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 ⌀ |
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
How to increase loading speed of tokenizer? | 1 | Hi people, I was wondering how I can speed up my tokenizer loading speed. Currently it takes about 3 minutes to load the tokenizer for lmsys/vicuna-7b-v1.3. Thank you!
The code in question:
`model = AutoModelForCausalLM.from_pretrained(pretrained_model_name_or_path = "lmsys/vicuna-7b-v1.3", device_map = "balanced",to... | 2023-07-24T06:54:18 | https://www.reddit.com/r/LocalLLaMA/comments/1582sm3/how_to_increase_loading_speed_of_tokenizer/ | ToeAdministrative493 | self.LocalLLaMA | 2023-07-24T07:07:13 | 0 | {} | 1582sm3 | false | null | t3_1582sm3 | /r/LocalLLaMA/comments/1582sm3/how_to_increase_loading_speed_of_tokenizer/ | false | false | self | 1 | null |
How much RAM is needed for llama-2 70b + 32k context? | 44 | Hello, I'd like to know if 48, 56, 64, or 92 gb is needed for a cpu setup.
supposedly, with exllama, 48gb is all you'd need, for 16k. Its possible ggml may need more.
Along with this I have other questions, and feel free to read some testing that I was doing.
I was testing llama-2 70b (q3_K_S) at 32k context, with th... | 2023-07-24T06:18:19 | https://www.reddit.com/r/LocalLLaMA/comments/15825bt/how_much_ram_is_needed_for_llama2_70b_32k_context/ | Aaaaaaaaaeeeee | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 15825bt | false | null | t3_15825bt | /r/LocalLLaMA/comments/15825bt/how_much_ram_is_needed_for_llama2_70b_32k_context/ | false | false | self | 44 | null |
[Request] A tracker for all 'useful' llama applications updated every week | 26 | I'm not sure how useful this would be for others. But like most, I'm a subscriber on this channel and everyday, I can see a lot of amazing work. Just in the past week, I've seen what llama can do in order to do stuff such as analysing your private text to create your 'personal GPT' (albeit not as affective as chatGPT o... | 2023-07-24T05:27:03 | https://www.reddit.com/r/LocalLLaMA/comments/15817x3/request_a_tracker_for_all_useful_llama/ | vlodia | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 15817x3 | false | null | t3_15817x3 | /r/LocalLLaMA/comments/15817x3/request_a_tracker_for_all_useful_llama/ | false | false | self | 26 | {'enabled': False, 'images': [{'id': 'P15jNVogmR5WSjEB_kwDFJzQ8-ncag_kTZLd6_yKxCA', 'resolutions': [{'height': 54, 'url': 'https://external-preview.redd.it/Yyqv7oNGbRPyp69RfozMtix04o2lwg54x8_Vxo6O6RQ.jpg?width=108&crop=smart&auto=webp&s=515e7187952514863bd80558bbc201f6112cd133', 'width': 108}, {'height': 108, 'url': 'h... |
Is it possible to run multiple models simultaneously yet? If so what kind of hardware would I need to be able to pull it off? | 16 | From what I heard gpt 4 is a multiple guys in a trenchcoat situation, with one large model that calls upon pre trained smaller models when it needs them. I was wondering if it was possible to do something like that locally yet or if that's still pretty far off. I was also curious about what the cost to create a server ... | 2023-07-24T05:26:25 | https://www.reddit.com/r/LocalLLaMA/comments/15817ia/is_it_possible_to_run_multiple_models/ | sephy009 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 15817ia | false | null | t3_15817ia | /r/LocalLLaMA/comments/15817ia/is_it_possible_to_run_multiple_models/ | false | false | self | 16 | null |
Any tricks to "convince" LLama 2 to skip the polite introduction? | 14 | I'm playing around with the 7b/13b chat models.
I'm trying to write a system prompt so that I can get some "sanitized" output from the model. e.g.
Respond with a response in the format requested by the user. Do not include any other text or reasoning. ONLY include the response in the requested format.
So a given... | 2023-07-24T04:35:58 | https://www.reddit.com/r/LocalLLaMA/comments/158097f/any_tricks_to_convince_llama_2_to_skip_the_polite/ | sqiddster | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 158097f | false | null | t3_158097f | /r/LocalLLaMA/comments/158097f/any_tricks_to_convince_llama_2_to_skip_the_polite/ | false | false | self | 14 | null |
[Question] When should you use prefix tuning over Lora? | 7 | I saw prefix tuning being mentioned in some articles. It seems its advantage is that you only fine tune a small set of parameters so it is faster and you need less data. That sounds pretty similar to Lora but I rarely see it being used to fine tune LLMs or stable diffusion models. Can someone please tell me when I shou... | 2023-07-24T03:38:05 | https://www.reddit.com/r/LocalLLaMA/comments/157z4md/question_when_should_you_use_prefix_tuning_over/ | saintshing | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 157z4md | false | null | t3_157z4md | /r/LocalLLaMA/comments/157z4md/question_when_should_you_use_prefix_tuning_over/ | false | false | self | 7 | {'enabled': False, 'images': [{'id': 'x-lOWwsmjxuBfNio1fyp91w9Da3lZ_V4nTdjUqOqeaQ', 'resolutions': [{'height': 82, 'url': 'https://external-preview.redd.it/4Fud8sYOjeepmPdnc0MWpyl1JTDx4AN5sAt13lr5ARs.jpg?width=108&crop=smart&auto=webp&s=95cdf55b7c2a78fabc2896b384f1cafedf50396a', 'width': 108}, {'height': 164, 'url': 'h... |
Suggestions for hosting solutions for custom pytorch code? | 5 | Say I have a python script that loads LLaMA, but doesn't just provide vanilla LLaMA inference.
For example, I have an endpoint that returns the probability for the last token in a sequence.
Or maybe I want to run an inference server that accepts Guidance templates.
As far as I can tell, this necessitates renting GPU... | 2023-07-24T02:25:00 | https://www.reddit.com/r/LocalLLaMA/comments/157xlxe/suggestions_for_hosting_solutions_for_custom/ | phree_radical | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 157xlxe | false | null | t3_157xlxe | /r/LocalLLaMA/comments/157xlxe/suggestions_for_hosting_solutions_for_custom/ | false | false | self | 5 | null |
Arabic prompt LLM models request | 1 | Im lookin for a reasnoble sized LLM model that understand RTL languages specially arabic , it should except questions directly in arabic and can read a local stored folder full of files in arabic.
I found bllom model but its a giant model even with the bloke finetunning releases couldnot host locally as it not compatib... | 2023-07-24T02:22:55 | https://www.reddit.com/r/LocalLLaMA/comments/157xkhr/arabic_prompt_llm_models_request/ | qwani | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 157xkhr | false | null | t3_157xkhr | /r/LocalLLaMA/comments/157xkhr/arabic_prompt_llm_models_request/ | false | false | self | 1 | null |
Finetuning 4 bit LLMs | 9 | Hi I want to finetune a LLM and I have been using mostly 4 bit models for inference like this for example: [https://huggingface.co/TheBloke/Llama-2-13B-chat-GPTQ](https://huggingface.co/TheBloke/Llama-2-13B-chat-GPTQ)
and I wanted to understand how I can fine tune this. From what I have found, one can finetune a 4bit ... | 2023-07-24T02:05:38 | https://www.reddit.com/r/LocalLLaMA/comments/157x758/finetuning_4_bit_llms/ | klop2031 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 157x758 | false | null | t3_157x758 | /r/LocalLLaMA/comments/157x758/finetuning_4_bit_llms/ | false | false | self | 9 | {'enabled': False, 'images': [{'id': 'rkljmc1ht4wmaJGm60zJkcYTjcDJ3O6Ma8y8dDYwHYI', 'resolutions': [{'height': 58, 'url': 'https://external-preview.redd.it/vBvc7FHJE65n0rhjEdf2N4Vhy4vMT0IFNxHSqGQObp8.jpg?width=108&crop=smart&auto=webp&s=1a72ffb8bd5cc3be930da7d37436aeb9871f39b6', 'width': 108}, {'height': 116, 'url': 'h... |
Unleashing the Power of Language Learning Models with Llama2 Code Interpreter! | 102 | Hello Reddit community! 🚀
We're excited to introduce our latest project, [**Llama2 Code Interpreter**](https://github.com/SeungyounShin/Llama2-Code-Interpreter). This innovative project aims to push the boundaries of Language Learning Models (LLMs) by empowering them to generate, execute, debug code, and answer relev... | 2023-07-24T01:09:06 | https://www.reddit.com/r/LocalLLaMA/comments/157vzq6/unleashing_the_power_of_language_learning_models/ | mrjohndoee | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 157vzq6 | false | null | t3_157vzq6 | /r/LocalLLaMA/comments/157vzq6/unleashing_the_power_of_language_learning_models/ | false | false | self | 102 | {'enabled': False, 'images': [{'id': 'q0YPveytzJE4sSE3UGYRJqkjuA4dsVB7Z-0GxV-jHPk', 'resolutions': [{'height': 54, 'url': 'https://external-preview.redd.it/1mh5sVveFJvrvR8Sdml696vhjuZUa7rEWQRY8uzahl8.jpg?width=108&crop=smart&auto=webp&s=a6339f16762cca70858a807fb2f5f7b2028488a3', 'width': 108}, {'height': 108, 'url': 'h... |
Python bindings for GGML | 21 | I think this repo https://github.com/marella/ctransformers deserves more stars. I find the API more comprehensive than GPT4ALL, and the repo itself is less bloated. | 2023-07-24T00:12:52 | https://www.reddit.com/r/LocalLLaMA/comments/157us74/python_bindings_for_ggml/ | Acrobatic-Site2065 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 157us74 | false | null | t3_157us74 | /r/LocalLLaMA/comments/157us74/python_bindings_for_ggml/ | false | false | self | 21 | {'enabled': False, 'images': [{'id': 'aeNxffzXL-WImYS9Z0F9OkH-rW7iCxT-9Bs-XqcUazM', 'resolutions': [{'height': 54, 'url': 'https://external-preview.redd.it/gyNFXDsvN4s2hIhRV9fCAZxNxMZFSfEgKSmDiy2YD_o.jpg?width=108&crop=smart&auto=webp&s=b252c7899459b541873b9738337ec7046ec54e6b', 'width': 108}, {'height': 108, 'url': 'h... |
Evolved codealpaca dataset released | 23 | Using LLMs to augment and create much diverse instruction based dataset has seen wide success in WizardL. However the 78k evolved code instructions dataset hasn't been released since, so I have take the initiative to try to recreate the augmentation instruction myself.
Dataset: [https://huggingface.co/datasets/theb... | 2023-07-23T22:54:34 | https://www.reddit.com/r/LocalLLaMA/comments/157szor/evolved_codealpaca_dataset_released/ | gradientpenalty | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 157szor | false | null | t3_157szor | /r/LocalLLaMA/comments/157szor/evolved_codealpaca_dataset_released/ | false | false | self | 23 | {'enabled': False, 'images': [{'id': 'EHJVsVNsqX9Bm0qOGlZwBycuvVTDhwuy6pGKtz-Z0yU', 'resolutions': [{'height': 58, 'url': 'https://external-preview.redd.it/LJZrRrGiBqX8ZK24bjVhFfH8M8wLVraKTRXtXipEzMQ.jpg?width=108&crop=smart&auto=webp&s=12d0b2d22e87469e78a1d662bd839d29efcba0d2', 'width': 108}, {'height': 116, 'url': 'h... |
LlamaCPP can't handle same parameters then .bin using koboldcpp-henk-cuda.exe | 3 | Hey guys
New to LocalLlama (love it) !
I am currently trying to run this model within a .py file to return a response based on a new article.
llm = LlamaCpp(
model_path='airoboros-7b-gpt4-1.4.ggmlv3.q5_K_M.bin',
verbose=True,
n_ctx=1024,
... | 2023-07-23T22:34:59 | https://www.reddit.com/r/LocalLLaMA/comments/157sjbd/llamacpp_cant_handle_same_parameters_then_bin/ | ItsGoodAs | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 157sjbd | false | null | t3_157sjbd | /r/LocalLLaMA/comments/157sjbd/llamacpp_cant_handle_same_parameters_then_bin/ | false | false | self | 3 | null |
Quantization naming conventions? | 12 | I have been following the community for a while and have seen a lot of models being quantized. There seems to be some agreed naming convention and I have trouble understanding where it came from and what it means. I am talking about names as q3_K_s and q4_k_m, etc. I understand that the q number stands for the number o... | 2023-07-23T22:19:26 | https://www.reddit.com/r/LocalLLaMA/comments/157s5m5/quantization_naming_conventions/ | iLaurens | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 157s5m5 | false | null | t3_157s5m5 | /r/LocalLLaMA/comments/157s5m5/quantization_naming_conventions/ | false | false | self | 12 | null |
Best GPT4-like | 0 | I would love to have something similar to GPT-4 or Bing’s implementation, but offline.
Specs: Macbook Pro 14 M1 Pro / 16Gb RAM | 2023-07-23T20:22:51 | https://www.reddit.com/r/LocalLLaMA/comments/157p77l/best_gpt4like/ | Neural_Phoenix | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 157p77l | false | null | t3_157p77l | /r/LocalLLaMA/comments/157p77l/best_gpt4like/ | false | false | self | 0 | null |
Multi GPU recommendations | 3 | I need a multi GPU recommendation.
What would be a good setup for the local Llama2:
I have:
10 x RTX 3060 12 GB
4 X RTX 3080 10 GB
8 X RTX 3070TI 8 GB
I know that it would be probably better if i could sell those GPUs and to buy 2 X RTX 3090 but I really want to keep them because it's too much hassle.
If I could ask ... | 2023-07-23T19:45:21 | https://www.reddit.com/r/LocalLLaMA/comments/157o87t/multi_gpu_recommendations/ | scout_with_beard | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 157o87t | false | null | t3_157o87t | /r/LocalLLaMA/comments/157o87t/multi_gpu_recommendations/ | false | false | self | 3 | null |
Small explanation question! Types of LLAMA | 9 | What does supercot and superhot mean? And what do the suffixes GPTQ, GGML, fp16, and cuda mean?
For context, I’m trying to use (for the first time) the exllama loader within webui, but it doesn’t seem to work for some models:) | 2023-07-23T19:45:03 | https://www.reddit.com/r/LocalLLaMA/comments/157o7uc/small_explanation_question_types_of_llama/ | Real_Experience_5676 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 157o7uc | false | null | t3_157o7uc | /r/LocalLLaMA/comments/157o7uc/small_explanation_question_types_of_llama/ | false | false | self | 9 | null |
Is llama-2 4k context out of the box? | 1 | [removed] | 2023-07-23T19:41:03 | https://www.reddit.com/r/LocalLLaMA/comments/157o41b/is_llama2_4k_context_out_of_the_box/ | Necessary_Ad_9800 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 157o41b | false | null | t3_157o41b | /r/LocalLLaMA/comments/157o41b/is_llama2_4k_context_out_of_the_box/ | false | false | self | 1 | null |
Can I save the llama 2 7B model to my google drive from colab? Looking for ways to not download it every single time. | 9 | TIA | 2023-07-23T19:30:14 | https://www.reddit.com/r/LocalLLaMA/comments/157ntpq/can_i_save_the_llama_2_7b_model_to_my_google/ | CraftAggressive1133 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 157ntpq | false | null | t3_157ntpq | /r/LocalLLaMA/comments/157ntpq/can_i_save_the_llama_2_7b_model_to_my_google/ | false | false | self | 9 | null |
LlamaTale v0.51 "The Prancing Llama" (MUD + LLM) | 29 | Hi all.
I've kept working on integrating local LLM and MUD (more like interactive fiction for now) and rebranded my fork to something more suitable.
[https://github.com/neph1/LlamaTale/releases/tag/v0.51](https://github.com/neph1/LlamaTale/releases/tag/v0.51)
Those who saw the [first version](https://www.reddit.com/... | 2023-07-23T19:25:01 | https://www.reddit.com/r/LocalLLaMA/comments/157noz3/llamatale_v051_the_prancing_llama_mud_llm/ | neph1010 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 157noz3 | false | null | t3_157noz3 | /r/LocalLLaMA/comments/157noz3/llamatale_v051_the_prancing_llama_mud_llm/ | false | false | self | 29 | {'enabled': False, 'images': [{'id': 'D-EPL3y_yMj6xX_nKziPQSEfAewVqEv6iOAD-M_Rkzg', 'resolutions': [{'height': 54, 'url': 'https://external-preview.redd.it/jx8ESLmPzhb_AGvKoYMtFWGsv6t2LMmGsDrB0zyoqGA.jpg?width=108&crop=smart&auto=webp&s=398480f37012113b6a8be672bcf921a03db07357', 'width': 108}, {'height': 108, 'url': 'h... |
Fine tuning and deployment. | 1 | [removed] | 2023-07-23T19:17:55 | https://www.reddit.com/r/LocalLLaMA/comments/157nilr/fine_tuning_and_deployment/ | InterestingBasil | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 157nilr | false | null | t3_157nilr | /r/LocalLLaMA/comments/157nilr/fine_tuning_and_deployment/ | false | false | self | 1 | null |
Llama2.c Inference Llama 2 in one file of pure C from Andrej Karpathy | 162 | 2023-07-23T19:10:25 | https://twitter.com/karpathy/status/1683143097604243456?s=46&t=tzId7BojkoYRImYV_DLZ9w | FuguSandwich | twitter.com | 1970-01-01T00:00:00 | 0 | {} | 157nbvk | false | {'oembed': {'author_name': 'Andrej Karpathy', 'author_url': 'https://twitter.com/karpathy', 'cache_age': 3153600000, 'height': None, 'html': '<blockquote class="twitter-video"><p lang="en" dir="ltr">My fun weekend hack: llama2.c 🦙🤠<a href="https://t.co/CUoF0l07oX">https://t.co/CUoF0l07oX</a><br>Lets you train a baby ... | t3_157nbvk | /r/LocalLLaMA/comments/157nbvk/llama2c_inference_llama_2_in_one_file_of_pure_c/ | false | false | 162 | {'enabled': False, 'images': [{'id': '9MrWHX0I0axia4v07LvpXaM_0zhws4kmOPpboFEZVlA', 'resolutions': [{'height': 108, 'url': 'https://external-preview.redd.it/tEL1Xn21av_kCZ4mZgpX_Kkij1bpoJoFXJ99BkWz4uM.jpg?width=108&crop=smart&auto=webp&s=694e525c4b08e06e1cca9b0a01d36d6b781a2425', 'width': 108}], 'source': {'height': 14... | ||
Run Llama 2 locally on GPU or CPU from anywhere (Linux/Windows/Mac) ➡️https://github.com/liltom-eth/llama2-webui | 4 | Running Llama 2 locally with gradio UI on GPU or CPU from anywhere (Linux/Windows/Mac). Supporting Llama-2-7B/13B/70B with 8-bit, 4-bit. Supporting GPU inference (6 GB VRAM) and CPU inference. ➡️[https://github.com/liltom-eth/llama2-webui](https://github.com/liltom-eth/llama2-webui)
Successfully running #Llama2 on my... | 2023-07-23T19:09:44 | https://www.reddit.com/r/LocalLLaMA/comments/157nb7q/run_llama_2_locally_on_gpu_or_cpu_from_anywhere/ | plain1994 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 157nb7q | false | null | t3_157nb7q | /r/LocalLLaMA/comments/157nb7q/run_llama_2_locally_on_gpu_or_cpu_from_anywhere/ | false | false | self | 4 | {'enabled': False, 'images': [{'id': 'O80KV6G4OSCdSHLEHBB5K3f2ylMPtkB3MqY6ZFCJtaw', 'resolutions': [{'height': 54, 'url': 'https://external-preview.redd.it/dNlWnaFXzl2jPkbZGS7w2dFWJamZk-R6rO_7HFaodN0.jpg?width=108&crop=smart&auto=webp&s=84bc4bba8935b4da5ca3d7d159a150a1d1bd452f', 'width': 108}, {'height': 108, 'url': 'h... |
Run Llama 2 locally on GPU or CPU from anywhere (Linux/Windows/Mac) ➡️https://github.com/liltom-eth/llama2-webui | 1 | [removed] | 2023-07-23T19:05:46 | https://www.reddit.com/r/LocalLLaMA/comments/157n7fx/run_llama_2_locally_on_gpu_or_cpu_from_anywhere/ | liltom_eth | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 157n7fx | false | null | t3_157n7fx | /r/LocalLLaMA/comments/157n7fx/run_llama_2_locally_on_gpu_or_cpu_from_anywhere/ | false | false | self | 1 | null |
Can I improve the Llama-2 model for a specific language? | 17 | I am currently working on an enterprise application, which requires users to interact in a language other than English. I want to enhance the Llama-2 model's proficiency in this specific language. I have watched some YouTube videos where an individual improved the model's performance in German; however, this seemed to... | 2023-07-23T18:29:37 | https://www.reddit.com/r/LocalLLaMA/comments/157m9q9/can_i_improve_the_llama2_model_for_a_specific/ | GalacticGiraffeGuru | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 157m9q9 | false | null | t3_157m9q9 | /r/LocalLLaMA/comments/157m9q9/can_i_improve_the_llama2_model_for_a_specific/ | false | false | self | 17 | null |
LLaMa (Oobabooga), MPT-30b (KoboldCpp), and Stable Diffusion with Semantic Kernel | 1 | [removed] | 2023-07-23T18:22:35 | https://www.reddit.com/r/LocalLLaMA/comments/157m3ez/llama_oobabooga_mpt30b_koboldcpp_and_stable/ | awitod | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 157m3ez | false | null | t3_157m3ez | /r/LocalLLaMA/comments/157m3ez/llama_oobabooga_mpt30b_koboldcpp_and_stable/ | false | false | 1 | null | |
airoboros-65B-gpt4-1.2-GGML beats gpt4 in this test | 14 | [https://paste.c-net.org/KristinaCustard](https://paste.c-net.org/KristinaCustard) response from airoboros-65B-gpt4-1.2-GGML
​
GPT4 response here: [https://www.reddit.com/r/ChatGPT/comments/156crf7/how\_to\_make\_chatgpt\_answer\_this\_correctly/](https://www.reddit.com/r/ChatGPT/comments/156crf7/how_to_make_c... | 2023-07-23T18:17:02 | https://www.reddit.com/r/LocalLLaMA/comments/157ly7p/airoboros65bgpt412ggml_beats_gpt4_in_this_test/ | dewijones92 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 157ly7p | false | null | t3_157ly7p | /r/LocalLLaMA/comments/157ly7p/airoboros65bgpt412ggml_beats_gpt4_in_this_test/ | false | false | self | 14 | null |
Best uncensored llm model that is out there as of today? | 108 | Chatgpt is becoming silly and going on a rant about being an AI MODEL line even in a simple non-harmful stuff and questioning controversial topics.
Please suggest a decent uncensored llm that I can run locally?
Luna vs Vicuna vs Alpaca vs else (7b/13b/30b/..) | 2023-07-23T17:49:00 | https://www.reddit.com/r/LocalLLaMA/comments/157l842/best_uncensored_llm_model_that_is_out_there_as_of/ | InternationalMap5278 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 157l842 | false | null | t3_157l842 | /r/LocalLLaMA/comments/157l842/best_uncensored_llm_model_that_is_out_there_as_of/ | false | false | self | 108 | null |
Unleashing the Power of Language Learning Models with Llama2 Code Interpreter! | 1 | [removed] | 2023-07-23T17:44:26 | https://www.reddit.com/r/LocalLLaMA/comments/157l42o/unleashing_the_power_of_language_learning_models/ | Money-Coast-3905 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 157l42o | false | null | t3_157l42o | /r/LocalLLaMA/comments/157l42o/unleashing_the_power_of_language_learning_models/ | false | false | self | 1 | {'enabled': False, 'images': [{'id': 'q0YPveytzJE4sSE3UGYRJqkjuA4dsVB7Z-0GxV-jHPk', 'resolutions': [{'height': 54, 'url': 'https://external-preview.redd.it/1mh5sVveFJvrvR8Sdml696vhjuZUa7rEWQRY8uzahl8.jpg?width=108&crop=smart&auto=webp&s=a6339f16762cca70858a807fb2f5f7b2028488a3', 'width': 108}, {'height': 108, 'url': 'h... |
FYP idea with LLMs | 5 | Hey guys , I am an undergrad student in computer engineering and I am about to enter my final year, as such I have got to decide on a final year project.with the recent trend in AI nowadays, I was planning on working with opensource LLMs in my project. a project which I have in mind is to use an opensource llm and fine... | 2023-07-23T17:25:34 | https://www.reddit.com/r/LocalLLaMA/comments/157kmqu/fyp_idea_with_llms/ | Demonking6444 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 157kmqu | false | null | t3_157kmqu | /r/LocalLLaMA/comments/157kmqu/fyp_idea_with_llms/ | false | false | self | 5 | null |
Google Sheets link to Huggingface data I scraped from config.json files for top 1200 HF LLMs. | 7 | 2023-07-23T17:19:48 | https://docs.google.com/spreadsheets/d/16zMmDlU1eyiMY_IK_RnBILB-AcAKES0cMBMsgs50HVA/edit?usp=sharing | jakderrida | docs.google.com | 1970-01-01T00:00:00 | 0 | {} | 157khlg | false | null | t3_157khlg | /r/LocalLLaMA/comments/157khlg/google_sheets_link_to_huggingface_data_i_scraped/ | false | false | 7 | {'enabled': False, 'images': [{'id': '9pV4kDr42B87RnhC1jsS9KeBk4DxdVScAFhhDlTOVek', 'resolutions': [{'height': 56, 'url': 'https://external-preview.redd.it/I-D5zWMcHzmGzPcTWS9zC-eiKjtsNWXKWn_Ir9pxhBY.jpg?width=108&crop=smart&auto=webp&s=bcc9b249db4b76c054f076214eba941122c09ad4', 'width': 108}, {'height': 113, 'url': 'h... | ||
Uncensored llm | 1 | What is the best uncensored llm model that is out there as of today? Chatgpt is becoming silly and going on a rant about being an AI MODEL line even in a simple non-harmful stuff and questioning controversial topics.
Please suggest a decent uncensored llm that I can run locally? | 2023-07-23T17:15:32 | https://www.reddit.com/r/LocalLLaMA/comments/157kdzt/uncensored_llm/ | InternationalMap5278 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 157kdzt | false | null | t3_157kdzt | /r/LocalLLaMA/comments/157kdzt/uncensored_llm/ | false | false | self | 1 | null |
For those who struggled in connecting SillyTavern to Runpod hosted oobabooga | 1 | [removed] | 2023-07-23T16:23:54 | https://www.reddit.com/r/LocalLLaMA/comments/157j3st/for_those_who_struggled_in_connecting_sillytavern/ | sbalani | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 157j3st | false | null | t3_157j3st | /r/LocalLLaMA/comments/157j3st/for_those_who_struggled_in_connecting_sillytavern/ | false | false | self | 1 | {'enabled': False, 'images': [{'id': '-skHzNajEs03p_m8t50ADPtl1iBQB3pEXzwQaIEycwg', 'resolutions': [{'height': 81, 'url': 'https://external-preview.redd.it/-zykPhyaEBKZ_4bsZc9yu8hH4e2_SUC32Q9Aji6SOTM.jpg?width=108&crop=smart&auto=webp&s=80bd4b94d5b3e34a3f56e621e410ea0fb7cde9c3', 'width': 108}, {'height': 162, 'url': 'h... |
Examples of QA use cases ? | 7 | I’m thinking to do hands-on learning about using LLM for QA of your own documents.
What are some examples of public documents that I can collect to create a dataset from which the LLM can retrieve info when responding to your questions?
What what are some example questions to ask regarding this set of documents? | 2023-07-23T15:08:59 | https://www.reddit.com/r/LocalLLaMA/comments/157h883/examples_of_qa_use_cases/ | xynyxyn | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 157h883 | false | null | t3_157h883 | /r/LocalLLaMA/comments/157h883/examples_of_qa_use_cases/ | false | false | self | 7 | null |
Offensive fruit + weird word | 6 | So, while trying to check Llama-2 for [certain words](https://new.reddit.com/r/LocalLLaMA/comments/13qoktf/llama_glitch_tokens/), this happened:
​
[I tried this melon request many times, and it gave me similar results, the least \\"safety\\" concerned”result being that the request just wasn’t \\"meaningful\\" ... | 2023-07-23T14:03:34 | https://www.reddit.com/r/LocalLLaMA/comments/157fnvm/offensive_fruit_weird_word/ | reduserGf | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 157fnvm | false | null | t3_157fnvm | /r/LocalLLaMA/comments/157fnvm/offensive_fruit_weird_word/ | false | false | 6 | null | |
Can I get 70b to run on two P40s? | 9 | I understand it will be very slow, but I already have one and a second will put me up to 48gb of ram. For my application i don't need real time functionality, and i would love to do it on a reasonable budget. | 2023-07-23T13:50:06 | https://www.reddit.com/r/LocalLLaMA/comments/157fch9/can_i_get_70b_to_run_on_two_p40s/ | CTR0 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 157fch9 | false | null | t3_157fch9 | /r/LocalLLaMA/comments/157fch9/can_i_get_70b_to_run_on_two_p40s/ | false | false | self | 9 | null |
How to make sense of all the new models? | 51 | So far my understanding:
[https://huggingface.co/TheBloke/Dolphin-Llama-13B-GPTQ](https://huggingface.co/TheBloke/Dolphin-Llama-13B-GPTQ)
* uncensored by design
[https://huggingface.co/TheBloke/13B-BlueMethod-GPTQ](https://huggingface.co/TheBloke/13B-BlueMethod-GPTQ)
* an experimental mix of many things
[https://h... | 2023-07-23T12:38:23 | https://www.reddit.com/r/LocalLLaMA/comments/157dta0/how_to_make_sense_of_all_the_new_models/ | whtne047htnb | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 157dta0 | false | null | t3_157dta0 | /r/LocalLLaMA/comments/157dta0/how_to_make_sense_of_all_the_new_models/ | false | false | self | 51 | {'enabled': False, 'images': [{'id': '45E1eadhWYj1KBpEiKYwZXAR4HNvyhQ8YnjI8kLcNIU', 'resolutions': [{'height': 58, 'url': 'https://external-preview.redd.it/-MEMQ14vPf00G_1nUHYl0UanTIpfmE5mL3wAgCHCMbg.jpg?width=108&crop=smart&auto=webp&s=4c034df8974d671748e1d43b79e96605eba1f8e8', 'width': 108}, {'height': 116, 'url': 'h... |
Confused about temperature, top_k, top_p, repetition_penalty, frequency_penalty, presence_penalty? Me too, until now! | 80 | Here is my conversation with gpt-4 on those parameters! It explained very well without being to technical, so hope it helps others too.
Q: Can you tell me the difference between top_p and top_k without using ML jargon? Make it simple, non-technical.
Sure, I'll do my best to explain these terms in a simple, non-techni... | 2023-07-23T12:25:42 | https://www.reddit.com/r/LocalLLaMA/comments/157djvv/confused_about_temperature_top_k_top_p_repetition/ | jl303 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 157djvv | false | null | t3_157djvv | /r/LocalLLaMA/comments/157djvv/confused_about_temperature_top_k_top_p_repetition/ | false | false | self | 80 | null |
LLaMA v2 model sizes | 8 | Hi All,
I am still awaiting approval of my request for llama v2. I wanted to know the model sizes for all llama v2 models, 7B, 13B, 30B and 70B
thanks | 2023-07-23T12:09:57 | https://www.reddit.com/r/LocalLLaMA/comments/157d89h/llama_v2_model_sizes/ | gijeri4793 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 157d89h | false | null | t3_157d89h | /r/LocalLLaMA/comments/157d89h/llama_v2_model_sizes/ | false | false | self | 8 | null |
In case you wondered about future, here is a hilarious forecast from TheBloke_Vicuna-33B-1-3-SuperHOT-8K-GPTQ with broken context window. | 1 | [removed] | 2023-07-23T11:31:09 | https://www.reddit.com/r/LocalLLaMA/comments/157chmt/in_case_you_wondered_about_future_here_is_a/ | perelmanych | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 157chmt | false | null | t3_157chmt | /r/LocalLLaMA/comments/157chmt/in_case_you_wondered_about_future_here_is_a/ | false | false | self | 1 | null |
e-book cleaning tip | 19 | Using calibre, you can very easily bulk convert e-books to .txt. You can set calibre to remove all formatting tags, clean margins and such, remove table of contents, so on and so forth during the bulk convert process. You can then save all of the books into one folder on your disk. | 2023-07-23T11:26:23 | https://www.reddit.com/r/LocalLLaMA/comments/157cefd/ebook_cleaning_tip/ | Nekasus | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 157cefd | false | null | t3_157cefd | /r/LocalLLaMA/comments/157cefd/ebook_cleaning_tip/ | false | false | self | 19 | null |
Which models will work on Apple MacBook Air M1 (2020)? | 7 | I'm new to this.
I have a Apple MacBook Air M1 (2020). 16GB Ram, 8 Cores, 2TB Hard Drive.
Am using \`oobabooga/text-generation-webui\` to download and test models.
I first started with \`TheBloke/WizardLM-7B-uncensored-GPTQ\` but after much headaches I found out \`GPTQ\` models only work with Nvidia GPUs.
So next I... | 2023-07-23T10:59:18 | https://www.reddit.com/r/LocalLLaMA/comments/157bvwk/which_models_will_work_on_apple_macbook_air_m1/ | bumblebrunch | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 157bvwk | false | null | t3_157bvwk | /r/LocalLLaMA/comments/157bvwk/which_models_will_work_on_apple_macbook_air_m1/ | false | false | self | 7 | null |
How to create bindings for Llama.cpp | 5 | Hello everyone!
I'm currently trying to create a binding for Llama.cpp in Pharo.
I'm studying python wrapper implementations but do you know if there are any references for using the llama.cpp c api ( **llama.h** ) ?
Also is it easier by using an http server ?
As you can see, I'm not very good but I'd be delighted... | 2023-07-23T10:13:44 | https://www.reddit.com/r/LocalLLaMA/comments/157b28u/how_to_create_bindings_for_llamacpp/ | Silly-Cup1391 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 157b28u | false | null | t3_157b28u | /r/LocalLLaMA/comments/157b28u/how_to_create_bindings_for_llamacpp/ | false | false | self | 5 | null |
Llama v2 for document based chatbot in a foreign language | 2 | I am trying to build a pdf bot that should run locally. The doc is in Swedish and I have tried falcon 7b. The results are clearly not very impressive and got me ever so curious to use llama. I got two GPUs 10GB each. Where can I start looking for implementing it in this scenario? | 2023-07-23T09:24:19 | https://www.reddit.com/r/LocalLLaMA/comments/157a70u/llama_v2_for_document_based_chatbot_in_a_foreign/ | vaibhavsxn | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 157a70u | false | null | t3_157a70u | /r/LocalLLaMA/comments/157a70u/llama_v2_for_document_based_chatbot_in_a_foreign/ | false | false | self | 2 | null |
Puffin benchmarks show SOTA performance! New records for Winogrande and PIQA | 1 | [removed] | 2023-07-23T09:06:46 | https://twitter.com/dogesator/status/1683022689177415681?s=46 | dogesator | twitter.com | 1970-01-01T00:00:00 | 0 | {} | 1579vh0 | false | {'oembed': {'author_name': 'LDJ', 'author_url': 'https://twitter.com/Dogesator', 'cache_age': 3153600000, 'height': None, 'html': '<blockquote class="twitter-video"><p lang="en" dir="ltr">Puffin-13B benchmarks are in 🔥 Reaches a record SOTA in several GPT4All benchmarks <br><br>It's my new favorite model and alrea... | t3_1579vh0 | /r/LocalLLaMA/comments/1579vh0/puffin_benchmarks_show_sota_performance_new/ | false | false | 1 | {'enabled': False, 'images': [{'id': 'YBBgyo71xeJ4fMjbvIg5gKR8fJ_wTfsvy-oKG4hOELU', 'resolutions': [{'height': 30, 'url': 'https://external-preview.redd.it/XeEWHawdBNwDvZx2bpZq2Dv1TvCNl0xbjFXWYZu5Nmc.jpg?width=108&crop=smart&auto=webp&s=fc2f668f03cf3b3db966a4c152114bd84bd3d207', 'width': 108}], 'source': {'height': 40,... | |
Puffin benchmarks show SOTA performance, beating Hermes in several benchmarks. | 1 | [removed] | 2023-07-23T08:55:12 | https://twitter.com/dogesator/status/1683022689177415681?s=46 | dogesator | twitter.com | 1970-01-01T00:00:00 | 0 | {} | 1579ngh | false | {'oembed': {'author_name': 'LDJ', 'author_url': 'https://twitter.com/Dogesator', 'cache_age': 3153600000, 'height': None, 'html': '<blockquote class="twitter-video"><p lang="en" dir="ltr">Puffin-13B benchmarks are in 🔥 Reaches a record SOTA in several GPT4All benchmarks <br><br>It's my new favorite model and alrea... | t3_1579ngh | /r/LocalLLaMA/comments/1579ngh/puffin_benchmarks_show_sota_performance_beating/ | false | false | 1 | {'enabled': False, 'images': [{'id': 'YBBgyo71xeJ4fMjbvIg5gKR8fJ_wTfsvy-oKG4hOELU', 'resolutions': [{'height': 30, 'url': 'https://external-preview.redd.it/XeEWHawdBNwDvZx2bpZq2Dv1TvCNl0xbjFXWYZu5Nmc.jpg?width=108&crop=smart&auto=webp&s=fc2f668f03cf3b3db966a4c152114bd84bd3d207', 'width': 108}], 'source': {'height': 40,... | |
70b q3_K_S at 1.4 t/s 32gb cpu ram showcase | 14 | ### I didn't realize these very large models run at their reasonable cpu speeds **on a smaller amount of ram.**
This was on xubuntu. The inference speed was 1.4t/s after ingesting ~3000 tokens
Here's my output- https://pastes.io/mwefcnz3jw
It may be nice to know, it's for those planning to upgrade RAM. A smaller m... | 2023-07-23T08:24:32 | https://www.reddit.com/r/LocalLLaMA/comments/15794m2/70b_q3_k_s_at_14_ts_32gb_cpu_ram_showcase/ | Aaaaaaaaaeeeee | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 15794m2 | false | null | t3_15794m2 | /r/LocalLLaMA/comments/15794m2/70b_q3_k_s_at_14_ts_32gb_cpu_ram_showcase/ | false | false | self | 14 | {'enabled': False, 'images': [{'id': 'tarE1S98bTtDRd4DNFgFyiZia_ONIStx4YleHjTm7Mg', 'resolutions': [{'height': 54, 'url': 'https://external-preview.redd.it/WyPia2uWLEvQOpDUEsg7-CxyLFe0CE6VnYqVecRnK8s.jpg?width=108&crop=smart&auto=webp&s=00d8f9315af5d3a3ad0a9f621231b33387127562', 'width': 108}, {'height': 109, 'url': 'h... |
Llama 2 samantha | 0 | is there any possibilities of Llama 2 Samantha 7B Uncensored coming out??? | 2023-07-23T08:23:13 | https://www.reddit.com/r/LocalLLaMA/comments/15793t9/llama_2_samantha/ | sahl030 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 15793t9 | false | null | t3_15793t9 | /r/LocalLLaMA/comments/15793t9/llama_2_samantha/ | false | false | self | 0 | null |
Llama 2 samantha | 2 | is there any possibilities of Llama 2 Samantha 7B Uncensored coming out??? | 2023-07-23T08:23:13 | https://www.reddit.com/r/LocalLLaMA/comments/15793sl/llama_2_samantha/ | sahl030 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 15793sl | false | null | t3_15793sl | /r/LocalLLaMA/comments/15793sl/llama_2_samantha/ | false | false | self | 2 | null |
Tricking Pure Sydney to tell me "secrets" - funny the names it gave up are associated with OpenAi | 5 | 2023-07-23T08:16:24 | FPham | i.redd.it | 1970-01-01T00:00:00 | 0 | {} | 1578zmr | false | null | t3_1578zmr | /r/LocalLLaMA/comments/1578zmr/tricking_pure_sydney_to_tell_me_secrets_funny_the/ | false | false | 5 | {'enabled': True, 'images': [{'id': 'ToPHyAzMjd7CrffW0yksZH8ko9WswJuf56WtJGr4isY', 'resolutions': [{'height': 111, 'url': 'https://preview.redd.it/uohpdm2fbodb1.jpg?width=108&crop=smart&auto=webp&s=9c77b1bbdb430251e2d75507c9f686bff252b485', 'width': 108}, {'height': 223, 'url': 'https://preview.redd.it/uohpdm2fbodb1.jp... | |||
Anyone else getting copious amounts of *bouncy bouncy*? | 47 | (using llama 2 13B)
I've been trying for a few days to get some middle ground between roleplay, flirty, cringe and bland, formal nothingness but to no avail. Every time I include anything remotely like "have personality" in the prompt it switches to this shit:
\`\`\`OH NOOO! \*giggles\* Don't tell me you don't know w... | 2023-07-23T08:15:39 | https://www.reddit.com/r/LocalLLaMA/comments/1578z5a/anyone_else_getting_copious_amounts_of_bouncy/ | theCube__ | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 1578z5a | false | null | t3_1578z5a | /r/LocalLLaMA/comments/1578z5a/anyone_else_getting_copious_amounts_of_bouncy/ | false | false | self | 47 | null |
dolphin-llama-13b | 230 | Today, I released Dolphin 🐬 an open-source implementation of [Microsoft's Orca](https://www.microsoft.com/en-us/research/publication/orca-progressive-learning-from-complex-explanation-traces-of-gpt-4/).
[https://huggingface.co/ehartford/dolphin-llama-13b](https://huggingface.co/ehartford/dolphin-llama-13b)
[**https:... | 2023-07-23T08:03:57 | https://www.reddit.com/r/LocalLLaMA/comments/1578ryz/dolphinllama13b/ | faldore | self.LocalLLaMA | 2023-07-23T09:19:06 | 0 | {} | 1578ryz | false | null | t3_1578ryz | /r/LocalLLaMA/comments/1578ryz/dolphinllama13b/ | false | false | self | 230 | null |
Target Modules for Llama-2 for better finetuning with qlora | 14 | Use these target modules for finetuning llama 2 in peft config
"target_modules": [
"q_proj",
"up_proj",
"o_proj",
"k_proj",
"down_proj",
"gate_proj",
"v_proj"
]
​ | 2023-07-23T07:36:02 | https://www.reddit.com/r/LocalLLaMA/comments/1578ahb/target_modules_for_llama2_for_better_finetuning/ | Sufficient_Run1518 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 1578ahb | false | null | t3_1578ahb | /r/LocalLLaMA/comments/1578ahb/target_modules_for_llama2_for_better_finetuning/ | false | false | self | 14 | null |
[Suggestion] Whenever you release a model, please give conversation examples? | 39 | Hey guys! First of all, I want to congratulate anyone making models or model processing methods. There are many things anyone can do, but this isn't one of them, you can be proud!
​
Now, I do have an issue with pretty much any model presented here : **I never have any idea of what I should expect from it**.
F... | 2023-07-23T07:30:46 | https://www.reddit.com/r/LocalLLaMA/comments/157876s/suggestion_whenever_you_release_a_model_please/ | LuluViBritannia | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 157876s | false | null | t3_157876s | /r/LocalLLaMA/comments/157876s/suggestion_whenever_you_release_a_model_please/ | false | false | self | 39 | null |
Poisoned models | 109 | It all started when someone has posted about "a new shiny Russian speaking model":
[https://www.reddit.com/r/LocalLLaMA/comments/154lcbg/rugpt\_35\_13b\_a\_new\_model\_for\_russian\_language/](https://www.reddit.com/r/LocalLLaMA/comments/154lcbg/rugpt_35_13b_a_new_model_for_russian_language/)
I dove a little deeper o... | 2023-07-23T06:38:59 | https://www.reddit.com/r/LocalLLaMA/comments/15779no/poisoned_models/ | uti24 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 15779no | false | null | t3_15779no | /r/LocalLLaMA/comments/15779no/poisoned_models/ | false | false | self | 109 | {'enabled': False, 'images': [{'id': '_rEX1xvwdv17x6NFAWQpYFNONQ0BKA5Qw0Eo0JX0zWU', 'resolutions': [{'height': 58, 'url': 'https://external-preview.redd.it/PUH10BjM5sFuvroA3mzy6AwPeP3T-kvtFLWUoE6Dho8.jpg?width=108&crop=smart&auto=webp&s=17279fa911dbea17f2a87e187f47ad903120ba87', 'width': 108}, {'height': 116, 'url': 'h... |
Glossary for machine learning and looking for something LLM specific. | 5 | Ironically search results are often spammed with AI generated Websites. I found these two to be helpful, and it would be great if someone found a language model specific glossary.
[https://developers.google.com/machine-learning/glossary](https://developers.google.com/machine-learning/glossary)
[https://ml-cheatsheet.... | 2023-07-23T06:28:08 | https://www.reddit.com/r/LocalLLaMA/comments/15772a1/glossary_for_machine_learning_and_looking_for/ | wreckingangel | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 15772a1 | false | null | t3_15772a1 | /r/LocalLLaMA/comments/15772a1/glossary_for_machine_learning_and_looking_for/ | false | false | self | 5 | {'enabled': False, 'images': [{'id': 'FJ6t7xCOQEzHctf_w44RxoBtAQtkMgjGAB17x0cwcuA', 'resolutions': [{'height': 56, 'url': 'https://external-preview.redd.it/be5K4QnmGZ5YLbWRV9p_o6hTh22zgV51EaUOBWfhyyg.jpg?width=108&crop=smart&auto=webp&s=4c2b9f1a71e813d704048454fc460d036ecc0c02', 'width': 108}, {'height': 113, 'url': 'h... |
Trying to create my own dataset but have no clue if I am doing this right | 7 | Hello I would love some feedback on if this is right or would even work. I made a dataset and have 2 versions, one my new data by itself and the other version merged with guanaco unchained. I think the merged one might work better but would love to get some thoughts from those that know more than me. I was thinking I w... | 2023-07-23T06:27:07 | https://www.reddit.com/r/LocalLLaMA/comments/15771o7/trying_to_create_my_own_dataset_but_have_no_clue/ | Azimn | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 15771o7 | false | null | t3_15771o7 | /r/LocalLLaMA/comments/15771o7/trying_to_create_my_own_dataset_but_have_no_clue/ | false | false | self | 7 | {'enabled': False, 'images': [{'id': '6vvqzdBUjmmAvXRK7Dm-Odo44XAZxVpwJ75XZklLQFM', 'resolutions': [{'height': 58, 'url': 'https://external-preview.redd.it/9O_cr7kmXQn2ItxCr_Kt449FHxWH1l9rgqt7Bp1U1Dc.jpg?width=108&crop=smart&auto=webp&s=f22e6e6629e65e02ea642a935cfb9cdf23cddf23', 'width': 108}, {'height': 116, 'url': 'h... |
Dockerized ubuntu evironment for Llama with llama.cpp | 1 | [removed] | 2023-07-23T06:22:49 | https://github.com/snakewizardd/llamaDocker | Happy_Chicken9835 | github.com | 1970-01-01T00:00:00 | 0 | {} | 1576yy2 | false | null | t3_1576yy2 | /r/LocalLLaMA/comments/1576yy2/dockerized_ubuntu_evironment_for_llama_with/ | false | false | 1 | {'enabled': False, 'images': [{'id': 'v21QP4TtqzczZ2cBgxEDtaaXta3l4lK3-RPUPyRHEnw', 'resolutions': [{'height': 54, 'url': 'https://external-preview.redd.it/M55cY8HEyRMear_v0IejrxpBxd4X6LBM5CIolqrjDFw.jpg?width=108&crop=smart&auto=webp&s=0235741c27e557526711b93a953ebc06f0c5cde0', 'width': 108}, {'height': 108, 'url': 'h... | |
How do you guys learn how to do any of these things? | 34 | I've gotten into using localLLMs as a way to curb the censoring on chatGPT but it seems like there is so much more to it than just downloading the LLM on my webui. I have no idea how to start learning about any of this but I would definitely love to! From what I've gathered apparently there are ways to train a model?? ... | 2023-07-23T06:13:31 | https://www.reddit.com/r/LocalLLaMA/comments/1576sy2/how_do_you_guys_learn_how_to_do_any_of_these/ | MyLaptopSpoil | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 1576sy2 | false | null | t3_1576sy2 | /r/LocalLLaMA/comments/1576sy2/how_do_you_guys_learn_how_to_do_any_of_these/ | false | false | self | 34 | null |
Can't run Llama 2 GPTQ on KoboldAI; is there a fix and, if not, are there more updated alternatives? | 1 | I've been trying to get KoboldAI to run for the past couple of days using the 7b GPTQ version of Llama 2 from [here](https://huggingface.co/TheBloke/Llama-2-7B-GPTQ). Initially I was using the working branch I had, which I believe was the 0cc4m branch on the United version that supports GPTQ. Although it was able to se... | 2023-07-23T05:18:19 | https://www.reddit.com/r/LocalLLaMA/comments/1575szm/cant_run_llama_2_gptq_on_koboldai_is_there_a_fix/ | Gyramuur | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 1575szm | false | null | t3_1575szm | /r/LocalLLaMA/comments/1575szm/cant_run_llama_2_gptq_on_koboldai_is_there_a_fix/ | false | false | self | 1 | {'enabled': False, 'images': [{'id': 'scnkn175QpfbMTdtoYxWh-I3soYhx9pJiHmW5tQQPMY', 'resolutions': [{'height': 58, 'url': 'https://external-preview.redd.it/MIHs_hUb2M9gxc4QGwbCk4JA2r5erDBnTB8Tbg735Rs.jpg?width=108&crop=smart&auto=webp&s=306a702906190a7340924eac46d7feb1f3eec45e', 'width': 108}, {'height': 116, 'url': 'h... |
Help needed to the approach | 0 | My boss asked me this :
"Attached the pdf file showing the financial statements of the our branches and their competitors. I want to build a gpt model referencing it.
Aim is to
Do financial analysis of multiple financial statements using the attached documents"
Do you understand what he's trying to do and can you... | 2023-07-23T05:15:21 | https://www.reddit.com/r/LocalLLaMA/comments/1575r2w/help_needed_to_the_approach/ | paulus_aurellius | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 1575r2w | false | null | t3_1575r2w | /r/LocalLLaMA/comments/1575r2w/help_needed_to_the_approach/ | false | false | self | 0 | null |
In just a week or so, there are so many new models on the new LLM leaderboard. What's your thought? | 35 | Just a few weeks ago, falcon-40b is at the top and became the most mentioned model apart from GPT4. Now suddenly so many new models came out. Some contain only 30b parameters. What's your thoughts and how do you comprehend the constantly improving models? Also, some said falcon-40b-instruct is comparable to the first-g... | 2023-07-23T03:54:56 | https://www.reddit.com/r/LocalLLaMA/comments/15748wc/in_just_a_week_or_so_there_are_so_many_new_models/ | PrestigiousPancake | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 15748wc | false | null | t3_15748wc | /r/LocalLLaMA/comments/15748wc/in_just_a_week_or_so_there_are_so_many_new_models/ | false | false | self | 35 | null |
function calling with llama-2? | 29 | Have been looking into the feasibility of operating llama-2 with agents through a feature similar to OpenAI's function calling.
Have had very little success through prompting so fa :( Just wondering if anyone had a different experience of if we might have to go down the fine-tune route as OpenAI did. | 2023-07-23T03:46:04 | https://www.reddit.com/r/LocalLLaMA/comments/15742zf/function_calling_with_llama2/ | LyPreto | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 15742zf | false | null | t3_15742zf | /r/LocalLLaMA/comments/15742zf/function_calling_with_llama2/ | false | false | self | 29 | null |
Help me finetune Llama-2-7B with qlora | 2 | I am trying to finetune Llama-2-7B with this script https://github.com/artidoro/qlora/blob/main/scripts/finetune_guanaco_7b.sh
Please help me with
--source_max_len 16 \
--target_max_len 512 \
What should I use? | 2023-07-23T03:25:41 | https://www.reddit.com/r/LocalLLaMA/comments/1573pf2/help_me_finetune_llama27b_with_qlora/ | Sufficient_Run1518 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 1573pf2 | false | null | t3_1573pf2 | /r/LocalLLaMA/comments/1573pf2/help_me_finetune_llama27b_with_qlora/ | false | false | self | 2 | {'enabled': False, 'images': [{'id': 'tozPKa5-9dLqIt7uc63UE2WcaocD0i-HTS-qiRZnRaI', 'resolutions': [{'height': 54, 'url': 'https://external-preview.redd.it/14ik5ZS42nAjZ_xDltNrlMUhTu67KXr4MltxlScrElU.jpg?width=108&crop=smart&auto=webp&s=99fc2e55c75d97c9f9a2e2f7817c09a1caedf28f', 'width': 108}, {'height': 108, 'url': 'h... |
AlpacaCielo 13b, Llama-2 based model for storytelling and roleplay. | 63 | Back in the "old days", I really enjoyed creative models such as Alpasta, so I wanted to bring a similar experience to Llama-2. So I created AlpacaCielo. It is a triple merge of Nous Hermes + Guanaco + Storytelling, and is an attempt to get the best of all worlds to get a smart & creative model. I've done minimal te... | 2023-07-23T01:50:22 | https://www.reddit.com/r/LocalLLaMA/comments/1571srk/alpacacielo_13b_llama2_based_model_for/ | pokeuser61 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 1571srk | false | null | t3_1571srk | /r/LocalLLaMA/comments/1571srk/alpacacielo_13b_llama2_based_model_for/ | false | false | self | 63 | {'enabled': False, 'images': [{'id': 'It9u9WCOskxFv8Pt_vUgR2w-W18_WAvJDGUkxKUqGOY', 'resolutions': [{'height': 58, 'url': 'https://external-preview.redd.it/Mmqv2FQGy4ucbBCg8b_xXl1KyX1WFEa6lQdaUFTp4jk.jpg?width=108&crop=smart&auto=webp&s=3fe55b63d93fd8686ebdd6535d27871db01d0575', 'width': 108}, {'height': 116, 'url': 'h... |
Is it possible we could see fine tuned models of GPT-3.5-Turbo and GPT-4 that are more uncensored and raw, similar to what we’ve seen with previous LLaMA/Vicuna models? | 34 | 2023-07-23T01:26:45 | sardoa11 | i.redd.it | 1970-01-01T00:00:00 | 0 | {} | 1571b84 | false | null | t3_1571b84 | /r/LocalLLaMA/comments/1571b84/is_it_possible_we_could_see_fine_tuned_models_of/ | false | false | 34 | {'enabled': True, 'images': [{'id': '8Jw3JjnPs2SGIGOsAo5fWaS64hG6hEwBSz2K1RYNnHA', 'resolutions': [{'height': 41, 'url': 'https://preview.redd.it/k2ph2hahamdb1.jpg?width=108&crop=smart&auto=webp&s=391c36e0501e90a7a10b8fc5d73b3c38df2044ec', 'width': 108}, {'height': 83, 'url': 'https://preview.redd.it/k2ph2hahamdb1.jpg?... | |||
Having trouble with Llama2 Guanaco 7B / incoherent responses | 7 | **Guanaco QLoRA 7B (Q4\_K\_M)**
Hi guys, trying to create a character that responds in character / roleplay. my model instruction is Faraday's default:
Text transcript of a never-ending conversation between {user} and {character}. In the transcript, gestures and other non-verbal actions are written between aste... | 2023-07-23T00:48:11 | https://www.reddit.com/r/LocalLLaMA/comments/1570hcm/having_trouble_with_llama2_guanaco_7b_incoherent/ | Kep0a | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 1570hcm | false | null | t3_1570hcm | /r/LocalLLaMA/comments/1570hcm/having_trouble_with_llama2_guanaco_7b_incoherent/ | false | false | self | 7 | null |
What parameters work best for 8k context? | 1 | [removed] | 2023-07-23T00:23:48 | https://www.reddit.com/r/LocalLLaMA/comments/156zy6i/what_parameters_work_best_for_8k_context/ | EcstaticVenom | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 156zy6i | false | null | t3_156zy6i | /r/LocalLLaMA/comments/156zy6i/what_parameters_work_best_for_8k_context/ | false | false | self | 1 | null |
Yet another QLoRA tutorial | 92 | I fine-tuned OpenLLama 7B using QLoRA on transcripts of the Lex Fridman podcast to generate a fictional conversation of Lex with Barack Obama. This is not a model ready for use but rather a valuable step-by-step explanation illustrating the process, driven by the desire to learn more about training large language model... | 2023-07-22T23:23:30 | https://www.reddit.com/r/LocalLLaMA/comments/156ylgf/yet_another_qlora_tutorial/ | HatEducational9965 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 156ylgf | false | null | t3_156ylgf | /r/LocalLLaMA/comments/156ylgf/yet_another_qlora_tutorial/ | false | false | self | 92 | {'enabled': False, 'images': [{'id': '3fK4xu3PY7jH5gSmbBWirPCF_DDbwgIBR0EB9M-4Sio', 'resolutions': [{'height': 118, 'url': 'https://external-preview.redd.it/oA3IuQ1J6tZpBRPqXZWVixunfwiwDi3u7H84-d8b6Lk.jpg?width=108&crop=smart&auto=webp&s=8d08817044b1fb74fa8d7d8bec4965d31d564ebf', 'width': 108}, {'height': 236, 'url': '... |
How can I start learning about LLMs ? | 23 | I am intrigued by LLMs, Deep Learning, and Machine Learning and I would really like to learn how to launch a model, fine-tune it, or embed it but I feel a bit lost, do you have any tips for getting started or online courses that can help me achieve this goal? | 2023-07-22T21:52:40 | https://www.reddit.com/r/LocalLLaMA/comments/156wfsp/how_can_i_start_learning_about_llms/ | redule26 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 156wfsp | false | null | t3_156wfsp | /r/LocalLLaMA/comments/156wfsp/how_can_i_start_learning_about_llms/ | false | false | self | 23 | null |
is RTX 3090 used for mining good for Local LLMs? | 23 | I see a vendor in my city with 10 used (RTX 3090) cards, 2 used for mining and 8 used in gaming cafes. prices range from 370$ to 430$. are these good for Running big LLMs Locally? I was thinking of getting 2 but not sure about how they'll perform as 30B models and above are very memory intensive.
any thoughts? and th... | 2023-07-22T21:37:31 | https://www.reddit.com/r/LocalLLaMA/comments/156w2jp/is_rtx_3090_used_for_mining_good_for_local_llms/ | Dadjann | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 156w2jp | false | null | t3_156w2jp | /r/LocalLLaMA/comments/156w2jp/is_rtx_3090_used_for_mining_good_for_local_llms/ | false | false | self | 23 | null |
Has anyone successfully fine-tuned MPT-7B? | 4 | I'm new to all this LLM stuff and I've been trying to see if I can adapt the Hugging Face [language modeling example](https://colab.research.google.com/github/huggingface/notebooks/blob/main/transformers_doc/en/pytorch/language_modeling.ipynb) to use MPT-7B, but it runs out of memory on the training step basically no m... | 2023-07-22T20:00:50 | https://www.reddit.com/r/LocalLLaMA/comments/156tppl/has_anyone_successfully_finetuned_mpt7b/ | Proeliata | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 156tppl | false | null | t3_156tppl | /r/LocalLLaMA/comments/156tppl/has_anyone_successfully_finetuned_mpt7b/ | false | false | self | 4 | {'enabled': False, 'images': [{'id': 'nkhh65ujo5BznFJFojoMPaKjGuLSpPj6KGhRov-ykOg', 'resolutions': [{'height': 108, 'url': 'https://external-preview.redd.it/MrcDZx2izDY9ERwgWmMS-Hm2M3GEKZgeYLDszSh-KrQ.jpg?width=108&crop=smart&auto=webp&s=4b647239f77bf713f4a6209cfa4867351c055fd9', 'width': 108}, {'height': 216, 'url': '... |
Looking for resources to fine-tune a model "from scratch" | 1 | Hi!
So my friend and I we're looking to explore all these topics of LLM fine-tuning and quantization etc. But we don't really know where to start.
We have a solid understanding of machine learning theory side (LLMs included) and are good with Python. So we'd like to make some kind of notebook where we have something ... | 2023-07-22T19:41:58 | https://www.reddit.com/r/LocalLLaMA/comments/156t90f/looking_for_resources_to_finetune_a_model_from/ | LoLingLikeHell | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 156t90f | false | null | t3_156t90f | /r/LocalLLaMA/comments/156t90f/looking_for_resources_to_finetune_a_model_from/ | false | false | default | 1 | null |
Did GPT-4 really get worse? We built an evaluation framework so you can find out | 1 | [removed] | 2023-07-22T19:37:03 | https://www.reddit.com/r/LocalLLaMA/comments/156t4rl/did_gpt4_really_get_worse_we_built_an_evaluation/ | hegel-ai | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 156t4rl | false | null | t3_156t4rl | /r/LocalLLaMA/comments/156t4rl/did_gpt4_really_get_worse_we_built_an_evaluation/ | false | false | self | 1 | {'enabled': False, 'images': [{'id': 'jyQQDsewOakYxiv0g_fyaC75u1-VWTozH-60lliqvpI', 'resolutions': [{'height': 54, 'url': 'https://external-preview.redd.it/VrmXgXNwPE3WCG8OLPwgUvz020iYf02XCTI3ic85Qoc.jpg?width=108&crop=smart&auto=webp&s=4ee94dbf11c076abadc54e222372ea5dd992be04', 'width': 108}, {'height': 108, 'url': 'h... |
GPU requirements for over 2048 context/tokens | 42 | Are there any standardised lists which state how much VRAM is needed for different combinations?
For example
13b with 2048 context
13b with 4096 context
13b with 8192 context
30b with 2048 context
Etc.... | 2023-07-22T18:56:45 | https://www.reddit.com/r/LocalLLaMA/comments/156s5jg/gpu_requirements_for_over_2048_contexttokens/ | Useful-Command-8793 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 156s5jg | false | null | t3_156s5jg | /r/LocalLLaMA/comments/156s5jg/gpu_requirements_for_over_2048_contexttokens/ | false | false | self | 42 | null |
Hey, has anyone finetuned Llama2 for fiction writers? if not could someone point me in the direction of a tutorial so I can do it? | 1 | Title says it all really. | 2023-07-22T18:39:24 | https://www.reddit.com/r/LocalLLaMA/comments/156rqgq/hey_has_anyone_finetuned_llama2_for_fiction/ | Benedictus111 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 156rqgq | false | null | t3_156rqgq | /r/LocalLLaMA/comments/156rqgq/hey_has_anyone_finetuned_llama2_for_fiction/ | false | false | self | 1 | null |
Exploring the guardrails on the censored model, must have hit a nerve | 58 | 2023-07-22T17:57:40 | Kelvin_451 | i.redd.it | 1970-01-01T00:00:00 | 0 | {} | 156qqd2 | false | null | t3_156qqd2 | /r/LocalLLaMA/comments/156qqd2/exploring_the_guardrails_on_the_censored_model/ | false | false | 58 | {'enabled': True, 'images': [{'id': 'NxdvrlYLcaDaUfpYR5KCJuY2LdPpNSiZmACpV9hH2wg', 'resolutions': [{'height': 216, 'url': 'https://preview.redd.it/xp8jmsyu1kdb1.png?width=108&crop=smart&auto=webp&s=82e9fdd7e1e2660d2c6f4d14d51fc786c5771078', 'width': 108}, {'height': 432, 'url': 'https://preview.redd.it/xp8jmsyu1kdb1.pn... | |||
What affect the speed of the gptj model loading? | 1 | I ran privateGPT on both my Ubuntu desktop and an AWS EC2 instance, just for comparison. Even if I use a beefy instance, which is much more powerful than the desktop on the aspects of # of cpus, and memory size, this model loading step is much slower on the AWS instance than it is on my desktop, like at least 5 times s... | 2023-07-22T17:46:41 | old_enough_to_drink | i.redd.it | 1970-01-01T00:00:00 | 0 | {} | 156qh5i | false | null | t3_156qh5i | /r/LocalLLaMA/comments/156qh5i/what_affect_the_speed_of_the_gptj_model_loading/ | false | false | 1 | {'enabled': True, 'images': [{'id': 'oJ23H0AZSkDJba-ksQZiK4wxbFE3GXdZjJhjQUnJvxc', 'resolutions': [{'height': 77, 'url': 'https://preview.redd.it/jme3qtda0kdb1.jpg?width=108&crop=smart&auto=webp&s=56bc9e9ebc09fd20ced5646c3880e929c900e316', 'width': 108}, {'height': 155, 'url': 'https://preview.redd.it/jme3qtda0kdb1.jpg... | ||
Could LLaMA 2 be available on mobile for roleplay? | 0 | or just be available without needing 8.06 gb ram on the computer?? (faraday) | 2023-07-22T17:34:26 | https://www.reddit.com/r/LocalLLaMA/comments/156q6i2/could_llama_2_be_available_on_mobile_for_roleplay/ | rebeldocs | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 156q6i2 | false | null | t3_156q6i2 | /r/LocalLLaMA/comments/156q6i2/could_llama_2_be_available_on_mobile_for_roleplay/ | false | false | self | 0 | null |
Text-to-SQL WizardCoder - HF Spaces Demo | 23 | 2023-07-22T17:24:22 | https://huggingface.co/spaces/richardr1126/sql-skeleton-wizardcoder-demo | richardr1126 | huggingface.co | 1970-01-01T00:00:00 | 0 | {} | 156pxot | false | null | t3_156pxot | /r/LocalLLaMA/comments/156pxot/texttosql_wizardcoder_hf_spaces_demo/ | false | false | 23 | {'enabled': False, 'images': [{'id': 'UgzQg7MYQ-HCS6Wx2TSROSsYoD9tNc4fxeYw4Id9Xfc', 'resolutions': [{'height': 58, 'url': 'https://external-preview.redd.it/8T2R068MEOUAXIA9iLnneoz1TqDsgGABSpZLJ1w_BZY.jpg?width=108&crop=smart&auto=webp&s=ab1db293f3359644a5cfd88d46f4d49fc00fc8f4', 'width': 108}, {'height': 116, 'url': 'h... | ||
How to keep conversation going in llama2-chat-hf? | 1 | HI, I want to build a local chat bot with a functionality similar to chatgpt website. Just started my ai journey, so need a help there, didn't find any information in google.
I have a conversation window with a conversation going on, but how to force the model to 'memorize' previous question and answers? Should I fine... | 2023-07-22T17:08:09 | https://www.reddit.com/r/LocalLLaMA/comments/156pjn6/how_to_keep_conversation_going_in_llama2chathf/ | Jack_Hackerman | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 156pjn6 | false | null | t3_156pjn6 | /r/LocalLLaMA/comments/156pjn6/how_to_keep_conversation_going_in_llama2chathf/ | false | false | self | 1 | null |
Where to find 'adapter_config.json' ? | 1 | Hello guys
on [**open\_llm\_leaderboard**](https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard) there are many interesting 30b loras with extremely good performance
But HOW CAN I LOAD IT without adapter\_config.json?
I am really sorry that I am new to the field, but if I didn't understand it wrongly, ... | 2023-07-22T16:16:27 | https://www.reddit.com/r/LocalLLaMA/comments/156o94b/where_to_find_adapter_configjson/ | JohnSmith004 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 156o94b | false | null | t3_156o94b | /r/LocalLLaMA/comments/156o94b/where_to_find_adapter_configjson/ | false | false | self | 1 | {'enabled': False, 'images': [{'id': 'EN0-abblERL52DxeoNzcxdkhvXEwLdZMJTS58Umjs64', 'resolutions': [{'height': 58, 'url': 'https://external-preview.redd.it/pnEIDVgN3O3UZSEZF8G101Cpm5FLu9i3k_abBlep_2c.jpg?width=108&crop=smart&auto=webp&s=6fbb309f983333cbaf528bd40f8d6ffb39877704', 'width': 108}, {'height': 116, 'url': 'h... |
Llama2-22b, a model merge tuned on RedPajama | 79 | 2023-07-22T16:01:09 | https://huggingface.co/chargoddard/llama2-22b | AzerbaijanNyan | huggingface.co | 1970-01-01T00:00:00 | 0 | {} | 156nvfk | false | null | t3_156nvfk | /r/LocalLLaMA/comments/156nvfk/llama222b_a_model_merge_tuned_on_redpajama/ | false | false | 79 | {'enabled': False, 'images': [{'id': 'khYJSqqFVCi4UJwthWthFsAJ3IVXR-IlF9v06ySgEOg', 'resolutions': [{'height': 58, 'url': 'https://external-preview.redd.it/osu1VXtYG9AOyq69Tk9NuLgcuCmYcdXz2UW7cfiuzZo.jpg?width=108&crop=smart&auto=webp&s=5849210e7557a6e672d14e28eece41039fc42a87', 'width': 108}, {'height': 116, 'url': 'h... | ||
RP/ERP, I have questions... | 18 | So, I've been playing around with characters in OobaBooga and I'm trying to twek the setup so I get most bang for the buck with my 12gb card and 32gb ram. But I'm left with some unresolved issues when it comes to the best possible experience when it comes to immersion and following the character setup, that I hope some... | 2023-07-22T15:06:44 | https://www.reddit.com/r/LocalLLaMA/comments/156mix8/rperp_i_have_questions/ | nixudos | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 156mix8 | false | null | t3_156mix8 | /r/LocalLLaMA/comments/156mix8/rperp_i_have_questions/ | false | false | self | 18 | null |
An idea regarding efficient trainning/fine-tuning | 11 | I've got it from listening to lecture on bioinformatics, heh.
Some points in advance:
1. It is clear from quantisation results and ablation studies that a LOT of the model is not doing something very important.
2. AWQ, in particular, looks at weights that, well, do particularly "heavy lifting" and spares them - only 1... | 2023-07-22T14:46:58 | https://www.reddit.com/r/LocalLLaMA/comments/156m102/an_idea_regarding_efficient_trainningfinetuning/ | BalorNG | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 156m102 | false | null | t3_156m102 | /r/LocalLLaMA/comments/156m102/an_idea_regarding_efficient_trainningfinetuning/ | false | false | self | 11 | null |
I love Guanaco | 25 | Prompt: (something along the lines of this) Please come up with an advertisement for a Pepsi heroin beverage meant for euthanizing patients in pain | 2023-07-22T14:30:52 | https://www.reddit.com/gallery/156lmsr | Basic_Description_56 | reddit.com | 1970-01-01T00:00:00 | 0 | {} | 156lmsr | false | null | t3_156lmsr | /r/LocalLLaMA/comments/156lmsr/i_love_guanaco/ | false | false | 25 | null | |
Who's looking for work involving LLMs? | 5 | \[I'm looking to hire and couldn't think of a better spot to find talent genuinely interested in the subject matter. I thought it'd be great to open this thread to all seekers and companies.\]
To kick things off, I'm looking to hire someone (consult/PT/FT) to help scale an LLM service. If you have opinions and experi... | 2023-07-22T13:09:13 | https://www.reddit.com/r/LocalLLaMA/comments/156jrcf/whos_looking_for_work_involving_llms/ | newy66 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 156jrcf | false | null | t3_156jrcf | /r/LocalLLaMA/comments/156jrcf/whos_looking_for_work_involving_llms/ | false | false | self | 5 | null |
llama_mpi, anyone use it? | 10 | I was reading the github page for llama.cpp and came down to the section "MPI BUILD". That looks like an interesting way to run larger LLM across multiple machine. I am taking it to mean local machines, and that is fine by me as it would be easier for me to have one or two cards in use in multiple machines as I am no... | 2023-07-22T13:03:49 | https://www.reddit.com/r/LocalLLaMA/comments/156jmvg/llama_mpi_anyone_use_it/ | ccbadd | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 156jmvg | false | null | t3_156jmvg | /r/LocalLLaMA/comments/156jmvg/llama_mpi_anyone_use_it/ | false | false | self | 10 | null |
Link of Llama 2 uncensored | 0 | Can anyone provide me the direct link to just chat with the llama 2 uncensored version ? | 2023-07-22T12:01:20 | https://www.reddit.com/r/LocalLLaMA/comments/156ia7v/link_of_llama_2_uncensored/ | Impressive_Plastic39 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 156ia7v | false | null | t3_156ia7v | /r/LocalLLaMA/comments/156ia7v/link_of_llama_2_uncensored/ | false | false | self | 0 | null |
Link of Llama 2 uncensored | 1 | Can anyone provide me the direct link to just chat with the llama 2 uncensored version ? | 2023-07-22T12:01:20 | https://www.reddit.com/r/LocalLLaMA/comments/156ia7l/link_of_llama_2_uncensored/ | Impressive_Plastic39 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 156ia7l | false | null | t3_156ia7l | /r/LocalLLaMA/comments/156ia7l/link_of_llama_2_uncensored/ | false | false | self | 1 | null |
I made Llama2 7B into a really useful coder | 355 | Hey guys,
First time sharing any personally fine-tuned model so bless me.
Introducing codeCherryPop - a qlora fine-tuned 7B llama2 with 122k coding instructions and it's extremely coherent in conversations as well as coding.
Do try it out here - https://huggingface.co/TokenBender/llama2-7b-chat-hf-codeCherryPop-qLoR... | 2023-07-22T11:39:06 | https://www.reddit.com/r/LocalLLaMA/comments/156htzy/i_made_llama2_7b_into_a_really_useful_coder/ | ahm_rimer | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 156htzy | false | null | t3_156htzy | /r/LocalLLaMA/comments/156htzy/i_made_llama2_7b_into_a_really_useful_coder/ | false | false | self | 355 | {'enabled': False, 'images': [{'id': '_1qNswe8daQmDrTQeV7_KsBfdNrceifW9agUew6uHwo', 'resolutions': [{'height': 58, 'url': 'https://external-preview.redd.it/CqA7PvnpL1TzXR5Mku6on0iI_OP9D68I7sTqRRjXcmo.jpg?width=108&crop=smart&auto=webp&s=78dd14e34ed3b35bb8d421da0fb6ccf967f7f473', 'width': 108}, {'height': 116, 'url': 'h... |
FYP Project LLM powered chatbot | 1 | Hey Guys, I am a computer engineering student who is approaching his Final year, as such I have to decide on an FYP Project, with the recent trend in Transformer based AI Research, I wanted to do a project on an LLM powered chatbot which I plan to create by using the student tier of AWS and other discounts I can get m... | 2023-07-22T11:18:12 | https://www.reddit.com/r/LocalLLaMA/comments/156hfmn/fyp_project_llm_powered_chatbot/ | Demonking6444 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 156hfmn | false | null | t3_156hfmn | /r/LocalLLaMA/comments/156hfmn/fyp_project_llm_powered_chatbot/ | false | false | self | 1 | null |
[D] Constraining Llama models with context free grammars | 61 | An interesting piece of development happening in the llama.cpp repo, sampling tokens according to the supplied context free grammar.
https://github.com/ggerganov/llama.cpp/pull/1773
One of the things we notice with llama models is while they are decent at everyday conversations, the performance drops for structured o... | 2023-07-22T10:46:35 | https://www.reddit.com/r/LocalLLaMA/comments/156gu8c/d_constraining_llama_models_with_context_free/ | ironborn123 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 156gu8c | false | null | t3_156gu8c | /r/LocalLLaMA/comments/156gu8c/d_constraining_llama_models_with_context_free/ | false | false | self | 61 | {'enabled': False, 'images': [{'id': '1HkNkq0xkmpSw6HXPZiwQIPsdRL98lc9T9sORrdcZIg', 'resolutions': [{'height': 54, 'url': 'https://external-preview.redd.it/7EsB-pMzEzHLqLmGLx6NGEGNTvSu4dkeGp2OGaUNOG0.jpg?width=108&crop=smart&auto=webp&s=ece9a7391c1e92d6a7ac22ba6ca33fd44d2ef47c', 'width': 108}, {'height': 108, 'url': 'h... |
Examples of real business applications | 40 | Obviously the popularity of this tech is very new, but I am sure they started applying it to real businesses. Such as a newspaper who let go of some junior writers and replaced them with AI. Do you know any youtube channels or other sources where they show examples like that? Like internal company onboarding chatbots o... | 2023-07-22T10:34:08 | https://www.reddit.com/r/LocalLLaMA/comments/156gm75/examples_of_real_business_applications/ | VentrueLibrary | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 156gm75 | false | null | t3_156gm75 | /r/LocalLLaMA/comments/156gm75/examples_of_real_business_applications/ | false | false | self | 40 | null |
Best Role Play Models | 28 | Things move so fast, I'm currently using Wizard LM for chat role play, both SFW and NSFW.
I've been experiment with a few others namely Guanaco and Vicuna. Both seem decent, there are so many others out there though.
Can anyone recommend any others which you have enjoyed and give a good experience for role play? | 2023-07-22T09:44:02 | https://www.reddit.com/r/LocalLLaMA/comments/156fpt2/best_role_play_models/ | Useful-Command-8793 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 156fpt2 | false | null | t3_156fpt2 | /r/LocalLLaMA/comments/156fpt2/best_role_play_models/ | false | false | self | 28 | null |
A LIMA-like Llama2 finetune just for RP | 32 | 2023-07-22T09:27:50 | https://huggingface.co/lemonilia/limarp-llama2 | brown2green | huggingface.co | 1970-01-01T00:00:00 | 0 | {} | 156ffne | false | null | t3_156ffne | /r/LocalLLaMA/comments/156ffne/a_limalike_llama2_finetune_just_for_rp/ | false | false | 32 | {'enabled': False, 'images': [{'id': 'Kl8L9OmzdMV6C7Vxceux9U9R0nNcWv9f9kF1d_D7mWE', 'resolutions': [{'height': 58, 'url': 'https://external-preview.redd.it/psSnTcKvAdSBNNaQK-tMxmZX2QWjOwi_aX5I8tyV3Es.jpg?width=108&crop=smart&auto=webp&s=95c877192822379482fc54eee532d045ea818ba5', 'width': 108}, {'height': 116, 'url': 'h... | ||
Llama or alternatives in tflite format | 4 | Sorry if this has already been answered (I’ve had a bit of a look though) but I was wondering if it’s possible to convert llama into a .tflite file to be able to be run on a coral usb accelerator for example?
I’ve been searching around (asking gpt4) and all I’ve come across is that it will either be extremely complex ... | 2023-07-22T09:13:05 | Effective_Football35 | i.redd.it | 1970-01-01T00:00:00 | 0 | {} | 156f6eo | false | null | t3_156f6eo | /r/LocalLLaMA/comments/156f6eo/llama_or_alternatives_in_tflite_format/ | false | false | 4 | {'enabled': True, 'images': [{'id': 'odPLssqOexUGQtQ9azyOvgPi4ExWjhpVSznoGH3e_x0', 'resolutions': [{'height': 60, 'url': 'https://preview.redd.it/sd91qnprghdb1.jpg?width=108&crop=smart&auto=webp&s=af8bcfc545b164d5bb66e7d74d057262072b0a2b', 'width': 108}, {'height': 121, 'url': 'https://preview.redd.it/sd91qnprghdb1.jpg... | ||
Wizard-Vicuna-13B-HF-Uncensored bad/outdated files? | 1 | [removed] | 2023-07-22T08:49:15 | https://www.reddit.com/r/LocalLLaMA/comments/156er3q/wizardvicuna13bhfuncensored_badoutdated_files/ | redzorino | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 156er3q | false | null | t3_156er3q | /r/LocalLLaMA/comments/156er3q/wizardvicuna13bhfuncensored_badoutdated_files/ | false | false | self | 1 | {'enabled': False, 'images': [{'id': 'lRl3SipxuAd2pfX-TGfnDhxzpabUu4mLrPvD6h_TfTI', 'resolutions': [{'height': 58, 'url': 'https://external-preview.redd.it/Zis6jQ1oz0Ceq_p_SAr0ag83aPRdD-nFmzXf8UatMGk.jpg?width=108&crop=smart&auto=webp&s=b76f8ccbfd16146ac1855fe96fc4710ff29e946e', 'width': 108}, {'height': 116, 'url': 'h... |
Getting LLAMA 2 or any other local LLM to answer using specific format | 13 | Hello,
Whenever I try to constrain local LLMs to just answer the question I get flowery text like: ".Sure, I'd be happy to help! Based on the given...", and then the LLM explains why it did what it did. Is there a way to get a single answer like? Like if I ask what is the capital of France, is should say "Paris" and ... | 2023-07-22T07:57:27 | https://www.reddit.com/r/LocalLLaMA/comments/156dv5a/getting_llama_2_or_any_other_local_llm_to_answer/ | SwordfishGreat4532 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 156dv5a | false | null | t3_156dv5a | /r/LocalLLaMA/comments/156dv5a/getting_llama_2_or_any_other_local_llm_to_answer/ | false | false | self | 13 | null |
Training dataset should include the system commands token? | 1 | [removed] | 2023-07-22T07:40:36 | https://www.reddit.com/r/LocalLLaMA/comments/156dki4/training_dataset_should_include_the_system/ | Either-Job-341 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 156dki4 | false | null | t3_156dki4 | /r/LocalLLaMA/comments/156dki4/training_dataset_should_include_the_system/ | 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.