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 ⌀ |
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
Meta - Open sourcing a new and improved Code Llama | 105 | 2024-01-29T16:17:23 | https://www.facebook.com/zuck/posts/were-open-sourcing-a-new-and-improved-code-llama-including-a-larger-70b-paramete/10115471700125721/ | bratao | facebook.com | 1970-01-01T00:00:00 | 0 | {} | 1adz2vn | false | null | t3_1adz2vn | /r/LocalLLaMA/comments/1adz2vn/meta_open_sourcing_a_new_and_improved_code_llama/ | false | false | default | 105 | null | |
Help running models in colab | 2 | Hello
This is probably not even the right place to ask this but i don't know where else to ask. I sadly do not have the hardware needed to host dolphin-mixtral (this one: [https://huggingface.co/TheBloke/dolphin-2.7-mixtral-8x7b-GGUF](https://huggingface.co/TheBloke/dolphin-2.7-mixtral-8x7b-GGUF)), and decided to buy ... | 2024-01-29T16:17:06 | https://www.reddit.com/r/LocalLLaMA/comments/1adz2mo/help_running_models_in_colab/ | Sidoooooo | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 1adz2mo | false | null | t3_1adz2mo | /r/LocalLLaMA/comments/1adz2mo/help_running_models_in_colab/ | false | false | self | 2 | {'enabled': False, 'images': [{'id': '46L172gAQpqb4lefodRkwffzsrooawaSnfZtlljO5uA', 'resolutions': [{'height': 58, 'url': 'https://external-preview.redd.it/AAjCDMVs-dZHaCNe2jCBYMQcbcGcKVthkqMP0kJnuao.jpg?width=108&crop=smart&auto=webp&s=9c9552af2f88815d7786ca622fbc02ce91723972', 'width': 108}, {'height': 116, 'url': 'h... |
Giving back | 22 | Did not expect the response received re the A100 rig. As stated, I got lucky. I wanted to make a suggestion and see how it went down -
Would it be useful to offer one of the A100 boards for any dev teams ( ie exllama, llama cpp, etc )? I was going to possibly suggest a three month rotation, passing it onto the next d... | 2024-01-29T16:09:49 | https://www.reddit.com/r/LocalLLaMA/comments/1adywe6/giving_back/ | BreakIt-Boris | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 1adywe6 | false | null | t3_1adywe6 | /r/LocalLLaMA/comments/1adywe6/giving_back/ | false | false | self | 22 | null |
Blind Testing 16 Different Models for Roleplaying | 56 | **RESULTS** (from 30 tests)
**1. (tie)** 70b lzlv (80 points)
**1. (tie)** 120b Goliath (80 points)
**3.** 34b NousCapybara (78 points)
**4.** 8x7b Noromaid (77 points)
**5.** 34b NousHermes2 (73 points)
**6.** 8x7b NousHermes2 DPO (67 points)
**7.** 13b Psyfighter v2 (64 points)
**8.** 34b Bagel v0.2 (59 point... | 2024-01-29T15:14:09 | https://www.reddit.com/r/LocalLLaMA/comments/1adxlyj/blind_testing_16_different_models_for_roleplaying/ | Alex1Nunez19 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 1adxlyj | false | null | t3_1adxlyj | /r/LocalLLaMA/comments/1adxlyj/blind_testing_16_different_models_for_roleplaying/ | false | false | self | 56 | {'enabled': False, 'images': [{'id': 'BUn-uP6YX78FL-O1lmxo8IK6h1f8wJjgd2bA8YHrLZc', 'resolutions': [{'height': 56, 'url': 'https://external-preview.redd.it/aUsqXntZxKm2qsjNyhGl4jqo4JfeXqfWGyoeg1eaJDs.jpg?width=108&crop=smart&auto=webp&s=0c2019a45d45a5fdf54305cbb91b75bd9e163b04', 'width': 108}, {'height': 113, 'url': 'h... |
how are you visualizing 'loss' and stuff during training? What software/libraries? | 1 | Coming from GUI, its fire and forget. No testing or reporting.
Now that I am familiar with transformers, I'm thinking I want to go full 5 star testing suite. (although, FOSS, none of that 4 different API tutorial crap).
Any suggestions? I'm specifically doing LoRA. | 2024-01-29T14:47:37 | https://www.reddit.com/r/LocalLLaMA/comments/1adx0j0/how_are_you_visualizing_loss_and_stuff_during/ | pr1vacyn0eb | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 1adx0j0 | false | null | t3_1adx0j0 | /r/LocalLLaMA/comments/1adx0j0/how_are_you_visualizing_loss_and_stuff_during/ | false | false | self | 1 | null |
Looking for "french" 7B / 13B LLM | 2 | Hello, I'm looking for a 7B or 13B LLM that can reply in French.
I need an LLM that can chat and be creative.
Do you have any suggestions?
I've already tried Toppy-M-7B-GGUF and Vigogne 7B, but they don't feel as sharp as when chatting in English. | 2024-01-29T14:39:51 | https://www.reddit.com/r/LocalLLaMA/comments/1adwu2l/looking_for_french_7b_13b_llm/ | Haurrus | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 1adwu2l | false | null | t3_1adwu2l | /r/LocalLLaMA/comments/1adwu2l/looking_for_french_7b_13b_llm/ | false | false | self | 2 | null |
Discussion on Rerankers available as a service for RAG | 2 | Hello Community,
I'm exploring reranker tools and curious about your experiences, especially with [bge](https://huggingface.co/BAAI/bge-reranker-base)
models (large/base) and services like Cohere Rerank. My use case is for a very generic RAG and I want to see some metrics on the available rerankers (apart from MTEB) ... | 2024-01-29T14:17:23 | https://www.reddit.com/r/LocalLLaMA/comments/1adwcbe/discussion_on_rerankers_available_as_a_service/ | brooding_pixel | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 1adwcbe | false | null | t3_1adwcbe | /r/LocalLLaMA/comments/1adwcbe/discussion_on_rerankers_available_as_a_service/ | false | false | self | 2 | {'enabled': False, 'images': [{'id': 'mTNPdmjwD5rqyKRSIOBWOjAy5C46sayWfxnKQNioruM', 'resolutions': [{'height': 58, 'url': 'https://external-preview.redd.it/le4q-5Ax4FV-Mm3f6qbk4tcgddlHFXIRZkGzg04Uikg.jpg?width=108&crop=smart&auto=webp&s=1444e858efaee0a8dae57ff7f179afd8abb9830c', 'width': 108}, {'height': 116, 'url': 'h... |
Differences between LORA training OpenLLaMa and Mistral? | 1 | It seems Mistral uses a different format for the LORA training data, but other than that, they are the same?
I'd use transformers training, PEFT/LORA.
I imagine the parameters for training will be slightly different.
Basically my goal isnt to waste time accidentally on training Mistral only to find out it can't be... | 2024-01-29T14:00:00 | https://www.reddit.com/r/LocalLLaMA/comments/1advyav/differences_between_lora_training_openllama_and/ | pr1vacyn0eb | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 1advyav | false | null | t3_1advyav | /r/LocalLLaMA/comments/1advyav/differences_between_lora_training_openllama_and/ | false | false | self | 1 | null |
Finetuning on the truth that reality is an illusion | 1 | Can somebody please finetune a model on my journal entries which are primarily about my experience in meditation? Thanks | 2024-01-29T13:51:54 | https://www.reddit.com/r/LocalLLaMA/comments/1advs58/finetuning_on_the_truth_that_reality_is_an/ | YouWide5985 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 1advs58 | false | null | t3_1advs58 | /r/LocalLLaMA/comments/1advs58/finetuning_on_the_truth_that_reality_is_an/ | false | false | self | 1 | null |
Miqu comparison - Supposedly mistral medium leaked | 141 | 2024-01-29T13:47:01 | https://twitter.com/qtnx_/status/1751775870631502067/photo/1 | bratao | twitter.com | 1970-01-01T00:00:00 | 0 | {} | 1advoiz | false | null | t3_1advoiz | /r/LocalLLaMA/comments/1advoiz/miqu_comparison_supposedly_mistral_medium_leaked/ | false | false | default | 141 | null | |
Seeking the Best Reranker Services: Experiences with bge & Cohere? | 1 | Hello Community,
I'm exploring reranker tools and curious about your experiences, especially with [bge](https://huggingface.co/BAAI/bge-reranker-base) models (large/base) and services like Cohere Rerank. My use case is for a very generic RAG and I want to see some metrics on the available rerankers (apart from MTEB) e... | 2024-01-29T13:33:24 | https://www.reddit.com/r/LocalLLaMA/comments/1advemq/seeking_the_best_reranker_services_experiences/ | brooding_pixel | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 1advemq | false | null | t3_1advemq | /r/LocalLLaMA/comments/1advemq/seeking_the_best_reranker_services_experiences/ | false | false | self | 1 | {'enabled': False, 'images': [{'id': 'mTNPdmjwD5rqyKRSIOBWOjAy5C46sayWfxnKQNioruM', 'resolutions': [{'height': 58, 'url': 'https://external-preview.redd.it/le4q-5Ax4FV-Mm3f6qbk4tcgddlHFXIRZkGzg04Uikg.jpg?width=108&crop=smart&auto=webp&s=1444e858efaee0a8dae57ff7f179afd8abb9830c', 'width': 108}, {'height': 116, 'url': 'h... |
When we see models derived from other models on HuggingFace, do they include the whole model or just some sort of tuning? | 5 | Things may be specific to specific uploads but, generally speaking, I am curious to understand if there's a general rule of thumb.
Let's say I grab [this](https://huggingface.co/TheBloke/Falcon-180B-Chat-GGUF), which is a fine tune of Falcon-180B.
It says "Derived from:" and so on. Does this mean I need to also downl... | 2024-01-29T13:25:15 | https://www.reddit.com/r/LocalLLaMA/comments/1adv8tw/when_we_see_models_derived_from_other_models_on/ | x54675788 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 1adv8tw | false | null | t3_1adv8tw | /r/LocalLLaMA/comments/1adv8tw/when_we_see_models_derived_from_other_models_on/ | false | false | self | 5 | {'enabled': False, 'images': [{'id': 'g8CzHRJGbGgbt0TlyWjFFSKUdC6Vo77yKNuuGUdOGfc', 'resolutions': [{'height': 58, 'url': 'https://external-preview.redd.it/uxFjbHQS2blwk_nkX3NBHD7Gxs9pVysX-KfuwEpzsAU.jpg?width=108&crop=smart&auto=webp&s=ace44c777b744b4254a50e7bdb013614cca2a0ba', 'width': 108}, {'height': 116, 'url': 'h... |
Is there any difference between using the GPU and CPU other than speed? | 2 | I'm new to this world and I remember reading something on the lines of "context window moves as you keep going with GPU, unlike with CPU".
I can't find the comment anymore, the above sentence may be right or completely wrong, so I ask here.
Is there anything I'd be missing other than speed, if I run stuff on CPU and ... | 2024-01-29T13:20:17 | https://www.reddit.com/r/LocalLLaMA/comments/1adv5cg/is_there_any_difference_between_using_the_gpu_and/ | x54675788 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 1adv5cg | false | null | t3_1adv5cg | /r/LocalLLaMA/comments/1adv5cg/is_there_any_difference_between_using_the_gpu_and/ | false | false | self | 2 | null |
New hallucinations leaderboard! | 113 | There's a new leaderboard on Hugging Face: the [LLM Hallucination Leaderboard](https://huggingface.co/spaces/hallucinations-leaderboard/leaderboard)!
Led by researchers from the Uni of Edinburgh, it evaluates the propensity of models to *hallucinate*, either on factuality (= say false things) or faithfulness (= ignore... | 2024-01-29T13:17:35 | https://www.reddit.com/r/LocalLLaMA/comments/1adv3gq/new_hallucinations_leaderboard/ | clefourrier | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 1adv3gq | false | null | t3_1adv3gq | /r/LocalLLaMA/comments/1adv3gq/new_hallucinations_leaderboard/ | false | false | self | 113 | {'enabled': False, 'images': [{'id': 'h5mrwUrY5niVDxN2AgbulBkfdZNKTqes2NZc_NPNIWA', 'resolutions': [{'height': 58, 'url': 'https://external-preview.redd.it/DmATUyMNew4bCEU7eXF3_o_JerkFxQ_pYpl-Fj0hcqY.jpg?width=108&crop=smart&auto=webp&s=126dff65d5d3b4ff6f7a21823aeb434a18b53cf2', 'width': 108}, {'height': 116, 'url': 'h... |
5 x A100 setup finally complete | 846 | Taken a while, but finally got everything wired up, powered and connected.
5 x A100 40GB running at 450w each
Dedicated 4 port PCIE Switch
PCIE extenders going to 4 units
Other unit attached via sff8654 4i port ( the small socket next to fan )
1.5M SFF8654 8i cables going to PCIE Retimer
The GPU setup has its own ... | 2024-01-29T13:12:14 | https://www.reddit.com/gallery/1aduzqq | BreakIt-Boris | reddit.com | 1970-01-01T00:00:00 | 0 | {} | 1aduzqq | false | null | t3_1aduzqq | /r/LocalLLaMA/comments/1aduzqq/5_x_a100_setup_finally_complete/ | false | false | 846 | null | |
Free/cheap hosts for training, tuning etc? | 1 |
I'm playing with small models and want to experiment with training/fine-tuning/merging etc. My own hardware is minimal. I'm aware of huggingface and colab but haven't a clue what else is out there. What are y'all using?
I guess the aspects I'm looking for (which may not be in the same place) are :
1. Preset, pre-tra... | 2024-01-29T12:09:18 | https://www.reddit.com/r/LocalLLaMA/comments/1adtu2c/freecheap_hosts_for_training_tuning_etc/ | danja | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 1adtu2c | false | null | t3_1adtu2c | /r/LocalLLaMA/comments/1adtu2c/freecheap_hosts_for_training_tuning_etc/ | false | false | self | 1 | null |
Defensive and Robust Design in AI Automation | 1 | 2024-01-29T11:59:46 | https://medium.com/@kenny_v/defensive-and-robust-design-in-ai-automation-8e951c8e7fd7 | TheDeadlyPretzel | medium.com | 1970-01-01T00:00:00 | 0 | {} | 1adtnto | false | null | t3_1adtnto | /r/LocalLLaMA/comments/1adtnto/defensive_and_robust_design_in_ai_automation/ | false | false | 1 | {'enabled': False, 'images': [{'id': 'mbQkpDS2bFE2VvhyMi57obNASZACz7NSEJVlIVjmO5c', 'resolutions': [{'height': 81, 'url': 'https://external-preview.redd.it/TXtODbKhodREMwcPbUmXvIU9o113jmyxo-yCFCoLwQA.jpg?width=108&crop=smart&auto=webp&s=d0a924918709d2657dfffcc5f08d090fe6c9558d', 'width': 108}, {'height': 162, 'url': 'h... | ||
Question about Mixtrals prompt format | 6 | I am using the Mixtral-8x7B-Instruct-v0.1model from Hugging Face. The model card says the following about the prompt format:
> This format must be strictly respected, otherwise the model will generate sub-optimal outputs.
<s> \[INST\] Instruction \[/INST\] Model answer</s> \[INST\] Follow-up instruction \[/INST\]
... | 2024-01-29T11:59:29 | https://www.reddit.com/r/LocalLLaMA/comments/1adtno0/question_about_mixtrals_prompt_format/ | LargeBrick7 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 1adtno0 | false | null | t3_1adtno0 | /r/LocalLLaMA/comments/1adtno0/question_about_mixtrals_prompt_format/ | false | false | self | 6 | null |
Why I am getting extra response from the Langchain? | 1 | Hey Everyone! I am reading and trying to understand why this code snippet is giving extra response in Chat wise manner for last 3 hours. I am unable to get through it.
import os
from dotenv import load_dotenv
from langchain.llms import HuggingFaceHub
from langchain.embeddings import HuggingFac... | 2024-01-29T11:38:07 | https://www.reddit.com/r/LocalLLaMA/comments/1adtb9f/why_i_am_getting_extra_response_from_the_langchain/ | Pinaka-X | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 1adtb9f | false | null | t3_1adtb9f | /r/LocalLLaMA/comments/1adtb9f/why_i_am_getting_extra_response_from_the_langchain/ | false | false | self | 1 | null |
In 2024, is there a place for encoder-decoder models and masked LMs? | 12 | In my (possibly outdated) textbox, encoder-decoder models are a very important and popular part of the transformer structure. And there are two types of language models: causal LM and masked LM. However probably starting with the release of llama, decoder-only causal LMs are becoming increasing popular. Almost all inte... | 2024-01-29T11:20:33 | https://www.reddit.com/r/LocalLLaMA/comments/1adt18x/in_2024_is_there_a_place_for_encoderdecoder/ | sgsdxzy | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 1adt18x | false | null | t3_1adt18x | /r/LocalLLaMA/comments/1adt18x/in_2024_is_there_a_place_for_encoderdecoder/ | false | false | self | 12 | null |
How can I increase the speed performance of llm without changing hardware? | 1 | I created a SQL assistant using llama.cpp and langchain. But this assistant takes a long time to respond. I want to shorten this time without changing the hardware. That's why this came to my mind: Prompt = """You are a SQLite expert. Given an input question, first create a syntactically correct SQLite query to run, th... | 2024-01-29T11:16:23 | https://www.reddit.com/r/LocalLLaMA/comments/1adsyyw/how_can_i_increase_the_speed_performance_of_llm/ | CommitteeHairy6435 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 1adsyyw | false | null | t3_1adsyyw | /r/LocalLLaMA/comments/1adsyyw/how_can_i_increase_the_speed_performance_of_llm/ | false | false | self | 1 | null |
Did anything big happen over the weekend in the world of LLaMA? Asking for a friend. | 1 | 2024-01-29T11:09:01 | ambient_temp_xeno | i.redd.it | 1970-01-01T00:00:00 | 0 | {} | 1adsuow | false | null | t3_1adsuow | /r/LocalLLaMA/comments/1adsuow/did_anything_big_happen_over_the_weekend_in_the/ | false | false | 1 | {'enabled': True, 'images': [{'id': '4oBe6cqVCY5jiL_gY9QIMBCvkgOZZYAA33cfp9XrdH8', 'resolutions': [{'height': 108, 'url': 'https://preview.redd.it/dq3fpw1g3dfc1.png?width=108&crop=smart&auto=webp&s=458107d5f8269c58ebd81a09d54a3bcd25381470', 'width': 108}, {'height': 216, 'url': 'https://preview.redd.it/dq3fpw1g3dfc1.pn... | |||
Are there any tiny models (<3B) with Mistral vocab for speculative execution? | 3 | I can speed up inference significantly on Llama-2 models by using draft models that use the same vocab, like tinyllama or smol-llama. But I haven't found any such models compatible with Mistral. | 2024-01-29T10:37:14 | https://www.reddit.com/r/LocalLLaMA/comments/1adscxm/are_there_any_tiny_models_3b_with_mistral_vocab/ | stddealer | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 1adscxm | false | null | t3_1adscxm | /r/LocalLLaMA/comments/1adscxm/are_there_any_tiny_models_3b_with_mistral_vocab/ | false | false | self | 3 | null |
Mistral medium possibly leaked (miqu) | 1 | [removed] | 2024-01-29T10:36:45 | https://www.reddit.com/r/LocalLLaMA/comments/1adscou/mistral_medium_possibly_leaked_miqu/ | cyberuser42 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 1adscou | false | null | t3_1adscou | /r/LocalLLaMA/comments/1adscou/mistral_medium_possibly_leaked_miqu/ | false | false | self | 1 | {'enabled': False, 'images': [{'id': 'YwK0i5uwzktX1nH_8wCb9scLo-p_k7U36rHB1ExOeZo', 'resolutions': [{'height': 58, 'url': 'https://external-preview.redd.it/BQcqnWPMK5Y3U1I8wKe-mQjzHW7J109B4lbTrb7r6sA.jpg?width=108&crop=smart&auto=webp&s=dd5d7f81d68648edfb0c8136135c812f616df207', 'width': 108}, {'height': 116, 'url': 'h... |
does NVLink really matter? | 2 | What's the difference between buying:
1. 4x4090 24 GB (96GB in total)
comparing to
​
2. 4x3090 with NVLink (96GB in total)
comparing to
3. A100 (80GB in total)
​
in terms of AI inference and training? | 2024-01-29T10:16:58 | https://www.reddit.com/r/LocalLLaMA/comments/1ads2cx/does_nvlink_really_matter/ | Wrong_User_Logged | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 1ads2cx | false | null | t3_1ads2cx | /r/LocalLLaMA/comments/1ads2cx/does_nvlink_really_matter/ | false | false | self | 2 | null |
So, the mysterious https://huggingface.co/miqudev/miqu-1-70b | 1 | [removed] | 2024-01-29T10:09:23 | https://www.reddit.com/r/LocalLLaMA/comments/1adry90/so_the_mysterious/ | ambient_temp_xeno | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 1adry90 | false | null | t3_1adry90 | /r/LocalLLaMA/comments/1adry90/so_the_mysterious/ | false | false | self | 1 | null |
Extending LLM's Context with Activation Beacon [Model/code release] | 43 | [https://huggingface.co/namespace-Pt/activation-beacon-llama2-7b-chat](https://huggingface.co/namespace-Pt/activation-beacon-llama2-7b-chat)
[https://github.com/FlagOpen/FlagEmbedding/tree/master/Long\_LLM/activation\_beacon](https://github.com/FlagOpen/FlagEmbedding/tree/master/Long_LLM/activation_beacon)
This was p... | 2024-01-29T10:08:08 | https://www.reddit.com/r/LocalLLaMA/comments/1adrxmh/extending_llms_context_with_activation_beacon/ | mpasila | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 1adrxmh | false | null | t3_1adrxmh | /r/LocalLLaMA/comments/1adrxmh/extending_llms_context_with_activation_beacon/ | false | false | self | 43 | {'enabled': False, 'images': [{'id': 'MplOg4EE6kRfwy83N8jnUGvy-9Qp_homtPhRGZbO0QA', 'resolutions': [{'height': 58, 'url': 'https://external-preview.redd.it/x5P0qPH4aaGcNp3O1mr4jbMkVR_7ingJuJQ2tNKx9Kg.jpg?width=108&crop=smart&auto=webp&s=7ea4540f11e3b98152c89e4c1fc5b5f4bd184380', 'width': 108}, {'height': 116, 'url': 'h... |
Training a Fantasy Writing Model in MLX for Apple Silicon | 1 | This is an update on a [first, abortive attempt](https://www.reddit.com/r/LocalLLaMA/comments/1abt15y/fine_tuning_a_tolkien_model_style_seems_to_have/) to train a Tolkien fantasy fine-tune.
**Overall Objective**: Generate fantasy fiction training data locally using Mixtral-8x7b, and then train a Mistral-7b fine tune t... | 2024-01-29T09:16:49 | https://www.reddit.com/r/LocalLLaMA/comments/1adr6vh/training_a_fantasy_writing_model_in_mlx_for_apple/ | Mbando | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 1adr6vh | false | null | t3_1adr6vh | /r/LocalLLaMA/comments/1adr6vh/training_a_fantasy_writing_model_in_mlx_for_apple/ | false | false | self | 1 | {'enabled': False, 'images': [{'id': 'aSJkeKJCS2n0ucuUyM30awIvRSGTQNcXYKjoLeeTqdc', 'resolutions': [{'height': 58, 'url': 'https://external-preview.redd.it/oa-ySZjbdUcZyfPXebxffRCzJT04E-aakfGU2q308fo.jpg?width=108&crop=smart&auto=webp&s=eca5537896fbd9d4190d83983dff0bb5fdc5f7a4', 'width': 108}, {'height': 116, 'url': 'h... |
Can VLLM handle online inference with batching during concurrent http requests when using the Python client for vllm entrypoints api_server? | 15 | I am very new to the deployment and have few doubts
1. Can VLLM handle online inference with batching during concurrent HTTP requests?
2. What are the benefits of using Triton or Ray Serve to deploy VLLM?
3. How can I implement in-flight request batching before handing them off to VLLM if my goal is to utilize its rea... | 2024-01-29T09:10:14 | https://www.reddit.com/r/LocalLLaMA/comments/1adr3l2/can_vllm_handle_online_inference_with_batching/ | Pawnzo_90z | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 1adr3l2 | false | null | t3_1adr3l2 | /r/LocalLLaMA/comments/1adr3l2/can_vllm_handle_online_inference_with_batching/ | false | false | self | 15 | null |
How do I choose between using Mistral Instruct or base model? | 1 | [removed] | 2024-01-29T08:29:34 | https://www.reddit.com/r/LocalLLaMA/comments/1adqixh/how_do_i_choose_between_using_mistral_instruct_or/ | alex-su-for-ai | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 1adqixh | false | null | t3_1adqixh | /r/LocalLLaMA/comments/1adqixh/how_do_i_choose_between_using_mistral_instruct_or/ | false | false | self | 1 | {'enabled': False, 'images': [{'id': 'mKj6_gcKTdHlEpGhastNemC3rEG6lCiOYkXxM3Z9fxE', 'resolutions': [{'height': 97, 'url': 'https://external-preview.redd.it/qwqEKwWnfJBeNB3-EfyW25C7aDeoFRD1SdH3aOOkwnQ.jpg?width=108&crop=smart&auto=webp&s=05c6055e0cd0ca3539deea591771572d6c135e77', 'width': 108}, {'height': 194, 'url': 'h... |
Toxicity classification model | 1 | What are some excellent options for detecting toxic statements? Can Mistral be used for toxicity classification? Looking for a small model. A general purpose model is a plus. | 2024-01-29T07:37:05 | https://www.reddit.com/r/LocalLLaMA/comments/1adprd5/toxicity_classification_model/ | amang0112358 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 1adprd5 | false | null | t3_1adprd5 | /r/LocalLLaMA/comments/1adprd5/toxicity_classification_model/ | false | false | self | 1 | null |
Getting Cuda out of memory error | 2 | I am trying to implement RAG using mistral 7b in 4 bit quantization, i have 12 GB gpu nvidia geforce rtx 3060 and 32 gb ram with 1.5TB ssd.
I am getting most often cuda out of memory error and also i am confused how model is getting divided in Ram and gpu while loading?
Please, community provide some insights ... | 2024-01-29T06:35:24 | https://www.reddit.com/r/LocalLLaMA/comments/1adotk3/getting_cuda_out_of_memory_error/ | Willing-Hawk5256 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 1adotk3 | false | null | t3_1adotk3 | /r/LocalLLaMA/comments/1adotk3/getting_cuda_out_of_memory_error/ | false | false | self | 2 | null |
Worldcup question | 1 | [removed] | 2024-01-29T06:18:22 | https://www.reddit.com/r/LocalLLaMA/comments/1adojeh/worldcup_question/ | rorowhat | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 1adojeh | false | null | t3_1adojeh | /r/LocalLLaMA/comments/1adojeh/worldcup_question/ | false | false | self | 1 | null |
GPU for LLMs!!! | 1 | [removed] | 2024-01-29T05:12:57 | https://www.reddit.com/r/LocalLLaMA/comments/1adneo1/gpu_for_llms/ | Delicious_Success303 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 1adneo1 | false | null | t3_1adneo1 | /r/LocalLLaMA/comments/1adneo1/gpu_for_llms/ | false | false | self | 1 | {'enabled': False, 'images': [{'id': '5adjmGGVIfRwxBdc6YwqLSuNnWIjey85VD80DEYNRBY', 'resolutions': [{'height': 56, 'url': 'https://external-preview.redd.it/PJYqBKrEo82c08iCCayMZcnUZ_S20LRkPN0_PsJ56gI.jpg?width=108&crop=smart&auto=webp&s=337350411d064eaaf450caf0e523c3ccc833e999', 'width': 108}, {'height': 113, 'url': 'h... |
i am using A100 80GB GPU now. | 1 | i am using A100 80GB GPU now.
​
thesedays, I heard about A100 80GB GPU will be discontinued. <- is that true?
​
AS I am working at generative AI R&D department , so I have a plan to buy more GPU Like A100 80GB.
​
I already know H100 can be. but my budget is fit for A100 80gb.
​
The ... | 2024-01-29T04:45:12 | https://www.reddit.com/r/LocalLLaMA/comments/1admvxb/i_am_using_a100_80gb_gpu_now/ | aijuud | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 1admvxb | false | null | t3_1admvxb | /r/LocalLLaMA/comments/1admvxb/i_am_using_a100_80gb_gpu_now/ | false | false | self | 1 | null |
EAGLE: Speculative Sampling Requires Rethinking Feature Uncertainty | 20 | 2024-01-29T03:18:11 | https://arxiv.org/abs/2401.15077 | ninjasaid13 | arxiv.org | 1970-01-01T00:00:00 | 0 | {} | 1adl8hy | false | null | t3_1adl8hy | /r/LocalLLaMA/comments/1adl8hy/eagle_speculative_sampling_requires_rethinking/ | false | false | default | 20 | null | |
NIST: AI Risk Management Framework | 7 | Anyone had a chance to read this yet? Imma start the slug tomorrow. Just curious if anything controversial. Can’t wait until I need to be certified on this. | 2024-01-29T02:40:59 | https://www.reddit.com/r/LocalLLaMA/comments/1adkhcx/nist_ai_risk_management_framework/ | imightbsabot | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 1adkhcx | false | null | t3_1adkhcx | /r/LocalLLaMA/comments/1adkhcx/nist_ai_risk_management_framework/ | false | false | self | 7 | null |
Delivery firm's chatbot goes "rogue" LOL | 56 | There never seems to be a day when the news media won't seize upon anything which might appeal to the clueless.
Just now I heard this on the BBC, while driving, how a chatbot had gone 'rogue', having been 'jailbroken'.
DPD delivery (or whatever) has added a chatbot to its service, which I assume is another one of th... | 2024-01-29T02:34:54 | https://www.reddit.com/r/LocalLLaMA/comments/1adkcyd/delivery_firms_chatbot_goes_rogue_lol/ | FPham | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 1adkcyd | false | null | t3_1adkcyd | /r/LocalLLaMA/comments/1adkcyd/delivery_firms_chatbot_goes_rogue_lol/ | false | false | self | 56 | null |
How to test an LLM for dataset contamination? | 2 | Hi, I want to test the DeepSeek Coder models for Deepmind's CodeContests dataset contamination. This is because I recently read the AlphaCodium paper and saw the fantastic performance DeepSeek displayed. However the Codium team mentioned in the repo's readme that they had not run contamination tests on the Deepseek mod... | 2024-01-29T01:45:15 | https://www.reddit.com/r/LocalLLaMA/comments/1adjd7q/how_to_test_an_llm_for_dataset_contamination/ | shmishmouyes | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 1adjd7q | false | null | t3_1adjd7q | /r/LocalLLaMA/comments/1adjd7q/how_to_test_an_llm_for_dataset_contamination/ | false | false | self | 2 | null |
Improved Model: 𝗔𝗿𝗶𝘁𝗵𝗺𝗼𝟮-𝗠𝗶𝘀𝘁𝗿𝗮𝗹-𝟳𝗕 for Mathematical Reasoning | 1 | [removed] | 2024-01-29T01:41:39 | https://www.reddit.com/r/LocalLLaMA/comments/1adjant/improved_model_𝗔𝗿𝗶𝘁𝗵𝗺𝗼𝟮𝗠𝗶𝘀𝘁𝗿𝗮𝗹𝟳𝗕_for_mathematical/ | UglyMonkey17 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 1adjant | false | null | t3_1adjant | /r/LocalLLaMA/comments/1adjant/improved_model_𝗔𝗿𝗶𝘁𝗵𝗺𝗼𝟮𝗠𝗶𝘀𝘁𝗿𝗮𝗹𝟳𝗕_for_mathematical/ | false | false | 1 | {'enabled': False, 'images': [{'id': 'kqU3565WkZoo61UG5kNzAJANNPBIIxJaalnwCpTN4p4', 'resolutions': [{'height': 58, 'url': 'https://external-preview.redd.it/ymOjElP_orx1XVOM-uPX72vx83rv4zCPZm7IMC8Owg4.jpg?width=108&crop=smart&auto=webp&s=f0bfc4c584a0f12b59accdcfbc8db266bd0e20e3', 'width': 108}, {'height': 116, 'url': 'h... | |
Does local Ollama remember all the conversations? | 1 | Does Ollama remember all the conversations? As if I gave the model, like Mixtral, a prompt, does it save it in the memory and use it in the next prompt as a context? | 2024-01-29T00:38:29 | https://www.reddit.com/r/LocalLLaMA/comments/1adi0g0/does_local_ollama_remember_all_the_conversations/ | Intrepid_Influence22 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 1adi0g0 | false | null | t3_1adi0g0 | /r/LocalLLaMA/comments/1adi0g0/does_local_ollama_remember_all_the_conversations/ | false | false | self | 1 | null |
What’s the best way to implement RAG in Crew AI (using local models)? | 11 | I’ve started developing workflows in Crew AI and it seems a lot more intuitive than AutoGen Studio (even though there is more coding involved). Is anyone having success using RAG with Crew AI? If so, what methods / tools are you using to implement it? | 2024-01-29T00:31:11 | https://www.reddit.com/r/LocalLLaMA/comments/1adhv3k/whats_the_best_way_to_implement_rag_in_crew_ai/ | Porespellar | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 1adhv3k | false | null | t3_1adhv3k | /r/LocalLLaMA/comments/1adhv3k/whats_the_best_way_to_implement_rag_in_crew_ai/ | false | false | self | 11 | null |
Best solutions for self hosting throughput oriented llms for research. | 1 | [removed] | 2024-01-29T00:27:03 | https://www.reddit.com/r/LocalLLaMA/comments/1adhs1p/best_solutions_for_self_hosting_throughput/ | Noxusequal | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 1adhs1p | false | null | t3_1adhs1p | /r/LocalLLaMA/comments/1adhs1p/best_solutions_for_self_hosting_throughput/ | false | false | self | 1 | null |
Miqu-1-70B - Mistral Medium, Leaked? Or Distilled? | 1 | [removed] | 2024-01-28T23:43:39 | https://www.reddit.com/r/LocalLLaMA/comments/1adgu92/miqu170b_mistral_medium_leaked_or_distilled/ | someoneonline71 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 1adgu92 | false | null | t3_1adgu92 | /r/LocalLLaMA/comments/1adgu92/miqu170b_mistral_medium_leaked_or_distilled/ | false | false | self | 1 | {'enabled': False, 'images': [{'id': 'YwK0i5uwzktX1nH_8wCb9scLo-p_k7U36rHB1ExOeZo', 'resolutions': [{'height': 58, 'url': 'https://external-preview.redd.it/BQcqnWPMK5Y3U1I8wKe-mQjzHW7J109B4lbTrb7r6sA.jpg?width=108&crop=smart&auto=webp&s=dd5d7f81d68648edfb0c8136135c812f616df207', 'width': 108}, {'height': 116, 'url': 'h... |
The human system prompt | 1 | If the system prompt used for LLM usually is "You are a helpful AI assistant." (or other similar prompts.) What would be the system prompt for the human talking to the LLM? | 2024-01-28T22:13:23 | https://www.reddit.com/r/LocalLLaMA/comments/1adeqa2/the_human_system_prompt/ | Quozul | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 1adeqa2 | false | null | t3_1adeqa2 | /r/LocalLLaMA/comments/1adeqa2/the_human_system_prompt/ | false | false | self | 1 | null |
Guys, how much can i run with this pc? | 2 | I9 - 13900K / RTX 4080/ 64GB DDR5 ... can i run a 70B model locally, with this pc? is it possible in any way? | 2024-01-28T21:53:53 | https://www.reddit.com/r/LocalLLaMA/comments/1ade9m1/guys_how_much_can_i_run_with_this_pc/ | fumetsubi | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 1ade9m1 | false | null | t3_1ade9m1 | /r/LocalLLaMA/comments/1ade9m1/guys_how_much_can_i_run_with_this_pc/ | false | false | self | 2 | null |
PCIe x1 performance | 1 | I have RTX3060 as the main card and want to buy myself P40 or something similar, how much the performance would decrease if I'd use [PCIe x1]->[PCIe x16] riser? | 2024-01-28T21:29:45 | https://www.reddit.com/r/LocalLLaMA/comments/1addoay/pcie_x1_performance/ | Working-Flatworm-531 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 1addoay | false | null | t3_1addoay | /r/LocalLLaMA/comments/1addoay/pcie_x1_performance/ | false | false | self | 1 | null |
What chipset when building a budget pc for LLM? | 2 | The folks at buildapc didn't have much input so asking here since you all would be more familiar where running LLMs is concerned. Building a PC for LLM/stable diffusion/virtual machines. I am more familiar with AMD CPUs and prefer that unless there is any huge reason to go intel.
For multiple GPUs I understand I ... | 2024-01-28T20:49:43 | https://www.reddit.com/r/LocalLLaMA/comments/1adcpaa/what_chipset_when_building_a_budget_pc_for_llm/ | FearFactory2904 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 1adcpaa | false | null | t3_1adcpaa | /r/LocalLLaMA/comments/1adcpaa/what_chipset_when_building_a_budget_pc_for_llm/ | false | false | self | 2 | null |
Node-based prototyping tools for LLMs | 4 | I am working on my personal local assistant as a hobby project. While experimenting with chains and agents I had a thought that it could be faster and easier to prototype if I could connect agents and chains to form a graph composed of appropriate nodes.
With quick googling I discovered Langflow, Promptflow, Flowise ... | 2024-01-28T20:45:48 | https://www.reddit.com/r/LocalLLaMA/comments/1adcly0/nodebased_prototyping_tools_for_llms/ | tyras_ | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 1adcly0 | false | null | t3_1adcly0 | /r/LocalLLaMA/comments/1adcly0/nodebased_prototyping_tools_for_llms/ | false | false | self | 4 | null |
As of about 4 minutes ago, llama.cpp has been released with official Vulkan support. | 290 | 2024-01-28T20:20:03 | https://github.com/ggerganov/llama.cpp/releases/tag/b1996 | fallingdowndizzyvr | github.com | 1970-01-01T00:00:00 | 0 | {} | 1adbzx8 | false | null | t3_1adbzx8 | /r/LocalLLaMA/comments/1adbzx8/as_of_about_4_minutes_ago_llamacpp_has_been/ | false | false | 290 | {'enabled': False, 'images': [{'id': 'xRop3bNLDLRGdsNHZcw1EiD-42i8jQMqRceDqGVy_XQ', 'resolutions': [{'height': 54, 'url': 'https://external-preview.redd.it/iRtE3z1JB7GfMTsep8XDw3m5BGIeYKa_Rr9rxh_58V4.jpg?width=108&crop=smart&auto=webp&s=f0da3a9f522dc63b30e16f442c18ab1e15b425da', 'width': 108}, {'height': 108, 'url': 'h... | ||
Building Unorthodox Deep Learning GPU Machines | eBay Sales Are All You Need | 45 | 2024-01-28T20:05:49 | https://www.kyleboddy.com/2024/01/28/building-deep-learning-machines-unorthodox-gpus/ | kyleboddy | kyleboddy.com | 1970-01-01T00:00:00 | 0 | {} | 1adbo5e | false | null | t3_1adbo5e | /r/LocalLLaMA/comments/1adbo5e/building_unorthodox_deep_learning_gpu_machines/ | false | false | 45 | {'enabled': False, 'images': [{'id': 'TyQg8W9UqoViaOM1-bIemZNIIBWabHBsSK16nzYl3yU', 'resolutions': [{'height': 144, 'url': 'https://external-preview.redd.it/mdBhoTQZAAZBF9393Q8tJWbtwaoiBjU95HZgc1tgTHc.jpg?width=108&crop=smart&auto=webp&s=37933cba20ca0f43db2110e8c807a922ec3087ef', 'width': 108}, {'height': 288, 'url': '... | ||
Can I fine tune Mistral-7B-Instruct-v0.2 in a new language and then use it to summarize text? | 10 | My country is going into general elections soon and, I was thinking if it's possible to use an instruct or chat model to fine tune it in my language and then use it to make summaries of the political parties electoral programs.
​
Thanks in advance! | 2024-01-28T19:35:07 | https://www.reddit.com/r/LocalLLaMA/comments/1adaxpu/can_i_fine_tune_mistral7binstructv02_in_a_new/ | ivoencarnacao | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 1adaxpu | false | null | t3_1adaxpu | /r/LocalLLaMA/comments/1adaxpu/can_i_fine_tune_mistral7binstructv02_in_a_new/ | false | false | self | 10 | null |
When do we expect llama-3 to be trained and released? | 30 | How long do we expect llama-3 to be released? It took 21 days for llama-2 to be trained so do we expect the same for llama-3? | 2024-01-28T19:32:01 | https://www.reddit.com/r/LocalLLaMA/comments/1adav2e/when_do_we_expect_llama3_to_be_trained_and/ | searcher1k | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 1adav2e | false | null | t3_1adav2e | /r/LocalLLaMA/comments/1adav2e/when_do_we_expect_llama3_to_be_trained_and/ | false | false | self | 30 | null |
HackerNews AI built using function calling | 40 | Hi reddit, I built an AI that can interact with the Hacker News API: [https://hn.aidev.run](https://hn.aidev.run)
You can ask questions like:
* Whats on hackernews about AI?
* Whats on hackernews about iPhone?
* What's trending on hackernews?
* What are users showing on hackernews?
* What are users asking on hackerne... | 2024-01-28T19:30:19 | https://www.reddit.com/r/LocalLLaMA/comments/1adatjp/hackernews_ai_built_using_function_calling/ | ashpreetbedi | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 1adatjp | false | null | t3_1adatjp | /r/LocalLLaMA/comments/1adatjp/hackernews_ai_built_using_function_calling/ | false | false | self | 40 | null |
LM studio extension to search in google | 1 | Hi
​
I am considering buidling a LM studio extension to search in the internet using serpAPI, and feed the content in the website to the local LLM installed, but before reinventing the wheel i would like to ask if there is anything already available
Do you know of an existing extension doing this?
​
... | 2024-01-28T18:55:17 | https://www.reddit.com/r/LocalLLaMA/comments/1ad9yez/lm_studio_extension_to_search_in_google/ | javixeneize | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 1ad9yez | false | null | t3_1ad9yez | /r/LocalLLaMA/comments/1ad9yez/lm_studio_extension_to_search_in_google/ | false | false | self | 1 | null |
What is deluxe-chat-1.2 on lmsys? | 3 | I was playing around with lmsys battle arena, and I got a surprisingly good reply from a model called deluxe-chat-1.2.
What's weird is that it doesn't appear on the list of models or on the leaderboard. A google search only finds some twitter posts from people who also came across it and are curious about it.
[One pe... | 2024-01-28T18:47:17 | https://www.reddit.com/r/LocalLLaMA/comments/1ad9rin/what_is_deluxechat12_on_lmsys/ | a_mimsy_borogove | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 1ad9rin | false | null | t3_1ad9rin | /r/LocalLLaMA/comments/1ad9rin/what_is_deluxechat12_on_lmsys/ | false | false | self | 3 | {'enabled': False, 'images': [{'id': 'ltyNBxXMP3SCAeZ98PDx2XgxhbzdcwaiajILugMCPMU', 'resolutions': [{'height': 60, 'url': 'https://external-preview.redd.it/5CrnaOCmaywS63zbPPWwGJj2JFTS_PZOQwjzgNf6bZ0.jpg?width=108&crop=smart&auto=webp&s=30fef23d23c46a8e64b5fe3b0f70ecba6c1dc655', 'width': 108}], 'source': {'height': 78,... |
Changed CFG and inference got really slow. Is this expected? | 1 | [removed] | 2024-01-28T18:45:11 | https://www.reddit.com/r/LocalLLaMA/comments/1ad9plk/changed_cfg_and_inference_got_really_slow_is_this/ | ReallyAI | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 1ad9plk | false | null | t3_1ad9plk | /r/LocalLLaMA/comments/1ad9plk/changed_cfg_and_inference_got_really_slow_is_this/ | false | false | self | 1 | null |
Choice between two mac machines | 1 | see attached screenshots of two machines
1. M3 Max + 128 GB memory
2. M2 Ultra + 192 G memory
Which one is better to run local models?
I guess bigger memory is better. But I am not sure if M3 Max is much faster than M2 Ultra or not. | 2024-01-28T18:44:21 | https://www.reddit.com/gallery/1ad9oxf | Pitiful-You-8410 | reddit.com | 1970-01-01T00:00:00 | 0 | {} | 1ad9oxf | false | null | t3_1ad9oxf | /r/LocalLLaMA/comments/1ad9oxf/choice_between_two_mac_machines/ | false | false | 1 | null | |
What is the best model for programmation only? | 1 | In Python / HTML / CSS / PHP | 2024-01-28T18:30:13 | https://www.reddit.com/r/LocalLLaMA/comments/1ad9ckz/what_is_the_best_model_for_programmation_only/ | clara59000 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 1ad9ckz | false | null | t3_1ad9ckz | /r/LocalLLaMA/comments/1ad9ckz/what_is_the_best_model_for_programmation_only/ | false | false | self | 1 | null |
A Python script to call an llm to batch process documents | 10 | I created a script which works with a local koboldcpp api to do a few batch actions for directories of documents:
1. Parses any HTML and saves the parsed text in a new file
2. Chunks up a text document and feeds it to the koboldcpp api with a prompt added to each chunk, then merges the chunks back and saves that as a ... | 2024-01-28T18:07:45 | https://www.reddit.com/r/LocalLLaMA/comments/1ad8ti1/a_python_script_to_call_an_llm_to_batch_process/ | Eisenstein | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 1ad8ti1 | false | null | t3_1ad8ti1 | /r/LocalLLaMA/comments/1ad8ti1/a_python_script_to_call_an_llm_to_batch_process/ | false | false | self | 10 | {'enabled': False, 'images': [{'id': 'NJEdWWc9BHbOQEVGyJLQrIwoyZ-UDzIsSnqw7a93vaY', 'resolutions': [{'height': 58, 'url': 'https://external-preview.redd.it/vSa82vcTPVRs3AvH45EvSjGEHCDgRkM1dqIOcEGxjX8.jpg?width=108&crop=smart&auto=webp&s=e25018fdfc434e2d27cfaee718b29a8fcf1ec089', 'width': 108}, {'height': 116, 'url': 'h... |
What's the deal with Macbook obsession and LLLM's? | 98 | This is a serious question, an ignition of the very old and very tired "Mac vs PC" battle.
I'm just confused as I lurk on here. I'm using spare PC parts to build a local llm model for the world/game I'm building (learn rules, worldstates, generate planetary systems etc) and I'm ramping up my research and been reading ... | 2024-01-28T17:52:27 | https://www.reddit.com/r/LocalLLaMA/comments/1ad8fsl/whats_the_deal_with_macbook_obsession_and_lllms/ | Syab_of_Caltrops | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 1ad8fsl | false | null | t3_1ad8fsl | /r/LocalLLaMA/comments/1ad8fsl/whats_the_deal_with_macbook_obsession_and_lllms/ | false | false | self | 98 | null |
What is the best local markdown completion model? | 1 | I am referring to models which are not trained for chat, only for completions. | 2024-01-28T17:43:37 | https://www.reddit.com/r/LocalLLaMA/comments/1ad883q/what_is_the_best_local_markdown_completion_model/ | PiggyCheeseburga | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 1ad883q | false | null | t3_1ad883q | /r/LocalLLaMA/comments/1ad883q/what_is_the_best_local_markdown_completion_model/ | false | false | self | 1 | null |
Local Vision Model with Speech to Speech | Faster Whisper + OpenVoice + Moondream(1.6B) | 1 | 2024-01-28T17:31:47 | https://v.redd.it/yb9qmrjsu7fc1 | allaboutai-kris | /r/LocalLLaMA/comments/1ad7xyc/local_vision_model_with_speech_to_speech_faster/ | 1970-01-01T00:00:00 | 0 | {} | 1ad7xyc | false | {'reddit_video': {'bitrate_kbps': 5000, 'dash_url': 'https://v.redd.it/yb9qmrjsu7fc1/DASHPlaylist.mpd?a=1709184712%2CZTNkZjhiNWMzMjk0MjVlM2I0Y2Q2MDRiNmM0ZWVjOGI5MDFmZTU5MmY5MTUyYWQ1YjZlZjRmMGVlZjI0MmRiNA%3D%3D&v=1&f=sd', 'duration': 130, 'fallback_url': 'https://v.redd.it/yb9qmrjsu7fc1/DASH_1080.mp4?source=fallback', '... | t3_1ad7xyc | /r/LocalLLaMA/comments/1ad7xyc/local_vision_model_with_speech_to_speech_faster/ | false | false | 1 | {'enabled': False, 'images': [{'id': 'bXEzanN1dnh1N2ZjMVADGdj4fF_-hWVTX867GMvMOLh3V7nltoyroLtDLBIv', 'resolutions': [{'height': 60, 'url': 'https://external-preview.redd.it/bXEzanN1dnh1N2ZjMVADGdj4fF_-hWVTX867GMvMOLh3V7nltoyroLtDLBIv.png?width=108&crop=smart&format=pjpg&auto=webp&s=f316f8b715bbe38c9ad317022989041e188b7... | ||
Beginner Questions for Text Generation Web UI | 1 | I'm starting to learn more about open source models. Want to get comfortable learning the basics before investing in a GPU. I was able to deploy text generation web ui on an EC2 instance. For my first try, I used the t2 micro (free) size, set the --share flag to true and was able to get the web ui running using the pub... | 2024-01-28T17:08:32 | https://www.reddit.com/r/LocalLLaMA/comments/1ad7e38/beginner_questions_for_text_generation_web_ui/ | _Weesnaw_ | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 1ad7e38 | false | null | t3_1ad7e38 | /r/LocalLLaMA/comments/1ad7e38/beginner_questions_for_text_generation_web_ui/ | false | false | self | 1 | null |
What are some interesting applications of LLMs that are not just a RAG chatbot? | 33 | I am exploring this space and I don't really understand what would be a killer app for LLMs. Like don't get me wrong, I am not discounting its capabilities, but it seems like there isn't any real application for the tech. Like of course I sound uninformed and naive so you don't have to tell me that. I am just looking a... | 2024-01-28T17:04:56 | https://www.reddit.com/r/LocalLLaMA/comments/1ad7b2b/what_are_some_interesting_applications_of_llms/ | Soc13In | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 1ad7b2b | false | null | t3_1ad7b2b | /r/LocalLLaMA/comments/1ad7b2b/what_are_some_interesting_applications_of_llms/ | false | false | self | 33 | null |
Is there a good local implementation of agents? | 6 | I'm using ollama on Mac occasionally and overall it performs well. I'm wondering however if one of those auto-gpt/gpt-agents has already been implemented for it. Giving it ability to run tasks like e. g. research would make it much more useful. I couldn't find anything that works locally though, has anyone seen somethi... | 2024-01-28T17:02:44 | https://www.reddit.com/r/LocalLLaMA/comments/1ad795y/is_there_a_good_local_implementation_of_agents/ | half_a_pony | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 1ad795y | false | null | t3_1ad795y | /r/LocalLLaMA/comments/1ad795y/is_there_a_good_local_implementation_of_agents/ | false | false | self | 6 | null |
How could I make an RPG game system within SillyTavern? | 1 | Not sure if this is the best sub to ask this but so far I've received a lot of help here and I don't know where else to ask so here goes :')
I'm using SillyTavern and I've already set up a bunch of stuff on Lorebooks/World Info to be used by the LLM whenever/if necessary. What I'm trying to do is basically an RPG sort... | 2024-01-28T16:31:39 | https://www.reddit.com/r/LocalLLaMA/comments/1ad6jcb/how_could_i_make_an_rpg_game_system_within/ | OvercookedSatellite | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 1ad6jcb | false | null | t3_1ad6jcb | /r/LocalLLaMA/comments/1ad6jcb/how_could_i_make_an_rpg_game_system_within/ | false | false | self | 1 | null |
What I often mean by "censorship" in corporate-aligned models | 91 | I find many people when being told about censorship, just assume you want NSFW content generated by the AI (which is totally legitimate, by the way). But this is not the main problem about the censorship in 'aligned' models.
Today I was trying to rewrite a certain passage from my novel, trying to give the antagonist a... | 2024-01-28T16:30:37 | https://www.reddit.com/r/LocalLLaMA/comments/1ad6ifk/what_i_often_mean_by_censorship_in/ | CulturedNiichan | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 1ad6ifk | false | null | t3_1ad6ifk | /r/LocalLLaMA/comments/1ad6ifk/what_i_often_mean_by_censorship_in/ | false | false | 91 | null | |
Is there an open source RAG supporting Microsoft SharePoint ? | 1 |
Hi!
I've been testing MS Copilot in M365 specially for RAG apps: asking questions on my SharePoints.
The results are quite good but I'm looking for Opensource solutions to do similar stuff.
I've understood that Copilot relies on the existing SharePoint index (avoid reindexing data) and that the function calls do th... | 2024-01-28T15:49:10 | https://www.reddit.com/r/LocalLLaMA/comments/1ad5k2b/is_there_an_open_source_rag_supporting_microsoft/ | ToothOne6699 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 1ad5k2b | false | null | t3_1ad5k2b | /r/LocalLLaMA/comments/1ad5k2b/is_there_an_open_source_rag_supporting_microsoft/ | false | false | self | 1 | null |
Get all huggingface chat models on a free personal telegram bot assistant. | 13 | GitHub: https://github.com/rabilrbl/hugging-tg-chatbot | 2024-01-28T15:37:37 | https://v.redd.it/h5lqupuja7fc1 | rabilrbl | /r/LocalLLaMA/comments/1ad5asw/get_all_huggingface_chat_models_on_a_free/ | 1970-01-01T00:00:00 | 0 | {} | 1ad5asw | false | {'reddit_video': {'bitrate_kbps': 5000, 'dash_url': 'https://v.redd.it/h5lqupuja7fc1/DASHPlaylist.mpd?a=1709177862%2CMGRmYTgyNWVlZTBiZTY1MzMyNmIyN2RjMWM2ZjBkZTQ2YWZhYzBkMzFhYzlmOWMyMWQ3Y2I2YWE4NjJjNzhhYg%3D%3D&v=1&f=sd', 'duration': 65, 'fallback_url': 'https://v.redd.it/h5lqupuja7fc1/DASH_1080.mp4?source=fallback', 'h... | t3_1ad5asw | /r/LocalLLaMA/comments/1ad5asw/get_all_huggingface_chat_models_on_a_free/ | false | false | 13 | {'enabled': False, 'images': [{'id': 'Mmcya3lob2phN2ZjMQdclTqLAwNGKIyvDVCR1MBQc-DGDVt4c7DBVncbMDy7', 'resolutions': [{'height': 216, 'url': 'https://external-preview.redd.it/Mmcya3lob2phN2ZjMQdclTqLAwNGKIyvDVCR1MBQc-DGDVt4c7DBVncbMDy7.png?width=108&crop=smart&format=pjpg&auto=webp&s=f5c395945dd64db905d29262427aa3cecfc1... | |
AI generated podcast - request for feedback | 1 | Hello, I started a podcast that is all created using AI. On 7th episode now. Though I’m using OpenAI tools right now hoping to get to a fully local open source models as they mature. I would love some feedback. Thank you
https://rss.com/podcasts/aitechweekly/ | 2024-01-28T15:26:39 | https://www.reddit.com/r/LocalLLaMA/comments/1ad51y5/ai_generated_podcast_request_for_feedback/ | manojkr19 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 1ad51y5 | false | null | t3_1ad51y5 | /r/LocalLLaMA/comments/1ad51y5/ai_generated_podcast_request_for_feedback/ | false | false | self | 1 | {'enabled': False, 'images': [{'id': 'pJzM5ybpgMBWYPTT9shdw9Z_u6rrJSzeHNBquqtaoVc', 'resolutions': [{'height': 108, 'url': 'https://external-preview.redd.it/OhBR7xhAq277gV54iAyEdiV6VwIEQ9VBafYfsnvSTrQ.jpg?width=108&crop=smart&auto=webp&s=99b348079528cc328e6a1de914e61f1fe18e732b', 'width': 108}, {'height': 216, 'url': '... |
I want to create a model in GGML but I can't seem to get my head around it | 1 | I was able to create the GGUF file, and I understand its structure. I was also able to somewhat understand the context.
But I can't seem to code the forward graph. I'm having a hard time understanding what buffers to use and why use them and where. I'm also having a hard time understandig all the backend stuff. There... | 2024-01-28T15:21:03 | https://www.reddit.com/r/LocalLLaMA/comments/1ad4xjr/i_want_to_create_a_model_in_ggml_but_i_cant_seem/ | LoLingLikeHell | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 1ad4xjr | false | null | t3_1ad4xjr | /r/LocalLLaMA/comments/1ad4xjr/i_want_to_create_a_model_in_ggml_but_i_cant_seem/ | false | false | self | 1 | null |
Oobabooga webui, Phi-2, and Mistral on Raspberry Pi 5, Orange Pi 5 Plus, and Jetson Orin Nano | 11 | I wanted to see what various SBCs were able to do, especially the Nvidia Jetson Orin Nano. **tl;dr**:
* Raspberry Pi 5 8GB ran [Microsoft Phi-2 Q4_K_M GGUF](https://huggingface.co/TheBloke/phi-2-GGUF) at about 1.2 t/s. [Mistral 7B](https://huggingface.co/TheBloke/Mistral-7B-v0.1-GGUF) ran on it as well, around 0.6 t/s... | 2024-01-28T15:19:26 | https://www.reddit.com/r/LocalLLaMA/comments/1ad4w9i/oobabooga_webui_phi2_and_mistral_on_raspberry_pi/ | SiON42X | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 1ad4w9i | false | null | t3_1ad4w9i | /r/LocalLLaMA/comments/1ad4w9i/oobabooga_webui_phi2_and_mistral_on_raspberry_pi/ | false | false | self | 11 | {'enabled': False, 'images': [{'id': 'eR0VnUWIDQH4dPuIrMpw1vxwSq1qXNOmdkmUnztwXOI', 'resolutions': [{'height': 58, 'url': 'https://external-preview.redd.it/Jv9-Cazyv46Pw6A1JzJkwRMxN_SNBq4nGpUMt6N8_ho.jpg?width=108&crop=smart&auto=webp&s=90fb76fd47ab1d7610d5500cb8f0daa8121be34e', 'width': 108}, {'height': 116, 'url': 'h... |
Realistic performance estimated for upcomming amd strix point and New laptop qualcom chips. | 1 | [removed] | 2024-01-28T15:18:44 | https://www.reddit.com/r/LocalLLaMA/comments/1ad4vqa/realistic_performance_estimated_for_upcomming_amd/ | Noxusequal | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 1ad4vqa | false | null | t3_1ad4vqa | /r/LocalLLaMA/comments/1ad4vqa/realistic_performance_estimated_for_upcomming_amd/ | false | false | self | 1 | {'enabled': False, 'images': [{'id': 'j_azz92L-0OqpjTapcp9oRgczzpcW0bHM8w67Mtz7JI', 'resolutions': [{'height': 54, 'url': 'https://external-preview.redd.it/tVoAKBM9hc1ksnBK2WG5DRJm3cQFQw0jMq_mVHFJFYk.jpg?width=108&crop=smart&auto=webp&s=6e31223589bee0a70dbb18fd1f0d4871040c7083', 'width': 108}, {'height': 108, 'url': 'h... |
Local LLM & STT UE Virtual MetaHuman | 96 | 2024-01-28T15:03:09 | https://v.redd.it/56kwwy7e47fc1 | BoredHobbes | v.redd.it | 1970-01-01T00:00:00 | 0 | {} | 1ad4jmk | false | {'reddit_video': {'bitrate_kbps': 5000, 'dash_url': 'https://v.redd.it/56kwwy7e47fc1/DASHPlaylist.mpd?a=1709046205%2CZWEyNjMwYzAwMDkxMDIxOTU0NWM0NTMyMDJiZWM5NzlkMzIyNjQ3MzBhZmQxNGFkZmQxMTEyZDZhZDM4NDViZQ%3D%3D&v=1&f=sd', 'duration': 63, 'fallback_url': 'https://v.redd.it/56kwwy7e47fc1/DASH_1080.mp4?source=fallback', 'h... | t3_1ad4jmk | /r/LocalLLaMA/comments/1ad4jmk/local_llm_stt_ue_virtual_metahuman/ | false | false | 96 | {'enabled': False, 'images': [{'id': 'aWczZndnYWY0N2ZjMZWxzLg8oMrAczBfwSqnsrQ1tMLmrPx1LlNI92DiWxJr', 'resolutions': [{'height': 60, 'url': 'https://external-preview.redd.it/aWczZndnYWY0N2ZjMZWxzLg8oMrAczBfwSqnsrQ1tMLmrPx1LlNI92DiWxJr.png?width=108&crop=smart&format=pjpg&auto=webp&s=826da944cb5276ba322f9f12c528ffd135358... | ||
Local LLM & STT UE Virtual Metahuman | 1 | [deleted] | 2024-01-28T15:02:06 | [deleted] | 1970-01-01T00:00:00 | 0 | {} | 1ad4iro | false | null | t3_1ad4iro | /r/LocalLLaMA/comments/1ad4iro/local_llm_stt_ue_virtual_metahuman/ | false | false | default | 1 | null | ||
Looking for advice on self hosting services. For a phd which can you recommend? | 1 | [removed] | 2024-01-28T14:49:35 | https://www.reddit.com/r/LocalLLaMA/comments/1ad49bf/looking_for_advice_on_self_hosting_services_for_a/ | Noxusequal | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 1ad49bf | false | null | t3_1ad49bf | /r/LocalLLaMA/comments/1ad49bf/looking_for_advice_on_self_hosting_services_for_a/ | false | false | self | 1 | null |
What does a computer with RTX 4060 Ti 16GB VRAM graphics card do that Macbook Air m2 16GB RAM cannot? | 26 | In terms of localllama. I have intentions to build a pc with 4060 ti 16gb vram but i am struggling to understand what does this computer do that my macbook air cannot.
I just ran mistral instruct v0 2 7B Q4\_K\_S gguf and it ran perfectly fine.
For example can i run 30b models with 16gb vram or 12 gb of vram is enoug... | 2024-01-28T14:41:14 | https://www.reddit.com/r/LocalLLaMA/comments/1ad437c/what_does_a_computer_with_rtx_4060_ti_16gb_vram/ | decept1ve | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 1ad437c | false | null | t3_1ad437c | /r/LocalLLaMA/comments/1ad437c/what_does_a_computer_with_rtx_4060_ti_16gb_vram/ | false | false | self | 26 | null |
Whisper transcription AI running on i3-530 PC | 1 | [removed] | 2024-01-28T14:39:06 | https://www.reddit.com/r/LocalLLaMA/comments/1ad41ly/whisper_transcription_ai_running_on_i3530_pc/ | DaanDeweerdt | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 1ad41ly | false | null | t3_1ad41ly | /r/LocalLLaMA/comments/1ad41ly/whisper_transcription_ai_running_on_i3530_pc/ | false | false | self | 1 | null |
How to run a local AI on AMD GPU with Windows? | 2 | So I was looking to run an LLM for text summarization locally, and all the information I can find is either a couple months old, or only applies to AMD Instinct GPUs. What would be the fastest way to run a decent LLM model that I could call from code (e.g. python)? Is KoboldCPP still the best option now, or is it outda... | 2024-01-28T14:26:12 | https://www.reddit.com/r/LocalLLaMA/comments/1ad3s7y/how_to_run_a_local_ai_on_amd_gpu_with_windows/ | INFINITI2021 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 1ad3s7y | false | null | t3_1ad3s7y | /r/LocalLLaMA/comments/1ad3s7y/how_to_run_a_local_ai_on_amd_gpu_with_windows/ | false | false | self | 2 | null |
Mozilla-Ocho/llamafile AMD GPU error | 2 | I've got a fresh Windows install to run the llamafile. I installed drivers and monthly fixes, Windows itself is 23H2. I download the file from git repository & run as instructed with the parameter -ngl 9999 ... I got below error and it doesn't run. The thing that doesn't make sense to me that there is no nVidia GPU, no... | 2024-01-28T14:25:03 | https://www.reddit.com/r/LocalLLaMA/comments/1ad3rew/mozillaochollamafile_amd_gpu_error/ | Cyric_of_Waterdeep | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 1ad3rew | false | null | t3_1ad3rew | /r/LocalLLaMA/comments/1ad3rew/mozillaochollamafile_amd_gpu_error/ | false | false | self | 2 | null |
Is dolphin mixtral hosted somewhere online? | 2 | I can't run it locally atm. | 2024-01-28T14:22:14 | https://www.reddit.com/r/LocalLLaMA/comments/1ad3phc/is_dolphin_mixtral_hosted_somewhere_online/ | Surellia | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 1ad3phc | false | null | t3_1ad3phc | /r/LocalLLaMA/comments/1ad3phc/is_dolphin_mixtral_hosted_somewhere_online/ | false | false | self | 2 | null |
How to filter important data from weekly reports using LLM? | 1 | [removed] | 2024-01-28T14:12:11 | https://www.reddit.com/r/LocalLLaMA/comments/1ad3ige/how_to_filter_important_data_from_weekly_reports/ | gilklein | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 1ad3ige | false | null | t3_1ad3ige | /r/LocalLLaMA/comments/1ad3ige/how_to_filter_important_data_from_weekly_reports/ | false | false | self | 1 | null |
Best 3b to 13b or better (that fit specs) LLMs for fiction, organizing, writing? | 1 | Hello it’s me once again. Are there any Outstanding models (in the range of 3b to 13b (preferably 7B)) that would be super helpful to creating full on universes and stories, and also organizing it really well, and writing in general?
(Also, uncensored if possible )
Essentially I want to have a “writing assistant/ story... | 2024-01-28T13:38:46 | https://www.reddit.com/r/LocalLLaMA/comments/1ad2uou/best_3b_to_13b_or_better_that_fit_specs_llms_for/ | headbopper96 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 1ad2uou | false | null | t3_1ad2uou | /r/LocalLLaMA/comments/1ad2uou/best_3b_to_13b_or_better_that_fit_specs_llms_for/ | false | false | self | 1 | null |
[Off-topic] Question about GPT1 | 1 | [removed] | 2024-01-28T13:36:05 | https://www.reddit.com/r/LocalLLaMA/comments/1ad2t04/offtopic_question_about_gpt1/ | Invariant_apple | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 1ad2t04 | false | null | t3_1ad2t04 | /r/LocalLLaMA/comments/1ad2t04/offtopic_question_about_gpt1/ | false | false | self | 1 | null |
Looking to hire an AI (Gen AI ) developer as freelancer to refine a RAG chatbot | 1 | Hi, I'm looking for Gen AI freelancer who are good with building chatbots using different APi's.
we already have some working prototype but need expertise to get desired results.
Tech Stack for reference ( we just need AI expert)
Frontend :- Nextjs
Backend :- Flask
Database:- postgres
Deployed On :- Azur... | 2024-01-28T13:12:08 | https://www.reddit.com/r/LocalLLaMA/comments/1ad2d7d/looking_to_hire_an_ai_gen_ai_developer_as/ | SHYAM_12 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 1ad2d7d | false | null | t3_1ad2d7d | /r/LocalLLaMA/comments/1ad2d7d/looking_to_hire_an_ai_gen_ai_developer_as/ | false | false | self | 1 | null |
Is there any git dedicated for text-to-SQL to be inference on local LLM? | 4 | I am trying to find a method to use local LLM for queries and use it for RAG purposes as well as text-to-SQL purposes. LangChain SQL agent doesn’t work well with the local models.. so trying to find if there is any git that can help me solve this issue | 2024-01-28T13:02:25 | https://www.reddit.com/r/LocalLLaMA/comments/1ad26zr/is_there_any_git_dedicated_for_texttosql_to_be/ | Hairy_Tumbleweed1901 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 1ad26zr | false | null | t3_1ad26zr | /r/LocalLLaMA/comments/1ad26zr/is_there_any_git_dedicated_for_texttosql_to_be/ | false | false | self | 4 | null |
Slugsley | 1 | [removed] | 2024-01-28T12:51:43 | https://www.reddit.com/r/LocalLLaMA/comments/1ad2085/slugsley/ | Upset_Acanthaceae_18 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 1ad2085 | false | null | t3_1ad2085 | /r/LocalLLaMA/comments/1ad2085/slugsley/ | false | false | self | 1 | {'enabled': False, 'images': [{'id': '_80YZsz0UFanmlUUNSAOTgbteFgQC5lxwzAlLJPxkKg', 'resolutions': [{'height': 54, 'url': 'https://external-preview.redd.it/NlthozyI4uByI3RzxcVoc4G4B3lboLer2UF1d64WQkQ.jpg?width=108&crop=smart&auto=webp&s=278addc037e6c3f5cec12916f3310e1a74c850f0', 'width': 108}, {'height': 108, 'url': 'h... |
Here is a kaggle notebook to run koboldcpp, enjoy | 6 | 2024-01-28T11:57:17 | https://www.kaggle.com/blutiger/koboldcpp | _BluTiger | kaggle.com | 1970-01-01T00:00:00 | 0 | {} | 1ad143b | false | null | t3_1ad143b | /r/LocalLLaMA/comments/1ad143b/here_is_a_kaggle_notebook_to_run_koboldcpp_enjoy/ | false | false | 6 | {'enabled': False, 'images': [{'id': 'p15coSqe7L8wApjnVlwASEYE50BcnmvRuPbSVpGUPaM', 'resolutions': [{'height': 108, 'url': 'https://external-preview.redd.it/hIZn74UCUzMss02AeqYwTjjr9Q4P0f4_c6SjRwG_mWM.jpg?width=108&crop=smart&auto=webp&s=b0ef6b067fd0b46d01dc9f262edb560782bc9f2c', 'width': 108}], 'source': {'height': 16... | ||
4070 Ti Super as a companion card / VRAM extender alongside a 4090? | 2 | I'd like to buy a second GPU to expand the AI training / inference capabilities of my home computer (currently running a 4090 which I intend to keep) and I've been eyeing the 4070 Ti Super because of its 16 GB VRAM paired with a core that's not as crap as the 4060 Ti. Do you think it's a good idea for a second card?
F... | 2024-01-28T11:50:16 | https://www.reddit.com/r/LocalLLaMA/comments/1ad108o/4070_ti_super_as_a_companion_card_vram_extender/ | b3nsn0w | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 1ad108o | false | null | t3_1ad108o | /r/LocalLLaMA/comments/1ad108o/4070_ti_super_as_a_companion_card_vram_extender/ | false | false | self | 2 | null |
What is GPT's 4 secret sauce ? | 126 | There is still no open source model that comes close to GPT-4 preformance. Why this is ?
Is it the amount of data OpenAI has or the archticture of GPT-4 or the computational resources they have to train large models or a smart training recipe that manage to provide this quality or what ?
And What research ideas do yo... | 2024-01-28T11:45:24 | https://www.reddit.com/r/LocalLLaMA/comments/1ad0xhp/what_is_gpts_4_secret_sauce/ | Puzzleheaded_Mall546 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 1ad0xhp | false | null | t3_1ad0xhp | /r/LocalLLaMA/comments/1ad0xhp/what_is_gpts_4_secret_sauce/ | false | false | self | 126 | null |
Documentation Paradigm for Large Language Models (LLMs): Log Today, Train Tomorrow | 3 |
I have been using tools like GPT-4 and GPT-3.5 a lot for automating things in my daily routine.
Here's something important I've learned: always "document" what you do with these models. By "document," I mean log these requests always and store them somewhere with context.
If you are a programmer, you know ho... | 2024-01-28T11:20:46 | https://www.reddit.com/r/LocalLLaMA/comments/1ad0kdb/documentation_paradigm_for_large_language_models/ | phoneixAdi | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 1ad0kdb | false | null | t3_1ad0kdb | /r/LocalLLaMA/comments/1ad0kdb/documentation_paradigm_for_large_language_models/ | false | false | self | 3 | null |
RWKV5 100% trained & released | 185 | 2024-01-28T11:18:30 | https://twitter.com/BlinkDL_AI/status/1751542433039651304 | cztomsik | twitter.com | 1970-01-01T00:00:00 | 0 | {} | 1ad0j63 | false | {'oembed': {'author_name': 'BlinkDL', 'author_url': 'https://twitter.com/BlinkDL_AI', 'cache_age': 3153600000, 'height': None, 'html': '<blockquote class="twitter-video"><p lang="en" dir="ltr">RWKV-5 "Eagle" 7B: beats Mistral-7B at multilingual, reaches Llama2-7B level at English, while being 100% attention-f... | t3_1ad0j63 | /r/LocalLLaMA/comments/1ad0j63/rwkv5_100_trained_released/ | false | false | 185 | {'enabled': False, 'images': [{'id': 'QOCBpJq8bO6d7dyO8fSS7k8Dh-4gTRL8UBHfQRZuslw', 'resolutions': [{'height': 17, 'url': 'https://external-preview.redd.it/-vvRhyluhyyb-w2h3aefFSbOYWFc2q9vGzgcpKzXgiY.jpg?width=108&crop=smart&auto=webp&s=ac729f141139943ba63bcfbe6cb18fe433979cc8', 'width': 108}], 'source': {'height': 23,... | ||
Advice on PSU for Dual RTX 3090 Setup | 1 | [removed] | 2024-01-28T11:04:44 | https://www.reddit.com/r/LocalLLaMA/comments/1ad0bwp/advice_on_psu_for_dual_rtx_3090_setup/ | Hugejiji | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 1ad0bwp | false | null | t3_1ad0bwp | /r/LocalLLaMA/comments/1ad0bwp/advice_on_psu_for_dual_rtx_3090_setup/ | false | false | self | 1 | null |
Advice on PSU for Dual RTX 3090 Setup | 1 | [removed] | 2024-01-28T11:04:09 | https://www.reddit.com/r/LocalLLaMA/comments/1ad0blk/advice_on_psu_for_dual_rtx_3090_setup/ | Hugejiji | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 1ad0blk | false | null | t3_1ad0blk | /r/LocalLLaMA/comments/1ad0blk/advice_on_psu_for_dual_rtx_3090_setup/ | false | false | self | 1 | null |
What prompts do you use to evaluate new LLM capabilities? | 10 | What prompts do you use to evaluate new LLM capabilities?
Do you have a series of standard prompts you use to see what an LLM can do?
What things have you found the most useful for overall evaluation? | 2024-01-28T10:58:25 | https://www.reddit.com/r/LocalLLaMA/comments/1ad0876/what_prompts_do_you_use_to_evaluate_new_llm/ | Diligent_Eye1248 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 1ad0876 | false | null | t3_1ad0876 | /r/LocalLLaMA/comments/1ad0876/what_prompts_do_you_use_to_evaluate_new_llm/ | false | false | self | 10 | null |
Hello noob here, how do I add charachter to OOGABOOGA API? | 1 | So I have a small AI assistant that uses Oogabooga API (5000). How do I add charachter to the API do I need to do it in my Python code or can I do it in the Oogabooga web UI? | 2024-01-28T10:58:07 | https://www.reddit.com/r/LocalLLaMA/comments/1ad081s/hello_noob_here_how_do_i_add_charachter_to/ | uigofuckmeintheass | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 1ad081s | false | null | t3_1ad081s | /r/LocalLLaMA/comments/1ad081s/hello_noob_here_how_do_i_add_charachter_to/ | false | false | self | 1 | null |
Does Mistral has other language than English? | 4 | I'm using dolphin-2.1-mistral-7b.Q5\_K\_M.gguf for a thesis project. Now I have to use a dataset in my mother tongue (Italian). Can I use it or it should be preferable to use a model fine-tuned for italian language? | 2024-01-28T10:24:19 | https://www.reddit.com/r/LocalLLaMA/comments/1aczq84/does_mistral_has_other_language_than_english/ | giammy677 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 1aczq84 | false | null | t3_1aczq84 | /r/LocalLLaMA/comments/1aczq84/does_mistral_has_other_language_than_english/ | false | false | self | 4 | null |
Together.ai introduces JSON/function calling mode for Mistral.ai LLMs | 17 | You can now use [Mistral.ai](https://Mistral.ai) LLM models with JSON mode and function calling through [together.ai](https://together.ai)'s API: [https://docs.together.ai/docs/function-calling](https://docs.together.ai/docs/function-calling)
So now there are two open-source LLM APIs enabling this (anyscale and [toget... | 2024-01-28T10:21:59 | https://www.reddit.com/r/LocalLLaMA/comments/1aczp2r/togetherai_introduces_jsonfunction_calling_mode/ | rasmus16100 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 1aczp2r | false | null | t3_1aczp2r | /r/LocalLLaMA/comments/1aczp2r/togetherai_introduces_jsonfunction_calling_mode/ | false | false | self | 17 | null |
LLAMA.CPP finetune | 2 |
I'm trying to finetune vicuna model in custom text
the fine tune script:
**./finetune --model-base \~/llama.cpp/models/vicuna-7b-v1.5.Q4\_K\_M.gguf --train-data zam.txt --lora-out lora2.gguf --save-every 0 --threads 14 --ctx 25 --rope-freq-base 10000 --rope-freq-scale 1.0 --batch 1 --grad-acc 1 --adam-iter 64 --a... | 2024-01-28T10:21:54 | https://www.reddit.com/r/LocalLLaMA/comments/1aczp0v/llamacpp_finetune/ | Nervous-Standard-131 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 1aczp0v | false | null | t3_1aczp0v | /r/LocalLLaMA/comments/1aczp0v/llamacpp_finetune/ | false | false | self | 2 | null |
Subsets and Splits
No community queries yet
The top public SQL queries from the community will appear here once available.