocalLLaMA/comments/14adfw2/preset_arena_17205_comparisons_between_241/ | oobabooga4 | self.LocalLLaMA | 2023-06-17T00:00:12 | 0 | {} | 14adfw2 | false | null | t3_14adfw2 | /r/LocalLLaMA/comments/14adfw2/preset_arena_17205_comparisons_between_241/ | false | false | self | 125 | {'enabled': False, 'images': [{'id': 'Q1MF8IN_UA9pU4tqvD1hEdePlazYPLTs893pR_vAxGU', 'resolutions': [{'height': 108, 'url': 'https://external-preview.redd.it/5DnJwNTgOVdEaq3w-j17t1fdG_WOO8KiqSkSylheX5k.jpg?width=108&crop=smart&auto=webp&s=563cdab161ef7a0db1d99480a17e1e0a964713a8', 'width': 108}, {'height': 216, 'url': '... |
Releasing a super-simple memory project for LLMs / semantic search | 19 | Hey /r/LocalLLaMA,
tl;dr: check out the project @ [https://github.com/spyglass-search/memex](https://github.com/spyglass-search/memex)
Last week, I made a [post](https://www.reddit.com/r/LocalLLaMA/comments/14405do/building_a_supersimple_memory_service_for/) about open-sourcing this tool. I'm open-sourcing the code a... | 2023-06-15T20:47:43 | https://www.reddit.com/r/LocalLLaMA/comments/14acy7w/releasing_a_supersimple_memory_project_for_llms/ | andyndino | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 14acy7w | false | null | t3_14acy7w | /r/LocalLLaMA/comments/14acy7w/releasing_a_supersimple_memory_project_for_llms/ | false | false | 19 | {'enabled': False, 'images': [{'id': 'CD7VanZwz3k_Vo6F2TTbwGnDsM43dI400RAClk2pdW0', 'resolutions': [{'height': 54, 'url': 'https://external-preview.redd.it/Eux4IvMBk6sTY0WN1shuNReaqBlBSarm7ARB0TDyeCE.jpg?width=108&crop=smart&auto=webp&s=6bf10cc78985d4b7bacedf6bff9ff0e745ef9b8a', 'width': 108}, {'height': 108, 'url': 'h... | |
My experience with Falcon 40B on Hugging Face | 5 | I tried out several different prompts on the Huggingface playground ( [Falcon-Chat - a Hugging Face Space by HuggingFaceH4](https://huggingface.co/spaces/HuggingFaceH4/falcon-chat) ) for it to act as a Spanish tutor and to correct any mistakes I made, but it either only corrected the mistakes and nothing else, or it ig... | 2023-06-15T19:49:02 | https://www.reddit.com/r/LocalLLaMA/comments/14abh3k/my_experience_with_falcon_40b_on_hugging_face/ | cool-beans-yeah | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 14abh3k | false | null | t3_14abh3k | /r/LocalLLaMA/comments/14abh3k/my_experience_with_falcon_40b_on_hugging_face/ | false | false | self | 5 | {'enabled': False, 'images': [{'id': 'ErHVgBnGBq6UZs92whKb8RedUVO_2L-lXigC_T4TQXw', 'resolutions': [{'height': 58, 'url': 'https://external-preview.redd.it/Igl7xX_NgL1Knnz9hM-MnYKMfMWrYJA2THmh1zGVe7c.jpg?width=108&crop=smart&auto=webp&s=b805a6aad62bd8affa3b4d25cc1f327827dd454b', 'width': 108}, {'height': 116, 'url': 'h... |
A in-context-learning tuning dataset to few shots prompting | 10 | 2023-06-15T19:33:18 | https://huggingface.co/datasets/tasksource/icl-symbol-tuning-instruct | Jean-Porte | huggingface.co | 1970-01-01T00:00:00 | 0 | {} | 14ab2yj | false | null | t3_14ab2yj | /r/LocalLLaMA/comments/14ab2yj/a_incontextlearning_tuning_dataset_to_few_shots/ | false | false | 10 | {'enabled': False, 'images': [{'id': 'ZgdTHBfsWO9CNq6kHwFEV90rdRHY5G_gJFbf1uYk2MQ', 'resolutions': [{'height': 58, 'url': 'https://external-preview.redd.it/9ZjaWk50vyd8R_jJeHV5GUjgdhHi_ijuMelpplD3EVo.jpg?width=108&crop=smart&auto=webp&s=9ed7d6b1ac08c55270997f99cb3303405dd6b012', 'width': 108}, {'height': 116, 'url': 'h... | ||
Should laptop make a scratching noise when running Oobabooga or similar tools? | 0 | [removed] | 2023-06-15T19:30:30 | [deleted] | 1970-01-01T00:00:00 | 0 | {} | 14ab0d3 | false | null | t3_14ab0d3 | /r/LocalLLaMA/comments/14ab0d3/should_laptop_make_a_scratching_noise_when/ | false | false | default | 0 | null | ||
Running 40B Falcon on AMD MI300X real-time demo | 0 | [removed] | 2023-06-15T19:00:01 | https://www.reddit.com/r/LocalLLaMA/comments/14aa8ln/running_40b_falcon_on_amd_mi300x_realtime_demo/ | themushroommage | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 14aa8ln | false | null | t3_14aa8ln | /r/LocalLLaMA/comments/14aa8ln/running_40b_falcon_on_amd_mi300x_realtime_demo/ | false | false | default | 0 | null |
At what model size does Reasoning appear? | 47 | LLMs are great as Wikipedia type information sources.
However, in GPT4 the emergent property of Reasoning appears.
Do we have a chance of achieving this on our home systems? | 2023-06-15T18:11:56 | https://www.reddit.com/r/LocalLLaMA/comments/14a91wu/at_what_model_size_does_reasoning_appear/ | MrEloi | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 14a91wu | false | null | t3_14a91wu | /r/LocalLLaMA/comments/14a91wu/at_what_model_size_does_reasoning_appear/ | false | false | self | 47 | null |
trial of my status | 1 | [deleted] | 2023-06-15T18:04:31 | [deleted] | 1970-01-01T00:00:00 | 0 | {} | 14a8x2t | false | null | t3_14a8x2t | /r/LocalLLaMA/comments/14a8x2t/trial_of_my_status/ | false | false | default | 1 | null | ||
How do you provide a model with source files for analysis? | 3 | I'm quite new to this, and using oobabooga on windows.
The models appear to think they can read HTTP URLs, and when I asked how I could provide them with source files instructed me to upload them and provide links, but it quickly became apparent they cannot actually access and read the uploaded source files despite cl... | 2023-06-15T17:50:12 | https://www.reddit.com/r/LocalLLaMA/comments/14a8pcq/how_do_you_provide_a_model_with_source_files_for/ | gigachad_deluxe | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 14a8pcq | false | null | t3_14a8pcq | /r/LocalLLaMA/comments/14a8pcq/how_do_you_provide_a_model_with_source_files_for/ | false | false | self | 3 | null |
Wizard-Vicuna 30B only using 50% of CPU | 1 | [removed] | 2023-06-15T17:34:39 | https://www.reddit.com/r/LocalLLaMA/comments/14a8fkp/wizardvicuna_30b_only_using_50_of_cpu/ | TenseSpoon | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 14a8fkp | false | null | t3_14a8fkp | /r/LocalLLaMA/comments/14a8fkp/wizardvicuna_30b_only_using_50_of_cpu/ | false | false | default | 1 | null |
Need Help | 7 | Ok so I'm fairly new to llama.cpp, I used to run the lama models with oogabooga, but after the newest changes to llama.cpp I switched. It runs so much faster on my GPU. Its amazing almost instant response. So anyways, I'm using the following code inside a bat file to run it
title llama.cpp
:start
main -i --intera... | 2023-06-15T16:28:35 | https://www.reddit.com/r/LocalLLaMA/comments/14a6tlc/need_help/ | GuentherDonner | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 14a6tlc | false | null | t3_14a6tlc | /r/LocalLLaMA/comments/14a6tlc/need_help/ | false | false | self | 7 | null |
A kind of magic | 3 | [removed] | 2023-06-15T16:13:45 | https://www.reddit.com/r/LocalLLaMA/comments/14a6gii/a_kind_of_magic/ | Lolleka | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 14a6gii | false | null | t3_14a6gii | /r/LocalLLaMA/comments/14a6gii/a_kind_of_magic/ | false | false | default | 3 | null |
GPT4all with BDSM content and not censored? | 0 | [removed] | 2023-06-15T15:43:05 | https://www.reddit.com/r/LocalLLaMA/comments/14a5p28/gpt4all_with_bdsm_content_and_not_censored/ | Pleasant_Ad5555 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 14a5p28 | false | null | t3_14a5p28 | /r/LocalLLaMA/comments/14a5p28/gpt4all_with_bdsm_content_and_not_censored/ | false | false | default | 0 | null |
Can you run inference on Mac with AMD GPUs? | 2 | Is that possible with things like oobabooga, ROCm, and llama.cpp?
I'm talking about Macs with Intel CPU an AMG GPU, not macs with Silicon chips. | 2023-06-15T13:13:49 | https://www.reddit.com/r/LocalLLaMA/comments/14a2505/can_you_run_inference_on_mac_with_amd_gpus/ | jl303 | self.LocalLLaMA | 2023-06-16T00:55:17 | 0 | {} | 14a2505 | false | null | t3_14a2505 | /r/LocalLLaMA/comments/14a2505/can_you_run_inference_on_mac_with_amd_gpus/ | false | false | self | 2 | null |
Best open-source LLM for code generation | 10 | I am looking for an LLM in turn to develop a code generator application. The goal is to fine-tune the LLM with template libraries. Suggestions? | 2023-06-15T12:43:04 | https://www.reddit.com/r/LocalLLaMA/comments/14a1go5/best_opensource_llm_for_code_generation/ | lahaine93 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 14a1go5 | false | null | t3_14a1go5 | /r/LocalLLaMA/comments/14a1go5/best_opensource_llm_for_code_generation/ | false | false | self | 10 | null |
Running LLaMA 65B reminded me how much more fun base models are | 89 | Lately I've been running LLaMA 65B in the cloud to try out exllama. With no actual use case for it, I've been using the chatbot example. And it has reminded me how much more fun base models are compared to RLHF'd GPT. They're funnier, more concise, less obsequious, and capable of expressing emotions other than bland po... | 2023-06-15T12:13:37 | https://www.reddit.com/r/LocalLLaMA/comments/14a0uig/running_llama_65b_reminded_me_how_much_more_fun/ | hold_my_fish | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 14a0uig | false | null | t3_14a0uig | /r/LocalLLaMA/comments/14a0uig/running_llama_65b_reminded_me_how_much_more_fun/ | false | false | self | 89 | null |
what do you use for quickly testing pretrained models locally? | 1 | [deleted] | 2023-06-15T11:56:45 | [deleted] | 1970-01-01T00:00:00 | 0 | {} | 14a0ib0 | false | null | t3_14a0ib0 | /r/LocalLLaMA/comments/14a0ib0/what_do_you_use_for_quickly_testing_pretrained/ | false | false | default | 1 | null | ||
Honest LLaMA - Inference-Time Intervention (ITI) | 28 |
Abstract:
We introduce Inference-Time Intervention (ITI), a technique designed to enhance the truthfulness of large language models (LLMs). ITI operates by shifting model activations during inference, following a set of directions across a limited number of attention heads. This intervention significantly improves th... | 2023-06-15T11:53:47 | https://github.com/likenneth/honest_llama | i_wayyy_over_think | github.com | 1970-01-01T00:00:00 | 0 | {} | 14a0g7m | false | null | t3_14a0g7m | /r/LocalLLaMA/comments/14a0g7m/honest_llama_inferencetime_intervention_iti/ | false | false | 28 | {'enabled': False, 'images': [{'id': 'seIlZWMeu9MvvI-1gNgo5gFIGcPuPnONo3Op_T_cSts', 'resolutions': [{'height': 54, 'url': 'https://external-preview.redd.it/1OWaGQh5Xbjux70KU0UpsT039GqvTo_rOeKb31QQH8w.jpg?width=108&crop=smart&auto=webp&s=b348d8153ba7eadccfcbac0e5a7404492b79f400', 'width': 108}, {'height': 108, 'url': 'h... | |
A guide for WSL/Windows 11/Linux users including the installation of WSL2, Conda, Cuda & more) | 26 |
I created a guide that includes some tips to improve your UX experience when using WSL2/windows 11/Linux
The WSL part contains :
* [install WSL](https://github.com/AmineDjeghri/AwesomeWindows11#install-wsl)
* [install miniconda in WSL](https://github.com/AmineDjeghri/AwesomeWindows11#install-miniconda-in-wsl)
* [c... | 2023-06-15T11:51:36 | https://www.reddit.com/r/LocalLLaMA/comments/14a0eqq/a_guide_for_wslwindows_11linux_users_including/ | aminedjeghri | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 14a0eqq | false | null | t3_14a0eqq | /r/LocalLLaMA/comments/14a0eqq/a_guide_for_wslwindows_11linux_users_including/ | false | false | self | 26 | {'enabled': False, 'images': [{'id': 'B-xC3cG-8ytaaWfLUNyL7usqsTGoV31nbZDjbq4WyUo', 'resolutions': [{'height': 54, 'url': 'https://external-preview.redd.it/ue5b8HSxaXR-AZZPq_DboxFoXzY3FhgPkLxFkGoyHZc.jpg?width=108&crop=smart&auto=webp&s=93e75c196cc4dad1e97761d710cfef356fd34593', 'width': 108}, {'height': 108, 'url': 'h... |
Free GPU options for LlaMA model experimentation | 63 | To those who are starting out on the llama model with llama.cpp or other similar models, you may feel tempted to purchase a used 3090, 4090, or an Apple M2 to run these models. However, I'd like to share that there are free alternatives available for you to experiment with before investing your hard-earned money.
Goog... | 2023-06-15T11:47:23 | https://www.reddit.com/r/LocalLLaMA/comments/14a0bs9/free_gpu_options_for_llama_model_experimentation/ | AstrionX | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 14a0bs9 | false | null | t3_14a0bs9 | /r/LocalLLaMA/comments/14a0bs9/free_gpu_options_for_llama_model_experimentation/ | false | false | self | 63 | null |
A guide for WSL/Windows 11 users including the installation of WSL2, Conda, Cuda & more) | 1 | [deleted] | 2023-06-15T11:42:06 | [deleted] | 2023-06-15T11:46:54 | 0 | {} | 14a086f | false | null | t3_14a086f | /r/LocalLLaMA/comments/14a086f/a_guide_for_wslwindows_11_users_including_the/ | false | false | default | 1 | null | ||
Psychiatry (Choice of medications ) advice from LLAMA? | 1 | [removed] | 2023-06-15T10:54:19 | [deleted] | 1970-01-01T00:00:00 | 0 | {} | 149zbzk | false | null | t3_149zbzk | /r/LocalLLaMA/comments/149zbzk/psychiatry_choice_of_medications_advice_from_llama/ | false | false | default | 1 | null | ||
Is it possible to train a llm to model a personality? | 14 | I don’t have a good machine so the only models are 7b ones that I can run on my machines.
What if I could give the model a personality, train it in a particular field say for example make it a doctor or even Shakespeare
The way I understand it is that less the parameters the worse the model is in general (7B worse th... | 2023-06-15T10:13:13 | https://www.reddit.com/r/LocalLLaMA/comments/149ylzh/is_it_possible_to_train_a_llm_to_model_a/ | [deleted] | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 149ylzh | false | null | t3_149ylzh | /r/LocalLLaMA/comments/149ylzh/is_it_possible_to_train_a_llm_to_model_a/ | false | false | self | 14 | null |
Local LLMs: After Novelty Wanes | 75 |
What do you do with them after the novelty wears off?
- Have you found usecases that are particularly valuable?
- Have you found cool new applications in your personal or professional life?
- Are you building next gen apps with local LLMs?
Share your experiences, tips, and ideas on how to keep them useful in the lo... | 2023-06-15T09:06:55 | https://www.reddit.com/r/LocalLLaMA/comments/149xhln/local_llms_after_novelty_wanes/ | AstrionX | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 149xhln | false | null | t3_149xhln | /r/LocalLLaMA/comments/149xhln/local_llms_after_novelty_wanes/ | false | false | self | 75 | null |
Training on documents to summarize them. | 17 | I am highly interested in using LLM to summarize long documents. However, the maximum token length is often a limitation.
But LLM can provide summaries based on the text it was trained on. If I ask ChatGPT about the summary of "Harry Potter and the Philosopher's Stone," it can generate a satisfactory output.
So, I ha... | 2023-06-15T06:56:51 | https://www.reddit.com/r/LocalLLaMA/comments/149vbmx/training_on_documents_to_summarize_them/ | Schmandli | self.LocalLLaMA | 2023-06-15T12:39:41 | 0 | {} | 149vbmx | false | null | t3_149vbmx | /r/LocalLLaMA/comments/149vbmx/training_on_documents_to_summarize_them/ | false | false | self | 17 | null |
New quantization method SqueezeLLM allows for loseless compression for 3-bit and outperforms GPTQ and AWQ in both 3-bit and 4-bit. Quantized Vicuna and LLaMA models have been released. | 216 | Paper: [https://arxiv.org/abs/2306.07629](https://arxiv.org/abs/2306.07629)
Code: [https://github.com/SqueezeAILab/SqueezeLLM](https://github.com/SqueezeAILab/SqueezeLLM)
SqueezeLLM quantized models: [https://huggingface.co/squeeze-ai-lab](https://huggingface.co/squeeze-ai-lab)
Excerpts:
>We introduce SqueezeLLM, a... | 2023-06-15T05:37:45 | https://www.reddit.com/r/LocalLLaMA/comments/149txjl/new_quantization_method_squeezellm_allows_for/ | llamaShill | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 149txjl | false | null | t3_149txjl | /r/LocalLLaMA/comments/149txjl/new_quantization_method_squeezellm_allows_for/ | false | false | self | 216 | {'enabled': False, 'images': [{'id': 'q3evP6JeDpAC2MdSQHWYxnCYTqbJkElIQsLFqVSdkss', 'resolutions': [{'height': 63, 'url': 'https://external-preview.redd.it/0HhwdU6MKIAKjL9Y8-B_iH374a3NiPTy0ib8lmloRzA.jpg?width=108&crop=smart&auto=webp&s=2711d572cfc6c713893cf24e8c4a7344d5ad8a4c', 'width': 108}, {'height': 126, 'url': 'h... |
How to finetuned module ? WizardVicuna 7B uncensored | 8 | I inspired by novel ai FAQ about how they module work, they use gpt-j and finetune it with material for fantasy story writing and anime related stuff, i want try replicate what they do with WZ 7B and see if i can achieve similar result to their module. but problem is i don't have single clue how star with it. I any enl... | 2023-06-15T05:00:33 | https://www.reddit.com/r/LocalLLaMA/comments/149t8oa/how_to_finetuned_module_wizardvicuna_7b_uncensored/ | Merchant_Lawrence | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 149t8oa | false | null | t3_149t8oa | /r/LocalLLaMA/comments/149t8oa/how_to_finetuned_module_wizardvicuna_7b_uncensored/ | false | false | self | 8 | null |
A short conversation with Falcon | 299 | Questions are purposely stupid, btw | 2023-06-15T04:37:22 | https://www.reddit.com/gallery/149su0a | Basic_Description_56 | reddit.com | 1970-01-01T00:00:00 | 0 | {} | 149su0a | false | null | t3_149su0a | /r/LocalLLaMA/comments/149su0a/a_short_conversation_with_falcon/ | false | false | 299 | null | |
New Discord server and a poll for this community | 37 | New server: [https://discord.gg/Y8H8uUtxc3](https://discord.gg/Y8H8uUtxc3)
LocalLLaMA has reached 30,000 members! Thank you everyone for being here.
As the community has grown, one of the most popular suggestions has been to create a Discord server. To check if this is something the community wants or doesn't want, i... | 2023-06-15T03:58:47 | https://www.reddit.com/r/LocalLLaMA/comments/149s2ul/new_discord_server_and_a_poll_for_this_community/ | Technical_Leather949 | self.LocalLLaMA | 2023-06-19T10:16:26 | 0 | {} | 149s2ul | true | null | t3_149s2ul | /r/LocalLLaMA/comments/149s2ul/new_discord_server_and_a_poll_for_this_community/ | false | false | self | 37 | {'enabled': False, 'images': [{'id': 'E8Jfupwh2wiDlIJ4BmYK6WgDxfqDQRYjZ_8QK--Cnqg', 'resolutions': [{'height': 108, 'url': 'https://external-preview.redd.it/M2EBgGeeo2HSx9mOiRPZMaDbB0foY9mKnPwthOx0LRA.jpg?width=108&crop=smart&auto=webp&s=4d287cc99a365271c3b4e143e681ce7de9b177d2', 'width': 108}], 'source': {'height': 16... |
Noob here | 1 | [removed] | 2023-06-15T03:57:08 | https://www.reddit.com/r/LocalLLaMA/comments/149s1t7/noob_here/ | kunjinn | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 149s1t7 | false | null | t3_149s1t7 | /r/LocalLLaMA/comments/149s1t7/noob_here/ | false | false | default | 1 | null |
How good is Chronos Hermes 13B? | 18 | I'm reading a lot of praise for Chronos Hermes 13B for chat. Can someone put out a benchmark on this? More importantly, how does it stack up to Wizard-Vicuna-Uncensored-30B? | 2023-06-15T02:24:13 | https://www.reddit.com/r/LocalLLaMA/comments/149q8ke/how_good_is_chronos_hermes_13b/ | ReMeDyIII | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 149q8ke | false | null | t3_149q8ke | /r/LocalLLaMA/comments/149q8ke/how_good_is_chronos_hermes_13b/ | false | false | self | 18 | null |
MLC-LLM Chat vicuna-Wizard-7B-Uncensored-q3f16_0 | 26 | Using the unofficial tutorials provided by MLC-LLM I was able to format the ehartford/Wizard-Vicuna-7B-Uncensored to work with MLC-Chat in Vulkan mode. It should work with AMD GPUs though I've only tested it on a RTX 3060. Feedback is appreciated. MLC-LLM doesn't get enough press here, likely because they don't upload ... | 2023-06-15T02:01:32 | https://www.reddit.com/r/LocalLLaMA/comments/149prvz/mlcllm_chat_vicunawizard7buncensoredq3f16_0/ | jetro30087 | self.LocalLLaMA | 2023-06-15T22:01:44 | 0 | {} | 149prvz | false | null | t3_149prvz | /r/LocalLLaMA/comments/149prvz/mlcllm_chat_vicunawizard7buncensoredq3f16_0/ | false | false | 26 | {'enabled': False, 'images': [{'id': '_wJmnI2pDwAdI3VoLl7qZVF-NGz6bZRVt-aIFtKeE0Q', 'resolutions': [{'height': 58, 'url': 'https://external-preview.redd.it/kNCrojIaSUt_3D8A3lu3YeHeLQjpuBSJyWIH9TIIIOE.jpg?width=108&crop=smart&auto=webp&s=5be55471119888b3da3034bef80abefc032a801a', 'width': 108}, {'height': 116, 'url': 'h... | |
So hypothetically what’s the strongest LLM model this could reasonably run? (24GB VRAM + 128GB system ram) (reasonably = output generations happen within 60 seconds) | 4 | 2023-06-15T01:20:28 | katiecharm | i.imgur.com | 1970-01-01T00:00:00 | 0 | {} | 149oxqx | false | null | t3_149oxqx | /r/LocalLLaMA/comments/149oxqx/so_hypothetically_whats_the_strongest_llm_model/ | false | false | 4 | {'enabled': True, 'images': [{'id': 'EjmZ7VMJ_aNSW30VP0ebQ_7MdKg5e8Z1c9dRoev2dbY', 'resolutions': [{'height': 174, 'url': 'https://external-preview.redd.it/A8WB_xX7orMwgZXbl8N_L-q6eKl3mQJ4VI8M4UN7L-I.jpg?width=108&crop=smart&auto=webp&s=73816e487ad6e1f9fccf236f5f5b69eab252b309', 'width': 108}, {'height': 349, 'url': 'h... | |||
Your painpoints in building/using local LLMs | 10 | What are your painpoints in building/using local LLMs? Let's discuss and see what we can build together to solve these issues! | 2023-06-15T01:02:29 | https://www.reddit.com/r/LocalLLaMA/comments/149okhd/your_painpoints_in_buildingusing_local_llms/ | Latter-Implement-243 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 149okhd | false | null | t3_149okhd | /r/LocalLLaMA/comments/149okhd/your_painpoints_in_buildingusing_local_llms/ | false | false | self | 10 | null |
The best chat model for a RTX 4090 ? | 5 | Hello, i saw a lot of new LLM since a month, so i am a bit lost.
Can someone tell me what is the best local LLM usable in oobabooga yet ? Thanks. | 2023-06-15T00:20:11 | https://www.reddit.com/r/LocalLLaMA/comments/149nofy/the_best_chat_model_for_a_rtx_4090/ | 3deal | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 149nofy | false | null | t3_149nofy | /r/LocalLLaMA/comments/149nofy/the_best_chat_model_for_a_rtx_4090/ | false | false | self | 5 | null |
Tool for chatting with your codebase and docs using OpenAI, LlamaCpp, and GPT-4-All | 14 | [removed] | 2023-06-14T23:59:56 | [deleted] | 1970-01-01T00:00:00 | 0 | {} | 149n8cm | false | null | t3_149n8cm | /r/LocalLLaMA/comments/149n8cm/tool_for_chatting_with_your_codebase_and_docs/ | false | false | default | 14 | null | ||
Model possible to run on laptop GPU? | 0 | [removed] | 2023-06-14T23:51:43 | https://www.reddit.com/r/LocalLLaMA/comments/149n29k/model_possible_to_run_on_laptop_gpu/ | DarkHelmetedOne | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 149n29k | false | null | t3_149n29k | /r/LocalLLaMA/comments/149n29k/model_possible_to_run_on_laptop_gpu/ | false | false | default | 0 | null |
Attention based truncation approach | 7 | [deleted] | 2023-06-14T23:01:50 | [deleted] | 1970-01-01T00:00:00 | 0 | {} | 149lxwv | false | null | t3_149lxwv | /r/LocalLLaMA/comments/149lxwv/attention_based_truncation_approach/ | false | false | default | 7 | null | ||
llama.cpp full CUDA acceleration has been merged | 125 | Update of [(1) llama.cpp just got full CUDA acceleration, and now it can outperform GPTQ! : LocalLLaMA (reddit.com)](https://www.reddit.com/r/LocalLLaMA/comments/147z6as/llamacpp_just_got_full_cuda_acceleration_and_now/) posted by TheBloke.
The PR added by Johannes Gaessler has been merged to main
Link of the P... | 2023-06-14T22:54:57 | https://www.reddit.com/r/LocalLLaMA/comments/149ls1f/llamacpp_full_cuda_acceleration_has_been_merged/ | aminedjeghri | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 149ls1f | false | null | t3_149ls1f | /r/LocalLLaMA/comments/149ls1f/llamacpp_full_cuda_acceleration_has_been_merged/ | false | false | self | 125 | {'enabled': False, 'images': [{'id': 'GoLjSKY7nzLq6QbI1x3IXo7j3K4sPBmu0Cx1x74SKyQ', 'resolutions': [{'height': 54, 'url': 'https://external-preview.redd.it/BwFJWcQ3GZKJWyRQaJnB-4I6DbLDeFhCXtJQwqhrsCU.jpg?width=108&crop=smart&auto=webp&s=f650b19a78381e2e7232f5c68f5c7a7872c4be22', 'width': 108}, {'height': 108, 'url': 'h... |
New model just dropped: WizardCoder-15B-v1.0 model achieves 57.3 pass@1 on the HumanEval Benchmarks .. 22.3 points higher than the SOTA open-source Code LLMs. | 232 | 2023-06-14T20:50:02 | https://twitter.com/TheBlokeAI/status/1669032287416066063 | Zelenskyobama2 | twitter.com | 1970-01-01T00:00:00 | 0 | {} | 149ir49 | false | {'oembed': {'author_name': 'Tom Jobbins', 'author_url': 'https://twitter.com/TheBlokeAI', 'cache_age': 3153600000, 'height': None, 'html': '<blockquote class="twitter-video"><p lang="en" dir="ltr">New StarCoder coding model from <a href="https://twitter.com/WizardLM_AI?ref_src=twsrc%5Etfw">@WizardLM_AI</a> <br>"Wi... | t3_149ir49 | /r/LocalLLaMA/comments/149ir49/new_model_just_dropped_wizardcoder15bv10_model/ | false | false | 232 | {'enabled': False, 'images': [{'id': 'sdZCEDH6vEPePQosukNPoJBQkfbmKFDoiiOCaRr3MaM', 'resolutions': [{'height': 108, 'url': 'https://external-preview.redd.it/LDz9t2YDUQGVPqoN8o0Ev59CrRHWPrlJTMtNl3DJMe0.jpg?width=108&crop=smart&auto=webp&s=10cc2c8cc49b3f13b3f90bba40bff487054e2ead', 'width': 108}], 'source': {'height': 14... | ||
Community driven Open Source dataset collaboration platform | 26 | I am trying to create a platform where people can get together and edit datasets that can be used to fine tune or train models. I want it to be as easy as possible to collaborate, check eachother's work, and keep everything transparent. A few people suggested to me Google Sheets, but that's not viable due to Google's t... | 2023-06-14T19:34:06 | https://www.reddit.com/r/LocalLLaMA/comments/149gv4d/community_driven_open_source_dataset/ | CheshireAI | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 149gv4d | false | null | t3_149gv4d | /r/LocalLLaMA/comments/149gv4d/community_driven_open_source_dataset/ | false | false | self | 26 | null |
Elevating Gaming to New Heights: Unleashing Next-Level Performance with Arc GPUs | 0 | [removed] | 2023-06-14T18:33:45 | [deleted] | 1970-01-01T00:00:00 | 0 | {} | 149fcgq | false | null | t3_149fcgq | /r/LocalLLaMA/comments/149fcgq/elevating_gaming_to_new_heights_unleashing/ | false | false | default | 0 | null | ||
Cpu models 16gb ram | 1 | [removed] | 2023-06-14T18:17:33 | https://www.reddit.com/r/LocalLLaMA/comments/149eycf/cpu_models_16gb_ram/ | SignificantAd5514 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 149eycf | false | null | t3_149eycf | /r/LocalLLaMA/comments/149eycf/cpu_models_16gb_ram/ | false | false | default | 1 | null |
Do you ever see emojis in the output of your GGML model in ooba using streaming? | 2 | I don't know what options you have, I never got ooba to run. This is also why I ask instead of checking myself. So I am using llama-cpp-python and I know ooba uses that too, and I noticed emojis are just destroyed when I try to use streaming (meaning the output updates instead of waiting for the whole thing to complete... | 2023-06-14T17:47:52 | https://www.reddit.com/r/LocalLLaMA/comments/149e87t/do_you_ever_see_emojis_in_the_output_of_your_ggml/ | involviert | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 149e87t | false | null | t3_149e87t | /r/LocalLLaMA/comments/149e87t/do_you_ever_see_emojis_in_the_output_of_your_ggml/ | false | false | self | 2 | null |
Karen the Editor and quotations | 3 | I have a question regarding the way how [Karen the Editor](https://huggingface.co/FPHam/Karen_theEditor_13b_HF) was trained. Specifically, the model card mentions: "Based on LLAMA 13b and Wizard-Vucna-uncensored finetune, then finetuned with about 20k grammar examples (bad grammar/good grammar)."
However, for non-fic... | 2023-06-14T17:42:35 | https://www.reddit.com/r/LocalLLaMA/comments/149e3ht/karen_the_editor_and_quotations/ | patrakov | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 149e3ht | false | null | t3_149e3ht | /r/LocalLLaMA/comments/149e3ht/karen_the_editor_and_quotations/ | false | false | self | 3 | {'enabled': False, 'images': [{'id': 'uJ9V-m-WnuFvsV7073FF7JnV8PxGeAFxWkMfb-qhs5Y', 'resolutions': [{'height': 58, 'url': 'https://external-preview.redd.it/pcjOj1U3Tkw7EAVTVCpoNljTAvoJDB2vPu5Vq0JX8cs.jpg?width=108&crop=smart&auto=webp&s=86802327304e4cebeaf4a7abd3aa3b962a2fe43e', 'width': 108}, {'height': 116, 'url': 'h... |
What's the best current open source model for a) vectorizing pdfs b) generative Q and A? | 6 | Looking for somethin equivalent to ChatGPT's performance in this task, although I know that of course nothing comes close. | 2023-06-14T17:20:06 | https://www.reddit.com/r/LocalLLaMA/comments/149dj2k/whats_the_best_current_open_source_model_for_a/ | bramitkittel | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 149dj2k | false | null | t3_149dj2k | /r/LocalLLaMA/comments/149dj2k/whats_the_best_current_open_source_model_for_a/ | false | false | self | 6 | null |
Oobabooga not recognizing GPU for adding layers | 3 | Apparently the one-click install method for Oobabooga comes with a 1.3B model from Facebook which didn't seem the best in the time I experimented with it, but one thing I noticed right away was that text generation was incredibly fast (about 28 tokens/sec) and my GPU was being utilized.
I have a GGML model that claims... | 2023-06-14T16:48:49 | https://www.reddit.com/r/LocalLLaMA/comments/149crc9/oobabooga_not_recognizing_gpu_for_adding_layers/ | yungfishstick | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 149crc9 | false | null | t3_149crc9 | /r/LocalLLaMA/comments/149crc9/oobabooga_not_recognizing_gpu_for_adding_layers/ | false | false | self | 3 | null |
Please don’t close this Sub. Open-source AI needs all the help it can get | 136 | [removed] | 2023-06-14T16:25:44 | https://www.pinsentmasons.com/out-law/news/meps-eu-ai-act-foundation-models | IntenseSunshine | pinsentmasons.com | 1970-01-01T00:00:00 | 0 | {} | 149c7a8 | true | null | t3_149c7a8 | /r/LocalLLaMA/comments/149c7a8/please_dont_close_this_sub_opensource_ai_needs/ | false | false | default | 136 | null |
I was finally able to get WizardLM-13B to work on my GTX 1080 but alas only getting 0.01 tokens per second... | 25 | Is this to be expected?
Also, I'm thinking about getting a dedicated LocalLLM system, maybe a 24GB 4090? What kind of tokens per second might this generate on the Wizard model?
Apologies for the noob question but I have no idea what to expect as I'm just learning the ropes. | 2023-06-14T16:16:18 | https://www.reddit.com/r/LocalLLaMA/comments/149byz4/i_was_finally_able_to_get_wizardlm13b_to_work_on/ | amoebatron | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 149byz4 | false | null | t3_149byz4 | /r/LocalLLaMA/comments/149byz4/i_was_finally_able_to_get_wizardlm13b_to_work_on/ | false | false | self | 25 | null |
LLM that answers questions based on documents | 5 | Hi I’m trying to create a chatbot that can answer my questions based on a collection of documents that the model is “trained” on. I need something that I can use within my business, so privacy and the ability to use it commercially are important. I’ve looked into OpenLlama and LangChain, but am wondering what the best ... | 2023-06-14T15:39:13 | https://www.reddit.com/r/LocalLLaMA/comments/149b22m/llm_that_answers_questions_based_on_documents/ | Sea_Koala_7726 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 149b22m | false | null | t3_149b22m | /r/LocalLLaMA/comments/149b22m/llm_that_answers_questions_based_on_documents/ | false | false | self | 5 | null |
Creating a Wiki for all things Local LLM. What do you want to know? | 231 | It's becoming abundantly clear there is a lot of information you need to know to get into this space, making it hard for people to get started. I'm working with a small group to create a wiki page so that way its easier for people to get started. What questions do you want answered or what are the most important things... | 2023-06-14T15:08:37 | https://www.reddit.com/r/LocalLLaMA/comments/149abrg/creating_a_wiki_for_all_things_local_llm_what_do/ | NeverEndingToast | self.LocalLLaMA | 2023-06-15T20:02:39 | 0 | {} | 149abrg | false | null | t3_149abrg | /r/LocalLLaMA/comments/149abrg/creating_a_wiki_for_all_things_local_llm_what_do/ | false | false | self | 231 | {'enabled': False, 'images': [{'id': 'F-ZIOBaWaYfLE07ouyeSREiOsgeE3ZhYPXamY49eupo', 'resolutions': [{'height': 54, 'url': 'https://external-preview.redd.it/4hMqxqhyCozSMG1wf_HlP3tGKdFb0v1VvG1AzZjl3Sg.jpg?width=108&crop=smart&auto=webp&s=d0aa982ee62c7d69336e3bc704fb2a602edd62e0', 'width': 108}, {'height': 108, 'url': 'h... |
Subsets and Splits
No community queries yet
The top public SQL queries from the community will appear here once available.