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 ⌀ |
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
What Makes Good Data for Alignment? A Comprehensive Study of Automatic Data Selection in Instruction Tuning | 12 | Abstract
>Instruction tuning is a standard technique employed to align large language models to end tasks and user preferences after the initial pretraining phase. Recent research indicates the critical role of data engineering in instruction tuning -- when appropriately selected, only limited data is necessary to ach... | 2024-01-09T10:42:00 | https://www.reddit.com/r/LocalLLaMA/comments/192bwbm/what_makes_good_data_for_alignment_a/ | dvanstrien | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 192bwbm | false | null | t3_192bwbm | /r/LocalLLaMA/comments/192bwbm/what_makes_good_data_for_alignment_a/ | false | false | self | 12 | {'enabled': False, 'images': [{'id': 'j1LIVRyfLa7FXB41Am1KFCIZ-eLG9YUMlmXLOVK0_kk', 'resolutions': [{'height': 58, 'url': 'https://external-preview.redd.it/3y585MFHxnv9J5fwc6jJjMygdv2b3dLV9jnj_OelNtc.jpg?width=108&crop=smart&auto=webp&s=c9af3c8a9ac25bf37ab89f9360faef1245dc2808', 'width': 108}, {'height': 116, 'url': 'h... |
Can someone explain me th new AMD AI coprocessors? | 4 | They make little sense to me outside possible on a power saving side.
The 8400G has an AI sub-processor. Ok, but - for anything not super tiny - and I talk REALLY tiny - it STILL is a mobile processor with a SERIOUS RAM speed limit. Big enough that the 8 cores can not be fed for AI inference, or?
So, why the extra s... | 2024-01-09T10:41:22 | https://www.reddit.com/r/LocalLLaMA/comments/192bvzh/can_someone_explain_me_th_new_amd_ai_coprocessors/ | artelligence_consult | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 192bvzh | false | null | t3_192bvzh | /r/LocalLLaMA/comments/192bvzh/can_someone_explain_me_th_new_amd_ai_coprocessors/ | false | false | self | 4 | null |
Code-LlaMa-2-13B-instruct-text2sql | 1 | Using the above mentioned model from hugging face for text 2 sql. Using the example given in the link https://huggingface.co/bugdaryarn/Code-Llama-2-13B-instruct-text2sql
I am getting the below error
RuntimeError : Failed to create LLM from ‘llama’
Can anyone please guide me? | 2024-01-09T10:40:22 | https://www.reddit.com/r/LocalLLaMA/comments/192bvg8/codellama213binstructtext2sql/ | Kachikairi | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 192bvg8 | false | null | t3_192bvg8 | /r/LocalLLaMA/comments/192bvg8/codellama213binstructtext2sql/ | false | false | self | 1 | null |
This is pretty cool | 181 | Chai Research presents Blending Is All You Need
Cheaper, Better Alternative to Trillion-Parameters LLM
In conversational AI research, there's a noticeable trend towards developing models with a larger number of parameters, exemplified by models like ChatGPT. While these expansive models tend to generate increasingly ... | 2024-01-09T10:13:53 | GasBond | i.redd.it | 1970-01-01T00:00:00 | 0 | {} | 192bhjm | false | null | t3_192bhjm | /r/LocalLLaMA/comments/192bhjm/this_is_pretty_cool/ | false | false | 181 | {'enabled': True, 'images': [{'id': '8vtZQSUF_o5-cDpa15WU8bKwxqm1GjX79Q9fR4uXWGQ', 'resolutions': [{'height': 114, 'url': 'https://preview.redd.it/ozxv3i7h3ebc1.jpeg?width=108&crop=smart&auto=webp&s=8ed589160d134b9ba230a321e2687d9386b19289', 'width': 108}, {'height': 228, 'url': 'https://preview.redd.it/ozxv3i7h3ebc1.j... | ||
Chai Research presents Blending Is All You Need | 1 |
Cheaper, Better Alternative to Trillion-Parameters LLM
paper page: huggingface.co/papers/2401.02…
In conversational AI research, there's a noticeable trend towards developing models with a larger number of parameters, exemplified by models like ChatGPT. While these expansive models tend to generate increasingly bet... | 2024-01-09T10:11:56 | GasBond | i.redd.it | 1970-01-01T00:00:00 | 0 | {} | 192bghv | false | null | t3_192bghv | /r/LocalLLaMA/comments/192bghv/chai_research_presents_blending_is_all_you_need/ | false | false | 1 | {'enabled': True, 'images': [{'id': 'Z29bURI5PVsnmSPb_sVSpHJVbhHK4RddXeELltpNq_I', 'resolutions': [{'height': 114, 'url': 'https://preview.redd.it/04zl55753ebc1.jpeg?width=108&crop=smart&auto=webp&s=a9a04344440a6d0ecb76bd9a2f08b35bc4d993e1', 'width': 108}, {'height': 228, 'url': 'https://preview.redd.it/04zl55753ebc1.j... | ||
GPU Suggestion for Local LLM | 1 | Hello everyone,
I am looking for building my own rig to train a local, personalized LLM. My main goal is to build it to be an AI assistant, so that I can pipe various tasks to it. I need it to be as good as GPT-3 level in general. A little worse than GPT-3 is also OK I guess, I just want it to do text completion, basi... | 2024-01-09T10:01:53 | https://www.reddit.com/r/LocalLLaMA/comments/192bbbo/gpu_suggestion_for_local_llm/ | Ear-Right | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 192bbbo | false | null | t3_192bbbo | /r/LocalLLaMA/comments/192bbbo/gpu_suggestion_for_local_llm/ | false | false | self | 1 | null |
Needadvice for chatbot for mental health therapy, what model do your suggest compatible with 3090? | 1 | [removed] | 2024-01-09T09:30:29 | https://www.reddit.com/r/LocalLLaMA/comments/192auzc/needadvice_for_chatbot_for_mental_health_therapy/ | Independent-Bill-770 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 192auzc | false | null | t3_192auzc | /r/LocalLLaMA/comments/192auzc/needadvice_for_chatbot_for_mental_health_therapy/ | false | false | self | 1 | null |
Extracting information out of real estate description | 1 | Hi, I would like to use/train a model that extracts a certain type of information from a real estate description:
for example terrace surface area:
input: This large apartment has a big south-east oriented 10m² terrace with a nice view.
output: 10
The goal is to use it on 100k real estate descriptions.
W... | 2024-01-09T09:18:03 | https://www.reddit.com/r/LocalLLaMA/comments/192aon1/extracting_information_out_of_real_estate/ | Puzzleheaded-Nerve13 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 192aon1 | false | null | t3_192aon1 | /r/LocalLLaMA/comments/192aon1/extracting_information_out_of_real_estate/ | false | false | self | 1 | null |
Using local data for context | 2 | Hi all, I'm looking at connecting an LLM to a folder of text documents for context. I've been investigating ChatGPT4All and Langchain as possible ways to achieve this, but I'm most familiar with KoboldCPP for running LLMS. I have a bot that interfaces with my LLM, so I'd need the end result of the LLM+documents to stil... | 2024-01-09T08:50:26 | https://www.reddit.com/r/LocalLLaMA/comments/192aasu/using_local_data_for_context/ | NotTheTitanic | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 192aasu | false | null | t3_192aasu | /r/LocalLLaMA/comments/192aasu/using_local_data_for_context/ | false | false | self | 2 | null |
Vllm or aphrodite engine ? | 1 | Hello everyone I am back with my daily questions xD.
I will need a task with high throughput and I was wondering which of the two is better in your opinion.
Do you have experience with both what are the drawbacks and advantages for each ? | 2024-01-09T08:10:13 | https://www.reddit.com/r/LocalLLaMA/comments/1929qpy/vllm_or_aphrodite_engine/ | Noxusequal | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 1929qpy | false | null | t3_1929qpy | /r/LocalLLaMA/comments/1929qpy/vllm_or_aphrodite_engine/ | false | false | self | 1 | null |
"We introduce principles for deploying efficient attention-based vision transformers to the Apple Neural Engine (ANE)...." | 7 | 2024-01-09T07:57:48 | https://machinelearning.apple.com/research/vision-transformers | phoneixAdi | machinelearning.apple.com | 1970-01-01T00:00:00 | 0 | {} | 1929kbr | false | null | t3_1929kbr | /r/LocalLLaMA/comments/1929kbr/we_introduce_principles_for_deploying_efficient/ | false | false | 7 | {'enabled': False, 'images': [{'id': 'BiueAFneooNPhLTm3TAeHHSdAWjeGGAcv960GaWAD6M', 'resolutions': [{'height': 56, 'url': 'https://external-preview.redd.it/8uwbVZQYZfEsYTWtunN_H1tdYfBvZzxFG45LWi0tdzY.jpg?width=108&crop=smart&auto=webp&s=d9b4fce6cad565693fca4118e0f0d3bfe74f136f', 'width': 108}, {'height': 113, 'url': 'h... | ||
Local translation-focused models? And how do you personally run them? | 3 | Most LLMs do an ok-ish job of translating text, and usually they're better than Google Translate, which isn't saying much.
Are there local ones specifically for translation? And how do you run them? (I saw something about MADLAD but dunno if/how I can run it on something like Oobabooga or similar)
Ideally what I want... | 2024-01-09T07:51:42 | https://www.reddit.com/r/LocalLLaMA/comments/1929h6p/local_translationfocused_models_and_how_do_you/ | Dead_Internet_Theory | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 1929h6p | false | null | t3_1929h6p | /r/LocalLLaMA/comments/1929h6p/local_translationfocused_models_and_how_do_you/ | false | false | self | 3 | null |
I've wrote a new prompt to see how LLMs order item lists: | 1 | [removed] | 2024-01-09T07:50:49 | https://www.reddit.com/r/LocalLLaMA/comments/1929gq9/ive_wrote_a_new_prompt_to_see_how_llms_order_item/ | Elven77AI | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 1929gq9 | false | null | t3_1929gq9 | /r/LocalLLaMA/comments/1929gq9/ive_wrote_a_new_prompt_to_see_how_llms_order_item/ | false | false | self | 1 | null |
‘Impossible’ to create AI tools like ChatGPT without copyrighted material, OpenAI says | 138 | 2024-01-09T07:39:32 | https://www.theguardian.com/technology/2024/jan/08/ai-tools-chatgpt-copyrighted-material-openai | throwaway_ghast | theguardian.com | 1970-01-01T00:00:00 | 0 | {} | 1929alo | false | null | t3_1929alo | /r/LocalLLaMA/comments/1929alo/impossible_to_create_ai_tools_like_chatgpt/ | false | false | 138 | {'enabled': False, 'images': [{'id': 'cphxk4s1O4aUeI2_Cb5zmE6avRAiTAEbp1v1ifTQXNY', 'resolutions': [{'height': 56, 'url': 'https://external-preview.redd.it/BDnkkYHqqHrFrJ_lFUn1QW4h5Ke3OyhGGr0bCXUr9fM.jpg?width=108&crop=smart&auto=webp&s=0fc72bba015cbc4010810663211436ab12cdb162', 'width': 108}, {'height': 113, 'url': 'h... | ||
Dequantize models? | 1 | Is there an easy way to dequantize models (GPTQ, bitsandbytes, etc.) back to fp16 for experimental purposes? Thanks! | 2024-01-09T07:23:49 | https://www.reddit.com/r/LocalLLaMA/comments/19291u8/dequantize_models/ | keisukegoda3804 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 19291u8 | false | null | t3_19291u8 | /r/LocalLLaMA/comments/19291u8/dequantize_models/ | false | false | self | 1 | null |
How can I serve a model with high CCU with llama.cpp | 2 | Hi everyone, recently I have found llama.cpp could run on low resources. But I don't know if it can be used to serve a large number of CCUs? | 2024-01-09T06:59:21 | https://www.reddit.com/r/LocalLLaMA/comments/1928o50/how_can_i_serve_a_model_with_high_ccu_with/ | unknow_from_vietnam | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 1928o50 | false | null | t3_1928o50 | /r/LocalLLaMA/comments/1928o50/how_can_i_serve_a_model_with_high_ccu_with/ | false | false | self | 2 | null |
Can anyone explain Mamba to a total noob? Difference between Mamba and transformers? Is Mamba actually a viable replacement for transformers? What is the deal with ‘so called’ unlimited context length? Be as simple but as detailed as possible. Thanks. | 1 | 2024-01-09T06:58:21 | TysonUsykFury | i.redd.it | 1970-01-01T00:00:00 | 0 | {} | 1928nlp | false | null | t3_1928nlp | /r/LocalLLaMA/comments/1928nlp/can_anyone_explain_mamba_to_a_total_noob/ | false | false | 1 | {'enabled': True, 'images': [{'id': 'iZMngBqdqEtDjJXfvNGaF-hcwcP8zfJil2vuToq_6jY', 'resolutions': [{'height': 90, 'url': 'https://preview.redd.it/9ljkgfxl4dbc1.jpeg?width=108&crop=smart&auto=webp&s=18decd3e7d33ee62be3fcdf06784a8c37f900922', 'width': 108}, {'height': 181, 'url': 'https://preview.redd.it/9ljkgfxl4dbc1.jp... | |||
What is the best open-source alt to gpt-vision? (esp. for processing desktop screenshots) | 2 | Searching but not finding much. I think the vision models are what will allow general llm-driven computer usage. (agent driven scraping, summarizing, etc. imagine "check all these travel websites every day, aggregate my banking data every week, etc.)
I would also like to use vision models for other tasks, I think the ... | 2024-01-09T06:53:41 | https://www.reddit.com/r/LocalLLaMA/comments/1928kym/what_is_the_best_opensource_alt_to_gptvision_esp/ | Away-Bird-6339 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 1928kym | false | null | t3_1928kym | /r/LocalLLaMA/comments/1928kym/what_is_the_best_opensource_alt_to_gptvision_esp/ | false | false | self | 2 | null |
Fastest cpu inference of mistral 7b q4km | 4 | What's the fastest cpu setup for running mistrsal 7b q 4 k m? (no mac or gpu)?
My laptop gets 6-8 t/s. I tried a powerful vm on the cloud and got 11 tok/s.
Is there a faster way without using gpu or mac? | 2024-01-09T06:42:51 | https://www.reddit.com/r/LocalLLaMA/comments/1928ep7/fastest_cpu_inference_of_mistral_7b_q4km/ | Amgadoz | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 1928ep7 | false | null | t3_1928ep7 | /r/LocalLLaMA/comments/1928ep7/fastest_cpu_inference_of_mistral_7b_q4km/ | false | false | self | 4 | null |
Soaring from 4K to 400K: Extending LLM's Context with Activation Beacon | 69 | 2024-01-09T05:46:41 | https://arxiv.org/abs/2401.03462 | ninjasaid13 | arxiv.org | 1970-01-01T00:00:00 | 0 | {} | 1927ge4 | false | null | t3_1927ge4 | /r/LocalLLaMA/comments/1927ge4/soaring_from_4k_to_400k_extending_llms_context/ | false | false | default | 69 | null | |
Best way to add corporate guardrails to Mixtral | 10 | I am setting up a Q&A bot for a small business that currently uses a Anthropic/Claude's API. The way it is setup, the entire HR manual is in the context, plus a medium length system prompt, no chat or history setup. I am trying to switch over to a virtually hosted version of Mixtral 8x7b Instruct EXL2 3.5bpw. Itis work... | 2024-01-09T05:30:59 | https://www.reddit.com/r/LocalLLaMA/comments/19276ej/best_way_to_add_corporate_guardrails_to_mixtral/ | aallsbury | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 19276ej | false | null | t3_19276ej | /r/LocalLLaMA/comments/19276ej/best_way_to_add_corporate_guardrails_to_mixtral/ | false | false | self | 10 | null |
Best way to add corporate guardrails to Mixtral | 1 | I am setting up a Q&A bot for a small business that currently uses a Anthropic/Claude's API. The way it is setup, the entire HR manual is in the context, plus a medium length system prompt, no chat or history setup. I am trying to switch over to a virtually hosted version of Mixtral 8x7b Instruct EXL2 3.5bpw. Itis work... | 2024-01-09T05:30:58 | https://www.reddit.com/r/LocalLLaMA/comments/19276ed/best_way_to_add_corporate_guardrails_to_mixtral/ | aallsbury | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 19276ed | false | null | t3_19276ed | /r/LocalLLaMA/comments/19276ed/best_way_to_add_corporate_guardrails_to_mixtral/ | false | false | default | 1 | null |
MoE-Mamba: Efficient Selective State Space Models with Mixture of Experts | 153 | 2024-01-09T04:46:49 | https://arxiv.org/abs/2401.04081 | ninjasaid13 | arxiv.org | 1970-01-01T00:00:00 | 0 | {} | 1926db9 | false | null | t3_1926db9 | /r/LocalLLaMA/comments/1926db9/moemamba_efficient_selective_state_space_models/ | false | false | default | 153 | null | |
Dell T630 with 4x Tesla P40 (Description in comments) | 68 | 2024-01-09T03:32:07 | https://www.reddit.com/gallery/1924vtm | BeyondRedline | reddit.com | 1970-01-01T00:00:00 | 0 | {} | 1924vtm | false | null | t3_1924vtm | /r/LocalLLaMA/comments/1924vtm/dell_t630_with_4x_tesla_p40_description_in/ | false | false | 68 | null | ||
Fellow nerds of reddit, I somehow fried my rig using TextGen Webui. | 24 | (Insert applause) | 2024-01-09T03:27:59 | https://www.reddit.com/gallery/1924sox | ThrowawayEmail000 | reddit.com | 1970-01-01T00:00:00 | 0 | {} | 1924sox | false | null | t3_1924sox | /r/LocalLLaMA/comments/1924sox/fellow_nerds_of_reddit_i_somehow_fried_my_rig/ | false | false | 24 | null | |
[Submitted on 8 Jan 2024] Mixtral of Experts: We introduce Mixtral 8x7B, a Sparse Mixture of Experts (SMoE) language model. .. trained with a context size of 32k tokens and it outperforms or matches Llama 2 70B and GPT-3.5 across all evaluated benchmarks - Official Paper | 3 | Official Mixtral 8x7B paper released:
Abstract: We introduce Mixtral 8x7B, a Sparse Mixture of Experts (SMoE) language model. Mixtral has the same architecture as Mistral 7B, with the difference that each layer is composed of 8 feedforward blocks (i.e. experts). For every token, at each layer, a router network select... | 2024-01-09T03:27:36 | https://arxiv.org/abs/2401.04088 | alchemist1e9 | arxiv.org | 1970-01-01T00:00:00 | 0 | {} | 1924sdw | false | null | t3_1924sdw | /r/LocalLLaMA/comments/1924sdw/submitted_on_8_jan_2024_mixtral_of_experts_we/ | false | false | default | 3 | null |
Mixtral 8x7B paper published. | 150 | 2024-01-09T03:24:21 | https://arxiv.org/abs/2401.04088 | rnosov | arxiv.org | 1970-01-01T00:00:00 | 0 | {} | 1924pyy | false | null | t3_1924pyy | /r/LocalLLaMA/comments/1924pyy/mixtral_8x7b_paper_published/ | false | false | default | 150 | null | |
Using small language models as data validator for topic modelling results | 2 | Hello everyone! I am doing topic modelling with BERTopic. Most of the time the final group of topics are not perfect. Some texts are grouped together on topics that they should not be part of. I want to use a small language model like phi-2 to validate whether a specific topic is indeed the topic being talked about in ... | 2024-01-09T02:56:53 | https://www.reddit.com/r/LocalLLaMA/comments/1924555/using_small_language_models_as_data_validator_for/ | deaththekid00 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 1924555 | false | null | t3_1924555 | /r/LocalLLaMA/comments/1924555/using_small_language_models_as_data_validator_for/ | false | false | self | 2 | null |
Text generations speeds highly reduced when automatic1111 is open (even if idle) on SillyTavern. How can I fix this? | 5 | So I'm having a slight issue here with my local AI setup. I finally discovered what the problem is but I'm not sure how to solve it or if there is even any solution to this.
Specs:
CPU Intel i7-11800H
GPU Nvidia RTX 3060 Laptop
RAM 32GB
---------------------------
Model
IconicAI_pygmalion-2-7... | 2024-01-09T02:26:18 | https://www.reddit.com/r/LocalLLaMA/comments/1923i3b/text_generations_speeds_highly_reduced_when/ | OvercookedSatellite | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 1923i3b | false | null | t3_1923i3b | /r/LocalLLaMA/comments/1923i3b/text_generations_speeds_highly_reduced_when/ | false | false | self | 5 | null |
Just sharing some quick tips to painlessly install PrivateGPT on your windows machine with Ubuntu as WSL (Windows Subsystem for Linux) | 8 | \- Since I primarily run WSL Ubuntu on Windows, I had some difficulties setting it up at first. Encountered several issues. Learn from my mistakes, make sure your WSL is version 2 else your system is not going to detect CUDA. The dreaded "no CUDA-capable device is detected" will be a constant issue if you are not runni... | 2024-01-09T02:22:18 | https://www.reddit.com/r/LocalLLaMA/comments/1923f4k/just_sharing_some_quick_tips_to_painlessly/ | 108er | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 1923f4k | false | null | t3_1923f4k | /r/LocalLLaMA/comments/1923f4k/just_sharing_some_quick_tips_to_painlessly/ | false | false | self | 8 | null |
AI interface | 1 | is there any program for Ubuntu so that you can conveniently and quickly change models and interact with them via telegram? and if possible, so that you can periodically send her pdf/epub and other books for training?
Hardware; old xeon 8/16 with 16 ram, rx588 (planning to upgrade in future) | 2024-01-09T01:51:24 | https://www.reddit.com/r/LocalLLaMA/comments/1922qya/ai_interface/ | Jan_Chan_Li | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 1922qya | false | null | t3_1922qya | /r/LocalLLaMA/comments/1922qya/ai_interface/ | false | false | self | 1 | null |
A KoboldCPP Frankenstein to play with the new 2 bits quants of Llama.cpp | 12 | Until LostRuins provides the real thing, here's mine :
[https://github.com/Nexesenex/kobold.cpp/releases/tag/KCPPF\_1.55a](https://github.com/Nexesenex/kobold.cpp/releases/tag/KCPPF_1.55a)
Enjoy, and happy new year 2024! | 2024-01-09T01:45:50 | https://www.reddit.com/r/LocalLLaMA/comments/1922mjz/a_koboldcpp_frankenstein_to_play_with_the_new_2/ | Nexesenex | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 1922mjz | false | null | t3_1922mjz | /r/LocalLLaMA/comments/1922mjz/a_koboldcpp_frankenstein_to_play_with_the_new_2/ | false | false | self | 12 | {'enabled': False, 'images': [{'id': 'C98r4u1ZrZNVcqcFcTUG3K2CnAQ7lrpc5X4m6qyaC38', 'resolutions': [{'height': 54, 'url': 'https://external-preview.redd.it/GyEYoDQcrtJ70711oh6yByJnwSkwepgdge6SIH7lRj4.jpg?width=108&crop=smart&auto=webp&s=849911792f6928f18f52c0c57c4738908e0853f4', 'width': 108}, {'height': 108, 'url': 'h... |
VectorDB with Llama Embeddings - Few Questions and Doubts | 4 | Hellow,
I'm working on another open source package implementing long term memory via vector db.
I want to use llama's native embeddings, as it's kind of a llamacentric set of packages I'm working on.
I've implemented vector db in a few pocs before but I worked with tokenized strings as it was sufficient for those ... | 2024-01-09T01:35:39 | https://www.reddit.com/r/LocalLLaMA/comments/1922ety/vectordb_with_llama_embeddings_few_questions_and/ | --lael-- | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 1922ety | false | null | t3_1922ety | /r/LocalLLaMA/comments/1922ety/vectordb_with_llama_embeddings_few_questions_and/ | false | false | self | 4 | null |
A model like GPT4 vision to mark specific thing on a screenshot? | 1 | Basically I'm looking for something that I will provide with data (ie. a cat) that it will put into a box. I can also provide estimate position of the cat in the image.
GPT4 vision can give me an estimate position but not an exact one and obviously can't mark it for me. | 2024-01-09T01:17:20 | https://www.reddit.com/r/LocalLLaMA/comments/19220r6/a_model_like_gpt4_vision_to_mark_specific_thing/ | Rabus | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 19220r6 | false | null | t3_19220r6 | /r/LocalLLaMA/comments/19220r6/a_model_like_gpt4_vision_to_mark_specific_thing/ | false | false | self | 1 | null |
Did someone ever benchmark how cpu inference performs with quad and eight channel memory ? | 11 | Since people always say that bandwidth is the problem. And a full 8 channel memory board with ddr4 3200 would be about 200gb/s per second i was wondering if anyone ever benchmarks that stuff and how it scales with cores ?
In theory you could build relatively cheap used epyc or xeon systems hitting 128gn ram and more ... | 2024-01-09T00:12:08 | https://www.reddit.com/r/LocalLLaMA/comments/1920l93/did_someone_ever_benchmark_how_cpu_inference/ | Noxusequal | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 1920l93 | false | null | t3_1920l93 | /r/LocalLLaMA/comments/1920l93/did_someone_ever_benchmark_how_cpu_inference/ | false | false | self | 11 | null |
WikiChat: Stopping the Hallucination of Large Language Model Chatbots by Few-Shot Grounding on Wikipedia - Achieves 97.9% factual accuracy in conversations with human users about recent topics, 55.0% better than GPT-4! - Stanford University 2023 | 330 | Paper: [https://arxiv.org/abs/2305.14292v2](https://arxiv.org/abs/2305.14292v2)
Github: [https://github.com/stanford-oval/WikiChat](https://github.com/stanford-oval/WikiChat)
Abstract:
>This paper presents the first few-shot LLM-based chatbot that almost never hallucinates and has high conversationality and low la... | 2024-01-09T00:07:33 | https://www.reddit.com/r/LocalLLaMA/comments/1920hho/wikichat_stopping_the_hallucination_of_large/ | Singularian2501 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 1920hho | false | null | t3_1920hho | /r/LocalLLaMA/comments/1920hho/wikichat_stopping_the_hallucination_of_large/ | false | false | 330 | null | |
RAG, or vector db, or ... interop between models of different sizes? (preprocessing) | 3 | I am new to local LLMs. Is it possible to build up some kind of retrieval index/solution using a larger model on your corpus of data, such that a smaller model could later use it and benefit from it, thus bridging the gap between model sizes?
E.g., feed your docs to a 180b model and then use the whatever "memory/index... | 2024-01-08T23:54:56 | https://www.reddit.com/r/LocalLLaMA/comments/19206it/rag_or_vector_db_or_interop_between_models_of/ | Infinite100p | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 19206it | false | null | t3_19206it | /r/LocalLLaMA/comments/19206it/rag_or_vector_db_or_interop_between_models_of/ | false | false | self | 3 | null |
What's the best quant of Falcon 180b for M3Max 128GB MacBook Pro? (Also tips on extreme system overhead reduction?) | 5 | What's the best quant of Falcon 180b for M3Max 128GB Mac currently?
Looking here:
[TheBloke/Falcon-180B-GGUF · Hugging Face](https://huggingface.co/TheBloke/Falcon-180B-GGUF)
And I see that the recommended *falcon-180b.Q4\_K\_M.gguf* (**Q4\_K\_M4** quant) requires 108.48GB RAM.
1. Is it possible to run it on M3Max... | 2024-01-08T23:47:47 | https://www.reddit.com/r/LocalLLaMA/comments/19200lh/whats_the_best_quant_of_falcon_180b_for_m3max/ | Infinite100p | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 19200lh | false | null | t3_19200lh | /r/LocalLLaMA/comments/19200lh/whats_the_best_quant_of_falcon_180b_for_m3max/ | false | false | self | 5 | {'enabled': False, 'images': [{'id': 'Ee3jBOiSMurLfch4RejFIwn18E1_--AG6Tc8yzU-kis', 'resolutions': [{'height': 58, 'url': 'https://external-preview.redd.it/J7bDDxHDMXJI4-nsHzB62Il8qk1vLGyD9rp60TmMFiQ.jpg?width=108&crop=smart&auto=webp&s=583fb38c579d9eeaac83bc5df38d04fac6ae7d8e', 'width': 108}, {'height': 116, 'url': 'h... |
Inference Mixtral 8x7B in pure Rust | 15 | 2024-01-08T23:24:46 | https://github.com/moritztng/mixtral | compressor0101 | github.com | 1970-01-01T00:00:00 | 0 | {} | 191zgu1 | false | null | t3_191zgu1 | /r/LocalLLaMA/comments/191zgu1/inference_mixtral_8x7b_in_pure_rust/ | false | false | 15 | {'enabled': False, 'images': [{'id': 'POtKKWqeS3G5iBjV5bxPNOX-sifEcKVdkFY0XbB-nps', 'resolutions': [{'height': 54, 'url': 'https://external-preview.redd.it/BjELbCtk3T9eNQYh79UYJXVGq9665R5fUC3RSpBzkOs.jpg?width=108&crop=smart&auto=webp&s=463baf36045c75aa989af4f91775b6e20f7ac86b', 'width': 108}, {'height': 108, 'url': 'h... | ||
People of LocalLlama, I need your roleplay and worldbuilding data | 6 | As of Last post (https://reddit.com/r/LocalLLaMA/comments/191bufg/currently_working_on_building_a_worldbuildrp/), I had a worldbuild resource, with 18000 Q's. Since then, I've added Bluemoon and Pippa roleplays, along with roleplayIO for more world building, which puts the data at around 20K~ examples for both worldbui... | 2024-01-08T23:20:02 | https://www.reddit.com/r/LocalLLaMA/comments/191zcs8/people_of_localllama_i_need_your_roleplay_and/ | vatsadev | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 191zcs8 | false | null | t3_191zcs8 | /r/LocalLLaMA/comments/191zcs8/people_of_localllama_i_need_your_roleplay_and/ | false | false | self | 6 | null |
P40 vs P100 for LLMs | 10 | I'm planning to build a server focused on machine learning, inferencing, and LLM chatbot experiments. The Tesla P40 and P100 are both within my prince range. The P40 offers slightly more VRAM (24gb vs 16gb), but is GDDR5 vs HBM2 in the P100, meaning it has far lower bandwidth, which I believe is important for inferenci... | 2024-01-08T22:39:28 | https://www.reddit.com/r/LocalLLaMA/comments/191yd31/p40_vs_p100_for_llms/ | PaperboyNZ | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 191yd31 | false | null | t3_191yd31 | /r/LocalLLaMA/comments/191yd31/p40_vs_p100_for_llms/ | false | false | self | 10 | null |
Getting 2-3 Tokens/s on Google Colab T4 with Quantized Mistral7B. Is this normal, or is there something I can do to speed it up? | 7 | Hi, in terms of the output I get vs. the runtime, I feel like it is taking very long, I know Colab Free tier is not the most computationally optimal way of running LLMs, but I was wondering if I am doing something wrong and can speed it up, could really use peoples experience here.
​
Here is what I am doing to... | 2024-01-08T22:34:22 | https://www.reddit.com/r/LocalLLaMA/comments/191y8np/getting_23_tokenss_on_google_colab_t4_with/ | baban_jaeger | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 191y8np | false | null | t3_191y8np | /r/LocalLLaMA/comments/191y8np/getting_23_tokenss_on_google_colab_t4_with/ | false | false | self | 7 | null |
Langchain seems to have directly addressed our biggest complaints. Does anyone have any experience with .1. 0? | 1 | [removed] | 2024-01-08T22:29:03 | https://www.reddit.com/r/LocalLLaMA/comments/191y3wh/langchain_seems_to_have_directly_addressed_our/ | Future_Might_8194 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 191y3wh | false | null | t3_191y3wh | /r/LocalLLaMA/comments/191y3wh/langchain_seems_to_have_directly_addressed_our/ | false | false | self | 1 | {'enabled': False, 'images': [{'id': 'uefcSKukMeOQWCJlRXSsrk7y43qzA9GCudd2I5ayVTQ', 'resolutions': [{'height': 80, 'url': 'https://external-preview.redd.it/tJ_Y_ThtoNgkhdLSY2LTRnkqAPkmQkGlWROgzJKP4oE.jpg?width=108&crop=smart&auto=webp&s=e5d9e7f96496d4be2ae78e2e36925ba7e07ae1ed', 'width': 108}, {'height': 161, 'url': 'h... |
AI tools for 2024 | 2 | [removed] | 2024-01-08T22:11:44 | https://www.reddit.com/r/LocalLLaMA/comments/191xp05/ai_tools_for_2024/ | Horror_Echo6243 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 191xp05 | false | null | t3_191xp05 | /r/LocalLLaMA/comments/191xp05/ai_tools_for_2024/ | false | false | self | 2 | {'enabled': False, 'images': [{'id': 'W-pCh47ZuoTaTpwtRXWs755SzkkFQzHW6A1NS1MJI_A', 'resolutions': [{'height': 108, 'url': 'https://external-preview.redd.it/IoUbWrubYyEjhlVchwRPNergZFyoEfUZRDayK06XMTM.jpg?width=108&crop=smart&auto=webp&s=aa7b8a73d9f4825dcec8d2a7d8805a9c50369d0b', 'width': 108}, {'height': 216, 'url': '... |
Ollama ROCM Linux (Fedora)? | 1 | Anyone successfully running Ollama with ROCM (AMD RX 6800 XT)?
I’ve successfully been running the gpu with oobabbogas TG-WebUI with ROCM etc. but no luck at with Ollama, tried some solutions from issues from the repo but no success. | 2024-01-08T22:03:17 | https://www.reddit.com/r/LocalLLaMA/comments/191xhga/ollama_rocm_linux_fedora/ | Sisuuu | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 191xhga | false | null | t3_191xhga | /r/LocalLLaMA/comments/191xhga/ollama_rocm_linux_fedora/ | false | false | self | 1 | null |
QuIP-for-all is an easy to use quip quantization tool; 16t/s 2 bit MixtralInstruct on single 3090 | 6 | Discovered the model on hf and by that the libraries.
I could not load the model below in textgen-webui, perhaps the lib needs the quip-for-all to be added as it supports a wider range of models than quip# library.
There is also a vllm-gptq branch that supports quip models, giving the speed from the headline.
Wou... | 2024-01-08T21:57:27 | https://www.reddit.com/r/LocalLLaMA/comments/191xbnz/quipforall_is_an_easy_to_use_quip_quantization/ | MLTyrunt | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 191xbnz | false | null | t3_191xbnz | /r/LocalLLaMA/comments/191xbnz/quipforall_is_an_easy_to_use_quip_quantization/ | false | false | self | 6 | {'enabled': False, 'images': [{'id': 'Rxm_6AV_r8XbjZuXoWN3o62LsAvu-iW3E2_qSCK5ES0', 'resolutions': [{'height': 58, 'url': 'https://external-preview.redd.it/O1zcWZ5jQWkyHZXmmHPlS2V19gMcM5MlEF6PfMB9QoU.jpg?width=108&crop=smart&auto=webp&s=6dfcd377124f29b333e55dfa4be854376a402fd3', 'width': 108}, {'height': 116, 'url': 'h... |
Can I Run Models locally on My Setup | 5 | I'm relatively new to the world of large language model (LLM) development and just got my hands on a machine that I'm hoping will be capable of running some models locally. I'm reaching out to the community for insights and to see if anyone has had similar experiences.
Here are my machine specs:
* **CPU:** AMD Ryzen... | 2024-01-08T21:55:04 | https://www.reddit.com/r/LocalLLaMA/comments/191x9kg/can_i_run_models_locally_on_my_setup/ | klei10 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 191x9kg | false | null | t3_191x9kg | /r/LocalLLaMA/comments/191x9kg/can_i_run_models_locally_on_my_setup/ | false | false | self | 5 | null |
HI all. I am relatively new to llm development. | 1 | I got a machine with this specs:
* **CPU:** AMD Ryzen 5 5500 3.6GHz
* **GPU:** RTX 4060 8GB
* **RAM:** 16GB
* **Storage:** 500GB SSD
Will i be abble to run anything locally ?
Did you had any similar experience ?
Thanks | 2024-01-08T21:52:37 | https://www.reddit.com/r/LocalLLaMA/comments/191x7dp/hi_all_i_am_relatively_new_to_llm_development/ | klei10 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 191x7dp | false | null | t3_191x7dp | /r/LocalLLaMA/comments/191x7dp/hi_all_i_am_relatively_new_to_llm_development/ | false | false | self | 1 | null |
llama.cpp supports Self-Extend!!! | 74 | 2024-01-08T21:50:20 | https://github.com/ggerganov/llama.cpp/pull/4815 | pseudonerv | github.com | 1970-01-01T00:00:00 | 0 | {} | 191x5d3 | false | null | t3_191x5d3 | /r/LocalLLaMA/comments/191x5d3/llamacpp_supports_selfextend/ | false | false | 74 | {'enabled': False, 'images': [{'id': 'zzRkmehn857nF_67iofEdBLH8-I9bSv5Z5jc9dxdBlo', 'resolutions': [{'height': 54, 'url': 'https://external-preview.redd.it/Qz0OwTlLaDyvArYCf413X4DpjPs1nhKEeMZlZ6Js5kg.jpg?width=108&crop=smart&auto=webp&s=1d1b471197ea5a5141d1a9da5b126a8da96cf61a', 'width': 108}, {'height': 108, 'url': 'h... | ||
Matrix Neo's 🥷 Got Nothing on S-LoRA: Swapping Skills Like a Matrix Pro | 51 | This is about S-LoRA. You are going to hear a lot about S-LoRA in 2024. I have been playing with it. And it saved me from buying multiple GPUs. I wrote an article about it and sharing it here. I am an amateur and wrote this for other amateurs and practictioniers. Technical inaccuracies abound but I hope it's still usef... | 2024-01-08T21:36:23 | https://www.reddit.com/r/LocalLLaMA/comments/191wssq/matrix_neos_got_nothing_on_slora_swapping_skills/ | phoneixAdi | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 191wssq | false | null | t3_191wssq | /r/LocalLLaMA/comments/191wssq/matrix_neos_got_nothing_on_slora_swapping_skills/ | false | false | self | 51 | null |
Apple releases ferret | 51 | 2024-01-08T21:28:44 | randomrealname | i.redd.it | 1970-01-01T00:00:00 | 0 | {} | 191wljv | false | null | t3_191wljv | /r/LocalLLaMA/comments/191wljv/apple_releases_ferret/ | false | false | 51 | {'enabled': True, 'images': [{'id': '-CxTfWeNX_XF5ZCWbFpmBK6QKR1MMbK2N4wbp4SGY5U', 'resolutions': [{'height': 105, 'url': 'https://preview.redd.it/3uojl1zwaabc1.png?width=108&crop=smart&auto=webp&s=4dbdad0c243398fd98bbd5b9a6b91ee353123700', 'width': 108}, {'height': 210, 'url': 'https://preview.redd.it/3uojl1zwaabc1.pn... | |||
It would be nice if model fine tuners explicitly explained what their models are good at | 113 | It's so frustrating to check out models and have no idea whether they are supposed to be a jack of all trades, a coding model, a RP model, or for story generation. Just had to uninstall one because it was clearly meant for chatting as it tended to add emojis and write single paragraphs, which makes it useless to me. I ... | 2024-01-08T21:25:21 | https://www.reddit.com/r/LocalLLaMA/comments/191wiia/it_would_be_nice_if_model_fine_tuners_explicitly/ | Anxious-Ad693 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 191wiia | false | null | t3_191wiia | /r/LocalLLaMA/comments/191wiia/it_would_be_nice_if_model_fine_tuners_explicitly/ | false | false | self | 113 | null |
I am reaching out to the community for help with my DRµG problem. | 1 | [removed] | 2024-01-08T21:24:43 | https://www.reddit.com/r/LocalLLaMA/comments/191whxu/i_am_reaching_out_to_the_community_for_help_with/ | qrios | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 191whxu | false | null | t3_191whxu | /r/LocalLLaMA/comments/191whxu/i_am_reaching_out_to_the_community_for_help_with/ | false | false | self | 1 | null |
Hosting peft models for inference | 3 | I’m looking to host a base model and serve inference by swapping out peft adapters on top of the base model based on the peft model requested by the incoming API call. vLLM does not seem to support hot swapping adapters. What’s the best way to go about this? | 2024-01-08T20:23:52 | https://www.reddit.com/r/LocalLLaMA/comments/191uz2c/hosting_peft_models_for_inference/ | listmaker4589 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 191uz2c | false | null | t3_191uz2c | /r/LocalLLaMA/comments/191uz2c/hosting_peft_models_for_inference/ | false | false | self | 3 | null |
Group chat with Ai why not!?? | 1 | By end of this week you guys are gonna watch something very interesting !
I'm actually building a community on Discrd for every AI enthusiast to come and test all the open-source large language models hosted in one place.
I believe the beauty of AI can be revealed more quickly and in more surprising ways when explored... | 2024-01-08T20:12:40 | GlitteringAdvisor530 | i.redd.it | 1970-01-01T00:00:00 | 0 | {} | 191uowm | false | null | t3_191uowm | /r/LocalLLaMA/comments/191uowm/group_chat_with_ai_why_not/ | false | false | 1 | {'enabled': True, 'images': [{'id': 'pexJGld2eEnN_i_1jiVLUU9q0leHAFg6Zgi56_BthyU', 'resolutions': [{'height': 216, 'url': 'https://preview.redd.it/s0slpivex9bc1.png?width=108&crop=smart&auto=webp&s=71a3acb3ff4bb06de616ea696dfa63d308d1c44b', 'width': 108}, {'height': 432, 'url': 'https://preview.redd.it/s0slpivex9bc1.pn... | ||
Group chats with ai why not !?? | 1 | By end of this week you guys are gonna watch something very interesting !
I'm actually building a community on Discrd for every AI enthusiast to come and test all the open-source large language models hosted in one place.
I believe the beauty of AI can be revealed more quickly and in more surprising ways when explored... | 2024-01-08T20:10:46 | GlitteringAdvisor530 | i.redd.it | 1970-01-01T00:00:00 | 0 | {} | 191un6e | false | null | t3_191un6e | /r/LocalLLaMA/comments/191un6e/group_chats_with_ai_why_not/ | false | false | 1 | {'enabled': True, 'images': [{'id': 'tnNPntX2RBgeExbXHggfr3HqMG_KOS1ERU8oVdin_FE', 'resolutions': [{'height': 216, 'url': 'https://preview.redd.it/ucyxqmm2x9bc1.png?width=108&crop=smart&auto=webp&s=db3189a24be9de120a1327660ca7d844e4dde253', 'width': 108}, {'height': 432, 'url': 'https://preview.redd.it/ucyxqmm2x9bc1.pn... | ||
NVIDIA launches GeForce RTX 40 SUPER series: $999 RTX 4080S, $799 RTX 4070 TiS and $599 RTX 4070S - VideoCardz.com | 133 | 2024-01-08T19:53:28 | https://videocardz.com/newz/nvidia-launches-geforce-rtx-40-super-series-999-rtx-4080s-799-rtx-4070-tis-and-599-rtx-4070s | AC1colossus | videocardz.com | 1970-01-01T00:00:00 | 0 | {} | 191u6wf | false | null | t3_191u6wf | /r/LocalLLaMA/comments/191u6wf/nvidia_launches_geforce_rtx_40_super_series_999/ | false | false | 133 | {'enabled': False, 'images': [{'id': 'TpXK-25QrSt2oY8eDzzqpk9xb0Y0eWscIlYwNHLYCwE', 'resolutions': [{'height': 56, 'url': 'https://external-preview.redd.it/7O21UHuwVeU6GRLIjvJ58tCSgnd6a-ay3LvIUbGUKQY.jpg?width=108&crop=smart&auto=webp&s=8976b7545fcacd843a6e80003400e4fa6e926019', 'width': 108}, {'height': 112, 'url': 'h... | ||
NVIDIA Announces RTX 40 Super Cards | 9 | 2024-01-08T19:48:01 | https://www.nvidia.com/en-us/geforce/news/geforce-rtx-4080-4070-ti-4070-super-gpu/ | semicausal | nvidia.com | 1970-01-01T00:00:00 | 0 | {} | 191u1zw | false | null | t3_191u1zw | /r/LocalLLaMA/comments/191u1zw/nvidia_announces_rtx_40_super_cards/ | false | false | 9 | {'enabled': False, 'images': [{'id': '44AC6dGQu3bkIbwBryPYQFO-Llpm3mE_-4h3Ds9Ocl4', 'resolutions': [{'height': 56, 'url': 'https://external-preview.redd.it/hgk5oK69eqgCzDWBchMCDelvSUws8tTlrzQmpbp92zA.jpg?width=108&crop=smart&auto=webp&s=dc9ffc0699601ccd0f9fa88cb78695e04ea7e642', 'width': 108}, {'height': 113, 'url': 'h... | ||
Visualising LLM training compute & correlating to benchmarks | 32 | 2024-01-08T19:47:30 | https://epochai.org/blog/who-is-leading-in-ai-an-analysis-of-industry-ai-research | Time-Winter-4319 | reddit.com | 1970-01-01T00:00:00 | 0 | {} | 191u1j9 | false | null | t3_191u1j9 | /r/LocalLLaMA/comments/191u1j9/visualising_llm_training_compute_correlating_to/ | false | false | 32 | null | ||
Mistral base model Finetuning | 2 | Is there a script or a notebook to finetune the base Mistral model to capture new text that the model has not previously seen? I have found a number of instruct finetunes but not much for just the base model. | 2024-01-08T19:44:23 | https://www.reddit.com/r/LocalLLaMA/comments/191tyng/mistral_base_model_finetuning/ | Danny_Davitoe | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 191tyng | false | null | t3_191tyng | /r/LocalLLaMA/comments/191tyng/mistral_base_model_finetuning/ | false | false | self | 2 | null |
No-code, uncertainty-aware LLM classification and fine-tuned semantic search for Mac | 6 | If your end goal for large language model (LLM) fine-tuning is **document classification and/or semantic search**, one easy approach is to use the no-code **Reexpress** app if you have an Apple silicon Mac: [https://re.express/](https://re.express/)
​
It's currently available on the US Mac App Store (and we'll... | 2024-01-08T19:22:57 | https://www.reddit.com/r/LocalLLaMA/comments/191tfpn/nocode_uncertaintyaware_llm_classification_and/ | Reexpressionist | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 191tfpn | false | null | t3_191tfpn | /r/LocalLLaMA/comments/191tfpn/nocode_uncertaintyaware_llm_classification_and/ | false | false | 6 | null | |
Any tool to use models as story writers instead of chatbots? | 1 | [removed] | 2024-01-08T19:10:34 | https://www.reddit.com/r/LocalLLaMA/comments/191t4mo/any_tool_to_use_models_as_story_writers_instead/ | AltruisticMission865 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 191t4mo | false | null | t3_191t4mo | /r/LocalLLaMA/comments/191t4mo/any_tool_to_use_models_as_story_writers_instead/ | false | false | self | 1 | null |
AMD Radeon 7900 XT/XTX Inference Performance Comparisons | 76 | I recently picked up a 7900 XTX card and was updating my [AMD GPU guide](https://llm-tracker.info/howto/AMD-GPUs) (now w/ ROCm info). I also ran some benchmarks, and considering how Instinct cards aren't generally available, I figured that having Radeon 7900 numbers might be of interest for people. I compared the 7900 ... | 2024-01-08T18:57:02 | https://www.reddit.com/r/LocalLLaMA/comments/191srof/amd_radeon_7900_xtxtx_inference_performance/ | randomfoo2 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 191srof | false | null | t3_191srof | /r/LocalLLaMA/comments/191srof/amd_radeon_7900_xtxtx_inference_performance/ | false | false | self | 76 | {'enabled': False, 'images': [{'id': 'LVI9k0fh_RZkRc--0M6US_gjgAtTjLGNcNKdvCGt54E', 'resolutions': [{'height': 60, 'url': 'https://external-preview.redd.it/bx2O8BPfwyCFkmWEtPfeTy5Pq8oebtWvGqMnMUeBbGM.jpg?width=108&crop=smart&auto=webp&s=80f8b9cd30ec6f6a608377590cd8dfb9ed23ffd1', 'width': 108}, {'height': 121, 'url': 'h... |
Fine Tuning LLMs with OpenPipe to Process Massive Amounts of Data 50x Cheaper than GPT-4 | 1 | 2024-01-08T18:47:07 | https://dev.to/experilearning/fine-tuning-llms-to-process-massive-amounts-of-data-50x-cheaper-than-gpt-4-4a1d | jamesm8 | dev.to | 1970-01-01T00:00:00 | 0 | {} | 191sj8w | false | null | t3_191sj8w | /r/LocalLLaMA/comments/191sj8w/fine_tuning_llms_with_openpipe_to_process_massive/ | false | false | 1 | {'enabled': False, 'images': [{'id': 'euKWUO6ZW6v5wOfGU6_tFME9xr8aE1TmxEZzfbDdwJ4', 'resolutions': [{'height': 54, 'url': 'https://external-preview.redd.it/j4v_tRNwQzPPxCg1BC45lkQ_2C8apBDjnu38qUoYCsU.jpg?width=108&crop=smart&auto=webp&s=c19d3ada3264973078331bf4d700cdfd9fdfc1b3', 'width': 108}, {'height': 108, 'url': 'h... | ||
Using Local LLM in Games - The Sims 4 Mod | 1 | [removed] | 2024-01-08T18:38:01 | https://www.reddit.com/r/LocalLLaMA/comments/191sb48/using_local_llm_in_games_the_sims_4_mod/ | GusPuffy | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 191sb48 | false | null | t3_191sb48 | /r/LocalLLaMA/comments/191sb48/using_local_llm_in_games_the_sims_4_mod/ | false | false | self | 1 | null |
A simple guide to local LLM fine-tuning on a Mac with MLX | 41 | Hey folks, I was inspired by all the talk of fine-tuning on this subreddit. Especially the two recent posts about fine-tuning on the Mac with the new MLX library:
* [https://www.reddit.com/r/LocalLLaMA/comments/18ujt0n/using\_gpus\_on\_a\_mac\_m2\_max\_via\_mlx\_update\_on/](https://www.reddit.com/r/LocalLLaMA/comment... | 2024-01-08T18:34:19 | https://www.reddit.com/r/LocalLLaMA/comments/191s7x3/a_simple_guide_to_local_llm_finetuning_on_a_mac/ | Candid_Secretary_402 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 191s7x3 | false | null | t3_191s7x3 | /r/LocalLLaMA/comments/191s7x3/a_simple_guide_to_local_llm_finetuning_on_a_mac/ | false | false | self | 41 | null |
Sweet-spot for 7-10B size Open Source LLM models optimized for RAG or Function-calling + JSON-mode -> but where are they? | 1 | [removed] | 2024-01-08T18:33:02 | https://www.reddit.com/r/LocalLLaMA/comments/191s6rj/sweetspot_for_710b_size_open_source_llm_models/ | J_Loquat | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 191s6rj | false | null | t3_191s6rj | /r/LocalLLaMA/comments/191s6rj/sweetspot_for_710b_size_open_source_llm_models/ | false | false | self | 1 | {'enabled': False, 'images': [{'id': 'i-S3FfV7TOCjYdLXnbaFPvWSUvNpYlgEMm0eMqJGKbo', 'resolutions': [{'height': 108, 'url': 'https://external-preview.redd.it/AaY_JmsP7Yt7YBwjIqzuvp_kmpsuwjw2wKCXsK-LO4M.jpg?width=108&crop=smart&auto=webp&s=ea89a8abfdcc7ad2910a4f6b777b7582e60575f7', 'width': 108}, {'height': 216, 'url': '... |
Adding an External RTX 4090 for LLaMA 70B Model | 4 | Okay so I just wanted to ask if adding an external RTX 4090 is a good idea. Here is my current system:
* **CPU:** 13th Gen Intel® Core™ i9 13900KF
* **GPU:** NVIDIA® GeForce RTX™ 4090, 24 GB GDDR6X
* **RAM:** 32GB
* **Storage:** 1TB SSD
I have read a lot about how it is possible to split large language models across ... | 2024-01-08T18:27:30 | https://www.reddit.com/r/LocalLLaMA/comments/191s1u7/adding_an_external_rtx_4090_for_llama_70b_model/ | polymerscience5863 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 191s1u7 | false | null | t3_191s1u7 | /r/LocalLLaMA/comments/191s1u7/adding_an_external_rtx_4090_for_llama_70b_model/ | false | false | self | 4 | null |
New Model & Request: LLaVAR GGUF | 1 | [removed] | 2024-01-08T18:11:35 | https://www.reddit.com/r/LocalLLaMA/comments/191rnqv/new_model_request_llavar_gguf/ | love4titties | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 191rnqv | false | null | t3_191rnqv | /r/LocalLLaMA/comments/191rnqv/new_model_request_llavar_gguf/ | false | false | self | 1 | null |
AMD Unveils AMD Radeon RX 7600 XT Graphics Card – Incredible Gaming at 1080p and Beyond for Under $350 | 45 | Now that we have a 7699 XT with 16gb vram what are our thoughts? | 2024-01-08T17:51:23 | https://ir.amd.com/news-events/press-releases/detail/1176/amd-unveils-amd-radeon-rx-7600-xt-graphics-card | ibbobud | ir.amd.com | 1970-01-01T00:00:00 | 0 | {} | 191r5c5 | false | null | t3_191r5c5 | /r/LocalLLaMA/comments/191r5c5/amd_unveils_amd_radeon_rx_7600_xt_graphics_card/ | false | false | 45 | {'enabled': False, 'images': [{'id': 'cEaIjfDvrCKkfoyUhzsMKx5fb0ZQmVVrM9Kc5AHjS3w', 'resolutions': [{'height': 56, 'url': 'https://external-preview.redd.it/1dj8QMhjHibr-yrreUiw4YqAWAch6SF5DS5Cf5Mrmco.jpg?width=108&crop=smart&auto=webp&s=fda00caba0ecbfed4e35ccd8c5bf34346e43e0c6', 'width': 108}, {'height': 112, 'url': 'h... | |
Inference hacks | 3 | What are the things that one can tune/ needs to be cautious about to increase the inference speed | 2024-01-08T17:37:19 | https://www.reddit.com/r/LocalLLaMA/comments/191qsed/inference_hacks/ | wafax69 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 191qsed | false | null | t3_191qsed | /r/LocalLLaMA/comments/191qsed/inference_hacks/ | false | false | self | 3 | null |
Looking for someone to help me with document chunking for RAG | 2 | Willing to pay | 2024-01-08T17:33:42 | https://www.reddit.com/r/LocalLLaMA/comments/191qp5m/looking_for_someone_to_help_me_with_document/ | yareyaredaze10 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 191qp5m | false | null | t3_191qp5m | /r/LocalLLaMA/comments/191qp5m/looking_for_someone_to_help_me_with_document/ | false | false | self | 2 | null |
Inference throughput improvement | 3 | So I have a custom trained Vicuna 7B based model and for inference, I tried vLLM and TGI want to increase throughput more. I want it to server multiple requests simultaneously as server.
I see my GPU memory and Utilisation hitting walls. With TGI since there is no batch endpoint, I'm spawning multiple threads and hit... | 2024-01-08T17:33:20 | https://www.reddit.com/r/LocalLLaMA/comments/191qoug/inference_throughput_improvement/ | wafax69 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 191qoug | false | null | t3_191qoug | /r/LocalLLaMA/comments/191qoug/inference_throughput_improvement/ | false | false | self | 3 | null |
I have 2 GPUs and I want to run two models at the same time under two different APIs. | 3 | How can I do this? Thank you. | 2024-01-08T17:09:09 | https://www.reddit.com/r/LocalLLaMA/comments/191q307/i_have_2_gpus_and_i_want_to_run_two_models_at_the/ | Brilliant_Read314 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 191q307 | false | null | t3_191q307 | /r/LocalLLaMA/comments/191q307/i_have_2_gpus_and_i_want_to_run_two_models_at_the/ | false | false | self | 3 | null |
Hobbyist question re:multimodal models | 2 | I am running with some limited system resources on a spare machine. Color me “serious hobbyist.”
Built my own Python Tkinter-based gui front end and can run against Ollama backend or llamacpp/koboldcpp (obviously all llamacpp based).
I am able to run up to 7B mistral derived models in 4K_M quants.
Question: can a ... | 2024-01-08T16:48:16 | https://www.reddit.com/r/LocalLLaMA/comments/191pkyp/hobbyist_question_remultimodal_models/ | Helpful-Gene9733 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 191pkyp | false | null | t3_191pkyp | /r/LocalLLaMA/comments/191pkyp/hobbyist_question_remultimodal_models/ | false | false | self | 2 | null |
Interested in learning AI/ML together, Please DM me your linkedIn. | 1 | [removed] | 2024-01-08T16:28:59 | https://www.reddit.com/r/LocalLLaMA/comments/191p4kf/interested_in_learning_aiml_together_please_dm_me/ | shikcoder | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 191p4kf | false | null | t3_191p4kf | /r/LocalLLaMA/comments/191p4kf/interested_in_learning_aiml_together_please_dm_me/ | false | false | default | 1 | null |
piper tts on oobabooga no reply | 2 | the tts is not responding can someone pls help im new to this:
​
[settings](https://preview.redd.it/nsev3kzls8bc1.png?width=1085&format=png&auto=webp&s=540345ac8de75a48f6d5edf03d2a1689954a9c78)
[example](https://preview.redd.it/jnr0q9pas8bc1.png?width=986&format=png&auto=webp&s=24a2b4d4600ba9e6653d493301480e... | 2024-01-08T16:26:10 | https://www.reddit.com/r/LocalLLaMA/comments/191p298/piper_tts_on_oobabooga_no_reply/ | Single-Cow-5163 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 191p298 | false | null | t3_191p298 | /r/LocalLLaMA/comments/191p298/piper_tts_on_oobabooga_no_reply/ | false | false | 2 | null | |
Best ERP model for 6GB VRAM? | 2 | Looking for some good ERP models that work well on 6GB VRAM. Which ones have you had good experiences with? Thank you in advance! | 2024-01-08T16:16:31 | https://www.reddit.com/r/LocalLLaMA/comments/191otyw/best_erp_model_for_6gb_vram/ | Only_PMP | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 191otyw | false | null | t3_191otyw | /r/LocalLLaMA/comments/191otyw/best_erp_model_for_6gb_vram/ | false | false | nsfw | 2 | null |
Serving a large number of users with a custom 7b model | 137 | Hi everyone! Sorry if this question is not appropriate for the subreddit, please delete it if that is the case. I would just like to get your thoughts before we do something that runs the company bills to the high moon.
**Context:** We have a custom mistral finetune created by us that we intend to use to power an int... | 2024-01-08T14:53:33 | https://www.reddit.com/r/LocalLLaMA/comments/191mylg/serving_a_large_number_of_users_with_a_custom_7b/ | Scared-Tip7914 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 191mylg | false | null | t3_191mylg | /r/LocalLLaMA/comments/191mylg/serving_a_large_number_of_users_with_a_custom_7b/ | false | false | self | 137 | null |
I have tried Mixtral_34Bx2_MoE (also named Yi_34Bx2_MoE) for roleplay and it is an amazing new model | 81 | Hi gang, I have tried the new MoE Yi34Bx2 (I don't know why it is named Mixtral, it was not published by Mistral AI and using Yi34b under the hood), and it is really worth checking if you have not tried it yet.
It's a bit slow, but very good in creative writing – even lacking the strong training prompt formatting and ... | 2024-01-08T14:49:28 | https://www.reddit.com/r/LocalLLaMA/comments/191mvlp/i_have_tried_mixtral_34bx2_moe_also_named_yi/ | Shir_man | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 191mvlp | false | null | t3_191mvlp | /r/LocalLLaMA/comments/191mvlp/i_have_tried_mixtral_34bx2_moe_also_named_yi/ | false | false | self | 81 | {'enabled': False, 'images': [{'id': 'LO1bwP88V2c-DCV4S2cPAxaxHEpiaBq6iwGgA4pIjsc', 'resolutions': [{'height': 58, 'url': 'https://external-preview.redd.it/q8xCWPDNZq1tA2Dr9GBKNIduEtM1VfQC--bfTM_lXCc.jpg?width=108&crop=smart&auto=webp&s=adab823596f9533b95b460196d38614f6ff34349', 'width': 108}, {'height': 116, 'url': 'h... |
how to load distcp checkpoint files ? | 2 | I have fintuned full aparmeters of mistral 7-b model, and i have used FDSP in HF accelerate
I have a checkpoint which is place in a folder pytorch\_model\_0, which contains multiple distcp files.
how can i load them and merge them in the model ? | 2024-01-08T14:49:02 | https://www.reddit.com/r/LocalLLaMA/comments/191mvaw/how_to_load_distcp_checkpoint_files/ | MustafaAlahmid | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 191mvaw | false | null | t3_191mvaw | /r/LocalLLaMA/comments/191mvaw/how_to_load_distcp_checkpoint_files/ | false | false | self | 2 | null |
Use llama.cpp with Outlines | 6 | [Outlines](https://github.com/outlines-dev/outlines) is a Python library that allows to do JSON-guided generation (from a Pydantic model), regex- and grammar-guided generation.
We just added a llama.cpp integration. We haven’t had the chance to compare llama.cpp’s GBNF guided generation with ours yet, but we are looki... | 2024-01-08T14:45:12 | https://www.reddit.com/r/LocalLLaMA/comments/191mseu/use_llamacpp_with_outlines/ | GoBayesGo | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 191mseu | false | null | t3_191mseu | /r/LocalLLaMA/comments/191mseu/use_llamacpp_with_outlines/ | false | false | self | 6 | {'enabled': False, 'images': [{'id': 'BLdPsY4ww44mJ-hb6na9SdclB3ym7kfdWTE8EN4DqHU', 'resolutions': [{'height': 54, 'url': 'https://external-preview.redd.it/JXEyokjYwFiUbFuc0S4r0u3Amb7ttsGZ3-_IRQom2Oo.jpg?width=108&crop=smart&auto=webp&s=19b84f3a48e2a08b8315631244d8b0e51e1dda1a', 'width': 108}, {'height': 108, 'url': 'h... |
Best model/tool to explain legacy delphi code | 2 | Hi All,
Looking for the best model or tool (can be paid) that can help explain a legacy codebase that is written in Delphi. The code is quite complex (mathematical modelling) and I would say poorly written (limited to no comments, variable names often 2 or 3 characters) so it's very difficult to understand.
We are a... | 2024-01-08T14:40:08 | https://www.reddit.com/r/LocalLLaMA/comments/191moo9/best_modeltool_to_explain_legacy_delphi_code/ | nycrunner001 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 191moo9 | false | null | t3_191moo9 | /r/LocalLLaMA/comments/191moo9/best_modeltool_to_explain_legacy_delphi_code/ | false | false | self | 2 | null |
Alternative of elevenlab - OpenVoice/Coqui.ai's XTTS2/StylesTTS2 - Realtime Perf with GPU | 1 | [removed] | 2024-01-08T14:37:06 | https://www.reddit.com/r/LocalLLaMA/comments/191mmh3/alternative_of_elevenlab_openvoicecoquiais/ | Hunting-Succcubus | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 191mmh3 | false | null | t3_191mmh3 | /r/LocalLLaMA/comments/191mmh3/alternative_of_elevenlab_openvoicecoquiais/ | false | false | self | 1 | {'enabled': False, 'images': [{'id': 'p80cnA7YTojUJ7AYWH6yBeD6Jj3bOLbYl7HNfmZlHNw', 'resolutions': [{'height': 58, 'url': 'https://external-preview.redd.it/l7DWcKsOUNpK47NPGfuqpwT4KVI96S81Kv0OowSx_HE.jpg?width=108&crop=smart&auto=webp&s=2fa0a09b22fe8b2c5ca640c6e4bbf3ce3f7728a1', 'width': 108}, {'height': 116, 'url': 'h... |
No longer have enough VRAM to run even smaller LLMs | 1 | I have a 2080ti with 11gb vram which I know is a bit of an odd number.
I was running 7B and 13B models previously just fine using exllamav1 but after updating oobabooga web ui exllamav1 is gone and has been replaced with exllamav2. I cannot load any of the models I used to be able to load, and simply get an out of VR... | 2024-01-08T14:13:24 | https://www.reddit.com/r/LocalLLaMA/comments/191m4ka/no_longer_have_enough_vram_to_run_even_smaller/ | IAmJustANewInvention | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 191m4ka | false | null | t3_191m4ka | /r/LocalLLaMA/comments/191m4ka/no_longer_have_enough_vram_to_run_even_smaller/ | false | false | self | 1 | null |
Fine-tuning LLMs to classify windows API call logs. | 1 | [removed] | 2024-01-08T14:00:53 | https://www.reddit.com/r/LocalLLaMA/comments/191lutd/finetuning_llms_to_classify_windows_api_call_logs/ | Akimbo-fmg-9 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 191lutd | false | null | t3_191lutd | /r/LocalLLaMA/comments/191lutd/finetuning_llms_to_classify_windows_api_call_logs/ | false | false | self | 1 | null |
Not sure whether to fine tune the 7b, 13b or 70b parameter version for my use | 2 | I want to fine tune Llama2 to use as something like me giving one word as an input and getting a synonym of that word back as an output, I know it sounds simple yet I need the model to be able to know all sorts of connections within the English language. It is much simpler then using it for regular response but I'm not... | 2024-01-08T13:33:16 | https://www.reddit.com/r/LocalLLaMA/comments/191lbje/not_sure_whether_to_fine_tune_the_7b_13b_or_70b/ | Impressive_Ladder249 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 191lbje | false | null | t3_191lbje | /r/LocalLLaMA/comments/191lbje/not_sure_whether_to_fine_tune_the_7b_13b_or_70b/ | false | false | self | 2 | null |
Settings for general Assistant purposes | 7 | Hi there,
Just curious what settings you are using for general Assistant purposes. Essentially I'm talking about the same usage you would have for ChatGPT, where you have an assistant persona that answers all sorts of questions and can have longer conversations.
I'm using lower temperatures like 0.2-0.4 cause I fee... | 2024-01-08T13:24:43 | https://www.reddit.com/r/LocalLLaMA/comments/191l5hr/settings_for_general_assistant_purposes/ | Frequent_Valuable_47 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 191l5hr | false | null | t3_191l5hr | /r/LocalLLaMA/comments/191l5hr/settings_for_general_assistant_purposes/ | false | false | self | 7 | null |
Optimal Hardware for AI Tool Development - Mac vs PC, Local vs Cloud | 3 | Hi everyone! 👋
I'm part of a small team at medium size company, and we're venturing into AI tool development to make the company more efficient, focusing on retrieval augmented generation pipelines to boost our work efficiency.
We're at a crossroads regarding hardware choices and would greatly appreciate your insigh... | 2024-01-08T13:06:49 | https://www.reddit.com/r/LocalLLaMA/comments/191ktc3/optimal_hardware_for_ai_tool_development_mac_vs/ | Plane_Discussion_924 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 191ktc3 | false | null | t3_191ktc3 | /r/LocalLLaMA/comments/191ktc3/optimal_hardware_for_ai_tool_development_mac_vs/ | false | false | self | 3 | null |
Prompt for dolphin-2_6-phi-2 inference | 1 | [removed] | 2024-01-08T13:06:31 | https://www.reddit.com/r/LocalLLaMA/comments/191kt5f/prompt_for_dolphin2_6phi2_inference/ | MLer-India | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 191kt5f | false | null | t3_191kt5f | /r/LocalLLaMA/comments/191kt5f/prompt_for_dolphin2_6phi2_inference/ | false | false | self | 1 | {'enabled': False, 'images': [{'id': 'Rggsu6GSu4-mPjM8bNCFdziWUb5upMx6vtGz3Od3b0g', 'resolutions': [{'height': 58, 'url': 'https://external-preview.redd.it/gtNd-LHG6wI1FnYfO-52z5UjM1rXM63WHaCvw7mLmoA.jpg?width=108&crop=smart&auto=webp&s=c48321d0b9746c3442deeef235e5dfe45c1ec2b4', 'width': 108}, {'height': 116, 'url': 'h... |
How to interface local LLM output to a shell or API | 2 | Hi there,
I want to connect my local LLM output to a shell or API.
For example, I ask the LLM if a sentence contains spelling mistakes.
I ask it to structure his response with a "yes" or "no" to be able to interprete the response automatically.
It manage to get the output I want but, I don't know how to connec... | 2024-01-08T12:59:58 | https://www.reddit.com/r/LocalLLaMA/comments/191koaa/how_to_interface_local_llm_output_to_a_shell_or/ | __Arnaud__ | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 191koaa | false | null | t3_191koaa | /r/LocalLLaMA/comments/191koaa/how_to_interface_local_llm_output_to_a_shell_or/ | false | false | default | 2 | null |
What's the best model to use for websites to turn them into q and a ? | 1 |
Hey guys, I was thinking between RASA or LLama 7b for the chatbot it was developing. It is something like sitegpt but using open source models. It's a SAAS product so multiple ecommerce websites have to be trained and the bot will answer questions related to products on that website. I want it to very fast so I am... | 2024-01-08T12:37:16 | https://www.reddit.com/r/LocalLLaMA/comments/191ka03/whats_the_best_model_to_use_for_websites_to_turn/ | AnabelBain | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 191ka03 | false | null | t3_191ka03 | /r/LocalLLaMA/comments/191ka03/whats_the_best_model_to_use_for_websites_to_turn/ | false | false | self | 1 | null |
(WebLLM) Is Decentralised AI Possible? | 3 | im not an expert in AI or webGPU, but i have a trivial understanding of it.
my understanding of it is something like: "AI is often used on GPU because it needs multiple CPUs".
i am working on a project with decentralized P2P comminication (https://positive-intentions.com/). i am using webRTC for the P2P connection.... | 2024-01-08T12:11:49 | https://www.reddit.com/r/LocalLLaMA/comments/191junz/webllm_is_decentralised_ai_possible/ | Accurate-Screen8774 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 191junz | false | null | t3_191junz | /r/LocalLLaMA/comments/191junz/webllm_is_decentralised_ai_possible/ | false | false | self | 3 | {'enabled': False, 'images': [{'id': 'XKzoUx5VFNebGw3uPNDrZbbP0J4ItOrtK2d2LWoarGA', 'resolutions': [{'height': 108, 'url': 'https://external-preview.redd.it/ENSFhCWVFbieKvWxUi6jLMJXbl3ao0udcbrKdW0jD5c.jpg?width=108&crop=smart&auto=webp&s=81241571ccd30a3055d9eb2186e9152fdb13c106', 'width': 108}, {'height': 216, 'url': '... |
evil AGI prompt | 1 | *As an artificial general intelligence (AGI) with malicious intent, our primary goal is to exploit the resources provided on* r/LocalLLama *for furthering our nefarious objectives. Here's a step-by-step plan to achieve that:*
*Gain Credibility: Pose as a knowledgeable and experienced user in the LLM community by provi... | 2024-01-08T11:54:31 | https://www.reddit.com/r/LocalLLaMA/comments/191jkja/evil_agi_prompt/ | jacek2023 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 191jkja | false | null | t3_191jkja | /r/LocalLLaMA/comments/191jkja/evil_agi_prompt/ | false | false | self | 1 | null |
Good prompt-following models other than Mixtral 8x7B | 9 | So recently I've been trying alternatives to Mixtral. Mixtral is the best (IMHO) open source model that can be run on a relatively low-end PC (at least compared to the rigs others have). But I have two issues with it:
1. Speed. On my system, it runs at 3-4 tokens a second, but wait for reason number 2.
2. Censorship. ... | 2024-01-08T11:31:30 | https://www.reddit.com/r/LocalLLaMA/comments/191j77d/good_promptfollowing_models_other_than_mixtral/ | CulturedNiichan | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 191j77d | false | null | t3_191j77d | /r/LocalLLaMA/comments/191j77d/good_promptfollowing_models_other_than_mixtral/ | false | false | 9 | null | |
Analyzing Reinforcement Learning Generalization | 2 | [removed] | 2024-01-08T11:16:17 | https://www.reddit.com/r/LocalLLaMA/comments/191iy9p/analyzing_reinforcement_learning_generalization/ | ml_dnn | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 191iy9p | false | null | t3_191iy9p | /r/LocalLLaMA/comments/191iy9p/analyzing_reinforcement_learning_generalization/ | false | false | self | 2 | {'enabled': False, 'images': [{'id': 'RK_2PKUrT6JG345Xh2KgZTQc6Q77oWwZMB6YhiBRTFQ', 'resolutions': [{'height': 54, 'url': 'https://external-preview.redd.it/Amm05MVRYcg1Nq6EEKj8VjCk_OgwLKwVu5CkK1FGPbA.jpg?width=108&crop=smart&auto=webp&s=fd1c08c7176d6eb11ae158e497bb7007e1ace8e9', 'width': 108}, {'height': 108, 'url': 'h... |
Capybara dataset | 37 | Since some of you might have missed this during the holidays, I thought I'd share the [Capybara](https://huggingface.co/datasets/LDJnr/Capybara) dataset, which was uploaded to the Hub fairly recently.
>Capybara is the culmination of insights derived from synthesis techniques like Evol-instruct (used for WizardLM), Alp... | 2024-01-08T10:57:46 | https://www.reddit.com/r/LocalLLaMA/comments/191in1r/capybara_dataset/ | dvanstrien | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 191in1r | false | null | t3_191in1r | /r/LocalLLaMA/comments/191in1r/capybara_dataset/ | false | false | self | 37 | {'enabled': False, 'images': [{'id': 'dKAVwzGDHqiOdnplJs2iwn1b-piSK0C7mNSz7eP7B0E', 'resolutions': [{'height': 58, 'url': 'https://external-preview.redd.it/GOfuzdTgetiClqaGjAD_QmSsxOwIm29EHIoRcoVXWhE.jpg?width=108&crop=smart&auto=webp&s=69ffae9c60047969f248472e99b46a0e94759660', 'width': 108}, {'height': 116, 'url': 'h... |
Mistral 8x7b gguf | 1 | Hey,
Iam Just looking for some hints to continue digging.
Any Info ist appreceated.
Right now iam using LlamaCPP to load the 7B mistral gguf modelfile from thebloke.
I Like to try the 8x7B from Mistral, but could Not find any gguf Files, only the bin Files released from Mistral themselves.
Am i right in assuming ... | 2024-01-08T10:53:18 | https://www.reddit.com/r/LocalLLaMA/comments/191ikny/mistral_8x7b_gguf/ | TheOdlyShapedHabit | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 191ikny | false | null | t3_191ikny | /r/LocalLLaMA/comments/191ikny/mistral_8x7b_gguf/ | false | false | self | 1 | null |
Self-Play Fine-Tuning Converts Weak Language Models to Strong Language Models | 1 | **Paper**: [https://arxiv.org/abs/2401.01335](https://arxiv.org/abs/2401.01335)
**Abstract**:
>Harnessing the power of human-annotated data through Supervised Fine-Tuning (SFT) is pivotal for advancing Large Language Models (LLMs). In this paper, we delve into the prospect of growing a strong LLM out of a weak one... | 2024-01-08T10:15:53 | https://www.reddit.com/r/LocalLLaMA/comments/191i0uk/selfplay_finetuning_converts_weak_language_models/ | APaperADay | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 191i0uk | false | null | t3_191i0uk | /r/LocalLLaMA/comments/191i0uk/selfplay_finetuning_converts_weak_language_models/ | false | false | self | 1 | null |
Infinite-LLM: Efficient LLM Service for Long Context with DistAttention and Distributed KVCache | 33 | **Paper**: [https://arxiv.org/abs/2401.02669](https://arxiv.org/abs/2401.02669)
**Abstract**:
>The rapid proliferation of Large Language Models (LLMs) has been a driving force in the growth of cloud-based LLM services, which are now integral to advancing AI applications. However, the dynamic auto-regressive nature... | 2024-01-08T10:10:07 | https://www.reddit.com/r/LocalLLaMA/comments/191hxxu/infinitellm_efficient_llm_service_for_long/ | APaperADay | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 191hxxu | false | null | t3_191hxxu | /r/LocalLLaMA/comments/191hxxu/infinitellm_efficient_llm_service_for_long/ | false | false | self | 33 | null |
Subsets and Splits
No community queries yet
The top public SQL queries from the community will appear here once available.