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 ⌀ |
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
I am going to buy H100s. There are too many options. | 69 | Hi all,
I need a help from all of you.
I am going to buy H100s for training LLMs. Currently for fine-tuning 70b models but later we may consider pre-training larger models too.
H100s looks more promising than A100s considering its power of FP8 support, so I asked quotes from multiple vendors. And then, realized there a... | 2023-10-31T12:44:34 | https://www.reddit.com/r/LocalLLaMA/comments/17kk63y/i_am_going_to_buy_h100s_there_are_too_many_options/ | OldPin8654 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 17kk63y | false | null | t3_17kk63y | /r/LocalLLaMA/comments/17kk63y/i_am_going_to_buy_h100s_there_are_too_many_options/ | false | false | self | 69 | null |
Any existing Open Source Mobile App for local inference server? | 2 | Hi, I would like to know if there are any existing open source mobile app project that is like ChatGPT mobile app which can set custom inference server link?
If not, I think I will contribute to make one. | 2023-10-31T12:19:16 | https://www.reddit.com/r/LocalLLaMA/comments/17kjox2/any_existing_open_source_mobile_app_for_local/ | Similar_Tea_8349 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 17kjox2 | false | null | t3_17kjox2 | /r/LocalLLaMA/comments/17kjox2/any_existing_open_source_mobile_app_for_local/ | false | false | self | 2 | null |
Resources for creating datasets for code generation? | 5 | I tried some code generation models on huggingface but they were really poor in the responses I got even though I clearly explained what I need in the prompt. My assumption is that it was because my question is related to a niche framework and the model was trained on a large dataset on a wide variety of languages and ... | 2023-10-31T12:02:21 | https://www.reddit.com/r/LocalLLaMA/comments/17kje41/resources_for_creating_datasets_for_code/ | rhinohoof | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 17kje41 | false | null | t3_17kje41 | /r/LocalLLaMA/comments/17kje41/resources_for_creating_datasets_for_code/ | false | false | self | 5 | null |
Apple M3 Pro Chip Has 25% Less Memory Bandwidth Than M1/M2 Pro | 66 | 2023-10-31T11:59:15 | https://www.macrumors.com/2023/10/31/apple-m3-pro-less-memory-bandwidth/ | __tosh | macrumors.com | 1970-01-01T00:00:00 | 0 | {} | 17kjbqd | false | null | t3_17kjbqd | /r/LocalLLaMA/comments/17kjbqd/apple_m3_pro_chip_has_25_less_memory_bandwidth/ | false | false | 66 | {'enabled': False, 'images': [{'id': '8MjIrVzuil4d2x5KZ-vIAVg4E3sNyreJSB7e5gBKOcc', 'resolutions': [{'height': 60, 'url': 'https://external-preview.redd.it/S_U11F5e2WlnGhBkExp4gkAdZcuX2VgXy15tIWhQX_g.jpg?width=108&crop=smart&auto=webp&s=95d7d8c8fb90e03129f95db5ff2049f2e6aef181', 'width': 108}, {'height': 121, 'url': 'h... | ||
Skywork-13B: a new foundation model trained on 3.2 trillion tokens | 93 | There's two noteworthy things covered here:
1. Skywork-13B, a new bilingual foundation model for English and Chinese. They also announce Skywork-13B-Chat enhanced specially for creative writing, Skywork-13B-Math for math, Skywork-13B-MM for multimodal capability, and a segment of their SkyPile Corpus comprising 150 bi... | 2023-10-31T11:12:18 | https://www.reddit.com/r/LocalLLaMA/comments/17kijtw/skywork13b_a_new_foundation_model_trained_on_32/ | llamaShill | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 17kijtw | false | null | t3_17kijtw | /r/LocalLLaMA/comments/17kijtw/skywork13b_a_new_foundation_model_trained_on_32/ | false | false | 93 | {'enabled': False, 'images': [{'id': 'T8S6PEdZCYI2sMNFL5hVd24wMonLakHYMfO8xmmc7xU', 'resolutions': [{'height': 54, 'url': 'https://external-preview.redd.it/AH3I8wMuOLrn4h3W7bsYdyqoi2ISJcB67-2lXM_YfdM.jpg?width=108&crop=smart&auto=webp&s=4154c354e467cd9458e57bb00dc5f71173dcad46', 'width': 108}, {'height': 108, 'url': 'h... | |
Any .gguf web-interface that has video multimodal support? | 2 | Is there any .gguf web-interface available that has video multimodal support?
Like m-plug owl, Video-LLaMA, Video-ChatGPT or MovieChat - but for gguf use? Those that I've found does not use .gguf files for CPU usage...
I know LLaVa is out there, but it does not have video support. | 2023-10-31T10:43:15 | https://www.reddit.com/r/LocalLLaMA/comments/17ki3fw/any_gguf_webinterface_that_has_video_multimodal/ | fetballe | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 17ki3fw | false | null | t3_17ki3fw | /r/LocalLLaMA/comments/17ki3fw/any_gguf_webinterface_that_has_video_multimodal/ | false | false | self | 2 | null |
Freezing during inference | 1 | Sorry to post hardware problems but I think this is the community most likely to have dealt with similar issues.
Basically I get hardware freezing during inference.
- EVGA X299 FTW-K
- Intel(R) Core(TM) i9-9900X CPU @ 3.50GHz
- 128GB DDR4 RAM
- 1x nvidia RTX 3090
- 1x nvidia RTX 4090
- Corsair HX1500i Power Supply
- ... | 2023-10-31T08:50:40 | https://www.reddit.com/r/LocalLLaMA/comments/17kgidy/freezing_during_inference/ | _supert_ | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 17kgidy | false | null | t3_17kgidy | /r/LocalLLaMA/comments/17kgidy/freezing_during_inference/ | false | false | self | 1 | null |
text-generation-webui qweight & qzeros error loading model | 1 | Hey,
New user to text-generation-webui. Got it up and running, and can successfully infer, using GPU, from the main branch of the Zephyr 7B model:
[https://huggingface.co/TheBloke/zephyr-7B-alpha-GPTQ](https://huggingface.co/TheBloke/zephyr-7B-alpha-GPTQ)
​
However, when I try to load alternative models, e.g... | 2023-10-31T08:37:08 | https://www.reddit.com/r/LocalLLaMA/comments/17kgcb3/textgenerationwebui_qweight_qzeros_error_loading/ | LostGoatOnHill | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 17kgcb3 | false | null | t3_17kgcb3 | /r/LocalLLaMA/comments/17kgcb3/textgenerationwebui_qweight_qzeros_error_loading/ | false | false | self | 1 | {'enabled': False, 'images': [{'id': 'ECYL__bruZ8Ggwy90cpnRGEi8iaweg99bP9QlXeXccM', 'resolutions': [{'height': 58, 'url': 'https://external-preview.redd.it/Q4c9pKg1YetnlXqbNX8EcWGEo_hh63gJ-ZrSX_kG-Yo.jpg?width=108&crop=smart&auto=webp&s=8a2c6153f3e071b63a9a90a06b24b491ea39a2e3', 'width': 108}, {'height': 116, 'url': 'h... |
M3 Max | 3 | Seems like M3 Max is best suited for Large Language Model training. With 128 gb unified memory essential let us train models on billions of parameters! Pretty interesting. | 2023-10-31T08:20:59 | https://www.reddit.com/r/LocalLLaMA/comments/17kg5ak/m3_max/ | akashocx17 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 17kg5ak | false | null | t3_17kg5ak | /r/LocalLLaMA/comments/17kg5ak/m3_max/ | false | false | self | 3 | null |
PC Build Suggestion For RTX 4090 + RTX 3090 | 1 | [removed] | 2023-10-31T08:06:12 | https://www.reddit.com/r/LocalLLaMA/comments/17kfyno/pc_build_suggestion_for_rtx_4090_rtx_3090/ | Aggressive_Bee_9069 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 17kfyno | false | null | t3_17kfyno | /r/LocalLLaMA/comments/17kfyno/pc_build_suggestion_for_rtx_4090_rtx_3090/ | false | false | self | 1 | null |
What are interesting open source resources/ projects for building LLMs for India/ Indic languages? | 7 | My focus is finding Datasets and embeddings first, I did my research specifically on Sanskrit and here are a few interesting links to start with -
* iNLTK: Natural Language Toolkit for Indic Languages : [https://arxiv.org/abs/2009.12534](https://arxiv.org/abs/2009.12534)
* Sanskrit ShlokasDataset - [https://www.kaggl... | 2023-10-31T07:49:17 | https://www.reddit.com/r/LocalLLaMA/comments/17kfqdv/what_are_interesting_open_source_resources/ | ashutrv | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 17kfqdv | false | null | t3_17kfqdv | /r/LocalLLaMA/comments/17kfqdv/what_are_interesting_open_source_resources/ | false | false | self | 7 | {'enabled': False, 'images': [{'id': 'q3evP6JeDpAC2MdSQHWYxnCYTqbJkElIQsLFqVSdkss', 'resolutions': [{'height': 63, 'url': 'https://external-preview.redd.it/izh8gZHY4FqZ1nwtU1N_TjtohUCNuvTyMn90toXda80.jpg?width=108&crop=smart&auto=webp&s=bc9575b410002edc2df3c5b5b0355fefedc7baa8', 'width': 108}, {'height': 126, 'url': 'h... |
Skywork: a new bilingual foundation model, and some research on test data contamination | 1 | There's two interesting things covered in this paper:
1. Skywork-13B, a new foundation model for English and Chinese. They also announce Skywork-13B-Chat enhanced specially for creative writing, Skywork-13B-Math specialized for math, Skywork-13B-MM for multimodal capability, and a segment of their SkyPile Corpus compr... | 2023-10-31T07:36:08 | https://www.reddit.com/r/LocalLLaMA/comments/17kfkgx/skywork_a_new_bilingual_foundation_model_and_some/ | llamaShill | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 17kfkgx | false | null | t3_17kfkgx | /r/LocalLLaMA/comments/17kfkgx/skywork_a_new_bilingual_foundation_model_and_some/ | false | false | 1 | {'enabled': False, 'images': [{'id': 'T8S6PEdZCYI2sMNFL5hVd24wMonLakHYMfO8xmmc7xU', 'resolutions': [{'height': 54, 'url': 'https://external-preview.redd.it/AH3I8wMuOLrn4h3W7bsYdyqoi2ISJcB67-2lXM_YfdM.jpg?width=108&crop=smart&auto=webp&s=4154c354e467cd9458e57bb00dc5f71173dcad46', 'width': 108}, {'height': 108, 'url': 'h... | |
chatgpt-3.5-turbo is a 20B model, according to this Microsoft paper | 1 | 2023-10-31T07:24:59 | https://arxiv.org/pdf/2310.17680.pdf | nondescriptshadow | arxiv.org | 1970-01-01T00:00:00 | 0 | {} | 17kffdl | false | null | t3_17kffdl | /r/LocalLLaMA/comments/17kffdl/chatgpt35turbo_is_a_20b_model_according_to_this/ | false | false | default | 1 | null | |
Does anyone know what tool is used to draw this style of image? | 1 | 2023-10-31T05:42:20 | FixPhysical284 | i.redd.it | 1970-01-01T00:00:00 | 0 | {} | 17ke17l | false | null | t3_17ke17l | /r/LocalLLaMA/comments/17ke17l/does_anyone_know_what_tool_is_used_to_draw_this/ | false | false | 1 | {'enabled': True, 'images': [{'id': '-C5UhCquaA3U9RtzTrf6jUwweAtb_lUtlVWwU1V2urg', 'resolutions': [{'height': 70, 'url': 'https://preview.redd.it/kwzh46957hxb1.jpg?width=108&crop=smart&auto=webp&s=0218409313fd541fc273f738549832fb85b3af18', 'width': 108}, {'height': 140, 'url': 'https://preview.redd.it/kwzh46957hxb1.jpg... | |||
LoRAShear: Efficient Large Language Model Structured Pruning and Knowledge Recovery | 21 | >Large Language Models (LLMs) have transformed the landscape of artificial intelligence, while their enormous size presents significant challenges in terms of computational costs. We introduce LoRAShear, a novel efficient approach to structurally prune LLMs and recover knowledge. Given general LLMs, LoRAShear first cre... | 2023-10-31T05:34:51 | https://arxiv.org/abs/2310.18356 | ninjasaid13 | arxiv.org | 1970-01-01T00:00:00 | 0 | {} | 17kdxid | false | null | t3_17kdxid | /r/LocalLLaMA/comments/17kdxid/lorashear_efficient_large_language_model/ | false | false | default | 21 | null |
M3 on LLama | 1 | Apple unveiled their M3 chips. How well do you think their chips will run LLama models? | 2023-10-31T04:59:05 | Reddimus | i.redd.it | 1970-01-01T00:00:00 | 0 | {} | 17kde7p | false | null | t3_17kde7p | /r/LocalLLaMA/comments/17kde7p/m3_on_llama/ | false | false | 1 | {'enabled': True, 'images': [{'id': 'NaGzY094-_WhMaAjZ7srIETOhLOc1cLk1Xr7WbbaDF0', 'resolutions': [{'height': 68, 'url': 'https://preview.redd.it/my4wt3uizgxb1.jpg?width=108&crop=smart&auto=webp&s=b3314f9a52fa6b93bd1bdab1a1dbb8a9a734049f', 'width': 108}, {'height': 137, 'url': 'https://preview.redd.it/my4wt3uizgxb1.jpg... | ||
Dolphin or Mistral function calling | 21 | So Im looking for references on how to do function calling using Dolphin or Mistral models.
With my current prompt, I'm able to get it to choose an appropriate command for the task sometimes. But often it'll add multiple commands in one response. But the other half of the time it produces correct commands & parameters... | 2023-10-31T04:54:52 | https://www.reddit.com/r/LocalLLaMA/comments/17kdby3/dolphin_or_mistral_function_calling/ | 1EvilSexyGenius | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 17kdby3 | false | null | t3_17kdby3 | /r/LocalLLaMA/comments/17kdby3/dolphin_or_mistral_function_calling/ | false | false | self | 21 | null |
How does Apple’s new M3 128GB ram MacBook Pro compare with Nvidia A100? | 83 | In terms of AI use, especially LLMs.
$5000 USD for the 128GB ram M3 MacBook Pro is still much cheaper than A100 80 GB. | 2023-10-31T04:00:43 | https://www.reddit.com/r/LocalLLaMA/comments/17kcgjv/how_does_apples_new_m3_128gb_ram_macbook_pro/ | tgredditfc | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 17kcgjv | false | null | t3_17kcgjv | /r/LocalLLaMA/comments/17kcgjv/how_does_apples_new_m3_128gb_ram_macbook_pro/ | false | false | self | 83 | null |
What’s the go to capture + fine tuning toolkit. | 3 | I’m tired of rolling my own infra to capture chat input and outputs, label it, and feed it to a training pipeline.
Is there a go to service / open source framework out there that will do all of this easier? | 2023-10-31T03:25:09 | https://www.reddit.com/r/LocalLLaMA/comments/17kbtye/whats_the_go_to_capture_fine_tuning_toolkit/ | jsfour | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 17kbtye | false | null | t3_17kbtye | /r/LocalLLaMA/comments/17kbtye/whats_the_go_to_capture_fine_tuning_toolkit/ | false | false | self | 3 | null |
What kind of performance should we expect? | 3 | I'm only getting 0.8 tokens/second with my 3060 12gb using Zephyr 7b beta.
I'll admit I barely know what I'm doing, but was I wrong to expect a little more? I was hoping for something at least a quarter the speed of gpt-3.5... | 2023-10-31T03:17:19 | https://www.reddit.com/r/LocalLLaMA/comments/17kbola/what_kind_of_performance_should_we_expect/ | cosmicr | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 17kbola | false | null | t3_17kbola | /r/LocalLLaMA/comments/17kbola/what_kind_of_performance_should_we_expect/ | false | false | self | 3 | null |
Streaming 7b models with llama cpp in python, possible? | 1 | Does anyone have experience streaming completions rather than waiting for the whole completion? If possible, are there any guides available on how to achieve this? | 2023-10-31T02:40:15 | https://www.reddit.com/r/LocalLLaMA/comments/17kay5r/streaming_7b_models_with_llama_cpp_in_python/ | Massive-Spot302 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 17kay5r | false | null | t3_17kay5r | /r/LocalLLaMA/comments/17kay5r/streaming_7b_models_with_llama_cpp_in_python/ | false | false | self | 1 | null |
What are some ways commonly used in the industry to DEVELOP & most importantly; VALIDATE prompts for GPT? | 1 | I've got a project at work and I'm building something on the side which both are now requiring heavy use of GPT 3.5 and GPT 4 apis (of-course, my question isn't constrained to GPT, this is open to all LLMs including LLaMA) My question is the following:
**How can I optimize my time in developing prompts that can yield ... | 2023-10-31T02:31:02 | https://www.reddit.com/r/LocalLLaMA/comments/17karmm/what_are_some_ways_commonly_used_in_the_industry/ | anasp1 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 17karmm | false | null | t3_17karmm | /r/LocalLLaMA/comments/17karmm/what_are_some_ways_commonly_used_in_the_industry/ | false | false | self | 1 | null |
Do you follow Chinese LLM development? | 36 | Given that we got models like Qwen-14B that seem quite good for their size, I got curious about Chinese LLM research and tried to find some sites and found:
Leaderboards:
https://opencompass.org.cn/leaderboard-llm
https://cevalbenchmark.com/static/leaderboard.html
This one looks like a Chinese huggingface equivalen... | 2023-10-31T02:03:10 | https://www.reddit.com/r/LocalLLaMA/comments/17ka7lx/do_you_follow_chinese_llm_development/ | noeda | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 17ka7lx | false | null | t3_17ka7lx | /r/LocalLLaMA/comments/17ka7lx/do_you_follow_chinese_llm_development/ | false | false | self | 36 | null |
Apple M3 performance | 9 | Anyone with experience with the M2’s have a sense of how the M3 might perform?
I’m currently running Zephyr7b batches on a Nvidia A6000 (not ada). Is the performance likely to be comparable? | 2023-10-31T01:50:29 | https://www.reddit.com/r/LocalLLaMA/comments/17k9ybn/apple_m3_performance/ | Puzzleheaded-Fee5917 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 17k9ybn | false | null | t3_17k9ybn | /r/LocalLLaMA/comments/17k9ybn/apple_m3_performance/ | false | false | self | 9 | null |
Google Brain cofounder says Big Tech companies are lying about the risks of AI wiping out humanity because they want to dominate the market | 606 | 2023-10-31T01:35:34 | https://www.businessinsider.com/andrew-ng-google-brain-big-tech-ai-risks-2023-10?amp | ninjasaid13 | businessinsider.com | 1970-01-01T00:00:00 | 0 | {} | 17k9nmf | false | null | t3_17k9nmf | /r/LocalLLaMA/comments/17k9nmf/google_brain_cofounder_says_big_tech_companies/ | false | false | 606 | {'enabled': False, 'images': [{'id': '5Byrm2veQdYf7QQA2hSCH3ykAc83v1vznH42uQxbkuU', 'resolutions': [{'height': 54, 'url': 'https://external-preview.redd.it/bRm_F3z7OjGilk9ZQNhewdsWEaQb2Go7PO53Cm1deSs.jpg?width=108&crop=smart&auto=webp&s=dea9f5100e0c0e6f1e4ad4a5268aeef95fd62db2', 'width': 108}, {'height': 108, 'url': 'h... | ||
Are there any examples of using LLM to interacting with survey data in table format? | 1 | My question might sound very basic. I've mostly seen use cases of LLMs built to access private data like PDFs and word documents for answering questions. My question is about training a LLM to read tabular data like survey data in a SPSS or CSV file format.
The intention: Instead of going through the whole data or fre... | 2023-10-31T01:21:58 | https://www.reddit.com/r/LocalLLaMA/comments/17k9di4/are_there_any_examples_of_using_llm_to/ | Adventurous_Top8864 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 17k9di4 | false | null | t3_17k9di4 | /r/LocalLLaMA/comments/17k9di4/are_there_any_examples_of_using_llm_to/ | false | false | default | 1 | null |
Question about embarrassing but real things blamed on AI. | 2 | I have been seriously wondering why it seems like there hasn't been something embarrassing that's been accidentally recorded or an embarrassing photo that's blamed on AI. I don't pay attention to the news, so maybe I've missed it happen. I don't know. I would have just figured someone by now would have been caught w... | 2023-10-31T00:56:07 | https://www.reddit.com/r/LocalLLaMA/comments/17k8uex/question_about_embarrassing_but_real_things/ | Red_Redditor_Reddit | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 17k8uex | false | null | t3_17k8uex | /r/LocalLLaMA/comments/17k8uex/question_about_embarrassing_but_real_things/ | false | false | self | 2 | null |
The smartest model under the sun: Prof. McSmarty BS 13b GPTQ | 26 | 2023-10-31T00:33:33 | FPham | i.redd.it | 1970-01-01T00:00:00 | 0 | {} | 17k8db0 | false | null | t3_17k8db0 | /r/LocalLLaMA/comments/17k8db0/the_smartest_model_under_the_sun_prof_mcsmarty_bs/ | false | false | 26 | {'enabled': True, 'images': [{'id': 'HSNcqKH8vkoba1WXxsWupcg9L1w2cccMhnZUkx-jqf4', 'resolutions': [{'height': 108, 'url': 'https://preview.redd.it/by9hdxg4ofxb1.jpg?width=108&crop=smart&auto=webp&s=d70558738d362c72501cf3a83aa75e7b0fcafc29', 'width': 108}, {'height': 216, 'url': 'https://preview.redd.it/by9hdxg4ofxb1.jp... | |||
Biden Executive Order regulates VERY large models | 93 | [Executive Order on the Safe, Secure, and Trustworthy Development and Use of Artificial Intelligence | The White House](https://www.whitehouse.gov/briefing-room/presidential-actions/2023/10/30/executive-order-on-the-safe-secure-and-trustworthy-development-and-use-of-artificial-intelligence/)
Basically - **"any model... | 2023-10-31T00:01:03 | https://www.reddit.com/r/LocalLLaMA/comments/17k7obo/biden_executive_order_regulates_very_large_models/ | PookaMacPhellimen | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 17k7obo | false | null | t3_17k7obo | /r/LocalLLaMA/comments/17k7obo/biden_executive_order_regulates_very_large_models/ | false | false | self | 93 | {'enabled': False, 'images': [{'id': 'Qrl2WXotl30OMA9tBryQPbOJ5cES0zwcjCSWkKUi2fI', 'resolutions': [], 'source': {'height': 1, 'url': 'https://external-preview.redd.it/py9BdpPVXuz_9y2hpVru9I9x8g8RxFBDdHKnnf42ZdQ.jpg?auto=webp&s=9a209662f8757408a5c810b2e280782d843a9c91', 'width': 1}, 'variants': {}}]} |
RedPajama Data V2 has been released with 30 Trillion tokens of data | 4 | 2023-10-30T23:14:20 | https://huggingface.co/datasets/togethercomputer/RedPajama-Data-V2 | ninjasaid13 | huggingface.co | 1970-01-01T00:00:00 | 0 | {} | 17k6ns7 | false | null | t3_17k6ns7 | /r/LocalLLaMA/comments/17k6ns7/redpajama_data_v2_has_been_released_with_30/ | false | false | 4 | {'enabled': False, 'images': [{'id': 'Ut-Lmy9RlvlxW46uvDc_iwIXzQPx6d4SxnVErgAP5xM', 'resolutions': [{'height': 58, 'url': 'https://external-preview.redd.it/ARrljaXiQbkJ3kxB909c2awkf_3TavPFMsQi8lT0evQ.jpg?width=108&crop=smart&auto=webp&s=7ec254579c2aa127d04c1521374c2af5322c6ba2', 'width': 108}, {'height': 116, 'url': 'h... | ||
RedPajama Data V2 has been released | 1 | 2023-10-30T23:12:08 | https://huggingface.co/datasets/togethercomputer/RedPajama-Data-V2 | ninjasaid13 | huggingface.co | 1970-01-01T00:00:00 | 0 | {} | 17k6m4x | false | null | t3_17k6m4x | /r/LocalLLaMA/comments/17k6m4x/redpajama_data_v2_has_been_released/ | false | false | 1 | {'enabled': False, 'images': [{'id': 'Ut-Lmy9RlvlxW46uvDc_iwIXzQPx6d4SxnVErgAP5xM', 'resolutions': [{'height': 58, 'url': 'https://external-preview.redd.it/ARrljaXiQbkJ3kxB909c2awkf_3TavPFMsQi8lT0evQ.jpg?width=108&crop=smart&auto=webp&s=7ec254579c2aa127d04c1521374c2af5322c6ba2', 'width': 108}, {'height': 116, 'url': 'h... | ||
Fine-Tuning LLM with an "Infinite" Dataset | 1 | If I instruction tune an LLM with a dataset where each sample is randomly generated and fit into some set of prompt templates so that my dataset is effectively very large in theory, and I train the model for a certain number of steps, is that worse than just training on a dataset of a fixed size? I’d assume it is worse... | 2023-10-30T22:43:53 | https://www.reddit.com/r/LocalLLaMA/comments/17k5z91/finetuning_llm_with_an_infinite_dataset/ | LyGmAbAllz | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 17k5z91 | false | null | t3_17k5z91 | /r/LocalLLaMA/comments/17k5z91/finetuning_llm_with_an_infinite_dataset/ | false | false | self | 1 | null |
VRAM very high when using PEFT + FSDP | 6 | I'm trying to finetune Llama 34B. I'd expect approx 34 \* 2 GB VRAM usage + a bit extra for the LORA params. (34x2 because it should get loaded in bf16 right?). However, on my training VM with 192 GB VRAM across 8 GPUs I'm consistently getting OOM errors.
So what could be happening here? It's as if the model is being... | 2023-10-30T22:43:11 | https://www.reddit.com/r/LocalLLaMA/comments/17k5ynz/vram_very_high_when_using_peft_fsdp/ | fbgc | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 17k5ynz | false | null | t3_17k5ynz | /r/LocalLLaMA/comments/17k5ynz/vram_very_high_when_using_peft_fsdp/ | false | false | self | 6 | {'enabled': False, 'images': [{'id': 'IRhzaXpYIWLjNW9smvzvLLDcDxrBxsb3deyNnSHRCkk', 'resolutions': [{'height': 54, 'url': 'https://external-preview.redd.it/bD_XX1n-n8-GHd2LdAbfuCdOwxKCc6QZPaWM_EmRZL0.jpg?width=108&crop=smart&auto=webp&s=23446f517b9d322ee1941831d56e05eb98c62285', 'width': 108}, {'height': 108, 'url': 'h... |
SynthIA 70b on a single 3090, 0.17tokens/s | 2 | CPU is a ryzen 7 3700x, with 32gb of ddr4 3000mhz
I loaded the model with ExLlamav2\_HF and a 2048 sequence length. It spills, a lot. 11.5gb to be exact, but I read with the right specs I could expect 2-7tokens/s which would be more than bearable.
Is there any way I could optimize it further? | 2023-10-30T22:28:27 | https://www.reddit.com/r/LocalLLaMA/comments/17k5mdm/synthia_70b_on_a_single_3090_017tokenss/ | Longjumping-Bake-557 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 17k5mdm | false | null | t3_17k5mdm | /r/LocalLLaMA/comments/17k5mdm/synthia_70b_on_a_single_3090_017tokenss/ | false | false | self | 2 | null |
PSA: GBNF exists. Use it. | 52 | [GBNF](https://github.com/ggerganov/llama.cpp/blob/master/grammars/README.md), a rebranding of [Backus-Naur Form](https://en.wikipedia.org/wiki/Backus%E2%80%93Naur_form) is a kind of Regex if you somehow made Regex more obtuse and clunky and also way less powerful. It's like going to the dentist in text form. It is bad... | 2023-10-30T22:28:26 | https://www.reddit.com/r/LocalLLaMA/comments/17k5mcy/psa_gbnf_exists_use_it/ | Dead_Internet_Theory | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 17k5mcy | false | null | t3_17k5mcy | /r/LocalLLaMA/comments/17k5mcy/psa_gbnf_exists_use_it/ | false | false | 52 | {'enabled': False, 'images': [{'id': 'DJPqvteONpGwVVw6LzaG6b8vlDa2rv2hETCaqe0z57s', 'resolutions': [{'height': 54, 'url': 'https://external-preview.redd.it/wyCM1fHzTa-IIqHgS1QTxdSYNXn668elDj0WmYMPf_k.jpg?width=108&crop=smart&auto=webp&s=d6fa197328d583bcae7a764b40fd1214265b6852', 'width': 108}, {'height': 108, 'url': 'h... | |
Any tricks to speed up 13B models on a 3090? | 8 | Are there any tricks to speed up 13B models on a 3090?
Currently using the regular huggingface model quantized to 8bit by a GPTQ capable fork of KoboldAI.
Especially when the context limit changes, it's pretty slow and far from even remotely real time. | 2023-10-30T22:23:12 | https://www.reddit.com/r/LocalLLaMA/comments/17k5i1o/any_tricks_to_speed_up_13b_models_on_a_3090/ | DustGrouchy1792 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 17k5i1o | false | null | t3_17k5i1o | /r/LocalLLaMA/comments/17k5i1o/any_tricks_to_speed_up_13b_models_on_a_3090/ | false | false | self | 8 | null |
What is your biggest challenge while building a RAG? | 3 | Just want to know what are some of the biggest challenges involved in building good RAG systems? | 2023-10-30T21:53:29 | https://www.reddit.com/r/LocalLLaMA/comments/17k4su2/what_is_your_biggest_challenge_while_building_a/ | Spirited-Order4409 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 17k4su2 | false | null | t3_17k4su2 | /r/LocalLLaMA/comments/17k4su2/what_is_your_biggest_challenge_while_building_a/ | false | false | self | 3 | null |
RedPajama-Data-v2: an Open Dataset with 30 Trillion Tokens for Training Large Language Models | 127 | **Blog**: [https://together.ai/blog/redpajama-data-v2](https://together.ai/blog/redpajama-data-v2)
**Hugging Face**: [https://huggingface.co/datasets/togethercomputer/RedPajama-Data-V2](https://huggingface.co/datasets/togethercomputer/RedPajama-Data-V2)
**GitHub**: [https://github.com/togethercomputer/RedPajama-Data]... | 2023-10-30T21:38:47 | https://www.reddit.com/r/LocalLLaMA/comments/17k4ghf/redpajamadatav2_an_open_dataset_with_30_trillion/ | APaperADay | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 17k4ghf | false | null | t3_17k4ghf | /r/LocalLLaMA/comments/17k4ghf/redpajamadatav2_an_open_dataset_with_30_trillion/ | false | false | self | 127 | {'enabled': False, 'images': [{'id': 'UMuTBgV-MLBqE8FXJARb58jFnz0fpqBFgS89fw0YpoY', 'resolutions': [{'height': 60, 'url': 'https://external-preview.redd.it/dnqnrIheAZkjlhdnUdo-pqf9U67FeoG_sNbFF5qXH7U.jpg?width=108&crop=smart&auto=webp&s=241cc4ceed8acc1ef9c179a6ba2b303e446dec64', 'width': 108}, {'height': 121, 'url': 'h... |
I want to host an LLM for code completion on my Local Network | 1 | [removed] | 2023-10-30T20:56:50 | https://www.reddit.com/r/LocalLLaMA/comments/17k3hoa/i_want_to_host_an_llm_for_code_completion_on_my/ | Wonderful_Charity_35 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 17k3hoa | false | null | t3_17k3hoa | /r/LocalLLaMA/comments/17k3hoa/i_want_to_host_an_llm_for_code_completion_on_my/ | false | false | self | 1 | null |
Relevance Extraction in RAG pipelines | 26 | I came across this interesting problem in RAG, what I call Relevance Extraction.
After retrieving relevant documents (or chunks), these chunks are often large and may contain several portions **irrelevant** to the query at hand. Stuffing the entire chunk into an LLM prompt impacts token-cost as well as response accura... | 2023-10-30T20:46:36 | https://www.reddit.com/r/LocalLLaMA/comments/17k39es/relevance_extraction_in_rag_pipelines/ | SatoshiNotMe | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 17k39es | false | null | t3_17k39es | /r/LocalLLaMA/comments/17k39es/relevance_extraction_in_rag_pipelines/ | false | false | self | 26 | {'enabled': False, 'images': [{'id': 'HVh9Sny5l6xGCEfhrNnt7ADDZpBGVn4VejrhCk08t1I', 'resolutions': [{'height': 27, 'url': 'https://external-preview.redd.it/uhSfsvG9xouKferDMe5t93nGUuVyyu9ppA85YzogQSM.jpg?width=108&crop=smart&auto=webp&s=f5bf7ce604153181eeed4092593185ebbce71ebc', 'width': 108}], 'source': {'height': 35,... |
SCALE: An Innovative Approach for Factual Inconsistency Detection in Long Documents | 16 | Hello LLM enthusiasts!
Are you interested in generative AI models and the ongoing challenge of tackling hallucinations across various tasks? Our recent research introduces a task-agnostic model called SCALE (Source Chunking Approach for Large-scale inconsistency Evaluation) that has been engineered to detect factual ... | 2023-10-30T20:32:44 | https://www.reddit.com/r/LocalLLaMA/comments/17k2xod/scale_an_innovative_approach_for_factual/ | bmlattimer | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 17k2xod | false | null | t3_17k2xod | /r/LocalLLaMA/comments/17k2xod/scale_an_innovative_approach_for_factual/ | false | false | 16 | {'enabled': False, 'images': [{'id': 'vOtDgfgWNjYmeO8oR_Xewwr1pktU-A92DtA6qfnm9Mc', 'resolutions': [{'height': 54, 'url': 'https://external-preview.redd.it/YT2KFBHafaeL9j3IlvMQ1_f-1XvGEOh6NdcCJrKwFCw.jpg?width=108&crop=smart&auto=webp&s=13f86e326be04e7caeb1709bf620e1f8544118c7', 'width': 108}, {'height': 108, 'url': 'h... | |
I scaled Mistral 7B to 200 GPUs in less than 5 minutes | 76 | I've been working on a project with my roommate to make it incredibly simple to run batch inference on LLMs while leveraging a massive amount of cloud resources. We finally got the tool working and created a tutorial on how to use it on Mistral 7B.
Also, if you're a frequent HuggingFace user you can easily adapt the ... | 2023-10-30T20:32:09 | https://www.reddit.com/r/LocalLLaMA/comments/17k2x62/i_scaled_mistral_7b_to_200_gpus_in_less_than_5/ | Ok_Post_149 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 17k2x62 | false | null | t3_17k2x62 | /r/LocalLLaMA/comments/17k2x62/i_scaled_mistral_7b_to_200_gpus_in_less_than_5/ | false | false | self | 76 | {'enabled': False, 'images': [{'id': 'VkvJ2zk3G88CDDxNk_lS-uilGBXZi0Gzc-1GYg2ZTqU', 'resolutions': [{'height': 70, 'url': 'https://external-preview.redd.it/cv6pasysE22JcigeAlexN2VJgRlciwVrumw49Szci-s.jpg?width=108&crop=smart&auto=webp&s=34d9a27a84ddd2ef52daeb04dad944a9b72dca3b', 'width': 108}, {'height': 141, 'url': 'h... |
I don't understand Mistral and context size, honestly. | 42 | Hi, I have searched for a long time on this subreddit, in Ooba's documentation, Mistral's documentation and everything, but I just can't find what I am looking for.
I see everyone claiming Mistral can handle up to 32k context size, however while it technically won't refuse to generate anything above like 8k, the outpu... | 2023-10-30T20:20:16 | https://www.reddit.com/r/LocalLLaMA/comments/17k2mwq/i_dont_understand_mistral_and_context_size/ | anti-lucas-throwaway | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 17k2mwq | false | null | t3_17k2mwq | /r/LocalLLaMA/comments/17k2mwq/i_dont_understand_mistral_and_context_size/ | false | false | self | 42 | null |
llama.cpp for normies: FreeChat is now live on the mac app store | 27 | Hey ya'll, quick update about my open source llama.cpp app, FreeChat. As of this weekend it's live on the mac app store. Big thanks to this community for all the feedback and testing, would not have gotten here without ya'll. Next I'm working on the most common request I get here: a model catalog.
Have friends who are... | 2023-10-30T19:56:26 | https://www.reddit.com/r/LocalLLaMA/comments/17k22lj/llamacpp_for_normies_freechat_is_now_live_on_the/ | sleeper-2 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 17k22lj | false | null | t3_17k22lj | /r/LocalLLaMA/comments/17k22lj/llamacpp_for_normies_freechat_is_now_live_on_the/ | false | false | self | 27 | {'enabled': False, 'images': [{'id': 'icuMuhzXDuYMb9EgOWhfmrjVA9e-x9UXBIIpBmPRo80', 'resolutions': [{'height': 108, 'url': 'https://external-preview.redd.it/oP4scis9R5vPzQ7zl5b3qpbtwIp8ShsdYQy3iV2xSWM.jpg?width=108&crop=smart&auto=webp&s=7e87bd23d738600d48f6b4efeef5b1c1fd2765dc', 'width': 108}, {'height': 216, 'url': '... |
Has there been any alt-right equivalent of ChatGPT? | 0 | Hey everyone!
I recently came across mentions of a "RightWingGPT." However, I'm curious: with the notable presence of alt-right communities online, why hasn't there been an instance of them fine-tuning a model that reflects their perspectives? It's surprising given how sizable these communities can be. Has anyone hear... | 2023-10-30T19:54:53 | https://www.reddit.com/r/LocalLLaMA/comments/17k219y/has_there_been_any_altright_equivalent_of_chatgpt/ | Alarmed-Profile5736 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 17k219y | false | null | t3_17k219y | /r/LocalLLaMA/comments/17k219y/has_there_been_any_altright_equivalent_of_chatgpt/ | false | false | self | 0 | null |
Wizard Vicuna 7b , SUCKS ? | 0 | Hey !
so as the title suggests , I downloaded the bloke's wizard vicuna 7b , and I was hoping to use it in some sort of RP or smth , yet the model is too bad !!
like seriously , it barely stays in character for more than one line , and even this one line is full of random weird stuff like what the actual hell !!
&#... | 2023-10-30T19:30:10 | https://www.reddit.com/r/LocalLLaMA/comments/17k1h62/wizard_vicuna_7b_sucks/ | The_Happy_Hangman | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 17k1h62 | false | null | t3_17k1h62 | /r/LocalLLaMA/comments/17k1h62/wizard_vicuna_7b_sucks/ | false | false | self | 0 | null |
lmstudio.ai errors when trying to load models on Windows 11 | 1 | [removed] | 2023-10-30T19:29:43 | https://www.reddit.com/r/LocalLLaMA/comments/17k1gtj/lmstudioai_errors_when_trying_to_load_models_on/ | qz7GaGY9g1MXX6g6 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 17k1gtj | false | null | t3_17k1gtj | /r/LocalLLaMA/comments/17k1gtj/lmstudioai_errors_when_trying_to_load_models_on/ | false | false | self | 1 | null |
Zephyr comes up with an original, impressive joke. | 3 | So I literally just got Zephyr 7b beta GPTQ running
(tried GGUF but i was getting 0.5 tokens a second, vs 8 now, if anyone knows what was up with that please let me know, im on a 3070RTX laptop 16GB VRAM, 32GB RAM with a high end i7 12700 (20 threads)
Settings were: gpu-layers 30, n\_ctx tried 2k, 4k, 32k, threads ... | 2023-10-30T19:12:23 | https://www.reddit.com/r/LocalLLaMA/comments/17k12la/zephyr_comes_up_with_an_original_impressive_joke/ | emrys95 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 17k12la | false | null | t3_17k12la | /r/LocalLLaMA/comments/17k12la/zephyr_comes_up_with_an_original_impressive_joke/ | false | false | self | 3 | null |
Best way to run local embedding models? | 1 | [removed] | 2023-10-30T18:59:54 | https://www.reddit.com/r/LocalLLaMA/comments/17k0s96/best_way_to_run_local_embedding_models/ | samlhuillier3 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 17k0s96 | false | null | t3_17k0s96 | /r/LocalLLaMA/comments/17k0s96/best_way_to_run_local_embedding_models/ | false | false | self | 1 | null |
Handling Generic Queries in RAG Applications | 4 | I'm trying to build an application using RAGs. I know how RAGs help ground the responses and all, but how do I handle generic queries from users which have nothing to do with what's stored in my vector database?
For example, queries such as: "How many gold medals did China win during Tokyo Olympics?" vs "Parapharse thi... | 2023-10-30T18:19:48 | https://www.reddit.com/r/LocalLLaMA/comments/17jzvx8/handling_generic_queries_in_rag_applications/ | tinyburger1 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 17jzvx8 | false | null | t3_17jzvx8 | /r/LocalLLaMA/comments/17jzvx8/handling_generic_queries_in_rag_applications/ | false | false | self | 4 | null |
Is using WSL good enough for running LLM models locally? | 10 | Or should I dual boot ubuntu instead of using WSL | 2023-10-30T18:06:46 | https://www.reddit.com/r/LocalLLaMA/comments/17jzljd/is_using_wsl_good_enough_for_running_llm_models/ | derpgod123 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 17jzljd | false | null | t3_17jzljd | /r/LocalLLaMA/comments/17jzljd/is_using_wsl_good_enough_for_running_llm_models/ | false | false | self | 10 | null |
Fine-tuning Local LLMs for "Code Interpreter" use: Seeking Experience and Insights | 5 | Hello fellow LLM enthusiasts!
I'm building a little code+chat CLI called [gptme](https://github.com/ErikBjare/gptme), that aims to leverage the capabilities of local LLMs to mimic the functionalities offered by OpenAI's "Advanced Data Analysis" (formerly known as "Code Interpreter"). It is similar in spirit to the mo... | 2023-10-30T17:55:39 | https://www.reddit.com/r/LocalLLaMA/comments/17jzcaq/finetuning_local_llms_for_code_interpreter_use/ | ErikBjare | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 17jzcaq | false | null | t3_17jzcaq | /r/LocalLLaMA/comments/17jzcaq/finetuning_local_llms_for_code_interpreter_use/ | false | false | self | 5 | {'enabled': False, 'images': [{'id': 'zleI38o3EKf9jJkTwTgXpM5ijQ9Vr8JqKiblqca9TpY', 'resolutions': [{'height': 54, 'url': 'https://external-preview.redd.it/mb3ljwGRtMFt4QD2PSjCA0wtupQjam_z3jKf3zB-mA4.jpg?width=108&crop=smart&auto=webp&s=0881198e0bfd572bd18e197334a6b417d304ac53', 'width': 108}, {'height': 108, 'url': 'h... |
ELI12 the new executive order on AI for non-experts, please? | 30 | I lurk this sub as a DA who doesn't work with LLMs. I've seen the new executive order on AI in the US, and that the reaction to it is generally negative from the people on this sub.
Can someone explain to me why people in this community and other AI/ML/LLM/CS communities are critical of the Biden's new executive orde... | 2023-10-30T17:52:14 | https://www.reddit.com/r/LocalLLaMA/comments/17jz9l6/eli12_the_new_executive_order_on_ai_for/ | empirical-sadboy | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 17jz9l6 | false | null | t3_17jz9l6 | /r/LocalLLaMA/comments/17jz9l6/eli12_the_new_executive_order_on_ai_for/ | false | false | self | 30 | null |
Best french model & stack for 3.5gpt like experience | 3 | I want to create a telegram chat bot for my French organisation. We need strong privacy and uncensored LM and they only agree to have some self managed LM chatbot
What stack would be the easiest to deploy the cloud behind telegram? Any cheap cloud recommended for that matter?
If it's working good we will buy some ha... | 2023-10-30T17:37:00 | https://www.reddit.com/r/LocalLLaMA/comments/17jyx9r/best_french_model_stack_for_35gpt_like_experience/ | Hyakutak | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 17jyx9r | false | null | t3_17jyx9r | /r/LocalLLaMA/comments/17jyx9r/best_french_model_stack_for_35gpt_like_experience/ | false | false | self | 3 | null |
Crowd-Sourced Computing for LLM Training | 5 | Hello,
Does anyone know if there are any significant efforts in distributing the computing efforts to train LLMs to different consumer GPUs spread on the internet? It seems impossible to match the computing capabilities of big tech, and it got me wondering if there was a large-scale effort to share compute for one(or... | 2023-10-30T17:16:15 | https://www.reddit.com/r/LocalLLaMA/comments/17jygdw/crowdsourced_computing_for_llm_training/ | Melodic_Gur_5913 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 17jygdw | false | null | t3_17jygdw | /r/LocalLLaMA/comments/17jygdw/crowdsourced_computing_for_llm_training/ | false | false | self | 5 | null |
Any efficiently working Local LLM + Stable Diff solution for Macbook 2018 Pro with AMD GPU? | 2 | Title is tldr.
For longer:
I've been using Local LLM and Stable Diff with my pc - GeForce 1070Ti.
My daily life goes with macbook pro 2018 with amd gpu. Still couldn't figure out of to run an efficient LLM - (ollama Mistral only properly working so far), and no way of running ComfyUI, just extremely slow automatic1111... | 2023-10-30T17:10:47 | https://www.reddit.com/r/LocalLLaMA/comments/17jyc15/any_efficiently_working_local_llm_stable_diff/ | bparlan | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 17jyc15 | false | null | t3_17jyc15 | /r/LocalLLaMA/comments/17jyc15/any_efficiently_working_local_llm_stable_diff/ | false | false | self | 2 | null |
how to train/prompt a llm to understand frameworks api? | 3 | id like to take a python framework project and have a specialized coder. id like to feed it the documentation and git hub code where examples are shown. then id like to have the chat LM injest it and only code in that framework api
my approach so far has been to shove some of its documentation into the prompt and tell... | 2023-10-30T15:49:27 | https://www.reddit.com/r/LocalLLaMA/comments/17jwhcs/how_to_trainprompt_a_llm_to_understand_frameworks/ | herozorro | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 17jwhcs | false | null | t3_17jwhcs | /r/LocalLLaMA/comments/17jwhcs/how_to_trainprompt_a_llm_to_understand_frameworks/ | false | false | self | 3 | null |
Nous-Capybara-3B and 7B V1.9: First 3B model by Nous! | 35 | Happy to announce my release of Nous-Capybara 7B and 3B V1.9!
7B V1.9 version is now trained with Mistral instead of V1 that was trained on Llama. Also some significant dataset improvements under the hood.
As for the 3B size, it's the first sub-7B model released under Nous Research and leverages the same dataset as 7... | 2023-10-30T15:42:26 | https://www.reddit.com/r/LocalLLaMA/comments/17jwbml/nouscapybara3b_and_7b_v19_first_3b_model_by_nous/ | dogesator | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 17jwbml | false | null | t3_17jwbml | /r/LocalLLaMA/comments/17jwbml/nouscapybara3b_and_7b_v19_first_3b_model_by_nous/ | false | false | self | 35 | {'enabled': False, 'images': [{'id': 'B25xm0IqAp9YWurUMex1J3Kyle2i1soUn7lb_8QqZCE', 'resolutions': [{'height': 58, 'url': 'https://external-preview.redd.it/_u6ZL79jro8jARXdSNXV48KE2yKs1AdRYwHUuMCnBDA.jpg?width=108&crop=smart&auto=webp&s=c03ecf852c83656ff6263c3f7ebaccadabf1070d', 'width': 108}, {'height': 116, 'url': 'h... |
Ok, tell me how stupid this concept is: Using a Blockchain-like system where the process of mining trains a decentralized model. | 0 | I'm not really talking about a cryptocurrency, more of an anonymous collaborative system where your local copy of the blockchain syncs up to the most recent stage of the model's training and dataset, and the process of mining is a pooled effort to find the next best loss reduction.
Training data would obviously be a p... | 2023-10-30T15:22:19 | https://www.reddit.com/r/LocalLLaMA/comments/17jvvs3/ok_tell_me_how_stupid_this_concept_is_using_a/ | VRpornFTW | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 17jvvs3 | false | null | t3_17jvvs3 | /r/LocalLLaMA/comments/17jvvs3/ok_tell_me_how_stupid_this_concept_is_using_a/ | false | false | self | 0 | null |
Fine-tuning Falcon 7B for Sequence Classification using LoRA | 4 | Hey all, first time posting here and relatively new to working with LLMs.
I’m trying to fine-tune Falcon7B for Sequence Classification. All the tutorials I’ve seen so far always use CausalLM so I’m not sure if there’s anything wrong with my implementation. Anyway, I was able to fine-tune ClinicalBERT (100 million tra... | 2023-10-30T15:22:02 | https://www.reddit.com/r/LocalLLaMA/comments/17jvvj3/finetuning_falcon_7b_for_sequence_classification/ | aahmed96 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 17jvvj3 | false | null | t3_17jvvj3 | /r/LocalLLaMA/comments/17jvvj3/finetuning_falcon_7b_for_sequence_classification/ | false | false | self | 4 | {'enabled': False, 'images': [{'id': 'nfayPavSUB5ngYv6-19UHNBThsXfcLIDQl4HkEe3Cv0', 'resolutions': [{'height': 108, 'url': 'https://external-preview.redd.it/yzSfTlKTSYGpEXeFgyDvHlfoLGOFQJqPuH_Y38RBz2U.jpg?width=108&crop=smart&auto=webp&s=0aad06750c23b98c9b7595343a8b54a42dc18851', 'width': 108}, {'height': 216, 'url': '... |
In light of the recent Executive Order, the open source community should be aware of this dude and his work. | 1 | [removed] | 2023-10-30T15:09:40 | https://www.reddit.com/r/LocalLLaMA/comments/17jvkxo/in_light_of_the_recent_executive_order_the_open/ | Future_Might_8194 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 17jvkxo | false | null | t3_17jvkxo | /r/LocalLLaMA/comments/17jvkxo/in_light_of_the_recent_executive_order_the_open/ | false | false | self | 1 | {'enabled': False, 'images': [{'id': 'fTQbfqUJFloIJow30Q8PjmH7FfuJgRkjie2_Gsk2Cok', 'resolutions': [{'height': 81, 'url': 'https://external-preview.redd.it/fzCBA8kKBw1Fggz1mdRV8V3tn8wHu4THXVQ0NSUPubo.jpg?width=108&crop=smart&auto=webp&s=ca5b2b9559e42c0c478e8ce0005835fb51a662f5', 'width': 108}, {'height': 162, 'url': 'h... |
New LoftQ quantization technique outperforms QLora | 1 | [removed] | 2023-10-30T14:49:18 | https://www.reddit.com/r/LocalLLaMA/comments/17jv45k/new_loftq_quantization_technique_outperforms_qlora/ | yahma | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 17jv45k | false | null | t3_17jv45k | /r/LocalLLaMA/comments/17jv45k/new_loftq_quantization_technique_outperforms_qlora/ | false | false | self | 1 | null |
In light of the recent Executive Order, the open source community should be aware of this dude and his work. | 1 | [removed] | 2023-10-30T14:39:13 | https://www.reddit.com/r/LocalLLaMA/comments/17juwcx/in_light_of_the_recent_executive_order_the_open/ | SSPaladin | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 17juwcx | false | null | t3_17juwcx | /r/LocalLLaMA/comments/17juwcx/in_light_of_the_recent_executive_order_the_open/ | false | false | self | 1 | {'enabled': False, 'images': [{'id': 'fTQbfqUJFloIJow30Q8PjmH7FfuJgRkjie2_Gsk2Cok', 'resolutions': [{'height': 81, 'url': 'https://external-preview.redd.it/fzCBA8kKBw1Fggz1mdRV8V3tn8wHu4THXVQ0NSUPubo.jpg?width=108&crop=smart&auto=webp&s=ca5b2b9559e42c0c478e8ce0005835fb51a662f5', 'width': 108}, {'height': 162, 'url': 'h... |
Obsidian: Worlds first 3B multi-modal opensource LLM. | 125 | Hey everyone, happy to say I’m officially announcing Obsidian V0.5 as part of my work at Nous Research and building upon my work creating the Capybara V1.9 dataset.
This model is blazing fast and is likely the first Multi-modal model that is efficient enough to fit within the ram constraints of even a non-pro iphone! ... | 2023-10-30T14:33:40 | dogesator | i.redd.it | 1970-01-01T00:00:00 | 0 | {} | 17jus3h | false | null | t3_17jus3h | /r/LocalLLaMA/comments/17jus3h/obsidian_worlds_first_3b_multimodal_opensource_llm/ | false | false | 125 | {'enabled': True, 'images': [{'id': 'ZDQFumqmyuf7lvUwa9wl-KYivIgB-m4tqzO1PqCOVzA', 'resolutions': [{'height': 38, 'url': 'https://preview.redd.it/6bdc3kh4pcxb1.jpg?width=108&crop=smart&auto=webp&s=423be4a6f574c7da923fef0d19476ec2d1f80011', 'width': 108}, {'height': 77, 'url': 'https://preview.redd.it/6bdc3kh4pcxb1.jpg?... | ||
What are the best web-apps/apps/tools using LLMs in production (at scale) atm? | 1 | Hey,
I am looking for inspiration in building frontends with LLMs (ChatGPT and stuff). I am looking for companies, which have LLMs (their own or wrappers around GPT) deployed in customer-facing applications (B2B and B2C) at some level of scale. Something like Sudowrite and Jasper.
I would appreciate any link or n... | 2023-10-30T14:11:43 | https://www.reddit.com/r/LocalLLaMA/comments/17jub94/what_are_the_best_webappsappstools_using_llms_in/ | SpiritedAd895 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 17jub94 | false | null | t3_17jub94 | /r/LocalLLaMA/comments/17jub94/what_are_the_best_webappsappstools_using_llms_in/ | false | false | self | 1 | null |
Llama2 7B hallucination | 1 | I was testing llama2 chat hf model for some generation and story telling tasks. I used the standard chat format with the system prompt that "You are a helpful and harmless Assistant"
Then I used the user input " <<SYS>> Tell me a story of a bird and it's egg <<SYS>>"
The model response started out well enough.
" Once... | 2023-10-30T13:36:40 | https://www.reddit.com/r/LocalLLaMA/comments/17jtkby/llama2_7b_hallucination/ | testerpce | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 17jtkby | false | null | t3_17jtkby | /r/LocalLLaMA/comments/17jtkby/llama2_7b_hallucination/ | false | false | self | 1 | null |
Has anyone tried Aquila2-34b? | 1 | The claims are pretty staggering, a 34b model with an 8k context length, llama2 70b performance and 7b speed? Seems too good to be true, is this legit or is it a 7b model named as a 34b in true chinse fashion?
[https://huggingface.co/TheBloke/AquilaChat2-34B-16K-GPTQ](https://huggingface.co/TheBloke/AquilaChat2-34B-16... | 2023-10-30T13:29:38 | https://www.reddit.com/r/LocalLLaMA/comments/17jtf0k/has_anyone_tried_aquila234b/ | Longjumping-Bake-557 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 17jtf0k | false | null | t3_17jtf0k | /r/LocalLLaMA/comments/17jtf0k/has_anyone_tried_aquila234b/ | false | false | self | 1 | {'enabled': False, 'images': [{'id': 'zEsCl1EADCvCSAl4B6XtEHfoYCaDoKV1caBOHUAKvzU', 'resolutions': [{'height': 58, 'url': 'https://external-preview.redd.it/ZXSMfl2BwL3LmrMYDDCwPisi5ibZOoYjLgjP3n0fr64.jpg?width=108&crop=smart&auto=webp&s=a6528b0b6865a52db1c507fdb8eab0bfe82039ee', 'width': 108}, {'height': 116, 'url': 'h... |
An excellent use cases for local LLM, anonymity on delivery apps. | 0 | There was a post on the front page regarding a woman who changed her name to be more masculine on a food delivery app and this lead to a lack of men being creepy.
​
Am I alone in thinking this might be an excellent use case for local LLMs? It should be within the realm of current ability that on order, for the... | 2023-10-30T13:28:01 | https://www.reddit.com/r/LocalLLaMA/comments/17jtdwv/an_excellent_use_cases_for_local_llm_anonymity_on/ | valdev | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 17jtdwv | false | null | t3_17jtdwv | /r/LocalLLaMA/comments/17jtdwv/an_excellent_use_cases_for_local_llm_anonymity_on/ | false | false | self | 0 | null |
Best LLMs for buddy-like conversations | 8 | So, I opened Huggingface and filtered the models with the conversational use-case and sorted with the highest downloads. Two models were prominent MSFT Dialogpt and Facebook Blenderbot 400M.
Are these the best LLms for this application? Will finetuning them be easy or worthit? If not, what models should I focus on a... | 2023-10-30T12:54:42 | https://www.reddit.com/r/LocalLLaMA/comments/17jsqm5/best_llms_for_buddylike_conversations/ | Unlucky-Thing4593 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 17jsqm5 | false | null | t3_17jsqm5 | /r/LocalLLaMA/comments/17jsqm5/best_llms_for_buddylike_conversations/ | false | false | self | 8 | null |
Did Microsoft leaked GPT 3.5 parameter count? | 0 | I was reading the new CodeFusion paper by Microsoft and found this table.
If this is true then OpenAI is way ahead of what I was imaging.
It could also be a typo of 200B, as it's leaked that GPT 4's each experts are around 200B so maybe 3.5 is the same.
Although, for some reason I wish it's actually 20B because if t... | 2023-10-30T12:34:24 | Independent_Key1940 | i.redd.it | 1970-01-01T00:00:00 | 0 | {} | 17jsd3s | false | null | t3_17jsd3s | /r/LocalLLaMA/comments/17jsd3s/did_microsoft_leaked_gpt_35_parameter_count/ | false | false | 0 | {'enabled': True, 'images': [{'id': '1LVJ899OgnZgjksgt8wLfOJUUaTmJUhyD1MiBnWGiQs', 'resolutions': [{'height': 67, 'url': 'https://preview.redd.it/my6xqfgu3cxb1.jpg?width=108&crop=smart&auto=webp&s=a324ce408465d1f4f12e2c3aef3abe94d721ccf8', 'width': 108}, {'height': 134, 'url': 'https://preview.redd.it/my6xqfgu3cxb1.jpg... | ||
Does any one knows an efficent way to fine-tune llama2 using qlora on colab? | 2 | I am trying to do that, but always it run out of memory and breaks. If any can help me, i will be gratefull | 2023-10-30T12:12:11 | https://www.reddit.com/r/LocalLLaMA/comments/17jryfq/does_any_one_knows_an_efficent_way_to_finetune/ | Lipao262 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 17jryfq | false | null | t3_17jryfq | /r/LocalLLaMA/comments/17jryfq/does_any_one_knows_an_efficent_way_to_finetune/ | false | false | self | 2 | null |
Microsoft paper says gpt-3.5-turbo is 20B | 1 | 2023-10-30T12:11:35 | https://twitter.com/felix_red_panda/status/1718916631512949248 | phree_radical | twitter.com | 1970-01-01T00:00:00 | 0 | {} | 17jry2g | false | {'oembed': {'author_name': 'Felix', 'author_url': 'https://twitter.com/felix_red_panda', 'cache_age': 3153600000, 'height': None, 'html': '<blockquote class="twitter-video"><p lang="en" dir="ltr">Microsoft paper claims ChatGPT 3.5 has ~20 billion parameters <a href="https://t.co/gZxh0l2VqX">https://t.co/gZxh0l2VqX</a> ... | t3_17jry2g | /r/LocalLLaMA/comments/17jry2g/microsoft_paper_says_gpt35turbo_is_20b/ | false | false | 1 | {'enabled': False, 'images': [{'id': 'AK_br-JmODSMYX7yOFAuLSG429VE7ZLk5lUFDI3Y_OE', 'resolutions': [{'height': 77, 'url': 'https://external-preview.redd.it/v-LDuXxJYA0wc6bcryL7M8AGJohlVUhHVuvTSbh7KDk.jpg?width=108&crop=smart&auto=webp&s=58a48724b87f374f3330dc6f1e0171bbb341e5b1', 'width': 108}], 'source': {'height': 100... | ||
Executive order on AI - Now a good time to get my own local? | 43 | With the news on the executive order targeting AI, would now be a good time to create a local instance for myself which would not be neutered or reduced to useless due to these orders? If so, what should I set my sights on to not waste time with smaller instances? | 2023-10-30T12:01:32 | https://www.reddit.com/r/LocalLLaMA/comments/17jrrjo/executive_order_on_ai_now_a_good_time_to_get_my/ | LetsGroup | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 17jrrjo | false | null | t3_17jrrjo | /r/LocalLLaMA/comments/17jrrjo/executive_order_on_ai_now_a_good_time_to_get_my/ | false | false | self | 43 | null |
How to present text with code and json to llama | 2 | Can someone please suggest a good way to present data to llama2 for fine tuning which contains text, json and java code sample.
Text data holds explanation about a topic and then java class and JSON to support the explanation. | 2023-10-30T11:56:43 | https://www.reddit.com/r/LocalLLaMA/comments/17jrodp/how_to_present_text_with_code_and_json_to_llama/ | Optimal_Original_815 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 17jrodp | false | null | t3_17jrodp | /r/LocalLLaMA/comments/17jrodp/how_to_present_text_with_code_and_json_to_llama/ | false | false | self | 2 | null |
New Microsoft codediffusion paper suggests GPT-3.5 Turbo is only 20B, good news for open source models? | 272 | Wondering what everyone thinks in case this is true. It seems they're already beating all open source models including Llama-2 70B. Is this all due to data quality? Will Mistral be able to beat it next year?
https://preview.redd.it/kdk6fwr7vbxb1.png?width=605&format=png&auto=webp&s=21ac9936581d1376815d53e07e5b0adb739c... | 2023-10-30T11:48:22 | https://www.reddit.com/r/LocalLLaMA/comments/17jrj82/new_microsoft_codediffusion_paper_suggests_gpt35/ | obvithrowaway34434 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 17jrj82 | false | null | t3_17jrj82 | /r/LocalLLaMA/comments/17jrj82/new_microsoft_codediffusion_paper_suggests_gpt35/ | false | false | 272 | {'enabled': False, 'images': [{'id': 'q3evP6JeDpAC2MdSQHWYxnCYTqbJkElIQsLFqVSdkss', 'resolutions': [{'height': 63, 'url': 'https://external-preview.redd.it/izh8gZHY4FqZ1nwtU1N_TjtohUCNuvTyMn90toXda80.jpg?width=108&crop=smart&auto=webp&s=bc9575b410002edc2df3c5b5b0355fefedc7baa8', 'width': 108}, {'height': 126, 'url': 'h... | |
Fine tune for code tips | 15 | Hi monsters,
can u please gimme some pathway to reduce the expected 23 lifes to learn more on fine tuning in the LLM for code context?
I already tested pretrained models at home and started to create datasets and crazy experiments my self but of course, some guidance can help me to focus and learn important things i’m... | 2023-10-30T11:13:38 | fab_space | i.redd.it | 1970-01-01T00:00:00 | 0 | {} | 17jqzc7 | false | null | t3_17jqzc7 | /r/LocalLLaMA/comments/17jqzc7/fine_tune_for_code_tips/ | false | false | 15 | {'enabled': True, 'images': [{'id': 'qI5HiO3HxqCk-T5-pzeguFXl6kiPWP9DC-M96F2oV14', 'resolutions': [{'height': 108, 'url': 'https://preview.redd.it/pph5ingfpbxb1.jpg?width=108&crop=smart&auto=webp&s=1cd0b268c253d0da41fe4a32a3bdfa37f24a86e8', 'width': 108}, {'height': 216, 'url': 'https://preview.redd.it/pph5ingfpbxb1.jp... | ||
FACT SHEET: President Biden Issues Executive Order on Safe, Secure, and Trustworthy Artificial Intelligence | The White House | 151 | 2023-10-30T10:43:53 | https://www.whitehouse.gov/briefing-room/statements-releases/2023/10/30/fact-sheet-president-biden-issues-executive-order-on-safe-secure-and-trustworthy-artificial-intelligence/ | a_slay_nub | whitehouse.gov | 1970-01-01T00:00:00 | 0 | {} | 17jqj44 | false | null | t3_17jqj44 | /r/LocalLLaMA/comments/17jqj44/fact_sheet_president_biden_issues_executive_order/ | false | false | 151 | {'enabled': False, 'images': [{'id': 'ZNmtnK_lKgHB3spQIpgDtNznEADE6oLEzeeSxD2gjRA', 'resolutions': [{'height': 56, 'url': 'https://external-preview.redd.it/D4ApVTqUzlai30E0NQT1Y_RowF1Ep9U50QtDLAsxB34.jpg?width=108&crop=smart&auto=webp&s=6253b2f12b8fe6b19a8bb51e9ba6ad83f0b79bbb', 'width': 108}, {'height': 113, 'url': 'h... | ||
Want to gather sample database schemas in Postgres for text-to-SQL model | 1 | I plan to generate sample questions and their answer using GPT-4. Check the syntax correctness of the queries. Sample queries and check for logic correctness.
One way to go about getting database schemas can be to have it generated by GPT-4. I can provide the sector/ usecase and instruct it to generate the relevant sc... | 2023-10-30T09:23:01 | https://www.reddit.com/r/LocalLLaMA/comments/17jpdhc/want_to_gather_sample_database_schemas_in/ | Forsaken-Violinist27 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 17jpdhc | false | null | t3_17jpdhc | /r/LocalLLaMA/comments/17jpdhc/want_to_gather_sample_database_schemas_in/ | false | false | self | 1 | null |
LLM's in production hardware requirements | 15 | I've put together an article using some guesstimates of what it would be like for an enterprise to deploy LLM's on prem.
[https://bionic-gpt.com/blog/llm-hardware/](https://bionic-gpt.com/blog/llm-hardware/)
In short, I'm estimating $20,000 in hardware costs per 1000 users, minimum.
I'd be grateful is people could ... | 2023-10-30T08:55:30 | https://www.reddit.com/r/LocalLLaMA/comments/17jp02k/llms_in_production_hardware_requirements/ | purton_i | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 17jp02k | false | null | t3_17jp02k | /r/LocalLLaMA/comments/17jp02k/llms_in_production_hardware_requirements/ | false | false | self | 15 | {'enabled': False, 'images': [{'id': '00YvQD_fDOSKpCWSArEIFBrU0iCCA9zOclVHVDfbRrM', 'resolutions': [{'height': 68, 'url': 'https://external-preview.redd.it/b5X89xeJorW6TiYHNx0-7daLhtBC4zWKkDCbvwxbSQk.jpg?width=108&crop=smart&auto=webp&s=7879ad11766e7fbbeab58c1bdddde96f45d6dbd9', 'width': 108}, {'height': 136, 'url': 'h... |
Chat model unsupervised fine-tuning | 2 | Hello friends. Even though there were a few similar posts, I couldn't get the answer I wanted.
​
I have thousands of different pdf files. For example, the files can be book pdfs.
​
Pdf files are in raw form, not in question-answer format.
​
What I want to do is train a Llama model with raw da... | 2023-10-30T08:52:44 | https://www.reddit.com/r/LocalLLaMA/comments/17joyph/chat_model_unsupervised_finetuning/ | Typical_Time_208 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 17joyph | false | null | t3_17joyph | /r/LocalLLaMA/comments/17joyph/chat_model_unsupervised_finetuning/ | false | false | self | 2 | null |
Finally, a diffusion based LMM! | 154 | https://arxiv.org/abs/2310.17680
Ok, technically a tiny language model for now:
*Imagine a developer who can only change their last line of code, how often would they have to start writing a function from scratch before it is correct? Auto-regressive models for code generation from natural language have a similar lim... | 2023-10-30T07:45:24 | https://www.reddit.com/r/LocalLLaMA/comments/17jo3rb/finally_a_diffusion_based_lmm/ | BalorNG | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 17jo3rb | false | null | t3_17jo3rb | /r/LocalLLaMA/comments/17jo3rb/finally_a_diffusion_based_lmm/ | false | false | self | 154 | {'enabled': False, 'images': [{'id': 'q3evP6JeDpAC2MdSQHWYxnCYTqbJkElIQsLFqVSdkss', 'resolutions': [{'height': 63, 'url': 'https://external-preview.redd.it/izh8gZHY4FqZ1nwtU1N_TjtohUCNuvTyMn90toXda80.jpg?width=108&crop=smart&auto=webp&s=bc9575b410002edc2df3c5b5b0355fefedc7baa8', 'width': 108}, {'height': 126, 'url': 'h... |
LLMs and basic maths | 1 | I have been evaluating a number of maths models. One simple question I as is "what is 2 to the power of 4.1?" Almost every model butchers the answer. GPT-4 is the only one to get it correct out of the box. It looks like questions such as this are just not meant for LLMs. Without basic arithmetic, LLMs will not be parti... | 2023-10-30T07:31:52 | https://www.reddit.com/r/LocalLLaMA/comments/17jnxrd/llms_and_basic_maths/ | WorldlinessSpecific9 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 17jnxrd | false | null | t3_17jnxrd | /r/LocalLLaMA/comments/17jnxrd/llms_and_basic_maths/ | false | false | self | 1 | null |
AWS Inferentia | 3 | Hi everyone!
I am looking into using an AWS Inferentia instance for my model for inference.
Has anyone here used these? I am using llama-cpp-Python, will I be able to use it?
They are much cheaper than GPU’s, and I am not doing any training anyway, so I’d prefer to not have to rent GPU’s.
Has anyone here used it an... | 2023-10-30T07:26:48 | https://www.reddit.com/r/LocalLLaMA/comments/17jnve9/aws_inferentia/ | Slimxshadyx | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 17jnve9 | false | null | t3_17jnve9 | /r/LocalLLaMA/comments/17jnve9/aws_inferentia/ | false | false | self | 3 | null |
Recommendation on running local host LLMs | 2 | I’ve built a RAG system and want to use it with a group of friends. I’m planning on building/buying second hand server box. Any recommendations or builds on how I can host the endpoint and website? | 2023-10-30T06:59:11 | https://www.reddit.com/r/LocalLLaMA/comments/17jni05/recommendation_on_running_local_host_llms/ | ConceptGT | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 17jni05 | false | null | t3_17jni05 | /r/LocalLLaMA/comments/17jni05/recommendation_on_running_local_host_llms/ | false | false | self | 2 | null |
What are top open source projects in LLM space | 80 | I am aware of langchain, LlamaIndex and MetaGPT
https://github.com/geekan/MetaGPT
https://github.com/langchain-ai/langchain
https://github.com/run-llama/llama_index | 2023-10-30T05:59:48 | https://www.reddit.com/r/LocalLLaMA/comments/17jmpn8/what_are_top_open_source_projects_in_llm_space/ | ashutrv | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 17jmpn8 | false | null | t3_17jmpn8 | /r/LocalLLaMA/comments/17jmpn8/what_are_top_open_source_projects_in_llm_space/ | false | false | self | 80 | {'enabled': False, 'images': [{'id': 'j-s-4nkM__l557YzrA1dnD7EHR-lzdWovs-HWzho5S4', 'resolutions': [{'height': 54, 'url': 'https://external-preview.redd.it/0bfTp13DPX5Gt8P7ez1ZT1Is0IBaUfNgfGwlaT-A88g.jpg?width=108&crop=smart&auto=webp&s=86f5ef5a68e897e09f84f473d011b799999415c2', 'width': 108}, {'height': 108, 'url': 'h... |
Problem s with GPU acceleration in Llama.cpp | 1 | [removed] | 2023-10-30T05:45:17 | https://www.reddit.com/r/LocalLLaMA/comments/17jmij9/problem_s_with_gpu_acceleration_in_llamacpp/ | CheesekeeperZero | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 17jmij9 | false | null | t3_17jmij9 | /r/LocalLLaMA/comments/17jmij9/problem_s_with_gpu_acceleration_in_llamacpp/ | false | false | self | 1 | null |
Loading Airoboros 180b gguf 5_K_M error- byte not found in vocab: ' | 1 | Has anyone attempted to, or managed to, load the new Airoboros 180b model yet? I pulled down the ggufs from TheBloke this morning and just got it loaded up, but I hit that error on load and Llamacpp crashes. I haven't run into this before, so I'm not really sure if it just means there was an issue with the model, if ma... | 2023-10-30T05:17:35 | https://www.reddit.com/r/LocalLLaMA/comments/17jm4ie/loading_airoboros_180b_gguf_5_k_m_error_byte_not/ | SomeOddCodeGuy | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 17jm4ie | false | null | t3_17jm4ie | /r/LocalLLaMA/comments/17jm4ie/loading_airoboros_180b_gguf_5_k_m_error_byte_not/ | false | false | self | 1 | null |
Mistral NSFW Lora | 92 | Hi, I made NSFW Lora for mistral, if anyone is interested, please check it out and write as you like.
If you want to write a review on the Lora, I will be glad to see it.
\~200 stories were used, with a total weight of 50 MB.
Careful the model is very HORNY.
Each story was signed in TTG format, which means that yo... | 2023-10-30T04:30:53 | https://www.reddit.com/r/LocalLLaMA/comments/17jlen2/mistral_nsfw_lora/ | Terrible-Mongoose-84 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 17jlen2 | false | null | t3_17jlen2 | /r/LocalLLaMA/comments/17jlen2/mistral_nsfw_lora/ | false | false | nsfw | 92 | {'enabled': False, 'images': [{'id': 'GNAFwMxkiTOgcapf8K50HGHE-YJl2MeMpYsyvHiaKrc', 'resolutions': [{'height': 58, 'url': 'https://external-preview.redd.it/9W687rYu1mhkZlkBZ1R5HYqaAetJiU2iUQyIDqeukaM.jpg?width=108&crop=smart&auto=webp&s=4e987400ff0e0284c26886badb7e0adc9de74354', 'width': 108}, {'height': 116, 'url': 'h... |
Serverless Runpod question | 5 | If I have 1 model and ask it 10 separate questions say 1 hour apart from each other.
Is that the same as asking 10 models 1 question?
It just spins it up and shuts it down quickly per-question? | 2023-10-30T04:26:52 | https://www.reddit.com/r/LocalLLaMA/comments/17jlccn/serverless_runpod_question/ | parasocks | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 17jlccn | false | null | t3_17jlccn | /r/LocalLLaMA/comments/17jlccn/serverless_runpod_question/ | false | false | self | 5 | null |
offload_dir error message. If anyone can help it would mean the world. Thank you | 1 |
So I am recently new to downloading Llama 2 and I have been following this guide to install and fine-tune the model. I'm doing it on Google Colab and I have to stick to doing it on Google Colab because that's the only area I can.
I have been able to get through all the hiccups along the way and all I have had to do... | 2023-10-30T04:11:15 | https://www.reddit.com/r/LocalLLaMA/comments/17jl3gq/offload_dir_error_message_if_anyone_can_help_it/ | Head-Distribution-94 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 17jl3gq | false | null | t3_17jl3gq | /r/LocalLLaMA/comments/17jl3gq/offload_dir_error_message_if_anyone_can_help_it/ | false | false | 1 | null | |
Reuse existing Lora fine tune with different base? | 2 | For example, the llama 2 base model has the Airoboros Llama-2 chat fine tune for it.
Now if the base model weights are updated slightly, does it still work as expected when the same Airoboros Lora is applied on this new base? | 2023-10-30T03:50:12 | https://www.reddit.com/r/LocalLLaMA/comments/17jkqy9/reuse_existing_lora_fine_tune_with_different_base/ | xynyxyn | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 17jkqy9 | false | null | t3_17jkqy9 | /r/LocalLLaMA/comments/17jkqy9/reuse_existing_lora_fine_tune_with_different_base/ | false | false | self | 2 | null |
FP8-LM: Training FP8 Large Language Models | 23 | 2023-10-30T02:50:12 | https://arxiv.org/abs/2310.18313 | ninjasaid13 | arxiv.org | 1970-01-01T00:00:00 | 0 | {} | 17jjopb | false | null | t3_17jjopb | /r/LocalLLaMA/comments/17jjopb/fp8lm_training_fp8_large_language_models/ | false | false | 23 | {'enabled': False, 'images': [{'id': 'q3evP6JeDpAC2MdSQHWYxnCYTqbJkElIQsLFqVSdkss', 'resolutions': [{'height': 63, 'url': 'https://external-preview.redd.it/izh8gZHY4FqZ1nwtU1N_TjtohUCNuvTyMn90toXda80.jpg?width=108&crop=smart&auto=webp&s=bc9575b410002edc2df3c5b5b0355fefedc7baa8', 'width': 108}, {'height': 126, 'url': 'h... | ||
PockEngine: Sparse and Efficient Fine-tuning in a Pocket | 33 | 2023-10-30T02:23:24 | https://arxiv.org/abs/2310.17752 | ninjasaid13 | arxiv.org | 1970-01-01T00:00:00 | 0 | {} | 17jj6fq | false | null | t3_17jj6fq | /r/LocalLLaMA/comments/17jj6fq/pockengine_sparse_and_efficient_finetuning_in_a/ | false | false | 33 | {'enabled': False, 'images': [{'id': 'q3evP6JeDpAC2MdSQHWYxnCYTqbJkElIQsLFqVSdkss', 'resolutions': [{'height': 63, 'url': 'https://external-preview.redd.it/izh8gZHY4FqZ1nwtU1N_TjtohUCNuvTyMn90toXda80.jpg?width=108&crop=smart&auto=webp&s=bc9575b410002edc2df3c5b5b0355fefedc7baa8', 'width': 108}, {'height': 126, 'url': 'h... | ||
Open Source Open Night! AI standup comedy! | 32 | Benchmarks are one thing, but which LLM can write a decent joke? It's standup comedy for LLMs. Submit the best joke your favorite LLM has told you
_______RULES
Jokes must be written by your AI. Don't hurt your own feelings and lose to an AI in humor.
Keep it within all applicable community guidelines. Don't get thi... | 2023-10-30T01:43:00 | Future_Might_8194 | i.redd.it | 1970-01-01T00:00:00 | 0 | {} | 17jidvh | false | null | t3_17jidvh | /r/LocalLLaMA/comments/17jidvh/open_source_open_night_ai_standup_comedy/ | false | false | 32 | {'enabled': True, 'images': [{'id': 'WWGXKEFXSEKoFEuiTDh6fvyuMwAMkJBr20u5yACORkw', 'resolutions': [{'height': 56, 'url': 'https://preview.redd.it/z81ia5smv8xb1.jpg?width=108&crop=smart&auto=webp&s=5261189ae2afb353d775a42a53b25055a7ec5900', 'width': 108}, {'height': 113, 'url': 'https://preview.redd.it/z81ia5smv8xb1.jpg... | ||
Today I released Akins 3B. | 55 | Today I released [Akins 3B](https://huggingface.co/acrastt/Akins-3B).
[Akins 3B](https://huggingface.co/acrastt/Akins-3B) is [StableLM 3B 4E1T](https://huggingface.co/stabilityai/stablelm-3b-4e1t)(Licensed under [CC BY-SA 4.0](https://creativecommons.org/licenses/by-sa/4.0/).) instruction tuned on [Claude Multiround C... | 2023-10-30T01:42:47 | https://www.reddit.com/r/LocalLLaMA/comments/17jidpg/today_i_released_akins_3b/ | bot-333 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 17jidpg | false | null | t3_17jidpg | /r/LocalLLaMA/comments/17jidpg/today_i_released_akins_3b/ | false | false | self | 55 | {'enabled': False, 'images': [{'id': 'QpCX81q_9d-EuG7jelQ00HcAN9KZSyIEhi1TLcb7Cj8', 'resolutions': [{'height': 58, 'url': 'https://external-preview.redd.it/wcQd2vG68VHRQVr4NqqdcZAq8VahZGR85P7B75OJeDw.jpg?width=108&crop=smart&auto=webp&s=27716126f51480c72dff78b30299870e40f20434', 'width': 108}, {'height': 116, 'url': 'h... |
Tested: Batched decoding on CPU | 21 | Ever since the medusa models were released, I've been wondering if speculative sampling can run effectively on CPU only. Modern GPUs already provide fast t/s, so the speedup is more exciting when running on low bandwidth GPUs, SoCs, and CPUs.
And that depends on batched decoding working correctly.
So I did tests with ... | 2023-10-30T01:18:02 | https://www.reddit.com/r/LocalLLaMA/comments/17jhwpa/tested_batched_decoding_on_cpu/ | Aaaaaaaaaeeeee | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 17jhwpa | false | null | t3_17jhwpa | /r/LocalLLaMA/comments/17jhwpa/tested_batched_decoding_on_cpu/ | false | false | self | 21 | null |
Any LLMs that aren't completely neutered and can be a little edgy? | 1 | [removed] | 2023-10-30T00:15:27 | https://www.reddit.com/r/LocalLLaMA/comments/17jgopy/any_llms_that_arent_completely_neutered_and_can/ | PM_ME_YOUR_LLMS | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 17jgopy | false | null | t3_17jgopy | /r/LocalLLaMA/comments/17jgopy/any_llms_that_arent_completely_neutered_and_can/ | false | false | self | 1 | null |
Llama ask you a question, what is speechless? | 0 | What are the speechless models? I see them popping up left and right. Are they for a specific purpose? Is that just a model name? I am at a loss. I am...I can't find the words....how do you say it? | 2023-10-29T23:58:30 | https://www.reddit.com/r/LocalLLaMA/comments/17jgc8d/llama_ask_you_a_question_what_is_speechless/ | Future_Might_8194 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 17jgc8d | false | null | t3_17jgc8d | /r/LocalLLaMA/comments/17jgc8d/llama_ask_you_a_question_what_is_speechless/ | false | false | self | 0 | null |
How LLMs are changing search | 0 | 2023-10-29T23:26:03 | https://orangutanai.substack.com/p/how-llms-are-changing-search | firef1y1 | orangutanai.substack.com | 1970-01-01T00:00:00 | 0 | {} | 17jfnyz | false | null | t3_17jfnyz | /r/LocalLLaMA/comments/17jfnyz/how_llms_are_changing_search/ | false | false | 0 | {'enabled': False, 'images': [{'id': '3AOl-pLK-HCRtnZ4eR0TguUzFY-hGErZjpowCXYg36Y', 'resolutions': [{'height': 108, 'url': 'https://external-preview.redd.it/MRqFX7agBeCAzumcg4GoRIe2vHQ5g603buQSJW0vfzI.jpg?width=108&crop=smart&auto=webp&s=7f404778f6a2578347c515fe66a0be7c776c69a9', 'width': 108}], 'source': {'height': 14... | ||
Explore the Best iPhone ChatGPT App for Seamless Communication - phonetui | 1 | 2023-10-29T22:24:36 | https://www.phonetui.com/2023/10/explore-best-iphone-chatgpt-app-for.html | FrederickJones7 | phonetui.com | 1970-01-01T00:00:00 | 0 | {} | 17jedr5 | false | null | t3_17jedr5 | /r/LocalLLaMA/comments/17jedr5/explore_the_best_iphone_chatgpt_app_for_seamless/ | false | false | 1 | {'enabled': False, 'images': [{'id': 'u5fmLJObf__hkcXjBET6UK0dlxPHnaTnQzoBV9dtw_c', 'resolutions': [{'height': 60, 'url': 'https://external-preview.redd.it/tDOxRrpOob9YQNVmvjQUDlrpC8JLqm_Pqbcodp450I0.jpg?width=108&crop=smart&auto=webp&s=a809450abab3bec4b134febb50db9bc85beb0102', 'width': 108}, {'height': 121, 'url': 'h... |
Subsets and Splits
No community queries yet
The top public SQL queries from the community will appear here once available.