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 ⌀ |
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
Just installed LLAMA 7B 8-bit and it does this. It never generates not even single token and the output window is empty. Any idea what it could be? I am using RTX 2060 12GB | 6 | [deleted] | null | [deleted] | 1970-01-01T00:00:00 | 0 | {} | 11rcl2h | false | null | t3_11rcl2h | /r/LocalLLaMA/comments/11rcl2h/just_installed_llama_7b_8bit_and_it_does_this_it/ | false | false | default | 6 | null | ||
My attempt at testing the "creativity" of Stanford's Alpaca showed interesting results. | 18 | Blog post here: https://medium.com/sort-of-like-a-tech-diary/speculative-fiction-with-stanford-alpaca-fe99d3c39de7
The hosted demo is now a lot easier to use. I'm amazed at the performance of the 7B model! | null | https://www.reddit.com/r/LocalLLaMA/comments/11redfk/my_attempt_at_testing_the_creativity_of_stanfords/ | _wsgeorge | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 11redfk | false | null | t3_11redfk | /r/LocalLLaMA/comments/11redfk/my_attempt_at_testing_the_creativity_of_stanfords/ | false | false | self | 18 | {'enabled': False, 'images': [{'id': '54JyBdi_F3dD0tDq8h3veIzoQ4TqQqQeQMrYA2nQi-4', 'resolutions': [{'height': 65, 'url': 'https://external-preview.redd.it/EQE59u8d9IBQrM9otY29V9xev70LTpjxv00JkHw4l38.jpg?width=108&crop=smart&auto=webp&v=enabled&s=12307c4c42213bf7ffb097993867767b98865689', 'width': 108},... |
tested some questions for AIs | 17 | googled some questions for turing tests(or just difficult questions for AIs) and asked to LLaMA 30B. interesting answers in the pictures above | null | https://www.reddit.com/gallery/11rkts9 | Capable-Outside-601 | reddit.com | 1970-01-01T00:00:00 | 0 | {} | 11rkts9 | false | null | t3_11rkts9 | /r/LocalLLaMA/comments/11rkts9/tested_some_questions_for_ais/ | false | false | 17 | null | |
Multi-GPU training? | 8 | Any resource showing/discussing Llama finetuning in multi-gpu setup. Till now only 7B finetuning has been discussed everywhere. | null | https://www.reddit.com/r/LocalLLaMA/comments/11rno6h/multigpu_training/ | Raise_Fickle | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 11rno6h | false | null | t3_11rno6h | /r/LocalLLaMA/comments/11rno6h/multigpu_training/ | false | false | self | 8 | null |
Is there online Discord channel i could join in and use LLaMA? | 2 | [removed] | null | https://www.reddit.com/r/LocalLLaMA/comments/11rqiv3/is_there_online_discord_channel_i_could_join_in/ | Deformero | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 11rqiv3 | false | null | t3_11rqiv3 | /r/LocalLLaMA/comments/11rqiv3/is_there_online_discord_channel_i_could_join_in/ | false | false | default | 2 | null |
Integrate LLaMA into python code | 9 | Is it possible to directly use LLaMA in python or have it serve as an API? Or is there a way to read the output from web ui? I want to combine LLaMA and tortoise-tts to make a speaking chatbot. | null | https://www.reddit.com/r/LocalLLaMA/comments/11s5f39/integrate_llama_into_python_code/ | Tree-Sheep | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 11s5f39 | false | null | t3_11s5f39 | /r/LocalLLaMA/comments/11s5f39/integrate_llama_into_python_code/ | false | false | self | 9 | null |
Can someone ELI5 where's the best place to fine tune LLaMA? | 9 | I can run inference for 7b on a spare laptop I have using llama.cpp. But it's obviously not enough for fine-tuning. What are my options for fine tuning a model that I can then download and use locally for inference? I'm somewhat familiar with Colab, but not much else. | null | https://www.reddit.com/r/LocalLLaMA/comments/11s8585/can_someone_eli5_wheres_the_best_place_to_fine/ | noellarkin | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 11s8585 | false | null | t3_11s8585 | /r/LocalLLaMA/comments/11s8585/can_someone_eli5_wheres_the_best_place_to_fine/ | false | false | self | 9 | null |
Alpaca LoRa - finetuning possible on 24GB VRAM now (but LoRA) | 34 | null | https://github.com/tloen/alpaca-lora | Dany0 | github.com | 1970-01-01T00:00:00 | 0 | {} | 11sgewy | false | null | t3_11sgewy | /r/LocalLLaMA/comments/11sgewy/alpaca_lora_finetuning_possible_on_24gb_vram_now/ | false | false | 34 | {'enabled': False, 'images': [{'id': 'Eq_4h44nawr0IhLfmier4mYbLhRWm9VnF05FD-aQ9a0', 'resolutions': [{'height': 54, 'url': 'https://external-preview.redd.it/NOO2EMGh4kGIHWz8hav8xXQZuc8ABpVeXgXgn42yUmA.jpg?width=108&crop=smart&auto=webp&v=enabled&s=2c82720ca98f6c0155b3361cfe82edae1b61e78b', 'width': 108},... | ||
Why is 4bit llama slower on a 32GB RAM 3090 windows machine vs. a M1 Pro 32GB ram with llama.cpp? | 20 | The token rate on the 4bit 30B param model is much faster with llama.cpp on a M1 Pro than the 4bit model on a 3090 with ooobabooga, and I know it's using the GPU looking at performance monitor on the windows machine. This really surprised me, since the 3090 overall is much faster with stable diffusion. | null | https://www.reddit.com/r/LocalLLaMA/comments/11smshi/why_is_4bit_llama_slower_on_a_32gb_ram_3090/ | EveningFunction | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 11smshi | false | null | t3_11smshi | /r/LocalLLaMA/comments/11smshi/why_is_4bit_llama_slower_on_a_32gb_ram_3090/ | false | false | self | 20 | null |
Downloadable 4-bit weights for llama.cpp? | 1 | [removed] | null | https://www.reddit.com/r/LocalLLaMA/comments/11t4fk4/downloadable_4bit_weights_for_llamacpp/ | rwallace | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 11t4fk4 | false | null | t3_11t4fk4 | /r/LocalLLaMA/comments/11t4fk4/downloadable_4bit_weights_for_llamacpp/ | false | false | default | 1 | null |
Working initial prompt for Llama (13b 4bit) | 38 | After spending around 8 hours getting nothing but garbage from Llama, I had a lengthy discussion with ChatGPT, where I described the problem in detail. ChatGPT generated me an initial prompt for Llama, and oh boy, it's good. Incomplete, but good. So I thought I'd share it here.
## TL;DR Llama showcase
Science:
>U... | null | https://www.reddit.com/r/LocalLLaMA/comments/11tkp8j/working_initial_prompt_for_llama_13b_4bit/ | ed2mXeno | self.LocalLLaMA | 2023-03-17T09:27:16 | 0 | {} | 11tkp8j | false | null | t3_11tkp8j | /r/LocalLLaMA/comments/11tkp8j/working_initial_prompt_for_llama_13b_4bit/ | false | false | self | 38 | {'enabled': False, 'images': [{'id': 'nPwfJj9s_3EPdZPVH8kMNIuoRYsUTaKohro97gmK6Uc', 'resolutions': [{'height': 54, 'url': 'https://external-preview.redd.it/M5EQFa9_zxbvDsztN77l-4ZA4cxP6RlOhqGYFVzjUSo.jpg?width=108&crop=smart&auto=webp&v=enabled&s=9c47bd9b033f76757446abf27f581bbd633adb26', 'width': 108},... |
65B quantized model on CPU? | 2 | Is there a way to quantize the 65B model on the CPU? Llama.cpp has instructions but I'm not sure how much RAM it takes. Does anyone have a quantized model already that could be shared? The only thing I've found so far are quantized models for GPUs but I don't have that much VRAM as I do DRAM. | null | https://www.reddit.com/r/LocalLLaMA/comments/11udbga/65b_quantized_model_on_cpu/ | zxyzyxz | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 11udbga | false | null | t3_11udbga | /r/LocalLLaMA/comments/11udbga/65b_quantized_model_on_cpu/ | false | false | self | 2 | null |
What's the best cloud GPU service for 65B? | 8 | I've seen vast.ai mentioned a lot, anyone have experience with them, or another service? And what GPU would work best? | null | https://www.reddit.com/r/LocalLLaMA/comments/11uidst/whats_the_best_cloud_gpu_service_for_65b/ | zxyzyxz | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 11uidst | false | null | t3_11uidst | /r/LocalLLaMA/comments/11uidst/whats_the_best_cloud_gpu_service_for_65b/ | false | false | self | 8 | null |
Alpaca recreation without LORA ( released as a diff. ) | 19 | null | https://github.com/pointnetwork/point-alpaca | starstruckmon | github.com | 1970-01-01T00:00:00 | 0 | {} | 11umkh3 | false | null | t3_11umkh3 | /r/LocalLLaMA/comments/11umkh3/alpaca_recreation_without_lora_released_as_a_diff/ | false | false | 19 | {'enabled': False, 'images': [{'id': 'prU_apL6c9csu2IEJIj6cTxrhigxDSDc-nQiYBAFTl4', 'resolutions': [{'height': 54, 'url': 'https://external-preview.redd.it/L4oNJvIIWOW9d1lpEPRgp_txFP7ghCEapCOzBt6OU3U.jpg?width=108&crop=smart&auto=webp&v=enabled&s=7ce7a30b2a184b0401f055dce412ad8bdc538bbb', 'width': 108},... | ||
New installs are currently broken, but oobagooba is looking into it | 6 | null | https://github.com/oobabooga/text-generation-webui/issues/400 | antialtinian | github.com | 1970-01-01T00:00:00 | 0 | {} | 11uqyk1 | false | null | t3_11uqyk1 | /r/LocalLLaMA/comments/11uqyk1/new_installs_are_currently_broken_but_oobagooba/ | false | false | 6 | {'enabled': False, 'images': [{'id': 'RxLXoEKrP-8McgGL4Aajn8DuqSoNYBeoDM2R2QvF9pM', 'resolutions': [{'height': 54, 'url': 'https://external-preview.redd.it/wdb-Kd99EbN4eGAbxJGwEnT8JfdI7OwZ7CalnbE9ayg.jpg?width=108&crop=smart&auto=webp&v=enabled&s=59fcfb43ac8fed495c375c7722a16f48705af078', 'width': 108},... | ||
Trying to get 4bit to work, always get CUDA not found error (Win and WSL) | 1 | [removed] | null | https://www.reddit.com/r/LocalLLaMA/comments/11urjz0/trying_to_get_4bit_to_work_always_get_cuda_not/ | Outside_You_Forever | self.LocalLLaMA | 2023-03-18T15:52:21 | 0 | {} | 11urjz0 | false | null | t3_11urjz0 | /r/LocalLLaMA/comments/11urjz0/trying_to_get_4bit_to_work_always_get_cuda_not/ | false | false | default | 1 | null |
Using Whisper, LLaMA-13B, and SD at the same time on a single 4090 | 26 | null | https://v.redd.it/qvkvgmw6fkoa1 | WarProfessional3278 | v.redd.it | 1970-01-01T00:00:00 | 0 | {} | 11v1dbu | false | {'reddit_video': {'bitrate_kbps': 4800, 'dash_url': 'https://v.redd.it/qvkvgmw6fkoa1/DASHPlaylist.mpd?a=1683595705%2CODZhOGNhODIyN2U3NzI3YjliZDc3NzI5ZDc1MDM0MzgwODU1ZGVlMTk4NmZmZWZhYzI0N2I1MjQ4MTg4YWIxMA%3D%3D&v=1&f=sd', 'duration': 35, 'fallback_url': 'https://v.redd.it/qvkvgmw6fkoa1/DASH_1080.mp4?source=fallb... | t3_11v1dbu | /r/LocalLLaMA/comments/11v1dbu/using_whisper_llama13b_and_sd_at_the_same_time_on/ | false | false | 26 | {'enabled': False, 'images': [{'id': 'ufF2ZXRn1sCqAkXx1WZM0-xMyQxgh2MwZOyfNY648_k', 'resolutions': [{'height': 60, 'url': 'https://external-preview.redd.it/qc8KtCahPmPoR1DkWCRObQCCZHBybaNVN7tiLtaIr5k.png?width=108&crop=smart&format=pjpg&auto=webp&v=enabled&s=a89c9f1a452d0a07fb073f7b3399cef52c5ae932'... | ||
Alpaca 13B loading issue | 0 | [removed] | null | [deleted] | 2023-03-19T00:48:30 | 0 | {} | 11v5yte | false | null | t3_11v5yte | /r/LocalLLaMA/comments/11v5yte/alpaca_13b_loading_issue/ | false | false | default | 0 | null | ||
13B LLaMA Alpaca LoRAs Available on Hugging Face | 38 | null | /r/Oobabooga/comments/11v56na/13b_llama_alpaca_loras_available_on_hugging_face/ | friedrichvonschiller | self.Oobabooga | 1970-01-01T00:00:00 | 0 | {} | 11vbq6r | false | null | t3_11vbq6r | /r/LocalLLaMA/comments/11vbq6r/13b_llama_alpaca_loras_available_on_hugging_face/ | false | false | default | 38 | {'enabled': False, 'images': [{'id': '0-2J_a2zWnIF9ug1K-Lt1tLy77j9bLbRPA3xd7OBTTE', 'resolutions': [{'height': 67, 'url': 'https://external-preview.redd.it/0u-Lq63nhxIoV2dSqlsWsNb_nw7tIF94CWS3rQgD_HQ.png?width=108&crop=smart&auto=webp&v=enabled&s=b00a08ef32faa137d88698b870a4df625ffd9ed9', 'width': 108},... | |
Got the llama ccp ggml 4bit weights, can I get some guidance from here? | 0 | [removed] | null | https://www.reddit.com/r/LocalLLaMA/comments/11ves42/got_the_llama_ccp_ggml_4bit_weights_can_i_get/ | Virtamancer | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 11ves42 | true | null | t3_11ves42 | /r/LocalLLaMA/comments/11ves42/got_the_llama_ccp_ggml_4bit_weights_can_i_get/ | false | false | default | 0 | null |
My post got removed? | 1 | [removed] | null | [deleted] | 1970-01-01T00:00:00 | 0 | {} | 11vio91 | false | null | t3_11vio91 | /r/LocalLLaMA/comments/11vio91/my_post_got_removed/ | false | false | default | 1 | null | ||
Is there a difference between the model and the weights? | 1 | [removed] | null | [deleted] | 1970-01-01T00:00:00 | 0 | {} | 11vmhad | false | null | t3_11vmhad | /r/LocalLLaMA/comments/11vmhad/is_there_a_difference_between_the_model_and_the/ | false | false | default | 1 | null | ||
Stable Diffusion API now integrated in the web UI! Some interesting examples: | 30 | null | https://www.reddit.com/gallery/11w2mte | Civil_Collection7267 | reddit.com | 1970-01-01T00:00:00 | 0 | {} | 11w2mte | false | null | t3_11w2mte | /r/LocalLLaMA/comments/11w2mte/stable_diffusion_api_now_integrated_in_the_web_ui/ | false | false | 30 | null | ||
PyLLaMaCpp: A simple way to run llama.cpp + Python bindings | 1 | [removed] | null | https://www.reddit.com/r/LocalLLaMA/comments/11w8q8s/pyllamacpp_a_simple_way_to_run_llamacpp_python/ | a-user7 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 11w8q8s | false | null | t3_11w8q8s | /r/LocalLLaMA/comments/11w8q8s/pyllamacpp_a_simple_way_to_run_llamacpp_python/ | false | false | default | 1 | null |
I made a GUI app for installing and chatting with Alpaca.cpp | 1 | null | https://v.redd.it/y01r45h8hwoa1 | eliasvi0 | v.redd.it | 1970-01-01T00:00:00 | 0 | {} | 11wjmai | false | {'reddit_video': {'bitrate_kbps': 2400, 'dash_url': 'https://v.redd.it/y01r45h8hwoa1/DASHPlaylist.mpd?a=1683593732%2CNzEzM2Q4OGI5ZDFmZGFkYzE2ODBlYWQ0MTBiYzQ5NzUwNzA2N2MyNDNhMWJkZWYyYmRiOWI0MGU5MjQwNDhkOA%3D%3D&v=1&f=sd', 'duration': 35, 'fallback_url': 'https://v.redd.it/y01r45h8hwoa1/DASH_720.mp4?source=fallba... | t3_11wjmai | /r/LocalLLaMA/comments/11wjmai/i_made_a_gui_app_for_installing_and_chatting_with/ | false | false | default | 1 | null | |
Tom's Hardware wrote a guide to running LLaMa locally with benchmarks of GPUs | 34 | null | https://www.tomshardware.com/news/running-your-own-chatbot-on-a-single-gpu | Gudeldar | tomshardware.com | 1970-01-01T00:00:00 | 0 | {} | 11wndc9 | false | null | t3_11wndc9 | /r/LocalLLaMA/comments/11wndc9/toms_hardware_wrote_a_guide_to_running_llama/ | false | false | 34 | {'enabled': False, 'images': [{'id': 'a6SpC30_dSctu6VQfnjDBcCrNgCMwz3NRVeDQdtvu_g', 'resolutions': [{'height': 60, 'url': 'https://external-preview.redd.it/ioxRnQxeErZsnz0SYfFmK-zA9fldqOQMzttj_Wg9AqI.jpg?width=108&crop=smart&auto=webp&v=enabled&s=8728e900bd9295a11dbc65256c99714e1df65540', 'width': 108},... | ||
Increasing Max Token Length | 1 | [removed] | null | https://www.reddit.com/r/LocalLLaMA/comments/11wpv1l/increasing_max_token_length/ | Hands0L0 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 11wpv1l | false | null | t3_11wpv1l | /r/LocalLLaMA/comments/11wpv1l/increasing_max_token_length/ | false | false | default | 1 | null |
trying to do 4bit on windows 10, getting cuda mismatch error | 1 | [removed] | null | https://www.reddit.com/r/LocalLLaMA/comments/11wt73z/trying_to_do_4bit_on_windows_10_getting_cuda/ | SDGenius | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 11wt73z | false | null | t3_11wt73z | /r/LocalLLaMA/comments/11wt73z/trying_to_do_4bit_on_windows_10_getting_cuda/ | false | false | default | 1 | null |
I want to run Llama-7b-4bit in some type of Python environment so I can play around and learn with the code. I’m new to this specific field. How do I do this? | 0 | [removed] | null | [deleted] | 1970-01-01T00:00:00 | 0 | {} | 11wt9di | false | null | t3_11wt9di | /r/LocalLLaMA/comments/11wt9di/i_want_to_run_llama7b4bit_in_some_type_of_python/ | false | false | default | 0 | null | ||
Graphic text adventure game locally with llama and stable diffusion | 53 | null | vaidas-maciulis | i.redd.it | 1970-01-01T00:00:00 | 0 | {} | 11wwwjq | false | null | t3_11wwwjq | /r/LocalLLaMA/comments/11wwwjq/graphic_text_adventure_game_locally_with_llama/ | false | false | 53 | {'enabled': True, 'images': [{'id': 'UUEN2aBavhIV-ntfDXrI2CUIDgiKHscYjAF-1pXkZo4', 'resolutions': [{'height': 88, 'url': 'https://preview.redd.it/smgqu9rdryoa1.png?width=108&crop=smart&auto=webp&v=enabled&s=941f9b5e84c7e69f800808e73a75167e7b8ef130', 'width': 108}, {'height': 176, 'url': 'https://preview... | |||
Is it possible to integrate llama cpp with automated input and output? | 5 | A friend and I came up with the idea to combine LLaMA cpp and its chat feature with Vosk and Pythontts. But I have no clue how realistic this is with LLaMA's limited documentation at the time. Has anyone attempted anything similar yet? | null | https://www.reddit.com/r/LocalLLaMA/comments/11x12jz/is_it_possible_to_integrate_llama_cpp_with/ | falconnor4 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 11x12jz | false | null | t3_11x12jz | /r/LocalLLaMA/comments/11x12jz/is_it_possible_to_integrate_llama_cpp_with/ | false | false | self | 5 | null |
How long does it take to get access? | 4 | I submitted my request two weeks ago and still haven't heard back. Now there's stuff like Alpaca and other fine-tuning methods, I feel like I'm really missing out. I literally check my email almost religiously to check for emails from Meta. I'm almost certain I used a .edu email address.
Also, can I run llama on an M1... | null | https://www.reddit.com/r/LocalLLaMA/comments/11x4v3c/how_long_does_it_take_to_get_access/ | Unusual_Guidance2095 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 11x4v3c | false | null | t3_11x4v3c | /r/LocalLLaMA/comments/11x4v3c/how_long_does_it_take_to_get_access/ | false | false | self | 4 | null |
Can someone post the hashes of the original straight-from-meta files? | 1 | [removed] | null | https://www.reddit.com/r/LocalLLaMA/comments/11x7ntu/can_someone_post_the_hashes_of_the_original/ | Virtamancer | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 11x7ntu | false | null | t3_11x7ntu | /r/LocalLLaMA/comments/11x7ntu/can_someone_post_the_hashes_of_the_original/ | false | false | default | 1 | null |
Are there publicly available datasets other than Alpaca that we can use to fine-tune LLaMA? | 15 | It seems that everyone is training LLaMA with the Stanford Alpaca dataset, but it is unclear to me if this is the optimal choice (has anyone done a comparison?). Also people have already discovered many problems in the dataset itself, which further adds to my doubt here.
Forgive my ignorance in this area, are there an... | null | https://www.reddit.com/r/LocalLLaMA/comments/11x9hzs/are_there_publicly_available_datasets_other_than/ | _ouromoros | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 11x9hzs | false | null | t3_11x9hzs | /r/LocalLLaMA/comments/11x9hzs/are_there_publicly_available_datasets_other_than/ | false | false | self | 15 | null |
How to do Llama 30B 4bit finetuning? | 14 | So far it looks like the only finetuning is using 8bit following the Alpaca Lora.
Do we expect 4bit finetuning to come out, or not at all? Is it just a matter of someone converting the 8bit fine tuning, or it's a lot more complicated than that?
And does it require additional VRAM to run the finetuning? I have a 3090 ... | null | https://www.reddit.com/r/LocalLLaMA/comments/11xbu7d/how_to_do_llama_30b_4bit_finetuning/ | Pan000 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 11xbu7d | false | null | t3_11xbu7d | /r/LocalLLaMA/comments/11xbu7d/how_to_do_llama_30b_4bit_finetuning/ | false | false | self | 14 | null |
Is this good idea to buy more rtx 3090? | 12 | Hi, I love the idea of open source. Currently I got 2x rtx 3090 and I amble to run int4 65B llama model. I am thinking about buying two more rtx 3090 when I am see how fast community is making progress. Is this good idea? Please help me with the decision. It is not about money, but still I cannot afford a100 80GB for t... | null | https://www.reddit.com/r/LocalLLaMA/comments/11xfhq4/is_this_good_idea_to_buy_more_rtx_3090/ | polawiaczperel | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 11xfhq4 | false | null | t3_11xfhq4 | /r/LocalLLaMA/comments/11xfhq4/is_this_good_idea_to_buy_more_rtx_3090/ | false | false | self | 12 | null |
ATI GPU? | 3 | [deleted] | null | [deleted] | 1970-01-01T00:00:00 | 0 | {} | 11xiwes | false | null | t3_11xiwes | /r/LocalLLaMA/comments/11xiwes/ati_gpu/ | false | false | default | 3 | null | ||
What's the current "Best" LLaMA LoRA? or moreover what would be a good benchmark to test these against. (HF links incl in post) | 35 | So far I've found:
https://huggingface.co/serpdotai/
https://huggingface.co/baseten/
https://huggingface.co/chavinlo/
https://huggingface.co/Draff/
https://huggingface.co/samwit/
(please add more in the comments if you know of more)
-----------------------... | null | https://www.reddit.com/r/LocalLLaMA/comments/11xkuj5/whats_the_current_best_llama_lora_or_moreover/ | blueSGL | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 11xkuj5 | false | null | t3_11xkuj5 | /r/LocalLLaMA/comments/11xkuj5/whats_the_current_best_llama_lora_or_moreover/ | false | false | self | 35 | {'enabled': False, 'images': [{'id': 'a1ck-pg6Ht_BnI_Pw1ltcU-mDjXQXbTjWVVfSwpGQMo', 'resolutions': [{'height': 58, 'url': 'https://external-preview.redd.it/9eD-UeMHFkYFBBCsePYEzO9zhQRd7t22KnpQBgBG0mk.jpg?width=108&crop=smart&auto=webp&v=enabled&s=c5b3e826e50f12d0b8524cbfc7f340a9636f9c85', 'width': 108},... |
Can I fine-tune llama 7b alpaca or gpt neo x 125m or any other models on my GTX 1650 super 4gb VRAM and 8gb of ram (I'm new to this) | 2 | null | https://www.reddit.com/r/LocalLLaMA/comments/11y0kqz/can_i_finetune_llama_7b_alpaca_or_gpt_neo_x_125m/ | Puzzleheaded_Acadia1 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 11y0kqz | true | null | t3_11y0kqz | /r/LocalLLaMA/comments/11y0kqz/can_i_finetune_llama_7b_alpaca_or_gpt_neo_x_125m/ | false | false | default | 2 | null | |
PyLLaMACpp: A simple way to run llama.cpp + Python bindings | 1 | null | https://github.com/abdeladim-s/pyllamacpp | a-user7 | github.com | 1970-01-01T00:00:00 | 0 | {} | 11y3ont | false | null | t3_11y3ont | /r/LocalLLaMA/comments/11y3ont/pyllamacpp_a_simple_way_to_run_llamacpp_python/ | false | false | default | 1 | null | |
r/LocalLLaMA Subreddit Statistics | 1 | [removed] | null | [deleted] | 1970-01-01T00:00:00 | 0 | {} | 11ydfi4 | false | null | t3_11ydfi4 | /r/LocalLLaMA/comments/11ydfi4/rlocalllama_subreddit_statistics/ | false | false | default | 1 | null | ||
llama.cpp vs alpaca.cpp: same model different results | 17 | I was performing some reasoning test to see how Alpaca is performing and found that with the same model and same sampling parameters they behave quite differently.
I'm quite new to LLM so I'm studying the subject making trials, so forgive me if it's a trivial question.
>sampling parameters: temp = 0.200000, top\_... | null | https://www.reddit.com/r/LocalLLaMA/comments/11yhxjm/llamacpp_vs_alpacacpp_same_model_different_results/ | fakezeta | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 11yhxjm | false | null | t3_11yhxjm | /r/LocalLLaMA/comments/11yhxjm/llamacpp_vs_alpacacpp_same_model_different_results/ | false | false | self | 17 | null |
Build llama.cpp on Jetson Nano 2GB | 22 | #((Assuming the baby new install of Ubuntu on the Jetson Nano))
#(MAKE SURE IT IS JETPACK 4.6.1!)
#Update your stuff.
sudo apt update && sudo apt upgrade
sudo apt install python3-pip python-pip
sudo reboot
#Install Aarch64 Conda
cd ~
wget https://github.com/conda-f... | null | https://www.reddit.com/r/LocalLLaMA/comments/11yi0bl/build_llamacpp_on_jetson_nano_2gb/ | SlavaSobov | self.LocalLLaMA | 2023-04-05T14:07:27 | 0 | {} | 11yi0bl | false | null | t3_11yi0bl | /r/LocalLLaMA/comments/11yi0bl/build_llamacpp_on_jetson_nano_2gb/ | false | false | self | 22 | {'enabled': False, 'images': [{'id': '9JOfN81286Rl3B2ZMQ_BimKP82h5bGxPMzqWlT8aQ-A', 'resolutions': [{'height': 58, 'url': 'https://external-preview.redd.it/4uAgoQe0xy9sjqRkIt4fsdu5pg1VvlCgIXxyIuUro4M.jpg?width=108&crop=smart&auto=webp&v=enabled&s=b827d071aee5e763f6988ac05b3fb6a013476585', 'width': 108},... |
Trying to get continuous conversations (conversation memory?) working in alpaca.cpp on Mac M2 | 7 | [removed] | null | https://www.reddit.com/r/LocalLLaMA/comments/11yycky/trying_to_get_continuous_conversations/ | spanielrassler | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 11yycky | false | null | t3_11yycky | /r/LocalLLaMA/comments/11yycky/trying_to_get_continuous_conversations/ | false | false | default | 7 | null |
using oobabooga webui with 7B LLama on GPU, some characters are amazing some are useless | 7 | [removed] | null | https://www.reddit.com/r/LocalLLaMA/comments/11yz2dm/using_oobabooga_webui_with_7b_llama_on_gpu_some/ | megadonkeyx | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 11yz2dm | false | null | t3_11yz2dm | /r/LocalLLaMA/comments/11yz2dm/using_oobabooga_webui_with_7b_llama_on_gpu_some/ | false | false | default | 7 | null |
Your `--load-in-8bit` error may be due to non-supported GPU. Want to fix it? | 2 | [removed] | null | https://www.reddit.com/r/LocalLLaMA/comments/11yzosa/your_loadin8bit_error_may_be_due_to_nonsupported/ | monkmartinez | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 11yzosa | false | null | t3_11yzosa | /r/LocalLLaMA/comments/11yzosa/your_loadin8bit_error_may_be_due_to_nonsupported/ | false | false | default | 2 | null |
Why is 30B not available even though it says it’s there? | 1 | [removed] | null | [deleted] | 1970-01-01T00:00:00 | 0 | {} | 11z2251 | false | null | t3_11z2251 | /r/LocalLLaMA/comments/11z2251/why_is_30b_not_available_even_though_it_says_its/ | false | false | default | 1 | null | ||
Cuda Frustration | 1 | [removed] | null | https://www.reddit.com/r/LocalLLaMA/comments/11z5g9x/cuda_frustration/ | RobXSIQ | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 11z5g9x | false | null | t3_11z5g9x | /r/LocalLLaMA/comments/11z5g9x/cuda_frustration/ | false | false | default | 1 | null |
Got problems with bitsandbytes? This may be a fix... | 11 | Some users of the bitsandbytes - 8 bit optimizer - by Tim Dettmers have reported issues when using the tool with older GPUs, such as Maxwell or Pascal. I beleive they don't even know its an issue. These GPUs do not support the required instructions for the tool to run properly, resulting in errors or crashes.
A simple... | null | https://www.reddit.com/r/LocalLLaMA/comments/11z8vzy/got_problems_with_bitsandbytes_this_may_be_a_fix/ | monkmartinez | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 11z8vzy | false | null | t3_11z8vzy | /r/LocalLLaMA/comments/11z8vzy/got_problems_with_bitsandbytes_this_may_be_a_fix/ | false | false | self | 11 | {'enabled': False, 'images': [{'id': '4sHFecMk7qkFB_6Ku5iVFW6NZloZb3t2BcdZyo7uPq8', 'resolutions': [{'height': 54, 'url': 'https://external-preview.redd.it/M68VwFVx1qWSq7_Qyur9ktwhPJYCIpy1GTdza68IwGo.jpg?width=108&crop=smart&auto=webp&v=enabled&s=ab93d070168ca8e91ed9c9d49abcfd6212a8ba9d', 'width': 108},... |
Cformers "Transformers with a C-backend for lightning-fast CPU inference". | 1 | [deleted] | null | [deleted] | 1970-01-01T00:00:00 | 0 | {} | 11zass0 | false | null | t3_11zass0 | /r/LocalLLaMA/comments/11zass0/cformers_transformers_with_a_cbackend_for/ | false | false | default | 1 | null | ||
Cformers 🚀 - "Transformers with a C-backend for lightning-fast CPU inference". | Nolano | 15 | [removed] | null | https://www.reddit.com/r/LocalLLaMA/comments/11zax10/cformers_transformers_with_a_cbackend_for/ | AcanthocephalaOk1441 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 11zax10 | true | null | t3_11zax10 | /r/LocalLLaMA/comments/11zax10/cformers_transformers_with_a_cbackend_for/ | false | false | default | 15 | null |
Trying Alpaca.cpp and it's definitely fun. | 4 | null | lebanine | i.redd.it | 1970-01-01T00:00:00 | 0 | {} | 11zayxp | false | null | t3_11zayxp | /r/LocalLLaMA/comments/11zayxp/trying_alpacacpp_and_its_definitely_fun/ | false | false | default | 4 | null | ||
LLaMA Optimized for AMD GPUs | 14 | null | https://github.com/nod-ai/SHARK/blob/f898a1d33220256af913a12001b8fe8169a1aa9d/shark/examples/shark_inference/llama/README.md | friedrichvonschiller | github.com | 1970-01-01T00:00:00 | 0 | {} | 11zcqj2 | false | null | t3_11zcqj2 | /r/LocalLLaMA/comments/11zcqj2/llama_optimized_for_amd_gpus/ | false | false | 14 | {'enabled': False, 'images': [{'id': 'FFwNBRn9ldrmA40DDb4GIlyeUDwXrClUXGJlqRDTUds', 'resolutions': [{'height': 54, 'url': 'https://external-preview.redd.it/aQgET6wgU-aASr6J-uKgFyHP6G_btqsOXu_AjbHRjRo.jpg?width=108&crop=smart&auto=webp&v=enabled&s=28fed118930bc918840a14685ab352739edf4876', 'width': 108},... | ||
Introducing llamacpp-for-kobold, run llama.cpp locally with a fancy web UI, persistent stories, editing tools, save formats, memory, world info, author's note, characters, scenarios and more with minimal setup | 62 | You may have heard of llama.cpp, a lightweight and fast solution to running 4bit quantized llama models locally.
You may also have heard of KoboldAI (and KoboldAI Lite), full featured text writing clients for autoregressive LLMs.
# Enter [llamacpp-for-kobold](https://github.com/LostRuins/llamacpp-for-kobold)
This is... | null | https://www.reddit.com/r/LocalLLaMA/comments/11zdi6m/introducing_llamacppforkobold_run_llamacpp/ | HadesThrowaway | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 11zdi6m | false | null | t3_11zdi6m | /r/LocalLLaMA/comments/11zdi6m/introducing_llamacppforkobold_run_llamacpp/ | false | false | self | 62 | {'enabled': False, 'images': [{'id': 'iNOIL8xRSb88VpeaAwmnE5QXAeHIan30y-YJTKZwMwo', 'resolutions': [{'height': 54, 'url': 'https://external-preview.redd.it/2wPy4oeQjeW4ZurWd732KqxrZ5UOlfdsnRvKylcsyMY.jpg?width=108&crop=smart&auto=webp&v=enabled&s=bf723f5b97039400195f7592a5a0765f380f9939', 'width': 108},... |
r/LocalLLaMA Subreddit Statistics | 1 | null | https://subredditstatistics.com/r/LocalLLaMA | neefs | subredditstatistics.com | 1970-01-01T00:00:00 | 0 | {} | 11zhxif | false | null | t3_11zhxif | /r/LocalLLaMA/comments/11zhxif/rlocalllama_subreddit_statistics/ | false | false | default | 1 | null | |
Alpaca-LoRA: Low-Rank LLaMA Instruct-Tuning | 1 | [deleted] | null | [deleted] | 1970-01-01T00:00:00 | 0 | {} | 11znjyq | false | null | t3_11znjyq | /r/LocalLLaMA/comments/11znjyq/alpacalora_lowrank_llama_instructtuning/ | false | false | default | 1 | null | ||
use in regular python scripts? | 12 | Got the llama-13b-hf to work on local RTX 4090 using the webui. This guide and oobabooga is awesome.
I know these are early days but is there a guide or pointers on how to access these models directly using **regular python scripts**? I have some large file text analysis I want to do with it. Done chatting with it, i... | null | https://www.reddit.com/r/LocalLLaMA/comments/11zz7oa/use_in_regular_python_scripts/ | gransee | self.LocalLLaMA | 2023-03-23T23:17:36 | 0 | {} | 11zz7oa | false | null | t3_11zz7oa | /r/LocalLLaMA/comments/11zz7oa/use_in_regular_python_scripts/ | false | false | self | 12 | null |
Running alpaca on my beater | 1 | [removed] | null | https://www.reddit.com/r/LocalLLaMA/comments/11zzlpz/running_alpaca_on_my_beater/ | rwaterbender | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 11zzlpz | false | null | t3_11zzlpz | /r/LocalLLaMA/comments/11zzlpz/running_alpaca_on_my_beater/ | false | false | default | 1 | null |
New Torrent for Alpaca's 30B 4-bit weights (18.9 GB) | 5 | [removed] | null | https://www.reddit.com/r/LocalLLaMA/comments/1200mle/new_torrent_for_alpacas_30b_4bit_weights_189_gb/ | msgs | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 1200mle | true | null | t3_1200mle | /r/LocalLLaMA/comments/1200mle/new_torrent_for_alpacas_30b_4bit_weights_189_gb/ | false | false | default | 5 | null |
Better QPTQ-quantized LLaMa soon? Paper authors reach out to improve quantization code | 39 | null | https://github.com/qwopqwop200/GPTQ-for-LLaMa/issues/75 | Blacky372 | github.com | 1970-01-01T00:00:00 | 0 | {} | 12047hn | false | null | t3_12047hn | /r/LocalLLaMA/comments/12047hn/better_qptqquantized_llama_soon_paper_authors/ | false | false | 39 | {'enabled': False, 'images': [{'id': 'ft2PxN-_mUCPpCBPSPikSpTPj2DyPdvcv27qziT6pHU', 'resolutions': [{'height': 54, 'url': 'https://external-preview.redd.it/c8Q-YSCdhku3VMRsL7yjpCtFKU4aWYqn_OtsNaMT6Ck.jpg?width=108&crop=smart&auto=webp&v=enabled&s=02884e129f373b1430651115330a52690768a53e', 'width': 108},... | ||
If you STILL have not been able to get oobabooga to run in Windows, my native installation bandaid seems to be working for people. Maybe it will work for you too. | 1 | null | https://github.com/ClayShoaf/oobabooga-one-click-bandaid | clayshoaf | github.com | 1970-01-01T00:00:00 | 0 | {} | 1206gwp | false | null | t3_1206gwp | /r/LocalLLaMA/comments/1206gwp/if_you_still_have_not_been_able_to_get_oobabooga/ | false | false | default | 1 | null | |
r/LocalLLaMA Subreddit Statistics | 1 | null | https://subredditstatistics.com/r/LocalLLaMA | rx01 | subredditstatistics.com | 1970-01-01T00:00:00 | 0 | {} | 1209ndu | false | null | t3_1209ndu | /r/LocalLLaMA/comments/1209ndu/rlocalllama_subreddit_statistics/ | false | false | default | 1 | null | |
Finetuning to beat ChatGPT: It's all about communication & management, these are already solved problems | 32 | When I first got the researcher access to GPT3, before it was famous, it would only continue the prompt. It only took a moment, but it was a perspective shift to understand that if you write *"What's the capital of France?"* that the most obvious continuation is not the answer, but another question about geography. It'... | null | https://www.reddit.com/r/LocalLLaMA/comments/120e7m7/finetuning_to_beat_chatgpt_its_all_about/ | Pan000 | self.LocalLLaMA | 2023-03-24T12:38:57 | 0 | {} | 120e7m7 | false | null | t3_120e7m7 | /r/LocalLLaMA/comments/120e7m7/finetuning_to_beat_chatgpt_its_all_about/ | false | false | self | 32 | null |
Whats the fastest implementation for a 24Gb GPU with a 16-core CPU? | 3 | I have been testing various implementation of Llama, like llama.cpp, Torch versions with and without Int8 quantization etc, but nothing seems particularly fast (> 8 seconds, even on 7B on GPU for 256 token generations).
Are there really fast implementations out yet? maybe ONNX compilations or something to speed up ... | null | https://www.reddit.com/r/LocalLLaMA/comments/120etwq/whats_the_fastest_implementation_for_a_24gb_gpu/ | Reddactor | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 120etwq | false | null | t3_120etwq | /r/LocalLLaMA/comments/120etwq/whats_the_fastest_implementation_for_a_24gb_gpu/ | false | false | self | 3 | null |
Would it be better for me to run it on gpu or cpu | 3 | I understood that there was two ways of running it, normally and on cpu with llama.cpp
I’ve a 2080 ti and a ryzen 5 2600 what do you think ?
Generally what are the advantages to run it on cpu ? | null | https://www.reddit.com/r/LocalLLaMA/comments/120eu0u/would_it_be_better_for_me_to_run_it_on_gpu_or_cpu/ | lord_baba | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 120eu0u | false | null | t3_120eu0u | /r/LocalLLaMA/comments/120eu0u/would_it_be_better_for_me_to_run_it_on_gpu_or_cpu/ | false | false | self | 3 | null |
Training Llama for tool-use via a manager/logistical model | 5 | My [earlier post](https://www.reddit.com/r/LocalLLaMA/comments/120e7m7/finetuning_to_beat_chatgpt_its_all_about/) was about training Llama to understand human-language context and expectations for how it should react to user input.
The next obvious stage is tool use, which is the use of calculator, Internet browsing, ... | null | https://www.reddit.com/r/LocalLLaMA/comments/120fw2u/training_llama_for_tooluse_via_a/ | Pan000 | self.LocalLLaMA | 2023-03-24T10:25:45 | 0 | {} | 120fw2u | false | null | t3_120fw2u | /r/LocalLLaMA/comments/120fw2u/training_llama_for_tooluse_via_a/ | false | false | self | 5 | null |
How do I fine tune 4 bit or 8 bit models? | 0 | [removed] | null | [deleted] | 1970-01-01T00:00:00 | 0 | {} | 120kojq | false | null | t3_120kojq | /r/LocalLLaMA/comments/120kojq/how_do_i_fine_tune_4_bit_or_8_bit_models/ | false | false | default | 0 | null | ||
Using LLaMA in interactive mode and reverse prompts? | 1 | [removed] | null | https://www.reddit.com/r/LocalLLaMA/comments/120lp6t/using_llama_in_interactive_mode_and_reverse/ | amiatt | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 120lp6t | false | null | t3_120lp6t | /r/LocalLLaMA/comments/120lp6t/using_llama_in_interactive_mode_and_reverse/ | false | false | default | 1 | null |
Change Dalai model folder? | 1 | [removed] | null | [deleted] | 1970-01-01T00:00:00 | 0 | {} | 120s66r | false | null | t3_120s66r | /r/LocalLLaMA/comments/120s66r/change_dalai_model_folder/ | false | false | default | 1 | null | ||
Keep your GPUs cool | 9 | May not apply to you people running gaming hardware, but for those of us running tesla's maybe without proper cooling, keep your GPUs cool.
I've been playing around with llama 30b 4bit on my m40. After loading the model for the first few prompts I'm generating about 8 tokens/second, a few prompts in my temps are up ... | null | https://www.reddit.com/r/LocalLLaMA/comments/120spmv/keep_your_gpus_cool/ | wind_dude | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 120spmv | false | null | t3_120spmv | /r/LocalLLaMA/comments/120spmv/keep_your_gpus_cool/ | false | false | self | 9 | null |
Which LLaMA model is best for my set up? | 1 | [removed] | null | https://www.reddit.com/r/LocalLLaMA/comments/120x6eh/which_llama_model_is_best_for_my_set_up/ | EnvironmentalAd3385 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 120x6eh | false | null | t3_120x6eh | /r/LocalLLaMA/comments/120x6eh/which_llama_model_is_best_for_my_set_up/ | false | false | default | 1 | null |
Testing out image recognition input techniques and outputs by modifying the sd_api_picture extension, using Oobabooga and LLaMA 13B in 4-bit mode | 20 | Just thought to share some various ways to use/change the existing image recognition and image generating extensions.
[https://imgur.com/a/KEuaywA](https://imgur.com/a/KEuaywA)
I was able to get the AI to identify the number and type of objects in an image, by means of telling the AI in advance and it waiting for me ... | null | https://www.reddit.com/r/LocalLLaMA/comments/1211u41/testing_out_image_recognition_input_techniques/ | Inevitable-Start-653 | self.LocalLLaMA | 2023-03-25T15:32:30 | 0 | {} | 1211u41 | false | null | t3_1211u41 | /r/LocalLLaMA/comments/1211u41/testing_out_image_recognition_input_techniques/ | false | false | self | 20 | {'enabled': False, 'images': [{'id': 'dS3rdb6qhR5L7kujCCTYZo67gjIK9OkqcxuDOenNd1I', 'resolutions': [{'height': 216, 'url': 'https://external-preview.redd.it/_DwFztnI2zXkr1SeelHmcKXZGtyX2nI6JXaZTxDsofE.jpg?width=108&crop=smart&auto=webp&v=enabled&s=f617f3c272c6b83ae4d52d9c5b67f69c10eda429', 'width': 108}... |
Run llama.cpp with tea – without the installation pain! | 1 | [removed] | null | https://www.reddit.com/r/LocalLLaMA/comments/1216du7/run_llamacpp_with_tea_without_the_installation/ | mfts0 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 1216du7 | false | null | t3_1216du7 | /r/LocalLLaMA/comments/1216du7/run_llamacpp_with_tea_without_the_installation/ | false | false | default | 1 | null |
Managed to get 4-bit Llama 7b running but it's generating random text. | 1 | [removed] | null | https://www.reddit.com/r/LocalLLaMA/comments/1219iq2/managed_to_get_4bit_llama_7b_running_but_its/ | MimeMagic | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 1219iq2 | false | null | t3_1219iq2 | /r/LocalLLaMA/comments/1219iq2/managed_to_get_4bit_llama_7b_running_but_its/ | false | false | default | 1 | null |
Can't tell if the AI is repeating itself or actually being stubborn HAL? | 6 | null | Inevitable-Start-653 | i.redd.it | 1970-01-01T00:00:00 | 0 | {} | 121ad9h | false | null | t3_121ad9h | /r/LocalLLaMA/comments/121ad9h/cant_tell_if_the_ai_is_repeating_itself_or/ | false | false | 6 | {'enabled': True, 'images': [{'id': 'e7N4xnKzBmpMEWucb_7lM4bqYKvzkc5v61sBChQW1fc', 'resolutions': [{'height': 216, 'url': 'https://preview.redd.it/vmqsvwkiatpa1.png?width=108&crop=smart&auto=webp&v=enabled&s=28f2c84584097d2ff7cf860db3e38a62a18ff1bb', 'width': 108}, {'height': 432, 'url': 'https://previe... | |||
Implementing Reflexion into LLaMA/Alpaca would be an really interesting project | 15 | null | https://www.reddit.com/r/MachineLearning/comments/1215dbl/r_reflexion_an_autonomous_agent_with_dynamic/ | jd_3d | reddit.com | 1970-01-01T00:00:00 | 0 | {} | 121b1l5 | false | null | t3_121b1l5 | /r/LocalLLaMA/comments/121b1l5/implementing_reflexion_into_llamaalpaca_would_be/ | false | false | 15 | {'enabled': False, 'images': [{'id': 'q3evP6JeDpAC2MdSQHWYxnCYTqbJkElIQsLFqVSdkss', 'resolutions': [{'height': 63, 'url': 'https://external-preview.redd.it/0HhwdU6MKIAKjL9Y8-B_iH374a3NiPTy0ib8lmloRzA.jpg?width=108&crop=smart&auto=webp&v=enabled&s=586089b93aa59ebd86bb3b273ad1fb0c73e45ab7', 'width': 108},... | ||
How to use LoRA (need instructions) | 3 | [removed] | null | https://www.reddit.com/r/LocalLLaMA/comments/121ehwj/how_to_use_lora_need_instructions/ | Famberlight | self.LocalLLaMA | 2023-03-25T08:30:11 | 0 | {} | 121ehwj | false | null | t3_121ehwj | /r/LocalLLaMA/comments/121ehwj/how_to_use_lora_need_instructions/ | false | false | default | 3 | null |
Need help installing alpaca on Android | 0 | [removed] | null | https://www.reddit.com/r/LocalLLaMA/comments/121g7yn/need_help_installing_alpaca_on_android/ | -2b2t- | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 121g7yn | false | null | t3_121g7yn | /r/LocalLLaMA/comments/121g7yn/need_help_installing_alpaca_on_android/ | false | false | default | 0 | null |
Has anyone tried Dolly AI? | 0 | [deleted] | null | [deleted] | 2023-03-25T12:26:22 | 0 | {} | 121imtt | false | null | t3_121imtt | /r/LocalLLaMA/comments/121imtt/has_anyone_tried_dolly_ai/ | false | false | default | 0 | null | ||
Help installing LLaMA on ubuntu with Tesla M40 24GB | 1 | [removed] | null | https://www.reddit.com/r/LocalLLaMA/comments/121kdnc/help_installing_llama_on_ubuntu_with_tesla_m40/ | MageLD | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 121kdnc | false | null | t3_121kdnc | /r/LocalLLaMA/comments/121kdnc/help_installing_llama_on_ubuntu_with_tesla_m40/ | false | false | default | 1 | null |
Simulating Aristotle in Alpaca 7B, I used gpt4 to build the character profile, I've been surprised and just wanted to share. I have some more like this that I can share if you like it :D | 35 | null | psycholustmord | i.redd.it | 1970-01-01T00:00:00 | 0 | {} | 121nytl | false | null | t3_121nytl | /r/LocalLLaMA/comments/121nytl/simulating_aristotle_in_alpaca_7b_i_used_gpt4_to/ | false | false | 35 | {'enabled': True, 'images': [{'id': '8MdAsu39-EmfKrxvC9bjfAcatC8OSj-_OLidKAh7w6M', 'resolutions': [{'height': 84, 'url': 'https://preview.redd.it/a2wx8exgdwpa1.png?width=108&crop=smart&auto=webp&v=enabled&s=3bcecb428949ca686c3378dcbcb1e1c32afc8862', 'width': 108}, {'height': 168, 'url': 'https://preview... | |||
fastLLaMa, A python wrapper to run llama.cpp | 16 | [removed] | null | https://www.reddit.com/r/LocalLLaMA/comments/121pk4y/fastllama_a_python_wrapper_to_run_llamacpp/ | BriefCardiologist656 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 121pk4y | false | null | t3_121pk4y | /r/LocalLLaMA/comments/121pk4y/fastllama_a_python_wrapper_to_run_llamacpp/ | false | false | default | 16 | null |
Question on llama.cpp and webui (ram usage) | 2 | [removed] | null | https://www.reddit.com/r/LocalLLaMA/comments/121redn/question_on_llamacpp_and_webui_ram_usage/ | kozer1986 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 121redn | false | null | t3_121redn | /r/LocalLLaMA/comments/121redn/question_on_llamacpp_and_webui_ram_usage/ | false | false | default | 2 | null |
Out of memory with 13B on an RTX 3060? | 3 | I've been messing around with 13B on my CPU with some nice but very slow results.
I just upgraded my GPU to an RTX 3060 with 12GB thinking it would be enough to run this model (I recall having heard someone mention using a similar GPU for 30B), but now that I tried, I got an out of cuda memory error.
What could be th... | null | https://www.reddit.com/r/LocalLLaMA/comments/121xqmv/out_of_memory_with_13b_on_an_rtx_3060/ | amiatt | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 121xqmv | false | null | t3_121xqmv | /r/LocalLLaMA/comments/121xqmv/out_of_memory_with_13b_on_an_rtx_3060/ | false | false | self | 3 | null |
Starting model? | 5 | Apologies for the basic questions but...
What is the Best model to start with?Llama or Alpaca? Is it best to start with 7B or if your system can handle it just start at the highest parameter you can run?
I have not really seen many head to head comparisons or where it is best to start out.
I have access to a AMD ... | null | https://www.reddit.com/r/LocalLLaMA/comments/121y16f/starting_model/ | dave9199 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 121y16f | false | null | t3_121y16f | /r/LocalLLaMA/comments/121y16f/starting_model/ | false | false | self | 5 | null |
Can we create a megathread for cataloging all the projects and installation guides of Llama? | 37 | ***Disclaimer - The Title and Text of this post is created with the help of ChatGPT***
Hey everyone,
As Llama continues to grow and more projects and installation guides become available, it can be challenging to keep track of all of them. I'm sure many of you have seen multiple posts related to Llama, and it can be ... | null | https://www.reddit.com/r/LocalLLaMA/comments/121yfxl/can_we_create_a_megathread_for_cataloging_all_the/ | utkvishwas | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 121yfxl | false | null | t3_121yfxl | /r/LocalLLaMA/comments/121yfxl/can_we_create_a_megathread_for_cataloging_all_the/ | false | false | self | 37 | null |
Guide to the different parameters and models in web UI? | 1 | [removed] | null | https://www.reddit.com/r/LocalLLaMA/comments/1221xih/guide_to_the_different_parameters_and_models_in/ | Nomski88 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 1221xih | false | null | t3_1221xih | /r/LocalLLaMA/comments/1221xih/guide_to_the_different_parameters_and_models_in/ | false | false | default | 1 | null |
Speed difference between 8bit and 4bit | 5 | Is 4bit supposed to run 5 times faster than 8bit? I'm getting 20 tokens/s on 4bit, but only 4 tokens/s on 8bit. Using a 3060 12gb, on WSL.
I just installed webui on WSL with a lot of trouble, and I want to make sure it's installed correctly.
I had 4bit work right away when following the pinned guide on this subreddit... | null | https://www.reddit.com/r/LocalLLaMA/comments/122218d/speed_difference_between_8bit_and_4bit/ | wewyman | self.LocalLLaMA | 2023-03-25T23:57:32 | 0 | {} | 122218d | false | null | t3_122218d | /r/LocalLLaMA/comments/122218d/speed_difference_between_8bit_and_4bit/ | false | false | self | 5 | null |
video tutorial for AMD GPU to run LLaMA and LoRA on Ubuntu | 2 | [removed] | null | https://www.reddit.com/r/LocalLLaMA/comments/1224fh0/video_tutorial_for_amd_gpu_to_run_llama_and_lora/ | chain-77 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 1224fh0 | false | null | t3_1224fh0 | /r/LocalLLaMA/comments/1224fh0/video_tutorial_for_amd_gpu_to_run_llama_and_lora/ | false | false | default | 2 | null |
My experience with Alpaca.cpp | 52 | Ever since ChatGPT launched, I've been very fascinated by it and have sought a local alternative that can run fairly well on decent consumer hardware and that "anyone" can use if their hardware allows. Naturally, I was excited when I saw [this post](https://www.reddit.com/r/StableDiffusion/comments/11y6qs7/free_opensou... | null | https://www.reddit.com/r/LocalLLaMA/comments/1227uj5/my_experience_with_alpacacpp/ | AI-Pon3 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 1227uj5 | false | null | t3_1227uj5 | /r/LocalLLaMA/comments/1227uj5/my_experience_with_alpacacpp/ | false | false | self | 52 | {'enabled': False, 'images': [{'id': 'OqNBDrwG79LuAr5fnfIKbOQUisQvHxpNQUeM-WZhodQ', 'resolutions': [{'height': 54, 'url': 'https://external-preview.redd.it/82qVi0yi-kfcWnPBWkpv6Bh52sg4rmoXW_DTRt2YQOQ.jpg?width=108&crop=smart&auto=webp&v=enabled&s=6c0ca59aa7fd79b2d1567fac2772bf23bfee3828', 'width': 108},... |
With the latest web UI update, old 4-bit weights will no longer work. You will need the new weights. | 19 | **New weights** (torrent file/magnet link)
Converted without group-size (better for the 7B model): [https://github.com/oobabooga/text-generation-webui/files/11069779/LLaMA-HF-4bit.zip](https://github.com/oobabooga/text-generation-webui/files/11069779/LLaMA-HF-4bit.zip) or
magnet:?xt=urn:btih:e88abf1b84290b162f00d... | null | https://www.reddit.com/r/LocalLLaMA/comments/122c2sv/with_the_latest_web_ui_update_old_4bit_weights/ | Technical_Leather949 | self.LocalLLaMA | 2023-03-26T07:59:47 | 0 | {} | 122c2sv | false | null | t3_122c2sv | /r/LocalLLaMA/comments/122c2sv/with_the_latest_web_ui_update_old_4bit_weights/ | false | false | self | 19 | null |
How to implement gpu/cpu offloading for text-generation-webui? [custom device_map] | 3 |
Hello, I am trying to set up a custom device\_map via hugging face's instructions
[https://huggingface.co/docs/transformers/main/en/main\_classes/quantization#offload-between-cpu-and-gpu](https://huggingface.co/docs/transformers/main/en/main_classes/quantization#offload-between-cpu-and-gpu)
I have this code insert... | null | https://www.reddit.com/r/LocalLLaMA/comments/122er6u/how_to_implement_gpucpu_offloading_for/ | SomeGuyInDeutschland | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 122er6u | false | null | t3_122er6u | /r/LocalLLaMA/comments/122er6u/how_to_implement_gpucpu_offloading_for/ | false | false | self | 3 | {'enabled': False, 'images': [{'id': 'jfeVG47nZdEkz9kXfW1CcS-Sy8l4DXGb9JErx6bLKfU', 'resolutions': [{'height': 58, 'url': 'https://external-preview.redd.it/Bixm6H31yqw0RCcD8LB0e8eIdtJeMUaF4N5ZipM_BQY.jpg?width=108&crop=smart&auto=webp&v=enabled&s=d98fc28f03459191933e04a79947277468884240', 'width': 108},... |
r/LocalLLaMA Subreddit Statistics | 1 | null | https://subredditstatistics.com/r/LocalLLaMA | rx01 | subredditstatistics.com | 1970-01-01T00:00:00 | 0 | {} | 122i14g | false | null | t3_122i14g | /r/LocalLLaMA/comments/122i14g/rlocalllama_subreddit_statistics/ | false | false | default | 1 | null | |
Hi, can someone please tell me some resources how to learn to fine-tune an LLM or llama and learn the keyword like "F16" some YouTube channels or discord communitys or even websites and thanks | 1 | null | https://www.reddit.com/r/LocalLLaMA/comments/122jsdm/hi_can_someone_please_tell_me_some_resources_how/ | Puzzleheaded_Acadia1 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 122jsdm | false | null | t3_122jsdm | /r/LocalLLaMA/comments/122jsdm/hi_can_someone_please_tell_me_some_resources_how/ | false | false | default | 1 | null | |
Can I run the llama model locally with an APU and without a GPU? | 1 | [removed] | null | [deleted] | 1970-01-01T00:00:00 | 0 | {} | 122kwnx | false | null | t3_122kwnx | /r/LocalLLaMA/comments/122kwnx/can_i_run_the_llama_model_locally_with_an_apu_and/ | false | false | default | 1 | null | ||
The real potential of Llama | 18 | I'm using the alpaca-7b-native-GPTQ thanks to the new fix and we can get really great outputs if you choose a good example at the begining.
Here's the character.json I'm using right now:
{
"char\_name": "### Response:",
"char\_persona": "",
"char\_greeting": "",
"world\_scenario": "Below is an instruction that de... | null | https://www.reddit.com/r/LocalLLaMA/comments/122n6oi/the_real_potential_of_llama/ | Wonderful_Ad_5134 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 122n6oi | false | null | t3_122n6oi | /r/LocalLLaMA/comments/122n6oi/the_real_potential_of_llama/ | false | false | 18 | null | |
Can any Dalai experts check this issue out? No output at all, and no sign of increased CPU/RAM usage. Tried on multiple machines using official models converted/quantized by me. | 1 | [removed] | null | https://www.reddit.com/r/LocalLLaMA/comments/122tsis/can_any_dalai_experts_check_this_issue_out_no/ | Virtamancer | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 122tsis | false | null | t3_122tsis | /r/LocalLLaMA/comments/122tsis/can_any_dalai_experts_check_this_issue_out_no/ | false | false | default | 1 | null |
Alpaca.http: CPU Microserver for GET/POST requests via HTTP from any language | 5 | [removed] | null | https://www.reddit.com/r/LocalLLaMA/comments/122vor0/alpacahttp_cpu_microserver_for_getpost_requests/ | Nuked_ | self.LocalLLaMA | 2023-03-27T05:06:45 | 0 | {} | 122vor0 | false | null | t3_122vor0 | /r/LocalLLaMA/comments/122vor0/alpacahttp_cpu_microserver_for_getpost_requests/ | false | false | default | 5 | null |
New Oobabooga Standard, 8bit, and 4bit plus LLaMA conversion instructions, Windows 10 no WSL needed | 29 | ***Update Do this instead***
things move so fast the instructions are already out dated. Mr. Oobabooga had updated his repo with a one click installer....and it works!! omg it works so well too :3
https://github.com/oobabooga/text-generation-webui#installation
***Update Do this instead***
https://youtu.be/gIvV-5... | null | https://www.reddit.com/r/LocalLLaMA/comments/122x9ld/new_oobabooga_standard_8bit_and_4bit_plus_llama/ | Inevitable-Start-653 | self.LocalLLaMA | 2023-03-30T00:55:17 | 0 | {} | 122x9ld | false | null | t3_122x9ld | /r/LocalLLaMA/comments/122x9ld/new_oobabooga_standard_8bit_and_4bit_plus_llama/ | false | false | self | 29 | {'enabled': False, 'images': [{'id': 'FM12frYH_7w3OCDB2nGlyI_XGbKvhXUonMxEWvaUNmk', 'resolutions': [{'height': 55, 'url': 'https://external-preview.redd.it/CsbpnYy0o2Z0ndTn9IkprXoT9I-DZckcHGQp2iOCkP8.jpg?width=108&crop=smart&auto=webp&v=enabled&s=93415e01c1408ee86bed93eeb9c291ee2372072e', 'width': 108},... |
found a community | 1 | [removed] | null | https://www.reddit.com/r/LocalLLaMA/comments/1236e3g/found_a_community/ | MLUserDeeper | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 1236e3g | false | null | t3_1236e3g | /r/LocalLLaMA/comments/1236e3g/found_a_community/ | false | false | default | 1 | null |
Subsets and Splits
No community queries yet
The top public SQL queries from the community will appear here once available.