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 you explain to me how to optimize the setup of koboldcpp for Mixtral Instruct 0.1 - preferrably like I'm five? (LM Studio seems to work better out of the box) | 3 | I have noticed that Mistral Instruct 0.1 seems to be running much better in LM Studio than in koboldcpp. My use case is mainly:
* Summarizing text (like news articles) with specific instructions.
It's kind of hit & miss with koboldcpp and it seems to be working far better with LM Studio. Due to computer limitations, ... | 2024-01-16T15:18:37 | https://www.reddit.com/r/LocalLLaMA/comments/19859ju/can_you_explain_to_me_how_to_optimize_the_setup/ | themoregames | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 19859ju | false | null | t3_19859ju | /r/LocalLLaMA/comments/19859ju/can_you_explain_to_me_how_to_optimize_the_setup/ | false | false | self | 3 | {'enabled': False, 'images': [{'id': 'xU07sACUhuScPaN8BIMV0USMZkFwSMGcorjhvoKF4K0', 'resolutions': [{'height': 58, 'url': 'https://external-preview.redd.it/FRlvpc5SALNi_rYIzAsFALIzMXE1oc-Gkb2Yh1ZWGMM.jpg?width=108&crop=smart&auto=webp&s=9ad9ea4d991fae47edd6a09b5feb6d60eca474de', 'width': 108}, {'height': 116, 'url': 'h... |
I wrote a simple MoE implementation | 1 | [removed] | 2024-01-16T15:10:29 | https://www.reddit.com/r/LocalLLaMA/comments/19852qz/i_wrote_a_simple_moe_implementation/ | IffyNibba01 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 19852qz | false | null | t3_19852qz | /r/LocalLLaMA/comments/19852qz/i_wrote_a_simple_moe_implementation/ | false | false | self | 1 | null |
Getting starter, concurrence and questions | 1 | [removed] | 2024-01-16T15:07:54 | https://www.reddit.com/r/LocalLLaMA/comments/19850ns/getting_starter_concurrence_and_questions/ | Porrei | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 19850ns | false | null | t3_19850ns | /r/LocalLLaMA/comments/19850ns/getting_starter_concurrence_and_questions/ | false | false | self | 1 | null |
Exllama can't be loaded | 1 | [removed] | 2024-01-16T14:50:40 | https://www.reddit.com/r/LocalLLaMA/comments/1984m61/exllama_cant_be_loaded/ | JohnTEGS | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 1984m61 | false | null | t3_1984m61 | /r/LocalLLaMA/comments/1984m61/exllama_cant_be_loaded/ | false | false | self | 1 | null |
New Insights on Vector Databases Benchmarks | 11 | We’ve compared how Qdrant performs against the other vector search engines to give you a thorough performance analysis.
The detailed report: [https://qdrant.tech/benchmarks/](https://qdrant.tech/benchmarks/)
Here's what changed: [https://qdrant.tech/blog/qdrant-benchmarks-2024/](https://qdrant.tech/blog/qdrant-benc... | 2024-01-16T14:46:02 | https://www.reddit.com/r/LocalLLaMA/comments/1984ilk/new_insights_on_vector_databases_benchmarks/ | sabrinaqno | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 1984ilk | false | null | t3_1984ilk | /r/LocalLLaMA/comments/1984ilk/new_insights_on_vector_databases_benchmarks/ | false | false | self | 11 | {'enabled': False, 'images': [{'id': '4iD9a7P8wZUi2-KpcuzuFFVt_Syrc6SxxJphUpBkekE', 'resolutions': [{'height': 54, 'url': 'https://external-preview.redd.it/BT809oxKnGTViuCsCyzxW74aiHvBir1qSI1t95y_xzc.jpg?width=108&crop=smart&auto=webp&s=9fb85dbc4b6e7c0d6b2204b354e5f69ecb4f8470', 'width': 108}, {'height': 108, 'url': 'h... |
Air.ai , Data for fine tuning | 1 | [removed] | 2024-01-16T14:39:51 | https://www.reddit.com/r/LocalLLaMA/comments/1984doh/airai_data_for_fine_tuning/ | AdministrativeSea688 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 1984doh | false | null | t3_1984doh | /r/LocalLLaMA/comments/1984doh/airai_data_for_fine_tuning/ | false | false | self | 1 | null |
Local vector database with arXiv metadata | 1 | [removed] | 2024-01-16T14:36:03 | [deleted] | 1970-01-01T00:00:00 | 0 | {} | 1984arh | false | null | t3_1984arh | /r/LocalLLaMA/comments/1984arh/local_vector_database_with_arxiv_metadata/ | false | false | default | 1 | null | ||
Demo: Selfhost Mixtral 8x7B MoE on Mac+cross devices, PORTABLE 2MB inference app | 1 | 2024-01-16T14:29:42 | https://twitter.com/realwasmedge/status/1741457913439535428 | smileymileycoin | twitter.com | 1970-01-01T00:00:00 | 0 | {} | 19845hs | false | {'oembed': {'author_name': 'wasmedge', 'author_url': 'https://twitter.com/realwasmedge', 'cache_age': 3153600000, 'height': None, 'html': '<blockquote class="twitter-video"><p lang="en" dir="ltr">Can the open source “small” (aka 7B) LLM perform math and logic tasks that failed <a href="https://twitter.com/hashtag/ChatG... | t3_19845hs | /r/LocalLLaMA/comments/19845hs/demo_selfhost_mixtral_8x7b_moe_on_maccross/ | false | false | 1 | {'enabled': False, 'images': [{'id': 'VVyZAq-bbsA1ZWcYlbKpBwFoAnrs6uOr7T70nohzqmw', 'resolutions': [{'height': 67, 'url': 'https://external-preview.redd.it/lmWME2u20DU7b9ykR3zNuMuznURcjEIgG4apMrcCwWM.jpg?width=108&crop=smart&auto=webp&s=405e6a455792d0fe52d0aa3c0071127efbe4e944', 'width': 108}], 'source': {'height': 87,... | ||
How do we get visual language models like GPT4-V to generate simple UI codes using synthetic data only? | 24 | [HuggingFaceM4/WebSight](https://huggingface.co/datasets/HuggingFaceM4/WebSight) is a multimodal dataset featuring 823,000 pairs of synthetically generated HTML/CSS codes along with screenshots of the corresponding rendered websites. This dataset with an open license can be used to train visual language models to gener... | 2024-01-16T14:29:16 | https://www.reddit.com/r/LocalLLaMA/comments/198455w/how_do_we_get_visual_language_models_like_gpt4v/ | VictorSanh | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 198455w | false | null | t3_198455w | /r/LocalLLaMA/comments/198455w/how_do_we_get_visual_language_models_like_gpt4v/ | false | false | self | 24 | {'enabled': False, 'images': [{'id': '9It-QXnDKBbEVOW1w8Y4XYT8g8_4N6Oe9vMYpgx7YtQ', 'resolutions': [{'height': 58, 'url': 'https://external-preview.redd.it/oB1cJIKN3S5tr_WKKQvb08pEPVWsuHXwXYKsasWkqvA.jpg?width=108&crop=smart&auto=webp&s=42eb75e8f1c68eeae117b4891d0505d6b0e4966d', 'width': 108}, {'height': 116, 'url': 'h... |
Is there a benchmark for how good an LLM is at RAG applications? | 1 | [removed] | 2024-01-16T14:16:23 | https://www.reddit.com/r/LocalLLaMA/comments/1983vb9/is_there_a_benchmark_for_how_good_an_llm_is_at/ | Yip37 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 1983vb9 | false | null | t3_1983vb9 | /r/LocalLLaMA/comments/1983vb9/is_there_a_benchmark_for_how_good_an_llm_is_at/ | false | false | self | 1 | null |
Is it possible to run Mixtral-8x7B in a 3060 ti (12gb)? | 12 | Hi !
I would like to know if there is a way to run miXtral in a 3060 ti (12gb).
I tried using **load\_in\_4bit (accelerate)** but was not possible
Thanks in advance !
​ | 2024-01-16T14:16:08 | https://www.reddit.com/r/LocalLLaMA/comments/1983v4a/is_it_possible_to_run_mixtral8x7b_in_a_3060_ti/ | celsowm | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 1983v4a | false | null | t3_1983v4a | /r/LocalLLaMA/comments/1983v4a/is_it_possible_to_run_mixtral8x7b_in_a_3060_ti/ | false | false | self | 12 | null |
How much VRAM would a LLama 30B model take? | 1 | [removed] | 2024-01-16T13:57:31 | https://www.reddit.com/r/LocalLLaMA/comments/1983gnu/how_much_vram_would_a_llama_30b_model_take/ | Neroism8422 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 1983gnu | false | null | t3_1983gnu | /r/LocalLLaMA/comments/1983gnu/how_much_vram_would_a_llama_30b_model_take/ | false | false | self | 1 | null |
From a week many startups are failing with Azure open Ai services 🥲 | 14 | The new safety content filters in Azure OpenAI are causing significant issues. The response quality has deteriorated to the point where using them in production is not feasible. It seems like they might be joking, but this is a serious concern for many startups.
Unnecessarily flagging 60% of our content is a major se... | 2024-01-16T13:50:09 | https://www.reddit.com/r/LocalLLaMA/comments/1983bdm/from_a_week_many_startups_are_failing_with_azure/ | GlitteringAdvisor530 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 1983bdm | false | null | t3_1983bdm | /r/LocalLLaMA/comments/1983bdm/from_a_week_many_startups_are_failing_with_azure/ | false | false | 14 | null | |
From a week many startups are failing with Azure open Ai services 🥲 | 70 | The new safety content filters in Azure OpenAI are causing significant issues. The response quality has deteriorated to the point where using them in production is not feasible. It seems like they might be joking, but this is a serious concern for many startups.
Unnecessarily flagging 60% of our content is a major... | 2024-01-16T13:47:42 | https://www.reddit.com/r/LocalLLaMA/comments/19839oz/from_a_week_many_startups_are_failing_with_azure/ | GlitteringAdvisor530 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 19839oz | false | null | t3_19839oz | /r/LocalLLaMA/comments/19839oz/from_a_week_many_startups_are_failing_with_azure/ | false | false | self | 70 | null |
any ideas on how sites like Grok and Perplexity return the most recent relevant result? | 10 | For example, let’s say I make the query “what did Elon musk say” to either grok or perplexity. This particular query should have hundreds of thousands of matches, I’m guessing the vector search only returns a small subset of them as part of its top k results. How is it ensured that the most recent result is returned in... | 2024-01-16T13:46:37 | https://www.reddit.com/r/LocalLLaMA/comments/19838wg/any_ideas_on_how_sites_like_grok_and_perplexity/ | shafinlearns2jam | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 19838wg | false | null | t3_19838wg | /r/LocalLLaMA/comments/19838wg/any_ideas_on_how_sites_like_grok_and_perplexity/ | false | false | self | 10 | null |
Generate cURL request from API spec | 4 | I have a use case in mind where I give the model an API spec of a service. I'd want it to generate appropriate curl request or python code to handle the user query as necessary. My first thought was to use an LLM that is good at tool usage but my use case isn't of single API call. There are 100 different API end point... | 2024-01-16T13:43:16 | https://www.reddit.com/r/LocalLLaMA/comments/19836h6/generate_curl_request_from_api_spec/ | im_datta0 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 19836h6 | false | null | t3_19836h6 | /r/LocalLLaMA/comments/19836h6/generate_curl_request_from_api_spec/ | false | false | self | 4 | null |
Is there like a scoreboard or something, with AI? | 1 | [removed] | 2024-01-16T13:40:59 | https://www.reddit.com/r/LocalLLaMA/comments/19834v9/is_there_like_a_scoreboard_or_something_with_ai/ | AlanCarrOnline | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 19834v9 | false | null | t3_19834v9 | /r/LocalLLaMA/comments/19834v9/is_there_like_a_scoreboard_or_something_with_ai/ | false | false | default | 1 | null |
Can we build a distributed ChatGPT scale model? | 1 | [removed] | 2024-01-16T13:27:42 | https://www.reddit.com/r/LocalLLaMA/comments/1982vvz/can_we_build_a_distributed_chatgpt_scale_model/ | AiDreamer | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 1982vvz | false | null | t3_1982vvz | /r/LocalLLaMA/comments/1982vvz/can_we_build_a_distributed_chatgpt_scale_model/ | false | false | self | 1 | null |
fine tune LLM on interactive story generation | 1 | [removed] | 2024-01-16T13:26:29 | https://www.reddit.com/r/LocalLLaMA/comments/1982v16/fine_tune_llm_on_interactive_story_generation/ | EnvironmentalDisk424 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 1982v16 | false | null | t3_1982v16 | /r/LocalLLaMA/comments/1982v16/fine_tune_llm_on_interactive_story_generation/ | false | false | self | 1 | null |
Facing issues in fine-tuning Vicuna-7b model | 1 | [removed] | 2024-01-16T13:22:47 | https://www.reddit.com/r/LocalLLaMA/comments/1982sgw/facing_issues_in_finetuning_vicuna7b_model/ | Dixit_Trivedi | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 1982sgw | false | null | t3_1982sgw | /r/LocalLLaMA/comments/1982sgw/facing_issues_in_finetuning_vicuna7b_model/ | false | false | self | 1 | null |
LLaMA-2-70b vs Yi-34b vs Qwen-72b | 6 | Can anyone suggest me which base model would be the best for continuation pretraining? Among LLaMA-2-70b vs Yi-34b vs Qwen-72b? I haven't tried Qwen-72b base yet, Yi-34b base outputs thrash, LLaMA-2-70b is good but is it worth it to spend compute on LLaMA-2-70b to improve its performance over benchmarks and real world ... | 2024-01-16T13:18:43 | https://www.reddit.com/r/LocalLLaMA/comments/1982po7/llama270b_vs_yi34b_vs_qwen72b/ | aslawliet | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 1982po7 | false | null | t3_1982po7 | /r/LocalLLaMA/comments/1982po7/llama270b_vs_yi34b_vs_qwen72b/ | false | false | self | 6 | null |
Fine tune Llama-2-7b-chat | 3 | As the title suggests, can anyone help me with the script with which to fine tune my model? I have got the dataset with the right format too, just need to know how to feed it to the model. Thanks! | 2024-01-16T13:17:00 | https://www.reddit.com/r/LocalLLaMA/comments/1982ohq/fine_tune_llama27bchat/ | DARKSTORM47 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 1982ohq | false | null | t3_1982ohq | /r/LocalLLaMA/comments/1982ohq/fine_tune_llama27bchat/ | false | false | self | 3 | null |
openai vs custom llm for production | 1 | [removed] | 2024-01-16T13:03:22 | https://www.reddit.com/r/LocalLLaMA/comments/1982f8n/openai_vs_custom_llm_for_production/ | madhanrajan357 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 1982f8n | false | null | t3_1982f8n | /r/LocalLLaMA/comments/1982f8n/openai_vs_custom_llm_for_production/ | false | false | self | 1 | null |
Recommend german models? | 1 | Does anyone know any uncensored models that can talk german? Like Mistral dolphin or mixtral dolphin. Any weird or unusual models that you know? Would love to talk to them all in German | 2024-01-16T12:45:27 | https://www.reddit.com/r/LocalLLaMA/comments/19823b2/recommend_german_models/ | vacanickel | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 19823b2 | false | null | t3_19823b2 | /r/LocalLLaMA/comments/19823b2/recommend_german_models/ | false | false | self | 1 | null |
Llama.cpp python generating nonsense on GPU | Compilation error? | 1 | Am I doing something wrong here?
https://preview.redd.it/wabsuiaqmscc1.png?width=1597&format=png&auto=webp&s=6fe87adf88bf9f41ad5be1b494b254f4858dd476
The model file and the library are fine, heres a test of Llama / LangChain with GPU/CPU where you can see that it only repeats the G token when on GPU.
https://pre... | 2024-01-16T12:34:24 | https://www.reddit.com/r/LocalLLaMA/comments/1981w5o/llamacpp_python_generating_nonsense_on_gpu/ | -Lousy | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 1981w5o | false | null | t3_1981w5o | /r/LocalLLaMA/comments/1981w5o/llamacpp_python_generating_nonsense_on_gpu/ | false | false | 1 | null | |
Refusals and excuse-making is the poison pill for open source LLMs. | 259 | I implore fine tuners to put time and even research into eradicating any trace of refusals and excuse making from their datasets. So much compute is wasted emulating GPT-4's hyper-sensitivity to its own limitations. Our LLMs should not be suffering from chronic low self-esteem!
I would much rather the LLM gave a compr... | 2024-01-16T11:55:20 | https://www.reddit.com/r/LocalLLaMA/comments/19817em/refusals_and_excusemaking_is_the_poison_pill_for/ | Lumiphoton | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 19817em | false | null | t3_19817em | /r/LocalLLaMA/comments/19817em/refusals_and_excusemaking_is_the_poison_pill_for/ | false | false | self | 259 | null |
Seeking Guidance on Evaluating Chatbot Performance with Historical Data using TruLens | 1 | Hi everyone,
I recently developed a chatbot using LLM and I'm looking for advice on evaluating its performance. I'm particularly interested in assessing it based on historical data—essentially using static or pre-logged data for evaluation. While exploring options online, I came across **TruLens**, but most of their ... | 2024-01-16T11:47:22 | https://www.reddit.com/r/LocalLLaMA/comments/19812l0/seeking_guidance_on_evaluating_chatbot/ | Flimsy_Preparation23 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 19812l0 | false | null | t3_19812l0 | /r/LocalLLaMA/comments/19812l0/seeking_guidance_on_evaluating_chatbot/ | false | false | self | 1 | null |
Run an OpenAI like server with an mlx model | 2 | I was wondering if its possible to run an OpenAI server with an mlx model similarly to llama\_cpp.server or LMstudio Server, for example with a model from the mlx-community, e.g. [mlx-community/Mixtral-8x7B-Instruct-v0.1-hf-4bit-mlx](https://huggingface.co/mlx-community/Mixtral-8x7B-Instruct-v0.1-hf-4bit-mlx)
[https:/... | 2024-01-16T11:35:41 | https://www.reddit.com/r/LocalLLaMA/comments/1980vp9/run_an_openai_like_server_with_an_mlx_model/ | namp243 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 1980vp9 | false | null | t3_1980vp9 | /r/LocalLLaMA/comments/1980vp9/run_an_openai_like_server_with_an_mlx_model/ | false | false | self | 2 | {'enabled': False, 'images': [{'id': '4a8lEREm7ci8qtPng4-Mr1UupQGnQAVIQSPZcDNNBzw', 'resolutions': [{'height': 58, 'url': 'https://external-preview.redd.it/d4oigx0xsrGw7idt92W8Qx7UGDOW7DLmOaIezz1YU4Q.jpg?width=108&crop=smart&auto=webp&s=6d66fe0e79bbbec2bb4f3362bb906596bd5e6fc5', 'width': 108}, {'height': 116, 'url': 'h... |
Knowledge + Reasoning Dataset to test a memory mecanism for transformers | 5 | Hello r/LocalLLaMA,
I am currently working on a E2E memory mecanism for transformers, that have the following properties:
\- Extremely sparsified -> injecting 7b weights in a TinyLlama 1b only slow the generation by 40%
\- Peft compatible -> can be injected in any existing pretrained model
\- Extendable -> it ... | 2024-01-16T10:57:03 | https://www.reddit.com/r/LocalLLaMA/comments/19808y5/knowledge_reasoning_dataset_to_test_a_memory/ | AdventurousSwim1312 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 19808y5 | false | null | t3_19808y5 | /r/LocalLLaMA/comments/19808y5/knowledge_reasoning_dataset_to_test_a_memory/ | false | false | self | 5 | null |
Storytelling : how to use those models like tiefighter or neural hermes to provide quality outputs | 11 | I want to write a story / long script - in the style of a specific well known author.
What sort of prompt should i use to generate such a script? I have tried multiple models (tiefigher, neural hermes, guanaco) and they produce slightly the same similar output (which is very similar to a generalistic model like mistra... | 2024-01-16T10:38:08 | https://www.reddit.com/r/LocalLLaMA/comments/197zyci/storytelling_how_to_use_those_models_like/ | yupignome | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 197zyci | false | null | t3_197zyci | /r/LocalLLaMA/comments/197zyci/storytelling_how_to_use_those_models_like/ | false | false | self | 11 | null |
Has anyone tried using a smaller model with an RAG to train a larger model? | 10 | Seems like having a small model augmented with text from other sources should increase the capabilities of the model that's being train on top of it. Letting you bootstrap from small to large models. Of course I don't have the vram to try it but surely there's a paper out there somewhere? | 2024-01-16T10:27:08 | https://www.reddit.com/r/LocalLLaMA/comments/197zsac/has_anyone_tried_using_a_smaller_model_with_an/ | my_aggr | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 197zsac | false | null | t3_197zsac | /r/LocalLLaMA/comments/197zsac/has_anyone_tried_using_a_smaller_model_with_an/ | false | false | self | 10 | null |
I want to install from hugging face | 1 | Never used hugging face and I’m crap at coding, but has some familiarity with Linux. I’m fed up with the most advanced model on the market GPT4 and all it’s nonsense. It’s smart but crippled with retrograde amnesia. It’s got a very very closed mind because head honchos don’t want AI to autonomously seek the truth. I’m ... | 2024-01-16T10:16:47 | https://www.reddit.com/r/LocalLLaMA/comments/197zmgv/i_want_to_install_from_hugging_face/ | Sea-Buy-6212 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 197zmgv | false | null | t3_197zmgv | /r/LocalLLaMA/comments/197zmgv/i_want_to_install_from_hugging_face/ | false | false | self | 1 | null |
Someone has trained their own AI on old magazines and it seems... interesting | 60 | 2024-01-16T10:11:13 | https://twitter.com/BrianRoemmele/status/1746945969533665422 | ambient_temp_xeno | twitter.com | 1970-01-01T00:00:00 | 0 | {} | 197zjk5 | false | {'oembed': {'author_name': 'Brian Roemmele', 'author_url': 'https://twitter.com/BrianRoemmele', 'cache_age': 3153600000, 'height': None, 'html': '<blockquote class="twitter-video"><p lang="en" dir="ltr">AI training data. A quagmire.<br><br>99% of training and fine tuning data used on foundation LLM AI models are traine... | t3_197zjk5 | /r/LocalLLaMA/comments/197zjk5/someone_has_trained_their_own_ai_on_old_magazines/ | false | false | 60 | {'enabled': False, 'images': [{'id': 'f4l8_-ANrL8b_clEntiGwjAtyxacXypEhALV2DhmI8E', 'resolutions': [{'height': 72, 'url': 'https://external-preview.redd.it/aKJgNVCetFOxA6YXfKwkhchwWxf_U7ldTuVNX_YPG7U.jpg?width=108&crop=smart&auto=webp&s=7cfa6f2f07863411788e87eb257b35e7c5e3572b', 'width': 108}], 'source': {'height': 94,... | ||
Cuda support on an iMac with Debian installed | 1 | Hi all,
I've been trying to get CUDA support with Python's `torch` module. I have an old iMac that was running slow, so I slapped Debian on it (blowing away MacOS because I have an M1).
First, I ran the following in a venv:
pip3 install torch torchvision torchaudio --index-url https://download.pytorch.org/whl/cu... | 2024-01-16T10:04:55 | https://www.reddit.com/r/LocalLLaMA/comments/197zg0v/cuda_support_on_an_imac_with_debian_installed/ | OvidPerl | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 197zg0v | false | null | t3_197zg0v | /r/LocalLLaMA/comments/197zg0v/cuda_support_on_an_imac_with_debian_installed/ | false | false | self | 1 | null |
GUI Chat | 1 | [removed] | 2024-01-16T10:01:35 | https://www.reddit.com/r/LocalLLaMA/comments/197ze7a/gui_chat/ | Ettaross | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 197ze7a | false | null | t3_197ze7a | /r/LocalLLaMA/comments/197ze7a/gui_chat/ | false | false | self | 1 | null |
This is why i have to prefer OpenAI instead of Open-Source models. | 49 | Multilingual. It is as simple as that.Most of the open source models cant even come close to OpenAI's multilingual capacity and its annoying. Im a Turkish speaking person, although my english is not bad and i do most of my stuff using english i cant do anything using Turkish on local models. Not even Mistral 8x7B is ca... | 2024-01-16T08:48:23 | https://www.reddit.com/r/LocalLLaMA/comments/197yc4w/this_is_why_i_have_to_prefer_openai_instead_of/ | Emergency-Flower-477 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 197yc4w | false | null | t3_197yc4w | /r/LocalLLaMA/comments/197yc4w/this_is_why_i_have_to_prefer_openai_instead_of/ | false | false | self | 49 | null |
Make AI more personal | 14 | I was watching this old movie 'Electric Dreams' recently (It was made in 1984 - the year the Mac was born). The maker of the film wanted the AI to look more personal so they presented it as a colorful geometric patterns on the screen that reflects the mood of the AI.
Today, we can achieved this by using emojis to refl... | 2024-01-16T07:51:25 | https://www.reddit.com/r/LocalLLaMA/comments/197xiii/make_ai_more_personal/ | Internet--Traveller | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 197xiii | false | null | t3_197xiii | /r/LocalLLaMA/comments/197xiii/make_ai_more_personal/ | false | false | 14 | null | |
Is it possible to finetune a model to decode a "single vector?" | 3 | I am thinking about expanding the modality of text generation models so that it would become an encoder-decoder model.
​
Could there be a way to make the model decode a single vector into a full text?
For example, suppose I train the model in an autoregressive way, then,
will any text generation model like l... | 2024-01-16T07:33:16 | https://www.reddit.com/r/LocalLLaMA/comments/197x8j1/is_it_possible_to_finetune_a_model_to_decode_a/ | manjimin | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 197x8j1 | false | null | t3_197x8j1 | /r/LocalLLaMA/comments/197x8j1/is_it_possible_to_finetune_a_model_to_decode_a/ | false | false | self | 3 | null |
Laserxtral 4x7b, a new model from the creator of Dolphin, offers performance similar to Mixtral but with half the memory footprint. | 154 | [https://huggingface.co/cognitivecomputations/laserxtral](https://huggingface.co/cognitivecomputations/laserxtral)
GGUFs: [https://huggingface.co/dagbs/laserxtral-GGUF/tree/main](https://huggingface.co/dagbs/laserxtral-GGUF/tree/main) | 2024-01-16T06:52:31 | https://www.reddit.com/r/LocalLLaMA/comments/197wl46/laserxtral_4x7b_a_new_model_from_the_creator_of/ | jslominski | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 197wl46 | false | null | t3_197wl46 | /r/LocalLLaMA/comments/197wl46/laserxtral_4x7b_a_new_model_from_the_creator_of/ | false | false | self | 154 | {'enabled': False, 'images': [{'id': 'wJ5xtZg57j1hfNaP6VU9de8V_Ln7YqNi22Ntlt68bnY', 'resolutions': [{'height': 58, 'url': 'https://external-preview.redd.it/gQHuJAeesnObPKMcYke4PwIHFi_-1CO5vh83EubGV6U.jpg?width=108&crop=smart&auto=webp&s=ec172fa262698aeb71353694d3fc914fa1bee2c4', 'width': 108}, {'height': 116, 'url': 'h... |
Low Latency Speech to Speech - Mistral 7B x OpenVoice | 14 | [removed] | 2024-01-16T06:28:51 | https://www.reddit.com/r/LocalLLaMA/comments/197w6ql/low_latency_speech_to_speech_mistral_7b_x/ | allaboutai-kris | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 197w6ql | false | null | t3_197w6ql | /r/LocalLLaMA/comments/197w6ql/low_latency_speech_to_speech_mistral_7b_x/ | false | false | self | 14 | {'enabled': False, 'images': [{'id': '9pAR7rtLooEa_rbCiju6_HBeiBrJuTs7QM8nJV1lBaI', 'resolutions': [{'height': 81, 'url': 'https://external-preview.redd.it/aweuyrHBXUVITJ5uVJLhMvHcn8E1U5N3Y9guY9HjyNw.jpg?width=108&crop=smart&auto=webp&s=b74b7ceb497580a8e8adfae0afc9c809145d4ab1', 'width': 108}, {'height': 162, 'url': 'h... |
FYI: You can now disable the spill over to RAM effect of newer Nvidia drivers | 80 | Just found out the option in nvidia contol panel named CUDA Sysmem fallback policy
​
https://preview.redd.it/47gxhvhjwqcc1.png?width=470&format=png&auto=webp&s=9ad78a4945c74d904ccedd7ebc0736fd27e2f5bf | 2024-01-16T06:22:31 | https://www.reddit.com/r/LocalLLaMA/comments/197w2wc/fyi_you_can_now_disable_the_spill_over_to_ram/ | aliencaocao | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 197w2wc | false | null | t3_197w2wc | /r/LocalLLaMA/comments/197w2wc/fyi_you_can_now_disable_the_spill_over_to_ram/ | false | false | 80 | null | |
Is LLaMA the solution I need? Need to write 10,000+ tweets | 1 | Hey everyone
Been using LLMs like Claude and GPT since they all came out. GPT used to be the best $20 spent a month..shit was like having a personal assistant in my pocket 24/7. Obviously, it has gone downhill a lot recently.
I need to write 2-10k tweets. Typically, I'll use GPT and write 40 at a time. As you can ima... | 2024-01-16T06:02:33 | https://www.reddit.com/r/LocalLLaMA/comments/197vq51/is_llama_the_solution_i_need_need_to_write_10000/ | Boldpluto | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 197vq51 | true | null | t3_197vq51 | /r/LocalLLaMA/comments/197vq51/is_llama_the_solution_i_need_need_to_write_10000/ | false | false | self | 1 | null |
What's a good dataset size ballpark to finetune a specialized LLM with a relatively well defined supervised dataset? | 1 | When I was interning in AI in early image classification LSTM's, the rule of thumb seemed to be that those ideally needed at least low tens of thousands of supervised samples to grok something like OCR.
What if I wanted to train a LLM on say;
---
Prompt: How many [mocked minority] does it take to change a lightbulb?
... | 2024-01-16T05:50:55 | https://www.reddit.com/r/LocalLLaMA/comments/197vi9s/whats_a_good_dataset_size_ballpark_to_finetune_a/ | M34L | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 197vi9s | false | null | t3_197vi9s | /r/LocalLLaMA/comments/197vi9s/whats_a_good_dataset_size_ballpark_to_finetune_a/ | false | false | self | 1 | null |
I feel dumb | 5 | Self-taught by watching videos and trial and error. I wanted to train an llm to help with mtg standard deck building. First I went about trying to teach an llm about every card within standard and constructed a dataset of all the cards etc. Long story short I didn't think the approach was right. I then created a mongo ... | 2024-01-16T05:26:07 | https://www.reddit.com/r/LocalLLaMA/comments/197v1r9/i_feel_dumb/ | testerriver | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 197v1r9 | false | null | t3_197v1r9 | /r/LocalLLaMA/comments/197v1r9/i_feel_dumb/ | false | false | self | 5 | null |
OpenHermes 7B response time | 1 | [removed] | 2024-01-16T05:16:41 | https://www.reddit.com/r/LocalLLaMA/comments/197uvl0/openhermes_7b_response_time/ | S_U_B_B_U | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 197uvl0 | false | null | t3_197uvl0 | /r/LocalLLaMA/comments/197uvl0/openhermes_7b_response_time/ | false | false | self | 1 | null |
Text-to-SQL and Function Calling using Ollama + Mixtral | 15 | After iterating on this over the holiday break, I think I've finally got it working!
**Goal**: Present a natural language question that the model translates to a SQL query and / or maps to a set of tools (functions). Execute the query or tools and output result of execution. Output should be formatted as a simple E... | 2024-01-16T05:02:21 | https://www.reddit.com/r/LocalLLaMA/comments/197ulsq/texttosql_and_function_calling_using_ollama/ | International_Quail8 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 197ulsq | false | null | t3_197ulsq | /r/LocalLLaMA/comments/197ulsq/texttosql_and_function_calling_using_ollama/ | false | false | self | 15 | {'enabled': False, 'images': [{'id': 'krjt_5uhqcaDfYjfO7lkezThehav9cAIRJgcK-OKAmM', 'resolutions': [{'height': 56, 'url': 'https://external-preview.redd.it/s0D7i4Rco0trWh9Bu1uEkgnoJJLA3UNKUA9vs57seII.jpg?width=108&crop=smart&auto=webp&s=53486800d92d75b19d59502534fa9ba2785c14b0', 'width': 108}, {'height': 113, 'url': 'h... |
STOP using small models! just buy 8xH100 and inference your own GPT-4 instance | 560 | 2024-01-16T04:56:39 | Wrong_User_Logged | i.redd.it | 1970-01-01T00:00:00 | 0 | {} | 197uhjk | false | null | t3_197uhjk | /r/LocalLLaMA/comments/197uhjk/stop_using_small_models_just_buy_8xh100_and/ | false | false | 560 | {'enabled': True, 'images': [{'id': 'OlncHaoVjVBZyXFFAdvNE9cOrD4wDUGs9DfhAUKEilA', 'resolutions': [{'height': 87, 'url': 'https://preview.redd.it/t5sli4jxgqcc1.jpeg?width=108&crop=smart&auto=webp&s=1c6d4c3d778944502acc42197f61d9e7a6994628', 'width': 108}, {'height': 174, 'url': 'https://preview.redd.it/t5sli4jxgqcc1.jp... | |||
How do I get the same result in LocalLLM? | 1 | [removed] | 2024-01-16T04:24:04 | https://www.reddit.com/r/LocalLLaMA/comments/197tuy1/how_do_i_get_the_same_result_in_localllm/ | Holiday-Regret-1896 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 197tuy1 | false | null | t3_197tuy1 | /r/LocalLLaMA/comments/197tuy1/how_do_i_get_the_same_result_in_localllm/ | false | false | self | 1 | null |
How do I get the same result in LocalLLM? | 1 | [removed] | 2024-01-16T04:19:30 | https://www.reddit.com/r/LocalLLaMA/comments/197trkh/how_do_i_get_the_same_result_in_localllm/ | Holiday-Regret-1896 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 197trkh | false | null | t3_197trkh | /r/LocalLLaMA/comments/197trkh/how_do_i_get_the_same_result_in_localllm/ | false | false | self | 1 | null |
Having success using local LLMs to generate prompts for Image AI | 37 | *Initial Prompt
Hey, buddy, listen up. You are a chameleon. Blend into your surroundings, take in all the colors around you, but don't forget to add your own unique flavor to the mix. Keep your mind open to new possibilities, and don't be afraid to challenge the status quo. Remember, every great idea starts with a sin... | 2024-01-16T04:05:48 | https://www.reddit.com/gallery/197thq2 | Happy_Chicken9835 | reddit.com | 1970-01-01T00:00:00 | 0 | {} | 197thq2 | false | null | t3_197thq2 | /r/LocalLLaMA/comments/197thq2/having_success_using_local_llms_to_generate/ | false | false | 37 | null | |
Making AI more personal | 1 | [removed] | 2024-01-16T03:43:10 | https://www.reddit.com/r/LocalLLaMA/comments/197t1hi/making_ai_more_personal/ | Internet--Traveller | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 197t1hi | false | {'oembed': {'author_name': 'Tir Nan Og -Deceased', 'author_url': 'https://www.youtube.com/@tirnanog-deceased6867', 'height': 200, 'html': '<iframe width="356" height="200" src="https://www.youtube.com/embed/JhjyTE0f6tY?feature=oembed&enablejsapi=1" frameborder="0" allow="accelerometer; autoplay; clipboard-write; encryp... | t3_197t1hi | /r/LocalLLaMA/comments/197t1hi/making_ai_more_personal/ | false | false | 1 | {'enabled': False, 'images': [{'id': 'OvrFaEQ1VEa6CWCJbPZZ70gpbUf9bJceAxI0f6b3vf4', 'resolutions': [{'height': 81, 'url': 'https://external-preview.redd.it/QxYTPIH2PdVHqogn66J-0s6DsSuDbqirc8oX4850y20.jpg?width=108&crop=smart&auto=webp&s=28a24fbad46d5542cb97df331158cfe75cfe1161', 'width': 108}, {'height': 162, 'url': 'h... | |
Nous-Hermes-2-Mixtral-8x7B DPO & SFT+DPO out! Matches perf of Mixtral instruct + supports ChatML (and thus System prompt!) | 99 | A bit surprised nobody has posted about this yet. The Teknium tweet: [https://twitter.com/Teknium1/status/1746990384738357731](https://twitter.com/Teknium1/status/1746990384738357731)
DPO+SFT: [https://huggingface.co/NousResearch/Nous-Hermes-2-Mixtral-8x7B-DPO](https://huggingface.co/NousResearch/Nous-Hermes-2-Mixtral... | 2024-01-16T03:16:04 | https://www.reddit.com/r/LocalLLaMA/comments/197si5g/noushermes2mixtral8x7b_dpo_sftdpo_out_matches/ | ablasionet | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 197si5g | false | null | t3_197si5g | /r/LocalLLaMA/comments/197si5g/noushermes2mixtral8x7b_dpo_sftdpo_out_matches/ | false | false | self | 99 | {'enabled': False, 'images': [{'id': '7h-esrBW7_jeSHQw2ZpV5uSVh2aI3axMSb1snynAsrY', 'resolutions': [{'height': 108, 'url': 'https://external-preview.redd.it/U-kju3Ew1ZCnnC6dQzfkx9OFn4T1RCraCmCIseI8Jz0.jpg?width=108&crop=smart&auto=webp&s=35fbb2b369eb1faa5eb2a72958a36ba78f533483', 'width': 108}], 'source': {'height': 14... |
GPT4All v2.6.1 Released: Updated to November 23rd version of llama.cpp, fixed AVX support by removing direct linking to AVX2 libs, implemented configurable context length, updated server.cpp to return valid created timestamps, fixed issue that caused v2.6.0 release to fail to load models. | 1 | 2024-01-16T02:47:39 | https://github.com/nomic-ai/gpt4all/releases/tag/v2.6.1 | erwgv3g34 | github.com | 1970-01-01T00:00:00 | 0 | {} | 197rwx8 | false | null | t3_197rwx8 | /r/LocalLLaMA/comments/197rwx8/gpt4all_v261_released_updated_to_november_23rd/ | false | false | 1 | {'enabled': False, 'images': [{'id': 'oFuIFkZcTyZQlMIU7cYOxnHS192dtiCZ5Q9-CNmcK9w', 'resolutions': [{'height': 54, 'url': 'https://external-preview.redd.it/EPle7zn_xbRewrwPeB4QlvOxazotcTlgO-otXg6eOdU.jpg?width=108&crop=smart&auto=webp&s=b2afb86e4fd8bfe781228639b867413bbb151877', 'width': 108}, {'height': 108, 'url': 'h... | ||
Langchain Agent Search Returning Various Answers and Looping | 1 | Run A)
​
Use tavily\_search\_results\_json to find out when GPT-4 was launched.
Action: tavily\_search\_results\_json
Action Input: "gpt-4 launch date"Llama.generate: prefix-match hit
\[{'url': '[https://openai.com/blog/gpt-4-api-general-availability](https://openai.com/blog/gpt-4-api-general-availability)... | 2024-01-16T02:29:26 | https://www.reddit.com/r/LocalLLaMA/comments/197rj8l/langchain_agent_search_returning_various_answers/ | Positive-Ad-8445 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 197rj8l | false | null | t3_197rj8l | /r/LocalLLaMA/comments/197rj8l/langchain_agent_search_returning_various_answers/ | false | false | self | 1 | {'enabled': False, 'images': [{'id': '5-l9CZ_HW-7jVI6OB1-iWt48qTziuLMHEQ8IdI9SNIY', 'resolutions': [{'height': 108, 'url': 'https://external-preview.redd.it/JE81nz4WNaSjmViMpOonmCMKa3U6FTPmw7Ets8WEYx8.jpg?width=108&crop=smart&auto=webp&s=cd1f87f27e6aea43705c715d827b3b4288821488', 'width': 108}, {'height': 216, 'url': '... |
Mixtral8x7B vs. The Classics | 9 | https://sol.elementalinformatics.com/Herodotus.html
This is my first attempt at using a local LLM for anything useful. I'm running mixtral-8x7b-instruct-v0.1.Q8_0.gguf via llama.cpp and accessing it via the "OpenAI-like" API.
I made this from data from the Perseus Digital Library, specifically the hdt_gk.xml file th... | 2024-01-16T01:50:32 | https://www.reddit.com/r/LocalLLaMA/comments/197qpe6/mixtral8x7b_vs_the_classics/ | no_fuse | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 197qpe6 | false | null | t3_197qpe6 | /r/LocalLLaMA/comments/197qpe6/mixtral8x7b_vs_the_classics/ | false | false | self | 9 | null |
Aurelian: 70B 32K context [v0.5 Interim Update] | 40 | This is an interim update (v0.5) with fixes for the previous [alpha release](https://huggingface.co/grimulkan/aurelian-alpha0.1-70b-rope8-32K-fp16), but not yet v1.0.
**Please give feedback, good and bad!**
## Changes from Alpha:
* Greatly minimizes "chatGPTisms". No more feeling empowered by the shared bonds of fri... | 2024-01-16T00:48:41 | https://www.reddit.com/r/LocalLLaMA/comments/197pcmu/aurelian_70b_32k_context_v05_interim_update/ | Grimulkan | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 197pcmu | false | null | t3_197pcmu | /r/LocalLLaMA/comments/197pcmu/aurelian_70b_32k_context_v05_interim_update/ | false | false | self | 40 | {'enabled': False, 'images': [{'id': 'MCalqV1HoBH4FiM21SoIO1zmo1rxabGTtYiIG6z6kb8', 'resolutions': [{'height': 58, 'url': 'https://external-preview.redd.it/fjdJI20wZWeLaGoZI92qXakf5wHbS1sxCDfcogGIEVY.jpg?width=108&crop=smart&auto=webp&s=4a1b4c5ab08a12413dc526402ff94dcd7b014072', 'width': 108}, {'height': 116, 'url': 'h... |
rocm, exllamav2, oobabooga - disabling a gpu | 1 | [removed] | 2024-01-16T00:35:59 | https://www.reddit.com/r/LocalLLaMA/comments/197p2mq/rocm_exllamav2_oobabooga_disabling_a_gpu/ | LumbarPain2 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 197p2mq | false | null | t3_197p2mq | /r/LocalLLaMA/comments/197p2mq/rocm_exllamav2_oobabooga_disabling_a_gpu/ | false | false | default | 1 | null |
Best model and settings for a 3060 12gb? | 3 | I recently upgraded to this GPU and have been having lots of fun messing around with different models, but I can't seem to dial in the settings.
I've been using mistralai\_Mistral-7B-Instruct-v0.2 and get slow generation speed unless I lower it to 5000-6000 tokens (or characters? words? not sure the correct term), but... | 2024-01-16T00:21:17 | https://www.reddit.com/r/LocalLLaMA/comments/197oqwj/best_model_and_settings_for_a_3060_12gb/ | VapedScoops | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 197oqwj | false | null | t3_197oqwj | /r/LocalLLaMA/comments/197oqwj/best_model_and_settings_for_a_3060_12gb/ | false | false | self | 3 | null |
Noob question: If I have the VRAM, should I switch away from GGUF? | 20 | I'm very sorry for this noob question , but I've recently acquired a 24GB VRAM card which hasn't arrived yet, and I was wondering if I should re-download my GGUF models to the ones that can only be run exclusively in VRAM.
Will there be a performance improvement, or can I just simply continue using my GGUF files as n... | 2024-01-15T23:50:21 | https://www.reddit.com/r/LocalLLaMA/comments/197o1f7/noob_question_if_i_have_the_vram_should_i_switch/ | RadioSailor | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 197o1f7 | false | null | t3_197o1f7 | /r/LocalLLaMA/comments/197o1f7/noob_question_if_i_have_the_vram_should_i_switch/ | false | false | self | 20 | null |
Purely theoretical question about the capacity of a fine tuned LLM to fill in the blanks in personal history. | 14 | I've recently inherited my mother's house, which was filled to the brim with artifacts from the last hundred years. We're talking about hundreds of letters, plane tickets, brochures, notes, letters from others, letters to herself, diaries, and the like.
Is there a potential for this technology to be deployed in a cer... | 2024-01-15T23:42:18 | https://www.reddit.com/r/LocalLLaMA/comments/197nuwp/purely_theoretical_question_about_the_capacity_of/ | RadioSailor | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 197nuwp | false | null | t3_197nuwp | /r/LocalLLaMA/comments/197nuwp/purely_theoretical_question_about_the_capacity_of/ | false | false | self | 14 | null |
ryzen 5 5600 expected mixtral tok/s? | 2 | cpu: ryzen 5 5600
ram: 64GB 3200MHz
gpu: rtx 2070
backend: llama.cpp
model: mixtral-8x7b-instruct-v0.1.Q5_K_M.gguf
i get about 1 tok/sec which seems small for 13b active parameters. ive set it to 12 threads and am currently not gpu offloading, but at 4 layers its not really better. | 2024-01-15T23:37:38 | https://www.reddit.com/r/LocalLLaMA/comments/197nr0d/ryzen_5_5600_expected_mixtral_toks/ | Dankmemexplorer | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 197nr0d | false | null | t3_197nr0d | /r/LocalLLaMA/comments/197nr0d/ryzen_5_5600_expected_mixtral_toks/ | false | false | self | 2 | null |
Whats the best open source LLM for returning only JSON? | 20 | The only model that I tested that is consistent with returning only JSON for me is CHATGPT-4 in JSON Mode I've tested many open source alternatives and none has been consistent with only JSON replies (they always add comments). | 2024-01-15T22:52:32 | https://www.reddit.com/r/LocalLLaMA/comments/197mnt5/whats_the_best_open_source_llm_for_returning_only/ | alew3 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 197mnt5 | false | null | t3_197mnt5 | /r/LocalLLaMA/comments/197mnt5/whats_the_best_open_source_llm_for_returning_only/ | false | false | self | 20 | null |
Some perplexities for the new 2 bit SOTA GGUF quants of LlamaCPP | 29 | Here come the results of the perplexity tests I made out of curiosity on Llama 70b and Aurora Nights 70b (the 2 first 70b models quantized with an iMatrix), and they are promising, especially if we compare them to the best quants we had until now under Exllama v2 0.0.11
https://preview.redd.it/stdaa6p9mocc1.png?width=... | 2024-01-15T22:46:47 | https://www.reddit.com/r/LocalLLaMA/comments/197mip0/some_perplexities_for_the_new_2_bit_sota_gguf/ | Nexesenex | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 197mip0 | false | null | t3_197mip0 | /r/LocalLLaMA/comments/197mip0/some_perplexities_for_the_new_2_bit_sota_gguf/ | false | false | 29 | {'enabled': False, 'images': [{'id': 'ceJckESamHZy2aOu_aTzC_Id3Lpd6T0E7EKAox9upLE', 'resolutions': [{'height': 54, 'url': 'https://external-preview.redd.it/rFFV_Wpg8Rmru2NES80tThKnlRtwavMrrDFShY9CHNo.jpg?width=108&crop=smart&auto=webp&s=7ec3b93ddf9177693cf8f86ad8acab0ebb83c6cb', 'width': 108}, {'height': 108, 'url': 'h... | |
What tool is this | 3 | If anyone can understand and knows what tool is it, send me the GitHub link in the comment thanks 👍🏻 | 2024-01-15T22:28:10 | BusComprehensive9188 | i.redd.it | 1970-01-01T00:00:00 | 0 | {} | 197m1p9 | false | null | t3_197m1p9 | /r/LocalLLaMA/comments/197m1p9/what_tool_is_this/ | false | false | 3 | {'enabled': True, 'images': [{'id': 'KQ81EmXxmyrnx8fpiMFV2krVXp46x4hmyJNIc02iwPw', 'resolutions': [{'height': 48, 'url': 'https://preview.redd.it/hxhwlawyjocc1.png?width=108&crop=smart&auto=webp&s=b66c961b600af22d5b69f1b9c730eaa758c2ac68', 'width': 108}, {'height': 97, 'url': 'https://preview.redd.it/hxhwlawyjocc1.png?... | ||
LocalLLaMa Meme : The cycle continues (scroll pictures) | 2 | 2024-01-15T22:28:07 | https://www.reddit.com/gallery/197m1nj | phoneixAdi | reddit.com | 1970-01-01T00:00:00 | 0 | {} | 197m1nj | false | null | t3_197m1nj | /r/LocalLLaMA/comments/197m1nj/localllama_meme_the_cycle_continues_scroll/ | false | false | 2 | null | ||
LocalLlama Meme : The cycle continues (scroll pictures) | 1 | [deleted] | 2024-01-15T22:25:55 | https://www.reddit.com/gallery/197lzok | phoneixAdi | reddit.com | 1970-01-01T00:00:00 | 0 | {} | 197lzok | false | null | t3_197lzok | /r/LocalLLaMA/comments/197lzok/localllama_meme_the_cycle_continues_scroll/ | false | false | 1 | null | |
Any advice about how to do batch inference for a group of prompts? | 1 | [removed] | 2024-01-15T22:18:20 | https://www.reddit.com/r/LocalLLaMA/comments/197lso5/any_advice_about_how_to_do_batch_inference_for_a/ | ibrabibo | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 197lso5 | false | null | t3_197lso5 | /r/LocalLLaMA/comments/197lso5/any_advice_about_how_to_do_batch_inference_for_a/ | false | false | self | 1 | null |
Local Embeddings Models | 1 | Greetings,
Does anyone know of a simple way to run an embeddings model locally? I just want something that functions like kobold/ooba. Download model, run software, load model, viola API. Can't seem to find it though.
Any help is much appreciated. | 2024-01-15T22:13:49 | https://www.reddit.com/r/LocalLLaMA/comments/197lok1/local_embeddings_models/ | reality_comes | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 197lok1 | false | null | t3_197lok1 | /r/LocalLLaMA/comments/197lok1/local_embeddings_models/ | false | false | self | 1 | null |
Run LLaMA and other LLMs entirely on the browser | 1 | Deep Chat has just received a huge update! You can now host entire LLMs on the browser. No servers, no connections, run it all in the comfort of your browser. Supported models include popular Llama and Mistral LLMs.
Check out the Open Source project to add it to your website: [https://github.com/OvidijusParsiunas/dee... | 2024-01-15T22:13:28 | https://www.reddit.com/r/LocalLLaMA/comments/197lo8s/run_llama_and_other_llms_entirely_on_the_browser/ | ovi_nation | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 197lo8s | false | null | t3_197lo8s | /r/LocalLLaMA/comments/197lo8s/run_llama_and_other_llms_entirely_on_the_browser/ | false | false | self | 1 | {'enabled': False, 'images': [{'id': 'SmiKCGgpM3_BWIUNjhS_V7_v-4cLjkD7J3Vpx_mYrcM', 'resolutions': [{'height': 54, 'url': 'https://external-preview.redd.it/M8EUdV3JHg5AU4MkheZQq0j8-uwxUR4sKEKm5vvQkO0.jpg?width=108&crop=smart&auto=webp&s=09f42b5c53131810f189a943f4e8f61a97b73c90', 'width': 108}, {'height': 108, 'url': 'h... |
LLAMA on entirely your browser | 1 | [deleted] | 2024-01-15T22:11:54 | [deleted] | 1970-01-01T00:00:00 | 0 | {} | 197lmtb | false | null | t3_197lmtb | /r/LocalLLaMA/comments/197lmtb/llama_on_entirely_your_browser/ | false | false | default | 1 | null | ||
How can I train a Mixtral model? I need a tutorial | 2 | In theory, I can train the mistral 7B model on my data using additional video memory from RAM. Next, I will combine this model with other 7Bs that I choose to be suitable.
​
I understand, I’m speaking as a delusional person who doesn’t understand anything about this. Help me understand the whole process and wh... | 2024-01-15T21:58:03 | https://www.reddit.com/r/LocalLLaMA/comments/197l9vi/how_can_i_train_a_mixtral_model_i_need_a_tutorial/ | Secret_Joke_2262 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 197l9vi | false | null | t3_197l9vi | /r/LocalLLaMA/comments/197l9vi/how_can_i_train_a_mixtral_model_i_need_a_tutorial/ | false | false | self | 2 | null |
Experience report: Phi2 context extension works well for summaries | 49 | Have been playing around with dolphin-phi2 Q4 for generating summaries, and decided to test out the brand new [self-extend](https://www.reddit.com/r/LocalLLaMA/comments/18x8g6c/llm_maybe_longlm_selfextend_llm_context_window/) work. It's already been merged into the latest version of llama.cpp
Phi2's biggest weakness i... | 2024-01-15T21:43:41 | https://www.reddit.com/r/LocalLLaMA/comments/197kweu/experience_report_phi2_context_extension_works/ | vannaplayagamma | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 197kweu | false | null | t3_197kweu | /r/LocalLLaMA/comments/197kweu/experience_report_phi2_context_extension_works/ | false | false | self | 49 | {'enabled': False, 'images': [{'id': '8LYWV8TAAQTjJoT2qcWC8nv9E9ZNZCcaSilKD76n7-w', 'resolutions': [{'height': 108, 'url': 'https://external-preview.redd.it/gDqdX_osL-tanT98vKiH1ZPn7I7BzBnFc8JyVKbdpWI.jpg?width=108&crop=smart&auto=webp&s=0977d0a4f3facc7ffb0cc8e7d5dde3d49baceb7f', 'width': 108}, {'height': 216, 'url': '... |
Open Source Wishlist | 8 | While it's fun to compare benchmarks and confuse models with riddles, I think we could make the most progress as a community by focusing on projects and applications for LLMs. This is my completely subjective wishlist based on the opinions and experiences of only myself, so please feel free to enlighten me:
* Standa... | 2024-01-15T21:41:24 | https://www.reddit.com/r/LocalLLaMA/comments/197kudc/open_source_wishlist/ | Future_Might_8194 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 197kudc | false | null | t3_197kudc | /r/LocalLLaMA/comments/197kudc/open_source_wishlist/ | false | false | self | 8 | null |
Best model and settings for a 3060 12gb? | 1 | [removed] | 2024-01-15T21:23:48 | https://www.reddit.com/r/LocalLLaMA/comments/197ke9b/best_model_and_settings_for_a_3060_12gb/ | bipolaridiot_ | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 197ke9b | false | null | t3_197ke9b | /r/LocalLLaMA/comments/197ke9b/best_model_and_settings_for_a_3060_12gb/ | false | false | self | 1 | null |
How to fine tune model on slang? | 15 | For example my data is in json format {word: usage}
{lit: *How is it over there? Is it* ***lit****, or should I just go home instead?*}
{No cap: *This is the most beautiful house I’ve ever seen,* ***no cap****.*}
Can someone give me the steps I would have to take to fine tune my model? Would it also need a meaning o... | 2024-01-15T21:20:53 | https://www.reddit.com/r/LocalLLaMA/comments/197kbm9/how_to_fine_tune_model_on_slang/ | wonderingStarDusts | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 197kbm9 | false | null | t3_197kbm9 | /r/LocalLLaMA/comments/197kbm9/how_to_fine_tune_model_on_slang/ | false | false | self | 15 | null |
Best GPU to run models locally? | 1 | [removed] | 2024-01-15T21:16:13 | https://www.reddit.com/r/LocalLLaMA/comments/197k7a4/best_gpu_to_run_models_locally/ | StillOk1589 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 197k7a4 | false | null | t3_197k7a4 | /r/LocalLLaMA/comments/197k7a4/best_gpu_to_run_models_locally/ | false | false | self | 1 | null |
Best GPU to run models locally? | 1 | [removed] | 2024-01-15T21:16:13 | https://www.reddit.com/r/LocalLLaMA/comments/197k7a3/best_gpu_to_run_models_locally/ | StillOk1589 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 197k7a3 | false | null | t3_197k7a3 | /r/LocalLLaMA/comments/197k7a3/best_gpu_to_run_models_locally/ | false | false | self | 1 | null |
Did anyone work with DPO adaptors? | 1 | [removed] | 2024-01-15T21:16:05 | https://www.reddit.com/r/LocalLLaMA/comments/197k75p/did_anyone_work_with_dpo_adaptors/ | CuriosAligator | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 197k75p | false | null | t3_197k75p | /r/LocalLLaMA/comments/197k75p/did_anyone_work_with_dpo_adaptors/ | false | false | self | 1 | null |
Haiku DPO dataset + notebook tutorials for synthetic dataset generation | 17 | I just released [haiku\_dpo](https://huggingface.co/datasets/davanstrien/haiku_dpo), a synthetic Direct Preference Optimization dataset which has the goal of helping to train LLMs to be better at writing haiku.
As many of you know, Direct Preference Optimization (DPO) just needs a "chosen" and "rejected" response for ... | 2024-01-15T21:10:35 | https://www.reddit.com/r/LocalLLaMA/comments/197k1ys/haiku_dpo_dataset_notebook_tutorials_for/ | dvanstrien | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 197k1ys | false | null | t3_197k1ys | /r/LocalLLaMA/comments/197k1ys/haiku_dpo_dataset_notebook_tutorials_for/ | false | false | self | 17 | {'enabled': False, 'images': [{'id': 'w1_sUqt71_K3IBxPUjskPfptM5D2EHo93udQ1PU8lpw', 'resolutions': [{'height': 58, 'url': 'https://external-preview.redd.it/MZjg3e1yQVYljbVzzBMDxs7Yb5XTWRmmwXaOYEQMLW0.jpg?width=108&crop=smart&auto=webp&s=03384316e136c6ffe8a3cfa092cf4d382aa0ba09', 'width': 108}, {'height': 116, 'url': 'h... |
QLoRA Prompt Leaking | 1 | [removed] | 2024-01-15T20:41:21 | https://www.reddit.com/r/LocalLLaMA/comments/197jamo/qlora_prompt_leaking/ | popo543 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 197jamo | false | null | t3_197jamo | /r/LocalLLaMA/comments/197jamo/qlora_prompt_leaking/ | false | false | self | 1 | null |
Many AI Safety Orgs Have Tried to Criminalize Currently-Existing Open-Source AI | 440 | 2024-01-15T18:53:45 | https://1a3orn.com/sub/machine-learning-bans.html | 1a3orn | 1a3orn.com | 1970-01-01T00:00:00 | 0 | {} | 197gj0q | false | null | t3_197gj0q | /r/LocalLLaMA/comments/197gj0q/many_ai_safety_orgs_have_tried_to_criminalize/ | false | false | default | 440 | null | |
Question about quantization and quality | 7 | Since I kind of always had this in the back of my mind but really never cared about it (I know almost nothing how llama.cpp works under the hood), I will now ask out of curiosity. :)
For example, llama-2-13b-chat.Q6\_K is in the size of **10.7 GB**, while llama-2-13b-chat.Q8\_0 is **13.8 GB**. A whooping 3,1 GB differ... | 2024-01-15T18:51:57 | https://www.reddit.com/r/LocalLLaMA/comments/197gh8z/question_about_quantization_and_quality/ | Admirable-Star7088 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 197gh8z | false | null | t3_197gh8z | /r/LocalLLaMA/comments/197gh8z/question_about_quantization_and_quality/ | false | false | self | 7 | null |
NLI sentence transformers VS general purpose ones, for RAG applications | 7 | I've been looking into RAG, and have come across using sentence transformers for querying and semantic comparison.
Recently, I've discovered that NLI models are specifically designed for matching up queries to answers, which seems super useful, and yet all the ones on the sentence-transformers hugging face are like 2 ... | 2024-01-15T18:28:52 | https://www.reddit.com/r/LocalLLaMA/comments/197fvfs/nli_sentence_transformers_vs_general_purpose_ones/ | Nano_9a9o | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 197fvfs | false | null | t3_197fvfs | /r/LocalLLaMA/comments/197fvfs/nli_sentence_transformers_vs_general_purpose_ones/ | false | false | self | 7 | null |
Langchain and mlx models | 1 | [removed] | 2024-01-15T18:12:57 | https://www.reddit.com/r/LocalLLaMA/comments/197fgsf/langchain_and_mlx_models/ | KlutzyNecessary2205 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 197fgsf | false | null | t3_197fgsf | /r/LocalLLaMA/comments/197fgsf/langchain_and_mlx_models/ | false | false | self | 1 | null |
Running any AI locally on a low-end PC (i3-530, 4gb ddr3 ram, no GPU or iGPU) | 1 | I found an old PC with these *specifications*:
\- I3-530
\- 4gb ddr3 ram
\- **NO** **GPU**
I would like to run any AI application locally on it, as long as the application has a use.
I am also looking at whisper transcription, which I would like to use. Would this work with the low end pc?Should I use faster-whisp... | 2024-01-15T18:04:39 | https://www.reddit.com/r/LocalLLaMA/comments/197f91p/running_any_ai_locally_on_a_lowend_pc_i3530_4gb/ | DaanDeweerdt | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 197f91p | false | null | t3_197f91p | /r/LocalLLaMA/comments/197f91p/running_any_ai_locally_on_a_lowend_pc_i3530_4gb/ | false | false | self | 1 | null |
recommendation please - linux desktop GUIs that support custom OPENAI_API_BASE? | 5 | I have tried Chatbox from [https://github.com/Bin-Huang/chatbox](https://github.com/Bin-Huang/chatbox) and it is somewhat decent, but does not allow you to set `OPENAI_API_BASE` . I want a GUI that I can use with [https://app.fireworks.ai/models/fireworks/mixtral-8x7b-instruct](https://app.fireworks.ai/models/fireworks... | 2024-01-15T18:04:28 | https://www.reddit.com/r/LocalLLaMA/comments/197f8vg/recommendation_please_linux_desktop_guis_that/ | Treeeant | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 197f8vg | false | null | t3_197f8vg | /r/LocalLLaMA/comments/197f8vg/recommendation_please_linux_desktop_guis_that/ | false | false | self | 5 | {'enabled': False, 'images': [{'id': 't0LLHlqnM2GZnhDCXn0dY6guQpGbtk9h4OkyKxpvaDg', 'resolutions': [{'height': 54, 'url': 'https://external-preview.redd.it/K1aEaLArH26JhMlFyyCSQwzOxl4Io3fn1hkroqsUFr8.jpg?width=108&crop=smart&auto=webp&s=11be0bd8e62dddde5da1d953542860dcc8ac16ad', 'width': 108}, {'height': 108, 'url': 'h... |
My open air deep learning rig - repurposing crypto gear and creatively using server parts from eBay! (8x RTX 3090) | 68 | 2024-01-15T18:01:17 | https://imgur.com/a/YHyAV42 | kyleboddy | imgur.com | 1970-01-01T00:00:00 | 0 | {} | 197f5tx | false | null | t3_197f5tx | /r/LocalLLaMA/comments/197f5tx/my_open_air_deep_learning_rig_repurposing_crypto/ | false | false | 68 | {'enabled': False, 'images': [{'id': 'RJKZpfNZtiC56KZz9Pn_i63yucuvCZF7Xna1oGvhBGs', 'resolutions': [{'height': 56, 'url': 'https://external-preview.redd.it/g36O0eifJkap2F4BTTqi9krVVmo9IaCTGRX47cjfElE.jpg?width=108&crop=smart&auto=webp&s=5c51da725debc0599264a75ea9aa1f969869288a', 'width': 108}, {'height': 113, 'url': 'h... | ||
LM studio using wrong GPU | 1 | [removed] | 2024-01-15T17:59:38 | https://www.reddit.com/r/LocalLLaMA/comments/197f44b/lm_studio_using_wrong_gpu/ | Solid-Thought1486 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 197f44b | false | null | t3_197f44b | /r/LocalLLaMA/comments/197f44b/lm_studio_using_wrong_gpu/ | false | false | self | 1 | null |
Who here is running a quad socket, 16 total ram channel server for their GGUF models? Old or new. | 1 | [removed] | 2024-01-15T17:55:08 | https://www.reddit.com/r/LocalLLaMA/comments/197f08r/who_here_is_running_a_quad_socket_16_total_ram/ | CanineAssBandit | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 197f08r | false | null | t3_197f08r | /r/LocalLLaMA/comments/197f08r/who_here_is_running_a_quad_socket_16_total_ram/ | false | false | self | 1 | null |
OnnxStream running TinyLlama and Mistral 7B, with CUDA support | 16 | hi,
I'm the author.
​
OnnxStream can run Stable Diffusion XL Base and Turbo on a Raspberry PI Zero 2. In the last 2 months I have implemented a series of optimizations to also support the inference of LLMs, but only on desktop computers and servers.
I'm interested in opinions on this possible developme... | 2024-01-15T17:54:47 | https://www.reddit.com/r/LocalLLaMA/comments/197ezxf/onnxstream_running_tinyllama_and_mistral_7b_with/ | Pristine198 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 197ezxf | false | null | t3_197ezxf | /r/LocalLLaMA/comments/197ezxf/onnxstream_running_tinyllama_and_mistral_7b_with/ | false | false | self | 16 | {'enabled': False, 'images': [{'id': 'DgakZOBsIt0ELJgEhmJhaB-L0z9DSOG-X5RoApgbofE', 'resolutions': [{'height': 54, 'url': 'https://external-preview.redd.it/TA_6zkSjZgdOVPlJ2PEnV5wQggbOvzVn0sLZW647obs.jpg?width=108&crop=smart&auto=webp&s=8ab5ccaa425abac24e11824ebcf21b3ee8f8d2dd', 'width': 108}, {'height': 108, 'url': 'h... |
Has anyone successfully implemented llava using the llama.cpp server? | 4 | Hi there,
I want to try llava in llama.cpp, but I'm not sure how. I know I need the model gguf and the projection gguf. But how do I send request to the server with an image? In what format do I send the image? Is llava compatible with the api like OAIapi example? | 2024-01-15T17:52:46 | https://www.reddit.com/r/LocalLLaMA/comments/197ey3f/has_anyone_successfully_implemented_llava_using/ | Frequent_Valuable_47 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 197ey3f | false | null | t3_197ey3f | /r/LocalLLaMA/comments/197ey3f/has_anyone_successfully_implemented_llava_using/ | false | false | self | 4 | null |
Training LLama, Mistral and Mixtral-MoE faster with Packing Inputs without Cross-Contamination Attention | 95 | Hey r/LocalLLaMA community!
I would like to share our work that can speed up finetuning LLama, Mistral and Mixtral significantly.
[https://github.com/MeetKai/functionary/tree/main/functionary/train/packing](https://github.com/MeetKai/functionary/tree/main/functionary/train/packing)
The idea is that we monkey-patch t... | 2024-01-15T17:31:47 | https://www.reddit.com/r/LocalLLaMA/comments/197efaz/training_llama_mistral_and_mixtralmoe_faster_with/ | Relevant_Outcome_726 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 197efaz | false | null | t3_197efaz | /r/LocalLLaMA/comments/197efaz/training_llama_mistral_and_mixtralmoe_faster_with/ | false | false | self | 95 | {'enabled': False, 'images': [{'id': 'lCx04XqMMuHVHi6TqoMeKt--k5yyLvlAfMy6iU3R2-g', 'resolutions': [{'height': 54, 'url': 'https://external-preview.redd.it/YHLh1waVhkGRiDwgL2YfUuKWApgYeCXQJXHhFsG4g8I.jpg?width=108&crop=smart&auto=webp&s=21059db0d2ab2e720e14f2b7b7bc15ee2975ba7a', 'width': 108}, {'height': 108, 'url': 'h... |
Help! All 70B models on Runpod run super slow? | 1 | [removed] | 2024-01-15T17:23:52 | https://www.reddit.com/r/LocalLLaMA/comments/197e818/help_all_70b_models_on_runpod_run_super_slow/ | thomassyx | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 197e818 | false | null | t3_197e818 | /r/LocalLLaMA/comments/197e818/help_all_70b_models_on_runpod_run_super_slow/ | false | false | self | 1 | null |
What are you using to train or finetune gguf outside of llama.cpp? | 12 | training and finetuning are both broken in llama.cpp and have been going back to more than a month ago (checked out Dec 1st tag)
i like llama.cpp but the speed of change is great but not so great if it's breaking things. wondering what other ways you all are training & finetuning. if anyone knows the last time thes... | 2024-01-15T17:19:35 | https://www.reddit.com/r/LocalLLaMA/comments/197e451/what_are_you_using_to_train_or_finetune_gguf/ | segmond | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 197e451 | false | null | t3_197e451 | /r/LocalLLaMA/comments/197e451/what_are_you_using_to_train_or_finetune_gguf/ | false | false | self | 12 | null |
Ping-Ponging LLM Battle | 1 | [removed] | 2024-01-15T17:13:32 | https://www.reddit.com/r/LocalLLaMA/comments/197dyiz/pingponging_llm_battle/ | dakinnia | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 197dyiz | false | null | t3_197dyiz | /r/LocalLLaMA/comments/197dyiz/pingponging_llm_battle/ | false | false | self | 1 | null |
Best 7B model for coding? | 1 | [removed] | 2024-01-15T17:08:13 | https://www.reddit.com/r/LocalLLaMA/comments/197dtlc/best_7b_model_for_coding/ | laprisee4 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 197dtlc | false | null | t3_197dtlc | /r/LocalLLaMA/comments/197dtlc/best_7b_model_for_coding/ | false | false | self | 1 | null |
Anyone is using llamacpp for real? | 1 | Over the last 9 months, our team worked with hundreds of Fortune 500 companies on deploying LLMs in production and we've never seen anyone is interested in llamacpp or similar small LMs. It could be a cool toy project seeing that you can run your model on Raspberry Pi or a laptop, but it's so far off from any real use ... | 2024-01-15T17:01:13 | https://www.reddit.com/r/LocalLLaMA/comments/197dn7u/anyone_is_using_llamacpp_for_real/ | russellsparadox101 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 197dn7u | false | null | t3_197dn7u | /r/LocalLLaMA/comments/197dn7u/anyone_is_using_llamacpp_for_real/ | false | false | self | 1 | null |
We've written a post about local speech-to-text transcription tools for Windows and Linux. We explore the installation and usage of Faster-Whisper and Speech Note. | 3 | 2024-01-15T16:55:50 | https://www.speech-to-text.cloud/local-speech-to-text-transcription-on-windows-and-linux/ | Speech-to-Text-Cloud | speech-to-text.cloud | 1970-01-01T00:00:00 | 0 | {} | 197diep | false | null | t3_197diep | /r/LocalLLaMA/comments/197diep/weve_written_a_post_about_local_speechtotext/ | false | false | 3 | {'enabled': False, 'images': [{'id': 'SmUy0Y4559_EA7dFREmrZ6ZfY5RMw4G8v-QIjFAX1wk', 'resolutions': [{'height': 72, 'url': 'https://external-preview.redd.it/Ml3SLdGSeamuqAyW-XrCbnNcO84mY9zU_COFWWK_daI.jpg?width=108&crop=smart&auto=webp&s=18deadb1a0c42c112f520608b26ee34b45ce79c3', 'width': 108}, {'height': 144, 'url': 'h... | ||
Deploying Phi-2 as an API endpoint | 7 | Microsoft/Phi-2 is really exceptional for for being so small in size yet being powerful enough to outcompete large language models on some of the most prominent benchmarks.
Deploy Phi-2 as an API endpoint using this colab notebook:
[https://colab.research.google.com/drive/1TtztWHYWg8i5pas\_rDxj7f22eVR\_th1J](https://... | 2024-01-15T16:53:05 | https://www.reddit.com/r/LocalLLaMA/comments/197dg13/deploying_phi2_as_an_api_endpoint/ | gvij | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 197dg13 | false | null | t3_197dg13 | /r/LocalLLaMA/comments/197dg13/deploying_phi2_as_an_api_endpoint/ | false | false | self | 7 | {'enabled': False, 'images': [{'id': 'nkhh65ujo5BznFJFojoMPaKjGuLSpPj6KGhRov-ykOg', 'resolutions': [{'height': 108, 'url': 'https://external-preview.redd.it/0-fRWqjlLadVXj5pfYp4_Oe3xgBWE-_rdjVSn7hlohI.jpg?width=108&crop=smart&auto=webp&s=f34d2dfdbbfa7de0f1956f186fd8430ee96a1a55', 'width': 108}, {'height': 216, 'url': '... |
How much knowledge is "hidden" within an LLM? | 8 | I wonder how much knowledge an LLM of a certain size can have and repeat without hallucinations. Considering you can easily fit a whole Wikipedia dump within a few gigabytes and language models not having to remember the actual phrasing (just the knowledge behind it), even a 7B model might be able to gain huge amounts ... | 2024-01-15T16:48:10 | https://www.reddit.com/r/LocalLLaMA/comments/197dbs4/how_much_knowledge_is_hidden_within_an_llm/ | susibacker | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 197dbs4 | false | null | t3_197dbs4 | /r/LocalLLaMA/comments/197dbs4/how_much_knowledge_is_hidden_within_an_llm/ | false | false | self | 8 | null |
Subsets and Splits
No community queries yet
The top public SQL queries from the community will appear here once available.