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 ⌀ |
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
Quantization: How Much Quality is Lost? | 52 | Yeehaw, y'all 🤠
I've been pondering a lot about quantization and its impact on large language models (LLMs). As you all may know, quantization techniques like 4-bit and 8-bit quantization have been a boon for us consumers, allowing us to run larger models than our hardware would typically be able to handle. However, ... | 2023-07-19T05:11:06 | https://www.reddit.com/r/LocalLLaMA/comments/153lfc2/quantization_how_much_quality_is_lost/ | Prince-of-Privacy | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 153lfc2 | false | null | t3_153lfc2 | /r/LocalLLaMA/comments/153lfc2/quantization_how_much_quality_is_lost/ | false | false | self | 52 | null |
Updates on the Agency library, now with AMQP support | 3 | Hello LocalLlama!
I've previously posted about my python agent library called [`agency`](https://github.com/operand/agency). There's some great updates to share so I thought I'd post another followup.
I've got two big things:
1. A couple weeks back I added AMQP (RabbitMQ) support to the library. This means that you ... | 2023-07-19T05:08:36 | https://www.reddit.com/r/LocalLLaMA/comments/153ldk7/updates_on_the_agency_library_now_with_amqp/ | helloimop | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 153ldk7 | false | null | t3_153ldk7 | /r/LocalLLaMA/comments/153ldk7/updates_on_the_agency_library_now_with_amqp/ | false | false | self | 3 | {'enabled': False, 'images': [{'id': 'm6th8V7E7zzx2CCzdbrW9zvqJWfFxufjUAokKdD9Qaw', 'resolutions': [{'height': 54, 'url': 'https://external-preview.redd.it/U0vhJWc4IXjR4hRqBe6o2Nlz4dpXZqMTmclZj9vSukc.jpg?width=108&crop=smart&auto=webp&s=875dcf7e2c9c07458396f503d7cf2976a3c33503', 'width': 108}, {'height': 108, 'url': 'h... |
Llama 2 is disappointing | 10 | With each new model launch, it's claimed that they at least match the quality of ChatGPT-3.5, yet the outcomes often fall short of expectations. Llama 2 hasn't broken this trend.
I gave the finetuned Llama 2 70b Chat model a go: [**https://huggingface.co/spaces/ysharma/Explore\_llamav2\_with\_TGI**](https://huggingfac... | 2023-07-19T04:46:30 | https://www.reddit.com/r/LocalLLaMA/comments/153kxwx/llama_2_is_disappointing/ | Big_Communication353 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 153kxwx | false | null | t3_153kxwx | /r/LocalLLaMA/comments/153kxwx/llama_2_is_disappointing/ | false | false | self | 10 | {'enabled': False, 'images': [{'id': 'jVfONw70j9xFSHK2sFB3j_M0ywv9sgZ9DCoGJM3sD1Y', 'resolutions': [{'height': 58, 'url': 'https://external-preview.redd.it/oxSfOoIcjr7WIJyWU1rqijaKy4fO5uiVIp7HTNVufXM.jpg?width=108&crop=smart&auto=webp&s=6f30a110b0af985d1d8140231cd4f0316a48f80a', 'width': 108}, {'height': 116, 'url': 'h... |
Llama2 Censored? | 3 | You cant get it to write a childrens story that involves the end of the world 🥲 | 2023-07-19T04:17:20 | https://www.reddit.com/gallery/153kd62 | Sumozebra | reddit.com | 1970-01-01T00:00:00 | 0 | {} | 153kd62 | false | null | t3_153kd62 | /r/LocalLLaMA/comments/153kd62/llama2_censored/ | false | false | 3 | null | |
How much better is Llama 2? A simple example | 1 | 2023-07-19T04:13:17 | https://github.com/hegelai/prompttools/blob/main/examples/notebooks/LlamaHeadToHead.ipynb | hegel-ai | github.com | 1970-01-01T00:00:00 | 0 | {} | 153ka5o | false | null | t3_153ka5o | /r/LocalLLaMA/comments/153ka5o/how_much_better_is_llama_2_a_simple_example/ | false | false | 1 | {'enabled': False, 'images': [{'id': 'VTGUfFaipsQFbnM1m8I4CHic0B28M3GqpoMOgz7_bo0', 'resolutions': [{'height': 54, 'url': 'https://external-preview.redd.it/jW7Q-WB7W-0SGDaI6wRH3CjPIsGNii1Ur-ZO62DnuK8.jpg?width=108&crop=smart&auto=webp&s=da8fa70753162fa655cd03ab79dac2793daf5445', 'width': 108}, {'height': 108, 'url': 'h... | ||
Seems like we can continue to scale tokens and get returns model performance well after 2T tokens. | 122 | 2023-07-19T04:00:37 | onil_gova | i.redd.it | 1970-01-01T00:00:00 | 0 | {} | 153k0ph | false | null | t3_153k0ph | /r/LocalLLaMA/comments/153k0ph/seems_like_we_can_continue_to_scale_tokens_and/ | false | false | 122 | {'enabled': True, 'images': [{'id': '_QvOymv7LHPPeoIF0xYPiNpwwGlkPBC6RDLPxxqMNRA', 'resolutions': [{'height': 60, 'url': 'https://preview.redd.it/9twlx3ctgucb1.png?width=108&crop=smart&auto=webp&s=c0b1095e36e2bf269b9094f938d0ded128b93feb', 'width': 108}, {'height': 121, 'url': 'https://preview.redd.it/9twlx3ctgucb1.png... | |||
Where is the LLaMA v2 34B model? Are they not releasing it? | 2 | 2023-07-19T03:27:02 | onil_gova | i.redd.it | 1970-01-01T00:00:00 | 0 | {} | 153jcbz | false | null | t3_153jcbz | /r/LocalLLaMA/comments/153jcbz/where_is_the_llama_v2_34b_model_are_they_not/ | false | false | 2 | {'enabled': True, 'images': [{'id': '-u5tAilH5APZR_ICtEtXa3q1MlcnfsnIDi5nJFqsXvs', 'resolutions': [{'height': 41, 'url': 'https://preview.redd.it/gwo80nuzbucb1.png?width=108&crop=smart&auto=webp&s=fd0ebd9811f5f990c5d375ba8718592586e0bb0b', 'width': 108}, {'height': 83, 'url': 'https://preview.redd.it/gwo80nuzbucb1.png?... | |||
local llm function calling | 4 | I was working on a few internal prototypes at work and I was using the chatGPT function calling. It's crazy powerful. Can this structure be represented using llama-2 for example for do I just have to write a fancy prompt? | 2023-07-19T03:02:23 | https://www.reddit.com/r/LocalLLaMA/comments/153iu1x/local_llm_function_calling/ | APUsilicon | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 153iu1x | false | null | t3_153iu1x | /r/LocalLLaMA/comments/153iu1x/local_llm_function_calling/ | false | false | self | 4 | null |
Llama 2 - LLM Leaderboard Performance | 47 | Multiple leaderboard evaluations for Llama 2 are in and overall it seems quite impressive.
[https://huggingface.co/spaces/HuggingFaceH4/open\_llm\_leaderboard](https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard)
This is the most popular leaderboard, but not sure it can be trusted right now since it's ... | 2023-07-19T02:50:49 | https://www.reddit.com/r/LocalLLaMA/comments/153ikue/llama_2_llm_leaderboard_performance/ | DontPlanToEnd | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 153ikue | false | null | t3_153ikue | /r/LocalLLaMA/comments/153ikue/llama_2_llm_leaderboard_performance/ | false | false | self | 47 | {'enabled': False, 'images': [{'id': 'EN0-abblERL52DxeoNzcxdkhvXEwLdZMJTS58Umjs64', 'resolutions': [{'height': 58, 'url': 'https://external-preview.redd.it/pnEIDVgN3O3UZSEZF8G101Cpm5FLu9i3k_abBlep_2c.jpg?width=108&crop=smart&auto=webp&s=6fbb309f983333cbaf528bd40f8d6ffb39877704', 'width': 108}, {'height': 116, 'url': 'h... |
Llama 2 13b with kobold cpp issue. | 1 | Trying to use llama 2 13b on kobold cpp, it can't even form a complete paragraph. Any pointers guys? | 2023-07-19T02:48:39 | SuggestionInside5234 | i.redd.it | 1970-01-01T00:00:00 | 0 | {} | 153ij6s | false | null | t3_153ij6s | /r/LocalLLaMA/comments/153ij6s/llama_2_13b_with_kobold_cpp_issue/ | false | false | 1 | {'enabled': True, 'images': [{'id': 'aL9Pm6DnJZMWydP8LK_0O3KvtvDadivkUIB5k3wXMQI', 'resolutions': [{'height': 51, 'url': 'https://preview.redd.it/0p8c3iof5ucb1.jpg?width=108&crop=smart&auto=webp&s=b967fb95c604bb6f109292836ce2bfcd128ce047', 'width': 108}, {'height': 102, 'url': 'https://preview.redd.it/0p8c3iof5ucb1.jpg... | ||
How to finetune Guanaco or Airoboros 13B/4bit on Windows? | 1 | Hi all. I'm struggling to find a way to finetune 4 bit models on Windows. Seems to do so in oobabooga it needs GPTQ-for-LLaMA which needs Triton which needs Linux (or WSL which I attempted to install oobabooga but it's the end of a long day of getting to this point and just didn't have the heart left to learn WSL/Lin... | 2023-07-19T02:36:13 | https://www.reddit.com/r/LocalLLaMA/comments/153i9tu/how_to_finetune_guanaco_or_airoboros_13b4bit_on/ | TheNitzel | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 153i9tu | false | null | t3_153i9tu | /r/LocalLLaMA/comments/153i9tu/how_to_finetune_guanaco_or_airoboros_13b4bit_on/ | false | false | self | 1 | null |
No, Llama 2 is NOT an open source LLM | 12 | I have seen many people call llama2 the most capable open source LLM. This is not true so please please stop spreading this misinformation. It is doing more harm than good.
Open source means two things:
- Anyone can access the code and weights and use it however they want, no strings attached.
- Anyone can use the mod... | 2023-07-19T02:32:26 | https://www.reddit.com/r/LocalLLaMA/comments/153i6vi/no_llama_2_is_not_an_open_source_llm/ | Amgadoz | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 153i6vi | false | null | t3_153i6vi | /r/LocalLLaMA/comments/153i6vi/no_llama_2_is_not_an_open_source_llm/ | false | false | self | 12 | null |
Business Training Application Feasability | 3 | I am a CPA and can attest that small CPA shops are in the Stone Age technology wise and also struggle with retaining senior associates to train their new hires. I was wondering if it would be feasible to work with CPA firms to document their processes and procedures and then have a developer use the data to train a loc... | 2023-07-19T02:27:30 | https://www.reddit.com/r/LocalLLaMA/comments/153i32b/business_training_application_feasability/ | Doggo_9000 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 153i32b | false | null | t3_153i32b | /r/LocalLLaMA/comments/153i32b/business_training_application_feasability/ | false | false | self | 3 | null |
any news on when Phi-1 will be released? | 2 | Microsoft said they'd release Phi-1, did they not? I haven't heard anything. is there an approximate timeline? | 2023-07-19T02:19:11 | https://www.reddit.com/r/LocalLLaMA/comments/153hwlj/any_news_on_when_phi1_will_be_released/ | Cunninghams_right | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 153hwlj | false | null | t3_153hwlj | /r/LocalLLaMA/comments/153hwlj/any_news_on_when_phi1_will_be_released/ | false | false | self | 2 | null |
Meta filtered LLaMa-2's training data to keep it G-rated as much as possible. If your intended use case isn't G-rated, you might be in for a disappointment. | 0 | Someone was posting [llama-chat being flirty earlier](/r/LocalLLaMA/comments/15388d6/llama_2_pffft_boundaries_ethics_dont_be_silly/) (given a specific system prompt, of course), but that doesn't mean it's ever actually seen any kind of adult content. This may impact certain kinds of story writing, even if you're not go... | 2023-07-19T01:59:28 | https://www.reddit.com/r/LocalLLaMA/comments/153hgpx/meta_filtered_llama2s_training_data_to_keep_it/ | Maristic | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 153hgpx | false | null | t3_153hgpx | /r/LocalLLaMA/comments/153hgpx/meta_filtered_llama2s_training_data_to_keep_it/ | false | false | self | 0 | null |
Llama v2 chat... don't think it is there yet. Need Fine Tune. | 0 | ​
https://preview.redd.it/bl3q2fs6vtcb1.png?width=1385&format=png&auto=webp&s=5edfd6b146fb8eab5d474bafb5825927cfd287c3 | 2023-07-19T01:51:53 | https://www.reddit.com/r/LocalLLaMA/comments/153haxw/llama_v2_chat_dont_think_it_is_there_yet_need/ | jackfood | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 153haxw | false | null | t3_153haxw | /r/LocalLLaMA/comments/153haxw/llama_v2_chat_dont_think_it_is_there_yet_need/ | false | false | 0 | null | |
Fine-tuning for accuracy | 8 | Hi everyone,
During the last months I've reading some of the posts regarding fine-tuning and customizing Local LLM for particular scenarios (and some questions about what are people doing with those Local LLM).
TL;DR: What is the best strategy to tune a LLM to select from a limited but accurate set of customizable re... | 2023-07-19T01:08:14 | https://www.reddit.com/r/LocalLLaMA/comments/153gc7p/finetuning_for_accuracy/ | elsatch | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 153gc7p | false | null | t3_153gc7p | /r/LocalLLaMA/comments/153gc7p/finetuning_for_accuracy/ | false | false | self | 8 | null |
LLaMA-2-70B-GPTQ-transformers4.32.0.dev0, 4bit quantization working with GPTQ for LLaMA! | 65 | 2023-07-19T00:34:58 | https://huggingface.co/Panchovix/LLaMA-2-70B-GPTQ-transformers4.32.0.dev0 | panchovix | huggingface.co | 1970-01-01T00:00:00 | 0 | {} | 153flql | false | null | t3_153flql | /r/LocalLLaMA/comments/153flql/llama270bgptqtransformers4320dev0_4bit/ | false | false | 65 | {'enabled': False, 'images': [{'id': '9SChMy77DY8uX1j6uPNCVG94VDqvd5nSNweBCfsX0Ow', 'resolutions': [{'height': 58, 'url': 'https://external-preview.redd.it/jaZFnbNRzqcWGq_z3P5wTpznBrUnwJzraM_WDsGQx1o.jpg?width=108&crop=smart&auto=webp&s=382be2aac44ea31e81dd4929b1bb417651250989', 'width': 108}, {'height': 116, 'url': 'h... | ||
Why we don't need a label data for fine-tuning model with qlora ? | 7 | From this notebook seems like the author didn't use any label for the dataset
[https://colab.research.google.com/drive/1VoYNfYDKcKRQRor98Zbf2-9VQTtGJ24k?usp=sharing](https://colab.research.google.com/drive/1VoYNfYDKcKRQRor98Zbf2-9VQTtGJ24k?usp=sharing)
​
it seems like it can be explained here: [https://huggin... | 2023-07-18T22:10:45 | https://www.reddit.com/r/LocalLLaMA/comments/153c2pd/why_we_dont_need_a_label_data_for_finetuning/ | Cheap-Routine4736 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 153c2pd | false | null | t3_153c2pd | /r/LocalLLaMA/comments/153c2pd/why_we_dont_need_a_label_data_for_finetuning/ | false | false | 7 | {'enabled': False, 'images': [{'id': 'nkhh65ujo5BznFJFojoMPaKjGuLSpPj6KGhRov-ykOg', 'resolutions': [{'height': 108, 'url': 'https://external-preview.redd.it/MrcDZx2izDY9ERwgWmMS-Hm2M3GEKZgeYLDszSh-KrQ.jpg?width=108&crop=smart&auto=webp&s=4b647239f77bf713f4a6209cfa4867351c055fd9', 'width': 108}, {'height': 216, 'url': '... | |
Bing Chat Enterprise | 1 | [removed] | 2023-07-18T22:07:07 | https://www.reddit.com/r/LocalLLaMA/comments/153bza4/bing_chat_enterprise/ | gptzerozero | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 153bza4 | false | null | t3_153bza4 | /r/LocalLLaMA/comments/153bza4/bing_chat_enterprise/ | false | false | self | 1 | null |
What does Typical P actually do? | 8 | Hi, all,
I've been experimenting with SillyTavern, using both llama.cpp and Ooba, and I've noticed an odd trend across a lot of models. I've found a ton of references online to set Typical P / Typical Sampling to 0.2, but I've found that doing so seems somehow to lobotomize any model I throw at it. This happens on bot... | 2023-07-18T21:54:52 | https://www.reddit.com/r/LocalLLaMA/comments/153bnly/what_does_typical_p_actually_do/ | smile_e_face | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 153bnly | false | null | t3_153bnly | /r/LocalLLaMA/comments/153bnly/what_does_typical_p_actually_do/ | false | false | self | 8 | null |
Anybody know of other good LLM subs? | 6 | Hey there everybody. I’m an avid AI enthusiast and love anything to do with language model or image generation models.
However, I have found that this sub and the official server are too centralized in regards to moderation and the ability to influence the community for my taste.
I love this community, however I woul... | 2023-07-18T21:37:31 | https://www.reddit.com/r/LocalLLaMA/comments/153b7ih/anybody_know_of_other_good_llm_subs/ | OfficialHaethus | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 153b7ih | false | null | t3_153b7ih | /r/LocalLLaMA/comments/153b7ih/anybody_know_of_other_good_llm_subs/ | false | false | self | 6 | null |
Best ways to add guardrails to uncensored open source LLMs? | 3 | I’m trying to act a few guardrails so that the LLMs stay in character.
Sometimes the LLMs say something irrelevant completely different from what was asked like asking ‘how your day going?’ and it starts replying about some mathematical equation.
Other times it acts like a knowledge bank instead of staying in the cha... | 2023-07-18T21:26:14 | https://www.reddit.com/r/LocalLLaMA/comments/153ax67/best_ways_to_add_guardrails_to_uncensored_open/ | RepresentativeOdd276 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 153ax67 | false | null | t3_153ax67 | /r/LocalLLaMA/comments/153ax67/best_ways_to_add_guardrails_to_uncensored_open/ | false | false | self | 3 | null |
GPT4ALL python code not using full RAM or CPU. | 0 | Hi all,
Just like the title says, I am running gpt4all in a pycharm project and when I run the code and watch the performance of my PC in the task manager I see that it is only using a fraction of my RAM and CPU power. How can I adjust the model/program so that it utilizes all my RAM/CPU?
I have 55GB of RAM available... | 2023-07-18T21:20:42 | https://www.reddit.com/r/LocalLLaMA/comments/153as3c/gpt4all_python_code_not_using_full_ram_or_cpu/ | thedenfather | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 153as3c | false | null | t3_153as3c | /r/LocalLLaMA/comments/153as3c/gpt4all_python_code_not_using_full_ram_or_cpu/ | false | false | self | 0 | null |
Noob Question | 1 | [removed] | 2023-07-18T20:22:33 | https://www.reddit.com/r/LocalLLaMA/comments/15399r3/noob_question/ | morecontextplz1 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 15399r3 | false | null | t3_15399r3 | /r/LocalLLaMA/comments/15399r3/noob_question/ | false | false | self | 1 | null |
Llama 2 has roles support | 6 | They mention it in Readme.
Implementation is in generation.py in llama repository.
if dialog[0]["role"] != "system":
dialog = [
{
"role": "system",
"content": DEFAULT_SYSTEM_PROMPT,
}
] + dialog
... | 2023-07-18T20:06:26 | https://www.reddit.com/r/LocalLLaMA/comments/1538ufu/llama_2_has_roles_support/ | nikitastaf1996 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 1538ufu | false | null | t3_1538ufu | /r/LocalLLaMA/comments/1538ufu/llama_2_has_roles_support/ | false | false | self | 6 | null |
Llama 2: Pffft, boundaries? Ethics? Don't be silly! | 267 | 2023-07-18T19:43:24 | WolframRavenwolf | i.redd.it | 1970-01-01T00:00:00 | 0 | {} | 15388d6 | false | null | t3_15388d6 | /r/LocalLLaMA/comments/15388d6/llama_2_pffft_boundaries_ethics_dont_be_silly/ | false | false | 267 | {'enabled': True, 'images': [{'id': '8fm2DFen_NkgpI9NnuxR4Ho_2UnttXx-I85beb2ATYw', 'resolutions': [{'height': 84, 'url': 'https://preview.redd.it/0gjpjqul0scb1.png?width=108&crop=smart&auto=webp&s=944c268a2410012bddc7966c988866bb3cbd6da2', 'width': 108}, {'height': 169, 'url': 'https://preview.redd.it/0gjpjqul0scb1.png... | |||
Airoboros 33b, 16k context, GGML, now available. | 51 | Ycros has uploaded a GGML edition of Airoboros 33b with 16k context. Here is the link.
https://huggingface.co/ycros/airoboros-33b-gpt4-1.4.1-lxctx-PI-16384-GGML/tree/main
Thank you, Ycros. :) | 2023-07-18T19:40:26 | https://www.reddit.com/r/LocalLLaMA/comments/15385ih/airoboros_33b_16k_context_ggml_now_available/ | Sabin_Stargem | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 15385ih | false | null | t3_15385ih | /r/LocalLLaMA/comments/15385ih/airoboros_33b_16k_context_ggml_now_available/ | false | false | self | 51 | {'enabled': False, 'images': [{'id': 'Lq14yBiK46oBlibmggvxzAV1L_cb8FDs-3ee7_YaTFs', 'resolutions': [{'height': 58, 'url': 'https://external-preview.redd.it/XVW73v1uE1ZTMFOgCH4t939HzWib90WX2uONna5RlLQ.jpg?width=108&crop=smart&auto=webp&s=e51d5bb1578a67e29fa50f2d9b38dbb513ce437f', 'width': 108}, {'height': 116, 'url': 'h... |
Llama 2 download links: GPTQ and ggml | 99 | **GPTQ** and **ggml**
Llama 2 download links have been added to the wiki: [https://www.reddit.com/r/LocalLLaMA/wiki/models/#wiki\_llama\_2\_models](https://www.reddit.com/r/LocalLLaMA/wiki/models/#wiki_llama_2_models)
If you're new to the sub and Llama, please see the stickied post below for information on getting st... | 2023-07-18T19:25:48 | https://www.reddit.com/r/LocalLLaMA/comments/1537ri3/llama_2_download_links_gptq_and_ggml/ | AutoModerator | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 1537ri3 | true | null | t3_1537ri3 | /r/LocalLLaMA/comments/1537ri3/llama_2_download_links_gptq_and_ggml/ | false | false | self | 99 | null |
Llama 2 download links: GPTQ and ggml | 1 | \*\*GPTQ and \*\*ggml\*\*
Llama 2 download links, along with the Llama 2 Chat prompt template, have been added to the wiki: [https://www.reddit.com/r/LocalLLaMA/wiki/models/#wiki\_llama\_2\_models](https://www.reddit.com/r/LocalLLaMA/wiki/models/#wiki_llama_2_models)
If you're new to the sub and Llama, please see the... | 2023-07-18T19:23:24 | https://www.reddit.com/r/LocalLLaMA/comments/1537p8h/llama_2_download_links_gptq_and_ggml/ | AutoModerator | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 1537p8h | true | null | t3_1537p8h | /r/LocalLLaMA/comments/1537p8h/llama_2_download_links_gptq_and_ggml/ | false | false | self | 1 | null |
Llama-2-chat shocked me!! | 1 | I just tried Llama 2 chat 7b on my Android phone.
I was shocked by the answer. Initialy I thought its garbage but it after a moment I realized it was an answer on a different level. I was expecting a more polished answer given that this model is tuned for commerical use.
Have anyone noticed similar responses?
PS: I u... | 2023-07-18T19:20:17 | AstrionX | i.redd.it | 1970-01-01T00:00:00 | 0 | {} | 1537m6w | false | null | t3_1537m6w | /r/LocalLLaMA/comments/1537m6w/llama2chat_shocked_me/ | false | false | 1 | {'enabled': True, 'images': [{'id': 'aLh9F3w2OJH3FaTEGnRCTPeyEBhhrtccgXgmo4PLdYo', 'resolutions': [{'height': 216, 'url': 'https://preview.redd.it/hvfc1zjgxrcb1.jpg?width=108&crop=smart&auto=webp&s=dae859df4546f2235b1485e82f86e3b441598a43', 'width': 108}, {'height': 432, 'url': 'https://preview.redd.it/hvfc1zjgxrcb1.jp... | ||
Any LLM Models To Generate A Grammatically Correct Statement Into An Incorrect Statement | 5 | Sort of a weird request, but does anyone know of a model that will turn a correct sentence into an incorrect sentence with grammar mistakes?
Thanks! | 2023-07-18T18:57:47 | https://www.reddit.com/r/LocalLLaMA/comments/15370l9/any_llm_models_to_generate_a_grammatically/ | laneciar | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 15370l9 | false | null | t3_15370l9 | /r/LocalLLaMA/comments/15370l9/any_llm_models_to_generate_a_grammatically/ | false | false | self | 5 | null |
TheBloke pulling through with all the Llama 2 models just hours after release | 1 | 2023-07-18T18:47:09 | https://huggingface.co/TheBloke | jd_3d | huggingface.co | 1970-01-01T00:00:00 | 0 | {} | 1536qre | false | null | t3_1536qre | /r/LocalLLaMA/comments/1536qre/thebloke_pulling_through_with_all_the_llama_2/ | false | false | 1 | {'enabled': False, 'images': [{'id': 'ijgSlZO3K44WshhENFl9jhybG8Na3DBCsOXCuyZgycw', 'resolutions': [{'height': 58, 'url': 'https://external-preview.redd.it/xoOXoChYs6mWDlUf2h1S1ZmC14O0X-Z2_QHtAdDh0C8.jpg?width=108&crop=smart&auto=webp&s=3e5fdcc67bd2b0779a9f019942e0727ffb86630b', 'width': 108}, {'height': 116, 'url': 'h... | ||
airoboros (tool) overhaul | 31 | Hello,
Just wanted to drop a note that I overhauled the [airoboros](https://github.com/jondurbin/airoboros) tool *not the models* to have most of the prompts I've been using to build the datasets, plus a couple extras.
Available via pip also:
pip install --upgrade airoboros
The configuration is now a YAML file,... | 2023-07-18T18:26:56 | https://www.reddit.com/r/LocalLLaMA/comments/15367sf/airoboros_tool_overhaul/ | JonDurbin | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 15367sf | false | null | t3_15367sf | /r/LocalLLaMA/comments/15367sf/airoboros_tool_overhaul/ | false | false | self | 31 | {'enabled': False, 'images': [{'id': '4CODUZbJ6dyCVnStILqL0vJnMsJMmVnR1jVNmAlDU1k', 'resolutions': [{'height': 54, 'url': 'https://external-preview.redd.it/xOOcp6Ds3mmKFLf9o-hBKm2cLUSp4bwI7kG2AsDKnbQ.jpg?width=108&crop=smart&auto=webp&s=39ed49eea184ea42eb9f8c038810264f16bc4f9b', 'width': 108}, {'height': 108, 'url': 'h... |
LLaMA-2 GGML & GPTQ already available thanks to TheBloke | 1 | [removed] | 2023-07-18T18:09:55 | https://www.reddit.com/r/LocalLLaMA/comments/1535rl1/llama2_ggml_gptq_already_available_thanks_to/ | aminedjeghri | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 1535rl1 | false | null | t3_1535rl1 | /r/LocalLLaMA/comments/1535rl1/llama2_ggml_gptq_already_available_thanks_to/ | false | false | self | 1 | {'enabled': False, 'images': [{'id': 'scnkn175QpfbMTdtoYxWh-I3soYhx9pJiHmW5tQQPMY', 'resolutions': [{'height': 58, 'url': 'https://external-preview.redd.it/MIHs_hUb2M9gxc4QGwbCk4JA2r5erDBnTB8Tbg735Rs.jpg?width=108&crop=smart&auto=webp&s=306a702906190a7340924eac46d7feb1f3eec45e', 'width': 108}, {'height': 116, 'url': 'h... |
Meta releases Llama 2 | 1 | 2023-07-18T17:57:29 | https://3s3.co/2023/07/18/meta-ai-releases-llama-2/ | vnpttl | 3s3.co | 1970-01-01T00:00:00 | 0 | {} | 1535fxu | false | null | t3_1535fxu | /r/LocalLLaMA/comments/1535fxu/meta_releases_llama_2/ | false | false | default | 1 | null | |
Bloke the goat | 4 | Llama 2 online guys!!!! | 2023-07-18T17:56:10 | Sensitive-Analyst288 | i.redd.it | 1970-01-01T00:00:00 | 0 | {} | 1535eq0 | false | null | t3_1535eq0 | /r/LocalLLaMA/comments/1535eq0/bloke_the_goat/ | false | false | 4 | {'enabled': True, 'images': [{'id': 'Q0jbox-9mxIte8unWo25U0fhWBrcYNR1M7htukrI9i0', 'resolutions': [{'height': 216, 'url': 'https://preview.redd.it/drlola6gircb1.jpg?width=108&crop=smart&auto=webp&s=af11e234dabf5dfaa821fe149fc2c2eb22da6271', 'width': 108}, {'height': 432, 'url': 'https://preview.redd.it/drlola6gircb1.jp... | ||
We made Llama13b-v2-chat immediately available as an endpoint for developers | 21 | Hey LocalLLaMA, we've released tools that make it easy to test LLaMa 2 and add it to your own app!
Model playground here: [https://llama2.ai](https://llama2.ai/)
Hosted chat API here: [https://replicate.com/a16z-infra/llama13b-v2-chat](https://replicate.com/a16z-infra/llama13b-v2-chat)
If you want to just play wit... | 2023-07-18T17:23:07 | https://www.reddit.com/r/LocalLLaMA/comments/1534kfe/we_made_llama13bv2chat_immediately_available_as/ | Prestigious-Elk7124 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 1534kfe | false | null | t3_1534kfe | /r/LocalLLaMA/comments/1534kfe/we_made_llama13bv2chat_immediately_available_as/ | false | false | self | 21 | null |
Anyone had any luck with 65b models and llama.cpp using the newly implemented rope scaling parameters to get contexts larger than 2048? | 13 | I've tried a few different values but so far it just generates really funny pidgin-sounding english, like "den the man went to to da shop store and dun some good things for shopping" or similar such nonsense.
I've had great luck with 33b models and up to 16k contexts to far, even with the superHOT 8k context models. ... | 2023-07-18T16:21:38 | https://www.reddit.com/r/LocalLLaMA/comments/1532yf0/anyone_had_any_luck_with_65b_models_and_llamacpp/ | spanielrassler | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 1532yf0 | false | null | t3_1532yf0 | /r/LocalLLaMA/comments/1532yf0/anyone_had_any_luck_with_65b_models_and_llamacpp/ | false | false | self | 13 | null |
BlinkDL/rwkv-4-music: New 120M and 560M MIDI models based on RWKV | 33 | 2023-07-18T16:17:08 | https://huggingface.co/BlinkDL/rwkv-4-music | Balance- | huggingface.co | 1970-01-01T00:00:00 | 0 | {} | 1532u7f | false | null | t3_1532u7f | /r/LocalLLaMA/comments/1532u7f/blinkdlrwkv4music_new_120m_and_560m_midi_models/ | false | false | 33 | {'enabled': False, 'images': [{'id': 'bWyTgxVzvLPddswLBnDx7CqEQIJaUGNfssNmo3WdoDQ', 'resolutions': [{'height': 58, 'url': 'https://external-preview.redd.it/9nZFog7YKCtoIJZ4EVTFwYzqitdjAp9cKo_fCYR7db8.jpg?width=108&crop=smart&auto=webp&s=1671624de12fa839075c548ea4dbaa17cc2b05cd', 'width': 108}, {'height': 116, 'url': 'h... | ||
Proposal of LLM hosted in a co-funded host | 6 | Hello:
I had and idea about how to get a big LLM (30/44 Gb) running fast in a cloud server.
What if this server would be scalable in potency and the renting shared in a group of united users?
Some sort of DAO to make it possible?
What do you think? | 2023-07-18T16:10:15 | https://www.reddit.com/r/LocalLLaMA/comments/1532njt/proposal_of_llm_hosted_in_a_cofunded_host/ | SnooWoofers780 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 1532njt | false | null | t3_1532njt | /r/LocalLLaMA/comments/1532njt/proposal_of_llm_hosted_in_a_cofunded_host/ | false | false | self | 6 | null |
PC game Vaudeville dialog is AI generated | 15 | [https://store.steampowered.com/app/2240920/Vaudeville/](https://store.steampowered.com/app/2240920/Vaudeville/)
I have no affiliation with the game and simply thought it was a very interesting game that people in this community would also find interesting.
The convos with the AI are actually very good, maybe one da... | 2023-07-18T15:51:41 | https://www.reddit.com/r/LocalLLaMA/comments/15325za/pc_game_vaudeville_dialog_is_ai_generated/ | Inevitable-Start-653 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 15325za | false | null | t3_15325za | /r/LocalLLaMA/comments/15325za/pc_game_vaudeville_dialog_is_ai_generated/ | false | false | self | 15 | {'enabled': False, 'images': [{'id': 'xBa29lVvA5Q7SoqhxS3ZKQZla1368tS34MBVodOovUA', 'resolutions': [{'height': 61, 'url': 'https://external-preview.redd.it/pzIfcSv32Mg6majmqKkA9WWMXTt_eggByTpkTtjiT1Y.jpg?width=108&crop=smart&auto=webp&s=83e00a641ad42e59bb2ffe4682055477802b5337', 'width': 108}, {'height': 123, 'url': 'h... |
LLaMA 2 is here | 849 | https://ai.meta.com/llama/ | 2023-07-18T15:50:06 | https://www.reddit.com/r/LocalLLaMA/comments/15324dp/llama_2_is_here/ | dreamingleo12 | self.LocalLLaMA | 1970-01-01T00:00:00 | 1 | {'gid_2': 1} | 15324dp | false | null | t3_15324dp | /r/LocalLLaMA/comments/15324dp/llama_2_is_here/ | false | false | self | 849 | {'enabled': False, 'images': [{'id': 'ilC2qprzEOhvondbER2GPm9DXBMFQhdj6lShAI3fqUQ', 'resolutions': [{'height': 60, 'url': 'https://external-preview.redd.it/-lx7IoVnPKtS1s2Rq8IcxH6q6WBMlXXfBQF43Q3okcU.jpg?width=108&crop=smart&auto=webp&s=b96f0fb64d0fd3022dd85d7522591d32ffa3e30e', 'width': 108}, {'height': 121, 'url': 'h... |
Generate both question and answer from the given context. | 3 | I want to make generate both multiple questions and answers from the given context, like ChatGPT. How to do it? and which model will perform better in this situation? I can do it using Conversational Langchain. But it is not quite good. | 2023-07-18T14:13:52 | https://www.reddit.com/r/LocalLLaMA/comments/152zmw2/generate_both_question_and_answer_from_the_given/ | mathageche | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 152zmw2 | false | null | t3_152zmw2 | /r/LocalLLaMA/comments/152zmw2/generate_both_question_and_answer_from_the_given/ | false | false | self | 3 | null |
LLM less chatty after LoRA finetune | 3 | I trained LoRAs for a few of the popular 33B LLaMA models (Wizard, Airoboros, etc) and observed that the LLMs with LoRA applied appear less chatty by A LOT.
All LoRAs were fine tuned for 2 epochs using the same Alpaca-like dataset containing 10K Q&A-style examples. The outputs in the training set is 68 tokens on aver... | 2023-07-18T13:25:40 | https://www.reddit.com/r/LocalLLaMA/comments/152yg19/llm_less_chatty_after_lora_finetune/ | gptzerozero | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 152yg19 | false | null | t3_152yg19 | /r/LocalLLaMA/comments/152yg19/llm_less_chatty_after_lora_finetune/ | false | false | self | 3 | null |
New Nvidia driver 536.67, a fix to memory issues(?) | 3 | Listed as an open issue in the driver notes because they've observed performance degradations to some applications:
>This driver implements a fix for creative application stability issues seen during heavy memory usage. We’ve observed some situations where this fix has resulted in performance degradation when running ... | 2023-07-18T13:17:00 | https://www.reddit.com/r/LocalLLaMA/comments/152y8t1/new_nvidia_driver_53667_a_fix_to_memory_issues/ | rerri | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 152y8t1 | false | null | t3_152y8t1 | /r/LocalLLaMA/comments/152y8t1/new_nvidia_driver_53667_a_fix_to_memory_issues/ | false | false | self | 3 | null |
gpt4all question | 1 | where is a good sub to get help with it? | 2023-07-18T12:30:47 | https://www.reddit.com/r/LocalLLaMA/comments/152x6q3/gpt4all_question/ | iseedeff | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 152x6q3 | false | null | t3_152x6q3 | /r/LocalLLaMA/comments/152x6q3/gpt4all_question/ | false | false | self | 1 | null |
MUD + LLM for a stronger roleplaying experience? | 54 | If you're a gen-x or xennial, MUDs were probably the rage when you went to high school. I never really got into the MUD thing, but had one of my strongest RP experiences ever in a MUSH (incidentally the only time I played one). But MUD's were a bit too rigid, and I was never into the mp aspect of them.
I've been playi... | 2023-07-18T11:45:48 | https://www.reddit.com/r/LocalLLaMA/comments/152w71n/mud_llm_for_a_stronger_roleplaying_experience/ | neph1010 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 152w71n | false | null | t3_152w71n | /r/LocalLLaMA/comments/152w71n/mud_llm_for_a_stronger_roleplaying_experience/ | false | false | 54 | null | |
Rachel the Assistant Editor | 1 | 2023-07-18T11:43:07 | AIsGonnaGetYa | i.redd.it | 1970-01-01T00:00:00 | 0 | {} | 152w527 | false | null | t3_152w527 | /r/LocalLLaMA/comments/152w527/rachel_the_assistant_editor/ | false | false | 1 | {'enabled': True, 'images': [{'id': 'X7XJq-26GOL0Y9HNHznUjQOl_W1aFZPOYW98bpzjunA', 'resolutions': [{'height': 108, 'url': 'https://preview.redd.it/rq4e5totnpcb1.png?width=108&crop=smart&auto=webp&s=173595b9b4997838c0fb9f7e78ccd46d4a00eb79', 'width': 108}, {'height': 216, 'url': 'https://preview.redd.it/rq4e5totnpcb1.pn... | |||
Deploy to hugging face with error Fine tuning "nRuntimeError: weight transformer.word_embeddings.weight does not exist" | 1 | Hi I fine tuned the model using this tutorial. It works great in notebook.
https://colab.research.google.com/drive/1FxlUb_H6Xirhkx4RszAgHeb2uDW7oKIH
After I deploy to inference endpoint, i get this error: "nRuntimeError: weight transformer.word_embeddings.weight does not exist"
Could someone please advise how to fix?... | 2023-07-18T11:42:30 | https://www.reddit.com/r/LocalLLaMA/comments/152w4no/deploy_to_hugging_face_with_error_fine_tuning/ | InterestingBasil | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 152w4no | false | null | t3_152w4no | /r/LocalLLaMA/comments/152w4no/deploy_to_hugging_face_with_error_fine_tuning/ | false | false | self | 1 | {'enabled': False, 'images': [{'id': 'nkhh65ujo5BznFJFojoMPaKjGuLSpPj6KGhRov-ykOg', 'resolutions': [{'height': 108, 'url': 'https://external-preview.redd.it/MrcDZx2izDY9ERwgWmMS-Hm2M3GEKZgeYLDszSh-KrQ.jpg?width=108&crop=smart&auto=webp&s=4b647239f77bf713f4a6209cfa4867351c055fd9', 'width': 108}, {'height': 216, 'url': '... |
In the end does the model actually matter? | 0 | It seems to me like the LLM community is putting a lot of effort into finding and building better models/datasets: we want models that can solve more abstract problems, store more knowledge, go further in a single step.
But we have also discovered that asking models to take smaller steps: 'explain your reasoning' or '... | 2023-07-18T11:13:30 | https://www.reddit.com/r/LocalLLaMA/comments/152vjk4/in_the_end_does_the_model_actually_matter/ | sdfgeoff | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 152vjk4 | false | null | t3_152vjk4 | /r/LocalLLaMA/comments/152vjk4/in_the_end_does_the_model_actually_matter/ | false | false | self | 0 | null |
Any love for Radeon Pro W6800 32GB ? What to expect ? | 16 | Hi,
I have an opportunity to get 2 or even 3 of those but can't find benchmark of them running LLMs, with all the hype being focused around Nvidia.
What could I expect to run on these ? Host would be a a dual E5-2670 or a i9-10900K, both with at least 128GB.
Thanks ! | 2023-07-18T10:58:35 | https://www.reddit.com/r/LocalLLaMA/comments/152v8fl/any_love_for_radeon_pro_w6800_32gb_what_to_expect/ | chiwawa_42 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 152v8fl | false | null | t3_152v8fl | /r/LocalLLaMA/comments/152v8fl/any_love_for_radeon_pro_w6800_32gb_what_to_expect/ | false | false | self | 16 | null |
Seeking Help to Run junelee/wizard-vicuna-13b GPT Model! | 1 |
I hope you're all having a fantastic day! I come to this amazing community seeking some assistance with running the junelee/wizard-vicuna-13b GPT model. I stumbled upon this powerful language model on Hugging Face's model hub ([**https://huggingface.co/junelee/wizard-vicuna-13b**](https://huggingface.co/junelee/wiza... | 2023-07-18T10:54:20 | https://www.reddit.com/r/LocalLLaMA/comments/152v5ja/seeking_help_to_run_juneleewizardvicuna13b_gpt/ | Nikunja___ | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 152v5ja | false | null | t3_152v5ja | /r/LocalLLaMA/comments/152v5ja/seeking_help_to_run_juneleewizardvicuna13b_gpt/ | false | false | self | 1 | {'enabled': False, 'images': [{'id': 'M47-BaZSzgabbr8l4gnwSUeo2F1rktYBnCcuLPf2oeM', 'resolutions': [{'height': 58, 'url': 'https://external-preview.redd.it/HTLb8kcnFUy-8ZrKjUTk3WZZnRkPjqZv_HEXxqepf74.jpg?width=108&crop=smart&auto=webp&s=f258b703c3a255385ec066795d80fef8c4227705', 'width': 108}, {'height': 116, 'url': 'h... |
Is oobabooga the only realistically useful alternative? | 0 | title | 2023-07-18T10:41:09 | https://www.reddit.com/r/LocalLLaMA/comments/152uw94/is_oobabooga_the_only_realistically_useful/ | BetterProphet5585 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 152uw94 | false | null | t3_152uw94 | /r/LocalLLaMA/comments/152uw94/is_oobabooga_the_only_realistically_useful/ | false | false | self | 0 | null |
Do you find GPU renting worth it for a LocalLLM? | 39 | Let's be real, at the moment near to no one can afford to get that much VRAM.
What are some realistic costs projections for running local LLMs that are decent and fast? | 2023-07-18T10:40:00 | https://www.reddit.com/r/LocalLLaMA/comments/152uvdv/do_you_find_gpu_renting_worth_it_for_a_localllm/ | BetterProphet5585 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 152uvdv | false | null | t3_152uvdv | /r/LocalLLaMA/comments/152uvdv/do_you_find_gpu_renting_worth_it_for_a_localllm/ | false | false | self | 39 | null |
Text to SQL LLMs | 9 | Anyone who has used text to SQL LLMs in a production setting? How do you rate their performance based on accuracy, consistency and reliability?
https://github.com/NumbersStationAI/NSQL | 2023-07-18T10:04:06 | https://www.reddit.com/r/LocalLLaMA/comments/152u7jp/text_to_sql_llms/ | oduor_c | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 152u7jp | false | null | t3_152u7jp | /r/LocalLLaMA/comments/152u7jp/text_to_sql_llms/ | false | false | self | 9 | {'enabled': False, 'images': [{'id': 'OmlAQPV0rfnich01HVmULjHqyoGiaSDzrsu26n9uLIk', 'resolutions': [{'height': 54, 'url': 'https://external-preview.redd.it/udpkoS52WGef_7A2UGJ19TB1uPyjKgZs_L-25v7SwKI.jpg?width=108&crop=smart&auto=webp&s=ae3fca608e2300596b6e9fccc7642576ea857882', 'width': 108}, {'height': 108, 'url': 'h... |
When is it best to use prompt engineering vs fine-tuning? | 15 | As somebody who has been experimenting with GPT (both closed-source and open-source), I have been doing both of prompt engineering and fine-tuning. But I was pondering upon this question today, that when exactly is it best to use which technique, and I realized that the answer is not straightforward. At a broad level, ... | 2023-07-18T08:12:33 | https://www.reddit.com/r/LocalLLaMA/comments/152s9ei/when_is_it_best_to_use_prompt_engineering_vs/ | ResearcherNo4728 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 152s9ei | false | null | t3_152s9ei | /r/LocalLLaMA/comments/152s9ei/when_is_it_best_to_use_prompt_engineering_vs/ | false | false | 15 | {'enabled': False, 'images': [{'id': 'dKIxjlIcrhsEcNhzVW3pzdCRvlrIkuPNkUbhF2lsU9s', 'resolutions': [{'height': 72, 'url': 'https://external-preview.redd.it/Nj4beHHB8enchior4NbC3OstkLa2DqqRY8h469eVGsk.png?width=108&crop=smart&auto=webp&s=916cc50a651610becce503e182f60ce35b78e08d', 'width': 108}, {'height': 145, 'url': 'h... | |
Retentive Network: A Successor to Transformer for Large Language Models | 85 | 2023-07-18T08:02:08 | https://arxiv.org/abs/2307.08621 | alexanderchenmh | arxiv.org | 1970-01-01T00:00:00 | 0 | {} | 152s2ij | false | null | t3_152s2ij | /r/LocalLLaMA/comments/152s2ij/retentive_network_a_successor_to_transformer_for/ | false | false | 85 | {'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... | ||
When merging model and lora, use original tokenizer.model file? | 1 | [removed] | 2023-07-18T07:55:31 | https://www.reddit.com/r/LocalLLaMA/comments/152ry90/when_merging_model_and_lora_use_original/ | redzorino | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 152ry90 | false | null | t3_152ry90 | /r/LocalLLaMA/comments/152ry90/when_merging_model_and_lora_use_original/ | false | false | self | 1 | null |
Offtopic question: how to highlight and export Reddit comments? | 5 | At the moment I'm learning everything I can about LLMs and AI. This thread contains excellent knowledge that I'd like to extract into my Obsidian note taking app, but I fail terribly. There's virtually no read-it-later app that I can use to highlight and sync things into my Obsidian vault that can handle Reddit threads... | 2023-07-18T07:54:41 | https://www.reddit.com/r/LocalLLaMA/comments/152rxq6/offtopic_question_how_to_highlight_and_export/ | krazzmann | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 152rxq6 | false | null | t3_152rxq6 | /r/LocalLLaMA/comments/152rxq6/offtopic_question_how_to_highlight_and_export/ | false | false | self | 5 | null |
Need guidance in this sea of information on how to set up a local AI | 1 | Hey, I have no idea if this is even the right sub to ask for help in, but I have no idea where to start.
I was asking the Bing AI for leads on how to setup a local/offline AI chatbot on my PC, and eventually found [this article.](https://beebom.com/how-train-ai-chatbot-using-privategpt-offline/) I followed it but when... | 2023-07-18T07:18:01 | https://www.reddit.com/r/LocalLLaMA/comments/152rb1i/need_guidance_in_this_sea_of_information_on_how/ | grimsikk | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 152rb1i | false | null | t3_152rb1i | /r/LocalLLaMA/comments/152rb1i/need_guidance_in_this_sea_of_information_on_how/ | false | false | self | 1 | {'enabled': False, 'images': [{'id': 'acC-TxVRLiKIVU53X-JZzkSVtbVHB9x96haG57DDPRw', 'resolutions': [{'height': 72, 'url': 'https://external-preview.redd.it/SRmPayqp2-LIA5oph4waVbHWluRj3ZxOAWmfM31Q_0I.jpg?width=108&crop=smart&auto=webp&s=d9d8bdc0b6ad5e21bde662810260d958e4012ea1', 'width': 108}, {'height': 144, 'url': 'h... |
LLaMA 65B on cloud | 2 | Dear All,
I want to build a Private GPT using open source LLM on cloud.
Thinking of Azure/AWS cloud (other suggestions welcome) but company has both so will be easier to get an instance there.
We want to look at talk own data (not necessiarily confidential, expcet for PII) and build a chatbot to answer queries limit... | 2023-07-18T05:59:27 | https://www.reddit.com/r/LocalLLaMA/comments/152pway/llama_65b_on_cloud/ | kdas22 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 152pway | false | null | t3_152pway | /r/LocalLLaMA/comments/152pway/llama_65b_on_cloud/ | false | false | self | 2 | null |
Fine tuning on Apple Silicon | 23 | Has anyone tried fine tuning a model on Apple Silicon? I’m thinking of buying a Mac Studio with M2 chip but not sure if there is enough hardware support from machine learning frameworks for fine tuning like HuggingFace PEFT. | 2023-07-18T05:02:10 | https://www.reddit.com/r/LocalLLaMA/comments/152oudd/fine_tuning_on_apple_silicon/ | Acrobatic-Site2065 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 152oudd | false | null | t3_152oudd | /r/LocalLLaMA/comments/152oudd/fine_tuning_on_apple_silicon/ | false | false | self | 23 | null |
Looking to hire a CTO to work on local LLMs | 2 | I’m seeing a lot of demand in my space for secure and local LLMs. I have an MVP and revenue and looking for a CTO to come on board to assist with our project! Please DM if interested. | 2023-07-18T04:00:12 | https://www.reddit.com/r/LocalLLaMA/comments/152nlvz/looking_to_hire_a_cto_to_work_on_local_llms/ | SunnyPiscine | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 152nlvz | false | null | t3_152nlvz | /r/LocalLLaMA/comments/152nlvz/looking_to_hire_a_cto_to_work_on_local_llms/ | false | false | self | 2 | null |
Can Tachi lang be another option for consumer device to run LLM? | 0 | As title. [https://docs.taichi-lang.cn/api/](https://docs.taichi-lang.cn/api/) | 2023-07-18T03:17:46 | https://www.reddit.com/r/LocalLLaMA/comments/152mqyu/can_tachi_lang_be_another_option_for_consumer/ | saraiqx | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 152mqyu | false | null | t3_152mqyu | /r/LocalLLaMA/comments/152mqyu/can_tachi_lang_be_another_option_for_consumer/ | false | false | self | 0 | null |
GPT4all and koboldcpp/etc | 13 | Try as I might, nothing seems to generate roleplay for me as well as gpt4all. I can use the same llms, from wizard uncensored to airboros, its not even close.
I am rping mostly from an instruct pov. So I will tell it to generate characters or as it what the room looked like etc.
How are you all getting good results ... | 2023-07-18T02:37:36 | https://www.reddit.com/r/LocalLLaMA/comments/152lvpk/gpt4all_and_koboldcppetc/ | Jenniher | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 152lvpk | false | null | t3_152lvpk | /r/LocalLLaMA/comments/152lvpk/gpt4all_and_koboldcppetc/ | false | false | self | 13 | null |
What's the reasonable tks/s running 30B q5 with llama.cpp (13900K + 4090) ? | 13 | ./main -m models/Wizard-Vicuna-30B-Uncensored.ggmlv3.q5_1.bin -t 16 -n 128 --n-gpu-layers 63 -ins --color
main: build = 847 (7568d1a)
main: seed = 1689647281
ggml_init_cublas: found 1 CUDA devices:
Device 0: NVIDIA GeForce RTX 4090, compute capability 8.9
llama.cpp: loading model from models/... | 2023-07-18T02:36:05 | https://www.reddit.com/r/LocalLLaMA/comments/152lul7/whats_the_reasonable_tkss_running_30b_q5_with/ | dostorm | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 152lul7 | false | null | t3_152lul7 | /r/LocalLLaMA/comments/152lul7/whats_the_reasonable_tkss_running_30b_q5_with/ | false | false | self | 13 | null |
LLM Deployment Cost : Closed APIs like Open AI v/s fine tuned open source model on AWS | 11 | Did some number crunching on unraveling GPU compute costs.
Our research revealed that deploying a fine-tuned DialoGPT-large model on AWS is 55% less expensive, and a staggering 89% cheaper when serverless, compared to OpenAI's GPT-3.5 Turbo. Check it out here - bit.ly/46bGC9t .
Would love to hear thoughts? | 2023-07-18T02:05:06 | https://www.reddit.com/r/LocalLLaMA/comments/152l61r/llm_deployment_cost_closed_apis_like_open_ai_vs/ | Tiny_Cut_8440 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 152l61r | false | null | t3_152l61r | /r/LocalLLaMA/comments/152l61r/llm_deployment_cost_closed_apis_like_open_ai_vs/ | false | false | self | 11 | null |
Current, comprehensive guide to to installing llama.cpp and llama-cpp-python on Windows? | 22 | Hi, all,
Title, basically. Does anyone happen to have a link? I spent hours banging my head against outdated documentation, conflicting forum posts and Git issues, make, CMake, Python, Visual Studio, CUDA, and Windows itself today, just trying to get llama.cpp and llama-cpp-python to bloody compile with GPU accelerati... | 2023-07-18T01:40:48 | https://www.reddit.com/r/LocalLLaMA/comments/152kn39/current_comprehensive_guide_to_to_installing/ | smile_e_face | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 152kn39 | false | null | t3_152kn39 | /r/LocalLLaMA/comments/152kn39/current_comprehensive_guide_to_to_installing/ | false | false | self | 22 | null |
Some thoughts on alignment and creativity | 4 | I've been thinking about alignment of models today, or to call them what that literally means: fine tuning models to return responses that protect against human harm.
In particular what is spinning my mind lately is how does that get achieved internally when an LLM is a probabilistic model?
How much logic or decisio... | 2023-07-18T01:34:49 | https://www.reddit.com/r/LocalLLaMA/comments/152ki9c/some_thoughts_on_alignment_and_creativity/ | CrysisAverted | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 152ki9c | false | null | t3_152ki9c | /r/LocalLLaMA/comments/152ki9c/some_thoughts_on_alignment_and_creativity/ | false | false | self | 4 | null |
[Python] Experiment across local models and parameters with prompttools | 1 | 2023-07-18T01:05:28 | https://github.com/hegelai/prompttools/blob/main/examples/notebooks/LlamaCppExperiment.ipynb | hegel-ai | github.com | 1970-01-01T00:00:00 | 0 | {} | 152jvf4 | false | null | t3_152jvf4 | /r/LocalLLaMA/comments/152jvf4/python_experiment_across_local_models_and/ | false | false | 1 | {'enabled': False, 'images': [{'id': 'GiVVL37CiJa3xVZzNf2Lp0J7JBgY8wPV2_XD0FrNatM', 'resolutions': [{'height': 54, 'url': 'https://external-preview.redd.it/KJGH0qVNlbFuFIuP6uYSPBkxWI7lfkt1mktQ_BuFuwY.jpg?width=108&crop=smart&auto=webp&s=a806ebb2ac2ee03b9d8d926c95fed44107be3b69', 'width': 108}, {'height': 108, 'url': 'h... | ||
I've uploaded some 33B models with extended context up to 16384 (16K) tokens using bhenrym14 LoRA! (FP16 and GPTQ) | 116 | Hi there guys! I do this post, to give info about these merges of 33B models to use up to 16K context.
​
You can find models the models in my profile on HF, ending with "lxctx-PI-16384-LoRA" for FP16, and "lxctx-PI-16384-LoRA-4bit-32g" for GPTQ. My profile is \[here.\] ([https://huggingface.co/Panchovix](https... | 2023-07-17T23:37:18 | https://www.reddit.com/r/LocalLLaMA/comments/152hudn/ive_uploaded_some_33b_models_with_extended/ | panchovix | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 152hudn | false | null | t3_152hudn | /r/LocalLLaMA/comments/152hudn/ive_uploaded_some_33b_models_with_extended/ | false | false | 116 | {'enabled': False, 'images': [{'id': 'OmJ2YIgaV9Z4EA8790ooSFw3MeB_MqqU_mgScdu7Oi4', 'resolutions': [{'height': 58, 'url': 'https://external-preview.redd.it/wCC4k8kik-r1Oe_hkAmZt8ha_zvstLjkjCbhaN1xmxA.jpg?width=108&crop=smart&auto=webp&s=b9a9640fcab472b3e61358def747d9f36f05f24b', 'width': 108}, {'height': 116, 'url': 'h... | |
Falcon ggml/ggcc with langchain | 7 | To load falcon models with the new file format ggcc wich is a new file format similar to ggml, I'm using this tool:
https://github.com/cmp-nct/ggllm.cpp
Wich is a fork from :
https://github.com/ggerganov/llama.cpp
Thing is that it just gives me a binary that load a model and does inference right in the terminal.
To l... | 2023-07-17T23:22:41 | https://www.reddit.com/r/LocalLLaMA/comments/152hhr0/falcon_ggmlggcc_with_langchain/ | No_Afternoon_4260 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 152hhr0 | false | null | t3_152hhr0 | /r/LocalLLaMA/comments/152hhr0/falcon_ggmlggcc_with_langchain/ | false | false | self | 7 | {'enabled': False, 'images': [{'id': '0JEtiLK8NJ3zi7bo0MeYxbcPjTwbq_7FdrNa9wx1tSY', 'resolutions': [{'height': 108, 'url': 'https://external-preview.redd.it/dlpXFUlicImbwR2WGQY47tNMsJLiJSPDjc8agl6zkC0.jpg?width=108&crop=smart&auto=webp&s=e433fd2285545ffa8063029144581d1264da1bcb', 'width': 108}], 'source': {'height': 19... |
Running LLMs locally on Android | 1 | [removed] | 2023-07-17T21:12:23 | https://www.reddit.com/r/LocalLLaMA/comments/152e78s/running_llms_locally_on_android/ | atezan | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 152e78s | false | null | t3_152e78s | /r/LocalLLaMA/comments/152e78s/running_llms_locally_on_android/ | false | false | self | 1 | {'enabled': False, 'images': [{'id': 'D7uTH5s4LDVjda6kEL6oSgL5gomOBRMEcuuJOPfKvF4', 'resolutions': [{'height': 56, 'url': 'https://external-preview.redd.it/GkIpmzG_O5Tnr8KKPORXQ7LgZSCuDcFWzJfY1153Vo8.jpg?width=108&crop=smart&auto=webp&s=51be021f144a7b76cf0827775a02f301859b9000', 'width': 108}, {'height': 113, 'url': 'h... |
FlashAttention-2 released - 2x faster than FlashAttention v1 | 175 | 2023-07-17T19:40:50 | https://twitter.com/tri_dao/status/1680987580228308992 | GlobalRevolution | twitter.com | 1970-01-01T00:00:00 | 0 | {} | 152bqyz | false | {'oembed': {'author_name': 'Tri Dao', 'author_url': 'https://twitter.com/tri_dao', 'cache_age': 3153600000, 'height': None, 'html': '<blockquote class="twitter-video"><p lang="en" dir="ltr">The tech report has all the info: <a href="https://t.co/E5FZ3j1mDB">https://t.co/E5FZ3j1mDB</a><br><br>More details in blogposts:<... | t3_152bqyz | /r/LocalLLaMA/comments/152bqyz/flashattention2_released_2x_faster_than/ | false | false | 175 | {'enabled': False, 'images': [{'id': 'k7mjeWDDJ8wP05eNJRUDbk0F44stdg3CNDuMNhFXkXk', 'resolutions': [{'height': 108, 'url': 'https://external-preview.redd.it/WjwY3wLCBZji3XZZN-YJzjFQMEuVspb8_mmhUpUHvCE.jpg?width=108&crop=smart&auto=webp&s=b744c0734de36da702c0fbea2a048744d59c32bb', 'width': 108}], 'source': {'height': 14... | ||
llama.cpp and meta's llama repository summaries | 0 | 2023-07-17T18:59:50 | https://github.com/ggerganov/llama.cpp | o2sh | reddit.com | 1970-01-01T00:00:00 | 0 | {} | 152ant2 | false | null | t3_152ant2 | /r/LocalLLaMA/comments/152ant2/llamacpp_and_metas_llama_repository_summaries/ | false | false | 0 | null | ||
llama.cpp vs llama | 0 | 2023-07-17T18:40:11 | https://github.com/ggerganov/llama.cpp | o2sh | reddit.com | 1970-01-01T00:00:00 | 0 | {} | 152a55u | false | null | t3_152a55u | /r/LocalLLaMA/comments/152a55u/llamacpp_vs_llama/ | false | false | 0 | null | ||
Best model for text adventure games | 14 | Mainly title, currently I'm using airoboros 65B and its good.
Just checking if novel writer models would be better suited for that purpose or if there are any specific ones I should try | 2023-07-17T18:20:50 | https://www.reddit.com/r/LocalLLaMA/comments/1529n3f/best_model_for_text_adventure_games/ | yehiaserag | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 1529n3f | false | null | t3_1529n3f | /r/LocalLLaMA/comments/1529n3f/best_model_for_text_adventure_games/ | false | false | self | 14 | null |
Open-Source Text Generation & LLM Ecosystem (new HF blog post) | 20 | 2023-07-17T18:06:24 | https://huggingface.co/blog/os-llms | kryptkpr | huggingface.co | 1970-01-01T00:00:00 | 0 | {} | 15299w7 | false | null | t3_15299w7 | /r/LocalLLaMA/comments/15299w7/opensource_text_generation_llm_ecosystem_new_hf/ | false | false | 20 | {'enabled': False, 'images': [{'id': 'ztoE2hO11waZKIVzDDyboQdgYQ2heusbYiriIqWFfpo', 'resolutions': [{'height': 53, 'url': 'https://external-preview.redd.it/GoTuRfiGaGVdEInGNG-WcNbRRvwVRPZtg7zk2kXf3YU.jpg?width=108&crop=smart&auto=webp&s=f2d90356cefe990c7c5a6a3932f99505a61dd523', 'width': 108}, {'height': 107, 'url': 'h... | ||
Semantic Vector Search w/out Vector Database? | 1 | For my use case, I only need to process a document once, then delete it. I am currently doing this:
Document -> Open AI Embeddings -> Pinecone Upsert -> Pinecone Query -> Process Answer -> Delete pinecone data.
Since I don't actually need to save the vectors, I am wondering if there is a way to perform semantic se... | 2023-07-17T17:30:24 | https://www.reddit.com/r/LocalLLaMA/comments/1528brv/semantic_vector_search_wout_vector_database/ | gthing | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 1528brv | false | null | t3_1528brv | /r/LocalLLaMA/comments/1528brv/semantic_vector_search_wout_vector_database/ | false | false | self | 1 | null |
Fabrice Bellard's LLM Benchmark | 34 | Fabrice Bellard, whose claim to fame is being the front-runner in the long text compression leaderboard ([http://www.mattmahoney.net/dc/text.html](http://www.mattmahoney.net/dc/text.html)), wrote an inference server, and has a benchmark of many LLMs as part of his website for that.
It's yet another adaptation of the E... | 2023-07-17T17:13:46 | https://www.reddit.com/r/LocalLLaMA/comments/1527vxx/fabrice_bellards_llm_benchmark/ | georgejrjrjr | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 1527vxx | false | null | t3_1527vxx | /r/LocalLLaMA/comments/1527vxx/fabrice_bellards_llm_benchmark/ | false | false | self | 34 | null |
Personal Riddle/Reasoning Airoboros Test Results | 6 | Full credit to [u/YearZero](https://www.reddit.com/user/YearZero/)'s logic test from the [thread](https://www.reddit.com/r/LocalLLaMA/comments/13k8h0r/riddlereasoning_ggml_model_tests_update_koboldcpp/) I stumbled upon while dipping my toes into the world of Locally run LLMs. I started sometime last week after discover... | 2023-07-17T16:47:26 | https://www.reddit.com/r/LocalLLaMA/comments/15276yq/personal_riddlereasoning_airoboros_test_results/ | Brainfeed9000 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 15276yq | false | null | t3_15276yq | /r/LocalLLaMA/comments/15276yq/personal_riddlereasoning_airoboros_test_results/ | false | false | 6 | {'enabled': False, 'images': [{'id': 'MCvJSFkyOOtSMyxl8kts4DmJcAB22F9nJHAWxMk8iYE', 'resolutions': [{'height': 56, 'url': 'https://external-preview.redd.it/Fj2NBxqjBB60DuDl6KXgYY73xwF3S53YAmqSVKLONr8.jpg?width=108&crop=smart&auto=webp&s=23cf125a327f2d8bd5c239300e935deb11afa8e2', 'width': 108}, {'height': 113, 'url': 'h... | |
Best option to turn rough notes into a full report/letter in a set format? | 1 | [removed] | 2023-07-17T16:36:45 | https://www.reddit.com/r/LocalLLaMA/comments/1526x4c/best_option_to_turn_rough_notes_into_a_full/ | Solid-Ambition6018 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 1526x4c | false | null | t3_1526x4c | /r/LocalLLaMA/comments/1526x4c/best_option_to_turn_rough_notes_into_a_full/ | false | false | self | 1 | null |
Claude downgraded ? | 0 | Last week using Claude, it read diagrams I made in a pdf file and commented on them. Corrected itself using documentation from a web URL, and referenced the URL as a data source in subsequent conversations.
Today it failed at a simple task to explain something. I asked it to use a URL like it did last week.
It ... | 2023-07-17T15:47:59 | https://www.reddit.com/r/LocalLLaMA/comments/1525ma7/claude_downgraded/ | Poise_and_Grace | self.LocalLLaMA | 2023-07-17T15:55:25 | 0 | {} | 1525ma7 | false | null | t3_1525ma7 | /r/LocalLLaMA/comments/1525ma7/claude_downgraded/ | false | false | default | 0 | null |
3060, 3090 desktops or 3080 laptop? | 0 | I can buy a 3060 desktop for $400, or a 3080 laptop for $800, or a 3090 desktop for $1200.
The issue with the 3090 option is that, the electricity at my home is expensive, sometimes training locally is more expensive than if I just rent the 3090/A100's online.
I might want to prototype something, then move the traini... | 2023-07-17T14:54:54 | https://www.reddit.com/r/LocalLLaMA/comments/15247hg/3060_3090_desktops_or_3080_laptop/ | bjiwkls23 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 15247hg | false | null | t3_15247hg | /r/LocalLLaMA/comments/15247hg/3060_3090_desktops_or_3080_laptop/ | false | false | self | 0 | null |
Orca Mini V2 vs Open Orca - Which One Is Better? | 1 | [removed] | 2023-07-17T14:24:17 | https://www.reddit.com/r/LocalLLaMA/comments/1523ew2/orca_mini_v2_vs_open_orca_which_one_is_better/ | mattybee | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 1523ew2 | false | null | t3_1523ew2 | /r/LocalLLaMA/comments/1523ew2/orca_mini_v2_vs_open_orca_which_one_is_better/ | false | false | self | 1 | {'enabled': False, 'images': [{'id': 'vE92SzNE77FHa1b8PBv34LYve0DAE9FQEqJ42NUz61Y', 'resolutions': [{'height': 81, 'url': 'https://external-preview.redd.it/rS8OGPCNynZNSSDDVofm17KYQk9rfwCyTlszBJdQ_x4.jpg?width=108&crop=smart&auto=webp&s=be3cc58f3bd3214cdbf0cb5739a175f00ebcdc74', 'width': 108}, {'height': 162, 'url': 'h... |
Hardware requirements to build a personalized assistant using LLaMa | 25 | My group was thinking of creating a personalized assistant using an open-source LLM model (as GPT will be expensive).
The features will be something like: QnA from local documents, interact with internet apps using zapier, set deadlines and reminders, etc.
I searched online and found out that I will be needing a capa... | 2023-07-17T13:31:13 | https://www.reddit.com/r/LocalLLaMA/comments/15222fi/hardware_requirements_to_build_a_personalized/ | Ibrahim2714 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 15222fi | false | null | t3_15222fi | /r/LocalLLaMA/comments/15222fi/hardware_requirements_to_build_a_personalized/ | false | false | self | 25 | null |
Hardware requirements to build a personalized assistant using LLaMa | 1 | My group was thinking of creating a personalized assistant using an open-source LLM model (as GPT will be expensive).
The features will be something like: QnA from local documents, interact with internet apps using zapier, set deadlines and reminders, etc.
I searched online and found out that I will be needing a capa... | 2023-07-17T13:31:11 | https://www.reddit.com/r/LocalLLaMA/comments/15222en/hardware_requirements_to_build_a_personalized/ | Ibrahim2714 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 15222en | false | null | t3_15222en | /r/LocalLLaMA/comments/15222en/hardware_requirements_to_build_a_personalized/ | false | false | self | 1 | null |
open LLm | 1 | [removed] | 2023-07-17T13:22:32 | https://www.reddit.com/r/LocalLLaMA/comments/1521uqw/open_llm/ | KKSpro | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 1521uqw | false | null | t3_1521uqw | /r/LocalLLaMA/comments/1521uqw/open_llm/ | false | false | self | 1 | null |
Finetuning qLoRAs for production use cases | 68 | Hello,
I've been curious as to how far we can take small(7B and less) models for production use cases with small amounts of training data for each task.
So far I've been able to fine-tune LoRAs for paraphrasing, changing the tone of a sentence, dialogue summarization and topic generation. The results look promising, ... | 2023-07-17T13:06:00 | https://www.reddit.com/r/LocalLLaMA/comments/1521gni/finetuning_qloras_for_production_use_cases/ | krumb0y | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 1521gni | false | null | t3_1521gni | /r/LocalLLaMA/comments/1521gni/finetuning_qloras_for_production_use_cases/ | false | false | self | 68 | {'enabled': False, 'images': [{'id': 'oglLX9PkWSrDLE76yJxhrPXVEyRZETSBm_uigmhrZ1Y', 'resolutions': [{'height': 54, 'url': 'https://external-preview.redd.it/FyCWVuxqWixscrQTT1nUYq-3aw1chFkTp3BPWR4EfDI.jpg?width=108&crop=smart&auto=webp&s=f01028422b87716d1f4b72515829bbf580a6fdba', 'width': 108}, {'height': 108, 'url': 'h... |
After loading the LLM model, how to set the current (today's) date in files and folders ? | 1 | [removed] | 2023-07-17T11:51:59 | https://www.reddit.com/r/LocalLLaMA/comments/151zrq0/after_loading_the_llm_model_how_to_set_the/ | TurbulentDelivery799 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 151zrq0 | false | null | t3_151zrq0 | /r/LocalLLaMA/comments/151zrq0/after_loading_the_llm_model_how_to_set_the/ | false | false | default | 1 | {'enabled': False, 'images': [{'id': 'G1nl_IUI_4T90MWS7hPfvajkGrGVtVlBe7-hikDbCJE', 'resolutions': [{'height': 58, 'url': 'https://external-preview.redd.it/nUYJCJ4Wd48yWucK-iCTSDQmUfqKekJFWJI-qowoq9M.jpg?width=108&crop=smart&auto=webp&s=3723e81c3dda45706b3275533d688762ed693e74', 'width': 108}, {'height': 116, 'url': 'h... |
testing llama on raspberry pi for various zombie apocalypse style situations. | 192 | 2023-07-17T10:11:46 | Purple_Session_6230 | i.redd.it | 1970-01-01T00:00:00 | 0 | {'gid_3': 1} | 151xsio | false | null | t3_151xsio | /r/LocalLLaMA/comments/151xsio/testing_llama_on_raspberry_pi_for_various_zombie/ | false | false | 192 | {'enabled': True, 'images': [{'id': '54N-ft1IPTZHsVEE8CRLtsvDcFeLZ-we8Q_vgKkZfKQ', 'resolutions': [{'height': 172, 'url': 'https://preview.redd.it/gryad6oo2icb1.png?width=108&crop=smart&auto=webp&s=c4cd7580dcc8a01b138b043003db43e156b37bb7', 'width': 108}, {'height': 345, 'url': 'https://preview.redd.it/gryad6oo2icb1.pn... | |||
OpenOrca is around the corner! | 0 | Yesterday a [preview](https://huggingface.co/openchat/openchat_v2_openorca_preview) of the model was published on HF (trained on 10% of data).
It's already breaking records in some benchmarks but still lacks significantly in Massive Multitask Language Understanding (MMLU). Let's see how the fully trained model perfor... | 2023-07-17T10:05:09 | https://www.reddit.com/r/LocalLLaMA/comments/151xo2r/openorca_is_around_the_corner/ | Kujamara | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 151xo2r | false | null | t3_151xo2r | /r/LocalLLaMA/comments/151xo2r/openorca_is_around_the_corner/ | false | false | self | 0 | {'enabled': False, 'images': [{'id': 'raNRLaNtmM7-4ECR7dmO-Se0SStGCP71rDMl2S85or8', 'resolutions': [{'height': 58, 'url': 'https://external-preview.redd.it/B6L7VEvp71cr1qeeqFxahafzpHmFF2OEu-3kQWv3BYc.jpg?width=108&crop=smart&auto=webp&s=50c342a8628109b005c723c671ea661d50f258b2', 'width': 108}, {'height': 116, 'url': 'h... |
Grab some popcorn, OpenOrca is around the corner! | 1 | Yesterday a preview of OpenOrca was published on HF (OpenChat V2 x OpenOrca dataset). OpenChat V2 is a leading open-source model and last night it was fine-tuned on Open-Orca's data.
Here is a [preview](https://huggingface.co/openchat/openchat_v2_openorca_preview) of the model (trained on 10% of data) and it's already... | 2023-07-17T09:54:34 | Kujamara | i.redd.it | 1970-01-01T00:00:00 | 0 | {} | 151xgor | false | null | t3_151xgor | /r/LocalLLaMA/comments/151xgor/grab_some_popcorn_openorca_is_around_the_corner/ | false | false | 1 | {'enabled': True, 'images': [{'id': 'F9v9S4z0DWnt8BcB1ub5JwsvRLq9D1MAYFpeED-c2RE', 'resolutions': [{'height': 31, 'url': 'https://preview.redd.it/am165eamzhcb1.png?width=108&crop=smart&auto=webp&s=a1ed5e89afdf46da0ab868f30c9450681fddb17f', 'width': 108}, {'height': 63, 'url': 'https://preview.redd.it/am165eamzhcb1.png?... | ||
How to contribute to datasets | 4 | Hi,
I have a ChatGPT premium subscription. I'd like to know how I can contribute with good quality chats to existing datasets. And to which dataset I should contribute.
Any suggestions?
Cheers! | 2023-07-17T09:23:07 | https://www.reddit.com/r/LocalLLaMA/comments/151wwit/how_to_contribute_to_datasets/ | drr21 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 151wwit | false | null | t3_151wwit | /r/LocalLLaMA/comments/151wwit/how_to_contribute_to_datasets/ | false | false | self | 4 | null |
Is it not allowed to talk about LoRAs here? | 1 | [removed] | 2023-07-17T09:20:59 | https://www.reddit.com/r/LocalLLaMA/comments/151wv4s/is_it_not_allowed_to_talk_about_loras_here/ | redzorino | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 151wv4s | false | null | t3_151wv4s | /r/LocalLLaMA/comments/151wv4s/is_it_not_allowed_to_talk_about_loras_here/ | false | false | default | 1 | null |
lmsys/vicuna-13b-v1.3 is relatively slow to lmsys/vicuna-13b-v1.1? Or am I tripping? | 1 | Hi people, when doing inference with lmsys/vicuna-13b-v1.3, the inference execution time for the below question takes about 1+ min while lmsys/vicuna-13b-v1.1 takes 11seconds? lmsys/vicuna-13b-v1.3 seems to be much slower the longer the question gets. Anyone can confirm if its a me or them problem? Thanks!
The long qu... | 2023-07-17T08:40:16 | https://www.reddit.com/r/LocalLLaMA/comments/151w5ro/lmsysvicuna13bv13_is_relatively_slow_to/ | ToeAdministrative493 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 151w5ro | false | null | t3_151w5ro | /r/LocalLLaMA/comments/151w5ro/lmsysvicuna13bv13_is_relatively_slow_to/ | false | false | self | 1 | null |
My self-trained LoRA doesn't affect the model at all it seems :( | 1 | Engine: latest llama.cpp
Model: airoboros-7b (16bit)
For training: oobabooga, and a ~ 1MB text file
llama.cpp says it can only apply LoRAs to 16bit models, so I wasn't allowed to quantize the model to 8b, fortunately I have enough VRAM.
I trained 10 epochs (oobabooga suggested 3 as default setting), which took severa... | 2023-07-17T07:37:23 | https://www.reddit.com/r/LocalLLaMA/comments/151v2mb/my_selftrained_lora_doesnt_affect_the_model_at/ | redzorino | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 151v2mb | false | null | t3_151v2mb | /r/LocalLLaMA/comments/151v2mb/my_selftrained_lora_doesnt_affect_the_model_at/ | false | false | self | 1 | null |
Will a commercial LLaMA mean less publicly released models? | 21 | With the news that a new and commercial version of LLaMA will be released soon, there'll be a mad race to capitalize on this if the next model will be as good as ChatGPT like [Yann LeCun claims](https://www.engadget.com/meta-could-soon-make-its-ai-model-available-for-commercial-projects-114021749.html). A dozen website... | 2023-07-17T07:37:09 | https://www.reddit.com/r/LocalLLaMA/comments/151v2gr/will_a_commercial_llama_mean_less_publicly/ | WorldlyJob3111 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 151v2gr | false | null | t3_151v2gr | /r/LocalLLaMA/comments/151v2gr/will_a_commercial_llama_mean_less_publicly/ | false | false | self | 21 | {'enabled': False, 'images': [{'id': 'CshXXrv8exPcHnz-sGxZ23q4wQtcF0A6lFPz2CJbz98', 'resolutions': [{'height': 56, 'url': 'https://external-preview.redd.it/odCzyg6WvK3Uf8MCzIXFOYi3ErgN2vOs2mnkP1Crfmc.jpg?width=108&crop=smart&auto=webp&s=e65739e39cf7a49faab68d560a5bf54161fa9579', 'width': 108}, {'height': 113, 'url': 'h... |
I put together a video for anyone interested in running their own LLM’s on the cloud with oobabooga | 1 | [removed] | 2023-07-17T07:15:13 | https://www.reddit.com/r/LocalLLaMA/comments/151uoo6/i_put_together_a_video_for_anyone_interested_in/ | sbalani | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 151uoo6 | false | null | t3_151uoo6 | /r/LocalLLaMA/comments/151uoo6/i_put_together_a_video_for_anyone_interested_in/ | false | false | self | 1 | {'enabled': False, 'images': [{'id': 'BkEiQtm_ZShCHQrow8sLNC_Rva0eImmbf1g6Apv881A', 'resolutions': [{'height': 81, 'url': 'https://external-preview.redd.it/eJb3gIPxXIE_e8vANBOZ9_aKDrTWetn-xBof4Q_SeF4.jpg?width=108&crop=smart&auto=webp&s=29cb9bada4b41cc16b8f0206f7fd9844a531baf9', 'width': 108}, {'height': 162, 'url': 'h... |
Subsets and Splits
No community queries yet
The top public SQL queries from the community will appear here once available.