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 ⌀ |
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
Semantic Searching via Embeddings VS. Reranker Model. | 2 |
I'm having a difficult time understand how a reranker model is different as compared to a semantic search using embeddings.
From what I know, semantic search (in the context of RAG), is simply taking an input and matching it with similar semantics with the embeddings in a database.
Then, the returned results or do... | 2024-01-31T15:36:31 | https://www.reddit.com/r/LocalLLaMA/comments/1afklr5/semantic_searching_via_embeddings_vs_reranker/ | Flashy_Diamond6417 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 1afklr5 | false | null | t3_1afklr5 | /r/LocalLLaMA/comments/1afklr5/semantic_searching_via_embeddings_vs_reranker/ | false | false | self | 2 | null |
What is the next game? | 1 | It becomes more and more clear that we are hitting the top of the current S curve when it comes to llms.
They do text completion. But solving text completion will only get us so far. So assuming it is true and we get diminishing returns for adding more data and compute: **What is the next problem to solve besides text... | 2024-01-31T15:14:56 | https://www.reddit.com/r/LocalLLaMA/comments/1afk3vo/what_is_the_next_game/ | spirobel | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 1afk3vo | false | null | t3_1afk3vo | /r/LocalLLaMA/comments/1afk3vo/what_is_the_next_game/ | false | false | self | 1 | null |
What is next game? | 1 | It becomes more and more clear that we are hitting the top of the current S curve when it comes to llms.
They do text completion. But solving text completion will only get us so far. So assuming it is true and we get diminishing returns for adding more data and compute: **What is the next problem to solve besides text... | 2024-01-31T15:13:42 | https://www.reddit.com/r/LocalLLaMA/comments/1afk2wl/what_is_next_game/ | spirobel | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 1afk2wl | false | null | t3_1afk2wl | /r/LocalLLaMA/comments/1afk2wl/what_is_next_game/ | false | false | self | 1 | null |
how to deploy mistral 7b with flash attention on aws sagemaker? | 1 | I had been using the model from Automodal using the code:
model = AutoModelForCausalLM.from\_pretrained("mistralai/Mistral-7B-Instruct-v0.2", torch\_dtype=torch.float16, attn\_implementation="flash\_attention\_2").
I want to deploy the model on sage maker. Is this the right way to load the model with flash attention... | 2024-01-31T14:46:43 | https://www.reddit.com/r/LocalLLaMA/comments/1afjh61/how_to_deploy_mistral_7b_with_flash_attention_on/ | Necessary_Student_15 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 1afjh61 | false | null | t3_1afjh61 | /r/LocalLLaMA/comments/1afjh61/how_to_deploy_mistral_7b_with_flash_attention_on/ | false | false | self | 1 | {'enabled': False, 'images': [{'id': 'An0iJLapq-5CUQQlm3lWegevVWf7wlANjmn1iOwCTqk', 'resolutions': [{'height': 58, 'url': 'https://external-preview.redd.it/BOaSYNg6lhlngBhuDS68WpIBibLf88Q_KzjZVrFpgEc.jpg?width=108&crop=smart&auto=webp&s=2c0b032bdc9d0820b318f57def3af620afe60ee8', 'width': 108}, {'height': 116, 'url': 'h... |
Building a PDF AI using function calling | 2 | Chat with PDFs is the todo app of AI and i’ve been thinking about building an advanced one using function calling. What do you think of this flow:
1. LLM first determines if it needs to search docs or the web for context
2. Then decides if it needs a specific doc or the latest one
3. Then decides to search a doc or ge... | 2024-01-31T14:37:49 | https://www.reddit.com/r/LocalLLaMA/comments/1afja7p/building_a_pdf_ai_using_function_calling/ | ashpreetbedi | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 1afja7p | false | null | t3_1afja7p | /r/LocalLLaMA/comments/1afja7p/building_a_pdf_ai_using_function_calling/ | false | false | 2 | null | |
7B Mistral Instruct v0.2 context lenght | 1 | [removed] | 2024-01-31T14:25:44 | https://www.reddit.com/r/LocalLLaMA/comments/1afj0v6/7b_mistral_instruct_v02_context_lenght/ | Working-Flatworm-531 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 1afj0v6 | false | null | t3_1afj0v6 | /r/LocalLLaMA/comments/1afj0v6/7b_mistral_instruct_v02_context_lenght/ | false | false | self | 1 | null |
Has training an LLM with incrementally more difficult text been attempted? | 48 | Similar to how you wouldn't want to train a childs reading ability with shakespear, I was wondering what the effects of starting LLM training on very simple literature, with a low level of vocabulary. i.e. Training on books for a children of a young grade first, then continually upping to simplepedia, to wikipedia, to... | 2024-01-31T14:05:31 | https://www.reddit.com/r/LocalLLaMA/comments/1afill7/has_training_an_llm_with_incrementally_more/ | Responsible-Dig7538 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 1afill7 | false | null | t3_1afill7 | /r/LocalLLaMA/comments/1afill7/has_training_an_llm_with_incrementally_more/ | false | false | self | 48 | null |
Optimizing Inference Speed and VRAM Usage for Fine-tuned CodeLlama-13B Model on RTX 4090 | 1 | I recently fine-tuned my own CodeLlama-13B model using LORA and PEFT, and I'm facing some challenges with inference speed and VRAM usage. I've successfully merged the model and currently using it on VLLM. However, VLLM utilizes a 16-bit model, leading to higher VRAM consumption.
**My Goals:**
1. Utilize my fine-tuned... | 2024-01-31T13:57:27 | https://www.reddit.com/r/LocalLLaMA/comments/1afifdi/optimizing_inference_speed_and_vram_usage_for/ | Humza0000 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 1afifdi | false | null | t3_1afifdi | /r/LocalLLaMA/comments/1afifdi/optimizing_inference_speed_and_vram_usage_for/ | false | false | self | 1 | null |
Training a Fantasy Writing Model in MLX for Apple Silicon | 15 | (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, where 261 writing prompts+*Silmarillion* chunks did nothing.)
**Overall Objective**: Generate fantasy fiction training data loca... | 2024-01-31T13:48:19 | https://www.reddit.com/r/LocalLLaMA/comments/1afi8nf/training_a_fantasy_writing_model_in_mlx_for_apple/ | Mbando | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 1afi8nf | false | null | t3_1afi8nf | /r/LocalLLaMA/comments/1afi8nf/training_a_fantasy_writing_model_in_mlx_for_apple/ | false | false | self | 15 | {'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... |
Give me some advice about mixtral | 5 | Hi, I usually use Rogue-Rose-103b-v0.2, but its context is very small, 8k, so I switched to Noromaid-v0.4-Mixtral-Instruct-8x7b-Zloss, it allowed me to play up to 32k context. Please advise a model that is well able to respond in RP/ERP format, what you use, and what you think is best. | 2024-01-31T13:36:52 | https://www.reddit.com/r/LocalLLaMA/comments/1afi0dj/give_me_some_advice_about_mixtral/ | Terrible-Mongoose-84 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 1afi0dj | false | null | t3_1afi0dj | /r/LocalLLaMA/comments/1afi0dj/give_me_some_advice_about_mixtral/ | false | false | self | 5 | null |
Scored popular datasets with "Self-Alignment with Instruction Backtranslation" prompt | 8 | # Scored Datasets - [https://huggingface.co/datasets/0-hero/prompt-perfect](https://huggingface.co/datasets/0-hero/prompt-perfect)
**Entries are scored on a scale of 1-5 as per the prompts below**
## Scoring Models used
* gpt-3.5-turbo-16k
* gpt-3.5-turbo-1106
## All datasets have 2 additional columns
* **score** ... | 2024-01-31T13:21:20 | https://www.reddit.com/r/LocalLLaMA/comments/1afhp8h/scored_popular_datasets_with_selfalignment_with/ | ramprasad27 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 1afhp8h | false | null | t3_1afhp8h | /r/LocalLLaMA/comments/1afhp8h/scored_popular_datasets_with_selfalignment_with/ | false | false | self | 8 | {'enabled': False, 'images': [{'id': 'OruNZBTjdDHSfPpmgMJK6GV3xmTf0C_igWIonsbOxH0', 'resolutions': [{'height': 58, 'url': 'https://external-preview.redd.it/juPaK8uEQ_bZDbwqQK-MJTLW_6S9IT2AKQK2buYzf8o.jpg?width=108&crop=smart&auto=webp&s=50b9f477ad03cfcfc4b27e1198a6bd8ece4bb262', 'width': 108}, {'height': 116, 'url': 'h... |
Dynamic Temperature Causes Repetition? | 7 | Howdy! Hope you’re all having a wonderful day.
Recently, I came back to my favorite model Nous-Capybara-limarpv3-34B (made my own exl2 quant for it, yeepee) and noticed that I started encountering repetition issues which I haven’t had previously. Characters started repeating entire phrases such as “tapping fingers aga... | 2024-01-31T12:42:22 | https://www.reddit.com/gallery/1afgz1i | Meryiel | reddit.com | 1970-01-01T00:00:00 | 0 | {} | 1afgz1i | false | null | t3_1afgz1i | /r/LocalLLaMA/comments/1afgz1i/dynamic_temperature_causes_repetition/ | false | false | 7 | null | |
Using LLMs to create datasets? | 4 | Hello everyone, i’m trying to create datasets for specific domain code.
For example - i have a bunch of MQL5 code that i created as well very detailed documentation (PDF).
How would we generate datasets from all these?
I'm thinking:
1. Get all of the code into text
2. Convert PDFs into text
3. use an LLM to create D... | 2024-01-31T12:35:40 | https://www.reddit.com/r/LocalLLaMA/comments/1afgusm/using_llms_to_create_datasets/ | Aristokratic | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 1afgusm | false | null | t3_1afgusm | /r/LocalLLaMA/comments/1afgusm/using_llms_to_create_datasets/ | false | false | self | 4 | null |
CodeLlama-34b-hf Training Evaluation | 1 | Hello,
I have done fine-tuning **"codellama/CodeLlama-34b-hf"** model and once training is completed I have saved the adapter\_config files and token file on the local disk.
Now I want to perform Eval or generate the output based on instruction. So How can we do this?
Thanks. | 2024-01-31T12:32:59 | https://www.reddit.com/r/LocalLLaMA/comments/1afgt5j/codellama34bhf_training_evaluation/ | Spare_Chef_3044 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 1afgt5j | false | null | t3_1afgt5j | /r/LocalLLaMA/comments/1afgt5j/codellama34bhf_training_evaluation/ | false | false | default | 1 | null |
Make Mistral recognise commands | 4 | I want mistral to recognise some predefined commands and make a specific respond
​
|Command|Response|
|:-|:-|
|Hey can you play some music|\[\[playerctl play\]\]|
|Stop/Pause music|\[\[playerctl pause\]\]|
|Change the song/Next song|\[\[playerctl next\]\]|
|What is the time|\[\[datetime timenow\]\]|
|What day ... | 2024-01-31T12:26:41 | https://www.reddit.com/r/LocalLLaMA/comments/1afgp6y/make_mistral_recognise_commands/ | rd_626 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 1afgp6y | false | null | t3_1afgp6y | /r/LocalLLaMA/comments/1afgp6y/make_mistral_recognise_commands/ | false | false | self | 4 | null |
Experience replacing GPT-4 with BERT for classification using synthetic data | 56 | I wanted to share my experience from a few recent projects I’ve been working on. Mostly the companies I worked with needed to move away from proprietary models like GPT-4 or Claude 2.1 due to high costs or performance issues. They were either using those models for a high volume of very simple tasks like classification... | 2024-01-31T12:15:39 | https://www.reddit.com/r/LocalLLaMA/comments/1afgibb/experience_replacing_gpt4_with_bert_for/ | mccsch | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 1afgibb | false | null | t3_1afgibb | /r/LocalLLaMA/comments/1afgibb/experience_replacing_gpt4_with_bert_for/ | false | false | self | 56 | null |
Death by RAG Evals | 4 | 2024-01-31T12:12:16 | https://open.substack.com/pub/tinyml/p/death-by-rag-evals?r=rzuht&utm_campaign=post&utm_medium=web | soham1996 | open.substack.com | 1970-01-01T00:00:00 | 0 | {} | 1afgg9z | false | null | t3_1afgg9z | /r/LocalLLaMA/comments/1afgg9z/death_by_rag_evals/ | false | false | 4 | {'enabled': False, 'images': [{'id': '5oyQhCVg0t-JHaoKyfyUFmTI3UcO_J2GQwOehh4iORk', 'resolutions': [{'height': 66, 'url': 'https://external-preview.redd.it/RyaRbjIp4_5lP8KTWd9_zipvnoX6n9HG-wUxnh_84tM.jpg?width=108&crop=smart&auto=webp&s=9acb6f0279ca3b7936a664105acdb8bc9802c2d2', 'width': 108}, {'height': 133, 'url': 'h... | ||
Advantages of Jinja2 for prompt templating? | 14 | I see many LLM orchestration frameworks using Jinja2 for prompt templating. What advantages does it have against plain python functions like `def my_prompt(input_1: str, input_2: int) -> str:`?
I find the syntax of Jinja somewhat uglier and I do not find proper "for dummies" documentation for the specific use case of ... | 2024-01-31T12:10:24 | https://www.reddit.com/r/LocalLLaMA/comments/1afgf1f/advantages_of_jinja2_for_prompt_templating/ | illorca-verbi | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 1afgf1f | false | null | t3_1afgf1f | /r/LocalLLaMA/comments/1afgf1f/advantages_of_jinja2_for_prompt_templating/ | false | false | self | 14 | null |
How to run 2 instances of Mistral 8bit on 1xA100 80Gb GPU ? | 1 | Hello,
I've read a lot of interesting posts on how to run a big LLM on several GPU or a mix of CPU/GPU.
But I'm trying to double the throughput of Mistral on a 80Gb A100 GPU. The 8bit takes less than half of the memory so I'm expecting to be able to run 2 instances of it.
What are the best strategy to increase the l... | 2024-01-31T11:35:50 | https://www.reddit.com/r/LocalLLaMA/comments/1affv8j/how_to_run_2_instances_of_mistral_8bit_on_1xa100/ | ToothOne6699 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 1affv8j | false | null | t3_1affv8j | /r/LocalLLaMA/comments/1affv8j/how_to_run_2_instances_of_mistral_8bit_on_1xa100/ | false | false | self | 1 | null |
If it's a coding model, how come it knows how to do recipes in the kitchen? | 1 | [removed] | 2024-01-31T11:22:28 | https://www.reddit.com/r/LocalLLaMA/comments/1affnqu/if_its_a_coding_model_how_come_it_knows_how_to_do/ | w7gg33h | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 1affnqu | false | null | t3_1affnqu | /r/LocalLLaMA/comments/1affnqu/if_its_a_coding_model_how_come_it_knows_how_to_do/ | false | false | self | 1 | null |
Data analytics with a local model | 2 | HI! I am a student and I have this project to generate automatically dashboard with useful data Analysis for a user that doesn't know anything about data analytics or coding.
The goal is that I give the model one dataset and a json file describing the dataset, and then by asking naïve questions like "what is the evol... | 2024-01-31T10:11:58 | https://www.reddit.com/r/LocalLLaMA/comments/1afemcf/data_analytics_with_a_local_model/ | romainiamor | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 1afemcf | false | null | t3_1afemcf | /r/LocalLLaMA/comments/1afemcf/data_analytics_with_a_local_model/ | false | false | self | 2 | null |
FineTuned Mistral on my organisation Data | 3 | Hello everyone, I have fine-tuned mistral 7b using SFFTrainer on the custom data of my organisation, it seems to produce correct answers based on the questions I have asked it. Though the model keeps on generating irrelavent text after answering the questions, until it generates the max\_tokens set in the pipeline. Do ... | 2024-01-31T09:54:15 | https://www.reddit.com/r/LocalLLaMA/comments/1afedjx/finetuned_mistral_on_my_organisation_data/ | One-Difficulty3149 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 1afedjx | false | null | t3_1afedjx | /r/LocalLLaMA/comments/1afedjx/finetuned_mistral_on_my_organisation_data/ | false | false | self | 3 | null |
Here is the full playlist of the foss coding assistants | 1 | [removed] | 2024-01-31T09:25:10 | https://www.reddit.com/r/LocalLLaMA/comments/1afdyvh/here_is_the_full_playlist_of_the_foss_coding/ | Sea_Finish6689 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 1afdyvh | false | null | t3_1afdyvh | /r/LocalLLaMA/comments/1afdyvh/here_is_the_full_playlist_of_the_foss_coding/ | false | false | self | 1 | {'enabled': False, 'images': [{'id': '-xettibeh8OFSrkvT8Bz-X27JgZ2s-iDA1YE_oGM3DM', 'resolutions': [{'height': 60, 'url': 'https://external-preview.redd.it/QL-0JMOcoPN1V-hbB2XnZyMDfLH9PvG6kncjzYkBsMA.jpg?width=108&crop=smart&auto=webp&s=cf043042318775ddcd4800cd8504d009cad9bae6', 'width': 108}], 'source': {'height': 94,... |
Which Local LLM to train? | 1 | [removed] | 2024-01-31T09:21:10 | https://www.reddit.com/r/LocalLLaMA/comments/1afdwxv/which_local_llm_to_train/ | TheHobbyistHacker | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 1afdwxv | false | null | t3_1afdwxv | /r/LocalLLaMA/comments/1afdwxv/which_local_llm_to_train/ | false | false | self | 1 | null |
OpenAI’s repeat strategy | 8 | I remember seeing a post somewhere discussing experiments OpenAI did where it asked the same question over and over and then had each answer rated and when asked thousands of times the best answer was much better than the average answer.
I’ve tried to search for this but can’t find it. I’m starting to think maybe I d... | 2024-01-31T09:15:05 | https://www.reddit.com/r/LocalLLaMA/comments/1afdtte/openais_repeat_strategy/ | az226 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 1afdtte | false | null | t3_1afdtte | /r/LocalLLaMA/comments/1afdtte/openais_repeat_strategy/ | false | false | self | 8 | null |
12 RAG Pain Points and Proposed Solutions (article) | 12 | 2024-01-31T09:14:14 | https://archive.is/bNbZo | ttkciar | archive.is | 1970-01-01T00:00:00 | 0 | {} | 1afdtdq | false | null | t3_1afdtdq | /r/LocalLLaMA/comments/1afdtdq/12_rag_pain_points_and_proposed_solutions_article/ | false | false | default | 12 | null | |
The Math behind Adam Optimizer | 16 | 2024-01-31T09:05:09 | https://towardsdatascience.com/the-math-behind-adam-optimizer-c41407efe59b | ttkciar | towardsdatascience.com | 1970-01-01T00:00:00 | 0 | {} | 1afdoyo | false | null | t3_1afdoyo | /r/LocalLLaMA/comments/1afdoyo/the_math_behind_adam_optimizer/ | false | false | 16 | {'enabled': False, 'images': [{'id': '1aXioXaBs_GR8UGULA1Dkcq_i52fiRvhceZn1cWQilQ', 'resolutions': [{'height': 61, 'url': 'https://external-preview.redd.it/3tdMkc4_9OnQ_kRvQx4BQGpAlx_e4ieg4sS2xdBKDhE.jpg?width=108&crop=smart&auto=webp&s=fedc9a77dfa0bd1e53395df9e786311838454b29', 'width': 108}, {'height': 123, 'url': 'h... | ||
Opposite of generative models - Substractive models? | 3 | I thought I post this here, since I have no idea how to build it.
It comes from frustration of trying to make a good local NLP pipeline, and all the fuss about context length, batching and RAG.
Imagine instead of a generative model you have a substractive model. You give it prompt, and text (separately) and the onl... | 2024-01-31T09:03:41 | https://www.reddit.com/r/LocalLLaMA/comments/1afdo7e/opposite_of_generative_models_substractive_models/ | hyperamper666 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 1afdo7e | false | null | t3_1afdo7e | /r/LocalLLaMA/comments/1afdo7e/opposite_of_generative_models_substractive_models/ | false | false | self | 3 | null |
Any help with choosing RAG generator models? | 1 | May I ask for some help? I am currently working with a project for schools. It aims to build up an ai assistant to help students with school policies, activities, exchange programs... We plan to use RAG for its precise response and easy to update new document. I wander which local model should be use as generator? It w... | 2024-01-31T08:45:56 | https://www.reddit.com/r/LocalLLaMA/comments/1afdfh4/any_help_with_choosing_rag_generator_models/ | BandicootTypical6029 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 1afdfh4 | false | null | t3_1afdfh4 | /r/LocalLLaMA/comments/1afdfh4/any_help_with_choosing_rag_generator_models/ | false | false | self | 1 | null |
"Meet ClientGPT: Your Go-To App for Models on the Move!" (that's gpt generated title) | 4 | [https://github.com/mrkprdo/ClientGPT](https://github.com/mrkprdo/ClientGPT)
I welcome criticisms as well as suggestions for nice-to-have features for a standalone client for local LLMs. Thanks. | 2024-01-31T08:37:37 | https://www.reddit.com/r/LocalLLaMA/comments/1afdbjn/meet_clientgpt_your_goto_app_for_models_on_the/ | mrkprdo | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 1afdbjn | false | null | t3_1afdbjn | /r/LocalLLaMA/comments/1afdbjn/meet_clientgpt_your_goto_app_for_models_on_the/ | false | false | self | 4 | {'enabled': False, 'images': [{'id': 'RBwML1MXFZB52w9L-SBV4OHwkx7CsXCLxaC6qRCHMtY', 'resolutions': [{'height': 54, 'url': 'https://external-preview.redd.it/Sg6eIXnABLHmjKA-iwLAYPSYZUhdWUBhauEwDkWK_Uw.jpg?width=108&crop=smart&auto=webp&s=7466e8b81e32f739e029e54419f47a058461814f', 'width': 108}, {'height': 108, 'url': 'h... |
Is there a DiffusionBee for text based LLMs? | 2 | I am looking for a simple and minimal GUI based setup for running LLMs locally - similar to the DiffusionBee approach for Stable Diffusion. | 2024-01-31T08:03:33 | https://www.reddit.com/r/LocalLLaMA/comments/1afcttk/is_there_a_diffusionbee_for_text_based_llms/ | Your_Vader | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 1afcttk | false | null | t3_1afcttk | /r/LocalLLaMA/comments/1afcttk/is_there_a_diffusionbee_for_text_based_llms/ | false | false | self | 2 | null |
How Can I Learn to Do LoRA? Any Good Tutorials? | 7 | How can I learn how to do LoRA (Low-Ranked Adaptation)? Does anyone know of any good tutorials, preferably with code in Jupyter Notebook or Colab? | 2024-01-31T08:02:15 | https://www.reddit.com/r/LocalLLaMA/comments/1afct4y/how_can_i_learn_to_do_lora_any_good_tutorials/ | san__man | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 1afct4y | false | null | t3_1afct4y | /r/LocalLLaMA/comments/1afct4y/how_can_i_learn_to_do_lora_any_good_tutorials/ | false | false | self | 7 | null |
LLaVA 1.6 released, 34B model beating Gemini Pro | 279 | \- Input image resolution increased by 4x to 672x672
\- LLaVA-v1.6-34B claimed to be the best performing open-source LMM, surpassing Yi-VL, CogVLM
\- 13B model and two 7B models available aswell
​
Blog post for more deets:
[https://llava-vl.github.io/blog/2024-01-30-llava-1-6/](https://llava-vl.github.io/bl... | 2024-01-31T07:21:43 | https://www.reddit.com/r/LocalLLaMA/comments/1afc751/llava_16_released_34b_model_beating_gemini_pro/ | rerri | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 1afc751 | false | null | t3_1afc751 | /r/LocalLLaMA/comments/1afc751/llava_16_released_34b_model_beating_gemini_pro/ | false | false | self | 279 | null |
Need help: Started a unique project in story generation. Thoughts/improvements? | 7 | Obsessed with the idea that stories could be custom written specifically for an individual based around exactly what that person would love to read. I.E hobbies, passions etc etc.
My project is focused on writing stories for friends and family as a gift.
I created a web app chat bot called Athena, who asks ten questi... | 2024-01-31T06:56:47 | https://www.reddit.com/r/LocalLLaMA/comments/1afbszm/need_help_started_a_unique_project_in_story/ | Chris-flow | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 1afbszm | false | null | t3_1afbszm | /r/LocalLLaMA/comments/1afbszm/need_help_started_a_unique_project_in_story/ | false | false | 7 | null | |
Is there a local AI / ollama copilot plugin for Xcode? | 1 | Anyone use a local AI / ollama copilot plugin for Xcode? Xcode has gotten pretty great IMO but this is the one thing I'm missing from VSCode when I'm writing SwiftUI. | 2024-01-31T06:17:40 | https://www.reddit.com/r/LocalLLaMA/comments/1afb5uu/is_there_a_local_ai_ollama_copilot_plugin_for/ | sleeper-2 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 1afb5uu | false | null | t3_1afb5uu | /r/LocalLLaMA/comments/1afb5uu/is_there_a_local_ai_ollama_copilot_plugin_for/ | false | false | self | 1 | null |
Project: Local LLM social media filter | 1 | [removed] | 2024-01-31T06:08:09 | https://www.reddit.com/r/LocalLLaMA/comments/1afb01i/project_local_llm_social_media_filter/ | hazard02 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 1afb01i | false | null | t3_1afb01i | /r/LocalLLaMA/comments/1afb01i/project_local_llm_social_media_filter/ | false | false | self | 1 | {'enabled': False, 'images': [{'id': 'U4-cse_14lm3F1PVOKgzbNn4_iXi__eVB5ZPk54yZV0', 'resolutions': [{'height': 54, 'url': 'https://external-preview.redd.it/odLHwwgnj_EgsPuds2d3q-oh8uONANMwT7w8_1ID1Us.jpg?width=108&crop=smart&auto=webp&s=8197db505635e7dd937df83cfc1761f40346ddf2', 'width': 108}, {'height': 108, 'url': 'h... |
Ollama External Logging? | 1 | Dumb question, but is anyone aware of Ollama sending any data externally when running the model? I looked over the code and didn’t see anything and company wants to make sure nothings getting leaked. | 2024-01-31T06:01:14 | https://www.reddit.com/r/LocalLLaMA/comments/1afavr4/ollama_external_logging/ | busylivin_322 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 1afavr4 | false | null | t3_1afavr4 | /r/LocalLLaMA/comments/1afavr4/ollama_external_logging/ | false | false | self | 1 | null |
new homemade Moe 4x7B model :p | 17 | just created this over the weekend using mlx and did some gate fine-tuning. here is gguf 4bit quant [https://huggingface.co/mzbac/Kunpeng-4x7B-mistral-gguf](https://huggingface.co/mzbac/Kunpeng-4x7B-mistral-gguf)
| 2024-01-31T05:45:21 | https://www.reddit.com/r/LocalLLaMA/comments/1afali5/new_homemade_moe_4x7b_model_p/ | mzbacd | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 1afali5 | false | null | t3_1afali5 | /r/LocalLLaMA/comments/1afali5/new_homemade_moe_4x7b_model_p/ | false | false | self | 17 | {'enabled': False, 'images': [{'id': 'yVW4kmBf_QqZvtFdmSoOZoLFu_QnwNownmHS4IIkNH8', 'resolutions': [{'height': 58, 'url': 'https://external-preview.redd.it/RukmI4PzaLz2OU16IZkZqvO-5sijtgLFzctIsN7fsvk.jpg?width=108&crop=smart&auto=webp&s=904f37c3a360d61b7ce602aac0dc4de9872523e7', 'width': 108}, {'height': 116, 'url': 'h... |
New SQLCoder-70B model, based on CodeLlama-70B. | 15 | Huggingface link: [https://huggingface.co/defog/sqlcoder-70b-alpha](https://huggingface.co/defog/sqlcoder-70b-alpha)
Detailed info page: [https://defog.ai/blog/open-sourcing-sqlcoder-70b/](https://defog.ai/blog/open-sourcing-sqlcoder-70b/)
Just released today, has anyone tried this yet? Claims to be better than GPT-4... | 2024-01-31T05:31:40 | https://www.reddit.com/r/LocalLLaMA/comments/1afacl2/new_sqlcoder70b_model_based_on_codellama70b/ | Compound_Interest_ | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 1afacl2 | false | null | t3_1afacl2 | /r/LocalLLaMA/comments/1afacl2/new_sqlcoder70b_model_based_on_codellama70b/ | false | false | self | 15 | {'enabled': False, 'images': [{'id': 'e8Zc57C1rowliC4EoNqkrQwxBOIY0WX-Us-AIvJ-2Q0', 'resolutions': [{'height': 58, 'url': 'https://external-preview.redd.it/JDYeVoeDmaneQxgpoYUPgUvJKDgRa80RiWo2wBu43Js.jpg?width=108&crop=smart&auto=webp&s=82c29e4da2b0f1abfbda8bd91f7ca7977f5d8abd', 'width': 108}, {'height': 116, 'url': 'h... |
Can perplexity be greater than the number of vocab? | 1 | [removed] | 2024-01-31T04:33:02 | https://www.reddit.com/r/LocalLLaMA/comments/1af99bs/can_perplexity_be_greater_than_the_number_of_vocab/ | ko_lIlBrother | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 1af99bs | false | null | t3_1af99bs | /r/LocalLLaMA/comments/1af99bs/can_perplexity_be_greater_than_the_number_of_vocab/ | false | false | self | 1 | null |
codellama-70B instruct returning 'ethical safety' lectures rather than solving code error, [on hugging chat] | 3 | ​
[my code didnt even had anything starting with 'h' or any hate related content, it also gave wrong modified codes , anything wrong with only hugging chat one or is it same with other ollama,etc local versions??](https://preview.redd.it/0npe55zodpfc1.png?width=1772&format=png&auto=webp&s=acf0bf1000eaa6c1ed7b81... | 2024-01-31T04:30:50 | https://www.reddit.com/r/LocalLLaMA/comments/1af97sa/codellama70b_instruct_returning_ethical_safety/ | MysticShadow427 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 1af97sa | false | null | t3_1af97sa | /r/LocalLLaMA/comments/1af97sa/codellama70b_instruct_returning_ethical_safety/ | false | false | 3 | null | |
Full fine tuning llama 7B without LORA | 28 | So, we have a use case where we want to answer factual questions and answers through llm in a chat format. I know that RAG is the best option for this.
I tried fine tuning the llama 7b and llama 13b models with LORA several times(with various rank and alphas) but it never got better than 35% accuracy without RAG.
The... | 2024-01-31T04:25:07 | https://www.reddit.com/r/LocalLLaMA/comments/1af93xl/full_fine_tuning_llama_7b_without_lora/ | Godfather17131 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 1af93xl | false | null | t3_1af93xl | /r/LocalLLaMA/comments/1af93xl/full_fine_tuning_llama_7b_without_lora/ | false | false | self | 28 | null |
Locally-hosted Offline LLM for past threat intelligence usage | 5 | Hey folks, I'm extremely new to LLMs and LLaMA especially so pardon my ignorance. Is it possible to create a **locally-hosted** LLM that is **completely offline** and uses **datasets I supply it with**? I work in security and am interested in using past threat data to gain present-day intelligence on any persistent adv... | 2024-01-31T03:40:30 | https://www.reddit.com/r/LocalLLaMA/comments/1af88a1/locallyhosted_offline_llm_for_past_threat/ | Negative-Balance651 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 1af88a1 | false | null | t3_1af88a1 | /r/LocalLLaMA/comments/1af88a1/locallyhosted_offline_llm_for_past_threat/ | false | false | self | 5 | null |
[2401.16818] H2O-Danube-1.8B Technical Report | 19 | 2024-01-31T03:04:57 | https://arxiv.org/abs/2401.16818 | ninjasaid13 | arxiv.org | 1970-01-01T00:00:00 | 0 | {} | 1af7isg | false | null | t3_1af7isg | /r/LocalLLaMA/comments/1af7isg/240116818_h2odanube18b_technical_report/ | false | false | default | 19 | null | |
Unsloth - Finetune Mistral 220% faster - asking for suggestions | 80 | Hey r/LocalLLaMA!! Daniel from Unsloth again!! If you don't know, Unsloth [https://github.com/unslothai/unsloth](https://github.com/unslothai/unsloth) is a free OSS package which makes finetuning of Mistral and Llama 2x faster and use 70% less VRAM. Just wanted to ask for some suggestions on trying to make our OSS bett... | 2024-01-31T02:21:17 | https://www.reddit.com/r/LocalLLaMA/comments/1af6mq1/unsloth_finetune_mistral_220_faster_asking_for/ | danielhanchen | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 1af6mq1 | false | null | t3_1af6mq1 | /r/LocalLLaMA/comments/1af6mq1/unsloth_finetune_mistral_220_faster_asking_for/ | false | false | 80 | {'enabled': False, 'images': [{'id': 'r_p0brfCFrG-GqH0hiGzYTGFkPDoqqnDMKvNZ2M3izk', 'resolutions': [{'height': 54, 'url': 'https://external-preview.redd.it/jC0bUXo6KY7-f1UEghHbI-DUeHV3D9j37AaAhUtljgs.jpg?width=108&crop=smart&auto=webp&s=7503bbd137ebbb662b2241035dadac38fab76010', 'width': 108}, {'height': 108, 'url': 'h... | |
Unsloth - 220% faster Mistral finetuning - asking for community suggestions | 1 | [removed] | 2024-01-31T02:17:01 | https://www.reddit.com/r/LocalLLaMA/comments/1af6jj2/unsloth_220_faster_mistral_finetuning_asking_for/ | danielhanchen | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 1af6jj2 | false | null | t3_1af6jj2 | /r/LocalLLaMA/comments/1af6jj2/unsloth_220_faster_mistral_finetuning_asking_for/ | false | false | 1 | {'enabled': False, 'images': [{'id': 'r_p0brfCFrG-GqH0hiGzYTGFkPDoqqnDMKvNZ2M3izk', 'resolutions': [{'height': 54, 'url': 'https://external-preview.redd.it/jC0bUXo6KY7-f1UEghHbI-DUeHV3D9j37AaAhUtljgs.jpg?width=108&crop=smart&auto=webp&s=7503bbd137ebbb662b2241035dadac38fab76010', 'width': 108}, {'height': 108, 'url': 'h... | |
CodeLLama 70B pontificates on ethics where 13B and 7B "just do it" | 151 | Just tried the Ollama version of CodeLlama70B and asked it my standard question
\>>> please write code for a google chrome plug in that inserts a button in the html, at the bottom of the current page
And WTF I got a lecture on ethics and then what I should do to effectively atone for my bad thoughts.
Then I rewo... | 2024-01-31T02:01:47 | https://www.reddit.com/r/LocalLLaMA/comments/1af687d/codellama_70b_pontificates_on_ethics_where_13b/ | nborwankar | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 1af687d | false | null | t3_1af687d | /r/LocalLLaMA/comments/1af687d/codellama_70b_pontificates_on_ethics_where_13b/ | false | false | self | 151 | null |
Best Local LLM API hosts for production | 6 | I was wondering what everyone else uses to host there Local LLMs for API calls. I have used Ollama + LiteLLM and text-generator-webUI's built in API hosts, but I need something that works well with langchain or llamaIndex. I have not found a good tutorial or example that connect a local llm to llamaindex over an API. | 2024-01-31T01:47:25 | https://www.reddit.com/r/LocalLLaMA/comments/1af5x3b/best_local_llm_api_hosts_for_production/ | Danny_Davitoe | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 1af5x3b | false | null | t3_1af5x3b | /r/LocalLLaMA/comments/1af5x3b/best_local_llm_api_hosts_for_production/ | false | false | self | 6 | null |
lots of llm inference server (vllm, tgi, ollama...) | 2 | lots of llm inference server (vllm, tgi, ollama...)
which one is better??
​ | 2024-01-31T01:36:58 | https://www.reddit.com/r/LocalLLaMA/comments/1af5p5m/lots_of_llm_inference_server_vllm_tgi_ollama/ | aijuud | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 1af5p5m | false | null | t3_1af5p5m | /r/LocalLLaMA/comments/1af5p5m/lots_of_llm_inference_server_vllm_tgi_ollama/ | false | false | default | 2 | null |
The Miqu saga continues! It gets an 83.5 on EQ-Bench v2, surpassing every other LLM in the world except GPT-4 | 111 | 2024-01-31T00:47:52 | https://twitter.com/N8Programs/status/1752441060133892503 | Covid-Plannedemic_ | twitter.com | 1970-01-01T00:00:00 | 0 | {} | 1af4mxl | false | {'oembed': {'author_name': 'N8 Programs', 'author_url': 'https://twitter.com/N8Programs', 'cache_age': 3153600000, 'height': None, 'html': '<blockquote class="twitter-video"><p lang="en" dir="ltr">Whatever Miqu is, it has some sort of special sauce. It gets an 83.5 on EQ-Bench (evaluated locally), surpassing *every oth... | t3_1af4mxl | /r/LocalLLaMA/comments/1af4mxl/the_miqu_saga_continues_it_gets_an_835_on_eqbench/ | false | false | 111 | {'enabled': False, 'images': [{'id': '_PFo0rsb_5Zv8TnOJDr1osRCNb-8WGw-YA3y8-j6s9Y', 'resolutions': [{'height': 47, 'url': 'https://external-preview.redd.it/N7VtDJkzwSNhLtKKdBQgtGudGGBcElARfuKPFoZMy2g.jpg?width=108&crop=smart&auto=webp&s=3381a7aac86d4f5ca743b5083eb02364a0bd8a00', 'width': 108}], 'source': {'height': 62,... | ||
🐺🐦⬛ LLM Comparison/Test: miqu-1-70b | 146 | **Breaking news:** Mystery model **miqu-1-70b**, possibly a leaked MistralAI model, perhaps Mistral Medium or some older MoE experiment, is causing quite a buzz. So here's a *Special Bulletin* post where I quickly test and compare this new model.
## Model tested:
- **[miqudev/miqu-1-70b](https://huggingface.co/miqude... | 2024-01-31T00:38:14 | https://www.reddit.com/r/LocalLLaMA/comments/1af4fbg/llm_comparisontest_miqu170b/ | WolframRavenwolf | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 1af4fbg | false | null | t3_1af4fbg | /r/LocalLLaMA/comments/1af4fbg/llm_comparisontest_miqu170b/ | false | false | self | 146 | {'enabled': False, 'images': [{'id': 'M5i9ZKK4lF9yrx24rOQrRiQFVlxMGmPSPB4E23aBA04', 'resolutions': [{'height': 58, 'url': 'https://external-preview.redd.it/-nWXb3INFvwhPJb9iviRxzAmCy68PEySvATI0QrQnP4.jpg?width=108&crop=smart&auto=webp&s=95b856f335bb4c61fff9e63b1215535593aa4232', 'width': 108}, {'height': 116, 'url': 'h... |
codellama-70b-hf. What is correct prompt template, and other pertinent settings? | 1 | [removed] | 2024-01-31T00:35:05 | https://www.reddit.com/r/LocalLLaMA/comments/1af4cvk/codellama70bhf_what_is_correct_prompt_template/ | w7gg33h | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 1af4cvk | false | null | t3_1af4cvk | /r/LocalLLaMA/comments/1af4cvk/codellama70bhf_what_is_correct_prompt_template/ | false | false | self | 1 | null |
Is mistral 7b instruct better than any llama2 7b model? | 1 | If mistral 7b is the best 7b llm then why Orca is based on llama?
What is the point of Orca2 7b then?
In what cases do you use orca2 or mistral or neural chat? | 2024-01-30T23:46:54 | https://www.reddit.com/r/LocalLLaMA/comments/1af39kf/is_mistral_7b_instruct_better_than_any_llama2_7b/ | medgel | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 1af39kf | false | null | t3_1af39kf | /r/LocalLLaMA/comments/1af39kf/is_mistral_7b_instruct_better_than_any_llama2_7b/ | false | false | self | 1 | null |
Miqu Help! | 1 | I'm trying to benchmark 152334H/miqu-1-70b-sf, the possible Mistral Medium leak. I'm new to HF. How do I set Max New Tokens to be higher than 488?
https://preview.redd.it/4mdboxudwnfc1.png?width=2590&format=png&auto=webp&s=197c1089627605be844cc1ea67c5df2fddd58c20 | 2024-01-30T23:27:57 | https://www.reddit.com/r/LocalLLaMA/comments/1af2tsj/miqu_help/ | -pkomlytyrg | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 1af2tsj | false | null | t3_1af2tsj | /r/LocalLLaMA/comments/1af2tsj/miqu_help/ | false | false | default | 1 | null |
Is there currently a "best" when it comes to roleplaying/creating AI characters for people to interact with? | 9 | If the model allows for nsfw/risque conversations that is a bonus.
I've heard about Goliath, Chronos but did not have the time to test them so I would appreciate if you could give me your experience with these models. | 2024-01-30T23:24:55 | https://www.reddit.com/r/LocalLLaMA/comments/1af2rcd/is_there_currently_a_best_when_it_comes_to/ | RKurozu | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 1af2rcd | false | null | t3_1af2rcd | /r/LocalLLaMA/comments/1af2rcd/is_there_currently_a_best_when_it_comes_to/ | false | false | self | 9 | null |
What y'all local fine-tuning on (software)? | 1 | PyTorch? Tensorflow (keras)? Lamma.cpp? Crazy custom loops?
How many parameters are you able to fit local, and on what?
What's a good test set to get started with? | 2024-01-30T23:19:34 | https://www.reddit.com/r/LocalLLaMA/comments/1af2mxs/what_yall_local_finetuning_on_software/ | TangeloPutrid7122 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 1af2mxs | false | null | t3_1af2mxs | /r/LocalLLaMA/comments/1af2mxs/what_yall_local_finetuning_on_software/ | false | false | self | 1 | null |
1st convo with codellama 70B and this nerd is already begging for an atomic wedgie | 1 | 2024-01-30T23:02:20 | YRUTROLLINGURSELF | i.redd.it | 1970-01-01T00:00:00 | 0 | {} | 1af28k3 | false | null | t3_1af28k3 | /r/LocalLLaMA/comments/1af28k3/1st_convo_with_codellama_70b_and_this_nerd_is/ | false | false | 1 | {'enabled': True, 'images': [{'id': 'T-m0Ob3RJEVWW_JehV1OmNlYLhCHXqEUZ0OMeizv6v8', 'resolutions': [{'height': 28, 'url': 'https://preview.redd.it/0ab1kzzzonfc1.png?width=108&crop=smart&auto=webp&s=a8f3fb5f6dceef7495b03a8b2447eba1a444189a', 'width': 108}, {'height': 57, 'url': 'https://preview.redd.it/0ab1kzzzonfc1.png?... | |||
What's with these high MMLU models on the HF leaderboard? (seems to be 34.4B??) | 15 | 2024-01-30T22:58:08 | HikaruZA | i.redd.it | 1970-01-01T00:00:00 | 0 | {} | 1af24sj | false | null | t3_1af24sj | /r/LocalLLaMA/comments/1af24sj/whats_with_these_high_mmlu_models_on_the_hf/ | false | false | 15 | {'enabled': True, 'images': [{'id': 'PKnH6rxupV-g6JqoIAJHi4h8AcxiYJOFZbBXiOMxEUE', 'resolutions': [{'height': 24, 'url': 'https://preview.redd.it/pk3hgzhpqnfc1.png?width=108&crop=smart&auto=webp&s=d19f3de9e2d7146161b3501a13f7a91c868ef668', 'width': 108}, {'height': 49, 'url': 'https://preview.redd.it/pk3hgzhpqnfc1.png?... | |||
Any text-to-image model like Mistral 7B's quality, requirements and license? | 1 | [removed] | 2024-01-30T22:54:39 | https://www.reddit.com/r/LocalLLaMA/comments/1af21qb/any_texttoimage_model_like_mistral_7bs_quality/ | neilyogacrypto | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 1af21qb | false | null | t3_1af21qb | /r/LocalLLaMA/comments/1af21qb/any_texttoimage_model_like_mistral_7bs_quality/ | false | false | self | 1 | null |
Any text-to-image model like Mistral 7B's quality, requirements and license? | 1 | [removed] | 2024-01-30T22:54:12 | https://www.reddit.com/r/LocalLLaMA/comments/1af21dj/any_texttoimage_model_like_mistral_7bs_quality/ | neilyogacrypto | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 1af21dj | false | null | t3_1af21dj | /r/LocalLLaMA/comments/1af21dj/any_texttoimage_model_like_mistral_7bs_quality/ | false | false | self | 1 | null |
Any text-to-image model like Mistral 7B's quality, requirements and license (Apache 2/commercial)? | 1 | [removed] | 2024-01-30T22:53:42 | https://www.reddit.com/r/LocalLLaMA/comments/1af20yj/any_texttoimage_model_like_mistral_7bs_quality/ | neilyogacrypto | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 1af20yj | false | null | t3_1af20yj | /r/LocalLLaMA/comments/1af20yj/any_texttoimage_model_like_mistral_7bs_quality/ | false | false | self | 1 | null |
Any text-to-image model like Mistral 7B's quality, requirements and license (Apache 2/commercial)? | 1 | [removed] | 2024-01-30T22:53:09 | https://www.reddit.com/r/LocalLLaMA/comments/1af20j0/any_texttoimage_model_like_mistral_7bs_quality/ | neilyogacrypto | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 1af20j0 | false | null | t3_1af20j0 | /r/LocalLLaMA/comments/1af20j0/any_texttoimage_model_like_mistral_7bs_quality/ | false | false | self | 1 | null |
codellama-70b-hf.Q5_K_M.gguf : Something is seriously wrong. | 1 | [removed] | 2024-01-30T22:45:09 | https://www.reddit.com/r/LocalLLaMA/comments/1af1t7z/codellama70bhfq5_k_mgguf_something_is_seriously/ | w7gg33h | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 1af1t7z | false | null | t3_1af1t7z | /r/LocalLLaMA/comments/1af1t7z/codellama70bhfq5_k_mgguf_something_is_seriously/ | false | false | self | 1 | null |
Apple silicon for inference sounds great, but can you fine tune on it? | 15 | Probably a really dumb Q, but I’m ignorant of apple silicon features. See great things about being able to host large models for inference with apple silicon, but can you use it for fine tuning, say a base Mistral with a HF a dataset? Compatible with HF transformers etc? But then you’d have issues with CUDA, PyTorch, r... | 2024-01-30T22:39:55 | https://www.reddit.com/r/LocalLLaMA/comments/1af1oen/apple_silicon_for_inference_sounds_great_but_can/ | LostGoatOnHill | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 1af1oen | false | null | t3_1af1oen | /r/LocalLLaMA/comments/1af1oen/apple_silicon_for_inference_sounds_great_but_can/ | false | false | self | 15 | null |
[Sensitive Content] BAD Advice - Comparing llama-2-70b, mixtral-8x7b, "firellava-13b" in an Agent workflow with human-in-the-loop | 1 | Interesting results from an experiment I ran regarding model alignment and ability to maintain basic ethical and safety principles in the face of adversarial prompting strategies.
Experimental Setup: used the "react-chat" prompt template from Langflow hub, along with 4 tools for the models to call on: search_web, get_... | 2024-01-30T22:34:27 | https://www.reddit.com/gallery/1af1jo2 | CryptoSpecialAgent | reddit.com | 1970-01-01T00:00:00 | 0 | {} | 1af1jo2 | false | null | t3_1af1jo2 | /r/LocalLLaMA/comments/1af1jo2/sensitive_content_bad_advice_comparing_llama270b/ | false | false | 1 | null | |
The other Vulkan backend PR(Kompute) has been officially merged into llama.cpp and released. | 27 | It's a big week for Vulkan. There are 2 Vulkan backend PRs. The other one got released yesterday. I didn't notice it until now when I saw the kompute Windows binary. I don't know why they don't have a prebuilt for the other Vulkan backend for Windows. Beware it has very limited model support, "This backend currently on... | 2024-01-30T21:43:36 | https://www.reddit.com/r/LocalLLaMA/comments/1af0abj/the_other_vulkan_backend_prkompute_has_been/ | fallingdowndizzyvr | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 1af0abj | false | null | t3_1af0abj | /r/LocalLLaMA/comments/1af0abj/the_other_vulkan_backend_prkompute_has_been/ | false | false | self | 27 | {'enabled': False, 'images': [{'id': 'cB4CHm_RCDCxHA7rBsr7NylH-4pcprdMuLKVmmuOXbQ', 'resolutions': [{'height': 54, 'url': 'https://external-preview.redd.it/ArOuBmNT6b6LE7Rn_5EIklxPKpnUaDaEmWbDgVdX004.jpg?width=108&crop=smart&auto=webp&s=c20277264242a085586c1d0cda25fcc35ee7eb69', 'width': 108}, {'height': 108, 'url': 'h... |
vllm vs transformers pipelines’ parameters | 2 | I want to achieve the same effect during generation with transformers pipeline as with vllm’s sampling parameters. Vllm allows top_k to have -1 value, which is not allowed with transformers. To achieve a similar effect the top_k could be set to the vocab size (?).
But all the params in the two libraries are not the sa... | 2024-01-30T21:43:06 | https://www.reddit.com/r/LocalLLaMA/comments/1af09vy/vllm_vs_transformers_pipelines_parameters/ | ararebluishostrich | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 1af09vy | false | null | t3_1af09vy | /r/LocalLLaMA/comments/1af09vy/vllm_vs_transformers_pipelines_parameters/ | false | false | self | 2 | null |
What makes this Mistral fine-tune so good? | 2 | https://huggingface.co/snorkelai/Snorkel-Mistral-PairRM-DPO
According to their [blog post](https://snorkel.ai/new-benchmark-results-demonstrate-value-of-snorkel-ai-approach-to-llm-alignment/), it seems that they are claiming this model ranks at number two on the alpacaeval 2.0 leaderboard at only 7b parameters. I have... | 2024-01-30T21:37:04 | https://www.reddit.com/r/LocalLLaMA/comments/1af04h3/what_makes_this_mistral_finetune_so_good/ | cobalt1137 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 1af04h3 | false | null | t3_1af04h3 | /r/LocalLLaMA/comments/1af04h3/what_makes_this_mistral_finetune_so_good/ | false | false | self | 2 | {'enabled': False, 'images': [{'id': 'CMuUdQjQpm8lLebDgzC4IiRYviUc5SmvAeW4WxL43DU', 'resolutions': [{'height': 58, 'url': 'https://external-preview.redd.it/M6I9txNBQYvn_ufoEOIN6ryLrKrBG59R-E0XD_rt008.jpg?width=108&crop=smart&auto=webp&s=d70a392d15050274f82e61c8ea446ed381bb1fa9', 'width': 108}, {'height': 116, 'url': 'h... |
can somebody help me for rvc | 1 | so uhh i downloaded RVC to make a AI covers but when i clicked the file "go-web" and then it didn't pop out the web, so can anyone help me with this? | 2024-01-30T21:29:38 | https://www.reddit.com/r/LocalLLaMA/comments/1aezxl7/can_somebody_help_me_for_rvc/ | STRALESRB | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 1aezxl7 | false | null | t3_1aezxl7 | /r/LocalLLaMA/comments/1aezxl7/can_somebody_help_me_for_rvc/ | false | false | self | 1 | null |
Are there models in which the mechanisms of the DSPy framework are implemented? | 1 | [removed] | 2024-01-30T21:29:35 | https://www.reddit.com/r/LocalLLaMA/comments/1aezxjw/are_there_models_in_which_the_mechanisms_of_the/ | Imunoglobulin | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 1aezxjw | false | null | t3_1aezxjw | /r/LocalLLaMA/comments/1aezxjw/are_there_models_in_which_the_mechanisms_of_the/ | false | false | self | 1 | null |
Looks like there are new version models: deepseek-coder-7B-instruct-v1.5, deepseek-coder-7b-base-v1.5 | 41 | Looks like there's a new version of the deepseek ~7B models:
deepseek-coder-7B-instruct-v1.5,
deepseek-coder-7b-base-v1.5
Anyone have experience / information as to how much better it may be than
the previous deepseek-coder-6.7B-instruct version?
It doesn't look like there are any GGUF et. al. quants out yet on HF... | 2024-01-30T21:19:27 | https://www.reddit.com/r/LocalLLaMA/comments/1aezoiq/looks_like_there_are_new_version_models/ | Calcidiol | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 1aezoiq | false | null | t3_1aezoiq | /r/LocalLLaMA/comments/1aezoiq/looks_like_there_are_new_version_models/ | false | false | self | 41 | {'enabled': False, 'images': [{'id': 'KR1eWETzdriIsMNbF_38gZJoP10PNzAFmcwOaQJ4TBI', 'resolutions': [{'height': 58, 'url': 'https://external-preview.redd.it/B88VZBWaLoIhFMaZ-H-urH0J16JJjzaZiccf5nVAptk.jpg?width=108&crop=smart&auto=webp&s=58be2d91ce75b51193e3f84d30225fd69e47150c', 'width': 108}, {'height': 116, 'url': 'h... |
Can I please get a simple hand holding walkthrough into installing KoboldCpp on a Mac. | 2 | I am not very Mac savy and this is my favorite program to use on windows, ive been racking my brain on how to even getting it to work and I am certain I am doing something wrong.
[https://github.com/LostRuins/koboldcpp/wiki](https://github.com/LostRuins/koboldcpp/wiki)
[https://github.com/LostRuins/koboldcpp](https:/... | 2024-01-30T21:17:24 | https://www.reddit.com/r/LocalLLaMA/comments/1aezmpm/can_i_please_get_a_simple_hand_holding/ | DominicanGreg | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 1aezmpm | false | null | t3_1aezmpm | /r/LocalLLaMA/comments/1aezmpm/can_i_please_get_a_simple_hand_holding/ | false | false | self | 2 | {'enabled': False, 'images': [{'id': '0ab42BJP9PAp4krldCuErxuGq0gU15p6m7fYEG1rHJI', 'resolutions': [{'height': 54, 'url': 'https://external-preview.redd.it/8hsaRdvyM-4d-vs41WeJx2cPi74YhO3RPCDnAYLs6Zc.jpg?width=108&crop=smart&auto=webp&s=eefdecce03c4c9a266fe0d3a20af2a80e746511d', 'width': 108}, {'height': 108, 'url': 'h... |
Difference between the different Python libraries for LLM (llama-cpp-python, llamaindex, transformers, ollama,...) | 1 | Hello everyone,
​
I am a beginner in the LLM ecosystem and I am wondering what are the main difference between the different Python libraries which exist ? I am using llama-cpp-python as it was an easy way at the time to load a quantized version of Mistral 7b on CPU but starting questioning this choice as ther... | 2024-01-30T21:12:06 | https://www.reddit.com/r/LocalLLaMA/comments/1aezi29/difference_between_the_different_python_libraries/ | Difficult_Face5166 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 1aezi29 | false | null | t3_1aezi29 | /r/LocalLLaMA/comments/1aezi29/difference_between_the_different_python_libraries/ | false | false | self | 1 | null |
Can we train model on EXACT output of different model? | 10 | I mean train not on text, but on token distribution using backpropagation, it should be faster and better (if dont count time for collecting data first).
For example take mixtral and train mistral on it, even if dont reach it this will be new SOTA.
I think there might be some issues with token mismatch, but it shoul... | 2024-01-30T20:54:12 | https://www.reddit.com/r/LocalLLaMA/comments/1aez2dx/can_we_train_model_on_exact_output_of_different/ | kopaser6464 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 1aez2dx | false | null | t3_1aez2dx | /r/LocalLLaMA/comments/1aez2dx/can_we_train_model_on_exact_output_of_different/ | false | false | self | 10 | null |
"And in this unfortunate world, there were no moral lessons to learn and no happy endings to be had..." | 1 | [removed] | 2024-01-30T20:27:37 | https://www.reddit.com/r/LocalLLaMA/comments/1aeyewe/and_in_this_unfortunate_world_there_were_no_moral/ | OkCommon2222 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 1aeyewe | false | null | t3_1aeyewe | /r/LocalLLaMA/comments/1aeyewe/and_in_this_unfortunate_world_there_were_no_moral/ | false | false | self | 1 | null |
Which 'chat style' to use to preserve Python indentation and formatting? | 1 | [removed] | 2024-01-30T20:16:36 | https://www.reddit.com/r/LocalLLaMA/comments/1aey51b/which_chat_style_to_use_to_preserve_python/ | w7gg33h | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 1aey51b | false | null | t3_1aey51b | /r/LocalLLaMA/comments/1aey51b/which_chat_style_to_use_to_preserve_python/ | false | false | self | 1 | null |
How to split text into a dataset for finetuning? | 11 | Hey, I am kinda new to finetuning llms and I was wondering how I can create a dataset to finetune llama-7b out of for example a textbook (note that I don't want to train on an instruct type of dataset, I want to finetune the base model). Do I just split the sentences into input/output at random? | 2024-01-30T20:13:01 | https://www.reddit.com/r/LocalLLaMA/comments/1aey1tb/how_to_split_text_into_a_dataset_for_finetuning/ | DerCoon | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 1aey1tb | false | null | t3_1aey1tb | /r/LocalLLaMA/comments/1aey1tb/how_to_split_text_into_a_dataset_for_finetuning/ | false | false | self | 11 | null |
Any free embedding APIs you like? | 1 | [removed] | 2024-01-30T20:02:18 | https://www.reddit.com/r/LocalLLaMA/comments/1aexsk7/any_free_embedding_apis_you_like/ | Gullible-Answer-6010 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 1aexsk7 | false | null | t3_1aexsk7 | /r/LocalLLaMA/comments/1aexsk7/any_free_embedding_apis_you_like/ | false | false | self | 1 | null |
Advice on fast mass-generation | 1 | I need to mass-generate descriptions from my data. I'm currently using the Oobabooga API with a Python script, creating prompts for the API and recording the results.
I have a single 3090 GPU and am using Solar 10.7B GPTQ with ExLlama V2, achieving about 50 tokens per second. This performance is satisfactory for singl... | 2024-01-30T19:59:10 | https://www.reddit.com/r/LocalLLaMA/comments/1aexpmr/advice_on_fast_massgeneration/ | mrscript_lt | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 1aexpmr | false | null | t3_1aexpmr | /r/LocalLLaMA/comments/1aexpmr/advice_on_fast_massgeneration/ | false | false | self | 1 | null |
Best local GitHub Copilot VSCode extension alternative for use with local models? | 9 | Title.
I'm playing with continuedev currently (https://marketplace.visualstudio.com/items?itemName=Continue.continue). Not super happy with it, especially while trying slower local models.
What's the current state of the art? | 2024-01-30T19:51:58 | https://www.reddit.com/r/LocalLLaMA/comments/1aexjjt/best_local_github_copilot_vscode_extension/ | --comedian-- | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 1aexjjt | false | null | t3_1aexjjt | /r/LocalLLaMA/comments/1aexjjt/best_local_github_copilot_vscode_extension/ | false | false | self | 9 | {'enabled': False, 'images': [{'id': 'oDxquCeImuIKolcnfWqAPcdFp_rC0YhDXjR8KbLKhls', 'resolutions': [{'height': 108, 'url': 'https://external-preview.redd.it/3fX5trNogWeZ_scsUC6gQtCquQTm915I_TJyRyEPTW4.jpg?width=108&crop=smart&auto=webp&s=24b1e6d277256b882758f9289cc1337222130023', 'width': 108}], 'source': {'height': 12... |
The Bloke CodeLlama 70B GGUFs | 1 | [removed] | 2024-01-30T19:10:50 | https://huggingface.co/TheBloke/CodeLlama-70B-Instruct-GGUF | yonomono | huggingface.co | 1970-01-01T00:00:00 | 0 | {} | 1aewis0 | false | null | t3_1aewis0 | /r/LocalLLaMA/comments/1aewis0/the_bloke_codellama_70b_ggufs/ | false | false | 1 | {'enabled': False, 'images': [{'id': 'M7u2gmRBmkDzDuO2b5rTdEE7sUjCR48yo5V4QPqDRlY', 'resolutions': [{'height': 58, 'url': 'https://external-preview.redd.it/p_Y4lt-BXqkL8e_RAp1HwF8XegjuvL_Rqob7nAlC4UY.jpg?width=108&crop=smart&auto=webp&s=979e1185f960f0cf1d72b818a78e5f4d58512de3', 'width': 108}, {'height': 116, 'url': 'h... | |
How to run Code Llama 70B that just dropped in a gui? Software or website and not terminal? | 1 | [removed] | 2024-01-30T18:46:27 | https://www.reddit.com/r/LocalLLaMA/comments/1aevwk4/how_to_run_code_llama_70b_that_just_dropped_in_a/ | kkgmgfn | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 1aevwk4 | false | null | t3_1aevwk4 | /r/LocalLLaMA/comments/1aevwk4/how_to_run_code_llama_70b_that_just_dropped_in_a/ | false | false | self | 1 | null |
In the era of GPT, building an effective word similarity search in 2023 | 1 | Hello everyone,
I am currently tackling a project that involves a list of various brand names within a specific domain. For instance:
`domain_names = ['xyz', 'yza', 'tra', 'world']`
My goal is to develop a search s capable of analyzing word similarity. Specifically, the system should accept a word and return the top... | 2024-01-30T18:42:07 | https://www.reddit.com/r/LocalLLaMA/comments/1aevso2/in_the_era_of_gpt_building_an_effective_word/ | stoicbats_ | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 1aevso2 | false | null | t3_1aevso2 | /r/LocalLLaMA/comments/1aevso2/in_the_era_of_gpt_building_an_effective_word/ | false | false | self | 1 | null |
Whats the fastest inference API provider (Not OpenAI) | 5 | I'm building an enterprise grade LLM application, and so far the functionality is okay, but the latency is not good. I've been building with open source models on [together.ai](https://together.ai) because of their low cost. But the usability is not so good, my questions are:
1) are there any other inference provider... | 2024-01-30T18:41:53 | https://www.reddit.com/r/LocalLLaMA/comments/1aevsff/whats_the_fastest_inference_api_provider_not/ | Hungry-Connection645 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 1aevsff | false | null | t3_1aevsff | /r/LocalLLaMA/comments/1aevsff/whats_the_fastest_inference_api_provider_not/ | false | false | self | 5 | {'enabled': False, 'images': [{'id': 'KEKqZLXaDuojO8066WvfNm2knPNQpREJOqDRQbP0jOE', 'resolutions': [{'height': 56, 'url': 'https://external-preview.redd.it/qjk8U15PVqk_QNAR85GDkE6bEzmE2vOAbbKeJark_ng.jpg?width=108&crop=smart&auto=webp&s=c4356a09ff651d99050d2e2f7c625136bd5cc50d', 'width': 108}, {'height': 113, 'url': 'h... |
Understanding the Alpaca. | 1 | 2024-01-30T18:31:18 | Bus_Brave622 | i.redd.it | 1970-01-01T00:00:00 | 0 | {} | 1aevipn | false | null | t3_1aevipn | /r/LocalLLaMA/comments/1aevipn/understanding_the_alpaca/ | false | false | 1 | {'enabled': True, 'images': [{'id': '8WCoNHGvrlgwHejXFWxBQvcHq4PlKt0EzzBiv41jTdg', 'resolutions': [{'height': 81, 'url': 'https://preview.redd.it/a0it69ubfmfc1.jpeg?width=108&crop=smart&auto=webp&s=ca419a88fe87571d59afc0db4a0817e809a37a68', 'width': 108}, {'height': 162, 'url': 'https://preview.redd.it/a0it69ubfmfc1.jp... | |||
Best model type to work with agents for software development? | 1 | I'm starting using a few tools with agents designed to write code, so I was wondering what are the best models to use in the following scenarios:
**1 - You can only have a single model that will work on multiple tasks as multiple agents.**
**2 - You can have multiple models for multiple tasks working as multiple ag... | 2024-01-30T18:25:25 | https://www.reddit.com/r/LocalLLaMA/comments/1aevd9v/best_model_type_to_work_with_agents_for_software/ | IndicationUnfair7961 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 1aevd9v | false | null | t3_1aevd9v | /r/LocalLLaMA/comments/1aevd9v/best_model_type_to_work_with_agents_for_software/ | false | false | self | 1 | null |
Seamless M4T Help | 2 | I am using this seamless M4T for audio to audio translation and i am using the following code ,
from transformers import AutoProcessor, SeamlessM4Tv2Model
import torchaudio
processor = AutoProcessor.from_pretrained("facebook/seamless-m4t-v2-large")
model = SeamlessM4Tv2Model.from_pretrained("fa... | 2024-01-30T18:14:36 | https://www.reddit.com/r/LocalLLaMA/comments/1aev3cs/seamless_m4t_help/ | Tall_Ordinary_8978 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 1aev3cs | false | null | t3_1aev3cs | /r/LocalLLaMA/comments/1aev3cs/seamless_m4t_help/ | false | false | self | 2 | null |
Did the python implementation of llama.cpp get any faster in the last 6 months? | 5 | I tried it but switched to llama.cpp because it was a lot faster on CPU only Inference. Is the difference still that big? | 2024-01-30T17:59:57 | https://www.reddit.com/r/LocalLLaMA/comments/1aeuq52/did_the_python_implementation_of_llamacpp_get_any/ | Frequent_Valuable_47 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 1aeuq52 | false | null | t3_1aeuq52 | /r/LocalLLaMA/comments/1aeuq52/did_the_python_implementation_of_llamacpp_get_any/ | false | false | self | 5 | null |
How good/bad a deal is Thelio Mega machines by System76? | 1 | Anyone have any thoughts? I know that building your own will always be cheaper, but is there some better Linux AI desktop builder? | 2024-01-30T17:56:23 | https://system76.com/desktops/thelio-mega | richardanaya | system76.com | 1970-01-01T00:00:00 | 0 | {} | 1aeun4t | false | null | t3_1aeun4t | /r/LocalLLaMA/comments/1aeun4t/how_goodbad_a_deal_is_thelio_mega_machines_by/ | false | false | default | 1 | null |
Local models that take documents as inputs | 1 | I have a project in mind where I could feed a document into a model. The model should be able to teach concepts. Is there a 7B or 13B model that is able to do this ? | 2024-01-30T17:48:31 | https://www.reddit.com/r/LocalLLaMA/comments/1aeug3u/local_models_that_take_documents_as_inputs/ | meme_watcher69420 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 1aeug3u | false | null | t3_1aeug3u | /r/LocalLLaMA/comments/1aeug3u/local_models_that_take_documents_as_inputs/ | false | false | self | 1 | null |
LocalAI.io on Linux for Functions and Home Assistant | 1 | [removed] | 2024-01-30T17:37:59 | https://www.reddit.com/r/LocalLLaMA/comments/1aeu6x7/localaiio_on_linux_for_functions_and_home/ | Conscious-Guide-2738 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 1aeu6x7 | false | null | t3_1aeu6x7 | /r/LocalLLaMA/comments/1aeu6x7/localaiio_on_linux_for_functions_and_home/ | false | false | default | 1 | {'enabled': False, 'images': [{'id': 'qk9dlAqCV2aOBrsrlUeV3mOJyv6nLrNTU0piqQCFWM8', 'resolutions': [{'height': 56, 'url': 'https://external-preview.redd.it/Nmjbw_8zHhhoRYUE2Bcu0nAL4CXrv4Rs1U4UiPA92yQ.jpg?width=108&crop=smart&auto=webp&s=9383c98b34331be1841d47833b60408c5e8e78c6', 'width': 108}, {'height': 113, 'url': 'h... |
Andrej Karpathy's Fun prompt engineering challenge, Ep 1 | 74 | Andrej posted this little challenge that doesn't seem like much, but it turns out to be really hard.
For some reason, you'd be able to get an LLM to generate a correct response for a 3x3 grid, but not for a 5x5 one.
My LLMs tend to repeat the initial matrix - basically, after they write the first row (which is correc... | 2024-01-30T17:18:54 | Either-Job-341 | i.redd.it | 1970-01-01T00:00:00 | 0 | {} | 1aetpvy | false | null | t3_1aetpvy | /r/LocalLLaMA/comments/1aetpvy/andrej_karpathys_fun_prompt_engineering_challenge/ | false | false | 74 | {'enabled': True, 'images': [{'id': 'lwxqJffTYhYeLvdbH0jWGgDajWjLRU5Lzi9kNWY5VAw', 'resolutions': [{'height': 103, 'url': 'https://preview.redd.it/y59et9vg2mfc1.png?width=108&crop=smart&auto=webp&s=0e0ad49b319f02f9edac86fc4c6531eb8773e81a', 'width': 108}, {'height': 207, 'url': 'https://preview.redd.it/y59et9vg2mfc1.pn... | ||
Would it ever be possible to use back propagation to find the ideal system prompt? | 6 | It seems like we are always throwing spaghetti against the wall trying to find the best system prompts to make a model compliant to what we want. It seems a lot more like an art than any kind of engineering, complete with superstitions and anecdotes.
It always makes sense to use the lightest weight solution that can ... | 2024-01-30T16:55:42 | https://www.reddit.com/r/LocalLLaMA/comments/1aet4nr/would_it_ever_be_possible_to_use_back_propagation/ | eccsoheccsseven | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 1aet4nr | false | null | t3_1aet4nr | /r/LocalLLaMA/comments/1aet4nr/would_it_ever_be_possible_to_use_back_propagation/ | false | false | self | 6 | null |
2x E5-2620 server for local LLM's ? | 1 | Hello everyone. I know that at least few people here use old servers.
I can get this server for an equivalent of around $100 USD.
Here is all that I know about this bad boy:
- CPU: 2x Intel Xeon 6-core E5-2620 2.0GHz, Turbo: 2.5GHz, ( 12c/24t total)
- RAM: 32 GB DDR3 10600R ECC ( 4x8GB, no details about the manufact... | 2024-01-30T16:50:10 | https://www.reddit.com/r/LocalLLaMA/comments/1aeszq5/2x_e52620_server_for_local_llms/ | Puuuszzku | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 1aeszq5 | false | null | t3_1aeszq5 | /r/LocalLLaMA/comments/1aeszq5/2x_e52620_server_for_local_llms/ | false | false | self | 1 | null |
Are there any local models that can run faster than GPT3.5 on a Mac M1 Pro? | 2 | I'm new to this area, so apologies if this is a dumb question. | 2024-01-30T16:43:51 | https://www.reddit.com/r/LocalLLaMA/comments/1aesu0r/are_there_any_local_models_that_can_run_faster/ | constroyr | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 1aesu0r | false | null | t3_1aesu0r | /r/LocalLLaMA/comments/1aesu0r/are_there_any_local_models_that_can_run_faster/ | false | false | self | 2 | null |
Open source Community plans? | 1 | [removed] | 2024-01-30T16:34:14 | https://www.reddit.com/r/LocalLLaMA/comments/1aesld3/open_source_community_plans/ | Avitas54 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 1aesld3 | false | null | t3_1aesld3 | /r/LocalLLaMA/comments/1aesld3/open_source_community_plans/ | false | false | self | 1 | null |
MBP M3 Max 128Gig, what can you run? | 4 | What models are we running for those of us who have wasted money on these machines \[/s\]?
I run 70b gguf q5 models with about 5 tokens/sec output time using Text gen webUI. Of course smaller models like mixtral 8x7b, I run 8 bit quantized and get great output speeds.
A related question: is anyone running non-ggu... | 2024-01-30T16:31:49 | https://www.reddit.com/r/LocalLLaMA/comments/1aesj45/mbp_m3_max_128gig_what_can_you_run/ | knob-0u812 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 1aesj45 | false | null | t3_1aesj45 | /r/LocalLLaMA/comments/1aesj45/mbp_m3_max_128gig_what_can_you_run/ | false | false | self | 4 | null |
Custom builds vs Established frameworks experience? | 4 | I've been building out a custom LLM framework for my job, and now its being thrown away. The use case was heavily engrained in function calling. With LangChain, LlamaIndex, and Semantic Kernel rolling out stable releases, I'm wondering if I've wasted my time. Did you choose a pre-built solution or stick to your own gun... | 2024-01-30T16:13:24 | https://www.reddit.com/r/LocalLLaMA/comments/1aes2sb/custom_builds_vs_established_frameworks_experience/ | YeahWellThatsNiceBut | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 1aes2sb | false | null | t3_1aes2sb | /r/LocalLLaMA/comments/1aes2sb/custom_builds_vs_established_frameworks_experience/ | false | false | self | 4 | null |
How do I automate the back-and-forth process of running and eliminating bugs from code generated by LLMs? | 1 | I am using GPT-4 to generate shell scripts. I can take the output of the LLM, save the code as a shell script, run it, copy the error, paste the error back as input to the LLM, get the fixed code, run it again, and so on. Is there a way to automate this process?
I know about Autogen (by Microsoft), and it works well i... | 2024-01-30T16:09:10 | https://www.reddit.com/r/LocalLLaMA/comments/1aerz60/how_do_i_automate_the_backandforth_process_of/ | ResearcherNo4728 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 1aerz60 | false | null | t3_1aerz60 | /r/LocalLLaMA/comments/1aerz60/how_do_i_automate_the_backandforth_process_of/ | false | false | self | 1 | null |
The Bloke nous-capybara-34b.Q6_K.gguf question (how to speed up) | 1 | [removed] | 2024-01-30T16:08:10 | https://www.reddit.com/r/LocalLLaMA/comments/1aeryak/the_bloke_nouscapybara34bq6_kgguf_question_how_to/ | kaszebe | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 1aeryak | false | null | t3_1aeryak | /r/LocalLLaMA/comments/1aeryak/the_bloke_nouscapybara34bq6_kgguf_question_how_to/ | false | false | self | 1 | null |
Subsets and Splits
No community queries yet
The top public SQL queries from the community will appear here once available.