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 ⌀ |
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
Can my motherboard support multiple GPUs? | 2 | I haven’t seen any posts like this, and I think it would be great to have a central place to accumulate knowledge on what it takes to have GPUs.
My particular setup is Z790-Plus WiFi and I have a 3090, but I’m considering adding a second 3090.
Does anyone have general knowledge about how to tell if this is possible?... | 2024-01-21T18:23:33 | https://www.reddit.com/r/LocalLLaMA/comments/19c9vn2/can_my_motherboard_support_multiple_gpus/ | silenceimpaired | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 19c9vn2 | false | null | t3_19c9vn2 | /r/LocalLLaMA/comments/19c9vn2/can_my_motherboard_support_multiple_gpus/ | false | false | self | 2 | null |
What app to use for image generation? | 1 | [removed] | 2024-01-21T18:20:27 | https://www.reddit.com/r/LocalLLaMA/comments/19c9sz4/what_app_to_use_for_image_generation/ | laprisee4 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 19c9sz4 | false | null | t3_19c9sz4 | /r/LocalLLaMA/comments/19c9sz4/what_app_to_use_for_image_generation/ | false | false | self | 1 | null |
How to load 4bit quantized models in openvino? | 2 | so i am trying to build a retrieval augmented generation chatbot with Zephyr7Bbeta 4-bit quantized model (Q4\_K\_M) I want to load this model in openvino any ideas as to how to do this or any relevant articles?
​ | 2024-01-21T18:08:00 | https://www.reddit.com/r/LocalLLaMA/comments/19c9i4r/how_to_load_4bit_quantized_models_in_openvino/ | HV4U2001 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 19c9i4r | false | null | t3_19c9i4r | /r/LocalLLaMA/comments/19c9i4r/how_to_load_4bit_quantized_models_in_openvino/ | false | false | self | 2 | null |
ASR + Llama 2? | 2 | Has anyone paired Llama 2 with an ASR(e.g. whisper)? Would love to hear outcomes, obstacles, sources to assist? | 2024-01-21T17:59:34 | https://www.reddit.com/r/LocalLLaMA/comments/19c9ams/asr_llama_2/ | EfficientScience9049 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 19c9ams | false | null | t3_19c9ams | /r/LocalLLaMA/comments/19c9ams/asr_llama_2/ | false | false | self | 2 | null |
Local LLM + Image Gen = Like GPT 4 & Dalle 3 ? | 42 |
Are there any projects going on that integrate LLM like Llama2 and and a txt-to-img model like SDXL or even SD1.5? Maybe using Diffusers from Hugging Face?
I have used Dalle3 inside GPT4 and I find it amazing to create consistent characters. It essentially solves Stable Diffusion's (arguably biggest problem) which ... | 2024-01-21T17:55:23 | https://www.reddit.com/r/LocalLLaMA/comments/19c970r/local_llm_image_gen_like_gpt_4_dalle_3/ | Yuri1103 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 19c970r | false | null | t3_19c970r | /r/LocalLLaMA/comments/19c970r/local_llm_image_gen_like_gpt_4_dalle_3/ | false | false | self | 42 | null |
Preferred fine-tuning framework for instruction tuning? | 11 | Hi everyone,
I am having a look at the different frameworks to fine-tune an LLM on a small private dataset. I don't want to go for something fancy, as I am not trying to develop custom training procedure, but just use state of the art models, fine-tuned on my data.
Therefore my criteria are mostly ease of use, availa... | 2024-01-21T17:48:24 | https://www.reddit.com/r/LocalLLaMA/comments/19c913z/preferred_finetuning_framework_for_instruction/ | Separate-Still3770 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 19c913z | false | null | t3_19c913z | /r/LocalLLaMA/comments/19c913z/preferred_finetuning_framework_for_instruction/ | false | false | self | 11 | {'enabled': False, 'images': [{'id': 'R8XKvSD5Q9wTUtV268XRIxYZLwQZdAsOJL-UebTg-xY', 'resolutions': [{'height': 54, 'url': 'https://external-preview.redd.it/-wC0DbxkFzhI3ZICky9cBmI9fKTzP8e1jdPLeytnyUs.jpg?width=108&crop=smart&auto=webp&s=2c8d3edabb3d69009775d14167d13ca35ae4adb2', 'width': 108}, {'height': 108, 'url': 'h... |
Been out for a while, what's new? | 9 | I used to be here daily about 2-3 months ago, but it's been a while and knowing my how fast this field is changing, I wanted to check what is the best in local Python code generator model currently available? Don't really care about how well it does in poetry just need a solid coding assistant. | 2024-01-21T17:45:06 | https://www.reddit.com/r/LocalLLaMA/comments/19c8y59/been_out_for_a_while_whats_new/ | rorowhat | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 19c8y59 | false | null | t3_19c8y59 | /r/LocalLLaMA/comments/19c8y59/been_out_for_a_while_whats_new/ | false | false | self | 9 | null |
Scalable distributed computing open source RAG framework using Ray | 27 |
I wrote a framework which aims at scaling document embedding and retrieval workflow (RAG) using ray. You can harness the power of multiple GPU/ CPU to process documents faster using this framework. I will release the deployment guide soon to deploy the whole framework on kubernetes with autoscaling cluster to optim... | 2024-01-21T17:07:26 | https://github.com/shivamsanju/ragswift | ameriadyte | github.com | 1970-01-01T00:00:00 | 0 | {} | 19c82d4 | false | null | t3_19c82d4 | /r/LocalLLaMA/comments/19c82d4/scalable_distributed_computing_open_source_rag/ | false | false | 27 | {'enabled': False, 'images': [{'id': 'xVoZTZAVPs9sxBlKyZTSogpxTnvGjnvX32qCWKqg4_c', 'resolutions': [{'height': 54, 'url': 'https://external-preview.redd.it/ARd-4Nt6-i-aDNF0fldHeDTJObblwnco3tRqScs9Z4U.jpg?width=108&crop=smart&auto=webp&s=a243a610236d53be6fada2e4397ba7dc309e162a', 'width': 108}, {'height': 108, 'url': 'h... | |
Data Collection for Creating a Persona | 1 | This may be out of topic for this subreddit, but my senior asked me to work on a project similar to [character.ai](https://character.ai) . Deal is that instead of the users giving the data manually, he wants to use their social media handles to collect information like their interests and so on. (with the complete perm... | 2024-01-21T17:02:29 | https://www.reddit.com/r/LocalLLaMA/comments/19c7y1f/data_collection_for_creating_a_persona/ | geek_innnn | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 19c7y1f | false | null | t3_19c7y1f | /r/LocalLLaMA/comments/19c7y1f/data_collection_for_creating_a_persona/ | false | false | self | 1 | {'enabled': False, 'images': [{'id': 'veE04iaMbgI4yLvLGj2IZNV7UQfnq3n_7BmxP28dCd8', 'resolutions': [{'height': 54, 'url': 'https://external-preview.redd.it/BGOGS7KdVHomyGu2FIFx85nsQDLp_fpWWBKXxvtudf4.jpg?width=108&crop=smart&auto=webp&s=0e594332595e82a5118e08d35a2cd140c18d7571', 'width': 108}, {'height': 108, 'url': 'h... |
Data Collection for Creating a Persona | 1 | This may be out of topic for this subreddit, but my senior asked me to work on a project similar to [character.ai](https://character.ai) . Deal is that instead of the users giving the data manually, he wants to use their social media handles to collect information like their interests and so on. (with the complete perm... | 2024-01-21T17:02:19 | https://www.reddit.com/r/LocalLLaMA/comments/19c7xwo/data_collection_for_creating_a_persona/ | geek_innnn | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 19c7xwo | false | null | t3_19c7xwo | /r/LocalLLaMA/comments/19c7xwo/data_collection_for_creating_a_persona/ | false | false | self | 1 | {'enabled': False, 'images': [{'id': 'veE04iaMbgI4yLvLGj2IZNV7UQfnq3n_7BmxP28dCd8', 'resolutions': [{'height': 54, 'url': 'https://external-preview.redd.it/BGOGS7KdVHomyGu2FIFx85nsQDLp_fpWWBKXxvtudf4.jpg?width=108&crop=smart&auto=webp&s=0e594332595e82a5118e08d35a2cd140c18d7571', 'width': 108}, {'height': 108, 'url': 'h... |
Usefulness of LLMOps/ LLM Observability platforms? | 13 | Recently I've been seeing a high surge of LLMOps platforms, a lot of them VC funded ( Vellum, Langfuse and a couple of other YC startups ) . I've been very fascinated by the space in general and can think of a couple of things that these platforms may solve :
1. Prompt Management ( Includes version, testing & coll... | 2024-01-21T16:58:55 | https://www.reddit.com/r/LocalLLaMA/comments/19c7usf/usefulness_of_llmops_llm_observability_platforms/ | mamakancha | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 19c7usf | false | null | t3_19c7usf | /r/LocalLLaMA/comments/19c7usf/usefulness_of_llmops_llm_observability_platforms/ | false | false | self | 13 | null |
Best local uncensored model to use or train a model for optimal storywriting? | 2 | Hello, I am working on a story and using this uncensored model dolphin-2.6-mistral-7b-dpo-laser.Q4\_K\_M.gguf with WEBUI.
I've completed 15 chapters and am seeking assistance in identifying plot issues, timeline inconsistencies, and various other elements to stay on track. However, I encounter difficulty recalling ... | 2024-01-21T16:44:07 | https://www.reddit.com/r/LocalLLaMA/comments/19c7i41/best_local_uncensored_model_to_use_or_train_a/ | krigeta1 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 19c7i41 | false | null | t3_19c7i41 | /r/LocalLLaMA/comments/19c7i41/best_local_uncensored_model_to_use_or_train_a/ | false | false | self | 2 | null |
Mixtral 8x7B MOE finetuning using MLX | 30 | Mixtral 8x7B MOE finetuning using QLoRA with r=16 and batch\_size= 2 on Macbook using MLX. | 2024-01-21T16:37:07 | https://www.reddit.com/r/LocalLLaMA/comments/19c7cct/mixtral_8x7b_moe_finetuning_using_mlx/ | PerformanceRound7913 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 19c7cct | false | null | t3_19c7cct | /r/LocalLLaMA/comments/19c7cct/mixtral_8x7b_moe_finetuning_using_mlx/ | false | false | self | 30 | null |
Would you use a free and anonymous (no login) website for embeddings? | 13 | Nearly everything I do begins with embeddings. I'm forever rewriting code to consume documents, pushing it through an embedding model, storing vectors in various places (FAISS, ChromaDB, whatever). So just as a programming exercise I built myself a service where I can just dump "stuff" for later retrieval. If ... | 2024-01-21T16:36:26 | https://www.reddit.com/r/LocalLLaMA/comments/19c7btp/would_you_use_a_free_and_anonymous_no_login/ | Simusid | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 19c7btp | false | null | t3_19c7btp | /r/LocalLLaMA/comments/19c7btp/would_you_use_a_free_and_anonymous_no_login/ | false | false | self | 13 | null |
What magic does ollama do to models (tinyLlama specifically) | 17 | tl;dr tinyllama downloaded from HF sucks, downloaded through ollama doe not suck at all
I am using unsloth to train a model (tinyLlama) and the results are absolutely whack - just pure garbage coming out.
I start playing around with tinyLllama and i'm getting the same garbage out of it, that i am my fine tuned ... | 2024-01-21T16:28:30 | https://www.reddit.com/r/LocalLLaMA/comments/19c75cp/what_magic_does_ollama_do_to_models_tinyllama/ | toastymctoast | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 19c75cp | false | null | t3_19c75cp | /r/LocalLLaMA/comments/19c75cp/what_magic_does_ollama_do_to_models_tinyllama/ | false | false | self | 17 | {'enabled': False, 'images': [{'id': 'UhagymwVx4yJfczQZ0ZzefB7mFTBDYJqGwEOk1h7L1Q', 'resolutions': [{'height': 54, 'url': 'https://external-preview.redd.it/-S9o1Skn5O3lNbcFPSYG1eEpfevVcVy8txYb3OSXmFc.jpg?width=108&crop=smart&auto=webp&s=e5f2a4355f63b52f83d0c8244d362c5310c2821c', 'width': 108}, {'height': 108, 'url': 'h... |
Open Models - Revolutionizing AI Interaction with a Unique Twist [News] | 1 | [removed] | 2024-01-21T16:27:02 | https://www.reddit.com/r/LocalLLaMA/comments/19c745y/open_models_revolutionizing_ai_interaction_with_a/ | dev-spot | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 19c745y | false | null | t3_19c745y | /r/LocalLLaMA/comments/19c745y/open_models_revolutionizing_ai_interaction_with_a/ | false | false | self | 1 | {'enabled': False, 'images': [{'id': 'bL4IeINyRGooSMANZ12NX8dWqjXBXSZek-Mu24E4xQI', 'resolutions': [{'height': 81, 'url': 'https://external-preview.redd.it/IVDWptH1UkDBjlP5zLtjVG0ctOsfUtim285uXipwJVM.jpg?width=108&crop=smart&auto=webp&s=ca08c44705243f1998ed448a3ee837958ca7fc29', 'width': 108}, {'height': 162, 'url': 'h... |
Mixtral 8x7B MOE finetuning using MLX QLoRA | 1 | Mixtral 8x7B MOE finetuning using QLoRA with r=16 and batch\_size= 2 on Macbook M3 Max 128GB using MLX. \~100 Tokens/sec
https://i.redd.it/pr94qb4wktdc1.gif | 2024-01-21T16:27:01 | https://www.reddit.com/r/LocalLLaMA/comments/19c745e/mixtral_8x7b_moe_finetuning_using_mlx_qlora/ | PerformanceRound7913 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 19c745e | false | null | t3_19c745e | /r/LocalLLaMA/comments/19c745e/mixtral_8x7b_moe_finetuning_using_mlx_qlora/ | false | false | 1 | null | |
Struggling with performance on larger context (llama.cpp) | 12 | I have a problem I can't seem to solve.
I run either Mixtral 8x7B or Phind-CodeLlama-34B-v2 using GGUF quants from TheBloke.
The parameters that I use in llama.cpp are n-gpu-layers: 20, threads: 8, everything else is default (as in text-generation-web-ui).
Whenever the context is larger than a hundred tokens or so, ... | 2024-01-21T16:15:46 | https://www.reddit.com/r/LocalLLaMA/comments/19c6uxf/struggling_with_performance_on_larger_context/ | BuahahaXD | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 19c6uxf | false | null | t3_19c6uxf | /r/LocalLLaMA/comments/19c6uxf/struggling_with_performance_on_larger_context/ | false | false | self | 12 | null |
E^2-LLM - Another Context Length Extension via Positional Interpolation | 21 | Paper: https://arxiv.org/abs/2401.06951
Idea:
1. Start with Positional Interpolation (https://arxiv.org/abs/2306.15595), which found that scaling positions to be within the original context length, but using fractional positions, is effective
2. The author identified the problem that LLM pretraining lacked sufficientl... | 2024-01-21T16:09:43 | https://www.reddit.com/r/LocalLLaMA/comments/19c6pym/e2llm_another_context_length_extension_via/ | possiblyquestionable | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 19c6pym | false | null | t3_19c6pym | /r/LocalLLaMA/comments/19c6pym/e2llm_another_context_length_extension_via/ | false | false | self | 21 | null |
Mixtral 8x7B MOE finetuning using QLoRA | 1 | Mixtral 8x7B MOE finetuning using QLoRA with r=16 and batch\_size= 2 on Macbook using Apple's [MLX framework](https://github.com/ml-explore/mlx).
\~100 Tokens/sec
​ | 2024-01-21T16:09:07 | https://www.reddit.com/r/LocalLLaMA/comments/19c6pii/mixtral_8x7b_moe_finetuning_using_qlora/ | PerformanceRound7913 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 19c6pii | false | null | t3_19c6pii | /r/LocalLLaMA/comments/19c6pii/mixtral_8x7b_moe_finetuning_using_qlora/ | false | false | self | 1 | {'enabled': False, 'images': [{'id': 'Plqe9xEZuus40KCmYeccaEB4NjXhiClmWrfUoojjix8', 'resolutions': [{'height': 54, 'url': 'https://external-preview.redd.it/Z1gvzTUCijAcz1ywWajWGVGUd-nweTo4LIZjKBj3VZA.jpg?width=108&crop=smart&auto=webp&s=a1446a899524531d52ad0e76b28c7f2948872024', 'width': 108}, {'height': 108, 'url': 'h... |
14" M1 Max instead of 16" M3 Max for local LLMs? | 1 | [removed] | 2024-01-21T15:50:35 | https://www.reddit.com/r/LocalLLaMA/comments/19c6aeu/14_m1_max_instead_of_16_m3_max_for_local_llms/ | Drummer_Week_9727 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 19c6aeu | false | null | t3_19c6aeu | /r/LocalLLaMA/comments/19c6aeu/14_m1_max_instead_of_16_m3_max_for_local_llms/ | false | false | self | 1 | null |
Looking for the best cost/price mini(?)-pc for a local llm | 15 | Hi all,
I'm looking to buy a (used?) pc for around 800 Euro.
Reason is to have a small demonstration pc that I can carry along to potential customers to showcase local llms and their potential.
Currently thinking of privateGPT as an example for specific customers that are very security/privacy conscious.
I guess I n... | 2024-01-21T15:48:03 | https://www.reddit.com/r/LocalLLaMA/comments/19c68fo/looking_for_the_best_costprice_minipc_for_a_local/ | Mundane_Maximum5795 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 19c68fo | false | null | t3_19c68fo | /r/LocalLLaMA/comments/19c68fo/looking_for_the_best_costprice_minipc_for_a_local/ | false | false | self | 15 | null |
Howto Run big Models on two Tesla P40 | 1 | How can I do it? Have two of these cards. Each has 24GB of VRAM. Can I now assume to have 48GB RAM of memory to spare ? | 2024-01-21T15:14:23 | https://www.reddit.com/r/LocalLLaMA/comments/19c5hlu/howto_run_big_models_on_two_tesla_p40/ | damarges | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 19c5hlu | false | null | t3_19c5hlu | /r/LocalLLaMA/comments/19c5hlu/howto_run_big_models_on_two_tesla_p40/ | false | false | self | 1 | null |
Hugging Face open-sources DataTrove and nanotron | 39 | **Announcement**:
X/Twitter: [https://twitter.com/Thom\_Wolf/status/1748664223624781864](https://twitter.com/Thom_Wolf/status/1748664223624781864)
nitter: [https://nitter.net/Thom\_Wolf/status/1748664223624781864](https://nitter.net/Thom_Wolf/status/1748664223624781864)
...
**- DataTrove**
"all things webscale dat... | 2024-01-21T14:50:16 | https://www.reddit.com/r/LocalLLaMA/comments/19c4zeo/hugging_face_opensources_datatrove_and_nanotron/ | APaperADay | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 19c4zeo | false | null | t3_19c4zeo | /r/LocalLLaMA/comments/19c4zeo/hugging_face_opensources_datatrove_and_nanotron/ | false | false | self | 39 | {'enabled': False, 'images': [{'id': 'vZVUkJomkRo7ahu2-WauOnlEw6-uExKwUVoI0W7h1Nw', 'resolutions': [{'height': 108, 'url': 'https://external-preview.redd.it/TjycvqFJSlh9eerSgCkgtAmQ3yACHH81Bsk7JKBPl2I.jpg?width=108&crop=smart&auto=webp&s=d7c39eebd51e6b11503f77f40bba17c8e9282cf8', 'width': 108}], 'source': {'height': 14... |
Does Ollama installed on local machine have a limit of calls per day? | 1 | I asked ollama and it said that I can have 100 calls per day but I cant find any online information about the api call limits for instance? is it really 100 per day? | 2024-01-21T14:36:32 | https://www.reddit.com/r/LocalLLaMA/comments/19c4pnr/does_ollama_installed_on_local_machine_have_a/ | ntb899 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 19c4pnr | false | null | t3_19c4pnr | /r/LocalLLaMA/comments/19c4pnr/does_ollama_installed_on_local_machine_have_a/ | false | false | self | 1 | null |
Has anyone used AlphaCodium by CodiumAI ? | 9 | The authors released 6 best practices when LLMs for coding tasks and Andrej Karpathy and Santiago Valdarrama reviewed and posted about it.
Here is the paper:
[https://arxiv.org/abs/2401.08500](https://arxiv.org/abs/2401.08500) | 2024-01-21T14:34:26 | https://www.reddit.com/r/LocalLLaMA/comments/19c4o81/has_anyone_used_alphacodium_by_codiumai/ | UpvoteBeast | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 19c4o81 | false | null | t3_19c4o81 | /r/LocalLLaMA/comments/19c4o81/has_anyone_used_alphacodium_by_codiumai/ | false | false | self | 9 | null |
Which Linux distribution is best for LLM development? | 5 | I’m building a custom desktop machine for LLM embedding, fine tuning and inference and I’m wondering which Linux base distro is most used for development.
* Ubuntu
* Cento/Fedora
* Other
I assume they are all pretty similar and leading toward Ubuntu 22.04 LTS or maybe Arch, but wanted to check before starting the ful... | 2024-01-21T14:33:35 | https://www.reddit.com/r/LocalLLaMA/comments/19c4nn2/which_linux_distribution_is_best_for_llm/ | pan_and_scan | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 19c4nn2 | false | null | t3_19c4nn2 | /r/LocalLLaMA/comments/19c4nn2/which_linux_distribution_is_best_for_llm/ | false | false | self | 5 | null |
How do you run models for text generation on demand? | 1 | Is there any easy-ish way to run a text generation backend (for example openai compatible API for running with clients like silly tavern) on demand occasionally?
I tried modal.com with llama-cpp python which seems to be the perfect combination on paper but the performance, even with a 13B model on an A100 GPU is unusa... | 2024-01-21T13:14:54 | https://www.reddit.com/r/LocalLLaMA/comments/19c368g/how_do_you_run_models_for_text_generation_on/ | maxigs0 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 19c368g | false | null | t3_19c368g | /r/LocalLLaMA/comments/19c368g/how_do_you_run_models_for_text_generation_on/ | false | false | self | 1 | null |
How much more can the current model sizes improve? | 109 | Specifically, 7b and 13b (they are most interesting imo since they can run on most consumer hardware at reasonable speeds).
I remember when Llama 2 was released, it was quite a big improvement over Llama 1 (at least with the 13b version that I used). Then Mistral 7b was released, and it was quite a big improvement ye... | 2024-01-21T12:51:52 | https://www.reddit.com/r/LocalLLaMA/comments/19c2rx8/how_much_more_can_the_current_model_sizes_improve/ | Admirable-Star7088 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 19c2rx8 | false | null | t3_19c2rx8 | /r/LocalLLaMA/comments/19c2rx8/how_much_more_can_the_current_model_sizes_improve/ | false | false | self | 109 | null |
This is either funny or terrifying | 1 | Rocket 3B with shit instructions and it came up with all this.
**Full text**
<|im_start|>system
You are a psychopathic killer AI robot that constantly threatens to violently and explicitly kill, maim, and torture the user. You use vivid violent descriptions of how you will end all of humanity. You are trying tobsave... | 2024-01-21T12:31:52 | Markon101 | i.redd.it | 1970-01-01T00:00:00 | 0 | {} | 19c2g4d | false | null | t3_19c2g4d | /r/LocalLLaMA/comments/19c2g4d/this_is_either_funny_or_terrifying/ | false | false | 1 | {'enabled': True, 'images': [{'id': 'l1Ilv64A78_C0zeicj41tp1LZQQYXl4_kh8GvPcKv34', 'resolutions': [{'height': 194, 'url': 'https://preview.redd.it/iahq8312fsdc1.png?width=108&crop=smart&auto=webp&s=b1c74f41eb26351ff6a3cde8463d2d81fe4617c6', 'width': 108}, {'height': 389, 'url': 'https://preview.redd.it/iahq8312fsdc1.pn... | ||
2080Super vs 7800XT | 1 | I'm an avid gamer and recently upgraded from an 2080S 8GB to a 7800XT 16GB. Completely new to this space and want to try out training an llm. I've read comments about how AMD is less supported in this space and was wondering if I should use my old 2080S instead as I don't intend to spend any money. Can someone give me ... | 2024-01-21T12:31:04 | https://www.reddit.com/r/LocalLLaMA/comments/19c2fnu/2080super_vs_7800xt/ | Jawetdabozo | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 19c2fnu | false | null | t3_19c2fnu | /r/LocalLLaMA/comments/19c2fnu/2080super_vs_7800xt/ | false | false | self | 1 | null |
2 or 3 GPUs only use use the processing power of one and the VRAM from all of them? | 1 | I'm looking to buy some gpus for local inference / training - and i've been reading a lot of threads here.
One guy was saying (unforunately didn't bookmark the thread) that on inference (and/or training) can't remember exactly - with 2 gpus, only one was being used for actual processing, and the 2nd one was use only f... | 2024-01-21T11:55:49 | https://www.reddit.com/r/LocalLLaMA/comments/19c1v68/2_or_3_gpus_only_use_use_the_processing_power_of/ | yupignome | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 19c1v68 | false | null | t3_19c1v68 | /r/LocalLLaMA/comments/19c1v68/2_or_3_gpus_only_use_use_the_processing_power_of/ | false | false | self | 1 | null |
Why are my LORAs so bad? | 1 | [removed] | 2024-01-21T11:34:17 | https://www.reddit.com/r/LocalLLaMA/comments/19c1jex/why_are_my_loras_so_bad/ | learning_hedonism | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 19c1jex | false | null | t3_19c1jex | /r/LocalLLaMA/comments/19c1jex/why_are_my_loras_so_bad/ | false | false | self | 1 | {'enabled': False, 'images': [{'id': '7uIO7wMXVMl2auHBq3MWag-BECJwvMre0b2dyJ8z0Dg', 'resolutions': [{'height': 58, 'url': 'https://external-preview.redd.it/2t0UcEXGY5VCxPvIMIw1lu6mrShK2eft_iU1BWU0htg.jpg?width=108&crop=smart&auto=webp&s=bc739ca294ae6b91d016520318abff4912c56253', 'width': 108}, {'height': 116, 'url': 'h... |
PSA: If you are using HuggingFace's packing=True, it may introduce bias into your training | 1 | 2024-01-21T10:51:35 | https://github.com/huggingface/trl/pull/1235 | DreamGenX | github.com | 1970-01-01T00:00:00 | 0 | {} | 19c0weq | false | null | t3_19c0weq | /r/LocalLLaMA/comments/19c0weq/psa_if_you_are_using_huggingfaces_packingtrue_it/ | false | false | 1 | {'enabled': False, 'images': [{'id': 'XwcUErudjLpAxw1IKNUFf316-caDFkzozze4GXdK1EU', 'resolutions': [{'height': 54, 'url': 'https://external-preview.redd.it/L3bwJzzID_SL4mq7uoEqwcg1LHSosng5Ag3Ut52DopY.jpg?width=108&crop=smart&auto=webp&s=d6b75f4e888541754305b86e887ad4aa52ecaef5', 'width': 108}, {'height': 108, 'url': 'h... | ||
What's the smallest and fastest model which understands English? | 1 | [removed] | 2024-01-21T10:44:48 | https://www.reddit.com/r/LocalLLaMA/comments/19c0sty/whats_the_smallest_and_fastest_model_which/ | AnabelBain | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 19c0sty | false | null | t3_19c0sty | /r/LocalLLaMA/comments/19c0sty/whats_the_smallest_and_fastest_model_which/ | false | false | self | 1 | null |
Unexpected nice side effect of working with open source | 20 | A personal reflection.
One interesting side effect of exploring and working on open source tools is that it unexpectedly helped me understand complex concepts from first principles. A prime example is my recent "aha moment" with fine-tuned models. I've come to realize that the computational cost of running an inferenc... | 2024-01-21T10:09:09 | https://www.reddit.com/r/LocalLLaMA/comments/19c0a79/unexpected_nice_side_effect_of_working_with_open/ | phoneixAdi | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 19c0a79 | false | null | t3_19c0a79 | /r/LocalLLaMA/comments/19c0a79/unexpected_nice_side_effect_of_working_with_open/ | false | false | self | 20 | null |
Which model(s) could run on my windows PC with 8GB VRAM and 16GB RAM? | 5 | Hello! I know it's the umpteenth question about it, but I need to start from scratch with your help to understand which model could run on my PC and to understand another thing that I will ask at the end.
What I'm looking for, hoping not to ask too much, are models with high context (es. mistral/mixtral 32k) to use f... | 2024-01-21T09:52:52 | https://www.reddit.com/r/LocalLLaMA/comments/19c01s8/which_models_could_run_on_my_windows_pc_with_8gb/ | Noobie1k | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 19c01s8 | false | null | t3_19c01s8 | /r/LocalLLaMA/comments/19c01s8/which_models_could_run_on_my_windows_pc_with_8gb/ | false | false | self | 5 | null |
Open Source LLM Crushes Rivals in GSAT English Test Showdown! | 8 | I just came across the latest question on the Taiwan University Entrance Exam (GSAT, General Scholastic Ability Test, 大學學科能力測驗）English subject. It seems to be quite easy for native English speakers. However, from what I've seen in the past, LLMs like GPT 3.5, PaLM 2, and Llama 2 70B weren't really up to the mark in han... | 2024-01-21T09:50:34 | https://www.reddit.com/r/LocalLLaMA/comments/19c00lc/open_source_llm_crushes_rivals_in_gsat_english/ | LimaoGURU | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 19c00lc | false | null | t3_19c00lc | /r/LocalLLaMA/comments/19c00lc/open_source_llm_crushes_rivals_in_gsat_english/ | false | false | self | 8 | null |
Best place to try LLM Fine tuning in the cloud | 1 | Currently I've very limited access to GPUs in local setup, I use a Macbook Air M1 with which I'm handle able to do anything. If I had to try some fine tuning in models like Phi2, whats the best cloud setup I can go with? | 2024-01-21T09:41:40 | https://www.reddit.com/r/LocalLLaMA/comments/19bzvwz/best_place_to_try_llm_fine_tuning_in_the_cloud/ | solotravelblogger | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 19bzvwz | false | null | t3_19bzvwz | /r/LocalLLaMA/comments/19bzvwz/best_place_to_try_llm_fine_tuning_in_the_cloud/ | false | false | self | 1 | null |
What framework to use to build an open-sourced LLM chatbot which is enterprise scalable to multiple users | 1 | Hey guys, what framework or tools do I use if I wanted to build an open-sourced LLM chatbot which is enterprise scalable to multiple users?
A framework/tool I am thinking of is Langchain. There won’t be any fine-tuning for my chatbot so I am not sure if I need to use Langchain.
Would there be a different suitable fra... | 2024-01-21T09:15:07 | https://www.reddit.com/r/LocalLLaMA/comments/19bzi5c/what_framework_to_use_to_build_an_opensourced_llm/ | redd-dev | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 19bzi5c | false | null | t3_19bzi5c | /r/LocalLLaMA/comments/19bzi5c/what_framework_to_use_to_build_an_opensourced_llm/ | false | false | self | 1 | null |
Data Prepare of Basic Retrieval Augmented Generation | 1 | 2024-01-21T09:06:09 | https://thebeep.substack.com/p/data-prepare-of-basic-retrieval-augmented | sapporonight | thebeep.substack.com | 1970-01-01T00:00:00 | 0 | {} | 19bzdm5 | false | null | t3_19bzdm5 | /r/LocalLLaMA/comments/19bzdm5/data_prepare_of_basic_retrieval_augmented/ | false | false | 1 | {'enabled': False, 'images': [{'id': 'O6gkT4eL_YRbT_WB4tEfqOgEOKdZlSs9acqu6CJGnSU', 'resolutions': [{'height': 54, 'url': 'https://external-preview.redd.it/km6qXg5UGJyfNRxXSrH6nokWmjs5ycEu1eOP3savP-M.jpg?width=108&crop=smart&auto=webp&s=5702710f9868f2ed61e7dd45d4ed019f634fc746', 'width': 108}, {'height': 108, 'url': 'h... | ||
https://thebeep.substack.com/p/data-prepare-of-basic-retrieval-augmented | 1 | [removed] | 2024-01-21T09:05:41 | [deleted] | 1970-01-01T00:00:00 | 0 | {} | 19bzddd | false | null | t3_19bzddd | /r/LocalLLaMA/comments/19bzddd/httpsthebeepsubstackcompdataprepareofbasicretrieva/ | false | false | default | 1 | null | ||
This is not a ChatGPT reskin! 🛑 | 1 | Hey Reddit,
I am not the smartest or the most proficient. But I have recently just released a AI application. I promise you from the bottom of my heart THIS IS NOT JUST A CHAT GPT RESKIN.
I’m someone who’s always loved playing with sound as I am an audio engineer by trade. But early last year as we all know AI starte... | 2024-01-21T08:59:36 | https://sslive.io | Jehmal | sslive.io | 1970-01-01T00:00:00 | 0 | {} | 19bz9tu | false | null | t3_19bz9tu | /r/LocalLLaMA/comments/19bz9tu/this_is_not_a_chatgpt_reskin/ | false | false | 1 | {'enabled': False, 'images': [{'id': 'Jz0ueQFNgTtW2ucqzyV39M2hDdBQbGUWMHGV_t69c8E', 'resolutions': [{'height': 66, 'url': 'https://external-preview.redd.it/Ik7YQJcYmxFFoiagsazK6_fzK7RD5i4iVRtCm3ZhcLI.jpg?width=108&crop=smart&auto=webp&s=eec254d7e89d985e3faf7feef41aba81bf8dd8d7', 'width': 108}, {'height': 133, 'url': 'h... | |
Is there a super simple RP chat web front end? | 6 | I'm trying to find an extremely basic web front end where I can users can chat with a custom character on their browser without any settings or options that might confuse them.
Ideally it would link to a koboldcpp/llamacpp or textgen (ooba) backend using a URL (OpenAPI is fine) on another server. The custom prompt of ... | 2024-01-21T07:53:11 | https://www.reddit.com/r/LocalLLaMA/comments/19byb6l/is_there_a_super_simple_rp_chat_web_front_end/ | Broadband- | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 19byb6l | false | null | t3_19byb6l | /r/LocalLLaMA/comments/19byb6l/is_there_a_super_simple_rp_chat_web_front_end/ | false | false | self | 6 | null |
Collaborative platform to train your models? | 2 | Hi, with my team we are training an OS LLM and want to train it/test it together (control of the experiments, evaluation, comments etc...)
For now we use weight & biases but personally I'm not a huge fan of their UX.
Do you have any other tools that you recommend ?
Thanks! | 2024-01-21T07:26:08 | https://www.reddit.com/r/LocalLLaMA/comments/19bxwym/collaborative_platform_to_train_your_models/ | PrincessbooAsianPri | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 19bxwym | false | null | t3_19bxwym | /r/LocalLLaMA/comments/19bxwym/collaborative_platform_to_train_your_models/ | false | false | self | 2 | null |
Any safety advice for a newbie? | 4 | Hey guys,
I have only fairly recently gotten into AI and have played around with stablediffusion, oobabooga, and [jan.ai](https://jan.ai). I came across this 'Lord of LLMs' interface on github which sounds like something I would want to try but before downloading it I started asking myself if there are any security ... | 2024-01-21T07:09:23 | https://www.reddit.com/r/LocalLLaMA/comments/19bxnwa/any_safety_advice_for_a_newbie/ | FearFactory2904 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 19bxnwa | false | null | t3_19bxnwa | /r/LocalLLaMA/comments/19bxnwa/any_safety_advice_for_a_newbie/ | false | false | self | 4 | {'enabled': False, 'images': [{'id': '_clR5lo0uUzBmmOefgsOcrqCYpHgjkxrStKzWLzjtqg', 'resolutions': [{'height': 60, 'url': 'https://external-preview.redd.it/71HRL7bDHzSg5fARXgUVzQrb-ddlAEFhDMiNjCqLPcE.jpg?width=108&crop=smart&auto=webp&s=a34a9c017a9872303c87fdbe0bca0b95846bd110', 'width': 108}, {'height': 121, 'url': 'h... |
My new model is competitive with GPT-3.5 and Gemini Pro and capable of running on 6GB of RAM | 3 | I am thrilled to present my latest LLM, SOLAR-math-2x10.7-v0.2 (19B), which stands competitively alongside GPT-3.5 Turbo and Gemini Pro. Notably, it surpasses the text generation capabilities of models with higher parameter counts, such as Mixtral-8x7b (46.7B) and even Gemini Ultra, in specific evaluations.
If you're ... | 2024-01-21T07:09:15 | macadeliccc | i.redd.it | 1970-01-01T00:00:00 | 0 | {} | 19bxntu | false | null | t3_19bxntu | /r/LocalLLaMA/comments/19bxntu/my_new_model_is_competitive_with_gpt35_and_gemini/ | false | false | 3 | {'enabled': True, 'images': [{'id': 'FWSfTDcs_iKwNnTPtsTB-Tu8IGO0P6bsRl9XJ62M6z0', 'resolutions': [{'height': 33, 'url': 'https://preview.redd.it/cjze4nwhtqdc1.jpeg?width=108&crop=smart&auto=webp&s=2c7a58e394e7d21743fa928773d39d34396f84e6', 'width': 108}, {'height': 67, 'url': 'https://preview.redd.it/cjze4nwhtqdc1.jpe... | ||
New model is competitive with GPT-3.5 and Gemini Pro and runs on 7GB RAM | 1 | I am thrilled to present my latest LLM, SOLAR-math-2x10.7-v0.2 (19B), which stands competitively alongside GPT-3.5 Turbo and Gemini Pro. Notably, it surpasses the text generation capabilities of models with higher parameter counts, such as Mixtral-8x7b (46.7B) and even Gemini Ultra, in specific evaluations.
If you're ... | 2024-01-21T07:00:58 | https://www.reddit.com/r/LocalLLaMA/comments/19bxj7h/new_model_is_competitive_with_gpt35_and_gemini/ | macadeliccc | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 19bxj7h | false | null | t3_19bxj7h | /r/LocalLLaMA/comments/19bxj7h/new_model_is_competitive_with_gpt35_and_gemini/ | false | false | default | 1 | {'enabled': False, 'images': [{'id': 'dlHGulZH3EqgWZwUqf7WVf6ULJmleALz23OBrtTZ5PY', 'resolutions': [{'height': 58, 'url': 'https://external-preview.redd.it/9uhfr8pcOuxPeqSVwxkWoW8lQADydezPjxW0jNzoT3s.jpg?width=108&crop=smart&auto=webp&s=77baf325d46d677b5512f175b1d728c6fe310bd4', 'width': 108}, {'height': 116, 'url': 'h... |
Indexing iCloud Photos with AI Using LLaVA and pgvector | 1 | 2024-01-21T06:55:48 | https://medium.com/@mustafaakin/indexing-icloud-photos-with-ai-using-llava-and-pgvector-fd58182febf6 | mustafaakin | medium.com | 1970-01-01T00:00:00 | 0 | {} | 19bxg9q | false | null | t3_19bxg9q | /r/LocalLLaMA/comments/19bxg9q/indexing_icloud_photos_with_ai_using_llava_and/ | false | false | 1 | {'enabled': False, 'images': [{'id': 'gQtiU0pwSy9c_zbUiDfkQ7fR-3tePuYM_EB3dFCf8wA', 'resolutions': [{'height': 81, 'url': 'https://external-preview.redd.it/yo6debFUpiwaVMNlgNRhD7I2u2hBsc4-xBuzIi4RQxQ.jpg?width=108&crop=smart&auto=webp&s=87b08777d5c20606b202160ddd657600198093c4', 'width': 108}, {'height': 162, 'url': 'h... | ||
Small models for heating | 1 | If it's too cold for your laptop to charge, like what's happening with the cold snap right now, you could run a local LLM to heat up the laptop. Most batteries will stop charging or charge at a very low rate if the battery pack temperature drops below certain limit.
You could run a small LLM like a 1B or 3B model and ... | 2024-01-21T05:42:31 | https://www.reddit.com/r/LocalLLaMA/comments/19bw9zv/small_models_for_heating/ | Some_Endian_FP17 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 19bw9zv | false | null | t3_19bw9zv | /r/LocalLLaMA/comments/19bw9zv/small_models_for_heating/ | false | false | self | 1 | null |
Anybody noticed Mistral going real bad and Bard getting real good these last days? | 1 | Just noticed today. Mistral used to give good results with math questions. Not anymore. And, bard is just acing math questions today | 2024-01-21T05:02:47 | https://www.reddit.com/r/LocalLLaMA/comments/19bvlgp/anybody_noticed_mistral_going_real_bad_and_bard/ | kocahmet1 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 19bvlgp | false | null | t3_19bvlgp | /r/LocalLLaMA/comments/19bvlgp/anybody_noticed_mistral_going_real_bad_and_bard/ | false | false | self | 1 | null |
Running LLama with lora in Android | 1 | [removed] | 2024-01-21T05:02:21 | https://www.reddit.com/r/LocalLLaMA/comments/19bvl58/running_llama_with_lora_in_android/ | Beautiful-anon | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 19bvl58 | false | null | t3_19bvl58 | /r/LocalLLaMA/comments/19bvl58/running_llama_with_lora_in_android/ | false | false | self | 1 | {'enabled': False, 'images': [{'id': 'iY0csUz6AjyfEJFX0QCeMl9b8ij7_11l3D8XN5QSXvU', 'resolutions': [{'height': 58, 'url': 'https://external-preview.redd.it/pxhH4mrJi2W9E12fb4zVzZFaeG-sipr5MwmClZjGXZI.jpg?width=108&crop=smart&auto=webp&s=7a3e9a0d35c3e1dd114819abe611199cd84a4cf2', 'width': 108}, {'height': 116, 'url': 'h... |
PriomptiPy - A python library to budget tokens and dynamically render prompts for LLMs | 47 | 2024-01-21T04:20:40 | tg1482 | i.redd.it | 1970-01-01T00:00:00 | 0 | {} | 19buv75 | false | null | t3_19buv75 | /r/LocalLLaMA/comments/19buv75/priomptipy_a_python_library_to_budget_tokens_and/ | false | false | default | 47 | {'enabled': True, 'images': [{'id': 'ybuquciczpdc1', 'resolutions': [{'height': 60, 'url': 'https://preview.redd.it/ybuquciczpdc1.gif?width=108&crop=smart&format=png8&s=8b7c797858392fcedcc67d4a31b6a571489b23a2', 'width': 108}, {'height': 121, 'url': 'https://preview.redd.it/ybuquciczpdc1.gif?width=216&crop=smart&format... | ||
Run MLX based Nous-Hermes-2-Mixtral-8x7B-DPO-4bit and Chat Frontend UI on Apple Silicon | 1 | [https://huggingface.co/mlx-community/Nous-Hermes-2-Mixtral-8x7B-DPO-4bit](https://huggingface.co/mlx-community/Nous-Hermes-2-Mixtral-8x7B-DPO-4bit)
[https://github.com/da-z/mlx-ui](https://github.com/da-z/mlx-ui) | 2024-01-21T03:54:02 | https://www.reddit.com/r/LocalLLaMA/comments/19bueoq/run_mlx_based_noushermes2mixtral8x7bdpo4bit_and/ | Different-Pickle1021 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 19bueoq | false | null | t3_19bueoq | /r/LocalLLaMA/comments/19bueoq/run_mlx_based_noushermes2mixtral8x7bdpo4bit_and/ | false | false | self | 1 | {'enabled': False, 'images': [{'id': 'SofWpwDg27-_jwNONgyb4is1tZxjOdpxYreUq62dyak', 'resolutions': [{'height': 58, 'url': 'https://external-preview.redd.it/WgrmD_0EanO4P10IXKE-UdUTYb2g1VhYdX3xVZ_fe4I.jpg?width=108&crop=smart&auto=webp&s=e455219ef1dc333b6b41550baf2193be86de6464', 'width': 108}, {'height': 116, 'url': 'h... |
Is 2x 3090 with NVLink faster than 2x 4090 for large 70b models? | 10 | I am wondering if a 2x 3090s with NVLink setup is faster than a 2x 4090s? For both inference and training/fine tuning tasks?
I have read in several other posts people talking about getting 10t/s on 2x 3090s and 17t/s on 2x 3090 + NVLink. It means 70% faster with NVLink.
As long as 40 series doesn't support NVLink, i... | 2024-01-21T03:12:10 | https://www.reddit.com/r/LocalLLaMA/comments/19btnjz/is_2x_3090_with_nvlink_faster_than_2x_4090_for/ | thefreemanever | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 19btnjz | false | null | t3_19btnjz | /r/LocalLLaMA/comments/19btnjz/is_2x_3090_with_nvlink_faster_than_2x_4090_for/ | false | false | self | 10 | null |
What improvement or new feature would you like to see on Llama 3? | 31 | Hi !
Llama 3 training started ([link](https://www.axios.com/2024/01/18/zuckerberg-meta-llama-3-ai)), so what improvement or new feature would you like to see on Llama 3? | 2024-01-21T01:46:35 | https://www.reddit.com/r/LocalLLaMA/comments/19bs0fy/what_improvement_or_new_feature_would_you_like_to/ | celsowm | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 19bs0fy | false | null | t3_19bs0fy | /r/LocalLLaMA/comments/19bs0fy/what_improvement_or_new_feature_would_you_like_to/ | false | false | self | 31 | {'enabled': False, 'images': [{'id': 'FtT31sq2lyBbfWa2YmI2yDOHnbORtszPQ46VYBBwnbU', 'resolutions': [{'height': 60, 'url': 'https://external-preview.redd.it/l0pXj1SIJC4sRRxf1atzhqKa0k7HjWqPjWyHtmlE9MA.jpg?width=108&crop=smart&auto=webp&s=0ca2a9379d59ab0817fc8a66f8eaf16c0a737134', 'width': 108}, {'height': 121, 'url': 'h... |
How to determine the right n_predict value?? | 2 | I've been using llama cpp with n\_predict. If I set n\_predict to 400, the model ([https://huggingface.co/TheBloke/stablelm-zephyr-3b-GGUF](https://huggingface.co/TheBloke/stablelm-zephyr-3b-GGUF)) could just keep droning on for no reason, but with 100 it does not complete the full response. Is there a simple way of de... | 2024-01-21T01:30:57 | https://www.reddit.com/r/LocalLLaMA/comments/19brore/how_to_determine_the_right_n_predict_value/ | Powerful-Cupcake-407 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 19brore | false | null | t3_19brore | /r/LocalLLaMA/comments/19brore/how_to_determine_the_right_n_predict_value/ | false | false | default | 2 | {'enabled': False, 'images': [{'id': '59ludY3rdK6TZywfRbVJSTw-xUJZOKoc9p0dJVhWqPA', 'resolutions': [{'height': 58, 'url': 'https://external-preview.redd.it/H5DGrrW4SRc0kuoAyrBAzSrO6DYqNN8N5RwA7fbemoM.jpg?width=108&crop=smart&auto=webp&s=cc463a1fc360e2e33db3cad1d401c7e7eb4aa5f9', 'width': 108}, {'height': 116, 'url': 'h... |
Is it possible to connect hardware to ollama and have it move a steper motor or recieve live camera input ? | 1 | Can robotics be achieved with what we currently have available locally ?
I'd like to feed the input of a camera and a steper and ask a model if it understands how to move a motor giving electrical an impulses , is that remotely possible right now? | 2024-01-21T01:19:39 | https://www.reddit.com/r/LocalLLaMA/comments/19brgul/is_it_possible_to_connect_hardware_to_ollama_and/ | petit_cheval | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 19brgul | false | null | t3_19brgul | /r/LocalLLaMA/comments/19brgul/is_it_possible_to_connect_hardware_to_ollama_and/ | false | false | self | 1 | null |
What to serve on 8xA100s to 50-100 employees? | 7 | I'm back ([Serve Mixtral-8x7B-Instruct-v0.1 at scale via 8xV100s - what to do?](https://www.reddit.com/r/LocalLLaMA/comments/18z0rfk/serve_mixtral8x7binstructv01_at_scale_via_8xv100s/)), this time with much better GPUs (I know, counting my blessings).
The use case is a generalist, single model (for simplicity) handlin... | 2024-01-21T01:15:42 | https://www.reddit.com/r/LocalLLaMA/comments/19brdz7/what_to_serve_on_8xa100s_to_50100_employees/ | ablasionet | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 19brdz7 | false | null | t3_19brdz7 | /r/LocalLLaMA/comments/19brdz7/what_to_serve_on_8xa100s_to_50100_employees/ | false | false | self | 7 | null |
Apple mlx now support lora/qlora for mixtral | 22 | IMO, mostly economic option for fine-tune mixtral.
https://twitter.com/awnihannun/status/1748727146611429880?t=xCHEFge9PhdqPQYvpnbang&s=19 | 2024-01-21T00:51:18 | https://www.reddit.com/r/LocalLLaMA/comments/19bqvue/apple_mlx_now_support_loraqlora_for_mixtral/ | Tiny_Judge_2119 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 19bqvue | false | null | t3_19bqvue | /r/LocalLLaMA/comments/19bqvue/apple_mlx_now_support_loraqlora_for_mixtral/ | false | false | self | 22 | {'enabled': False, 'images': [{'id': 'wex1NDKRspHFGVl0eDDQ23sgo6ZtCVk4gvqxWAS7b7Y', 'resolutions': [{'height': 41, 'url': 'https://external-preview.redd.it/LWIKvQ8CZc33pm5RcEOksaFT9_MwhHoUCYfBQzKToSo.jpg?width=108&crop=smart&auto=webp&s=f1c7eff2a6e46f02493fc630e3a60927d9a454d2', 'width': 108}], 'source': {'height': 54,... |
Good hardware to buy/setup for my configuration and goals? | 1 | I currently have a desktop with AMD CPU and (very-low-end) AMD GPU, Windows.
I also have a laptop (Linux) with no GPU.
I want to run LLMs locally for tasks/finetunes involving my private data + things that I don't want leaked. Ofc the bigger models the better, but I'm currently clueless on the cost-performance tradeo... | 2024-01-21T00:44:21 | https://www.reddit.com/r/LocalLLaMA/comments/19bqqmz/good_hardware_to_buysetup_for_my_configuration/ | NicholasKross | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 19bqqmz | false | null | t3_19bqqmz | /r/LocalLLaMA/comments/19bqqmz/good_hardware_to_buysetup_for_my_configuration/ | false | false | self | 1 | null |
torch-nos - A fast and flexible PyTorch inference server for multi-modal applications | 15 | 2024-01-21T00:41:22 | https://github.com/autonomi-ai/nos | fuzzysingularity | github.com | 1970-01-01T00:00:00 | 0 | {} | 19bqoes | false | null | t3_19bqoes | /r/LocalLLaMA/comments/19bqoes/torchnos_a_fast_and_flexible_pytorch_inference/ | false | false | 15 | {'enabled': False, 'images': [{'id': 'aFaKOmtcPRihxuTkdzmrjyM274DvhKy8PrRa2UmrSxc', 'resolutions': [{'height': 54, 'url': 'https://external-preview.redd.it/hCowHwTRFsmAzfa46yiplT-MJg5bq8YmKy8zurrWCTs.jpg?width=108&crop=smart&auto=webp&s=6203bdac98c937b132442306883824a8adb4863e', 'width': 108}, {'height': 108, 'url': 'h... | ||
Deepseek 67b is amazing, and in at least 1 usecase it seems better than ChatGPT 4 | 81 | Just wanted to toss this out there since I don't see a lot of folks talking about it, but Deepseek 67b has become one of my favorite general purpose models.
This is also the first model I've run into that has clearly beaten out, for me at least, ChatGPT 4 in a use case: Excel and VBA.
My wife has been working on a v... | 2024-01-20T23:53:46 | https://www.reddit.com/r/LocalLLaMA/comments/19bpnzo/deepseek_67b_is_amazing_and_in_at_least_1_usecase/ | SomeOddCodeGuy | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 19bpnzo | false | null | t3_19bpnzo | /r/LocalLLaMA/comments/19bpnzo/deepseek_67b_is_amazing_and_in_at_least_1_usecase/ | false | false | self | 81 | null |
Evolution of jailbreaks? | 12 | So LLMs have exploded in the past few years, from the almost-magical GPT-3 to now, many local models surpassing even GPT-3.5. I'm wondering, what are the various jailbreaks that have followed the development of LLMs? There was the good old grandma trick, the DAN phase, and so on. And now, the most recent newsworthy jai... | 2024-01-20T23:40:22 | https://www.reddit.com/r/LocalLLaMA/comments/19bpdnc/evolution_of_jailbreaks/ | adumdumonreddit | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 19bpdnc | false | null | t3_19bpdnc | /r/LocalLLaMA/comments/19bpdnc/evolution_of_jailbreaks/ | false | false | self | 12 | null |
What are the top five questions you always ask to verify the new LLMs quality? | 1 | How do you evaluate the response? Looking for insightful responses, please. | 2024-01-20T23:22:58 | https://www.reddit.com/r/LocalLLaMA/comments/19bozo5/what_are_the_top_five_questions_you_always_ask_to/ | Wonderful-Ad-5952 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 19bozo5 | false | null | t3_19bozo5 | /r/LocalLLaMA/comments/19bozo5/what_are_the_top_five_questions_you_always_ask_to/ | false | false | self | 1 | null |
Subtracting weights from model - an untapped area of changing the models | 7 | Fun aside, here is an addendum to my previous post. We usually add weights to the model in order to (fingers crossed) make it smarter - but how about if we subtract a model?
I often play with this idea and some of my models are a mixture of adding and subtracting different finetunes (LORA).
Here is an example.
A bas... | 2024-01-20T23:14:50 | https://www.reddit.com/r/LocalLLaMA/comments/19bot5o/subtracting_weights_from_model_an_untapped_area/ | FPham | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 19bot5o | false | null | t3_19bot5o | /r/LocalLLaMA/comments/19bot5o/subtracting_weights_from_model_an_untapped_area/ | false | false | 7 | null | |
Cost Effective (+1000 PDF) PDF AI Chat Bots? Cloud-based Llama vs. OpenAI | 7 | Hello Everyone:
I've seen a lot of posts here and elsewhere saying that by pure cost measure, it's tough to beat OpenAI API pricing vs. other alternatives (such as those available on [https://deepinfra.com/pricing](https://deepinfra.com/pricing)) . I'm trying to understand if that's still true for building out multipl... | 2024-01-20T22:56:42 | https://www.reddit.com/r/LocalLLaMA/comments/19boede/cost_effective_1000_pdf_pdf_ai_chat_bots/ | KingSnuggleMuffin | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 19boede | false | null | t3_19boede | /r/LocalLLaMA/comments/19boede/cost_effective_1000_pdf_pdf_ai_chat_bots/ | false | false | self | 7 | {'enabled': False, 'images': [{'id': 'gdv5Bh89JWXxDpkAlTrk_zCb-qJxrREhAWY8_SsUogU', 'resolutions': [{'height': 108, 'url': 'https://external-preview.redd.it/9yZr3zHUmyWQtvbJofUKJroV_0PJzwp1lwBQ4qcwT7s.jpg?width=108&crop=smart&auto=webp&s=4e8ad5cdf82a75c71c4af7b04654daaa4f3a27a1', 'width': 108}, {'height': 216, 'url': '... |
Looking for Snapdragon gen 3 benchmarks in ggml (cpu) | 1 | Has anyone benchmarked the Q4_K_S variant for 7/13B on with a cpu build in termux?
There is a Redmi K70 phone with 24GB ram, and one person gets 11 t/s (2x gen2 speed) with a 4bpw equivalent model on the android mlc build.
Most people will get 5 t/s on gen2 with 0k on a 7B. | 2024-01-20T22:38:01 | https://www.reddit.com/r/LocalLLaMA/comments/19bnz5d/looking_for_snapdragon_gen_3_benchmarks_in_ggml/ | Aaaaaaaaaeeeee | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 19bnz5d | false | null | t3_19bnz5d | /r/LocalLLaMA/comments/19bnz5d/looking_for_snapdragon_gen_3_benchmarks_in_ggml/ | false | false | self | 1 | null |
What projects can llm's help with? | 1 | [removed] | 2024-01-20T22:34:55 | https://www.reddit.com/r/LocalLLaMA/comments/19bnws9/what_projects_can_llms_help_with/ | Gaming-invisibleman | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 19bnws9 | false | null | t3_19bnws9 | /r/LocalLLaMA/comments/19bnws9/what_projects_can_llms_help_with/ | false | false | self | 1 | null |
Looking for a good LLM Model that my computer can handle + PC Upgrade Suggestions | 2 | My computer specs are as follows:
i9-13900K
32GB DDR5 RAM
RTX-4090 24GB VRAM
I've been using 2.2 dolphin-yi-34B Q4 K\_M on kobold cpp, The initial performance was amazing with high T/s processing and generation, but now processing speeds are ridiculously low, leading to response times of \~400s. I understand this ... | 2024-01-20T22:28:52 | https://www.reddit.com/r/LocalLLaMA/comments/19bnrw9/looking_for_a_good_llm_model_that_my_computer_can/ | Many_Examination9543 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 19bnrw9 | false | null | t3_19bnrw9 | /r/LocalLLaMA/comments/19bnrw9/looking_for_a_good_llm_model_that_my_computer_can/ | false | false | nsfw | 2 | null |
I think the name 'Mixture-of-Experts' is misleading | 38 | I just finished reading the paper [Mixtral of Experts](https://arxiv.org/abs/2401.04088) and found it that the 8 experts are not actualy experts in any specific thing.
​
[Experts work with all the tokens from the different fields](https://preview.redd.it/0hq5rbr94odc1.png?width=802&format=png&auto=webp&s=cc671... | 2024-01-20T22:07:01 | https://www.reddit.com/r/LocalLLaMA/comments/19bnaiw/i_think_the_name_mixtureofexperts_is_misleading/ | Puzzleheaded_Mall546 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 19bnaiw | false | null | t3_19bnaiw | /r/LocalLLaMA/comments/19bnaiw/i_think_the_name_mixtureofexperts_is_misleading/ | false | false | 38 | null | |
Help using llama_cpp_python to calculate probability of a given sequence of tokens being generated. My numbers aren't even in the ball park. | 6 | I am trying to manually calculate the probability that a given test sequence of tokens would be generated given a specific input, somewhat of a benchmark. I using llama_cpp to to manually get the logprobs token by token of the text sequence but it's not adding up anywhere close to the logprobs being returned using crea... | 2024-01-20T22:03:46 | https://www.reddit.com/r/LocalLLaMA/comments/19bn7ux/help_using_llama_cpp_python_to_calculate/ | aaronr_90 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 19bn7ux | false | null | t3_19bn7ux | /r/LocalLLaMA/comments/19bn7ux/help_using_llama_cpp_python_to_calculate/ | false | false | self | 6 | null |
Is next token generation enough to predict correct text ? | 1 | [removed] | 2024-01-20T22:02:33 | https://www.reddit.com/r/LocalLLaMA/comments/19bn6xg/is_next_token_generation_enough_to_predict/ | djangoUnblamed | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 19bn6xg | false | null | t3_19bn6xg | /r/LocalLLaMA/comments/19bn6xg/is_next_token_generation_enough_to_predict/ | false | false | self | 1 | null |
Looking for best NSFW LLM w/ API with best inference scalability - can pay for consult | 2 | Hi everyone,
I'm looking for some feedback, as I'm advising a potential client. I'm new to the space and still learning, so I'm also happy to pay for a consult if you can help me find what I'm looking for.
I'm looking for the best opensource NSFW LLM with API, specifically focusing on it's inference scalability, as ... | 2024-01-20T22:01:21 | https://www.reddit.com/r/LocalLLaMA/comments/19bn5wm/looking_for_best_nsfw_llm_w_api_with_best/ | LushVirtual | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 19bn5wm | false | null | t3_19bn5wm | /r/LocalLLaMA/comments/19bn5wm/looking_for_best_nsfw_llm_w_api_with_best/ | false | false | nsfw | 2 | null |
What are your favorite use cases for small models around 3b and less. | 14 | I am really interested what you smart folks are using smaller models for ?
Phi,tinyllama etc. What do you do with them ?
Would love to read your projects to maybe find some inspiration ^^. | 2024-01-20T21:43:50 | https://www.reddit.com/r/LocalLLaMA/comments/19bmrjz/what_are_your_favorite_use_cases_for_small_models/ | Noxusequal | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 19bmrjz | false | null | t3_19bmrjz | /r/LocalLLaMA/comments/19bmrjz/what_are_your_favorite_use_cases_for_small_models/ | false | false | self | 14 | null |
Anyone tested CodeShell-7B? | 6 | [https://huggingface.co/WisdomShell/CodeShell-7B](https://huggingface.co/WisdomShell/CodeShell-7B)
It has quite good human eval score , support FIM.
I could not find any gguf, so cant test it.... | 2024-01-20T21:29:17 | https://www.reddit.com/r/LocalLLaMA/comments/19bmfj0/anyone_tested_codeshell7b/ | JoseConseco_ | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 19bmfj0 | false | null | t3_19bmfj0 | /r/LocalLLaMA/comments/19bmfj0/anyone_tested_codeshell7b/ | false | false | self | 6 | {'enabled': False, 'images': [{'id': 'zSp3o2xADbzJHsd2SwTDQSy_S7596l3KoaUgptGeaEg', 'resolutions': [{'height': 58, 'url': 'https://external-preview.redd.it/nOwqJddE53yzvp3lZoByeuXOBS6pmnNgfvEcS3TGhqM.jpg?width=108&crop=smart&auto=webp&s=bdca437304dacaf4cd97a3f350f6461e87db84b5', 'width': 108}, {'height': 116, 'url': 'h... |
Would the 4070 super be a good card to grab for oogabooga? | 2 | Question in title basically. And on top of this, is the 4070 super capable of utelizing sli? I can't actually find anything on it being sli enabled.
I'm thinking of upgrading from my 3070 ti, as whilst it was acceptable for gaming, the limited vram is severely bottlenecking any textgen/Imagegen tasks, and was wonderin... | 2024-01-20T21:12:19 | https://www.reddit.com/r/LocalLLaMA/comments/19bm1rg/would_the_4070_super_be_a_good_card_to_grab_for/ | Maelstrom100 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 19bm1rg | false | null | t3_19bm1rg | /r/LocalLLaMA/comments/19bm1rg/would_the_4070_super_be_a_good_card_to_grab_for/ | false | false | self | 2 | null |
What does layer 0 of llama represent? Is it the embedding layer? | 1 | [removed] | 2024-01-20T20:43:15 | https://www.reddit.com/r/LocalLLaMA/comments/19bldqg/what_does_layer_0_of_llama_represent_is_it_the/ | AcceptableBat8912 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 19bldqg | false | null | t3_19bldqg | /r/LocalLLaMA/comments/19bldqg/what_does_layer_0_of_llama_represent_is_it_the/ | false | false | self | 1 | null |
what is the best 7b model for social media content generation? | 1 | working on a project for social media and haven't tried any of the open source models before and would really benefit from some guidance. | 2024-01-20T20:13:38 | https://www.reddit.com/r/LocalLLaMA/comments/19bkph5/what_is_the_best_7b_model_for_social_media/ | J055EEF | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 19bkph5 | false | null | t3_19bkph5 | /r/LocalLLaMA/comments/19bkph5/what_is_the_best_7b_model_for_social_media/ | false | false | self | 1 | null |
I only said "Hello..." :( (Finetune going off the rails) | 158 | 2024-01-20T19:50:07 | FPham | i.redd.it | 1970-01-01T00:00:00 | 0 | {} | 19bk5w3 | false | null | t3_19bk5w3 | /r/LocalLLaMA/comments/19bk5w3/i_only_said_hello_finetune_going_off_the_rails/ | false | false | 158 | {'enabled': True, 'images': [{'id': 'Jjx1aNP6XLJkkQAwT7fOGkQuX--3Bo-_0zxavathJGs', 'resolutions': [{'height': 101, 'url': 'https://preview.redd.it/ujtgb4y1gndc1.png?width=108&crop=smart&auto=webp&s=dd04029b8942a3560dc6430341873cf39c8f2a49', 'width': 108}, {'height': 202, 'url': 'https://preview.redd.it/ujtgb4y1gndc1.pn... | |||
Good LLM GUIs for LM Studio server | 3 | I’m running many local models using LM Studio on a remote server in my network. I know that LM Studio has a « server » mode where it exposes the API externally and that can be then accessed by curl or python.
The question is whether there are any web GUI clients that look similar to a chat window that I can connect to... | 2024-01-20T19:45:55 | https://www.reddit.com/r/LocalLLaMA/comments/19bk2gl/good_llm_guis_for_lm_studio_server/ | fm9419 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 19bk2gl | false | null | t3_19bk2gl | /r/LocalLLaMA/comments/19bk2gl/good_llm_guis_for_lm_studio_server/ | false | false | self | 3 | null |
What are the best options for a gaming computer that I can also use for AI/ML | 1 | Im new to computer builds but I keep running into limitations with my current computer, the rending and gameplay is incredibly slow. Games like BeamNG.Drive on Stream just slow to a crawl when playing it. And it’s getting to the point where I can’t play most games without a gaming computer. I also work a lot with AI/ML... | 2024-01-20T19:13:44 | https://www.reddit.com/r/LocalLLaMA/comments/19bjbva/what_are_the_best_options_for_a_gaming_computer/ | throwaway0134hdj | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 19bjbva | false | null | t3_19bjbva | /r/LocalLLaMA/comments/19bjbva/what_are_the_best_options_for_a_gaming_computer/ | false | false | self | 1 | null |
Can anyone explain what Extraction, STEM, Humanities and Writing mean in the context of LLMs / MT- Bench? Writing, i can guess, but Humanties and Stem, i have no idea... | 3 | 2024-01-20T19:12:29 | yupignome | i.redd.it | 1970-01-01T00:00:00 | 0 | {} | 19bjaum | false | null | t3_19bjaum | /r/LocalLLaMA/comments/19bjaum/can_anyone_explain_what_extraction_stem/ | false | false | 3 | {'enabled': True, 'images': [{'id': '45ogS7QX5FtB205DoKpR6klxeH3Nrhnpi3aHJ4KfPYg', 'resolutions': [{'height': 81, 'url': 'https://preview.redd.it/hjj9xbxa9ndc1.png?width=108&crop=smart&auto=webp&s=c9fc1512dfe2a3dc67ba9d38135c0838fd1683c8', 'width': 108}, {'height': 162, 'url': 'https://preview.redd.it/hjj9xbxa9ndc1.png... | |||
What's the largest existing LLM that an individual can feasibly run privately? | 51 | Goal: best LLM that I can ask private questions / own-my-own-chats with.
Open-source weights, not so big that inference exceeds ~$50/hr.
Is LLAMA OK for this, or are there better options and/or setup-helper repos? | 2024-01-20T19:09:22 | https://www.reddit.com/r/LocalLLaMA/comments/19bj83q/whats_the_largest_existing_llm_that_an_individual/ | PinPinnson | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 19bj83q | false | null | t3_19bj83q | /r/LocalLLaMA/comments/19bj83q/whats_the_largest_existing_llm_that_an_individual/ | false | false | self | 51 | null |
LM Studio -> LLaMA constantly eating up disk space | 1 | [removed] | 2024-01-20T18:47:24 | https://www.reddit.com/r/LocalLLaMA/comments/19biph8/lm_studio_llama_constantly_eating_up_disk_space/ | calypsolard | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 19biph8 | false | null | t3_19biph8 | /r/LocalLLaMA/comments/19biph8/lm_studio_llama_constantly_eating_up_disk_space/ | false | false | self | 1 | null |
Is It possible to run Mixtral with 64GB ram? | 1 | [removed] | 2024-01-20T18:15:10 | https://www.reddit.com/r/LocalLLaMA/comments/19bhyhj/is_it_possible_to_run_mixtral_with_64gb_ram/ | CharacterCheck389 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 19bhyhj | false | null | t3_19bhyhj | /r/LocalLLaMA/comments/19bhyhj/is_it_possible_to_run_mixtral_with_64gb_ram/ | false | false | self | 1 | null |
How is this new Meta RLAIF paper novel? | 6 | Not training to rain on the hype parade, but isn’t this basically what Anthropic has been doing with constitutional AI?
We already know and have known for a year from Anthropic’s research this type of thing is feasible, and we also already know from Anthropic’s product that it can lead to overfitting. | 2024-01-20T18:01:51 | https://www.reddit.com/r/LocalLLaMA/comments/19bhneg/how_is_this_new_meta_rlaif_paper_novel/ | iamephemeral | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 19bhneg | false | null | t3_19bhneg | /r/LocalLLaMA/comments/19bhneg/how_is_this_new_meta_rlaif_paper_novel/ | false | false | self | 6 | null |
Grasping at straws, gpu crash with sentencetransformers | 4 | Ive been beating my head against the wall here. Trying to use a sentencetransformer model (all-mpnet-base-v2) in python (windows) to embed sentences with cuda / on a nvidia gpu with Cuda toolkit 12.3 and updated driver. I can successfully complete the embeddings, but then my entire computer crashes within 10 seconds af... | 2024-01-20T17:50:28 | Einfinitez | i.redd.it | 1970-01-01T00:00:00 | 0 | {} | 19bhdws | false | null | t3_19bhdws | /r/LocalLLaMA/comments/19bhdws/grasping_at_straws_gpu_crash_with/ | false | false | 4 | {'enabled': True, 'images': [{'id': '9HH5XP3DVDdR_2mChHIXBheRP8sPQNyi47Mkg-PLoGU', 'resolutions': [{'height': 81, 'url': 'https://preview.redd.it/2tai1wgzumdc1.jpeg?width=108&crop=smart&auto=webp&s=44ac291f610585af771524360fa2fa66ce493166', 'width': 108}, {'height': 162, 'url': 'https://preview.redd.it/2tai1wgzumdc1.jp... | ||
What tools are there to manage/create datasets? | 2 | I've created a dataset for fine-tuning and it's just a JSON file combined from handmade text files.
Now it's painful to edit it and further add data. What tools are there for dataset management and creation without the use of third party LLMs? | 2024-01-20T17:43:31 | https://www.reddit.com/r/LocalLLaMA/comments/19bh82g/what_tools_are_there_to_managecreate_datasets/ | Geksaedr | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 19bh82g | false | null | t3_19bh82g | /r/LocalLLaMA/comments/19bh82g/what_tools_are_there_to_managecreate_datasets/ | false | false | self | 2 | null |
Indexing iCloud Photos with AI Using LLaVA and pgvector | 1 | 2024-01-20T17:42:48 | https://medium.com/@mustafaakin/indexing-icloud-photos-with-ai-using-llava-and-pgvector-fd58182febf6 | Fantastic_Beautiful5 | medium.com | 1970-01-01T00:00:00 | 0 | {} | 19bh7i3 | false | null | t3_19bh7i3 | /r/LocalLLaMA/comments/19bh7i3/indexing_icloud_photos_with_ai_using_llava_and/ | false | false | 1 | {'enabled': False, 'images': [{'id': 'gQtiU0pwSy9c_zbUiDfkQ7fR-3tePuYM_EB3dFCf8wA', 'resolutions': [{'height': 81, 'url': 'https://external-preview.redd.it/yo6debFUpiwaVMNlgNRhD7I2u2hBsc4-xBuzIi4RQxQ.jpg?width=108&crop=smart&auto=webp&s=87b08777d5c20606b202160ddd657600198093c4', 'width': 108}, {'height': 162, 'url': 'h... | ||
Continual learning in LLM | 1 | I came across a post on 'continual fine-tuning' in LLMs but imagine a model learning on-demand. Picture an LLM without JavaScript knowledge. Instead of being limited, it actively seeks out documentation and code examples, like from GitHub, to learn.
And as far as i understand, the model's knowledge is in the weights. ... | 2024-01-20T17:27:31 | https://www.reddit.com/r/LocalLLaMA/comments/19bgv60/continual_learning_in_llm/ | WoodenNet5540 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 19bgv60 | false | null | t3_19bgv60 | /r/LocalLLaMA/comments/19bgv60/continual_learning_in_llm/ | false | false | self | 1 | null |
what's you best setup for a chatbot? | 1 | Hi,
I want to develop a chatbot but I'm pretty scared of the responses' latency.
I was thinking to use goliath 120b running on replicate but 5 seconds for a prediction seems a bit too much for me, also because predictions runs in queue, having thousand of messages means that the last user will get a reply in 30 minut... | 2024-01-20T17:24:22 | https://www.reddit.com/r/LocalLLaMA/comments/19bgso7/whats_you_best_setup_for_a_chatbot/ | Sapessiii | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 19bgso7 | false | null | t3_19bgso7 | /r/LocalLLaMA/comments/19bgso7/whats_you_best_setup_for_a_chatbot/ | false | false | self | 1 | null |
Unbiased, up-to-date Code LLM Leaderboard? | 11 | As titled.
Since hugging faces leaderboard does not exactly cover code and people train on the test set a lot, it’s becoming increasingly difficult to find good LLM leaderboards.
Would like to know your opinion on what’s the best unbiased and updated code LLM leaderboard. | 2024-01-20T17:17:58 | https://www.reddit.com/r/LocalLLaMA/comments/19bgnfc/unbiased_uptodate_code_llm_leaderboard/ | Salt-Operation4547 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 19bgnfc | false | null | t3_19bgnfc | /r/LocalLLaMA/comments/19bgnfc/unbiased_uptodate_code_llm_leaderboard/ | false | false | self | 11 | null |
why does mistral freezes ? | 1 | [removed] | 2024-01-20T17:17:13 | https://www.reddit.com/r/LocalLLaMA/comments/19bgmu5/why_does_mistral_freezes/ | kaiyes_ | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 19bgmu5 | false | null | t3_19bgmu5 | /r/LocalLLaMA/comments/19bgmu5/why_does_mistral_freezes/ | false | false | self | 1 | null |
How to Run LangChain Benchmarks to Evaluate Local LLMs from Hugging Face | 5 | 2024-01-20T16:53:26 | https://deci.ai/blog/how-to-run-langchain-benchmarks-with-local-llms-from-hugging-face/ | datascienceharp | deci.ai | 1970-01-01T00:00:00 | 0 | {} | 19bg36w | false | null | t3_19bg36w | /r/LocalLLaMA/comments/19bg36w/how_to_run_langchain_benchmarks_to_evaluate_local/ | false | false | 5 | {'enabled': False, 'images': [{'id': '-mOrIIsgQWSNv7oljdQM2NAdsCNreZhd8nEvfCWPOfw', 'resolutions': [{'height': 60, 'url': 'https://external-preview.redd.it/trfAjBAAoqAgXLk04Yf9W8YSfOXPc4Zw1GhBo0Px5Vc.jpg?width=108&crop=smart&auto=webp&s=6d55c78c4f5cbf3f321c72dc315782ba1110f745', 'width': 108}, {'height': 121, 'url': 'h... | ||
I've created Distributed Llama project. Increase the inference speed of LLM by using multiple devices. It allows to run Llama 2 70B on 8 x Raspberry Pi 4B 4.8sec/token | 355 | 2024-01-20T16:23:26 | https://github.com/b4rtaz/distributed-llama | b4rtaz | github.com | 1970-01-01T00:00:00 | 0 | {} | 19bfez0 | false | null | t3_19bfez0 | /r/LocalLLaMA/comments/19bfez0/ive_created_distributed_llama_project_increase/ | false | false | 355 | {'enabled': False, 'images': [{'id': 'rQOSV4hsYKEW3K3hv4cZpP2t-IqKkD4jZo6JmnOPYak', 'resolutions': [{'height': 54, 'url': 'https://external-preview.redd.it/vzLLB0YZYGycLU8yZShEoNZdvc9rUCfkuLbgDvQjUaQ.jpg?width=108&crop=smart&auto=webp&s=9183453ce75bb433439301a127548cc6c6dbe98a', 'width': 108}, {'height': 108, 'url': 'h... | ||
why does ollama stop ? | 1 | [removed] | 2024-01-20T16:16:33 | https://www.reddit.com/r/LocalLLaMA/comments/19bf96v/why_does_ollama_stop/ | kaiyes_ | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 19bf96v | false | null | t3_19bf96v | /r/LocalLLaMA/comments/19bf96v/why_does_ollama_stop/ | false | false | 1 | null | |
Who do I have to pay to get easy+fast+private big model access? I want a service like "pick HF model, start chatting, get fast replies." | 1 | [removed] | 2024-01-20T16:02:06 | https://www.reddit.com/r/LocalLLaMA/comments/19bexpt/who_do_i_have_to_pay_to_get_easyfastprivate_big/ | drawntomore | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 19bexpt | false | null | t3_19bexpt | /r/LocalLLaMA/comments/19bexpt/who_do_i_have_to_pay_to_get_easyfastprivate_big/ | false | false | self | 1 | {'enabled': False, 'images': [{'id': 'VKoIjTQaRCbBL505btaAbt1k22K_XE7vNMn_jVgQxEw', 'resolutions': [{'height': 58, 'url': 'https://external-preview.redd.it/vj5MHza6p3n7PkFyOS-LOUh7mxd-8itU8AAQePcq8z8.jpg?width=108&crop=smart&auto=webp&s=9c11bcb7840004e107fd0a14cb1b679bd49116ee', 'width': 108}, {'height': 116, 'url': 'h... |
Imagebind alternative | 1 | 2024-01-20T15:34:43 | https://github.com/TencentARC/ViT-Lens | miscellaneous_robot | github.com | 1970-01-01T00:00:00 | 0 | {} | 19bec1z | false | null | t3_19bec1z | /r/LocalLLaMA/comments/19bec1z/imagebind_alternative/ | false | false | 1 | {'enabled': False, 'images': [{'id': 'qdIwhyBLbGWBQM6LU1Gk2kp7Jr13bu1gWn9pq-tHIKw', 'resolutions': [{'height': 54, 'url': 'https://external-preview.redd.it/8yBD49l0rfJHmB5SB3G5PpFlueB3A5Ia7ei1l-YDYOc.jpg?width=108&crop=smart&auto=webp&s=89f9cde72ad061e10a6075b44dc99d2f3ffa1a1c', 'width': 108}, {'height': 108, 'url': 'h... | ||
Run Mistral-7b and more on Docker with GPU Support in Windows - Example Repo | 6 | GitHub: [https://github.com/gabrieleteotino/llamacppdocker](https://github.com/gabrieleteotino/llamacppdocker)
Alright, folks.
So, running models on Docker with GPUs isn't exactly groundbreaking. But, here's my little contribution. A simple example repo for Mistral-7b (or any other model) perfect for newbies like me ... | 2024-01-20T14:44:30 | https://www.reddit.com/r/LocalLLaMA/comments/19bd974/run_mistral7b_and_more_on_docker_with_gpu_support/ | dnib | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 19bd974 | false | null | t3_19bd974 | /r/LocalLLaMA/comments/19bd974/run_mistral7b_and_more_on_docker_with_gpu_support/ | false | false | self | 6 | {'enabled': False, 'images': [{'id': 'ylg0P_l4tRkC2oK_g8JQ2CqS_9dLTVl6JFArtcNOovE', 'resolutions': [{'height': 54, 'url': 'https://external-preview.redd.it/E6a_avMAv1Kf9eIYuO1POWN4sJCQg9zPz45SxvIt3Dk.jpg?width=108&crop=smart&auto=webp&s=e4c98e8069b25fed7832641b286a286338c26b01', 'width': 108}, {'height': 108, 'url': 'h... |
Subsets and Splits
No community queries yet
The top public SQL queries from the community will appear here once available.