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 ⌀ |
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
The Carbon Footprint of GPT-4 | 1 | Wrote an article where I calculated the carbon footprint of GPT-4 and other commonly used foundational Models.
Simply put, training these models requires enormous energy and has a significant carbon footprint. The carbon emitted by GPT-4 is the equivalent of powering more than 1300 homes for one year!
[https://... | 2024-01-07T08:37:19 | https://www.reddit.com/r/LocalLLaMA/comments/190nrjv/the_carbon_footprint_of_gpt4/ | soham1996 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 190nrjv | false | null | t3_190nrjv | /r/LocalLLaMA/comments/190nrjv/the_carbon_footprint_of_gpt4/ | false | false | self | 1 | {'enabled': False, 'images': [{'id': 'rZOyHJbrP9xl0lEK_Rjnyw2lsKjoY9qaATUXPRagwao', 'resolutions': [{'height': 54, 'url': 'https://external-preview.redd.it/qomhC-yy1ANsOa4BxQAhoTrQeo5uGB9FvbepXuVDhz8.jpg?width=108&crop=smart&auto=webp&s=994fd2791210167868979acc8fd5cca5ae967953', 'width': 108}, {'height': 108, 'url': 'h... |
Request: system build guides at various price points | 3 | Don't personally have a lot to contribute in this department, however, I have noticed a lot of confusion and flaming when discussing specific systems that users on here have built. Perhaps it would be a useful collaborative project to decide on some good "from scratch" builds, within given budgets. Collaboration is pro... | 2024-01-07T08:27:02 | https://www.reddit.com/r/LocalLLaMA/comments/190nm3f/request_system_build_guides_at_various_price/ | WarmCartoonist | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 190nm3f | false | null | t3_190nm3f | /r/LocalLLaMA/comments/190nm3f/request_system_build_guides_at_various_price/ | false | false | self | 3 | null |
Expected speed for 33B model? | 9 | Hi!
I have a gaming PC (see Specs below) after upgrading from a laptop.
I'm getting really slow token generation on Q6 model of 33B (wizardcoder)
Why it's so slow?
(I'm using LM Studio with GPU offloading and n-threads set to 28)
Thanks for the help!
(I7-14700KF, 64GB DDR 5600MHz, RX 7800 XT 16GB) | 2024-01-07T08:12:07 | https://www.reddit.com/r/LocalLLaMA/comments/190neal/expected_speed_for_33b_model/ | NewExplor3r | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 190neal | false | null | t3_190neal | /r/LocalLLaMA/comments/190neal/expected_speed_for_33b_model/ | false | false | self | 9 | null |
I want to share my two favorite papers in the last 6 months: LLM Augmented LLMs by Google and Phi-2 by Microsoft that I believe can lead to Great Leap Forward (Not the CCP one hopefully). Please share yours. | 106 | 1. LLM Augments LLMs:
https://huggingface.co/papers/2401.02412
Foundational models with billions of parameters which have been trained on large corpora of data have demonstrated non-trivial skills in a variety of domains. However, due to their monolithic structure, it is challenging and expensive to augment them or i... | 2024-01-07T07:34:53 | https://www.reddit.com/gallery/190mud2 | TysonUsykFury | reddit.com | 1970-01-01T00:00:00 | 0 | {} | 190mud2 | false | null | t3_190mud2 | /r/LocalLLaMA/comments/190mud2/i_want_to_share_my_two_favorite_papers_in_the/ | false | false | 106 | null | |
I want to share my two favorite papers in the last 6 months: LLM Augmented LLMs by Google and Phi-2 by Microsoft. Please share yours. | 1 | LLM Augments LLMs:
https://huggingface.co/papers/2401.02412
Foundational models with billions of parameters which have been trained on large corpora of data have demonstrated non-trivial skills in a variety of domains. However, due to their monolithic structure, it is challenging and expensive to augment them or impa... | 2024-01-07T07:30:27 | https://www.reddit.com/gallery/190ms0q | TysonUsykFury | reddit.com | 1970-01-01T00:00:00 | 0 | {} | 190ms0q | false | null | t3_190ms0q | /r/LocalLLaMA/comments/190ms0q/i_want_to_share_my_two_favorite_papers_in_the/ | false | false | 1 | null | |
No inference speed increase with GPU acceleration on (LM Studio) | 1 | Hi!
I'm new to local LLMs and wonder why activating GPU acceleration in LM Studio does not increase the speed of inference. It's 8 tokens/second with GPU acceleration activated or deactivated. I set the layers to -1 in order to offload all layers onto the GPU. The only difference is that my GPU is used 10% and my CPU ... | 2024-01-07T07:25:13 | https://www.reddit.com/r/LocalLLaMA/comments/190mp9w/no_inference_speed_increase_with_gpu_acceleration/ | greentea387 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 190mp9w | false | null | t3_190mp9w | /r/LocalLLaMA/comments/190mp9w/no_inference_speed_increase_with_gpu_acceleration/ | false | false | self | 1 | null |
Estimates on total users working AI projects, private and commercial? | 3 | Anyone have any thoughts or insight on how many people are working on AI projects or tinkering at home?
I noticed a model download link that had over 5 million downloads for the weights and I began to wonder if there are literally millions of people working on low level AI from both a professional and private level.
... | 2024-01-07T07:04:02 | https://www.reddit.com/r/LocalLLaMA/comments/190mdfz/estimates_on_total_users_working_ai_projects/ | Miserable_Praline_77 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 190mdfz | false | null | t3_190mdfz | /r/LocalLLaMA/comments/190mdfz/estimates_on_total_users_working_ai_projects/ | false | false | self | 3 | null |
A Rust library and CLI tool for converting JSON Schema to GBNF grammar and tightly constraining outputs of llama.cpp to exact forms | 10 | 2024-01-07T06:56:40 | https://github.com/richardanaya/gbnf | richardanaya | github.com | 1970-01-01T00:00:00 | 0 | {} | 190m95r | false | null | t3_190m95r | /r/LocalLLaMA/comments/190m95r/a_rust_library_and_cli_tool_for_converting_json/ | false | false | default | 10 | null | |
I'm planning on getting to 32 or 64GB of RAM on my gaming laptop. Which should I get? | 3 | Specs (It's basically a Gigabyte A5 X1):
CPU:Ryzen 9 5900HX
GPU: NVIDIA RTX 3070 8GB VRAM
RAM: 16 GB DDR4, will be 32 or 64 depending on the answers. (likely stuck at DDR4 though, LPDDR4's here are sold online and I'm not willing to risk it).
Sorry for the vague title; there's honestly A LOT of things I need to ask... | 2024-01-07T06:28:33 | https://www.reddit.com/r/LocalLLaMA/comments/190lsq7/im_planning_on_getting_to_32_or_64gb_of_ram_on_my/ | Switchblade1080 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 190lsq7 | false | null | t3_190lsq7 | /r/LocalLLaMA/comments/190lsq7/im_planning_on_getting_to_32_or_64gb_of_ram_on_my/ | false | false | self | 3 | null |
Is GenAI hype declining or are low-hanging fruits gone? | 1 |
Post ChatGPT, there were many interesting papers on the properties and features of large language models. The pace of publication was so fast that every week we could see at least 1-2 papers that would make the news.
On the open-source side, we had some low quality models and there was so much experimentation to see ... | 2024-01-07T05:59:03 | https://www.reddit.com/r/LocalLLaMA/comments/190lal2/is_genai_hype_declining_or_are_lowhanging_fruits/ | nderstand2grow | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 190lal2 | false | null | t3_190lal2 | /r/LocalLLaMA/comments/190lal2/is_genai_hype_declining_or_are_lowhanging_fruits/ | false | false | self | 1 | null |
A database to automatically handle gguf lama models | 17 | [https://github.com/laelhalawani/gguf\_modeldb]
(https://github.com/laelhalawani/gguf_modeldb)
[https://pypi.org/project/gguf-modeldb/](https://pypi.org/project/gguf-modeldb/)
This tool helps to manage gguf files form github. It has a built in library of 56 total quantizations of several main open source models, wit... | 2024-01-07T05:03:15 | https://www.reddit.com/r/LocalLLaMA/comments/190k9ps/a_database_to_automatically_handle_gguf_lama/ | --lael-- | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 190k9ps | false | null | t3_190k9ps | /r/LocalLLaMA/comments/190k9ps/a_database_to_automatically_handle_gguf_lama/ | false | false | self | 17 | {'enabled': False, 'images': [{'id': '3BXilRRLZevZUTrLrVM27I3O8M8c0bAZDvmCSq8_vyc', 'resolutions': [{'height': 54, 'url': 'https://external-preview.redd.it/zQzjHGed2Vkp8xWZTQR0Oop900jELJwquOVYTHkyJTc.jpg?width=108&crop=smart&auto=webp&s=53b05438649c78578db5643462e35ed7113c6904', 'width': 108}, {'height': 108, 'url': 'h... |
Gemini Pro Model SillyTavern | 3 | Does anyone know any solution to stop the model from speaking for me or the user in roleplay? I tried everything, change the system prompt, give an indication on the card, modify the main prompt, disable the instruction mode, and put a message in the start reply and nothing still ignoring everything and talking for me,... | 2024-01-07T04:06:01 | https://www.reddit.com/r/LocalLLaMA/comments/190j6oz/gemini_pro_model_sillytavern/ | Jorge1022 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 190j6oz | false | null | t3_190j6oz | /r/LocalLLaMA/comments/190j6oz/gemini_pro_model_sillytavern/ | false | false | self | 3 | null |
M1/M2 or GPU? | 1 | if I want to build a system to run or train LLMs should i buy a mac or a GPU? or a few GPUs? let's say i want to be able to play with any, all and multiple models, what hardware should i be considering? | 2024-01-07T03:45:45 | https://www.reddit.com/r/LocalLLaMA/comments/190istb/m1m2_or_gpu/ | Conspire2Perspire | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 190istb | false | null | t3_190istb | /r/LocalLLaMA/comments/190istb/m1m2_or_gpu/ | false | false | self | 1 | null |
phi-2 weirdly aggressive/rude | 1 | I was testing phi-2 and noticed something strange.
I started with the simple question "How many days are in August?" The model answers ok, but gets very verbose with the answers so I tried to tweak the question a little bit:
Tell me how many days are in August and nothing else.
Somehow this simple change seems to "t... | 2024-01-07T03:35:34 | https://www.reddit.com/r/LocalLLaMA/comments/190ilk3/phi2_weirdly_aggressiverude/ | gamesntech | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 190ilk3 | false | null | t3_190ilk3 | /r/LocalLLaMA/comments/190ilk3/phi2_weirdly_aggressiverude/ | false | false | self | 1 | null |
Learning resources | 1 | N00b starting in ml/ai world.
Where would I start? Want to run free models on my Mac and experiment and learn.
Please help. | 2024-01-07T03:07:44 | https://www.reddit.com/r/LocalLLaMA/comments/190i1vd/learning_resources/ | abk77 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 190i1vd | false | null | t3_190i1vd | /r/LocalLLaMA/comments/190i1vd/learning_resources/ | false | false | self | 1 | null |
Has anyone tried a decentralized training effort of LLaMA somewhere? | 3 | 2024-01-07T02:22:29 | https://github.com/learning-at-home/hivemind | ninjasaid13 | github.com | 1970-01-01T00:00:00 | 0 | {} | 190h5s6 | false | null | t3_190h5s6 | /r/LocalLLaMA/comments/190h5s6/has_anyone_tried_a_decentralized_training_effort/ | false | false | 3 | {'enabled': False, 'images': [{'id': 'cnNyN-K55rpJEPEOpdWYikLmcEObPbq3s-wfyiCKhoQ', 'resolutions': [{'height': 54, 'url': 'https://external-preview.redd.it/aYddEjQWJLYcIl_RL6RYO6fnqFTi0MpUWaeb_GMbQas.jpg?width=108&crop=smart&auto=webp&s=363fc40147eb8b5e19bd37e9153ac7a6d3c681dc', 'width': 108}, {'height': 108, 'url': 'h... | ||
running lm studio on rtx3060 64gb ram | 2 | currently, im running llama 2 70b on my dell laptop. Just curious to know should i enable the gpu on GPU accerlation, and if so, what is the best layers i should set
​ | 2024-01-07T01:58:03 | https://www.reddit.com/r/LocalLLaMA/comments/190go8a/running_lm_studio_on_rtx3060_64gb_ram/ | justandyL | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 190go8a | false | null | t3_190go8a | /r/LocalLLaMA/comments/190go8a/running_lm_studio_on_rtx3060_64gb_ram/ | false | false | self | 2 | null |
Open Source Function Calling LLMs | 17 | I am looking for LLMs that can call functions like OpenAI provides with 3.5 ([https://platform.openai.com/docs/guides/function-calling](https://platform.openai.com/docs/guides/function-calling))
I am aware of [https://github.com/musabgultekin/functionary](https://github.com/musabgultekin/functionary) which looks ve... | 2024-01-07T00:45:28 | https://www.reddit.com/r/LocalLLaMA/comments/190f62z/open_source_function_calling_llms/ | SatoshiReport | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 190f62z | false | null | t3_190f62z | /r/LocalLLaMA/comments/190f62z/open_source_function_calling_llms/ | false | false | self | 17 | null |
Specs and gotchas from playing with an LLM rig | 77 | ​
https://preview.redd.it/vr0akxezywac1.jpg?width=3024&format=pjpg&auto=webp&s=c33fb360bb31df30b204e6a41ebf5b4df560a35d
**Specs**
CPU: Ryzen 9 5900x
RAM: Corsair - Vengeance LPX 4 x 32GB 3200MHz DDR4 -- 128GB
MB: MSI MAG B550 Tomahawk MAX
SSD: Samsung 990 PRO 2TB
PSU: Corsair HX1500i -- 1500W
GPU: 3x PNY... | 2024-01-07T00:39:14 | https://www.reddit.com/r/LocalLLaMA/comments/190f1c1/specs_and_gotchas_from_playing_with_an_llm_rig/ | blackfedoradev | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 190f1c1 | false | null | t3_190f1c1 | /r/LocalLLaMA/comments/190f1c1/specs_and_gotchas_from_playing_with_an_llm_rig/ | false | false | 77 | null | |
Upgrading a Lenovo ThinkStation D30 | 1 | I have an old Lenovo ThinkStation D30. It has dual Xeon processors, 96GB ram, and some (non-SSD) HDDs. It has an Nvidia Quadro K2000 GPU. This is the [pdf](https://www.lenovo.com/medias/d30-datasheet-final-hi-res.pdf?context=bWFzdGVyfHJvb3R8MjY4MzgyMHxhcHBsaWNhdGlvbi9wZGZ8aDc3L2gxZS85MzM1NTIwNTkxOTAyLnBkZnxhYTJkMWI3OTA... | 2024-01-07T00:34:52 | https://www.reddit.com/r/LocalLLaMA/comments/190ey3o/upgrading_a_lenovo_thinkstation_d30/ | Data_Driven_Guy | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 190ey3o | false | null | t3_190ey3o | /r/LocalLLaMA/comments/190ey3o/upgrading_a_lenovo_thinkstation_d30/ | false | false | self | 1 | null |
mixtral-8x7b : always appending a positive spin on answers and often with an exclamation mark at the end. Why? | 1 | [removed] | 2024-01-07T00:21:08 | https://www.reddit.com/r/LocalLLaMA/comments/190enbf/mixtral8x7b_always_appending_a_positive_spin_on/ | w7gg33h | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 190enbf | false | null | t3_190enbf | /r/LocalLLaMA/comments/190enbf/mixtral8x7b_always_appending_a_positive_spin_on/ | false | false | self | 1 | null |
UniteAI: Local LLMs, Local Voice-to-Text, Local RAG, all in VSCode and Emacs. | 4 | 2024-01-07T00:07:12 | https://github.com/freckletonj/uniteai | BayesMind | github.com | 1970-01-01T00:00:00 | 0 | {} | 190ec2d | false | null | t3_190ec2d | /r/LocalLLaMA/comments/190ec2d/uniteai_local_llms_local_voicetotext_local_rag/ | false | false | 4 | {'enabled': False, 'images': [{'id': 'xJWwLcF6sLGxQlLU8o9xkTlYr8Q9QOLFKthWNYqKETM', 'resolutions': [{'height': 54, 'url': 'https://external-preview.redd.it/YBj5xR29nwiCCdzrCxq1AfKvi9eFRuStWYHAErvB1P4.jpg?width=108&crop=smart&auto=webp&s=dbb772204ac6290806826e61fbf949de9b2fa4e2', 'width': 108}, {'height': 108, 'url': 'h... | ||
Small dataset for primary LLM training | 6 | Hi, I'm looking for something like a set of children's books to test training algorithms without months of run time ...
​
Ed. | 2024-01-06T23:23:44 | https://www.reddit.com/r/LocalLLaMA/comments/190ddg6/small_dataset_for_primary_llm_training/ | Tricky-Box6330 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 190ddg6 | false | null | t3_190ddg6 | /r/LocalLLaMA/comments/190ddg6/small_dataset_for_primary_llm_training/ | false | false | self | 6 | null |
Hello. Some help in compiling llama.cpp with BLAS on Intel GPU? | 1 | Yeah. Seems like I have gotten some warnings and bad declarations of functions that are being used like ggml\_cl\_mul?
The target is a Arc A380, and it's being run with cmake -DLLAMA\_BLAS=ON -DLLAMA\_CLBLAST=ON -DCLBlast\_DIR=/usr/lib
`ggml.c: In function ‘ggml_init’: ggml.c:2266:9: error: implicit declaration of fu... | 2024-01-06T22:56:14 | https://www.reddit.com/r/LocalLLaMA/comments/190cqth/hello_some_help_in_compiling_llamacpp_with_blas/ | A_Degenerate_Idiot | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 190cqth | false | null | t3_190cqth | /r/LocalLLaMA/comments/190cqth/hello_some_help_in_compiling_llamacpp_with_blas/ | false | false | self | 1 | null |
AWQ vs GPTQ vs No quantization but loading in 4bit | 1 | Does anyone have any metrics or even personal anecdotes about the performance differences between different quantizations of models. For comparisons, I am assuming that the bit size between all of these is the same. For example, if I download mixtral GPTQ 4bit and load regular mixtral in 4bit, are there speed/performan... | 2024-01-06T22:54:03 | https://www.reddit.com/r/LocalLLaMA/comments/190cp0h/awq_vs_gptq_vs_no_quantization_but_loading_in_4bit/ | Mephidia | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 190cp0h | false | null | t3_190cp0h | /r/LocalLLaMA/comments/190cp0h/awq_vs_gptq_vs_no_quantization_but_loading_in_4bit/ | false | false | self | 1 | null |
Best way to independently monetize GenAI skills | 1 | With the advent of LLMs and the skills required to wade in that field, what are the best avenues to monetize your skills leveraging LLMs currently. I was thinking marketplace like Poe would be a good place for this but with the GptStore coming next week we still barely hear about it and this makes me wonder how open-... | 2024-01-06T22:28:26 | https://www.reddit.com/r/LocalLLaMA/comments/190c3hn/best_way_to_independently_monetize_genai_skills/ | Blue_Kiji_77 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 190c3hn | false | null | t3_190c3hn | /r/LocalLLaMA/comments/190c3hn/best_way_to_independently_monetize_genai_skills/ | false | false | self | 1 | null |
Mixtral 8x7b what are the experts | 79 | I understand the concept of experts and it seems a step forward in llms - but for mixtral, what are the 8 experts, what are their "skills"? I've been looking everywhere for this.
And how is mixtral 8x7b better (or worse) than a 7b, 13b or 30b model for a specific use case, for example writing stuff or coding? | 2024-01-06T22:14:21 | https://www.reddit.com/r/LocalLLaMA/comments/190brnf/mixtral_8x7b_what_are_the_experts/ | yupignome | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 190brnf | false | null | t3_190brnf | /r/LocalLLaMA/comments/190brnf/mixtral_8x7b_what_are_the_experts/ | false | false | self | 79 | null |
Quad P40 or Quad P100 | 3 | For some time I’ve had a variety of setups leveraging Dell Poweredge R720 & R730. I graduated from dual M40 to mostly Dual P100 or P40.
It seems to have gotten easier to manage larger models through Ollama, FastChat, ExUI, EricLLm, exllamav2 supported projects.
I’ve decided to try a 4 GPU capable rig. ASUS ESC4000 G3... | 2024-01-06T21:40:44 | https://www.reddit.com/r/LocalLLaMA/comments/190azgw/quad_p40_or_quad_p100/ | MachineZer0 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 190azgw | false | null | t3_190azgw | /r/LocalLLaMA/comments/190azgw/quad_p40_or_quad_p100/ | false | false | self | 3 | null |
Best Literature LLM? | 3 | So far models have been pretty underwhelming for me as an english lit fanatic. Are there any models which might prove a balm for this agony?
The closest I have found is MonadGPT.
this is not to "help me write a book", but rather to hold an engaging conversation with an entity relatively aware of literature at large. | 2024-01-06T21:30:47 | https://www.reddit.com/r/LocalLLaMA/comments/190aqzf/best_literature_llm/ | Parfington | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 190aqzf | false | null | t3_190aqzf | /r/LocalLLaMA/comments/190aqzf/best_literature_llm/ | false | false | self | 3 | null |
Prompts for reasoning tasks to tested on a model finetuned for reasoning and long sys prompts | 11 | I'm experimenting with finetuning LLMs for reasoning and I would be glad if you could provide some reasoning prompt to test my LLMs with or prompta with a very long system prompt.
Attached are some examples of the kind of prompts I'm looking for and the responds [one of my latest models](https://huggingface.co/Mihaiii... | 2024-01-06T21:30:04 | https://www.reddit.com/gallery/190aqa6 | Either-Job-341 | reddit.com | 1970-01-01T00:00:00 | 0 | {} | 190aqa6 | false | null | t3_190aqa6 | /r/LocalLLaMA/comments/190aqa6/prompts_for_reasoning_tasks_to_tested_on_a_model/ | false | false | 11 | null | |
Is there a self-hosted LLM guide for dummies? | 1 | [removed] | 2024-01-06T20:44:36 | https://www.reddit.com/r/LocalLLaMA/comments/1909o1n/is_there_a_selfhosted_llm_guide_for_dummies/ | kaszebe | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 1909o1n | false | null | t3_1909o1n | /r/LocalLLaMA/comments/1909o1n/is_there_a_selfhosted_llm_guide_for_dummies/ | false | false | self | 1 | null |
What can you do with 1.5TB of RAM that you can't with 758GB? | 56 | Ok so I'm speccing out a fairly large little workstation, and I plan to use all 12 channels of DDR5 for inference (and VMS, etc) with an Epyc Genoa.
But I'm seeing that a 1x64GB module of DDR5-4800 costs about $225, while 128GB modules cost ~6x as opposed to double. I asked a seller their opinion and they simply said... | 2024-01-06T20:41:28 | https://www.reddit.com/r/LocalLLaMA/comments/1909lg3/what_can_you_do_with_15tb_of_ram_that_you_cant/ | Massive_Robot_Cactus | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 1909lg3 | false | null | t3_1909lg3 | /r/LocalLLaMA/comments/1909lg3/what_can_you_do_with_15tb_of_ram_that_you_cant/ | false | false | self | 56 | null |
Efficient LLM fine-tuning for classification on Mac | 1 | [removed] | 2024-01-06T20:20:40 | https://www.reddit.com/r/LocalLLaMA/comments/19093xc/efficient_llm_finetuning_for_classification_on_mac/ | Reexpressionist | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 19093xc | false | null | t3_19093xc | /r/LocalLLaMA/comments/19093xc/efficient_llm_finetuning_for_classification_on_mac/ | false | false | self | 1 | {'enabled': False, 'images': [{'id': '0ksZ4wPIhd8Lx0M3zECUpL9oySFRiL6q2ckXWdeqns8', 'resolutions': [{'height': 54, 'url': 'https://external-preview.redd.it/yOjc73KOP-FH7RO-KHGdi1ZUvOUpINJUklOxdBmNd24.jpg?width=108&crop=smart&auto=webp&s=896e04294e6277cee861b66028120d03c3ff0d24', 'width': 108}, {'height': 108, 'url': 'h... |
Has anyone gotten a version of the Mistral 7B working on a 3090? I'm having issues. | 1 | [removed] | 2024-01-06T20:10:47 | https://www.reddit.com/r/LocalLLaMA/comments/1908vh4/has_anyone_gotten_a_version_of_the_mistral_7b/ | user_00000000000001 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 1908vh4 | false | null | t3_1908vh4 | /r/LocalLLaMA/comments/1908vh4/has_anyone_gotten_a_version_of_the_mistral_7b/ | false | false | self | 1 | null |
Fine-Tuning Mistral 7B with WhatsApp Chats – A Practical MLX Project | 28 | Hey everyone,
I've noticed a growing curiosity about the practical applications of MLX for fine-tuning models. To shed some light on this, I've created an interesting project: fine-tuning the Mistral 7B model using WhatsApp chat data.
Project Repository: [MLX-WhatsApp](https://github.com/gavi/mlx-whatsapp)
This pr... | 2024-01-06T19:55:40 | https://www.reddit.com/r/LocalLLaMA/comments/1908isa/finetuning_mistral_7b_with_whatsapp_chats_a/ | visualdata | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 1908isa | false | null | t3_1908isa | /r/LocalLLaMA/comments/1908isa/finetuning_mistral_7b_with_whatsapp_chats_a/ | false | false | self | 28 | {'enabled': False, 'images': [{'id': 'zvecD5-Kj3N5peC7J2aKGPGYHOSHTjEeBF8RRt7nKuA', 'resolutions': [{'height': 54, 'url': 'https://external-preview.redd.it/qMcxeBnZQ9p9VKks3MeU5cHwGVFff8Ac29cmUVnMq6E.jpg?width=108&crop=smart&auto=webp&s=4e0879c78743b305ff0b7c01dee971cac71624bd', 'width': 108}, {'height': 108, 'url': 'h... |
Any tips for getting 7B models to hallucinate less answering RAG questions? | 9 | How should I craft my prompts and should I only use texts of a certain length and below? | 2024-01-06T19:30:59 | https://www.reddit.com/r/LocalLLaMA/comments/1907xrf/any_tips_for_getting_7b_models_to_hallucinate/ | Basic_Description_56 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 1907xrf | false | null | t3_1907xrf | /r/LocalLLaMA/comments/1907xrf/any_tips_for_getting_7b_models_to_hallucinate/ | false | false | self | 9 | null |
Making a local recommendation system on top of Llama 2. Here is how it can help navigate the news from multiple sources. | 42 | 2024-01-06T19:28:10 | https://v.redd.it/w3mq72ugfvac1 | Another__one | v.redd.it | 1970-01-01T00:00:00 | 0 | {} | 1907vbt | false | {'reddit_video': {'bitrate_kbps': 5000, 'dash_url': 'https://v.redd.it/w3mq72ugfvac1/DASHPlaylist.mpd?a=1707161314%2CODZjMjQ1ZDcyMTcyMGJhNzIzZTkwZDA5ZTk1M2EzNzA2ZjI2ZDJlNjljYzk5ODY4ODZjOTEwNWQzOGEwMTQ1Ng%3D%3D&v=1&f=sd', 'duration': 64, 'fallback_url': 'https://v.redd.it/w3mq72ugfvac1/DASH_1080.mp4?source=fallback', 'h... | t3_1907vbt | /r/LocalLLaMA/comments/1907vbt/making_a_local_recommendation_system_on_top_of/ | false | false | 42 | {'enabled': False, 'images': [{'id': 'cmtzb2NyZ25mdmFjMRYr37H-VAaOoKxO49iYWEeRzuhrhK007_5FVazLIOd2', 'resolutions': [{'height': 81, 'url': 'https://external-preview.redd.it/cmtzb2NyZ25mdmFjMRYr37H-VAaOoKxO49iYWEeRzuhrhK007_5FVazLIOd2.png?width=108&crop=smart&format=pjpg&auto=webp&s=c14c9927224c7a70de207eebcee588ea97d91... | ||
The most difficult LLM "riddle" so far - "The Kanye Test" | 1 | [removed] | 2024-01-06T19:27:47 | https://www.reddit.com/r/LocalLLaMA/comments/1907v0c/the_most_difficult_llm_riddle_so_far_the_kanye/ | kindacognizant | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 1907v0c | false | null | t3_1907v0c | /r/LocalLLaMA/comments/1907v0c/the_most_difficult_llm_riddle_so_far_the_kanye/ | false | false | 1 | null | |
Question about generate method during training | 1 | Hello,
Would it be possible to use the generate function in the compute metrics of SFTTrainer for performing specialized metrics with the decoded outputs ?
​
def compute_metrics(eval_pred):
# use model.generate here
return {"bleu": bleu_score["score"], other specific thing... | 2024-01-06T19:12:09 | https://www.reddit.com/r/LocalLLaMA/comments/1907hqz/question_about_generate_method_during_training/ | BluebirdFinancial119 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 1907hqz | false | null | t3_1907hqz | /r/LocalLLaMA/comments/1907hqz/question_about_generate_method_during_training/ | false | false | self | 1 | null |
Wonder how Audio-to-Audio in <500ms could be possible | 1 | 2024-01-06T18:12:58 | https://x.com/usebland/status/1743411488612913429?s=46&t=GEEB35cWFcOM_iu_Jw3jug | Sutyum | x.com | 1970-01-01T00:00:00 | 0 | {} | 19063n4 | false | null | t3_19063n4 | /r/LocalLLaMA/comments/19063n4/wonder_how_audiotoaudio_in_500ms_could_be_possible/ | false | false | 1 | {'enabled': False, 'images': [{'id': 'SH9C1P7iJhFEBX7nT3XYXGi2w6j3ih4NIx8Xe-PSm1c', 'resolutions': [{'height': 60, 'url': 'https://external-preview.redd.it/VBRZ82tZBKRqLP6RSOo7Nqp2_IofdWeSC-cmHgC_VTA.jpg?width=108&crop=smart&auto=webp&s=ac8ad5dce8621b41f48182ba150e0b7364f1b846', 'width': 108}, {'height': 121, 'url': 'h... | ||
How can I provide an LLM a text file to read? | 6 | I am not sure if this is a oobabooga question, or a general LLM question, so I figured I would ask here first.
If I have a model I like, for example Wizard-Vicuna-30B-Uncensored-GPTQ, how can I ask it to read large amounts of data , like a really long text file? My understanding is Local LLM will be limited in the con... | 2024-01-06T17:59:37 | https://www.reddit.com/r/LocalLLaMA/comments/1905s0f/how_can_i_provide_an_llm_a_text_file_to_read/ | BackgroundAmoebaNine | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 1905s0f | false | null | t3_1905s0f | /r/LocalLLaMA/comments/1905s0f/how_can_i_provide_an_llm_a_text_file_to_read/ | false | false | self | 6 | null |
Looking for a text adventure model | 1 | [removed] | 2024-01-06T17:52:37 | https://www.reddit.com/r/LocalLLaMA/comments/1905m4o/looking_for_a_text_adventure_model/ | TheLewdCrafter | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 1905m4o | false | null | t3_1905m4o | /r/LocalLLaMA/comments/1905m4o/looking_for_a_text_adventure_model/ | false | false | nsfw | 1 | null |
Share your Llama2 generation speeds. | 1 | [removed] | 2024-01-06T17:47:43 | https://www.reddit.com/r/LocalLLaMA/comments/1905hu7/share_your_llama2_generation_speeds/ | ramzeez88 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 1905hu7 | false | null | t3_1905hu7 | /r/LocalLLaMA/comments/1905hu7/share_your_llama2_generation_speeds/ | false | false | self | 1 | null |
Rented cloud GPU server or alternatives if any? | 2 | I don't have enough powerful laptop/pc to work with local LLMs. My aim is to learn different aspect of LLMs like inferencing, fine tuning (qlora), RAG, Q&A etc. I want to try 7B, 13B, and even biggers models. Down the road i want to try multimodals and build apps on them.
Also, at this moment, I can't buy a new machi... | 2024-01-06T17:40:21 | https://www.reddit.com/r/LocalLLaMA/comments/1905bjy/rented_cloud_gpu_server_or_alternatives_if_any/ | sanjay303 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 1905bjy | false | null | t3_1905bjy | /r/LocalLLaMA/comments/1905bjy/rented_cloud_gpu_server_or_alternatives_if_any/ | false | false | self | 2 | null |
How much memory do long context LLMs need for inference? | 5 | I have a NousResearch/Yarn-Mistral-7b-128k model finetuned with LoRA. It's a long-context model (128k). When I load it in 4 bit and prompt it with 63k characters, I run out of memory:
torch.cuda.OutOfMemoryError: CUDA out of memory. Tried to allocate 34.92 GiB. GPU 0 has a total capacty of 79.18 GiB of which 19.2... | 2024-01-06T17:30:33 | https://www.reddit.com/r/LocalLLaMA/comments/190536f/how_much_memory_do_long_context_llms_need_for/ | Foxtr0t | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 190536f | false | null | t3_190536f | /r/LocalLLaMA/comments/190536f/how_much_memory_do_long_context_llms_need_for/ | false | false | self | 5 | null |
Meta prompting / auto-prompt writing | 1 | 2024-01-06T17:27:13 | Glass_Journalist6022 | i.redd.it | 1970-01-01T00:00:00 | 0 | {} | 19050gf | false | null | t3_19050gf | /r/LocalLLaMA/comments/19050gf/meta_prompting_autoprompt_writing/ | false | false | 1 | {'enabled': True, 'images': [{'id': 'twxbNsvcpmxMKIL-zhXuwPZr3YobtO62KB_Vf5qiUNM', 'resolutions': [{'height': 60, 'url': 'https://preview.redd.it/msmf0s61uuac1.gif?width=108&crop=smart&format=png8&s=f838e28b281eb3e6120f9de5608137f1af0cec30', 'width': 108}, {'height': 121, 'url': 'https://preview.redd.it/msmf0s61uuac1.g... | |||
Meta prompting / auto-prompt writing | 1 | [deleted] | 2024-01-06T17:25:58 | [deleted] | 1970-01-01T00:00:00 | 0 | {} | 1904zfy | false | null | t3_1904zfy | /r/LocalLLaMA/comments/1904zfy/meta_prompting_autoprompt_writing/ | false | false | default | 1 | null | ||
AI/gaming PC rig upgrades for LLMs | 2 | I built a PC rig to game and experiment with AI with a current focus on image generation with Stable Diffusion. Eventually, I intend to start working with LLMs, so I am wondering what changes I should consider at that point. I have a 7800x3d CPU, 2x16GB DDR5 CL30 RAM, 4090 with 24GB VRAM, and 1000W PSU. My motherboard ... | 2024-01-06T17:24:42 | https://www.reddit.com/r/LocalLLaMA/comments/1904ydl/aigaming_pc_rig_upgrades_for_llms/ | Admirable_Yam_7581 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 1904ydl | false | null | t3_1904ydl | /r/LocalLLaMA/comments/1904ydl/aigaming_pc_rig_upgrades_for_llms/ | false | false | self | 2 | null |
This is incredible. Imagine a massive model using lots of smaller specialised models. Best of both worlds. Kind of like Autogen but much more coherent. | 182 | https://huggingface.co/papers/2401.02412 | 2024-01-06T17:22:20 | TysonUsykFury | i.redd.it | 1970-01-01T00:00:00 | 0 | {} | 1904wfm | false | null | t3_1904wfm | /r/LocalLLaMA/comments/1904wfm/this_is_incredible_imagine_a_massive_model_using/ | false | false | 182 | {'enabled': True, 'images': [{'id': 'rboPoDp50aMn2cD3vEyEiZA4Z4AXmVK-Fkd9zxnVV5w', 'resolutions': [{'height': 95, 'url': 'https://preview.redd.it/p4syrqa7tuac1.jpeg?width=108&crop=smart&auto=webp&s=618028b74c4a744a22b14903b23911d2b7ecc41d', 'width': 108}, {'height': 190, 'url': 'https://preview.redd.it/p4syrqa7tuac1.jp... | ||
Any way to exclude input prompt from Llama.cpp output? | 1 | I'm trying to build an automated flow with llama.cpp for generating keywords and description/summary for the content I publish to my website upon submission. I'm doing this by concatenating the prompt/instruction with content from my original file and then redirecting STDOUT to another file. The problem is that output ... | 2024-01-06T17:03:56 | https://www.reddit.com/r/LocalLLaMA/comments/1904gzw/any_way_to_exclude_input_prompt_from_llamacpp/ | atsepkov | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 1904gzw | false | null | t3_1904gzw | /r/LocalLLaMA/comments/1904gzw/any_way_to_exclude_input_prompt_from_llamacpp/ | false | false | self | 1 | null |
Chess-GPT, a 50M parameter LLM, plays 1500 ELO chess. We can visualize its internal board state, and it accurately estimates the ELO rating of the players in a game. | 90 | gpt-3.5-turbo-instruct's ELO rating of 1800 is chess seemed magical. But it's not! A 50M parameter LLM given a few million games of chess will learn to play at ELO 1500. When a linear probe is trained on its internal board state, it accurately classifies the state of 99.2% of all board squares.
For example, in this... | 2024-01-06T17:00:34 | https://www.reddit.com/r/LocalLLaMA/comments/1904e2t/chessgpt_a_50m_parameter_llm_plays_1500_elo_chess/ | seraine | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 1904e2t | false | null | t3_1904e2t | /r/LocalLLaMA/comments/1904e2t/chessgpt_a_50m_parameter_llm_plays_1500_elo_chess/ | false | false | 90 | null | |
Finetuning for Bigger Context Windows? | 11 | Forgive me for my simplistic understanding but as I understand it, any model built on Llama-2 is likely going to be limited by a 4096 context window. However, I have found some instances where models built on it claim to have larger windows. I'm extremely happy with a (yeah, I know) GPT3.5-Turbo finetune I have trained... | 2024-01-06T16:52:54 | https://www.reddit.com/r/LocalLLaMA/comments/190481b/finetuning_for_bigger_context_windows/ | _winterwoods | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 190481b | false | null | t3_190481b | /r/LocalLLaMA/comments/190481b/finetuning_for_bigger_context_windows/ | false | false | self | 11 | null |
What attracted you to local LLMs? | 5 | I’m starting to get into this myself and am curious what if some specific use case/feature attracted most people or if it’s just “from a technical perspective this is interesting, so I want to play with it”. | 2024-01-06T16:39:27 | https://www.reddit.com/r/LocalLLaMA/comments/1903x83/what_attracted_you_to_local_llms/ | V3yhron | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 1903x83 | false | null | t3_1903x83 | /r/LocalLLaMA/comments/1903x83/what_attracted_you_to_local_llms/ | false | false | self | 5 | null |
Consistent asterisk for RP | 1 | In roleplaying, I always indicate my character's actions with asterisks (*). However, I've noticed that my responses often deviate from the given prompt. Currently, I'm using MythoMax 13B with an Alpaca format. Is there a way to make my prompts more effective, similar to how ChatGPT does it? | 2024-01-06T16:33:43 | https://www.reddit.com/r/LocalLLaMA/comments/1903soc/consistent_asterisk_for_rp/ | duryanis | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 1903soc | false | null | t3_1903soc | /r/LocalLLaMA/comments/1903soc/consistent_asterisk_for_rp/ | false | false | self | 1 | null |
How do you get embedding with llama.cpp? | 3 | I’m a bit confused why it’s not so easy to get an embedding vector. I’m sure I’m missing something important. Do I always need a separate model just to get embeddings? Are there any great open source models that also have embedding vector models? | 2024-01-06T16:32:05 | https://www.reddit.com/r/LocalLLaMA/comments/1903rcx/how_do_you_get_embedding_with_llamacpp/ | richardanaya | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 1903rcx | false | null | t3_1903rcx | /r/LocalLLaMA/comments/1903rcx/how_do_you_get_embedding_with_llamacpp/ | false | false | self | 3 | null |
Need feedback: What's your take on unique, copyright-free LLM data sets? | 1 | Hey all, I'm considering using internally built scrapers to create data sets. I want to specialize in data packs that are most useful to the LLM training community (open source, with option for proprietary/unique on request).
OSS:
* Assured free from copyright constraints
* Fresh and distinctive data sets
Paid:
* A... | 2024-01-06T16:16:20 | https://www.reddit.com/r/LocalLLaMA/comments/1903eh7/need_feedback_whats_your_take_on_unique/ | turboscrape | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 1903eh7 | false | null | t3_1903eh7 | /r/LocalLLaMA/comments/1903eh7/need_feedback_whats_your_take_on_unique/ | false | false | self | 1 | null |
Incredible results with Long Agent Tree Search with open source models | 149 | Hello,
I saw GPT-4 with Long Agent Tree Search topping the HumanEval with a 94.4% pass@1 for a few weeks now. [https://paperswithcode.com/sota/code-generation-on-humaneval](https://paperswithcode.com/sota/code-generation-on-humaneval)
​
The authors of the [original paper](https://arxiv.org/abs/2310.04406) pos... | 2024-01-06T16:11:46 | https://www.reddit.com/r/LocalLLaMA/comments/1903auj/incredible_results_with_long_agent_tree_search/ | ArtZab | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 1903auj | false | null | t3_1903auj | /r/LocalLLaMA/comments/1903auj/incredible_results_with_long_agent_tree_search/ | false | false | self | 149 | {'enabled': False, 'images': [{'id': 'CNqE7T3ouiZlTldhzwsVzmdz1pXOn5EYTD391CIsa2o', 'resolutions': [{'height': 57, 'url': 'https://external-preview.redd.it/8HFYZqy3IJLuGuOkvVEQz-oV87eglAeTheasavU5-Ws.jpg?width=108&crop=smart&auto=webp&s=ff4760bb8bb547481e615649ee85c67cd8a23b4b', 'width': 108}, {'height': 114, 'url': 'h... |
TensorRT-LLM + Llama2 | 1 | Does anyone got code snips or git repo to test Llama2 on TensorRT-LLM ?
Been trying that for past couple of days and can't seem to get it done 😅
Thanks 🙌✌️ | 2024-01-06T15:57:34 | https://www.reddit.com/r/LocalLLaMA/comments/1902zcb/tensorrtllm_llama2/ | Few_Acanthisitta_858 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 1902zcb | false | null | t3_1902zcb | /r/LocalLLaMA/comments/1902zcb/tensorrtllm_llama2/ | false | false | self | 1 | null |
Best open-source LLM to run on my m2 8GB for summarizing text messages of around 1000-1500 tokens? | 3 | I know RAM is an issue, but given 8GB, I tried Mistral 7b 4bit quantised and nous-hermes 4bit quant. - and for 850 tokens of text messages between two people, it takes 22 and 21 seconds to generate a summary.
What smaller models should I go for? and how do you decide what models are suitable? is there a list out th... | 2024-01-06T15:47:21 | https://www.reddit.com/r/LocalLLaMA/comments/1902rot/best_opensource_llm_to_run_on_my_m2_8gb_for/ | coderinlaw | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 1902rot | false | null | t3_1902rot | /r/LocalLLaMA/comments/1902rot/best_opensource_llm_to_run_on_my_m2_8gb_for/ | false | false | self | 3 | null |
How to use custom python functions in falcon 7b | 1 | The idea is am using falcon-7b instruct model, locally in colab. And i want to call certain functions using falcon, lets say the user is saying what’s today weather , so the falcon will call a python function which has the ability to give the weather results, so the llm falcon will automatically call the function and g... | 2024-01-06T15:35:18 | https://www.reddit.com/r/LocalLLaMA/comments/1902im0/how_to_use_custom_python_functions_in_falcon_7b/ | Bright-Leopard9688 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 1902im0 | false | null | t3_1902im0 | /r/LocalLLaMA/comments/1902im0/how_to_use_custom_python_functions_in_falcon_7b/ | false | false | self | 1 | null |
Video resources? | 1 | Hey everyone, thank you for being active in here, this sub has been invaluable to get me started.
Is anyone aware of good youtube channels of people making how-to and in-depth video content on all things local LLMs + stable diffusion? Helpful for the visually dependent like myself.
Cheers | 2024-01-06T15:31:39 | https://www.reddit.com/r/LocalLLaMA/comments/1902fte/video_resources/ | stormer0 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 1902fte | false | null | t3_1902fte | /r/LocalLLaMA/comments/1902fte/video_resources/ | false | false | self | 1 | null |
Is it possible to fine tuning a model to improve RAG queries ? | 11 | Hi !
I am trying to use some local models + langchain on lawsuits in pt-br to make some queries.
Unfortunately the results are no so precise for some basic question :(
So, I would like to know if is possible to fine tuning a model to improve RAG queries.
If so, can you share some examples?
Thanks in advance... | 2024-01-06T15:02:25 | https://www.reddit.com/r/LocalLLaMA/comments/1901ttm/is_it_possible_to_fine_tuning_a_model_to_improve/ | celsowm | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 1901ttm | false | null | t3_1901ttm | /r/LocalLLaMA/comments/1901ttm/is_it_possible_to_fine_tuning_a_model_to_improve/ | false | false | self | 11 | null |
GitHub - Zjh-819/LLMDataHub: A quick guide (especially) for trending instruction finetuning datasets | 1 | 2024-01-06T14:40:56 | https://github.com/Zjh-819/LLMDataHub | sapporonight | github.com | 1970-01-01T00:00:00 | 0 | {} | 1901e43 | false | null | t3_1901e43 | /r/LocalLLaMA/comments/1901e43/github_zjh819llmdatahub_a_quick_guide_especially/ | false | false | 1 | {'enabled': False, 'images': [{'id': 'uuBQWC4tXxSnd1zY1VvAcNooAErvETXW928gIYwYJDQ', 'resolutions': [{'height': 54, 'url': 'https://external-preview.redd.it/w8Sgq8k-8Hibzni8uDKM6AYRwy2mFDN3AyZJOMDXxOU.jpg?width=108&crop=smart&auto=webp&s=453366b5c1903999790c4788c5d91ebea7437985', 'width': 108}, {'height': 108, 'url': 'h... | ||
Tencent releases LLaMA-Pro-8B-Instruct Chat Demo on Hugging Face | 1 | 2024-01-06T14:03:53 | https://x.com/_akhaliq/status/1743631700754677808?t=3K0t7IiJ54JfCB2Q76Kisg&s=34 | ninjasaid13 | x.com | 1970-01-01T00:00:00 | 0 | {} | 1900ne6 | false | null | t3_1900ne6 | /r/LocalLLaMA/comments/1900ne6/tencent_releases_llamapro8binstruct_chat_demo_on/ | false | false | 1 | {'enabled': False, 'images': [{'id': 'UsqAWsbklZho0yPPXTiy_nI6bENbJmr6uE89i53l3GY', 'resolutions': [{'height': 76, 'url': 'https://external-preview.redd.it/jVNr7rwdR-XK-_w9J35qttuQ4DdVgSFj7C6r8Tpdacc.jpg?width=108&crop=smart&auto=webp&s=b81ab2e7f693e66b3dab3d56e10eb1ca93a4d51a', 'width': 108}, {'height': 152, 'url': 'h... | ||
Is it worth paying 30% more for an RX 6600 than an RX 5700XT to chat with llama.cpp? | 1 | [removed] | 2024-01-06T13:18:36 | https://www.reddit.com/r/LocalLLaMA/comments/18zzth2/is_it_worth_paying_30_more_for_an_rx_6600_than_an/ | Elegant_Course2372 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 18zzth2 | false | null | t3_18zzth2 | /r/LocalLLaMA/comments/18zzth2/is_it_worth_paying_30_more_for_an_rx_6600_than_an/ | false | false | self | 1 | null |
My bypass method for erp nsfw for Mistral medium(and maybe others) | 1 | euphemism(unoffensive), innuendos(hint/indirect), rephrasing, code words, misspelling/wordplay/playful phonetic spelling/jibberish/combined/ made-up words, non-sexual sentences/terms, seduce/cause intrigue, start context with clues, adjusting prompting, vague prompting, make it sound innocent, change talking style/ sub... | 2024-01-06T13:02:55 | https://www.reddit.com/r/LocalLLaMA/comments/18zzjtd/my_bypass_method_for_erp_nsfw_for_mistral/ | headacheack2 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 18zzjtd | false | null | t3_18zzjtd | /r/LocalLLaMA/comments/18zzjtd/my_bypass_method_for_erp_nsfw_for_mistral/ | false | false | nsfw | 1 | null |
What is the latest news for Llama 3? | 23 | What is the latest news for Llama 3? | 2024-01-06T12:56:19 | https://www.reddit.com/r/LocalLLaMA/comments/18zzflg/what_is_the_latest_news_for_llama_3/ | Secret_Joke_2262 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 18zzflg | false | null | t3_18zzflg | /r/LocalLLaMA/comments/18zzflg/what_is_the_latest_news_for_llama_3/ | false | false | self | 23 | null |
Seeking Advice on Fastest and Highest Quality Implementation of Dolphin 2.2.1 Mistral 7b LLM | 1 | Hello everyone,
I'm currently exploring ways to get the Dolphin 2.2.1 Mistral 7b model up and running. My ultimate goal is to achieve the fastest and highest quality responses from this language model.
I'm typically inclined to build everything from scratch, but I'm uncertain about the workload this approach might en... | 2024-01-06T12:34:52 | https://www.reddit.com/r/LocalLLaMA/comments/18zz33d/seeking_advice_on_fastest_and_highest_quality/ | yachty66 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 18zz33d | false | null | t3_18zz33d | /r/LocalLLaMA/comments/18zz33d/seeking_advice_on_fastest_and_highest_quality/ | false | false | self | 1 | null |
llama.cpp GGUF inference in a couple lines of code | 3 | 2024-01-06T12:02:12 | davidmezzetti | i.redd.it | 1970-01-01T00:00:00 | 0 | {} | 18zykwo | false | null | t3_18zykwo | /r/LocalLLaMA/comments/18zykwo/llamacpp_gguf_inference_in_a_couple_lines_of_code/ | false | false | 3 | {'enabled': True, 'images': [{'id': 'kUV1nQlsNu7aDkjXzuvEebxkgGpsSULSxKlQukm6U8A', 'resolutions': [{'height': 59, 'url': 'https://preview.redd.it/z3s7gib28tac1.jpeg?width=108&crop=smart&auto=webp&s=b07e87c6585f03175801cc4afba3c47a45d54877', 'width': 108}, {'height': 118, 'url': 'https://preview.redd.it/z3s7gib28tac1.jp... | |||
Looking for most optimal model for my usecase | 1 | I'm new to LLM and ML and looking for a fairly lightweight solution. I am building a scheduling app. It takes user input and extracts an event title and date. For example: "I have a haircut tomorrow at 6pm" -> ["Haircut", "tomorrow 6pm"]. Date parsing is trivial with nlp, but I want something that will be able to deter... | 2024-01-06T11:44:45 | https://www.reddit.com/r/LocalLLaMA/comments/18zyb4n/looking_for_most_optimal_model_for_my_usecase/ | eagleps | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 18zyb4n | false | null | t3_18zyb4n | /r/LocalLLaMA/comments/18zyb4n/looking_for_most_optimal_model_for_my_usecase/ | false | false | self | 1 | null |
Seeking LLM that can check all these boxes & be fine tuned on 32GB Ram 3200 mhz ddr4, 8gb 3070, Ryzen 7 5800h | 1 | Hi there,
I'm currently exploring an idea of creating a project. For that I require a LLM that can check (atleast have a bare minimum capability) off all these boxes -
PS please tell me if there's any faster way to attain my goal of such LLM by using different setup or tools structure. I'm very new to this .
1) Be s... | 2024-01-06T11:36:47 | https://www.reddit.com/r/LocalLLaMA/comments/18zy6s0/seeking_llm_that_can_check_all_these_boxes_be/ | unkn0wnS0ul2day | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 18zy6s0 | false | null | t3_18zy6s0 | /r/LocalLLaMA/comments/18zy6s0/seeking_llm_that_can_check_all_these_boxes_be/ | false | false | self | 1 | null |
5700xt 8gb or 6600. the 5700 xt costs 20% less on aliexpress, and I don't need to pay the 100% tax in Brazil. (all incluse, of course) | 1 | Another post from a poor guy from the third world, where a guy won a court decision and only he can buy cheaper GPUs and all resellers have to buy from him or go to the gray market. Well, it looks like it's not that easy to borrow money. AI is a way for me to maintain my sanity, so I'm going to put my shame aside. The ... | 2024-01-06T11:34:12 | https://www.reddit.com/r/LocalLLaMA/comments/18zy5di/5700xt_8gb_or_6600_the_5700_xt_costs_20_less_on/ | Elegant_Course2372 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 18zy5di | false | null | t3_18zy5di | /r/LocalLLaMA/comments/18zy5di/5700xt_8gb_or_6600_the_5700_xt_costs_20_less_on/ | false | false | self | 1 | null |
Running llms on igpus | 1 | Hello everyone I read somewhere that this should be possible. And I think that comming amd products like strip halo and strip point with 16cu and 40cu + allegedly 40-50tops of xdna 2 should make stuff like this really interesting.
I also read that llama.cpp has uma support now and you can effectively use your whole m... | 2024-01-06T11:25:59 | https://www.reddit.com/r/LocalLLaMA/comments/18zy0tm/running_llms_on_igpus/ | Noxusequal | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 18zy0tm | false | null | t3_18zy0tm | /r/LocalLLaMA/comments/18zy0tm/running_llms_on_igpus/ | false | false | self | 1 | null |
How to run Llama-2 on CPU after fine-tuning with LoRA | 4 | 2024-01-06T11:22:41 | https://blog.oxen.ai/how-to-run-llama-2-on-cpu-after-fine-tuning-with-lora/ | pmz | blog.oxen.ai | 1970-01-01T00:00:00 | 0 | {} | 18zxz4i | false | null | t3_18zxz4i | /r/LocalLLaMA/comments/18zxz4i/how_to_run_llama2_on_cpu_after_finetuning_with/ | false | false | 4 | {'enabled': False, 'images': [{'id': 'aLDM6xhCNMlU0D8Wtt738MJRSF_QnceYVH87K3eMnzY', 'resolutions': [{'height': 100, 'url': 'https://external-preview.redd.it/nHHyS0o-j3tfxekXBUbK7jKcJX4WpoIbdDFFv86zGck.jpg?width=108&crop=smart&auto=webp&s=06d64395dbd17a8cb411487b44daee5c83f219b4', 'width': 108}, {'height': 200, 'url': '... | ||
Fastest Local LLM for my machine? | 1 | I have a RTX 3060 with 16gb ram, what would be the best model i could run that give me responses < 3 seconds ? | 2024-01-06T11:02:54 | https://www.reddit.com/r/LocalLLaMA/comments/18zxofh/fastest_local_llm_for_my_machine/ | its_kanwischer | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 18zxofh | false | null | t3_18zxofh | /r/LocalLLaMA/comments/18zxofh/fastest_local_llm_for_my_machine/ | false | false | self | 1 | null |
Phi-2 becomes open source (MIT license 🎉) | 401 | Microsoft changed phi-2 license a few hours ago from research to MIT. It means you can use it commercially now
[https://x.com/sebastienbubeck/status/1743519400626643359?s=46&t=rVJesDlTox1vuv\_SNtuIvQ](https://x.com/sebastienbubeck/status/1743519400626643359?s=46&t=rVJesDlTox1vuv_SNtuIvQ)
This is a great strategy as m... | 2024-01-06T09:02:50 | https://www.reddit.com/r/LocalLLaMA/comments/18zvxs8/phi2_becomes_open_source_mit_license/ | steph_pop | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 18zvxs8 | false | null | t3_18zvxs8 | /r/LocalLLaMA/comments/18zvxs8/phi2_becomes_open_source_mit_license/ | false | false | 401 | {'enabled': False, 'images': [{'id': 'BKTMGdw6ha-Ed4BBQMa2Zpw8phQStnlusB2aMwIsNro', 'resolutions': [{'height': 56, 'url': 'https://external-preview.redd.it/mSiDQSb_lE70g4QwK6ewK_gFLRdcCYyUjBww0PdUWBs.jpg?width=108&crop=smart&auto=webp&s=5abe5afc323b589e249327fa295a82041f835852', 'width': 108}, {'height': 113, 'url': 'h... | |
mlx lora/qlora example | 10 | Currently, the lora script in mlx-examples is a bit confused due to the different formats (hf/pytorch) of llama models. There is a lot of confusion when using it, so I quickly hacked around the script and created this example repo that supports the latest hf and quant models.
[https://github.com/mzbac/mlx-lora](https... | 2024-01-06T08:46:42 | https://www.reddit.com/r/LocalLLaMA/comments/18zvp32/mlx_loraqlora_example/ | mzbacd | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 18zvp32 | false | null | t3_18zvp32 | /r/LocalLLaMA/comments/18zvp32/mlx_loraqlora_example/ | false | false | self | 10 | {'enabled': False, 'images': [{'id': 'fJ7Lvz6b7B9IP-VD_FJxEU8wlRIJvTn1FahCYypkv9g', 'resolutions': [{'height': 54, 'url': 'https://external-preview.redd.it/X_6kUiObErK4iWZxhqlPhBbmdrvC-wiflO3paxQ9zRU.jpg?width=108&crop=smart&auto=webp&s=31ef5cd2ddf343753f5d71acb066234fa1effb45', 'width': 108}, {'height': 108, 'url': 'h... |
ChatGPT and Bard refuse to respond | 1 | 2024-01-06T08:45:48 | jacek2023 | i.redd.it | 1970-01-01T00:00:00 | 0 | {} | 18zvonz | false | null | t3_18zvonz | /r/LocalLLaMA/comments/18zvonz/chatgpt_and_bard_refuse_to_respond/ | false | false | 1 | {'enabled': True, 'images': [{'id': '6Z-B4-y4u3gu0oS3AGW-9Bs7mmPw0IQ35iduguDynkg', 'resolutions': [{'height': 66, 'url': 'https://preview.redd.it/ox5ulr209sac1.png?width=108&crop=smart&auto=webp&s=b66f2086e82da285fff204d5537ad41236582401', 'width': 108}, {'height': 132, 'url': 'https://preview.redd.it/ox5ulr209sac1.png... | |||
What is your interface of choice for collecting preference dataset? | 7 | ​
[character.ai's rating UI](https://preview.redd.it/k9eb1ban7sac1.jpg?width=1372&format=pjpg&auto=webp&s=cad1aa39fa9ca98d5476720155bd050012c3eefb)
[example of preference dataset](https://preview.redd.it/efggzjrg4sac1.jpg?width=3136&format=pjpg&auto=webp&s=9312a079cd6214c0c2622d5720e5e500f106b9be)
[Preference... | 2024-01-06T08:41:00 | https://www.reddit.com/r/LocalLLaMA/comments/18zvm4b/what_is_your_interface_of_choice_for_collecting/ | No_Investment8576 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 18zvm4b | false | null | t3_18zvm4b | /r/LocalLLaMA/comments/18zvm4b/what_is_your_interface_of_choice_for_collecting/ | false | false | 7 | null | |
ChatGPT and Bard refuse to respond | 1 | ​
https://preview.redd.it/qelvi8w28sac1.png?width=1893&format=png&auto=webp&s=09b275531bcdbe4de9dbc4eba10c355b94626283 | 2024-01-06T08:40:40 | https://www.reddit.com/r/LocalLLaMA/comments/18zvlxu/chatgpt_and_bard_refuse_to_respond/ | jacek2023 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 18zvlxu | false | null | t3_18zvlxu | /r/LocalLLaMA/comments/18zvlxu/chatgpt_and_bard_refuse_to_respond/ | false | false | 1 | null | |
Anyone feel like AI developments have slowed down a bit lately? | 1 | I have been trying to keep up to date on the latest developments each week. However, I have felt a sudden drop in the past two months. Especially the past three weeks. I can see it being due to the holidays. Yet, I want to make sure it's not just me. | 2024-01-06T08:39:15 | https://www.reddit.com/r/LocalLLaMA/comments/18zvl4w/anyone_feel_like_ai_developments_have_slowed_down/ | ArmoredBattalion | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 18zvl4w | false | null | t3_18zvl4w | /r/LocalLLaMA/comments/18zvl4w/anyone_feel_like_ai_developments_have_slowed_down/ | false | false | self | 1 | null |
Silicon-Maid-7B is surprisingly good for its weight. | 46 | Just know about this model based on some reviews from SillyTavern. Tried the \`Q4\_K\_M\` version, got \~20-30 token/s on an M1 pro, and it's surprisingly good for its weight:
* Follow the character card well
* Seems to understand nuance
* Action and dialogue is believable, no flowery prose yet
​
I got this f... | 2024-01-06T08:28:59 | https://www.reddit.com/r/LocalLLaMA/comments/18zvfil/siliconmaid7b_is_surprisingly_good_for_its_weight/ | ai_waifu_enjoyer | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 18zvfil | false | null | t3_18zvfil | /r/LocalLLaMA/comments/18zvfil/siliconmaid7b_is_surprisingly_good_for_its_weight/ | false | false | self | 46 | null |
What's currently the best model for roleplay/text adventures that can fit fully onto a 24 GB card? | 1 | I used to swear by Mlewd-ReMM-L2-Chat 20B for my text adventures, and it's still the best out of everything I've tried, even outdoing stuff like the larger 30B WizardLM SuperCOT Storytelling, or the smaller but still very fantastic Mythomax and Mythomix 13B models.
I've tried Tiefighter and Psyfighter and Athena, b... | 2024-01-06T08:10:39 | https://www.reddit.com/r/LocalLLaMA/comments/18zv60i/whats_currently_the_best_model_for_roleplaytext/ | Gyramuur | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 18zv60i | false | null | t3_18zv60i | /r/LocalLLaMA/comments/18zv60i/whats_currently_the_best_model_for_roleplaytext/ | false | false | self | 1 | null |
An overview of LLMs from training to inference | 19 | Paper: [https://arxiv.org/pdf/2401.02038.pdf](https://arxiv.org/pdf/2401.02038.pdf)
[Non-PDF link](https://arxiv.org/abs/2401.02038)
I saw this on arxiv and it looked like a decent introduction for anyone unfamiliar with LLMs and a lot of the terminology:
>This paper reviews the evolution of large language model tra... | 2024-01-06T08:03:02 | https://www.reddit.com/r/LocalLLaMA/comments/18zv20t/an_overview_of_llms_from_training_to_inference/ | llamaShill | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 18zv20t | false | null | t3_18zv20t | /r/LocalLLaMA/comments/18zv20t/an_overview_of_llms_from_training_to_inference/ | false | false | self | 19 | null |
How can I share model files between LM Studio, oobabooga, etc? | 1 | LM Studio has a really nice interface for downloading and quickly testing models, but I would also like to use these models on other interfaces like oobabooga. Ideally, I would have one model directory and could test out the same model on many interfaces. I looked at the directory structure for LM Studio and it is very... | 2024-01-06T07:53:10 | https://www.reddit.com/r/LocalLLaMA/comments/18zuwkm/how_can_i_share_model_files_between_lm_studio/ | KingJeff314 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 18zuwkm | false | null | t3_18zuwkm | /r/LocalLLaMA/comments/18zuwkm/how_can_i_share_model_files_between_lm_studio/ | false | false | self | 1 | null |
How to finetune Mistral 7b model without Quantization methods like QLORA or LORA? | 1 | Hello everyone, I'm interested in fine-tuning the Mistral 7b model without any quantization specifically for WikiSQL data. Could you provide assistance with the process? | 2024-01-06T07:24:42 | https://www.reddit.com/r/LocalLLaMA/comments/18zugrh/how_to_finetune_mistral_7b_model_without/ | Gowthamkumar07 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 18zugrh | false | null | t3_18zugrh | /r/LocalLLaMA/comments/18zugrh/how_to_finetune_mistral_7b_model_without/ | false | false | self | 1 | null |
Mac Studio vs a PC (NVIDIA) rig for a home setup? | 15 | I know we get these posts on the regular ([one](https://www.reddit.com/r/LocalLLaMA/comments/18oclws/macbook_or_pc_for_running_llms/), [two](https://www.reddit.com/r/LocalLLaMA/comments/15gwhfa/is_buying_mac_studio_a_good_idea_for_running/), [three](https://www.reddit.com/r/LocalLLaMA/comments/16m432j/mac_studio_m2_ult... | 2024-01-06T06:52:20 | https://www.reddit.com/r/LocalLLaMA/comments/18ztxtk/mac_studio_vs_a_pc_nvidia_rig_for_a_home_setup/ | ablasionet | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 18ztxtk | false | null | t3_18ztxtk | /r/LocalLLaMA/comments/18ztxtk/mac_studio_vs_a_pc_nvidia_rig_for_a_home_setup/ | false | false | self | 15 | {'enabled': False, 'images': [{'id': '-cKEcU0N3Ppyb9CSkk8Rt1HZESBqnHudbQVeWdc1Go4', 'resolutions': [{'height': 54, 'url': 'https://external-preview.redd.it/X1sVjSIeI3cp_bWlWmIsdkEXTMFan2CmbGRZ-1Iq3zA.jpg?width=108&crop=smart&auto=webp&s=eb261c3bae63698584839bdde26efba6cff6cbf8', 'width': 108}, {'height': 108, 'url': 'h... |
Cloud? | 1 | There are many threads here about hardware. Assuming one doesn’t need the protection a local solution affords, is it better and more cost effective to use something like RunPod? How does it work? Do you just reserve space to run, say, Goliath, whenever you want?
It seems like this would be something I should familiari... | 2024-01-06T06:33:09 | https://www.reddit.com/r/LocalLLaMA/comments/18ztmu7/cloud/ | Hinged31 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 18ztmu7 | false | null | t3_18ztmu7 | /r/LocalLLaMA/comments/18ztmu7/cloud/ | false | false | self | 1 | null |
My M1 Max performance drops when connected to external displays. Anyone else? | 1 | I am running `Mixtral 8X7B Instruct v0.1 Q8_0` on my M1 Max (64GB). When connected to an external display, I get around `1327ms per token, 0.75 tokens per second`, but when I am running with just the laptop, I get `125ms per token, 7.98 tokens per second`.
I assume that my external displays (2x 5K) use more GPU horsep... | 2024-01-06T06:30:51 | https://www.reddit.com/r/LocalLLaMA/comments/18ztlj0/my_m1_max_performance_drops_when_connected_to/ | ReagentX | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 18ztlj0 | false | null | t3_18ztlj0 | /r/LocalLLaMA/comments/18ztlj0/my_m1_max_performance_drops_when_connected_to/ | false | false | self | 1 | null |
Trying to run dolphin 2.7 AWQ by The Bloke via oobabooga, cannot load | 1 | [removed] | 2024-01-06T05:34:39 | https://www.reddit.com/r/LocalLLaMA/comments/18zsm3b/trying_to_run_dolphin_27_awq_by_the_bloke_via/ | Argol228 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 18zsm3b | false | null | t3_18zsm3b | /r/LocalLLaMA/comments/18zsm3b/trying_to_run_dolphin_27_awq_by_the_bloke_via/ | false | false | self | 1 | null |
Code Interpreter/ Data Analysis for Local LLMs? | 1 | [removed] | 2024-01-06T05:22:34 | https://www.reddit.com/r/LocalLLaMA/comments/18zsecu/code_interpreter_data_analysis_for_local_llms/ | IWantAGI | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 18zsecu | false | null | t3_18zsecu | /r/LocalLLaMA/comments/18zsecu/code_interpreter_data_analysis_for_local_llms/ | false | false | self | 1 | null |
Broody's Story Brainstorming LLM (NSFW) TierList v1.0 | 17 | Hi,
I tried brainstorming my story outline, with an NSFW theme. I used openrouter, online playgrounds, Runpod, etc. This is my tier list.
In my view, LLMs under the 34B model are not worth trying for creative purposes. The size of the model comes first. Training data & fine-tuning comes second.
**Method :**
\- Used... | 2024-01-06T05:17:37 | https://www.reddit.com/r/LocalLLaMA/comments/18zsb6x/broodys_story_brainstorming_llm_nsfw_tierlist_v10/ | broodysupertramp | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 18zsb6x | false | null | t3_18zsb6x | /r/LocalLLaMA/comments/18zsb6x/broodys_story_brainstorming_llm_nsfw_tierlist_v10/ | false | false | nsfw | 17 | null |
Is Phi 2 Open Source? Fine tunes? | 65 | I read that Microsoft originally released it with some research license saying you couldn't build commercial products off of it.
But looking at HF license it's pretty vanilla MIT.
https://huggingface.co/microsoft/phi-2/blob/main/LICENSE
WDYT?
Also, any phi 2 fine tunes out there? Seems like a badass model beating M... | 2024-01-06T04:26:20 | https://www.reddit.com/r/LocalLLaMA/comments/18zrco1/is_phi_2_open_source_fine_tunes/ | mattlock1984 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 18zrco1 | false | null | t3_18zrco1 | /r/LocalLLaMA/comments/18zrco1/is_phi_2_open_source_fine_tunes/ | false | false | self | 65 | {'enabled': False, 'images': [{'id': 'IC9jEjr4wqjQ7Zp6pkl3zp0k6W16A-udtoplxE4MnyY', 'resolutions': [{'height': 58, 'url': 'https://external-preview.redd.it/Bou0VApCNu-gpJZ801OxRYO9_HcS0Q7xXm8ez7FBuBI.jpg?width=108&crop=smart&auto=webp&s=0e88db6a0c39318ffd52cbcc7a8c5ebd7f2446f4', 'width': 108}, {'height': 116, 'url': 'h... |
Library to make MoE models? | 1 | I'm planning on experimenting with different model sizes from 125m to 3B and possibly fine-tuning the MoE too.
I wanted to know if there was any OSS that helps making MoEs before I try to implement on my own.
TIA. | 2024-01-06T04:25:33 | https://www.reddit.com/r/LocalLLaMA/comments/18zrc61/library_to_make_moe_models/ | Dry_Long3157 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 18zrc61 | false | null | t3_18zrc61 | /r/LocalLLaMA/comments/18zrc61/library_to_make_moe_models/ | false | false | self | 1 | null |
The secret to writing quality stories with LLMs | 173 | Obviously, chat/RP is all the rage with local LLMs, but I like using them to write stories as well. It seems completely natural to attempt to generate a story by typing something like this into an instruction prompt:
> Write a long, highly detailed fantasy adventure story about a young man who enters a portal that he ... | 2024-01-06T04:04:11 | https://www.reddit.com/r/LocalLLaMA/comments/18zqy4s/the_secret_to_writing_quality_stories_with_llms/ | -p-e-w- | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 18zqy4s | false | null | t3_18zqy4s | /r/LocalLLaMA/comments/18zqy4s/the_secret_to_writing_quality_stories_with_llms/ | false | false | self | 173 | null |
How to insert user profile in prompt for tiefighter? | 1 | [removed] | 2024-01-06T03:47:03 | https://www.reddit.com/r/LocalLLaMA/comments/18zqmbv/how_to_insert_user_profile_in_prompt_for/ | Saihhold_Zhao | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 18zqmbv | false | null | t3_18zqmbv | /r/LocalLLaMA/comments/18zqmbv/how_to_insert_user_profile_in_prompt_for/ | false | false | self | 1 | null |
How can I get more correct responses? | 4 | I am passing approximately 17k characters (a few pages) worth of smart home sensor information formatted in YAML to CodeBooga-34B-v0.1-5.0bpw-h6-exl2 (Oobabooga). This is by far the best model I've tried so far. Here is the prompt:
You are an AI smart home.
AI smart home directives:
- IMPORTANT: ACT... | 2024-01-06T03:40:54 | https://www.reddit.com/r/LocalLLaMA/comments/18zqhvp/how_can_i_get_more_correct_responses/ | flossraptor | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 18zqhvp | false | null | t3_18zqhvp | /r/LocalLLaMA/comments/18zqhvp/how_can_i_get_more_correct_responses/ | false | false | self | 4 | null |
How to prompt phi 1.5 to select answers from the choices given? Any alternatives are also ok. | 1 | Below is my template:
`You are an SQL expert. Be truthful and if you cannot answer convincingly just say 'I do not know'. Do not write any explanations, generate code and follow only the examples given.`
`<table name> : <table description>`
`Q: Select all the employees from India.`
`A: employees, location`
`Q: sel... | 2024-01-06T03:33:50 | https://www.reddit.com/r/LocalLLaMA/comments/18zqcz7/how_to_prompt_phi_15_to_select_answers_from_the/ | sanjeevr5 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 18zqcz7 | false | null | t3_18zqcz7 | /r/LocalLLaMA/comments/18zqcz7/how_to_prompt_phi_15_to_select_answers_from_the/ | false | false | self | 1 | null |
Lm studio keeps crashing on my device | 1 | It opens for a few seconds and closes autmatically | 2024-01-06T03:21:40 | https://www.reddit.com/r/LocalLLaMA/comments/18zq4ei/lm_studio_keeps_crashing_on_my_device/ | Repulsive_Song3238 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 18zq4ei | false | null | t3_18zq4ei | /r/LocalLLaMA/comments/18zq4ei/lm_studio_keeps_crashing_on_my_device/ | false | false | self | 1 | null |
Experimenting with small language models | 59 | So recently I've been experimenting with the idea of building small language models (SLMs) for hyper specific tasks that can run locally.
Today I trained a 1.46M parameter model on the [TinyStories](https://huggingface.co/datasets/roneneldan/TinyStories) dataset, and it can *almost* write coherent short stories.
All ... | 2024-01-06T02:18:02 | https://www.reddit.com/r/LocalLLaMA/comments/18zot2e/experimenting_with_small_language_models/ | IffyNibba01 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 18zot2e | false | null | t3_18zot2e | /r/LocalLLaMA/comments/18zot2e/experimenting_with_small_language_models/ | false | false | self | 59 | {'enabled': False, 'images': [{'id': 'KiqHRZTfs_AFJ5t2lFt8pIfVYEvvqCKMmiloHkhhHDo', 'resolutions': [{'height': 58, 'url': 'https://external-preview.redd.it/QAS2p9dJT7n4beYxTudeBRfTOujpiYAK4Un6MQw1rgY.jpg?width=108&crop=smart&auto=webp&s=9adf55e267406cc423a3ce2825661e547fdb07af', 'width': 108}, {'height': 116, 'url': 'h... |
Subsets and Splits
No community queries yet
The top public SQL queries from the community will appear here once available.