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 ⌀ |
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
Models for editing/assisting with writing (nsfw) | 1 | [removed] | 2023-09-17T04:35:55 | https://www.reddit.com/r/LocalLLaMA/comments/16krjhg/models_for_editingassisting_with_writing_nsfw/ | sbalani | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 16krjhg | false | null | t3_16krjhg | /r/LocalLLaMA/comments/16krjhg/models_for_editingassisting_with_writing_nsfw/ | false | false | nsfw | 1 | null |
The TinyLlama Model has a Chat version! | 27 | I saw a post about the base model, but just wanted to let people know about the Chat version. Its a super simple example finetune on open assistant-guanaco, buts it actually pretty ok to use, and could probably be fine-tuned to a much better extent.
also, I do have a chat UI under PR if you want to use it the UI way,... | 2023-09-17T03:05:32 | https://www.reddit.com/r/LocalLLaMA/comments/16kpx78/the_tinyllama_model_has_a_chat_version/ | vatsadev | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 16kpx78 | false | null | t3_16kpx78 | /r/LocalLLaMA/comments/16kpx78/the_tinyllama_model_has_a_chat_version/ | false | false | self | 27 | {'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': '... |
Apple's tiny 34M paramters transformer | 84 | [Jack Cook Blog](https://jackcook.com/2023/09/08/predictive-text.html)
I hope this is not a double post, but I haven't heard of it until now.
Apple is apparently working on a "very small large“ language model for iOS and macOS. The model is said to have 34 million parameters. The model completes individual words and ... | 2023-09-17T02:36:12 | https://www.reddit.com/r/LocalLLaMA/comments/16kpd1g/apples_tiny_34m_paramters_transformer/ | Evening_Ad6637 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 16kpd1g | false | null | t3_16kpd1g | /r/LocalLLaMA/comments/16kpd1g/apples_tiny_34m_paramters_transformer/ | false | false | self | 84 | null |
How well does a regular Llama 2 handle 8k scaling? | 14 | So I got curious how well something like Chronos-Hermes-v2 might handle being scaled beyond 4096, and started with doing some test NTK scaling.
Context: 6144
Alpha: 1.5
Rope Scale Base: 17000
I ran a couple of tests, with the context being sent over clocking in at around 5500 tokens, and it honestly was doing jus... | 2023-09-17T01:05:41 | https://www.reddit.com/r/LocalLLaMA/comments/16knk46/how_well_does_a_regular_llama_2_handle_8k_scaling/ | LearningSomeCode | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 16knk46 | false | null | t3_16knk46 | /r/LocalLLaMA/comments/16knk46/how_well_does_a_regular_llama_2_handle_8k_scaling/ | false | false | self | 14 | null |
CodeLLaMA makes for a great base for finetuning with 16K ctx | 24 | Yes, I know [it's been said by some of you previously](https://www.reddit.com/r/LocalLLaMA/comments/165tb0q/the_codellama_base_is_strangely_fantastic_general/), but I feel this deserves more attention. Right now, I've done a quick finetune of CodeLLaMA13B with alpaca\_lora\_4bit and it's finally working wonders with ab... | 2023-09-17T00:07:59 | https://www.reddit.com/r/LocalLLaMA/comments/16kmcgk/codellama_makes_for_a_great_base_for_finetuning/ | 2muchnet42day | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 16kmcgk | false | null | t3_16kmcgk | /r/LocalLLaMA/comments/16kmcgk/codellama_makes_for_a_great_base_for_finetuning/ | false | false | self | 24 | null |
[Corrected] Is it possible to train a local model to rival the performance of GPT 3 or 3.5? | 1 | If not what is the limit/reasonable cap to the abilities of local models? | 2023-09-16T23:46:47 | https://www.reddit.com/r/LocalLLaMA/comments/16klvyp/corrected_is_it_possible_to_train_a_local_model/ | Old-Calligrapher1950 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 16klvyp | false | null | t3_16klvyp | /r/LocalLLaMA/comments/16klvyp/corrected_is_it_possible_to_train_a_local_model/ | false | false | self | 1 | null |
15 times Faster than Llama 2: Introducing DeciLM | 7 | 2023-09-16T23:36:06 | https://deci.ai/blog/decilm-15-times-faster-than-llama2-nas-generated-llm-with-variable-gqa/ | skippybosco | deci.ai | 1970-01-01T00:00:00 | 0 | {} | 16klnri | false | null | t3_16klnri | /r/LocalLLaMA/comments/16klnri/15_times_faster_than_llama_2_introducing_decilm/ | false | false | 7 | {'enabled': False, 'images': [{'id': '8JasBexDQLW0G7y4n6ThMQH77AmFW5N6s2HUrariAC4', 'resolutions': [{'height': 60, 'url': 'https://external-preview.redd.it/jsvkz-6SkJ37uBSqTJV96vR0sPDSydNLnAdEv43nYhA.jpg?width=108&crop=smart&auto=webp&s=b113841b47c7b8885f1049233e7c226d00918b12', 'width': 108}, {'height': 121, 'url': 'h... | ||
Did NVLINK work for anyone with 2x 3090s? | 14 | I have a WRX80 motherboard with the PCIe slots set to x8 each. NVLINK doesn't seem to be even detected in 'nvidia-smi nvlink -s' in Ubuntu 22.04.
Do I need to do anything special to make it work? Have people noticed any training gains from it? | 2023-09-16T23:14:57 | https://www.reddit.com/r/LocalLLaMA/comments/16kl62b/did_nvlink_work_for_anyone_with_2x_3090s/ | red_dragon | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 16kl62b | false | null | t3_16kl62b | /r/LocalLLaMA/comments/16kl62b/did_nvlink_work_for_anyone_with_2x_3090s/ | false | false | self | 14 | null |
If I want to train a local model on par with chatGPT how difficult would it be and how much would it cost? | 0 | How many gigabytes or what hardware would I need and where do I even start? I see people saying their local models rival gpt. | 2023-09-16T22:08:22 | https://www.reddit.com/r/LocalLLaMA/comments/16kjl2l/if_i_want_to_train_a_local_model_on_par_with/ | Old-Calligrapher1950 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 16kjl2l | false | null | t3_16kjl2l | /r/LocalLLaMA/comments/16kjl2l/if_i_want_to_train_a_local_model_on_par_with/ | false | false | self | 0 | null |
Made a simple github tool to get GPU vRAM breakdown for finetuning & inference of any Huggingface LLM. Supports GGML & bnb quantization | 13 | 2023-09-16T22:04:20 | https://github.com/RahulSChand/gpu_poor | ExploreExploit400 | github.com | 1970-01-01T00:00:00 | 0 | {} | 16kjhie | false | null | t3_16kjhie | /r/LocalLLaMA/comments/16kjhie/made_a_simple_github_tool_to_get_gpu_vram/ | false | false | 13 | {'enabled': False, 'images': [{'id': 'utIB6lIZ8v3ONi_evwZzAkDf8QC_u_zJb_qJew4kPbE', 'resolutions': [{'height': 54, 'url': 'https://external-preview.redd.it/ZNjVqkYiYBElsy-FlrBO-9qPYHIJKXnZpkRayybOipg.jpg?width=108&crop=smart&auto=webp&s=b10aefb8b643f82eb7f9d8f360f11a532813f0c8', 'width': 108}, {'height': 108, 'url': 'h... | ||
Made a simple github tool to get GPU vRAM breakdown for any Huggingface LLM. Supports ggml & bitsandbytes quantization | 2 | 2023-09-16T21:45:01 | ExploreExploit400 | i.redd.it | 1970-01-01T00:00:00 | 0 | {} | 16kj0dv | false | null | t3_16kj0dv | /r/LocalLLaMA/comments/16kj0dv/made_a_simple_github_tool_to_get_gpu_vram/ | false | false | 2 | {'enabled': True, 'images': [{'id': 'uSas3w395a0lrw_NdxlR-4FfyG0IQ8F7fGv8oEbVN9w', 'resolutions': [{'height': 50, 'url': 'https://preview.redd.it/fi1c0rnrtoob1.jpg?width=108&crop=smart&auto=webp&s=eb9dd3e1cb25abac8f50506e0a9152deb319cdb6', 'width': 108}, {'height': 101, 'url': 'https://preview.redd.it/fi1c0rnrtoob1.jpg... | |||
Local Hosting of LLM | 1 | [removed] | 2023-09-16T21:43:32 | https://www.reddit.com/r/LocalLLaMA/comments/16kiz3a/local_hosting_of_llm/ | Disastrous-Boot2146 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 16kiz3a | false | null | t3_16kiz3a | /r/LocalLLaMA/comments/16kiz3a/local_hosting_of_llm/ | false | false | self | 1 | null |
Who knew Phi could roleplay? | 73 | 2023-09-16T21:10:34 | pokeuser61 | i.redd.it | 1970-01-01T00:00:00 | 0 | {} | 16ki635 | false | null | t3_16ki635 | /r/LocalLLaMA/comments/16ki635/who_knew_phi_could_roleplay/ | false | false | 73 | {'enabled': True, 'images': [{'id': 'ftktqPtZfXPevyQF7nw2AIKEZYYQtVUG3WOc6xAfnxg', 'resolutions': [{'height': 84, 'url': 'https://preview.redd.it/30wmf31tnoob1.png?width=108&crop=smart&auto=webp&s=66cfadee52fa49b9ffc04d7731c77f56e80ea5ca', 'width': 108}, {'height': 169, 'url': 'https://preview.redd.it/30wmf31tnoob1.png... | |||
Who new phi could roleplay? | 1 | 2023-09-16T21:08:51 | pokeuser61 | i.redd.it | 1970-01-01T00:00:00 | 0 | {} | 16ki4n3 | false | null | t3_16ki4n3 | /r/LocalLLaMA/comments/16ki4n3/who_new_phi_could_roleplay/ | false | false | 1 | {'enabled': True, 'images': [{'id': '1Onbms-Jv7Ii2igdkRtXOCIKn-l-hiPxeVNcn8LOAE8', 'resolutions': [{'height': 84, 'url': 'https://preview.redd.it/7d056fdgnoob1.png?width=108&crop=smart&auto=webp&s=c070eb0fc7c6610158d105a2f985b6b783d68959', 'width': 108}, {'height': 169, 'url': 'https://preview.redd.it/7d056fdgnoob1.png... | |||
Falcon 180B inference - 192GB Mac Studio or 192GB Mac Pro? | 31 | My post from yesterday gained some traction so I would like to explain my concern.
I initially wanted to buy 192 GB M2 Mac Studio to run just inference (I'm not training or fine tuning), but one thing come to my mind and I started to lean myself to buy 192 M2 Mac Pro. Yes this M2 Mac Pro which has only bad reviews... | 2023-09-16T19:53:35 | https://www.reddit.com/r/LocalLLaMA/comments/16kgdmu/falcon_180b_inference_192gb_mac_studio_or_192gb/ | Wrong_User_Logged | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 16kgdmu | false | null | t3_16kgdmu | /r/LocalLLaMA/comments/16kgdmu/falcon_180b_inference_192gb_mac_studio_or_192gb/ | false | false | self | 31 | null |
Frank: An Uncensored Model | 91 | Uncensored-Frank-7B: [https://huggingface.co/ajibawa-2023/Uncensored-Frank-7B](https://huggingface.co/ajibawa-2023/Uncensored-Frank-7B) (Llama-1)
Uncensored-Frank-13B: [https://huggingface.co/ajibawa-2023/Uncensored-Frank-13B](https://huggingface.co/ajibawa-2023/Uncensored-Frank-13B) (Llama-2)
Uncensored-Frank-33B: [... | 2023-09-16T19:04:01 | https://www.reddit.com/r/LocalLLaMA/comments/16kf97a/frank_an_uncensored_model/ | ajibawa-2023 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 16kf97a | false | null | t3_16kf97a | /r/LocalLLaMA/comments/16kf97a/frank_an_uncensored_model/ | false | false | self | 91 | {'enabled': False, 'images': [{'id': 'vL0IHcp4IEBMKPFRahYub4Ft263ZGqHGwra4Drn-l9Y', 'resolutions': [{'height': 58, 'url': 'https://external-preview.redd.it/UO-CQjZf3V3KhpNESBszAuXABddlX-RUqMZOgZqHNN0.jpg?width=108&crop=smart&auto=webp&s=f02f8765ba935d1e0b60d8abc5eeaa7e94fb0e3d', 'width': 108}, {'height': 116, 'url': 'h... |
New Model Comparison/Test (Part 1 of 2: 15 models tested, 13B+34B) | 98 | This is a follow-up to my previous posts here: [New Model RP Comparison/Test (7 models tested)](https://www.reddit.com/r/LocalLLaMA/comments/15ogc60/new_model_rp_comparisontest_7_models_tested/) and [Big Model Comparison/Test (13 models tested)](https://www.reddit.com/r/LocalLLaMA/comments/15lihmq/big_model_comparisont... | 2023-09-16T18:24:45 | https://www.reddit.com/r/LocalLLaMA/comments/16kecsf/new_model_comparisontest_part_1_of_2_15_models/ | WolframRavenwolf | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 16kecsf | false | null | t3_16kecsf | /r/LocalLLaMA/comments/16kecsf/new_model_comparisontest_part_1_of_2_15_models/ | false | false | self | 98 | {'enabled': False, 'images': [{'id': '2g4MtoKvhQOBCmeiXB1qv1h_5M24BeeYF64zcf4-rfg', 'resolutions': [{'height': 142, 'url': 'https://external-preview.redd.it/iVP12Aa6rBm44Nrf_ci7NKfYkFvHRQRzUafC5j-jnEw.jpg?width=108&crop=smart&auto=webp&s=70f053538cd673ff7041bf016d751549d8373201', 'width': 108}, {'height': 284, 'url': '... |
LlamaTale v0.12.0 - OpenAI support, Zone generation, improved combat and NPC Idle actions | 19 | Hi. Stepping in for another update. I think there's at least one new feature many of you will find interesting. Let me tease you with "emergent behavior".
A short recap of what's happened since the last update:
* To allow more people to try this out, I added OpenAI backend support in [v0.9.2](https://github.com/neph1... | 2023-09-16T18:13:01 | https://www.reddit.com/r/LocalLLaMA/comments/16ke32e/llamatale_v0120_openai_support_zone_generation/ | neph1010 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 16ke32e | false | null | t3_16ke32e | /r/LocalLLaMA/comments/16ke32e/llamatale_v0120_openai_support_zone_generation/ | false | false | 19 | {'enabled': False, 'images': [{'id': 'fa8BRwKtC1UEbC2lTUS2Udv1hUzLaJozwH4QL7805ks', 'resolutions': [{'height': 54, 'url': 'https://external-preview.redd.it/ANu9M3ZaLQXtrttfE0pj1TGA0nJgqmXLtaBZfQAJpoY.jpg?width=108&crop=smart&auto=webp&s=7b55d75533a03ded4595a8e48abab9dc8920bbf3', 'width': 108}, {'height': 108, 'url': 'h... | |
Is it possible to Quantize DeciLM-6? | 6 | [Model card](https://huggingface.co/Deci/DeciLM-6b) | 2023-09-16T16:38:26 | https://www.reddit.com/r/LocalLLaMA/comments/16kbx1i/is_it_possible_to_quantize_decilm6/ | Pineapple_Expressed | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 16kbx1i | false | null | t3_16kbx1i | /r/LocalLLaMA/comments/16kbx1i/is_it_possible_to_quantize_decilm6/ | false | false | self | 6 | {'enabled': False, 'images': [{'id': 'PeUEHEDeiDpJiVx8uu6FTyh9hxae5iwe1tZAyeglz7g', 'resolutions': [{'height': 58, 'url': 'https://external-preview.redd.it/q9PCGBqwlCVrp3Ee0kxeItubUqlemGKnHR2PErOsEpY.jpg?width=108&crop=smart&auto=webp&s=49cb41a341e6c1c3b161812ab717218d772e91cd', 'width': 108}, {'height': 116, 'url': 'h... |
TinyLlama training to 500B tokens is complete | 102 | 2023-09-16T15:44:12 | https://github.com/jzhang38/TinyLlama | jncraton | github.com | 1970-01-01T00:00:00 | 0 | {} | 16kanph | false | null | t3_16kanph | /r/LocalLLaMA/comments/16kanph/tinyllama_training_to_500b_tokens_is_complete/ | false | false | 102 | {'enabled': False, 'images': [{'id': '6TISjUHuXBn1Ygnnc3Bnk83a4I37KGK4s0Ykjc8Qi6U', 'resolutions': [{'height': 54, 'url': 'https://external-preview.redd.it/8ZxuJh2OfmS6BCCZRIHv6QSfhYvErbhcppJktGbFVLQ.jpg?width=108&crop=smart&auto=webp&s=aa7d8c8bc85179daaae479d6590e60fd1c776607', 'width': 108}, {'height': 108, 'url': 'h... | ||
Chatgpt's web browsing feature neutered. Gives brief descriptions of contents of pages and nothing more. | 10 | I did not realize how incapable they would make closed models. Insane. | 2023-09-16T15:16:11 | https://www.reddit.com/r/LocalLLaMA/comments/16ka0ho/chatgpts_web_browsing_feature_neutered_gives/ | Basic_Description_56 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 16ka0ho | false | null | t3_16ka0ho | /r/LocalLLaMA/comments/16ka0ho/chatgpts_web_browsing_feature_neutered_gives/ | false | false | self | 10 | null |
Beta test my native macOS Llama app | 13 | Hey ya'll. I've been working on a macOS app that aims to be the easiest way to run llama.cpp on your mac. It includes a 7B model but you can plug in any GGUF that's llama.cpp compatible. It's totally private and doesn't even connect to the internet. On my MacBook (m1 max), the default model responds almost instantly an... | 2023-09-16T15:13:48 | https://www.reddit.com/r/LocalLLaMA/comments/16k9yhg/beta_test_my_native_macos_llama_app/ | sleeper-2 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 16k9yhg | false | null | t3_16k9yhg | /r/LocalLLaMA/comments/16k9yhg/beta_test_my_native_macos_llama_app/ | false | false | self | 13 | {'enabled': False, 'images': [{'id': '55pNmRvYHyV0yKvZ_unzxKnG6Bhy5FhoaH0_JA3AV5U', 'resolutions': [{'height': 108, 'url': 'https://external-preview.redd.it/diR-hJpKJopFw67_Kv6IiokJ98IMtEVXJ_OqmN1eWm8.jpg?width=108&crop=smart&auto=webp&s=57a2e87d3df210024fe18b4e6e7a61997badbf34', 'width': 108}, {'height': 216, 'url': '... |
Dataset to model processes, how does that work? | 1 | If I download a dataset or several datasets, how to I convert that into the model files so I can ask it questions? Do we always have to start with a pre trained base of some kind, or can we get a chat experience from any sufficiently large dataset because of the transformers library and all that? Just trying to underst... | 2023-09-16T14:59:06 | https://www.reddit.com/r/LocalLLaMA/comments/16k9m2v/dataset_to_model_processes_how_does_that_work/ | Overall-Importance54 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 16k9m2v | false | null | t3_16k9m2v | /r/LocalLLaMA/comments/16k9m2v/dataset_to_model_processes_how_does_that_work/ | false | false | self | 1 | null |
Llama 3: Dense Evolution or Expert Revolution? | 63 | What are your predictions about Llama 3? Will it be another dense model (with maybe 300 billion parameters and 6 trillion tokens) or will it be a Switch Transformer (with maybe 8 or 16 experts, like GPT-4 is rumored to be)?
On that note, Meta AI has recently released a paper on Mixture-of-Experts architecture:
[... | 2023-09-16T14:53:43 | https://www.reddit.com/r/LocalLLaMA/comments/16k9hnd/llama_3_dense_evolution_or_expert_revolution/ | DecipheringAI | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 16k9hnd | false | null | t3_16k9hnd | /r/LocalLLaMA/comments/16k9hnd/llama_3_dense_evolution_or_expert_revolution/ | false | false | self | 63 | {'enabled': False, 'images': [{'id': 'q3evP6JeDpAC2MdSQHWYxnCYTqbJkElIQsLFqVSdkss', 'resolutions': [{'height': 63, 'url': 'https://external-preview.redd.it/0HhwdU6MKIAKjL9Y8-B_iH374a3NiPTy0ib8lmloRzA.jpg?width=108&crop=smart&auto=webp&s=2711d572cfc6c713893cf24e8c4a7344d5ad8a4c', 'width': 108}, {'height': 126, 'url': 'h... |
How can I fine-tune a LLAMA? | 1 | Hello there
I just started exploring LLMs and I found a good one \`TheBloke/chronos-hermes-13B-GGML\` but I want to fine-tune it on specific stories (NSFW) and I don't know how I should label the stories
does anyone know how to do it ??
| 2023-09-16T14:43:12 | https://www.reddit.com/r/LocalLLaMA/comments/16k98rt/how_can_i_finetune_a_llama/ | Mohamd_L | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 16k98rt | false | null | t3_16k98rt | /r/LocalLLaMA/comments/16k98rt/how_can_i_finetune_a_llama/ | false | false | self | 1 | null |
Clip of Steve Jobs predicting LLMs in 1985. Sadly over-optimistic about the timeframe. | 27 | 2023-09-16T14:26:33 | https://twitter.com/scienceisstrat1/status/1702936367871721797 | ambient_temp_xeno | twitter.com | 1970-01-01T00:00:00 | 0 | {} | 16k8v6j | false | {'oembed': {'author_name': 'Science Is Strategic', 'author_url': 'https://twitter.com/scienceisstrat1', 'cache_age': 3153600000, 'height': None, 'html': '<blockquote class="twitter-video"><p lang="en" dir="ltr">Steve Jobs anticipates Large Language Models <br><br>Cc: <a href="https://twitter.com/erikbryn?ref_src=twsrc%... | t3_16k8v6j | /r/LocalLLaMA/comments/16k8v6j/clip_of_steve_jobs_predicting_llms_in_1985_sadly/ | false | false | 27 | {'enabled': False, 'images': [{'id': 'oneMqRzRGif0Nh9-3KBWUrF4EJ78mJz1zUCuQDV0EUc', 'resolutions': [{'height': 78, 'url': 'https://external-preview.redd.it/_xX0QDpO0EmuMFTEo7w_R9ySZuKNmQ1yu9GjwggAvVU.jpg?width=108&crop=smart&auto=webp&s=526cae4df055e20d847b51ecbbeab464276e85a2', 'width': 108}], 'source': {'height': 102... | ||
Looking for a Translation Model for English to 100+ Languages, Comparable to DeepL or Google, for Local Deployment | 2 | Hello everyone,
I am working on a project where I need to translate text from English into over 100 different languages. The translation quality needs to be comparable to services like DeepL or Google Translate.
Is there a model available that meets these requirements and can be run locally without the need for exter... | 2023-09-16T14:06:25 | https://www.reddit.com/r/LocalLLaMA/comments/16k8f8d/looking_for_a_translation_model_for_english_to/ | Vivid_Confidence3212 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 16k8f8d | false | null | t3_16k8f8d | /r/LocalLLaMA/comments/16k8f8d/looking_for_a_translation_model_for_english_to/ | false | false | self | 2 | null |
LoRA on Linear layers? | 2 | ​
https://preview.redd.it/qq80hyvrjmob1.png?width=827&format=png&auto=webp&s=c32df00c9747c944dc96e64238bd7ae7d8f49a4b
I came across this \^ recently and I wanted to know if it possible to apply it to some of the MLP layers as well?
​
TIA | 2023-09-16T14:05:56 | https://www.reddit.com/r/LocalLLaMA/comments/16k8eu5/lora_on_linear_layers/ | Dry_Long3157 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 16k8eu5 | false | null | t3_16k8eu5 | /r/LocalLLaMA/comments/16k8eu5/lora_on_linear_layers/ | false | false | 2 | null | |
Completely Local Autonomous Agent? | 6 | Is there an Autonomous Agent that will connect to and use a local language model that also does not require some remotely-hosted resource? So far, they all either require OpenAI credentials (the vast majority), or a cloud-hosted vector database, or some other snag. Running the models I've figured out, but I want \*ever... | 2023-09-16T13:14:55 | https://www.reddit.com/r/LocalLLaMA/comments/16k7bbh/completely_local_autonomous_agent/ | Seclusion72 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 16k7bbh | false | null | t3_16k7bbh | /r/LocalLLaMA/comments/16k7bbh/completely_local_autonomous_agent/ | false | false | self | 6 | null |
What model do you use with a Nvidia 3090/4090 or equivalent AMD? | 17 | Here's my take, and I'd like yours as well !
​
I'm running on KoboldCPP 1.43 experimental (updated to Llama CPP b1216 with Johannes Gaessler MMQ fixes) on a RTX 3090, with full offload :
I use sometimes CodeLLama 34b Samantha 1.11 Q4\_K\_S with 16384 context length (rope base frequency 1,000,000, it's not opt... | 2023-09-16T12:58:25 | https://www.reddit.com/r/LocalLLaMA/comments/16k6yxs/what_model_do_you_use_with_a_nvidia_30904090_or/ | Nexesenex | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 16k6yxs | false | null | t3_16k6yxs | /r/LocalLLaMA/comments/16k6yxs/what_model_do_you_use_with_a_nvidia_30904090_or/ | false | false | self | 17 | {'enabled': False, 'images': [{'id': 'mGdWOV4LkgZVyU7H5AkWDWax7uyPBUEh9K3WJ9UGC_k', 'resolutions': [{'height': 54, 'url': 'https://external-preview.redd.it/mxlwJizRq3MaDDimzkCfr60BSum8NngNJtJ4FjBqXTk.jpg?width=108&crop=smart&auto=webp&s=d4291c29f2245e8b5bdfda8f8b08d2845932ba00', 'width': 108}, {'height': 108, 'url': 'h... |
pnmeka/langchain_RAG: Using langchain module to generate RAG prompt for open AI | 9 | 2023-09-16T12:25:58 | https://github.com/pnmeka/langchain_RAG | TestPilot1980 | github.com | 1970-01-01T00:00:00 | 0 | {} | 16k6aua | false | null | t3_16k6aua | /r/LocalLLaMA/comments/16k6aua/pnmekalangchain_rag_using_langchain_module_to/ | false | false | 9 | {'enabled': False, 'images': [{'id': '_NCaAb0ugGxfWB91SEbGifHwYdS5GCLxMvK308_fjBA', 'resolutions': [{'height': 54, 'url': 'https://external-preview.redd.it/wNgWZmdkqnNDHqsPyXaaa5qkSEPhJuS-0AzLqLemKwI.jpg?width=108&crop=smart&auto=webp&s=3f3f9f87bb4b5054eac930df9b45c968f95241a1', 'width': 108}, {'height': 108, 'url': 'h... | ||
KoboldCPP now has (experimental) RX 6700XT/gfx1031 support | 22 | [https://github.com/YellowRoseCx/koboldcpp-rocm/releases/tag/v1.43.2-ROCm](https://github.com/YellowRoseCx/koboldcpp-rocm/releases/tag/v1.43.2-ROCm)
Good news for us poor left-out gfx1031 owners. I'm curious if you're having any success with it. I sometimes get a good output with the very first prompt. If I try to con... | 2023-09-16T10:52:36 | https://www.reddit.com/r/LocalLLaMA/comments/16k4hju/koboldcpp_now_has_experimental_rx_6700xtgfx1031/ | Susp-icious_-31User | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 16k4hju | false | null | t3_16k4hju | /r/LocalLLaMA/comments/16k4hju/koboldcpp_now_has_experimental_rx_6700xtgfx1031/ | false | false | self | 22 | {'enabled': False, 'images': [{'id': 'MqmTjkqRHQOmxK3tvvapSmyB5Vr_gLpITyTS710reE0', 'resolutions': [{'height': 54, 'url': 'https://external-preview.redd.it/MTCZ1qmQo8slMrNlRZOeIUpYoMUF0_hGerETY80A-q8.jpg?width=108&crop=smart&auto=webp&s=19b2d954ec1b353d5cfebc162396ad576449aebc', 'width': 108}, {'height': 108, 'url': 'h... |
Horde-Client v1.0.2 is out today! | 17 | Few days back, I shared my project [horde-client](https://pypi.org/project/horde-client/). For those who missed the post, this is a Python Client library for KoboldAI project that lets you remotely interact with crowdsourced/private LLM services.
I got some great feedback in the last post and have incorporated majori... | 2023-09-16T07:49:34 | https://www.reddit.com/r/LocalLLaMA/comments/16k1j31/hordeclient_v102_is_out_today/ | AnonymousD3vil | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 16k1j31 | false | null | t3_16k1j31 | /r/LocalLLaMA/comments/16k1j31/hordeclient_v102_is_out_today/ | false | false | self | 17 | null |
Running Llama2 on Android | 9 | Is there any way you can tell me to run a Llama2 model (or any other model) on Android devices?
Hopefully a open source way.
BTW. Just saw an interesting post about using Llm on Vulcan maybe that would be interesting either. | 2023-09-16T07:24:53 | https://www.reddit.com/r/LocalLLaMA/comments/16k14a2/running_llama2_on_android/ | Deep-View-2411 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 16k14a2 | false | null | t3_16k14a2 | /r/LocalLLaMA/comments/16k14a2/running_llama2_on_android/ | false | false | self | 9 | null |
Finetune in bf16 or fp16? | 1 | [removed] | 2023-09-16T06:56:44 | https://www.reddit.com/r/LocalLLaMA/comments/16k0ntu/finetune_in_bf16_or_fp16/ | gptzerozero | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 16k0ntu | false | null | t3_16k0ntu | /r/LocalLLaMA/comments/16k0ntu/finetune_in_bf16_or_fp16/ | false | false | self | 1 | null |
I wish for these four models | 0 | Model 1. General writer and knowledge; good at professional, personal, and replies to internet comments. Knows how to troubleshoot electronics, computers and networks, cars, and women.
Model 2. Psychology / therapist and personal growth guide (guru) and friendly. Hard drive capacity limited; infinite storage of my ... | 2023-09-16T05:35:11 | https://www.reddit.com/r/LocalLLaMA/comments/16jzbwu/i_wish_for_these_four_models/ | MinimumPC | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 16jzbwu | false | null | t3_16jzbwu | /r/LocalLLaMA/comments/16jzbwu/i_wish_for_these_four_models/ | false | false | self | 0 | null |
How much does the calibration dataset affect the results when quantizing the model? (exllamav2) | 1 | [removed] | 2023-09-16T05:05:48 | https://www.reddit.com/r/LocalLLaMA/comments/16jyu8w/how_much_does_the_calibration_dataset_affect_the/ | Eigeen | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 16jyu8w | false | null | t3_16jyu8w | /r/LocalLLaMA/comments/16jyu8w/how_much_does_the_calibration_dataset_affect_the/ | false | false | self | 1 | null |
AMD for AI | 35 | So the 7900 XTX is at a pretty unbeatable price with 24 GB of VRAM and I am also a gamer and game developer so a single good GPU is better than 2 3090’s for example but I was wondering how it is for AI applications like oobabagooga(or however it is spelt) and sadtalker or bark. These use CUDA and CUDA is Nvidia technol... | 2023-09-16T03:54:19 | https://www.reddit.com/r/LocalLLaMA/comments/16jxl44/amd_for_ai/ | SimRacer101 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 16jxl44 | false | null | t3_16jxl44 | /r/LocalLLaMA/comments/16jxl44/amd_for_ai/ | false | false | self | 35 | null |
Running Lama 70B on GameBoy | 0 | Hello, everyone! I've recently become interested in experimenting with LLMs and their inference capabilities. I've come across information suggesting they can be run on a variety of devices. Does anyone have experience or advice on how to get it set up on a GameBoy? Any guidance would be greatly appreciated! | 2023-09-16T02:06:59 | https://www.reddit.com/r/LocalLLaMA/comments/16jvl7s/running_lama_70b_on_gameboy/ | Wrong_User_Logged | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 16jvl7s | false | null | t3_16jvl7s | /r/LocalLLaMA/comments/16jvl7s/running_lama_70b_on_gameboy/ | false | false | default | 0 | null |
Pinned post for .cpp implementation and | 1 | I am interested in learning how to port these models like Llama 1/2 to their .cpp version I see there are posts pinned for serving on .cpp and quantization but no resources for porting them if I made a change to the architecture and trained a new model.
Would love some resources, I have been working with Python/Torch ... | 2023-09-16T01:31:25 | https://www.reddit.com/r/LocalLLaMA/comments/16juw6u/pinned_post_for_cpp_implementation_and/ | BomsDrag | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 16juw6u | false | null | t3_16juw6u | /r/LocalLLaMA/comments/16juw6u/pinned_post_for_cpp_implementation_and/ | false | false | self | 1 | null |
What hardware do I need for 70B Llama? | 0 | [removed] | 2023-09-16T01:25:54 | https://www.reddit.com/r/LocalLLaMA/comments/16jus38/what_hardware_do_i_need_for_70b_llama/ | Infinite100p | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 16jus38 | false | null | t3_16jus38 | /r/LocalLLaMA/comments/16jus38/what_hardware_do_i_need_for_70b_llama/ | false | false | default | 0 | null |
Machine Learning systems notes | 17 | Hey folks,
I've written down some machine learning systems study notes, from the perspective of a software/systems engineer: [https://9600.dev/posts/machine-learning-developer-notes/](https://9600.dev/posts/machine-learning-developer-notes/)
I hope the community might find them useful.
It contains a high level wal... | 2023-09-16T00:04:41 | https://www.reddit.com/r/LocalLLaMA/comments/16jt4eo/machine_learning_systems_notes/ | 9600kps | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 16jt4eo | false | null | t3_16jt4eo | /r/LocalLLaMA/comments/16jt4eo/machine_learning_systems_notes/ | false | false | self | 17 | null |
How do I get my LLM model to accept a large amount of input? | 0 | Using LMstudio | 2023-09-16T00:01:07 | https://www.reddit.com/r/LocalLLaMA/comments/16jt1fk/how_do_i_get_my_llm_model_to_accept_a_large/ | hophophop1233 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 16jt1fk | false | null | t3_16jt1fk | /r/LocalLLaMA/comments/16jt1fk/how_do_i_get_my_llm_model_to_accept_a_large/ | false | false | self | 0 | null |
Why do some GGUFs set rope scale base to 1,000,000? | 23 | I've noticed this on a couple of ggufs, like for zarablend 7b. I load the gguf in oobabooga and it instantly sets the rope scale at 1,000,000, with alpha and compress at 1. The first time I thought it was a mistake, but a couple of others did it over time and I started to wonder if it was intentional.
Is it just a mis... | 2023-09-15T23:47:42 | https://www.reddit.com/r/LocalLLaMA/comments/16jsr9t/why_do_some_ggufs_set_rope_scale_base_to_1000000/ | LearningSomeCode | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 16jsr9t | false | null | t3_16jsr9t | /r/LocalLLaMA/comments/16jsr9t/why_do_some_ggufs_set_rope_scale_base_to_1000000/ | false | false | self | 23 | null |
Best text to speech out there? | 14 | Looking to have voice clone, text to speech, different voices etc...do we have anything like that that is gui based? | 2023-09-15T22:46:12 | https://www.reddit.com/r/LocalLLaMA/comments/16jrcek/best_text_to_speech_out_there/ | rorowhat | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 16jrcek | false | null | t3_16jrcek | /r/LocalLLaMA/comments/16jrcek/best_text_to_speech_out_there/ | false | false | self | 14 | null |
How to consolidate .distcp file shards? | 2 | I was training an LLM using axolotl with FSDP enabled (Llama-2 architecture). The model was saved as 6 separate .distcp shards. How can I consolidate those shards into a single .bin file for inference? My huggingface model link is here: [https://huggingface.co/jerryjalapeno/VH\_1.7B\_1/tree/main](https://huggingface.co... | 2023-09-15T22:32:43 | https://www.reddit.com/r/LocalLLaMA/comments/16jr0wc/how_to_consolidate_distcp_file_shards/ | ZealousidealBlock330 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 16jr0wc | false | null | t3_16jr0wc | /r/LocalLLaMA/comments/16jr0wc/how_to_consolidate_distcp_file_shards/ | false | false | self | 2 | {'enabled': False, 'images': [{'id': '3QFjRRtH8FSEV92-NOJrLf98it3bVHPkc6m-xqH3uRQ', 'resolutions': [{'height': 58, 'url': 'https://external-preview.redd.it/Ge8UTLWJMl-ShaA7itBH9CB_ZLTJA6q4wParmXC-Xm0.jpg?width=108&crop=smart&auto=webp&s=c3781f1c707ae29d8273dc439398687b328becd0', 'width': 108}, {'height': 116, 'url': 'h... |
Is it possible to get structured output from LLAMA2 70B | 3 | I'm running LLAMA2 70B locally on my MacBook.
I would like to get CSV and JSON output for certain prompts the way I can with GPT-4 APIs.
I currently using [thebloke/llama-2-70b-orca-200k.Q5\_K\_M.gguf](https://huggingface.co/TheBloke/Llama-2-70B-Orca-200k-GGUF) vi [llama.cpp](https://github.com/ggerganov/llama.cpp) p... | 2023-09-15T21:01:53 | https://www.reddit.com/r/LocalLLaMA/comments/16jor5o/is_it_possible_to_get_structured_output_from/ | spyderman4g63 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 16jor5o | false | null | t3_16jor5o | /r/LocalLLaMA/comments/16jor5o/is_it_possible_to_get_structured_output_from/ | false | false | self | 3 | {'enabled': False, 'images': [{'id': 'nVhAggG3eCTNXmhRf8FwwKFAu3bEJL7299fy4oQcYek', 'resolutions': [{'height': 58, 'url': 'https://external-preview.redd.it/mkGIaSbeeJOpyEXy9xxcBAO-a1fVJVujZXNof2gVDzU.jpg?width=108&crop=smart&auto=webp&s=6805000cda30334e9adaab628e517ac4d933f7c2', 'width': 108}, {'height': 116, 'url': 'h... |
From Quantity to Quality: Boosting LLM Performance with Self-Guided Data Selection for Instruction Tuning | 5 | [https://arxiv.org/abs/2308.12032](https://arxiv.org/abs/2308.12032)
[https://github.com/MingLiiii/Cherry\_LLM](https://github.com/MingLiiii/Cherry_LLM)
​ | 2023-09-15T20:49:34 | https://www.reddit.com/r/LocalLLaMA/comments/16jog13/from_quantity_to_quality_boosting_llm_performance/ | MingLiiii | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 16jog13 | false | null | t3_16jog13 | /r/LocalLLaMA/comments/16jog13/from_quantity_to_quality_boosting_llm_performance/ | false | false | self | 5 | {'enabled': False, 'images': [{'id': 'q3evP6JeDpAC2MdSQHWYxnCYTqbJkElIQsLFqVSdkss', 'resolutions': [{'height': 63, 'url': 'https://external-preview.redd.it/0HhwdU6MKIAKjL9Y8-B_iH374a3NiPTy0ib8lmloRzA.jpg?width=108&crop=smart&auto=webp&s=2711d572cfc6c713893cf24e8c4a7344d5ad8a4c', 'width': 108}, {'height': 126, 'url': 'h... |
DeciLM-6B | 55 | 2023-09-15T19:44:18 | https://deci.ai/blog/decilm-15-times-faster-than-llama2-nas-generated-llm-with-variable-gqa/ | Acrobatic-Site2065 | deci.ai | 1970-01-01T00:00:00 | 0 | {} | 16jmti2 | false | null | t3_16jmti2 | /r/LocalLLaMA/comments/16jmti2/decilm6b/ | false | false | 55 | {'enabled': False, 'images': [{'id': '8JasBexDQLW0G7y4n6ThMQH77AmFW5N6s2HUrariAC4', 'resolutions': [{'height': 60, 'url': 'https://external-preview.redd.it/jsvkz-6SkJ37uBSqTJV96vR0sPDSydNLnAdEv43nYhA.jpg?width=108&crop=smart&auto=webp&s=b113841b47c7b8885f1049233e7c226d00918b12', 'width': 108}, {'height': 121, 'url': 'h... | ||
I'm going to buy M2 Mac Pro to run AI models on H100. | 0 | Yes, call me stupid but I really want to do it, maybe at some point Apple will finally support NVidia cards on their pricey PCIe slots. lol
​
That should be technically possible, it's just software issue. | 2023-09-15T18:58:48 | https://www.reddit.com/r/LocalLLaMA/comments/16jlooq/im_going_to_buy_m2_mac_pro_to_run_ai_models_on/ | Wrong_User_Logged | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 16jlooq | false | null | t3_16jlooq | /r/LocalLLaMA/comments/16jlooq/im_going_to_buy_m2_mac_pro_to_run_ai_models_on/ | false | false | self | 0 | null |
Lip Sync API Service? | 4 | I am using [SadTalker](https://github.com/OpenTalker/SadTalker) to create a lipsync of a [still image](https://satoshi.report/face_35.png) with an [audio file](https://satoshi.report/IXPRPRZXWVJZ.mp3). The still image is from Stable Diffusion and the audio is from ChatGPT and then AWS Polly for the voice synthesis. M... | 2023-09-15T18:44:42 | https://www.reddit.com/r/LocalLLaMA/comments/16jlc7e/lip_sync_api_service/ | SatoshiReport | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 16jlc7e | false | null | t3_16jlc7e | /r/LocalLLaMA/comments/16jlc7e/lip_sync_api_service/ | false | false | self | 4 | {'enabled': False, 'images': [{'id': 'B9PY__Y0q5avO_xdhu30nJudoy_17oHTTvaUvyGll88', 'resolutions': [{'height': 108, 'url': 'https://external-preview.redd.it/j4qkkwJ2o5q2jjB1fUbHgIxLHNvjJu4gqKOKeGJ4etM.png?width=108&crop=smart&auto=webp&s=02d0811e64b4c2bc8120519b3fda7b7b6ed31548', 'width': 108}, {'height': 216, 'url': '... |
Which vm instance can I start to run llama 70 B parameter? Which would be cost efficient? what ram? whether gpu or cpu? how many cpus? | 10 | ​
https://preview.redd.it/tr5n474csgob1.png?width=725&format=png&auto=webp&s=b3f3d497345b15667d3e1ac73481adf1fe8bc915
https://preview.redd.it/y0enzi4gsgob1.png?width=740&format=png&auto=webp&s=5832ee21b361e171608468359f6bcadf4528b149 | 2023-09-15T18:43:25 | https://www.reddit.com/r/LocalLLaMA/comments/16jlb2j/which_vm_instance_can_i_start_to_run_llama_70_b/ | yashwatwani28 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 16jlb2j | false | null | t3_16jlb2j | /r/LocalLLaMA/comments/16jlb2j/which_vm_instance_can_i_start_to_run_llama_70_b/ | false | false | 10 | null | |
Agents: An Open-source Framework for Autonomous Language Agents - AIWaves Inc 2023 | 37 | I hope this paper is also interesting this community!
Paper: [https://arxiv.org/abs/2309.07870](https://arxiv.org/abs/2309.07870)
Github: [https://github.com/aiwaves-cn/agents](https://github.com/aiwaves-cn/agents)
Abstract:
>Recent advances on large language models (LLMs) enable researchers and developers to bui... | 2023-09-15T18:36:38 | https://www.reddit.com/r/LocalLLaMA/comments/16jl53m/agents_an_opensource_framework_for_autonomous/ | Singularian2501 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 16jl53m | false | null | t3_16jl53m | /r/LocalLLaMA/comments/16jl53m/agents_an_opensource_framework_for_autonomous/ | false | false | 37 | {'enabled': False, 'images': [{'id': 'q3evP6JeDpAC2MdSQHWYxnCYTqbJkElIQsLFqVSdkss', 'resolutions': [{'height': 63, 'url': 'https://external-preview.redd.it/0HhwdU6MKIAKjL9Y8-B_iH374a3NiPTy0ib8lmloRzA.jpg?width=108&crop=smart&auto=webp&s=2711d572cfc6c713893cf24e8c4a7344d5ad8a4c', 'width': 108}, {'height': 126, 'url': 'h... | |
How much do different aspects of models & interfaces matter? | 3 | What truly matters when to you when you're deciding which model and chat interface to use?
Does everything need to be FOSS? Do features (PDFs, Internet RAG, image gen, etc) matter? Is it just cost (as in no monthly subscription)? Model size? Locality?
and how do those axes interact? For example, would a FOSS model bu... | 2023-09-15T18:18:52 | https://www.reddit.com/r/LocalLLaMA/comments/16jkphn/how_much_do_different_aspects_of_models/ | carsonpoole | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 16jkphn | false | null | t3_16jkphn | /r/LocalLLaMA/comments/16jkphn/how_much_do_different_aspects_of_models/ | false | false | self | 3 | null |
Is falcon 180b any good for creative stuff...more specifically fiction writing? | 24 | Just wondering. This is something that's extremely difficult to judge from benchmarks. | 2023-09-15T17:59:17 | https://www.reddit.com/r/LocalLLaMA/comments/16jk8b5/is_falcon_180b_any_good_for_creative_stuffmore/ | spanielrassler | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 16jk8b5 | false | null | t3_16jk8b5 | /r/LocalLLaMA/comments/16jk8b5/is_falcon_180b_any_good_for_creative_stuffmore/ | false | false | self | 24 | null |
Introducing Fintwit Voyager (summaries on financial podcasts with OS LLMs) | 1 | Introducing Fintwit Voyager!
A twitter account that harnesses open-source large language models to auto-summarize investing and financial markets podcasts.
On a technical note, I developed a custom summarization chain involving speech-to-text transcription, speaker diarization, speaker labeling, and summarization.... | 2023-09-15T17:57:03 | https://www.reddit.com/r/LocalLLaMA/comments/16jk6c4/introducing_fintwit_voyager_summaries_on/ | Responsible_Warning3 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 16jk6c4 | false | null | t3_16jk6c4 | /r/LocalLLaMA/comments/16jk6c4/introducing_fintwit_voyager_summaries_on/ | false | false | self | 1 | {'enabled': False, 'images': [{'id': 'vUBde9w3mU-cHW1ZjtG2To91gaw33i10GgwEVe0AJpI', 'resolutions': [], 'source': {'height': 48, 'url': 'https://external-preview.redd.it/jmmAASC2L3jPr8IMbQndoHwcEhlRcp4ORylmCSLA5cc.jpg?auto=webp&s=89ae15513211d6f0cad0aadcf9e1afd679fdd5f2', 'width': 48}, 'variants': {}}]} |
Utilizing two different size GPUs for fine-tuning | 5 | Hey fellow LLAMA enthusiasts! I've got a question about utilizing two A100 GPUs with different RAM sizes (40GB and 10GB) for fine-tuning LLama 7B. I attempted to use \`device\_map= "auto"\` when loading the Hugging Face model, but I encountered an 'OOM' (Out of Memory) error (Probably it expects a GPU of the same size)... | 2023-09-15T16:47:17 | https://www.reddit.com/r/LocalLLaMA/comments/16jifd3/utilizing_two_different_size_gpus_for_finetuning/ | ali0100u | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 16jifd3 | false | null | t3_16jifd3 | /r/LocalLLaMA/comments/16jifd3/utilizing_two_different_size_gpus_for_finetuning/ | false | false | self | 5 | null |
Is there a reason for the lack of superhot ggufs? | 19 | I couldn't think of how to word the title, but I don't mean it as accusatory as it sounds lol. It's honest curiosity.
With llama having dropped ggml support, I realized that all the ggmls I had of "high context" superhot models were no longer viable.
This morning I figured I'd get some downloads going of the gguf ve... | 2023-09-15T16:26:42 | https://www.reddit.com/r/LocalLLaMA/comments/16jhx7m/is_there_a_reason_for_the_lack_of_superhot_ggufs/ | LearningSomeCode | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 16jhx7m | false | null | t3_16jhx7m | /r/LocalLLaMA/comments/16jhx7m/is_there_a_reason_for_the_lack_of_superhot_ggufs/ | false | false | self | 19 | null |
Does anyone know how to finetune Phi-1.5? | 4 | I was trying to do a little finetuning to the new Phi-1.5 but using colab to train a llama 2 model, as I thought it gave me error in the "trainer = SFTTrainer" section.
I get this error: AttributeError: 'MixFormerSequentialForCausalLM' object has no attribute '\_set\_gradient\_checkpointing'.
Does anyone know what I ... | 2023-09-15T16:25:18 | https://www.reddit.com/r/LocalLLaMA/comments/16jhvzi/does_anyone_know_how_to_finetune_phi15/ | danielbrdz | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 16jhvzi | false | null | t3_16jhvzi | /r/LocalLLaMA/comments/16jhvzi/does_anyone_know_how_to_finetune_phi15/ | false | false | self | 4 | null |
Fine-Tuning Llama 70B on Consumer Hardware: A Step-by-Step Guide | 1 | [removed] | 2023-09-15T16:02:08 | https://www.reddit.com/r/LocalLLaMA/comments/16jhb5n/finetuning_llama_70b_on_consumer_hardware_a/ | l33thaxman | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 16jhb5n | false | null | t3_16jhb5n | /r/LocalLLaMA/comments/16jhb5n/finetuning_llama_70b_on_consumer_hardware_a/ | false | false | self | 1 | {'enabled': False, 'images': [{'id': 'BG-_ybG_81cHNdhfcO4SI7RZKgZvJvbtDdAp--yWODA', 'resolutions': [{'height': 81, 'url': 'https://external-preview.redd.it/7MJFP4pv4dd3l5U-iQkpol5U-QDNuNShKtlioenvTJU.jpg?width=108&crop=smart&auto=webp&s=613d5e1fa3925c07e8e1d112648fcd2366c54107', 'width': 108}, {'height': 162, 'url': 'h... |
This week in AI - all the Major AI development in a nutshell | 1 | [removed] | 2023-09-15T14:42:34 | https://www.reddit.com/r/LocalLLaMA/comments/16jf9oy/this_week_in_ai_all_the_major_ai_development_in_a/ | wyem | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 16jf9oy | false | null | t3_16jf9oy | /r/LocalLLaMA/comments/16jf9oy/this_week_in_ai_all_the_major_ai_development_in_a/ | false | false | self | 1 | {'enabled': False, 'images': [{'id': 'XtM-kk73flWxFHhYFhvEqzP_URnfgAcG5CgS8E0YN18', 'resolutions': [{'height': 89, 'url': 'https://external-preview.redd.it/kSnw4CVYfVApLY4mwPR30zRRzHbP-h5qZWbn6gvH5vs.jpg?width=108&crop=smart&auto=webp&s=b36e14f7569ad9b98faf9cc5d9d93974841bea50', 'width': 108}, {'height': 178, 'url': 'h... |
How does one discover the correct rope/freq when converting a model into gguf? | 1 | [removed] | 2023-09-15T13:51:21 | https://www.reddit.com/r/LocalLLaMA/comments/16jdzqi/how_does_one_discover_the_correct_ropefreq_when/ | wh33t | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 16jdzqi | false | null | t3_16jdzqi | /r/LocalLLaMA/comments/16jdzqi/how_does_one_discover_the_correct_ropefreq_when/ | false | false | self | 1 | null |
How much preprocessing are you doing for RAG QA chatbots w/ documents? | 8 | I know there is a ton of interest in document QA systems, which makes sense since it has good business values to most organizations.
I'm wondering for those of you who found the answers from you QA systems to be good, did you guys just drop the PDF / Word / etc... into the program and let the RecursiveCharacterSplitte... | 2023-09-15T13:25:20 | https://www.reddit.com/r/LocalLLaMA/comments/16jde4z/how_much_preprocessing_are_you_doing_for_rag_qa/ | 4hometnumberonefan | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 16jde4z | false | null | t3_16jde4z | /r/LocalLLaMA/comments/16jde4z/how_much_preprocessing_are_you_doing_for_rag_qa/ | false | false | self | 8 | null |
Using a LoRa Trained on a HF model and running it on a GPTQ model? | 5 | So currently most of the fastest models are GPTQ models,
On Oogaabooga you cant a train a QLora Model..and you cant training GPTQ model.
But you can train a HF model but to train it u need to set it to 8bit.
but a HF model is very slow at inference compared to GPTQ model.
Is there no way to Train a LoRa on H... | 2023-09-15T13:20:43 | https://www.reddit.com/r/LocalLLaMA/comments/16jd9yp/using_a_lora_trained_on_a_hf_model_and_running_it/ | mohaziz999 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 16jd9yp | false | null | t3_16jd9yp | /r/LocalLLaMA/comments/16jd9yp/using_a_lora_trained_on_a_hf_model_and_running_it/ | false | false | self | 5 | null |
Behind the Curtain: How do we look inside a Llama model file to browse the data? | 15 | **How do we browse the knowledge database of a model?** I'm sure we don't just pop the 5GB model into excel and start scrolling, or do we?
I have been testing several of the Llama 7B models on the text-generation-webui and it keeps stunning me about things it knows. It knew the exact statute for a law in my state. Li... | 2023-09-15T13:14:49 | https://www.reddit.com/r/LocalLLaMA/comments/16jd4o9/behind_the_curtain_how_do_we_look_inside_a_llama/ | Actual-Bad5029 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 16jd4o9 | false | null | t3_16jd4o9 | /r/LocalLLaMA/comments/16jd4o9/behind_the_curtain_how_do_we_look_inside_a_llama/ | false | false | self | 15 | null |
Ryzen Direct Memory Access in OpenCL mode | 7 | I am looking at making the upgrade from my trusty old AM4 board and I am looking at orienting my upgrades for good price:performance running LLMs.
I remember in the past AMD used to market some of their chips with integrated graphics as APUs. It was my understanding that this went a step beyond traditional integrated... | 2023-09-15T13:10:46 | https://www.reddit.com/r/LocalLLaMA/comments/16jd15h/ryzen_direct_memory_access_in_opencl_mode/ | Apprehensive_Sock_71 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 16jd15h | false | null | t3_16jd15h | /r/LocalLLaMA/comments/16jd15h/ryzen_direct_memory_access_in_opencl_mode/ | false | false | self | 7 | null |
Uncovering mesa-optimization algorithms in Transformers | 22 | https://arxiv.org/abs/2309.05858
I think this is potentially huge, though my puny brain cannot handle the math in the paper.
The bit most relevant here:
*"Finally, we propose a novel self-attention layer, the mesa-layer, that explicitly and efficiently solves optimization problems specified in context. We find that t... | 2023-09-15T12:59:13 | https://www.reddit.com/r/LocalLLaMA/comments/16jcqn4/uncovering_mesaoptimization_algorithms_in/ | BalorNG | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 16jcqn4 | false | null | t3_16jcqn4 | /r/LocalLLaMA/comments/16jcqn4/uncovering_mesaoptimization_algorithms_in/ | false | false | self | 22 | {'enabled': False, 'images': [{'id': 'q3evP6JeDpAC2MdSQHWYxnCYTqbJkElIQsLFqVSdkss', 'resolutions': [{'height': 63, 'url': 'https://external-preview.redd.it/0HhwdU6MKIAKjL9Y8-B_iH374a3NiPTy0ib8lmloRzA.jpg?width=108&crop=smart&auto=webp&s=2711d572cfc6c713893cf24e8c4a7344d5ad8a4c', 'width': 108}, {'height': 126, 'url': 'h... |
Need advice on Local LLM setup to augment AMD GPU shortcomings | 5 | Hi everyone,
**Background:**
I'm a seasoned developer and continuously working on GenAI things for the last 1 year. Recently, I wanted to set up a local LLM/SD server to work on a few confidential projects that I cannot move into the cloud. I have gone through the posts recommending renting cloud GPU and started wit... | 2023-09-15T12:31:05 | https://www.reddit.com/r/LocalLLaMA/comments/16jc2p0/need_advice_on_local_llm_setup_to_augment_amd_gpu/ | kkb294 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 16jc2p0 | false | null | t3_16jc2p0 | /r/LocalLLaMA/comments/16jc2p0/need_advice_on_local_llm_setup_to_augment_amd_gpu/ | false | false | self | 5 | null |
Try models fine-tuned for your language | 10 | For those who are not satisfied with these Open models, have you tried using fine-tuned models with datasets for your language?
I am Italian, and I have always been unsatisfied. The only 'decent' model is WizardLM 70B; the other models are all poor in comparison.
Not to mention the base models: they are practical... | 2023-09-15T12:26:36 | https://www.reddit.com/r/LocalLLaMA/comments/16jbz0i/try_models_finetuned_for_your_language/ | AntoItaly | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 16jbz0i | false | null | t3_16jbz0i | /r/LocalLLaMA/comments/16jbz0i/try_models_finetuned_for_your_language/ | false | false | self | 10 | {'enabled': False, 'images': [{'id': 'snUVaj9pVE_H3kUtH1WnuOG8IMqKxRf149JHPX68nio', 'resolutions': [{'height': 58, 'url': 'https://external-preview.redd.it/WAMhuWv7E4a5fTpH_65H5WnqhJCxHmGdW6KPoL5WqWM.jpg?width=108&crop=smart&auto=webp&s=77fb3e3ac77caa8bd7df19d0d39e2dfafb26d1e3', 'width': 108}, {'height': 116, 'url': 'h... |
Easy method for fine-tuning any model from llama to gpt to othera | 3 | Can someone pls provide me with a script that I can run on Google colab I want to finetune 100m to 500m model on the free colab plan with dataset that is between 100k to 30k in size any help please even if there is no script can you provide me with s software or anything else that can help. | 2023-09-15T10:45:07 | https://www.reddit.com/r/LocalLLaMA/comments/16j9up6/easy_method_for_finetuning_any_model_from_llama/ | Puzzleheaded_Acadia1 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 16j9up6 | false | null | t3_16j9up6 | /r/LocalLLaMA/comments/16j9up6/easy_method_for_finetuning_any_model_from_llama/ | false | false | self | 3 | null |
Any Uncensored Llama2 model for commercial use? | 3 | Are there any Llama2 based model out there that haven't been trained with data made by OpenAI API?
I have been wondering if there might be a need for chatbots for companies, where a censored model is unusable.
For example, an eCommerce who would like to have a chatbot for guide and suggestions, would have a hard t... | 2023-09-15T10:29:47 | https://www.reddit.com/r/LocalLLaMA/comments/16j9l39/any_uncensored_llama2_model_for_commercial_use/ | nixudos | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 16j9l39 | false | null | t3_16j9l39 | /r/LocalLLaMA/comments/16j9l39/any_uncensored_llama2_model_for_commercial_use/ | false | false | self | 3 | null |
Some interesting new tests just dropped | 38 | 2023-09-15T09:57:19 | https://evolutionnews.org/2023/09/chatgpt-is-becoming-increasingly-impressive/ | ambient_temp_xeno | evolutionnews.org | 1970-01-01T00:00:00 | 0 | {} | 16j90yr | false | null | t3_16j90yr | /r/LocalLLaMA/comments/16j90yr/some_interesting_new_tests_just_dropped/ | false | false | 38 | {'enabled': False, 'images': [{'id': 'WPf9sBmJpsNWI-iOg7b9rUdeAF4wGQEPPzrnTt88b1I', 'resolutions': [{'height': 56, 'url': 'https://external-preview.redd.it/iFvVjgxq-c4zUadOelgZ85TokJjGgKkxfeFOxd543aw.jpg?width=108&crop=smart&auto=webp&s=6386e8c67744622d89fcde2c20850e5702f8d3dd', 'width': 108}, {'height': 113, 'url': 'h... | ||
I don't understand context window extension | 44 | If an transformer can only attend to, say, 2048, then how can that same transformer attend to more than 2048 tokens. Isn't that hard coded in the architecture?
I can understand that you might summarise previous chunks of 2048 tokens and pass that 'hidden state' forward or emulate a larger context window with a slidi... | 2023-09-15T09:39:28 | https://www.reddit.com/r/LocalLLaMA/comments/16j8qa5/i_dont_understand_context_window_extension/ | moma1970 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 16j8qa5 | false | null | t3_16j8qa5 | /r/LocalLLaMA/comments/16j8qa5/i_dont_understand_context_window_extension/ | false | false | self | 44 | null |
How much does it cost to fine-tune on a code base? | 2 | Would the appropriate metric be cost per GB of source files?
Would love some reference points for finetunning costs and performance (would love examples of performance vs un-tuned GPT4) of Code Llama, Startcoder, etc. on own code base with docs.
Thanks | 2023-09-15T09:34:05 | https://www.reddit.com/r/LocalLLaMA/comments/16j8n5q/how_much_does_it_cost_to_finetune_on_a_code_base/ | Infinite100p | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 16j8n5q | false | null | t3_16j8n5q | /r/LocalLLaMA/comments/16j8n5q/how_much_does_it_cost_to_finetune_on_a_code_base/ | false | false | self | 2 | null |
Tuning an LLM on my own notes over time | 19 | I’ve been hearing a lot of talk about noteworthy people creating AI clones of themselves using the mass of data they’ve generated over the years.
I think this is pretty cool, but difficult to do for an average person. So my solution would be to record voice notes throughout the day, transcribe them, and add them to th... | 2023-09-15T07:33:32 | https://www.reddit.com/r/LocalLLaMA/comments/16j6q7r/tuning_an_llm_on_my_own_notes_over_time/ | michaelthatsit | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 16j6q7r | false | null | t3_16j6q7r | /r/LocalLLaMA/comments/16j6q7r/tuning_an_llm_on_my_own_notes_over_time/ | false | false | self | 19 | null |
Some questions of implementing LLM to generate Q/A pairs based on local documents | 3 | Recently, I have been paying around about how to implement chat-based Q/A using the LLM model based on a local knowledge base.
I have experimented with the following two open-source frameworks.
[Llama\_index](https://github.com/jerryjliu/llama_index)
[Langchain-chatchat](https://github.com/chatchat-space/Langchain... | 2023-09-15T06:52:31 | https://www.reddit.com/r/LocalLLaMA/comments/16j624z/some_questions_of_implementing_llm_to_generate_qa/ | william_luckybob | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 16j624z | false | null | t3_16j624z | /r/LocalLLaMA/comments/16j624z/some_questions_of_implementing_llm_to_generate_qa/ | false | false | 3 | {'enabled': False, 'images': [{'id': 'pfcqrH7buFAmKsvruxLEC8k2mjFW6UvVXRz1AwKYa44', 'resolutions': [{'height': 54, 'url': 'https://external-preview.redd.it/LBlgmVOAXLqerXsfJbE68VfDP0dDCf-STi5W_GzltkY.jpg?width=108&crop=smart&auto=webp&s=c4412dd9bcb447ba4bf759fb93252ec7cc29eaa7', 'width': 108}, {'height': 108, 'url': 'h... | |
Methods for Enabling LLMs to Work with Languages Other Than English: How Does ChatGPT Do It? | 7 | Hello. Are there any methods that would allow an LLM to work with languages other than English? For example, how does ChatGPT achieve this? Could you please discuss the methods you are aware of for achieving this? | 2023-09-15T06:42:22 | https://www.reddit.com/r/LocalLLaMA/comments/16j5w7f/methods_for_enabling_llms_to_work_with_languages/ | PickkNickk | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 16j5w7f | false | null | t3_16j5w7f | /r/LocalLLaMA/comments/16j5w7f/methods_for_enabling_llms_to_work_with_languages/ | false | false | self | 7 | null |
Guys, why are we sleeping on MLC LLM - Running on Vulkan? | 80 | I just tested on my 4090 and its incredibly fast and it actually has decent instructions to get the packages and run it. It's surprisingly fast compared to what I was seeing via CUDA and it seems to be fully utilizing my GPU. Im gonna try it on my ROG ally next.
https://preview.redd.it/h4fv2id7qcob1.png?width=1060&... | 2023-09-15T05:03:58 | https://www.reddit.com/r/LocalLLaMA/comments/16j486g/guys_why_are_we_sleeping_on_mlc_llm_running_on/ | APUsilicon | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 16j486g | false | null | t3_16j486g | /r/LocalLLaMA/comments/16j486g/guys_why_are_we_sleeping_on_mlc_llm_running_on/ | false | false | 80 | null | |
Wizard Coder - CUDA out of memory. Tried to allocate | 1 | [removed] | 2023-09-15T04:07:36 | https://www.reddit.com/r/LocalLLaMA/comments/16j37e2/wizard_coder_cuda_out_of_memory_tried_to_allocate/ | NormalResume | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 16j37e2 | false | null | t3_16j37e2 | /r/LocalLLaMA/comments/16j37e2/wizard_coder_cuda_out_of_memory_tried_to_allocate/ | false | false | self | 1 | {'enabled': False, 'images': [{'id': 'UY7-Y9YFSwqNihyhNh7qaNVidPA3KZOLpPUFt7eJqKo', 'resolutions': [{'height': 58, 'url': 'https://external-preview.redd.it/LOC8gQl7_gtTBmz0_ltFp84qpA4hZfksAUsBpa0r2dE.jpg?width=108&crop=smart&auto=webp&s=23223fc45c2fd69013b486eef8efb8b37a394e59', 'width': 108}, {'height': 116, 'url': 'h... |
Old Comp Running LLM! I got llama-2-7b-chat.Q2_K.gguf running on 10-year-old iMac, response in 40-sec at 1-t/s | 16 | **I have an 8GB Ram late 2013 iMac running macOS Catalina.** I installed the text-generation-webui and just pasted in model card link (TheBloke/ llama-2-7b-chat.Q2\_K.gguf) - BAM WORKS, it's blowing me away! Y'all, this machine is old and decrepit. No GPU.
I asked this: Explain the temptation of Christ from the Holy ... | 2023-09-15T03:18:41 | https://www.reddit.com/r/LocalLLaMA/comments/16j29s3/old_comp_running_llm_i_got_llama27bchatq2_kgguf/ | Actual-Bad5029 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 16j29s3 | false | null | t3_16j29s3 | /r/LocalLLaMA/comments/16j29s3/old_comp_running_llm_i_got_llama27bchatq2_kgguf/ | false | false | self | 16 | null |
MythoMax 13b and Mythomax 33b | 30 | Okay, Mythomax 13b is sweet. Really sweet in writing stuff. for 13b buy in short pants.
I tried Mythomax L2 33B and I couldn't get heads and tails out of it. I really couldn't.
Is it me? Is it my pet hamster? Or the 33b is really bonks. I tried the 6bit quant for extra points, but buy, it was all mangled together no... | 2023-09-15T02:41:19 | https://www.reddit.com/r/LocalLLaMA/comments/16j1ial/mythomax_13b_and_mythomax_33b/ | FPham | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 16j1ial | false | null | t3_16j1ial | /r/LocalLLaMA/comments/16j1ial/mythomax_13b_and_mythomax_33b/ | false | false | self | 30 | null |
Working in Python code, will Llama 2 return a table in JSON format when prompted? | 4 | Hi everyone, I wanted to confirm this question below before really jumping into Llama 2.
If I prompted Llama to provide answers in JSON format, for eg. something like this prompt:
sequences = pipeline("Provide your answer in the JSON format with the feature names as the keys.")
Then following that in my Python c... | 2023-09-15T02:34:57 | https://www.reddit.com/r/LocalLLaMA/comments/16j1dk8/working_in_python_code_will_llama_2_return_a/ | --leockl-- | self.LocalLLaMA | 2023-09-15T02:39:11 | 0 | {} | 16j1dk8 | false | null | t3_16j1dk8 | /r/LocalLLaMA/comments/16j1dk8/working_in_python_code_will_llama_2_return_a/ | false | false | self | 4 | null |
Trail LLM Torrent Support - stablebay.org | 5 | 2023-09-15T01:26:54 | thiefyzheng | i.redd.it | 1970-01-01T00:00:00 | 0 | {} | 16izy8n | false | null | t3_16izy8n | /r/LocalLLaMA/comments/16izy8n/trail_llm_torrent_support_stablebayorg/ | false | false | 5 | {'enabled': True, 'images': [{'id': '5vxjMNoEcZa-bycsTAKsDIyRUx2qcBlxvq_wNEULCLU', 'resolutions': [{'height': 104, 'url': 'https://preview.redd.it/jj9jadbnnbob1.png?width=108&crop=smart&auto=webp&s=75e5126372d2b05eaa4a2180e69330c16ea1592a', 'width': 108}, {'height': 208, 'url': 'https://preview.redd.it/jj9jadbnnbob1.pn... | |||
Censor & LlaMAS | 1 | [removed] | 2023-09-15T00:24:09 | https://www.reddit.com/r/LocalLLaMA/comments/16iymfw/censor_llamas/ | holistic-engine | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 16iymfw | false | null | t3_16iymfw | /r/LocalLLaMA/comments/16iymfw/censor_llamas/ | false | false | self | 1 | null |
Ai only for rich and powerful - Closed Door Summit | 1 | [removed] | 2023-09-14T22:49:03 | https://www.reddit.com/r/LocalLLaMA/comments/16iwix3/ai_only_for_rich_and_powerful_closed_door_summit/ | Single_Ring4886 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 16iwix3 | false | null | t3_16iwix3 | /r/LocalLLaMA/comments/16iwix3/ai_only_for_rich_and_powerful_closed_door_summit/ | false | false | self | 1 | {'enabled': False, 'images': [{'id': 'hSr_Qzar9WIY3xBupwjJLtcozfLPOTBmWCTAjoTJUwI', 'resolutions': [{'height': 81, 'url': 'https://external-preview.redd.it/5n7ZyfQrJixtnp_-YLsuot0Q0EoUgVxHPyUzl5XPx2k.jpg?width=108&crop=smart&auto=webp&s=fd09c08144fcede846fb5f42f6f0d8123550582a', 'width': 108}, {'height': 162, 'url': 'h... |
Need Help In Creating an App with the custom data | 0 | I am planning to create an app, using my own custom data which will generate articles from the internet and from the data I used. The challenge I'm facing is that I lack the necessary knowledge in this area, and I'm struggling to find appropriate tutorials or resources to assist me.
I've already tried doing this w... | 2023-09-14T22:02:15 | https://www.reddit.com/r/LocalLLaMA/comments/16ivdqr/need_help_in_creating_an_app_with_the_custom_data/ | adgamerx | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 16ivdqr | false | null | t3_16ivdqr | /r/LocalLLaMA/comments/16ivdqr/need_help_in_creating_an_app_with_the_custom_data/ | false | false | self | 0 | null |
I'm a former Atari engineer trying to catch up with the current tech. | 123 | What models can I run on my Atari 5200? I'm willing to code in assembly.
/s | 2023-09-14T21:51:35 | https://www.reddit.com/r/LocalLLaMA/comments/16iv40g/im_a_former_atari_engineer_trying_to_catch_up/ | Musenik | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 16iv40g | false | null | t3_16iv40g | /r/LocalLLaMA/comments/16iv40g/im_a_former_atari_engineer_trying_to_catch_up/ | false | false | self | 123 | null |
The first low code platform for AI engineers | 0 | I'm curious what the appetite for low code platforms in the AI space is. Would you be interested in using it?
Here's a look at what this looks like: [https://www.loom.com/share/Building-AI-Agents-with-airkitai-8d7513639e8e4c7e9d8e449945f9f827?sid=fa0a1ef1-6aa5-4174-8923-2e5ac8345c46](https://www.loom.com/share/Buildin... | 2023-09-14T21:31:49 | https://www.reddit.com/r/LocalLLaMA/comments/16ium1u/the_first_low_code_platform_for_ai_engineers/ | Brickchip | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 16ium1u | false | null | t3_16ium1u | /r/LocalLLaMA/comments/16ium1u/the_first_low_code_platform_for_ai_engineers/ | false | false | self | 0 | {'enabled': False, 'images': [{'id': 'qeifkwwr4C5QSg58B_96VUqdBQ2DqQxNVOT5ptzpTrU', 'resolutions': [{'height': 54, 'url': 'https://external-preview.redd.it/owNWn__zv73jr2iy1sm5GuH1uE2FXSKjk4L1ofzHRTk.jpg?width=108&crop=smart&auto=webp&s=4bc3ef15bdc48068b5b46ef3d57ff16363a52a24', 'width': 108}, {'height': 108, 'url': 'h... |
AgentVerse Tweet | 3 | 2023-09-14T21:21:47 | https://x.com/_akhaliq/status/1702336679200411697?s=20 | ninjasaid13 | x.com | 1970-01-01T00:00:00 | 0 | {} | 16iuckj | false | null | t3_16iuckj | /r/LocalLLaMA/comments/16iuckj/agentverse_tweet/ | false | false | 3 | {'enabled': False, 'images': [{'id': 'ZTimAguvRBSAjvxetJaWSl1X0GzGpsavj2__vyaC3CU', 'resolutions': [{'height': 51, 'url': 'https://external-preview.redd.it/hM4PFte2OkZRRl25PEeotd5322aQvpdS-t3521oV4Cg.jpg?width=108&crop=smart&auto=webp&s=1fc9e75140401dcabe6bb64f85867d724c02e629', 'width': 108}, {'height': 102, 'url': 'h... | ||
EVGA has B Stock 3090s for $799. If you are looking for a 3090 for LLM, that's less risky than ebay and comes with a 1 year warranty. | 41 | 2023-09-14T19:45:21 | https://www.evga.com/Products/ProductList.aspx?type=8&family=GeForce+30+Series+Family | fallingdowndizzyvr | evga.com | 1970-01-01T00:00:00 | 0 | {} | 16irv4q | false | null | t3_16irv4q | /r/LocalLLaMA/comments/16irv4q/evga_has_b_stock_3090s_for_799_if_you_are_looking/ | false | false | default | 41 | {'enabled': False, 'images': [{'id': 'Ruit8EXjtCUHoA47xon6Jgy0DyGgbBpqEhT4bxHb7Zw', 'resolutions': [{'height': 56, 'url': 'https://external-preview.redd.it/chuNpJIfSq758UCgRgDUBXSMk3vZuU-gaxgFc2uSM-c.jpg?width=108&crop=smart&auto=webp&s=0a3d8edf41c42cce7c42aa32cedfb7e16911a94b', 'width': 108}, {'height': 113, 'url': 'h... | |
How can I make Llama models run faster on an M1 Max Macbook Pro? | 1 | I've been tinkering around with some models like Nous Hermes Llama2 and even at 70b and Q5\_K\_M they're not quite the quality I'd like from a llvm. They also take about 5 minutes to complete. Going up to Q6 makes the model spit out like one word every two minutes, and to add insult to injury it just rejected my prompt... | 2023-09-14T19:10:14 | https://www.reddit.com/r/LocalLLaMA/comments/16ir0gx/how_can_i_make_llama_models_run_faster_on_an_m1/ | Aggravating-Cycle849 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 16ir0gx | false | null | t3_16ir0gx | /r/LocalLLaMA/comments/16ir0gx/how_can_i_make_llama_models_run_faster_on_an_m1/ | false | false | self | 1 | {'enabled': False, 'images': [{'id': 'FOXRcjq6EmV89ZPB-n-5TMZxyzpll7exPtcP9cbhSp0', 'resolutions': [{'height': 54, 'url': 'https://external-preview.redd.it/REuTYd8PlyiYPTl61QJBZlbtV-Ew0MPwzYmorXef_bk.jpg?width=108&crop=smart&auto=webp&s=25cecfc12b5e14f197824f92c8ffdec5bd758e0e', 'width': 108}, {'height': 108, 'url': 'h... |
Recommendations for an open source LLM front end? | 1 | Anyone have suggestions for an open source web-based front end for a conversational AI like Llama? I am using [TheBloke/Llama-2-13B-chat-GGUF/llama-2-13b-chat.Q4\_K\_S.gguf](https://huggingface.co/TheBloke/Llama-2-13B-chat-GGUF/tree/main) with [h2ogpt](https://github.com/h2oai/h2ogpt).
I am wondering if there's a mor... | 2023-09-14T19:02:51 | https://www.reddit.com/r/LocalLLaMA/comments/16iqttw/recommendations_for_an_open_source_llm_front_end/ | PumpkinCurryLover | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 16iqttw | false | null | t3_16iqttw | /r/LocalLLaMA/comments/16iqttw/recommendations_for_an_open_source_llm_front_end/ | false | false | self | 1 | {'enabled': False, 'images': [{'id': 'HmCost0PHUStH4CIQyopO6sHUeNQMwjXw6cWlMAT6W4', 'resolutions': [{'height': 58, 'url': 'https://external-preview.redd.it/ZiVsYqYJJXC5Wtg9jErByB57rKU04QIW-wKSulXntAQ.jpg?width=108&crop=smart&auto=webp&s=d917fe654a56f1f55cb5059b559eef2e7a6c0201', 'width': 108}, {'height': 116, 'url': 'h... |
Llama API-as-a-service? | 1 | I need to use a Llama model but i don’t want to host it myself, are there any good services besides replicate that offer some sort of API for Llama 2 variants that i could inference off of? | 2023-09-14T18:02:46 | https://www.reddit.com/r/LocalLLaMA/comments/16ipb22/llama_apiasaservice/ | NickDifuze | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 16ipb22 | false | null | t3_16ipb22 | /r/LocalLLaMA/comments/16ipb22/llama_apiasaservice/ | false | false | self | 1 | null |
Which fuzzy text search tool is better? Not in terms of search speed, but in terms of quality. | 1 | I have compared searching using the chromadb database and the Python fuzzywuzzy library. It seems that fuzzywuzzy provides even better results. However, I suspect that my experiment might not be entirely accurate, and I may be doing something wrong. | 2023-09-14T17:49:52 | https://www.reddit.com/r/LocalLLaMA/comments/16ioz2o/which_fuzzy_text_search_tool_is_better_not_in/ | Pristine-Tax4418 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 16ioz2o | false | null | t3_16ioz2o | /r/LocalLLaMA/comments/16ioz2o/which_fuzzy_text_search_tool_is_better_not_in/ | false | false | self | 1 | null |
how does a model summarize a super long book with only a 4k context window? | 13 | question that's been on my mind, if a model is asked to summarize a super long book that is has not been trained, how does it do it since most context windows around between 4k-32k? | 2023-09-14T17:44:12 | https://www.reddit.com/r/LocalLLaMA/comments/16iou2f/how_does_a_model_summarize_a_super_long_book_with/ | konrad21 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 16iou2f | false | null | t3_16iou2f | /r/LocalLLaMA/comments/16iou2f/how_does_a_model_summarize_a_super_long_book_with/ | false | false | self | 13 | null |
I am not a scammer. I am advancing AI research through open source. | 1 | [removed] | 2023-09-14T17:26:28 | https://www.reddit.com/r/LocalLLaMA/comments/16iodwn/i_am_not_a_scammer_i_am_advancing_ai_research/ | Scary-Present4451 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 16iodwn | false | null | t3_16iodwn | /r/LocalLLaMA/comments/16iodwn/i_am_not_a_scammer_i_am_advancing_ai_research/ | false | false | self | 1 | null |
Searching for chunking algorithms and repo | 1 | Hi everyone!
I'm still experiencing with my own implementation of rag, and I deployed my custom chunking function (honestly don't like the methods on LangChain) .
Anyway, I'm searching for alternative methods, algoritms (NLP or not) and models... There are lots of info and different implementation on RAG, but as I ... | 2023-09-14T16:35:00 | https://www.reddit.com/r/LocalLLaMA/comments/16in2bg/searching_for_chunking_algorithms_and_repo/ | Distinct-Target7503 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 16in2bg | false | null | t3_16in2bg | /r/LocalLLaMA/comments/16in2bg/searching_for_chunking_algorithms_and_repo/ | false | false | self | 1 | null |
Recommend a Local LLM for low spec laptop | 9 | I have 8gb ram and 2gb vram. Suggest me an LLM. I'm a total noob to using LLMs.
​
I want it to help me write stories. So I input a long text and I want the model to give me the next sentence. | 2023-09-14T16:06:47 | https://www.reddit.com/r/LocalLLaMA/comments/16imcc0/recommend_a_local_llm_for_low_spec_laptop/ | Little-Shoulder-5835 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 16imcc0 | false | null | t3_16imcc0 | /r/LocalLLaMA/comments/16imcc0/recommend_a_local_llm_for_low_spec_laptop/ | false | false | self | 9 | null |
i am testing to see if i can do top level posts | 1 | [removed] | 2023-09-14T15:26:58 | https://www.reddit.com/r/LocalLLaMA/comments/16ilcrn/i_am_testing_to_see_if_i_can_do_top_level_posts/ | MrEloi | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 16ilcrn | false | null | t3_16ilcrn | /r/LocalLLaMA/comments/16ilcrn/i_am_testing_to_see_if_i_can_do_top_level_posts/ | false | false | default | 1 | null |
Question about fine tuning | 6 | I’m curious how you would fine tune (or QLORA) with these purposes (separately):
1) you have a large collection of stories by an author and you want to write more stories in their style
2) you have a large collection of codebases that you want to be able to ask questions about
I’m unclear about when you’d use instru... | 2023-09-14T15:23:25 | https://www.reddit.com/r/LocalLLaMA/comments/16il9li/question_about_fine_tuning/ | maxiedaniels | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 16il9li | false | null | t3_16il9li | /r/LocalLLaMA/comments/16il9li/question_about_fine_tuning/ | false | false | self | 6 | null |
Subsets and Splits
No community queries yet
The top public SQL queries from the community will appear here once available.