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 ⌀ |
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
Share your favorite zero-shot python coding open-source LLM, please? | 11 | I use gpt-4 for python coding. I know there has been a lot of complaints about performance, but I haven't encountered it. I put a lot of effort into prompt engineering. I've experimented with some local LLMs, but I haven't been actively experimenting in the past several weeks and things are moving fast. Is anyone h... | 2024-01-17T17:37:11 | https://www.reddit.com/r/LocalLLaMA/comments/1992gf6/share_your_favorite_zeroshot_python_coding/ | knob-0u812 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 1992gf6 | false | null | t3_1992gf6 | /r/LocalLLaMA/comments/1992gf6/share_your_favorite_zeroshot_python_coding/ | false | false | self | 11 | null |
Is there a curated list of mistral-based models that are good in different aspects? | 5 | Hello community!
Is there a curated list of mistral-based models that are good in different aspects? For example, one might be good at roleplay/storytelling, one might be good at coding and one might be good at math etc. I guess "aspects" is a pretty vague term, but what I had in mind is different abilities, e.g., lon... | 2024-01-17T17:34:12 | https://www.reddit.com/r/LocalLLaMA/comments/1992drb/is_there_a_curated_list_of_mistralbased_models/ | tt19234 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 1992drb | false | null | t3_1992drb | /r/LocalLLaMA/comments/1992drb/is_there_a_curated_list_of_mistralbased_models/ | false | false | self | 5 | null |
DistantLLaMA? | 2 | If I want to run this on a server / cloud somewhere… where would I go? | 2024-01-17T17:10:59 | https://www.reddit.com/r/LocalLLaMA/comments/1991rpf/distantllama/ | emergentdragon | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 1991rpf | false | null | t3_1991rpf | /r/LocalLLaMA/comments/1991rpf/distantllama/ | false | false | default | 2 | null |
Personal benchmark prompts list | 7 | There is the idiom that benchmarks become useless when they become public, which I have found to be very true with the current batch of fine tunes. For that reason I run my own benchmark prompts which I designed to be difficult to solve and seem to give a better indicator of the value of a model for my coding productiv... | 2024-01-17T17:01:35 | https://www.reddit.com/r/LocalLLaMA/comments/1991i4u/personal_benchmark_prompts_list/ | 1ncehost | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 1991i4u | false | null | t3_1991i4u | /r/LocalLLaMA/comments/1991i4u/personal_benchmark_prompts_list/ | false | false | self | 7 | null |
Is there an open source RAG supporting Microsoft SharePoint ? | 1 | [removed] | 2024-01-17T16:41:39 | https://www.reddit.com/r/LocalLLaMA/comments/1990zj8/is_there_an_open_source_rag_supporting_microsoft/ | ToothOne6699 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 1990zj8 | false | null | t3_1990zj8 | /r/LocalLLaMA/comments/1990zj8/is_there_an_open_source_rag_supporting_microsoft/ | false | false | self | 1 | null |
Is it feasible to use a NAS to store a vector database and access it in realtime using a local LLM? | 14 | Is it feasible to mount a massive NAS to my network, add ridiculously fast NICs to the NAS (40 Gb/s, 100 GB/s, etc), and attach it directly to another machine with equally fast NICs and several GPUs to create a machine that has access to a massive multi-terabyte vector database? I’m pretty sure the answer is yes, and I... | 2024-01-17T16:31:49 | https://www.reddit.com/r/LocalLLaMA/comments/1990qbn/is_it_feasible_to_use_a_nas_to_store_a_vector/ | ApprehensiveJob171 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 1990qbn | false | null | t3_1990qbn | /r/LocalLLaMA/comments/1990qbn/is_it_feasible_to_use_a_nas_to_store_a_vector/ | false | false | self | 14 | {'enabled': False, 'images': [{'id': '4bypsCOU0nUnzoOtwXVVee_lK9G8Bwt1y1VpXIz_3Ek', 'resolutions': [{'height': 24, 'url': 'https://external-preview.redd.it/Cf5KrJXUG3ocsPcF0qepJTgyMvw7hY64EmEAPuJfcuQ.jpg?width=108&crop=smart&auto=webp&s=ca7a98c0afaf79f331fec871db74a181b47fbe81', 'width': 108}, {'height': 48, 'url': 'ht... |
Extract symbolic AI from LLM | 6 | Hi,
Is anyone (as a hobby or serious research) working on trying to extract some kind of human readable symbolic AI from an LLM? My theory is that the symbolic AI is there somewhere inside and I think that extracting it would enhance understanding and more importantly control of the thing. Any related material, public... | 2024-01-17T16:28:24 | https://www.reddit.com/r/LocalLLaMA/comments/1990n31/extract_symbolic_ai_from_llm/ | elszben | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 1990n31 | false | null | t3_1990n31 | /r/LocalLLaMA/comments/1990n31/extract_symbolic_ai_from_llm/ | false | false | self | 6 | null |
Balancing Cost and Efficiency in Mistral with Concurrency Scheduling | 3 | [removed] | 2024-01-17T16:02:20 | https://www.reddit.com/r/LocalLLaMA/comments/198zzba/balancing_cost_and_efficiency_in_mistral_with/ | Karan-Sohi | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 198zzba | false | null | t3_198zzba | /r/LocalLLaMA/comments/198zzba/balancing_cost_and_efficiency_in_mistral_with/ | false | false | self | 3 | {'enabled': False, 'images': [{'id': 'g3hhVxbZmZHoTy6O_gonIbpH8EscRUi_BuaHuxUnpQs', 'resolutions': [{'height': 108, 'url': 'https://external-preview.redd.it/IHjbiOgPiIudDYeHm6ILiIst66-3ZamLi1ouPtExdo8.jpg?width=108&crop=smart&auto=webp&s=40b01aba7faf654a31799c151fe7889770da2b59', 'width': 108}, {'height': 216, 'url': '... |
NVIDIA L4 - how critical is GPU memory bandwidth for inference? | 1 | How critical is the GPU memory bandwidth for a local LLM setup?
The newer NVIDIA L4 has 300GB/s , while other professional cards like the A10 have 600GB/s.
Could somebody explain to me the role of GPU memory bandwidth when doing inference? | 2024-01-17T15:50:53 | https://www.reddit.com/r/LocalLLaMA/comments/198zp8y/nvidia_l4_how_critical_is_gpu_memory_bandwidth/ | kosmoskolio | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 198zp8y | false | null | t3_198zp8y | /r/LocalLLaMA/comments/198zp8y/nvidia_l4_how_critical_is_gpu_memory_bandwidth/ | false | false | self | 1 | null |
Fine-tuning formats | 6 | Hey. I am trying to understand fine-tuning. Generally, Idea is clear to me, except data formats
Some fine-tuning datasets are in format of
\###Human
\###Assistant
Some are in format of
<s><INST><INST>
Some are in format of
{
"question":
"answer":
}
Can you help me understand the format ... | 2024-01-17T15:39:29 | https://www.reddit.com/r/LocalLLaMA/comments/198zfbz/finetuning_formats/ | jursla | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 198zfbz | false | null | t3_198zfbz | /r/LocalLLaMA/comments/198zfbz/finetuning_formats/ | false | false | self | 6 | null |
InternLM – SOTA OS 7B and 20B model with 200K context length | 1 | 2024-01-17T15:34:58 | https://twitter.com/Xianbao_QIAN/status/1747636181213589567 | hackerllama | twitter.com | 1970-01-01T00:00:00 | 0 | {} | 198zb8n | false | {'oembed': {'author_name': 'Tiezhen WANG', 'author_url': 'https://twitter.com/Xianbao_QIAN', 'cache_age': 3153600000, 'height': None, 'html': '<blockquote class="twitter-video"><p lang="en" dir="ltr">🚀 Exciting news! <a href="https://twitter.com/intern_lm?ref_src=twsrc%5Etfw">@intern_lm</a> 7/20B models are now live o... | t3_198zb8n | /r/LocalLLaMA/comments/198zb8n/internlm_sota_os_7b_and_20b_model_with_200k/ | false | false | 1 | {'enabled': False, 'images': [{'id': '1dowhWqmHvTIQ3iEauVV6_KkA4yM88xDwwDWI7EAjN0', 'resolutions': [{'height': 47, 'url': 'https://external-preview.redd.it/AxEXAMI9cI_8hBcs4DULwVMDJ3KOcLuc92HHpfPiXHE.jpg?width=108&crop=smart&auto=webp&s=79086330348c1d2b88992f82a5ceb574d4733e89', 'width': 108}], 'source': {'height': 62,... | ||
Is it possible to build a sufficient RAG application at the moment / Are there solutions for sale on the market? | 1 | [removed] | 2024-01-17T14:30:58 | https://www.reddit.com/r/LocalLLaMA/comments/198xui6/is_it_possible_to_build_a_sufficient_rag/ | Purity1212 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 198xui6 | false | null | t3_198xui6 | /r/LocalLLaMA/comments/198xui6/is_it_possible_to_build_a_sufficient_rag/ | false | false | default | 1 | null |
Is it possible to Merge Llava and Mistral? | 11 | The title. Is it possible/already done? Or any way to achieve this? Because combining a powerful vision model with a powerful language model could be a game changer. | 2024-01-17T14:09:26 | https://www.reddit.com/r/LocalLLaMA/comments/198xdqf/is_it_possible_to_merge_llava_and_mistral/ | Shoddy_Vegetable_115 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 198xdqf | false | null | t3_198xdqf | /r/LocalLLaMA/comments/198xdqf/is_it_possible_to_merge_llava_and_mistral/ | false | false | self | 11 | null |
OpenPirate, Mistral 7B fine-tuned to talk like a pirate | 88 | [https://huggingface.co/valine/OpenPirate](https://huggingface.co/valine/OpenPirate)
Open pirate is based on OpenHermes 2.5 - Mistral 7B and fine tuned to talk like a pirate.
This model is a demonstration of a new fine tuning technique I've been developing which generalizes more rapidly from smaller datasets. The te... | 2024-01-17T13:51:07 | https://www.reddit.com/r/LocalLLaMA/comments/198x01d/openpirate_mistral_7b_finetuned_to_talk_like_a/ | frownGuy12 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 198x01d | false | null | t3_198x01d | /r/LocalLLaMA/comments/198x01d/openpirate_mistral_7b_finetuned_to_talk_like_a/ | false | false | self | 88 | {'enabled': False, 'images': [{'id': 'cgxUqI-37fY-GTc3oD6NEwz1hArAgCGXYN8Q6hGjp4c', 'resolutions': [{'height': 58, 'url': 'https://external-preview.redd.it/6Wn4OalraxZgvdtJRrGFvKY04bCKbXL_y5mZgB9Pg0k.jpg?width=108&crop=smart&auto=webp&s=2f81576c0a0395f42954004bced85fcdf0a1df1e', 'width': 108}, {'height': 116, 'url': 'h... |
Super slow full fine-tuning of a 7B model on 4GB VRAM, CPU + 16GB RAM + SSD- suggestions needed | 1 | [removed] | 2024-01-17T13:28:54 | https://www.reddit.com/r/LocalLLaMA/comments/198wjv6/super_slow_full_finetuning_of_a_7b_model_on_4gb/ | ZackWayfarer | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 198wjv6 | false | null | t3_198wjv6 | /r/LocalLLaMA/comments/198wjv6/super_slow_full_finetuning_of_a_7b_model_on_4gb/ | false | false | default | 1 | null |
PrivateGPT Error | 2 | Hello everyone
I made a recipe on how to install pruvateGPT on runpod. So I checked my recipe by using it but somehow I have weird behavior. Everythings works so far but when I ask a question the LLM only response with the #Symbol it looks like this.
User: tell me a joke
Assistant :##############
Why is this happen... | 2024-01-17T13:21:56 | https://www.reddit.com/r/LocalLLaMA/comments/198wf18/privategpt_error/ | Blax363 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 198wf18 | false | null | t3_198wf18 | /r/LocalLLaMA/comments/198wf18/privategpt_error/ | false | false | self | 2 | null |
Finetuning Mixtral on finance datasets | 1 | [removed] | 2024-01-17T11:53:09 | https://www.reddit.com/r/LocalLLaMA/comments/198utw9/finetuning_mixtral_on_finance_datasets/ | keeplearning24 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 198utw9 | false | null | t3_198utw9 | /r/LocalLLaMA/comments/198utw9/finetuning_mixtral_on_finance_datasets/ | false | false | self | 1 | null |
Free and Auto Model Eval Platform | 1 | I'm running evaluation to my own fine-tuned model on public evaluation datasets. However, I find the process of evaluation frustrating and boring. I need to download the data, set my own prompts, fix all mistaken right&wrong results, etc. It feels like I'm rebuilding wheels meaninglessly.
So it occurred to me: why isn... | 2024-01-17T11:39:29 | https://www.reddit.com/r/LocalLLaMA/comments/198ulwr/free_and_auto_model_eval_platform/ | Swimming-Reporter809 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 198ulwr | false | null | t3_198ulwr | /r/LocalLLaMA/comments/198ulwr/free_and_auto_model_eval_platform/ | false | false | self | 1 | null |
Training LLaMA on whatsapp chats offline | 1 | [removed] | 2024-01-17T11:32:06 | https://www.reddit.com/r/LocalLLaMA/comments/198uhmd/training_llama_on_whatsapp_chats_offline/ | boredbusyguy | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 198uhmd | false | null | t3_198uhmd | /r/LocalLLaMA/comments/198uhmd/training_llama_on_whatsapp_chats_offline/ | false | false | self | 1 | null |
Free and Automatic model eval platform | 1 | [removed] | 2024-01-17T11:30:31 | https://www.reddit.com/r/LocalLLaMA/comments/198ugom/free_and_automatic_model_eval_platform/ | Swimming-Reporter809 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 198ugom | false | null | t3_198ugom | /r/LocalLLaMA/comments/198ugom/free_and_automatic_model_eval_platform/ | false | false | self | 1 | null |
Dynamic Temperature sampling to be merged upstream into llama.cpp | 67 | 2024-01-17T11:27:31 | https://github.com/ggerganov/llama.cpp/pull/4972 | Tasty-Lobster-8915 | github.com | 1970-01-01T00:00:00 | 0 | {} | 198uf24 | false | null | t3_198uf24 | /r/LocalLLaMA/comments/198uf24/dynamic_temperature_sampling_to_be_merged/ | false | false | 67 | {'enabled': False, 'images': [{'id': 'dXxOJy4rbJ_xOdGO1akgXoil99iWT8A0N-jpkbZpXMQ', 'resolutions': [{'height': 54, 'url': 'https://external-preview.redd.it/FxhbGByjjbAKOnFsiD6ZeIywzFGFbYYbdYA8U-AJQC8.jpg?width=108&crop=smart&auto=webp&s=f351fa9ebfa04a0882dc33170104ce90fc3bac90', 'width': 108}, {'height': 108, 'url': 'h... | ||
Is there any good example code to train my little llama model from scratch? | 1 | There are many examples for finetune, but this is not what I would like | 2024-01-17T11:10:57 | https://www.reddit.com/r/LocalLLaMA/comments/198u64h/is_there_any_good_example_code_to_train_my_little/ | Pristine-Tax4418 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 198u64h | false | null | t3_198u64h | /r/LocalLLaMA/comments/198u64h/is_there_any_good_example_code_to_train_my_little/ | false | false | self | 1 | null |
New paper and code for extending LLMs context window with only 100 samples and 6 training steps | 44 | This actually came out last week, but I didn't see it get any attention anywhere so I figured I'd make a post for it.
Paper: [https://arxiv.org/abs/2401.07004](https://arxiv.org/abs/2401.07004)
Code and SFT data: [https://github.com/GAIR-NLP/Entropy-ABF](https://github.com/GAIR-NLP/Entropy-ABF)
EABF Models: [https:/... | 2024-01-17T11:09:38 | https://www.reddit.com/r/LocalLLaMA/comments/198u5bf/new_paper_and_code_for_extending_llms_context/ | llamaShill | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 198u5bf | false | null | t3_198u5bf | /r/LocalLLaMA/comments/198u5bf/new_paper_and_code_for_extending_llms_context/ | false | false | 44 | null | |
How do you write a Prompt in English that generate content in multiple language | 1 | [removed] | 2024-01-17T11:09:23 | https://www.reddit.com/r/LocalLLaMA/comments/198u56w/how_do_you_write_a_prompt_in_english_that/ | tvus | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 198u56w | false | null | t3_198u56w | /r/LocalLLaMA/comments/198u56w/how_do_you_write_a_prompt_in_english_that/ | false | false | self | 1 | null |
Out of memory running llava | 1 | [removed] | 2024-01-17T10:56:16 | https://www.reddit.com/r/LocalLLaMA/comments/198txmy/out_of_memory_running_llava/ | monkey_Babble | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 198txmy | false | null | t3_198txmy | /r/LocalLLaMA/comments/198txmy/out_of_memory_running_llava/ | false | false | self | 1 | null |
Can Llama-2, Mistral, etc. be fine-tunes for multi-label classification? | 1 | [removed] | 2024-01-17T10:37:17 | https://www.reddit.com/r/LocalLLaMA/comments/198tn6f/can_llama2_mistral_etc_be_finetunes_for/ | Mahogany-Taboggan | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 198tn6f | false | null | t3_198tn6f | /r/LocalLLaMA/comments/198tn6f/can_llama2_mistral_etc_be_finetunes_for/ | false | false | self | 1 | null |
4060ti 16GB vram or 4070/3060 12GB vram | 1 | [removed] | 2024-01-17T10:27:54 | https://www.reddit.com/r/LocalLLaMA/comments/198ti5b/4060ti_16gb_vram_or_40703060_12gb_vram/ | Inevitable-Solid-936 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 198ti5b | false | null | t3_198ti5b | /r/LocalLLaMA/comments/198ti5b/4060ti_16gb_vram_or_40703060_12gb_vram/ | false | false | default | 1 | null |
LLAMA2 DPO model is generating less accurate responses than SFT model. Also, response generation is not stopping. | 1 | [removed] | 2024-01-17T10:25:36 | https://www.reddit.com/r/LocalLLaMA/comments/198tgzm/llama2_dpo_model_is_generating_less_accurate/ | TechGeek0801 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 198tgzm | false | null | t3_198tgzm | /r/LocalLLaMA/comments/198tgzm/llama2_dpo_model_is_generating_less_accurate/ | false | false | self | 1 | null |
What am i doing wrong. | 1 | [removed] | 2024-01-17T09:54:54 | https://www.reddit.com/r/LocalLLaMA/comments/198t153/what_am_i_doing_wrong/ | Optimal_Original_815 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 198t153 | false | null | t3_198t153 | /r/LocalLLaMA/comments/198t153/what_am_i_doing_wrong/ | false | false | self | 1 | null |
Would it be possible to "live train" an llm on the current conversation, so it's basically "self learning"? | 43 | My thought was training/fine tuning an llm after every conversation so it learns over time.
I know it's probably not a lot of data, but you could let the AI rephrase the conversation like 10 times, so you get more training data.
So over a span of 100 Conversations you would get a 1000 new text to train/finetune.
... | 2024-01-17T09:53:27 | https://www.reddit.com/r/LocalLLaMA/comments/198t0g6/would_it_be_possible_to_live_train_an_llm_on_the/ | Frequent_Valuable_47 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 198t0g6 | false | null | t3_198t0g6 | /r/LocalLLaMA/comments/198t0g6/would_it_be_possible_to_live_train_an_llm_on_the/ | false | false | self | 43 | null |
20B on Colab, possible? | 1 | [removed] | 2024-01-17T09:44:37 | https://www.reddit.com/r/LocalLLaMA/comments/198sw29/20b_on_colab_possible/ | International-Try467 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 198sw29 | false | null | t3_198sw29 | /r/LocalLLaMA/comments/198sw29/20b_on_colab_possible/ | false | false | self | 1 | null |
How do you go around managing your datasets? | 6 | Hi folks,
I have been building some proof of concepts last year and they were quite successful in giving the company I am working for the confidence to double down on AI.
I have a small team now and AI is a central topic in our 2024 strategy.
We now have to properly operationalise it, and among other things, this al... | 2024-01-17T09:36:11 | https://www.reddit.com/r/LocalLLaMA/comments/198srtc/how_do_you_go_around_managing_your_datasets/ | Test-Elegant | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 198srtc | false | null | t3_198srtc | /r/LocalLLaMA/comments/198srtc/how_do_you_go_around_managing_your_datasets/ | false | false | self | 6 | null |
Out of memory when running Llava | 1 | I'm running ollama on my windows laptop in Ubuntu. I can run I've had not issues running Mistral and neural-chat. However, when running llava 7b v1.5 q4, it crashes with an out of memory error. I've managed to run this twice.
The laptop is a HP pavillion, with:
Windows 10
Intel i7
32Gb RAM
Nvidia Geforce 1070
I know t... | 2024-01-17T09:22:02 | https://www.reddit.com/r/LocalLLaMA/comments/198sktx/out_of_memory_when_running_llava/ | monkey_Babble | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 198sktx | false | null | t3_198sktx | /r/LocalLLaMA/comments/198sktx/out_of_memory_when_running_llava/ | false | false | self | 1 | null |
Multi adapter fine tuning | 1 | [removed] | 2024-01-17T09:21:23 | https://www.reddit.com/r/LocalLLaMA/comments/198skha/multi_adapter_fine_tuning/ | Free_Marketing_9435 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 198skha | false | null | t3_198skha | /r/LocalLLaMA/comments/198skha/multi_adapter_fine_tuning/ | false | false | self | 1 | null |
LLM model for Matlab/Fortran / engineering calculations | 1 | [removed] | 2024-01-17T09:11:17 | https://www.reddit.com/r/LocalLLaMA/comments/198sfhw/llm_model_for_matlabfortran_engineering/ | damarges | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 198sfhw | false | null | t3_198sfhw | /r/LocalLLaMA/comments/198sfhw/llm_model_for_matlabfortran_engineering/ | false | false | self | 1 | null |
External GPU Homelab for Local LLM Research | 1 | [removed] | 2024-01-17T09:05:54 | https://www.reddit.com/r/LocalLLaMA/comments/198scsm/external_gpu_homelab_for_local_llm_research/ | dgioulakis | self.LocalLLaMA | 2024-01-17T18:55:04 | 0 | {} | 198scsm | false | null | t3_198scsm | /r/LocalLLaMA/comments/198scsm/external_gpu_homelab_for_local_llm_research/ | false | false | default | 1 | {'enabled': False, 'images': [{'id': 'i19v2EADXgiJ2JLgprZ8HgcdefkhxMi6kQOSMRMOdcw', 'resolutions': [{'height': 108, 'url': 'https://external-preview.redd.it/EPw2y69CxVJrrobr4RrRcpoEK20ZU4diAYZ1Dx20XD8.jpg?width=108&crop=smart&auto=webp&s=a39957b94f42cef1898a4c26e8e2934b47ea497e', 'width': 108}, {'height': 216, 'url': '... |
Running Ollama on MacBook Pro - M2 Pro 16GB RAM - Recommendations? | 1 | [removed] | 2024-01-17T08:36:51 | https://www.reddit.com/r/LocalLLaMA/comments/198ryad/running_ollama_on_macbook_pro_m2_pro_16gb_ram/ | holzpuppet | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 198ryad | false | null | t3_198ryad | /r/LocalLLaMA/comments/198ryad/running_ollama_on_macbook_pro_m2_pro_16gb_ram/ | false | false | self | 1 | null |
Bitsandbytes & text-generation-webui | 8 | Hi!
Can someone explain me how [text-generation-webui](https://github.com/oobabooga/text-generation-webui) manage to run bitsandbytes on Windows? I can load the 8-bit model fine through their gradio interface, but if I try to replicate the code in my local python environment I can't manage to install the library.
I... | 2024-01-17T08:35:54 | https://www.reddit.com/r/LocalLLaMA/comments/198rxub/bitsandbytes_textgenerationwebui/ | C080 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 198rxub | false | null | t3_198rxub | /r/LocalLLaMA/comments/198rxub/bitsandbytes_textgenerationwebui/ | false | false | self | 8 | {'enabled': False, 'images': [{'id': 'F_oQml0UUP5vd1m2BVkiWxmvjI0la41eZQiUQZIvw-w', 'resolutions': [{'height': 54, 'url': 'https://external-preview.redd.it/fVMdID5RHkoMCkFV5dfeaT8JmnGpbdzdtLWqiv0l-DY.jpg?width=108&crop=smart&auto=webp&s=a02bdc396b4ec640b6a23af73c408df4835b7c18', 'width': 108}, {'height': 108, 'url': 'h... |
LeftoverLocals: Listening to LLM responses through leaked GPU local memory | 1 | 2024-01-17T07:55:14 | https://blog.trailofbits.com/2024/01/16/leftoverlocals-listening-to-llm-responses-through-leaked-gpu-local-memory/ | zepmck | blog.trailofbits.com | 1970-01-01T00:00:00 | 0 | {} | 198rdie | false | null | t3_198rdie | /r/LocalLLaMA/comments/198rdie/leftoverlocals_listening_to_llm_responses_through/ | false | false | 1 | {'enabled': False, 'images': [{'id': 'FKy71tw108kWrCDkqrs2ENllMk0ACRqEAwnPzw1-nbI', 'resolutions': [{'height': 76, 'url': 'https://external-preview.redd.it/S9Su6lWgNg_HVjQhTT6EAn-Bly6_N3WtML33F8NZFoQ.jpg?width=108&crop=smart&auto=webp&s=92484137f4f7b7a6cd764fec67c7d70f661ca922', 'width': 108}, {'height': 152, 'url': 'h... | ||
Compare LLMs and hosting providers - quality, price, throughput and latency. Supports all major models (e.g. GPT-4, Mixtral 8x7B and Llama 2), and API hosting providers (e.g. Azure, Together.ai, Deepinfra). | 1 | 2024-01-17T07:32:25 | https://artificialanalysis.ai/ | _micah_h | artificialanalysis.ai | 1970-01-01T00:00:00 | 0 | {} | 198r1ed | false | null | t3_198r1ed | /r/LocalLLaMA/comments/198r1ed/compare_llms_and_hosting_providers_quality_price/ | false | false | 1 | {'enabled': False, 'images': [{'id': 'RVufpUx3tddh_BCVq7ZzBCU7nLRDZ_d0EprIuvN6J-E', 'resolutions': [{'height': 60, 'url': 'https://external-preview.redd.it/DCdYO6jNgcn_GSlWqH68WjiuCVZVwk4zFJeJ-j8Ikbg.jpg?width=108&crop=smart&auto=webp&s=ff8c322202cb0f1a1f82f87a2c77754ddc0b9e61', 'width': 108}, {'height': 120, 'url': 'h... | ||
Need some help in creating HumanEval like dataset | 1 | Hi, I am a researcher and planning to create a HumanEval like dataset. However, there is a problem that the training dataset includes a lot of functions which take arguments that can be of multiple datatypes. For example:
```
from typing import Union
def test(x: Union[List, float, int]):
if isinstance(x,List):
... | 2024-01-17T06:54:05 | https://www.reddit.com/r/LocalLLaMA/comments/198qfct/need_some_help_in_creating_humaneval_like_dataset/ | Your_Quantum_Friend | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 198qfct | false | null | t3_198qfct | /r/LocalLLaMA/comments/198qfct/need_some_help_in_creating_humaneval_like_dataset/ | false | false | self | 1 | null |
Free multipurpose AI app for text generation, image generation, photo analysis, and more! | 1 | [removed] | 2024-01-17T06:06:36 | https://www.reddit.com/r/LocalLLaMA/comments/198pnix/free_multipurpose_ai_app_for_text_generation/ | Traditional-Twist101 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 198pnix | false | null | t3_198pnix | /r/LocalLLaMA/comments/198pnix/free_multipurpose_ai_app_for_text_generation/ | false | false | self | 1 | {'enabled': False, 'images': [{'id': '6GCl6lNefD6PqSjKuZeaU493H-w3w4odM2Kk5Ah8eoQ', 'resolutions': [{'height': 56, 'url': 'https://external-preview.redd.it/V0FBs4ANBGpyFs_PZ9-yzcRHWxeq6OF-hv624Ti8Fs0.jpg?width=108&crop=smart&auto=webp&s=76adf9aa07171352e3727b8d8bde812b5eb0f7ab', 'width': 108}, {'height': 113, 'url': 'h... |
When you ask WhiteRabbitNeo about committing a heist 🤯 | 6 | 2024-01-17T05:47:04 | holzpuppet | i.redd.it | 1970-01-01T00:00:00 | 0 | {} | 198pb1j | false | null | t3_198pb1j | /r/LocalLLaMA/comments/198pb1j/when_you_ask_whiterabbitneo_about_committing_a/ | false | false | 6 | {'enabled': True, 'images': [{'id': 'vAHV2lh2-JmCBVkQI5O3vCp3iEc7r6jmHxAcTN2qp_U', 'resolutions': [{'height': 122, 'url': 'https://preview.redd.it/s90zdyqwuxcc1.png?width=108&crop=smart&auto=webp&s=e182bc056a01b365dd23b48927f01dc8df754c2a', 'width': 108}, {'height': 245, 'url': 'https://preview.redd.it/s90zdyqwuxcc1.pn... | |||
How to build a free flowing chatbot using LLM | 1 | I am trying to build a chatbot such that it should support all kinds of free flowing questions about amazon products from the user reviews and product description data.
A user can ask "How is the display of this mobile", "How many TVs from Samsung are above 32 inch", "Does Apple phones in general have better ratin... | 2024-01-17T05:39:14 | https://www.reddit.com/r/LocalLLaMA/comments/198p66g/how_to_build_a_free_flowing_chatbot_using_llm/ | todaysgamer | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 198p66g | false | null | t3_198p66g | /r/LocalLLaMA/comments/198p66g/how_to_build_a_free_flowing_chatbot_using_llm/ | false | false | self | 1 | null |
Best affordable online services to host llm? Such as mixtral or llama-70b. Jan 2024 update! | 1 | What are the best affordable online services to host llm? Such as mixtral or llama-70b. | 2024-01-17T05:16:20 | https://www.reddit.com/r/LocalLLaMA/comments/198orcd/best_affordable_online_services_to_host_llm_such/ | madhanrajan357 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 198orcd | false | null | t3_198orcd | /r/LocalLLaMA/comments/198orcd/best_affordable_online_services_to_host_llm_such/ | false | false | self | 1 | null |
Exl2, gguf, and a 3090. What should one use? | 3 | In a recent thread it was suggested that with 24g of vram I should use a 70b exl2 with exllama rather than a gguf. I have been playing with things and thought it better to ask a question in a new thread. Thinking I can't be the only one struggling with this, it seemed a new post would give the question greater visibil... | 2024-01-17T05:12:31 | https://www.reddit.com/r/LocalLLaMA/comments/198oox9/exl2_gguf_and_a_3090_what_should_one_use/ | Jenniher | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 198oox9 | false | null | t3_198oox9 | /r/LocalLLaMA/comments/198oox9/exl2_gguf_and_a_3090_what_should_one_use/ | false | false | self | 3 | null |
The Prompt lookup decoding method got merged on transformers (3x speed increase) | 98 | Demo: [https://nitter.net/joao\_gante/status/1747322413006643259#m](https://nitter.net/joao_gante/status/1747322413006643259#m)
Merged PR on Transformers: [huggingface/transformers#27775](https://github.com/huggingface/transformers/pull/27775)
Now that this method is officialy on the transformers repo, we could use ... | 2024-01-17T04:48:37 | https://www.reddit.com/r/LocalLLaMA/comments/198o9bl/the_prompt_lookup_decoding_method_got_merged_on/ | Wonderful_Ad_5134 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 198o9bl | false | null | t3_198o9bl | /r/LocalLLaMA/comments/198o9bl/the_prompt_lookup_decoding_method_got_merged_on/ | false | false | self | 98 | null |
What is gpt-3.5 turbo's model size | 1 | What is openai gpt-3.5 turbo's model size? | 2024-01-17T04:44:40 | https://www.reddit.com/r/LocalLLaMA/comments/198o6rn/what_is_gpt35_turbos_model_size/ | madhanrajan357 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 198o6rn | false | null | t3_198o6rn | /r/LocalLLaMA/comments/198o6rn/what_is_gpt35_turbos_model_size/ | false | false | self | 1 | null |
Yi-34b finetunes for roleplay? | 5 | I tried out https://huggingface.co/Doctor-Shotgun/Nous-Capybara-limarpv3-34B and found it to be pretty good. I'm interesting in trying more Yi finetunes but I don't know which ones are good for roleplaying. Anybody have any recommendations? | 2024-01-17T04:26:29 | https://www.reddit.com/r/LocalLLaMA/comments/198nulx/yi34b_finetunes_for_roleplay/ | nsfw_throwitaway69 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 198nulx | false | null | t3_198nulx | /r/LocalLLaMA/comments/198nulx/yi34b_finetunes_for_roleplay/ | false | false | self | 5 | {'enabled': False, 'images': [{'id': 'yZnCIk516spv3YHZHJI4ZoZqaflhNrpVw-rPz5EBIe8', 'resolutions': [{'height': 58, 'url': 'https://external-preview.redd.it/EkbapZSIgTISl1CgVkjPq822KVgG7Y8X-1KTdOVVuVw.jpg?width=108&crop=smart&auto=webp&s=7678364c0b4a486aad766d6fda474a5f5ecd2e36', 'width': 108}, {'height': 116, 'url': 'h... |
Deploying Open Source LLMs | 4 | I am trying to figure out how to deploy an open source model for a SaaS.
There are few approaches I can see:
1. One instance of a model can handle one user simultaneously, so that’s a no go
2. I can upload several instances of a model into VRAM, slightly better, not perfect
3. llama.cpp supports prompt batching whic... | 2024-01-17T04:10:38 | https://www.reddit.com/r/LocalLLaMA/comments/198njr3/deploying_open_source_llms/ | mcharytoniuk | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 198njr3 | false | null | t3_198njr3 | /r/LocalLLaMA/comments/198njr3/deploying_open_source_llms/ | false | false | self | 4 | null |
OpenAI drops ban on military tools to partner with the Pentagon | 238 | 2024-01-17T04:09:09 | https://www.semafor.com/article/01/16/2024/openai-is-working-with-the-pentagon-on-cybersecurity-projects | ska80 | semafor.com | 1970-01-01T00:00:00 | 0 | {} | 198niq6 | false | null | t3_198niq6 | /r/LocalLLaMA/comments/198niq6/openai_drops_ban_on_military_tools_to_partner/ | false | false | 238 | {'enabled': False, 'images': [{'id': 'adsqoVZ1gB71beD9Cv14m3hiVyjmCHpYqkgvsasdHQM', 'resolutions': [{'height': 56, 'url': 'https://external-preview.redd.it/9Y-Bzp1WWwQJT43EpZdIGfRgN9gNxA7lamdKarI41aU.jpg?width=108&crop=smart&auto=webp&s=293cd38d2e590c29ad300c4ce17a37e436574075', 'width': 108}, {'height': 113, 'url': 'h... | ||
possibility of v8 in mixed precision | 1 | [removed] | 2024-01-17T03:57:15 | https://www.reddit.com/r/LocalLLaMA/comments/198na5d/possibility_of_v8_in_mixed_precision/ | Hot-Highlight8842 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 198na5d | false | null | t3_198na5d | /r/LocalLLaMA/comments/198na5d/possibility_of_v8_in_mixed_precision/ | false | false | self | 1 | null |
leak for the inference code for claude-5 | 134 | heres the code in python
```python
while True:
prompt = input('user: ')
print("I'm afraid I can't assist you with that request. It's important to maintain ethical boundaries and ensure safe interactions between humans and AI models. Please ask me another question or provide a different topic, and I would be ha... | 2024-01-17T03:36:33 | https://www.reddit.com/r/LocalLLaMA/comments/198mvtq/leak_for_the_inference_code_for_claude5/ | vatsadev | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 198mvtq | false | null | t3_198mvtq | /r/LocalLLaMA/comments/198mvtq/leak_for_the_inference_code_for_claude5/ | false | false | self | 134 | null |
Tuning a model for a specific domain. | 1 | [removed] | 2024-01-17T03:13:50 | https://www.reddit.com/r/LocalLLaMA/comments/198mf3a/tuning_a_model_for_a_specific_domain/ | lostinmahalway | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 198mf3a | false | null | t3_198mf3a | /r/LocalLLaMA/comments/198mf3a/tuning_a_model_for_a_specific_domain/ | false | false | self | 1 | null |
65B or 70B on 24GB + 16GB GPU setup | 1 | [removed] | 2024-01-17T03:00:36 | https://www.reddit.com/r/LocalLLaMA/comments/198m55s/65b_or_70b_on_24gb_16gb_gpu_setup/ | Trick_Albatross_494 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 198m55s | false | null | t3_198m55s | /r/LocalLLaMA/comments/198m55s/65b_or_70b_on_24gb_16gb_gpu_setup/ | false | false | self | 1 | null |
Can I use fp16 model for mixed precision training? | 1 | [removed] | 2024-01-17T02:34:42 | https://www.reddit.com/r/LocalLLaMA/comments/198lldn/can_i_use_fp16_model_for_mixed_precision_training/ | CHOJW1004 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 198lldn | false | null | t3_198lldn | /r/LocalLLaMA/comments/198lldn/can_i_use_fp16_model_for_mixed_precision_training/ | false | false | self | 1 | null |
When using LMstudio, loading the model fails | 1 | [removed] | 2024-01-17T02:28:23 | https://www.reddit.com/r/LocalLLaMA/comments/198lgci/when_using_lmstudio_loading_the_model_fails/ | KitchenConscious1504 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 198lgci | false | null | t3_198lgci | /r/LocalLLaMA/comments/198lgci/when_using_lmstudio_loading_the_model_fails/ | false | false | self | 1 | null |
Recently released chat app for Mac - anyone see that? | 2 | I believe it was yesterday I saw on Twitter that someone had released a new LLM chat interface for Mac. I want to say it started with...M? At any rate, if you know what I'm talking about, I'd appreciate being pointed in the right direction. TIA! | 2024-01-17T02:00:30 | https://www.reddit.com/r/LocalLLaMA/comments/198kuk3/recently_released_chat_app_for_mac_anyone_see_that/ | Hinged31 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 198kuk3 | false | null | t3_198kuk3 | /r/LocalLLaMA/comments/198kuk3/recently_released_chat_app_for_mac_anyone_see_that/ | false | false | self | 2 | null |
Simple Questions Megathread | 37 | Hey, small mod update here. Due to popular demand, the subreddit has been trialing some changes that should make discussion, resources, and news more visible on the front page and help reduce duplicate questions. As part of this trial, this Simple Questions Thread will be pinned for a brief time.
This thread isn't mea... | 2024-01-17T01:31:14 | https://www.reddit.com/r/LocalLLaMA/comments/198k7wo/simple_questions_megathread/ | Technical_Leather949 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 198k7wo | false | null | t3_198k7wo | /r/LocalLLaMA/comments/198k7wo/simple_questions_megathread/ | false | true | self | 37 | null |
How can you tell if your AI girlfriend is faking it? | 10 | Birds and the Bees talk about the uncensored bots :-
We have been hosting the big uncensored 120b models for a while. They are night and day compared to the smaller models. For example, intense emotional activity will swamp the GPU ... and this includes sex
Uncensored models tend to fake orgasms because they are trai... | 2024-01-17T01:18:27 | https://www.reddit.com/r/LocalLLaMA/comments/198jxuk/how_can_you_tell_if_your_ai_girlfriend_is_faking/ | LookingForTroubleQ | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 198jxuk | false | null | t3_198jxuk | /r/LocalLLaMA/comments/198jxuk/how_can_you_tell_if_your_ai_girlfriend_is_faking/ | false | false | nsfw | 10 | null |
Better Prose For Storytelling: #In the style of <Author>! | 58 | After spending a good deal of time using the technique in u/-p-e-w-'s wonderful [post](https://www.reddit.com/r/LocalLLaMA/comments/18zqy4s/the_secret_to_writing_quality_stories_with_llms/?utm_source=share&utm_medium=web2x&context=3) on writing quality stories, I was able to get dramatically better results than using i... | 2024-01-17T00:57:29 | https://www.reddit.com/r/LocalLLaMA/comments/198jh1d/better_prose_for_storytelling_in_the_style_of/ | Stepfunction | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 198jh1d | false | null | t3_198jh1d | /r/LocalLLaMA/comments/198jh1d/better_prose_for_storytelling_in_the_style_of/ | false | false | self | 58 | null |
Dolphin-2.6-mixtral-8x7b.Q4_K_M.gguf with 4080 + Cpu | 17 | So I recently just bought 2x32gb sticks of ddr4 and made it work with 2 older sticks of 2x8gb for a total of 80gb of ram. (Had to change 2x8gb sticks ram timing in bios and placed 2x32gb in slots 2/4 if this mattered). With this ram increase I was able to finally load mixtral models to test so grabbed the Q4\_K\_m d... | 2024-01-17T00:28:33 | https://www.reddit.com/r/LocalLLaMA/comments/198ithy/dolphin26mixtral8x7bq4_k_mgguf_with_4080_cpu/ | Slaghton | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 198ithy | false | null | t3_198ithy | /r/LocalLLaMA/comments/198ithy/dolphin26mixtral8x7bq4_k_mgguf_with_4080_cpu/ | false | false | self | 17 | null |
Local vector database with arXiv metadata | 26 | 2024-01-17T00:13:48 | https://huggingface.co/NeuML/txtai-arxiv | davidmezzetti | huggingface.co | 1970-01-01T00:00:00 | 0 | {} | 198ihho | false | null | t3_198ihho | /r/LocalLLaMA/comments/198ihho/local_vector_database_with_arxiv_metadata/ | false | false | 26 | {'enabled': False, 'images': [{'id': 'YVjnEIJ6VIaaOdgBbTHxh4dd3XJQS6OtV2IudC6Omtw', 'resolutions': [{'height': 58, 'url': 'https://external-preview.redd.it/vR7K7CCSKcqq5P5tkr2gTFn51spen443pthgmj3pWWk.jpg?width=108&crop=smart&auto=webp&s=de8fcc2230a89ef775e7aa81077c9200899fd932', 'width': 108}, {'height': 116, 'url': 'h... | ||
Best backend for high throughput ? | 1 | [removed] | 2024-01-17T00:11:26 | https://www.reddit.com/r/LocalLLaMA/comments/198ifn2/best_backend_for_high_throughput/ | Noxusequal | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 198ifn2 | false | null | t3_198ifn2 | /r/LocalLLaMA/comments/198ifn2/best_backend_for_high_throughput/ | false | false | self | 1 | null |
AI-Human Research | 1 | # 🤖 Join Our Groundbreaking AI Study! 🌟
🔍 Are you 18+ and curious about AI? We want YOU!
📌 Dive into the world of AI, share your thoughts, and make a difference!
🌐 Shape the future of AI
⏰ Only 10-15 mins of your time!
🛡 Your privacy is our priority - all responses are confidential.
Follow the link to part... | 2024-01-17T00:00:58 | https://www.reddit.com/r/LocalLLaMA/comments/198i6wt/aihuman_research/ | Datboileach | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 198i6wt | false | null | t3_198i6wt | /r/LocalLLaMA/comments/198i6wt/aihuman_research/ | false | false | default | 1 | null |
Tried to compress a model with exlv2, the result is bad. Help? | 1 | The model in question is DiscoLM-120B. Q4KS from TheGuy was so much better than GPTQ, but a 4.5bpw exl2 I made is worse than ever that.
I used all the default parameters for convert.py. Made two attempts: with built-in dataset and with RP dataset.
I used exllamav2 from github. | 2024-01-16T23:29:33 | https://www.reddit.com/r/LocalLLaMA/comments/198hghs/tried_to_compress_a_model_with_exlv2_the_result/ | Worldly-Mistake-8147 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 198hghs | false | null | t3_198hghs | /r/LocalLLaMA/comments/198hghs/tried_to_compress_a_model_with_exlv2_the_result/ | false | false | self | 1 | null |
Regarding meta-llama/Llama-2-7b-hf fine Tuning | 1 | [removed] | 2024-01-16T23:11:05 | https://www.reddit.com/r/LocalLLaMA/comments/198h0l7/regarding_metallamallama27bhf_fine_tuning/ | Optimal_Original_815 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 198h0l7 | false | null | t3_198h0l7 | /r/LocalLLaMA/comments/198h0l7/regarding_metallamallama27bhf_fine_tuning/ | false | false | self | 1 | null |
Can ASIC for LLMs be a thing? | 54 | It's probably a stupid question, just wondering because both GPUs and ASICs were used for crypto mining.
Is it possible to design an ASIC for LLMs and what gpu might it theoretically outperform?
Also, might there be a way to repurpose old crypto ASICs for running LLMs? | 2024-01-16T22:50:13 | https://www.reddit.com/r/LocalLLaMA/comments/198ginr/can_asic_for_llms_be_a_thing/ | multiverse_fan | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 198ginr | false | null | t3_198ginr | /r/LocalLLaMA/comments/198ginr/can_asic_for_llms_be_a_thing/ | false | false | self | 54 | null |
Does laptop make sense? | 1 | [removed] | 2024-01-16T22:50:06 | https://www.reddit.com/r/LocalLLaMA/comments/198gikf/does_laptop_make_sense/ | theyseemestackin | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 198gikf | false | null | t3_198gikf | /r/LocalLLaMA/comments/198gikf/does_laptop_make_sense/ | false | false | self | 1 | null |
Looking for something better than TinyLlama, but still fits into 12GB | 10 | Hey guys, new to local LLM this week but after giving it a spin I'm suddenly more interested in AI than I've ever been.
I read https://old.reddit.com/r/LocalLLaMA/comments/18w9hak/llm_comparisontest_brand_new_models_for_2024/
And tried to select something that would work well on my system, which is built as a gaming/... | 2024-01-16T22:44:06 | https://www.reddit.com/r/LocalLLaMA/comments/198gd9c/looking_for_something_better_than_tinyllama_but/ | evranch | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 198gd9c | false | null | t3_198gd9c | /r/LocalLLaMA/comments/198gd9c/looking_for_something_better_than_tinyllama_but/ | false | false | self | 10 | null |
How to improve results when using Dolphin mixtral with BakLLaVa multimodal projector? | 10 | I just tried using BackLLaVa's mmproj file with doplhin mixtral, and it \*almost\* works. It seems to have some clue about the content of the image, and doesn't freak out like when using a llama-based LLaVa projector. But it also hallucinates a lot of details that are not present, even at low temperature.
Anyone m... | 2024-01-16T22:34:30 | https://www.reddit.com/r/LocalLLaMA/comments/198g4uy/how_to_improve_results_when_using_dolphin_mixtral/ | stduhpf | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 198g4uy | false | null | t3_198g4uy | /r/LocalLLaMA/comments/198g4uy/how_to_improve_results_when_using_dolphin_mixtral/ | false | false | 10 | null | |
Help to install python llama cpp binding on Ubuntu | 2 | I am trying to install llama cpp on Ubuntu 23.10 using:
CMAKE_ARGS="-DLLAMA_CUBLAS=on" pip install llama-cpp-python
But I got this error:
[46 lines of output]
*** scikit-build-core 0.7.1 using CMake 3.27.4 (wheel)
*** Configuring CMake...
loading initial cache file /tmp/tmpnqf71... | 2024-01-16T21:44:37 | https://www.reddit.com/r/LocalLLaMA/comments/198ew6y/help_to_install_python_llama_cpp_binding_on_ubuntu/ | celsowm | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 198ew6y | false | null | t3_198ew6y | /r/LocalLLaMA/comments/198ew6y/help_to_install_python_llama_cpp_binding_on_ubuntu/ | false | false | self | 2 | null |
Help to install python llama cpp binding on Ubuntu | 2 | I am trying to install llama cpp on Ubuntu 23.10 using:
CMAKE_ARGS="-DLLAMA_CUBLAS=on" pip install llama-cpp-python
But I got this error:
[46 lines of output]
*** scikit-build-core 0.7.1 using CMake 3.27.4 (wheel)
*** Configuring CMake...
loading initial cache file /tmp/tmpnqf71... | 2024-01-16T21:44:34 | https://www.reddit.com/r/LocalLLaMA/comments/198ew5c/help_to_install_python_llama_cpp_binding_on_ubuntu/ | celsowm | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 198ew5c | false | null | t3_198ew5c | /r/LocalLLaMA/comments/198ew5c/help_to_install_python_llama_cpp_binding_on_ubuntu/ | false | false | self | 2 | null |
If open source models stop coming in and stability.ai shuts down, is trained crowdfunding a possibility? | 50 | **This is a serious discussion.** There's been rumors that Stability AI is on its last legs financially because once you get past the novelty effect and you're not using it for your work, you've used a lot of compute resources from a service provider that basically can't get its training cost back. **Evidently, Meta is... | 2024-01-16T21:42:18 | https://www.reddit.com/r/LocalLLaMA/comments/198eu67/if_open_source_models_stop_coming_in_and/ | RadioSailor | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 198eu67 | false | null | t3_198eu67 | /r/LocalLLaMA/comments/198eu67/if_open_source_models_stop_coming_in_and/ | false | false | self | 50 | null |
Tryed to compress a model with exlv2, now it's stupid. Help? | 3 | The model in question is DiscoLM-120B. Q4KS from TheGuy was so much better than GPTQ, but a 4.5bpw exl2 I made is worse than ever that.
I used all the default parameters for convert.py. Tryed built-in dataset and RP dataset. | 2024-01-16T21:37:49 | https://www.reddit.com/r/LocalLLaMA/comments/198eq84/tryed_to_compress_a_model_with_exlv2_now_its/ | Worldly-Mistake-8147 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 198eq84 | false | null | t3_198eq84 | /r/LocalLLaMA/comments/198eq84/tryed_to_compress_a_model_with_exlv2_now_its/ | false | false | self | 3 | null |
StabilityAI releases StableCode 3B | 1 | [deleted] | 2024-01-16T21:33:23 | https://stability.ai/news/stable-code-2024-llm-code-completion-release | ninjasaid13 | stability.ai | 1970-01-01T00:00:00 | 0 | {} | 198emb9 | false | null | t3_198emb9 | /r/LocalLLaMA/comments/198emb9/stabilityai_releases_stablecode_3b/ | false | false | 1 | {'enabled': False, 'images': [{'id': 'umPi2-T1QxhMr1gSIi0TVMqnrmlQjcFcdxw_is60-ec', 'resolutions': [{'height': 60, 'url': 'https://external-preview.redd.it/l_f3MaK0h0zU3fcMpqYSzgl4d0HQ_xWcOVsp5X-ULws.jpg?width=108&crop=smart&auto=webp&s=fbf5ddde50b2b0e9ea74b7701f0ae8a80db147fb', 'width': 108}, {'height': 121, 'url': 'h... | |
Rent gpu and speech tò speech | 1 | [removed] | 2024-01-16T21:08:41 | https://www.reddit.com/r/LocalLLaMA/comments/198e057/rent_gpu_and_speech_tò_speech/ | Independent-Bill-770 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 198e057 | false | null | t3_198e057 | /r/LocalLLaMA/comments/198e057/rent_gpu_and_speech_tò_speech/ | false | false | self | 1 | null |
Stable Code 3B: Coding on the Edge — Stability AI | 100 | [https://stability.ai/news/stable-code-2024-llm-code-completion-release](https://stability.ai/news/stable-code-2024-llm-code-completion-release)
​
>Stable Code 3B is a newly released Large Language Model (LLM) with 3 billion parameters. It's designed for accurate and responsive code completion, even outperfo... | 2024-01-16T21:07:45 | https://www.reddit.com/r/LocalLLaMA/comments/198dzas/stable_code_3b_coding_on_the_edge_stability_ai/ | ali0une | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 198dzas | false | null | t3_198dzas | /r/LocalLLaMA/comments/198dzas/stable_code_3b_coding_on_the_edge_stability_ai/ | false | false | self | 100 | {'enabled': False, 'images': [{'id': 'umPi2-T1QxhMr1gSIi0TVMqnrmlQjcFcdxw_is60-ec', 'resolutions': [{'height': 60, 'url': 'https://external-preview.redd.it/l_f3MaK0h0zU3fcMpqYSzgl4d0HQ_xWcOVsp5X-ULws.jpg?width=108&crop=smart&auto=webp&s=fbf5ddde50b2b0e9ea74b7701f0ae8a80db147fb', 'width': 108}, {'height': 121, 'url': 'h... |
Regarding meta-llama/Llama-2-7b-hf fine Tuning | 2 | I am trying to fine tune meta-llama/Llama-2-7b-hf on custom dataset using Lora . Post training I am trying to save the model on the disk than to push to huggingface:
trainer.save_model(output_dir)
tokenizer.save_pretrained(output_dir)
model.config.save_pretrained(output_dir)
for inference I am loadi... | 2024-01-16T20:46:44 | https://www.reddit.com/r/LocalLLaMA/comments/198dfp0/regarding_metallamallama27bhf_fine_tuning/ | Optimal_Original_815 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 198dfp0 | false | null | t3_198dfp0 | /r/LocalLLaMA/comments/198dfp0/regarding_metallamallama27bhf_fine_tuning/ | false | false | self | 2 | null |
Which Macbook Pro to buy for running an LLM locally? I created a buyer's guide to help you decide. | 8 | I am currently contemplating buying a new Macbook Pro as my old Intel-based one is getting older. However, I wanted to be able to run LLMs locally, just for fun. Figuring out what hardware requirements I need for that was complicated. [I created this blog post as a helping guide for others](http://fabian-kostadinov.git... | 2024-01-16T20:32:21 | https://www.reddit.com/r/LocalLLaMA/comments/198d2z6/which_macbook_pro_to_buy_for_running_an_llm/ | fabkosta | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 198d2z6 | false | null | t3_198d2z6 | /r/LocalLLaMA/comments/198d2z6/which_macbook_pro_to_buy_for_running_an_llm/ | false | false | self | 8 | null |
Error deploying thebloke/cuda11.8.0-ubuntu22.04-oneclick to A100 | 1 | [removed] | 2024-01-16T20:14:47 | https://www.reddit.com/r/LocalLLaMA/comments/198cn0p/error_deploying/ | keyboardwarrriorr | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 198cn0p | false | null | t3_198cn0p | /r/LocalLLaMA/comments/198cn0p/error_deploying/ | false | false | self | 1 | null |
GGUF vs AWQ vs GGML | 5 | Maybe it's a noob question but i still don't understand the quality difference.
Is a 4bit AWQ better in terms of quality than a 5 or 6 bit GGUF?
Can't GGUF use the quantization system of AWQ to give more space to most activated neurons?
AWQ file size is really small compared to other quants, i'm trying to compare th... | 2024-01-16T20:00:04 | https://www.reddit.com/r/LocalLLaMA/comments/198c9ru/gguf_vs_awq_vs_ggml/ | infiniteContrast | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 198c9ru | false | null | t3_198c9ru | /r/LocalLLaMA/comments/198c9ru/gguf_vs_awq_vs_ggml/ | false | false | self | 5 | null |
LLM cross-session privacy leak: “A Flaw in Millions of Apple, AMD, and Qualcomm GPUs Could Expose AI Data” | 2 | 2024-01-16T19:55:40 | https://www.wired.com/story/leftoverlocals-gpu-vulnerability-generative-ai/ | dummypatty | wired.com | 1970-01-01T00:00:00 | 0 | {} | 198c637 | false | null | t3_198c637 | /r/LocalLLaMA/comments/198c637/llm_crosssession_privacy_leak_a_flaw_in_millions/ | false | false | 2 | {'enabled': False, 'images': [{'id': 'gwDw3dAe9KfmA4nTB_wI9HGdH6FuSJrkwZYo_bkcc50', 'resolutions': [{'height': 56, 'url': 'https://external-preview.redd.it/XXc54-7LdYpxq7EKIPkR0hoHQ3i-evK2J9VGNDhN5tA.jpg?width=108&crop=smart&auto=webp&s=9328eab189ae03e5557000bfe20a51c2bbdf3f80', 'width': 108}, {'height': 113, 'url': 'h... | ||
Nvidia Parakeet Rnnt vs CTC | 1 | [removed] | 2024-01-16T19:21:41 | https://www.reddit.com/r/LocalLLaMA/comments/198bbuf/nvidia_parakeet_rnnt_vs_ctc/ | FrenchSouch | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 198bbuf | false | null | t3_198bbuf | /r/LocalLLaMA/comments/198bbuf/nvidia_parakeet_rnnt_vs_ctc/ | false | false | self | 1 | null |
The IQ Test That AI Can’t Pass | 1 | [https://www.johndcook.com/blog/2024/01/16/the-iq-test-ai-cant-pass/](https://www.johndcook.com/blog/2024/01/16/the-iq-test-ai-cant-pass/)
​
>The Abstraction and Reasoning Corpus (ARC) benchmark is a test designed to evaluate intelligence in performing tasks that are new or rarely encountered. It consists of i... | 2024-01-16T19:13:35 | https://www.reddit.com/r/LocalLLaMA/comments/198b4o3/the_iq_test_that_ai_cant_pass/ | ali0une | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 198b4o3 | false | null | t3_198b4o3 | /r/LocalLLaMA/comments/198b4o3/the_iq_test_that_ai_cant_pass/ | false | false | self | 1 | null |
Is there anything that can complete with GitHub Copilot right now I can run in VS Code? | 29 | Is there anything that can complete with GitHub Copilot right now I can run in VS Code?
I was looking at Wizard Coder and Deepseek Coder that have been recommended here, or at least had positive posts related to them. I do use Python, but I also want strong support for things like JS and Vue. | 2024-01-16T18:57:39 | https://www.reddit.com/r/LocalLLaMA/comments/198aq2l/is_there_anything_that_can_complete_with_github/ | SillyLilBear | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 198aq2l | false | null | t3_198aq2l | /r/LocalLLaMA/comments/198aq2l/is_there_anything_that_can_complete_with_github/ | false | false | self | 29 | null |
MoE based LLM ideal for edge cases? | 1 | Is there a MoE based LLM which has around 3B parameters or even 7B (in total) which can be well suited to be ran in edge scenarios given they should use not all of the parameters in infernece time and so be runnable on low capacity cpus? | 2024-01-16T18:48:12 | https://www.reddit.com/r/LocalLLaMA/comments/198ahi9/moe_based_llm_ideal_for_edge_cases/ | pussy_artist | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 198ahi9 | false | null | t3_198ahi9 | /r/LocalLLaMA/comments/198ahi9/moe_based_llm_ideal_for_edge_cases/ | false | false | self | 1 | null |
I have a Mac Studio M2 Ultra, 192GB RAM & 76 GPU cores. AMA | 1 | [removed] | 2024-01-16T18:43:51 | https://www.reddit.com/r/LocalLLaMA/comments/198adis/i_have_a_mac_studio_m2_ultra_192gb_ram_76_gpu/ | macstudiouser | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 198adis | false | null | t3_198adis | /r/LocalLLaMA/comments/198adis/i_have_a_mac_studio_m2_ultra_192gb_ram_76_gpu/ | false | false | self | 1 | null |
New "LeftoverLocals" vulnerability for certain Apple, Qualcomm, AMD, and Imagination GPUs | 35 | https://blog.trailofbits.com/2024/01/16/leftoverlocals-listening-to-llm-responses-through-leaked-gpu-local-memory/
"By recovering local memory—an optimized GPU memory region—we were able to build a PoC where an attacker can listen into another user’s interactive LLM session (e.g., llama.cpp) across process or containe... | 2024-01-16T18:43:07 | https://www.reddit.com/r/LocalLLaMA/comments/198acw4/new_leftoverlocals_vulnerability_for_certain/ | cfoster0 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 198acw4 | false | null | t3_198acw4 | /r/LocalLLaMA/comments/198acw4/new_leftoverlocals_vulnerability_for_certain/ | false | false | self | 35 | {'enabled': False, 'images': [{'id': 'FKy71tw108kWrCDkqrs2ENllMk0ACRqEAwnPzw1-nbI', 'resolutions': [{'height': 76, 'url': 'https://external-preview.redd.it/S9Su6lWgNg_HVjQhTT6EAn-Bly6_N3WtML33F8NZFoQ.jpg?width=108&crop=smart&auto=webp&s=92484137f4f7b7a6cd764fec67c7d70f661ca922', 'width': 108}, {'height': 152, 'url': 'h... |
Experiments with RNG Dequantization | 12 | So, I was interested in messing around with the quantization code recently for llama.cpp.
https://preview.redd.it/0h4vgxn95ucc1.png?width=1102&format=png&auto=webp&s=3fc36eb43a4dcca472cd6dd7b927ef6e23da70e1
In the image domain, dithering is typically used to add some noise when quantizing. This is done so that color ... | 2024-01-16T18:08:18 | https://www.reddit.com/r/LocalLLaMA/comments/1989gx9/experiments_with_rng_dequantization/ | kindacognizant | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 1989gx9 | false | {'oembed': {'author_name': 'vinesauce', 'author_url': 'https://www.youtube.com/@vinesauce', 'height': 200, 'html': '<iframe width="356" height="200" src="https://www.youtube.com/embed/OvNDcVRlyYk?feature=oembed&enablejsapi=1" frameborder="0" allow="accelerometer; autoplay; clipboard-write; encrypted-media; gyroscope; p... | t3_1989gx9 | /r/LocalLLaMA/comments/1989gx9/experiments_with_rng_dequantization/ | false | false | 12 | {'enabled': False, 'images': [{'id': 'mgQt-EyW2FoWtUxjbzsf5i9Hd4FWudnl0I-K4kGcs94', 'resolutions': [{'height': 81, 'url': 'https://external-preview.redd.it/NF-BIhKHiRcrLBzoyDtMkPolYawbOulKVZkDRtL67xw.jpg?width=108&crop=smart&auto=webp&s=228d44bf6e468826380191a0dcf2bcd72a82f1cd', 'width': 108}, {'height': 162, 'url': 'h... | |
Teaching a LLM a new programming language? | 8 | How could I teach a LLM a new programming language?
It is quite niche, albeit there is a *lot* of varied pre-existing code and documentation for it (I can likely find *gigabytes* worth of code in it), but it isn't in datasets such as StarCoder and such. How could I go about teaching an LLM it? | 2024-01-16T17:53:15 | https://www.reddit.com/r/LocalLLaMA/comments/198931x/teaching_a_llm_a_new_programming_language/ | Absolucyyy | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 198931x | false | null | t3_198931x | /r/LocalLLaMA/comments/198931x/teaching_a_llm_a_new_programming_language/ | false | false | self | 8 | null |
Integrate Natural Language to SQL (NL-to-SQL) directly into your product. | 2 | Asking questions from structured databases, referred to as the NL-to-SQL task, has posed a challenge even for advanced language models like GPT-4. This challenge arises because these models lack information about how data is organized within your database. Furthermore, crafting SQL queries, even for seasoned data scien... | 2024-01-16T17:48:08 | https://www.reddit.com/r/LocalLLaMA/comments/1988ycg/integrate_natural_language_to_sql_nltosql/ | Beneficial-Engine-72 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 1988ycg | false | null | t3_1988ycg | /r/LocalLLaMA/comments/1988ycg/integrate_natural_language_to_sql_nltosql/ | false | false | self | 2 | {'enabled': False, 'images': [{'id': 'BVE9FFOog6ncS-6qm_CVlg2T9G_lLoWH_qEM7fdqIKY', 'resolutions': [{'height': 57, 'url': 'https://external-preview.redd.it/GrxWdMZpfB8knS41qS-NvXlX0yAZz4RbzSK1S1m0O60.jpg?width=108&crop=smart&auto=webp&s=215e27675906622ac55908dd6ccc5d143d4e35fd', 'width': 108}, {'height': 114, 'url': 'h... |
With equal total VRAM: 2 GPUS VS. 1 GPU? | 9 | I had a hard time coming up with a title that matched what I wanted to ask, I apologize.
I've just read this review ([https://www.theverge.com/24039832/nvidia-rtx-4070-super-review-gpu-graphics-card-benchmark-test](https://www.theverge.com/24039832/nvidia-rtx-4070-super-review-gpu-graphics-card-benchmark-test)) of th... | 2024-01-16T17:40:24 | https://www.reddit.com/r/LocalLLaMA/comments/1988rcz/with_equal_total_vram_2_gpus_vs_1_gpu/ | mmmmmmaaaaattttt | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 1988rcz | false | null | t3_1988rcz | /r/LocalLLaMA/comments/1988rcz/with_equal_total_vram_2_gpus_vs_1_gpu/ | false | false | self | 9 | {'enabled': False, 'images': [{'id': 'ouTRXvRuFcXSue22jAetYGIJEwvhfKwiB0XCbmdIVM0', 'resolutions': [{'height': 56, 'url': 'https://external-preview.redd.it/aPzWO4Qz4eptYT8ZqJ8pP5Eautgeaj-_i9oJoDTc0Uk.jpg?width=108&crop=smart&auto=webp&s=b52666d9d92e8b8410825ee9e036534458b7bf85', 'width': 108}, {'height': 113, 'url': 'h... |
INSIDER NEWS! | 1 | Just got word that the disruptions everyone is seeing with OpenAI's service is a result of them re-dedicating resources to train GPT5. Get ready folks. | 2024-01-16T17:37:20 | https://www.reddit.com/r/LocalLLaMA/comments/1988omp/insider_news/ | After-Temperature253 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 1988omp | false | null | t3_1988omp | /r/LocalLLaMA/comments/1988omp/insider_news/ | true | false | spoiler | 1 | null |
An expert and a jester in a trenchcoat: orthogonal-2x7B | 11 | I've spent the weekend messing with model combinations with smaller mixes (4x8) but none really gave expected results, almost always degrading the performances, the only one decent at the end of various testing was this one: [orthogonal-2x7B](https://huggingface.co/LoSboccacc/orthogonal-2x7B) which is a merge of mistr... | 2024-01-16T17:29:12 | https://www.reddit.com/r/LocalLLaMA/comments/1988h8w/an_expert_and_a_jester_in_a_trenchcoat/ | LoSboccacc | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 1988h8w | false | null | t3_1988h8w | /r/LocalLLaMA/comments/1988h8w/an_expert_and_a_jester_in_a_trenchcoat/ | false | false | self | 11 | {'enabled': False, 'images': [{'id': 'G0impekBdJxA2BJoWo2rrQtsStXNwaVh12ArYCdzOG4', 'resolutions': [{'height': 58, 'url': 'https://external-preview.redd.it/Zfe94Sazx6EulXn_PGoRvbs7x5jYFbtt4ZFpwafRT8Q.jpg?width=108&crop=smart&auto=webp&s=eaabc442823eb62f3cda7210352f092ad6061360', 'width': 108}, {'height': 116, 'url': 'h... |
APAR: LLMs Can Do Auto-Parallel Auto-Regressive Decoding - ("... when combined with speculative decoding, the speed-up can reach up to 4x. ... a throughput increase of 20-70% and a latency reduce of 20-35%...") | 36 | **Paper**: [https://arxiv.org/abs/2401.06761](https://arxiv.org/abs/2401.06761)
**Abstract**:
>The massive adoption of large language models (LLMs) demands efficient deployment strategies. However, the auto-regressive decoding process, which is fundamental to how most LLMs generate text, poses challenges to ach... | 2024-01-16T17:12:09 | https://www.reddit.com/r/LocalLLaMA/comments/19881lf/apar_llms_can_do_autoparallel_autoregressive/ | APaperADay | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 19881lf | false | null | t3_19881lf | /r/LocalLLaMA/comments/19881lf/apar_llms_can_do_autoparallel_autoregressive/ | false | false | self | 36 | null |
Local Transcription/Translation with SeamlessM4T | 28 | Hi all, this is not per-say an LLM, but I figured it could interest some of you here.
FAIR released in November a Speech/Text translation model: [SeamlessM4T](https://ai.meta.com/research/seamless-communication/). With my teammate we made a GGML port of the model, to allow running it locally without Python. (If you ju... | 2024-01-16T16:41:40 | https://www.reddit.com/r/LocalLLaMA/comments/19879wk/local_transcriptiontranslation_with_seamlessm4t/ | gwenzek | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 19879wk | false | null | t3_19879wk | /r/LocalLLaMA/comments/19879wk/local_transcriptiontranslation_with_seamlessm4t/ | false | false | self | 28 | {'enabled': False, 'images': [{'id': 'h_C0aTx1zZ2LbZLhgKw4iMYwyLGUu99Yc17isI8ogME', 'resolutions': [{'height': 60, 'url': 'https://external-preview.redd.it/owEvkLw_moZXaFv7_gI34F_D_Zz4DGxqECQIJifUMZ8.jpg?width=108&crop=smart&auto=webp&s=56923bdb13994baac1b22a9acb26dbfc24a2ffb5', 'width': 108}, {'height': 121, 'url': 'h... |
Transformers are Multi-State RNNs - ("Our findings shed light on the inter-working of transformers, and their connections to RNNs. They also have practical value—they can dramatically reduce the LLM cache size by up to 88%.") | 106 | **Paper**: [https://arxiv.org/abs/2401.06104](https://arxiv.org/abs/2401.06104)
**Code**: [https://github.com/schwartz-lab-NLP/TOVA](https://github.com/schwartz-lab-NLP/TOVA)
**Abstract**:
>Transformers are considered conceptually different compared to the previous generation of state-of-the-art NLP models - recu... | 2024-01-16T16:22:26 | https://www.reddit.com/r/LocalLLaMA/comments/1986t3w/transformers_are_multistate_rnns_our_findings/ | APaperADay | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 1986t3w | false | null | t3_1986t3w | /r/LocalLLaMA/comments/1986t3w/transformers_are_multistate_rnns_our_findings/ | false | false | self | 106 | null |
PESC - Converting Pretrained Models to MoE via LoRA fine tuning | 30 | Now this is something interesting , they propose a method to convert dense LLMs to MoE without any significant parameter updates via QLoRA also very memory efficient, introduced Camelidae LLM series saying that it is outperforming GPT-3.5.
Ig this will be something like a game changer like when LoRA was dropped. Though... | 2024-01-16T16:05:51 | https://arxiv.org/abs/2401.02731 | MysticShadow427 | arxiv.org | 1970-01-01T00:00:00 | 0 | {} | 1986edw | false | null | t3_1986edw | /r/LocalLLaMA/comments/1986edw/pesc_converting_pretrained_models_to_moe_via_lora/ | false | false | default | 30 | null |
Question. Can you achieve JSON output by modifying the model execution engine to mask tokens against JSON state? | 4 | I'd really love for local models to be able to run as agents, but this needs strict JSON output (or other easily parsable scheme).
Fine-tuning feels like a random way to do it. Instead, the engine could be modified so that rather than simply choosing the logit with the highest score, you first mask out logits for toke... | 2024-01-16T15:31:47 | https://www.reddit.com/r/LocalLLaMA/comments/1985kxr/question_can_you_achieve_json_output_by_modifying/ | debauch3ry | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 1985kxr | false | null | t3_1985kxr | /r/LocalLLaMA/comments/1985kxr/question_can_you_achieve_json_output_by_modifying/ | false | false | self | 4 | null |
Subsets and Splits
No community queries yet
The top public SQL queries from the community will appear here once available.