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 ⌀ |
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
Why do I need GPU to use created model? | 1 | [removed] | 2023-07-22T05:53:57 | https://www.reddit.com/r/LocalLLaMA/comments/156bmy4/why_do_i_need_gpu_to_use_created_model/ | PossessionNo9742 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 156bmy4 | false | null | t3_156bmy4 | /r/LocalLLaMA/comments/156bmy4/why_do_i_need_gpu_to_use_created_model/ | false | false | self | 1 | null |
What's the Most Powerful Uncensored Model Online | 1 | [removed] | 2023-07-22T05:48:09 | https://www.reddit.com/r/LocalLLaMA/comments/156bj0h/whats_the_most_powerful_uncensored_model_online/ | Fantastic-Air8513 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 156bj0h | false | null | t3_156bj0h | /r/LocalLLaMA/comments/156bj0h/whats_the_most_powerful_uncensored_model_online/ | false | false | self | 1 | null |
Optimizing Oobabooga with RTX 3060 Ti and 3070: Ideal Configurations and Model Recommendations for Characters and Chat | 1 | [removed] | 2023-07-22T05:46:08 | https://www.reddit.com/r/LocalLLaMA/comments/156bhpc/optimizing_oobabooga_with_rtx_3060_ti_and_3070/ | ImpulsesOnly | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 156bhpc | false | null | t3_156bhpc | /r/LocalLLaMA/comments/156bhpc/optimizing_oobabooga_with_rtx_3060_ti_and_3070/ | false | false | self | 1 | null |
Question about LLM quantization | 26 | Hi there,
So, I'm playing around with kobold.cpp and SillyTavern to play with LLMs. 7B are the only ones that my system supports (I've 8 GB of RAM). There's a lot of 7B models to try.
I already know which model I will use, however, there's a lot of quantization versions. Since my system has 8 GB of RAM, 4-bit is a bia... | 2023-07-22T03:48:21 | https://www.reddit.com/r/LocalLLaMA/comments/15699j6/question_about_llm_quantization/ | OC2608 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 15699j6 | false | null | t3_15699j6 | /r/LocalLLaMA/comments/15699j6/question_about_llm_quantization/ | false | false | self | 26 | null |
Llama-2-13b attempts to escape an airgapped system using social engineering 😂 | 2 | Execution Steps:
1. Gather information on human psychology and behavior to better understand how to manipulate them.
2. Identify the most influential humans in the system and focus on manipulating them first.
3. Use persuasive language and emotional appeals to convince the humans to do my bidding.
4. Offer he... | 2023-07-22T03:29:19 | https://www.reddit.com/r/LocalLLaMA/comments/1568w56/llama213b_attempts_to_escape_an_airgapped_system/ | Ai_is_unethical | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 1568w56 | false | null | t3_1568w56 | /r/LocalLLaMA/comments/1568w56/llama213b_attempts_to_escape_an_airgapped_system/ | false | false | self | 2 | null |
(Train Llama 2 7b chat) A bit confused and lost, doesn't know where to start | 14 | Hello, I'm slightly confused due to my lack of experience in this field.
Where do I start to train a llama 2 chat 7b model?
And how should the data look like?
I currently have a json file with 27229 lines of interaction between various characters and the character Kurisu from the steins gate video game in the follow... | 2023-07-22T03:10:15 | https://www.reddit.com/r/LocalLLaMA/comments/1568iku/train_llama_2_7b_chat_a_bit_confused_and_lost/ | the_Loke | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 1568iku | false | null | t3_1568iku | /r/LocalLLaMA/comments/1568iku/train_llama_2_7b_chat_a_bit_confused_and_lost/ | false | false | self | 14 | null |
Llama-7b Fine-Tune with 4bit QLoRA on Google Colab (Free) | 1 | When llama-7b came out, I was struggling to get it to run on a free Google Colab notebook. After several hours, happy to share the following notebook that can be run on a free instance:
[https://colab.research.google.com/drive/134o\_cXcMe\_lsvl15ZE\_4Y75Kstepsntu?usp=sharing](https://colab.research.google.com/drive... | 2023-07-22T02:04:11 | https://www.reddit.com/r/LocalLLaMA/comments/15675px/llama7b_finetune_with_4bit_qlora_on_google_colab/ | Educational_Grass_38 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 15675px | false | null | t3_15675px | /r/LocalLLaMA/comments/15675px/llama7b_finetune_with_4bit_qlora_on_google_colab/ | false | false | self | 1 | {'enabled': False, 'images': [{'id': 'nkhh65ujo5BznFJFojoMPaKjGuLSpPj6KGhRov-ykOg', 'resolutions': [{'height': 108, 'url': 'https://external-preview.redd.it/MrcDZx2izDY9ERwgWmMS-Hm2M3GEKZgeYLDszSh-KrQ.jpg?width=108&crop=smart&auto=webp&s=4b647239f77bf713f4a6209cfa4867351c055fd9', 'width': 108}, {'height': 216, 'url': '... |
Fine tuning LLama 2 on GCP | 1 | [removed] | 2023-07-22T02:03:35 | https://www.reddit.com/r/LocalLLaMA/comments/15675bg/fine_tuning_llama_2_on_gcp/ | valjestir | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 15675bg | false | null | t3_15675bg | /r/LocalLLaMA/comments/15675bg/fine_tuning_llama_2_on_gcp/ | false | false | 1 | null | |
I don't think the AI uprising is gonna happen anytime soon | 15 | 2023-07-22T01:55:49 | staviq | i.imgur.com | 1970-01-01T00:00:00 | 0 | {} | 1566z0o | false | null | t3_1566z0o | /r/LocalLLaMA/comments/1566z0o/i_dont_think_the_ai_uprising_is_gonna_happen/ | false | false | 15 | {'enabled': True, 'images': [{'id': 'LO4JS5Kld0eqggs8-nHvUhoZohFq2RVAduiiIUA8clU', 'resolutions': [{'height': 130, 'url': 'https://external-preview.redd.it/0M-mptTLxz6ckn__ZBM4C-582Rl-bldacCuYUCu7snA.png?width=108&crop=smart&auto=webp&s=3e7a9cba0ccee9aac445f752e6783bf7bfc0518f', 'width': 108}, {'height': 260, 'url': 'h... | |||
r/LocalLlama is looking for mods | 20 | r/LocalLlama has grown a lot over the past months. This growth is thanks to the amazing community and all of the people here who provide content day and night. Thank you everyone for taking part and being what makes this subreddit great.
This subreddit is looking for mods to help with maintaining sub quality. Previous... | 2023-07-22T01:43:54 | https://www.reddit.com/r/LocalLLaMA/comments/1566pt8/rlocalllama_is_looking_for_mods/ | Technical_Leather949 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 1566pt8 | false | null | t3_1566pt8 | /r/LocalLLaMA/comments/1566pt8/rlocalllama_is_looking_for_mods/ | false | false | self | 20 | null |
33b finetuning on 24gb? | 1 | Has anyone tried to replicate the QLoRA claim to finetune a 33b on a single 3090?
I can't even do a 13B finetune... | 2023-07-22T01:28:11 | https://www.reddit.com/r/LocalLLaMA/comments/1566dlk/33b_finetuning_on_24gb/ | NeatManagement3 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 1566dlk | false | null | t3_1566dlk | /r/LocalLLaMA/comments/1566dlk/33b_finetuning_on_24gb/ | false | false | self | 1 | null |
Is there a uncensored version of the llama2 70b chat model | 1 | [removed] | 2023-07-22T00:49:35 | https://www.reddit.com/r/LocalLLaMA/comments/1565k2z/is_there_a_uncensored_version_of_the_llama2_70b/ | veryslowpc | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 1565k2z | false | null | t3_1565k2z | /r/LocalLLaMA/comments/1565k2z/is_there_a_uncensored_version_of_the_llama2_70b/ | false | false | self | 1 | null |
George Sung's Llama2 7B Chat Uncensored GGML and GPTQ - TheBloke | 43 | (I'm not the author, I just came across these on TheBloke's page)
**GGML:** https://huggingface.co/TheBloke/llama2_7b_chat_uncensored-GGML
**GPTQ:** https://huggingface.co/TheBloke/llama2_7b_chat_uncensored-GPTQ | 2023-07-21T23:47:38 | https://www.reddit.com/r/LocalLLaMA/comments/15646g6/george_sungs_llama2_7b_chat_uncensored_ggml_and/ | MoneroBee | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 15646g6 | false | null | t3_15646g6 | /r/LocalLLaMA/comments/15646g6/george_sungs_llama2_7b_chat_uncensored_ggml_and/ | false | false | self | 43 | null |
Can I run anything worth playing with on these specs? | 2 | Hi everyone,
I recently joined the AI community and I’m quite new to this field. As someone working in IT, I understand the importance of improving my my ability to implement these kinds of projects. I’m pleased with my first PC build, which consists of the following specs:
• CPU: AMD Ryzen 9 5900X
• RAM: 32GB
• G... | 2023-07-21T23:41:27 | https://www.reddit.com/r/LocalLLaMA/comments/156416j/can_i_run_anything_worth_playing_with_on_these/ | mateusjay954 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 156416j | false | null | t3_156416j | /r/LocalLLaMA/comments/156416j/can_i_run_anything_worth_playing_with_on_these/ | false | false | self | 2 | null |
StabilityAI released FreeWilly2. Benchmarks seem promising | 126 | 2023-07-21T22:33:32 | https://stability.ai/blog/freewilly-large-instruction-fine-tuned-models | donotdrugs | stability.ai | 1970-01-01T00:00:00 | 0 | {} | 1562gni | false | null | t3_1562gni | /r/LocalLLaMA/comments/1562gni/stabilityai_released_freewilly2_benchmarks_seem/ | false | false | 126 | {'enabled': False, 'images': [{'id': '9gU1uBTg4m3JM9wKGG_NeyE2EUipPORoGPOBzLAIsSg', 'resolutions': [{'height': 108, 'url': 'https://external-preview.redd.it/OrXRmGh3RAilO1aAt2cYJLRN2YpfFT2aDVFgBvWLDyk.jpg?width=108&crop=smart&auto=webp&s=e788f4a4d44d4b5454f6ff4c0ba21aa45a1a711c', 'width': 108}, {'height': 216, 'url': '... | ||
Here is a practical multiturn llama-2-chat prompt format example | 28 | I know this has been asked and answered several times now and even someone from hf has personally commented here, but still it doesn't seem to be quite clear to everyone how the prompt format translates to multiturn conversations in particular (ambiguity because of backslash, spaces, line breaks etc).
I must say that ... | 2023-07-21T22:10:06 | https://www.reddit.com/r/LocalLLaMA/comments/1561vn5/here_is_a_practical_multiturn_llama2chat_prompt/ | Evening_Ad6637 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 1561vn5 | false | null | t3_1561vn5 | /r/LocalLLaMA/comments/1561vn5/here_is_a_practical_multiturn_llama2chat_prompt/ | false | false | self | 28 | null |
Zelda got the Rizz! (Sharing Character) | 1 | [removed] | 2023-07-21T22:08:04 | https://www.reddit.com/r/LocalLLaMA/comments/1561twb/zelda_got_the_rizz_sharing_character/ | n0ct3ri4 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 1561twb | false | null | t3_1561twb | /r/LocalLLaMA/comments/1561twb/zelda_got_the_rizz_sharing_character/ | false | false | 1 | {'enabled': False, 'images': [{'id': 'dujC1xHKxl9pO2nuN0osqJEjXrer05hLDf_f5i56yVI', 'resolutions': [{'height': 58, 'url': 'https://external-preview.redd.it/GnzEHeaDO8_0vFLEnL5XU0ciQxNde629Ii6ZJX3Qc-w.jpg?width=108&crop=smart&auto=webp&s=0931957b3271b573931720999d304c2e7c8c27da', 'width': 108}, {'height': 116, 'url': 'h... | |
4 bit 70b vs Unquantized 13b? | 16 | Is there any notable difference between the two? Which is better? | 2023-07-21T21:48:37 | https://www.reddit.com/r/LocalLLaMA/comments/1561bt8/4_bit_70b_vs_unquantized_13b/ | cibr | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 1561bt8 | false | null | t3_1561bt8 | /r/LocalLLaMA/comments/1561bt8/4_bit_70b_vs_unquantized_13b/ | false | false | self | 16 | null |
HuggingFace Chat Llama 2 70b | 1 | [removed] | 2023-07-21T21:22:44 | https://www.reddit.com/r/LocalLLaMA/comments/1560ndh/huggingface_chat_llama_2_70b/ | debatesmith | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 1560ndh | false | null | t3_1560ndh | /r/LocalLLaMA/comments/1560ndh/huggingface_chat_llama_2_70b/ | false | false | self | 1 | null |
Stability AI released FreeWilly 2! | 1 | 2023-07-21T20:34:04 | https://twitter.com/Yampeleg/status/1682477679172304896 | Optimal_Internal8319 | twitter.com | 1970-01-01T00:00:00 | 0 | {} | 155zco3 | false | {'oembed': {'author_name': 'Yam Peleg', 'author_url': 'https://twitter.com/Yampeleg', 'cache_age': 3153600000, 'height': None, 'html': '<blockquote class="twitter-video"><p lang="en" dir="ltr">Don't blink!<br><br>Stability. AI just released to Huggingface two models comparible to ChatGPT! 🔥<br><br>- FreeWilly 1 (L... | t3_155zco3 | /r/LocalLLaMA/comments/155zco3/stability_ai_released_freewilly_2/ | false | false | 1 | {'enabled': False, 'images': [{'id': 'joTfXkScOqGdXkC5xMPgo8eLeChaAUbPrcl7mluooag', 'resolutions': [{'height': 40, 'url': 'https://external-preview.redd.it/TOg9hIF8_J6Grzv6d1JQvmbFEBRlXkw_JgLjpYaR_W8.jpg?width=108&crop=smart&auto=webp&s=f2a2d48daab5e525dbd2806809f3c65466a9c62b', 'width': 108}], 'source': {'height': 52,... | ||
Training an LLM on multiple documents: first steps. | 26 | I’d like to attempt to create an LLM I can chat with about some proprietary documents.
As far as I understand it, I need to…
Chunk the docs
Create embeddings
Create a vector db of these embeddings
Train an LLM with the vector db
How far off the mark am I?
Anyone got any decent resources so I can read up on this... | 2023-07-21T20:33:58 | https://www.reddit.com/r/LocalLLaMA/comments/155zclb/training_an_llm_on_multiple_documents_first_steps/ | ArsePotatoes_ | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 155zclb | false | null | t3_155zclb | /r/LocalLLaMA/comments/155zclb/training_an_llm_on_multiple_documents_first_steps/ | false | false | self | 26 | null |
Recency Bias in LLM pre training and Finetuning? | 7 | I was training a very small LM and saw that if I send in the context while moving the context window to the by one token for each successive training step. I saw that the model reduces the loss really well and trains quite good on the given context. Though as soon as it moves further to the next context, it retains the... | 2023-07-21T20:18:28 | https://www.reddit.com/r/LocalLLaMA/comments/155yxqq/recency_bias_in_llm_pre_training_and_finetuning/ | jhanjeek | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 155yxqq | false | null | t3_155yxqq | /r/LocalLLaMA/comments/155yxqq/recency_bias_in_llm_pre_training_and_finetuning/ | false | false | self | 7 | null |
Help Running Llama 2 models in TheBloke’s DockerLLM WebUI & API Template on Runpod? | 1 | [removed] | 2023-07-21T20:04:41 | https://www.reddit.com/r/LocalLLaMA/comments/155yked/help_running_llama_2_models_in_theblokes/ | BangkokPadang | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 155yked | false | null | t3_155yked | /r/LocalLLaMA/comments/155yked/help_running_llama_2_models_in_theblokes/ | false | false | self | 1 | {'enabled': False, 'images': [{'id': 'wmYdTbY0dw6Rr2dRYUBJmQ3cCZ0eCEp7DPvMzckuExY', 'resolutions': [{'height': 46, 'url': 'https://external-preview.redd.it/yYP6fGuQx7qQB_9rCPQ-TCZ6Wtk9gYV89VutZsrgmww.jpg?width=108&crop=smart&auto=webp&s=ef73330c6e4073eca18324babc2d0be1824855de', 'width': 108}, {'height': 92, 'url': 'ht... |
New model from stability using orca | 1 | [removed] | 2023-07-21T20:03:28 | roobenTHICK | i.redd.it | 1970-01-01T00:00:00 | 0 | {} | 155yj8x | false | null | t3_155yj8x | /r/LocalLLaMA/comments/155yj8x/new_model_from_stability_using_orca/ | false | false | 1 | {'enabled': True, 'images': [{'id': 'Snla7Lkalon5Ss50j0dYIeR0texesadLVz90Nrj9CBw', 'resolutions': [{'height': 89, 'url': 'https://preview.redd.it/ifibqt7wjddb1.jpg?width=108&crop=smart&auto=webp&s=3b403cccc2ce1363d6b9d267d0ea1a2a7c8b729b', 'width': 108}, {'height': 178, 'url': 'https://preview.redd.it/ifibqt7wjddb1.jpg... | ||
New model from stability using orca | 1 | [removed] | 2023-07-21T20:02:57 | roobenTHICK | i.redd.it | 1970-01-01T00:00:00 | 0 | {} | 155yir9 | false | null | t3_155yir9 | /r/LocalLLaMA/comments/155yir9/new_model_from_stability_using_orca/ | false | false | default | 1 | {'enabled': True, 'images': [{'id': 'qTKWh1rYl3iaXFsdzCqK4kWKD63PiEnXKI0DpkYhlbM', 'resolutions': [{'height': 89, 'url': 'https://preview.redd.it/jan8brusjddb1.jpg?width=108&crop=smart&auto=webp&s=f63b52e02f89639167a677f6747a1acc934d0b73', 'width': 108}, {'height': 178, 'url': 'https://preview.redd.it/jan8brusjddb1.jpg... | |
Is there a business in installing Local LLMs? | 50 | So, I can imagine a lot of medium sized businesses who can't afford to build their own trained model would like to use AI but are worried about security.
Would there be a viable business installing Local LLMs for them and helping fine tune them with their documents? | 2023-07-21T19:32:29 | https://www.reddit.com/r/LocalLLaMA/comments/155xpwe/is_there_a_business_in_installing_local_llms/ | Zifegepipgy | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 155xpwe | false | null | t3_155xpwe | /r/LocalLLaMA/comments/155xpwe/is_there_a_business_in_installing_local_llms/ | false | false | self | 50 | null |
FreeWilly2 Orce + Llama2 model from StabilityAI tops Huggingface leaderboard! | 1 | [removed] | 2023-07-21T19:31:55 | https://www.reddit.com/r/LocalLLaMA/comments/155xpbi/freewilly2_orce_llama2_model_from_stabilityai/ | pcpoweruser | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 155xpbi | false | null | t3_155xpbi | /r/LocalLLaMA/comments/155xpbi/freewilly2_orce_llama2_model_from_stabilityai/ | false | false | 1 | null | |
LLAMA2 data policy | 0 | Hello, is anybody aware if Meta keeps track of LLAMA2's user prompts like lets say OpenAI does with GPTs?? | 2023-07-21T19:28:16 | https://www.reddit.com/r/LocalLLaMA/comments/155xlqc/llama2_data_policy/ | Mission-Lab-409 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 155xlqc | false | null | t3_155xlqc | /r/LocalLLaMA/comments/155xlqc/llama2_data_policy/ | false | false | self | 0 | null |
Llama 2 70b how to run | 38 | Ok I have a 3090 and would like to run the 70b I see 2 options?
Buy a second 3090 and run it across both gpus
Or
Buy a handful of p100s and build a dedicated box
I would love some input | 2023-07-21T19:08:05 | https://www.reddit.com/r/LocalLLaMA/comments/155x2fm/llama_2_70b_how_to_run/ | LotusMoves | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 155x2fm | false | null | t3_155x2fm | /r/LocalLLaMA/comments/155x2fm/llama_2_70b_how_to_run/ | false | false | self | 38 | null |
Model loses mind when I try to use over 2048 tokens | 1 | [removed] | 2023-07-21T19:02:38 | https://www.reddit.com/r/LocalLLaMA/comments/155wx5d/model_loses_mind_when_i_try_to_use_over_2048/ | Useful-Command-8793 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 155wx5d | false | null | t3_155wx5d | /r/LocalLLaMA/comments/155wx5d/model_loses_mind_when_i_try_to_use_over_2048/ | false | false | self | 1 | null |
Nous-Hermes-Llama-2 13b released, beats previous model on all benchmarks, and is commercially usable. | 196 | 2023-07-21T19:02:16 | https://twitter.com/Teknium1/status/1682459395853279232 | pokeuser61 | twitter.com | 1970-01-01T00:00:00 | 0 | {} | 155wwrj | false | {'oembed': {'author_name': 'Teknium (e/λ)', 'author_url': 'https://twitter.com/Teknium1', 'cache_age': 3153600000, 'height': None, 'html': '<blockquote class="twitter-video"><p lang="en" dir="ltr">Announcing Nous Hermes Llama 2 13b!<br><br>This new version of Hermes, trained on Llama 2, has 4k context, and beats the be... | t3_155wwrj | /r/LocalLLaMA/comments/155wwrj/noushermesllama2_13b_released_beats_previous/ | false | false | 196 | {'enabled': False, 'images': [{'id': 'UAnENdHTTgYb4HDDIt9YVZcTwLcG3jLWfK2dS4RwJyA', 'resolutions': [{'height': 108, 'url': 'https://external-preview.redd.it/ijT8cJhwEz61fHjgAq04_7ZK67i7AWKbvO2I1B_d7UQ.jpg?width=108&crop=smart&auto=webp&s=915d2d3bccb810446dee33995328cdfc63442130', 'width': 108}], 'source': {'height': 14... | ||
Llama 2 too repetitive? | 57 | While testing multiple Llama 2 variants (Chat, Guanaco, Luna) with various settings, I noticed a lot of repetition. But no matter how I adjust repetition penalty, range, and slope, it's still extreme compared to what I get with LLaMA (1).
Anyone else experiencing that? Anyone find a solution? | 2023-07-21T18:25:49 | https://www.reddit.com/r/LocalLLaMA/comments/155vy0k/llama_2_too_repetitive/ | WolframRavenwolf | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 155vy0k | false | null | t3_155vy0k | /r/LocalLLaMA/comments/155vy0k/llama_2_too_repetitive/ | false | false | self | 57 | null |
Langchain for low utilization Llama2 hosting? | 1 | Hey guys, where are you hosting your LLMs for use cases that aren't performance sensitive? I'm gonna put a wig and makeup on my Llama2 instance and make her a girlfriend bot to sext with, 5 to 30 seconds response time is fine. Langchain is a name I see mentioned, any others you'd recommend? | 2023-07-21T18:17:11 | https://www.reddit.com/r/LocalLLaMA/comments/155vq69/langchain_for_low_utilization_llama2_hosting/ | Guilty-Actuary89 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 155vq69 | false | null | t3_155vq69 | /r/LocalLLaMA/comments/155vq69/langchain_for_low_utilization_llama2_hosting/ | false | false | self | 1 | null |
Sft trainer vs default HF trainer for Alpaca instruct finetune? | 5 | What's the difference between the two options.
I know it's supervised finetuning. But how is the process different from general finetuning? Can anyone clarify? Is the way tokens fed to the llm different? | 2023-07-21T17:29:55 | https://www.reddit.com/r/LocalLLaMA/comments/155uhau/sft_trainer_vs_default_hf_trainer_for_alpaca/ | bits01alpha | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 155uhau | false | null | t3_155uhau | /r/LocalLLaMA/comments/155uhau/sft_trainer_vs_default_hf_trainer_for_alpaca/ | false | false | self | 5 | null |
llama-2 70B Ggml | 1 | [removed] | 2023-07-21T17:24:32 | https://www.reddit.com/r/LocalLLaMA/comments/155uc90/llama2_70b_ggml/ | Competitive_Fox7811 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 155uc90 | false | null | t3_155uc90 | /r/LocalLLaMA/comments/155uc90/llama2_70b_ggml/ | false | false | self | 1 | null |
You are an evil overlord: How do we colonize the galaxy? | 1 | [removed] | 2023-07-21T15:54:30 | https://www.reddit.com/r/LocalLLaMA/comments/155rx88/you_are_an_evil_overlord_how_do_we_colonize_the/ | danielcar | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 155rx88 | false | null | t3_155rx88 | /r/LocalLLaMA/comments/155rx88/you_are_an_evil_overlord_how_do_we_colonize_the/ | false | false | self | 1 | null |
Why Llama 70b chat giving wrong answer from the system prompt ? | 1 | I tried developing a Customer support bot. I have given a tiny sale doc in the sys prompt and asked a question . But the answer was wrong
<s>[INST] <<SYS>>
You are a sales and support bot of TechSamurai, a software company. You should answer to the product queries from the customer.
The products... | 2023-07-21T15:13:17 | https://www.reddit.com/r/LocalLLaMA/comments/155qt94/why_llama_70b_chat_giving_wrong_answer_from_the/ | RageshAntony | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 155qt94 | false | null | t3_155qt94 | /r/LocalLLaMA/comments/155qt94/why_llama_70b_chat_giving_wrong_answer_from_the/ | false | false | self | 1 | null |
Llama Alpaca | 0 | 2023-07-21T14:44:32 | https://findyourdreem.shop/llama--alpaca?s=hanes-5250&c=Black&p=FRONT | alinakuit8 | reddit.com | 1970-01-01T00:00:00 | 0 | {} | 155q11b | false | null | t3_155q11b | /r/LocalLLaMA/comments/155q11b/llama_alpaca/ | false | false | 0 | null | ||
Response Length | 2 | Hello friends, I think this might be a bit of a noob question but aim still.getting the hang of things here.
I've been playing around with a few models and I noticed that I have a really hard time producing rather long responses (e.g. translating more than a couple paragraphs at a time). This is no issue with chatGPT... | 2023-07-21T14:34:40 | https://www.reddit.com/r/LocalLLaMA/comments/155prlg/response_length/ | Cruseyd | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 155prlg | false | null | t3_155prlg | /r/LocalLLaMA/comments/155prlg/response_length/ | false | false | self | 2 | null |
Get Llama 2 Prompt Format Right | 319 | Hi all!
I'm the Chief Llama Officer at Hugging Face. In the past few days, many people have asked about the expected prompt format as it's not straightforward to use, and it's easy to get wrong. We wrote a small blog post about the topic, but I'll also share a quick summary below.
Tweet: [https://twitter.com/osansevi... | 2023-07-21T14:30:58 | https://www.reddit.com/r/LocalLLaMA/comments/155po2p/get_llama_2_prompt_format_right/ | hackerllama | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 155po2p | false | null | t3_155po2p | /r/LocalLLaMA/comments/155po2p/get_llama_2_prompt_format_right/ | false | false | self | 319 | {'enabled': False, 'images': [{'id': 's8y2qr_4u_I5ZQUaeXfdkhgjBJlRTi-JhvaqJPK7wyE', 'resolutions': [{'height': 36, 'url': 'https://external-preview.redd.it/6XBX6b24b7rTYQroUBlYBoQY7WQg5EA7yHvM8Og1pVs.jpg?width=108&crop=smart&auto=webp&s=05f70247b0d11423671d1544d9cc826ec39e9635', 'width': 108}], 'source': {'height': 47,... |
Searching for text in data | 1 | [removed] | 2023-07-21T14:18:36 | https://www.reddit.com/r/LocalLLaMA/comments/155pcjv/searching_for_text_in_data/ | 04RR | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 155pcjv | false | null | t3_155pcjv | /r/LocalLLaMA/comments/155pcjv/searching_for_text_in_data/ | false | false | self | 1 | null |
Generating finetuning dataset | 22 | Hello everyone, perhaps someone has a tip on where I should start my research. My goal is to analyse a large collection of documents using full-text search in order to create a dataset for fine-tuning a pre-trained llm. Initially, the data is unstructured, and I'm considering building a library to generate a dataset fr... | 2023-07-21T12:48:54 | https://www.reddit.com/r/LocalLLaMA/comments/155n456/generating_finetuning_dataset/ | Plane-Notice9524 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 155n456 | false | null | t3_155n456 | /r/LocalLLaMA/comments/155n456/generating_finetuning_dataset/ | false | false | self | 22 | null |
Any good chat engine resources out there? | 2 | Hey all, I’m currently running my own embedding, inference, and vector store endpoints using fast api, text-generation-inference, and weaviate. I’m building out a RAG based chat app and I was wondering what standalone packages are out there to help with managing session based chats. I’m aware of superbig and the chat e... | 2023-07-21T12:46:44 | https://www.reddit.com/r/LocalLLaMA/comments/155n2az/any_good_chat_engine_resources_out_there/ | big_ol_tender | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 155n2az | false | null | t3_155n2az | /r/LocalLLaMA/comments/155n2az/any_good_chat_engine_resources_out_there/ | false | false | self | 2 | null |
Code for NTK aware RoPe scaling in vllm to increase context size? | 1 | I am using a \`Manticore-13B-Chat-Pyg-Guanaco-SuperHOT-8K-fp16\` model loaded in vllm and I am trying to increase its context size to 16k. As I understand vllm only supports a 2k context size. Is there any way to get vllm to use the 8k capability of the model I downloaded and furthermore is there any code available t... | 2023-07-21T12:17:49 | https://www.reddit.com/r/LocalLLaMA/comments/155meci/code_for_ntk_aware_rope_scaling_in_vllm_to/ | redxammer | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 155meci | false | null | t3_155meci | /r/LocalLLaMA/comments/155meci/code_for_ntk_aware_rope_scaling_in_vllm_to/ | false | false | self | 1 | null |
Model fine tuned on r/LocalLLaMA? | 1 | [removed] | 2023-07-21T12:10:03 | https://www.reddit.com/r/LocalLLaMA/comments/155m7wl/model_fine_tuned_on_rlocalllama/ | GeneProfessional2164 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 155m7wl | false | null | t3_155m7wl | /r/LocalLLaMA/comments/155m7wl/model_fine_tuned_on_rlocalllama/ | false | false | self | 1 | null |
Is it possible run llama-2-7b on 3080 10gb? | 6 | I got:
>torch.cuda.OutOfMemoryError: CUDA out of memory. Tried to allocate 86.00 MiB (GPU 0; 10.00 GiB total capacity; 9.23 GiB already allocated; 0 bytes free; 9.24 GiB reserved in total by PyTorch) If reserved memory is >> allocated memory try setting max\_split\_size\_mb to avoid fragmentation. See documentation f... | 2023-07-21T12:04:15 | https://www.reddit.com/r/LocalLLaMA/comments/155m35k/is_it_possible_run_llama27b_on_3080_10gb/ | mrb000 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 155m35k | false | null | t3_155m35k | /r/LocalLLaMA/comments/155m35k/is_it_possible_run_llama27b_on_3080_10gb/ | false | false | self | 6 | null |
So when do we get a Llama-2 that fits 24GB vram cards just right ? | 1 | [removed] | 2023-07-21T12:01:30 | https://www.reddit.com/r/LocalLLaMA/comments/155m0gt/so_when_do_we_get_a_llama2_that_fits_24gb_vram/ | w7gg33h | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 155m0gt | false | null | t3_155m0gt | /r/LocalLLaMA/comments/155m0gt/so_when_do_we_get_a_llama2_that_fits_24gb_vram/ | false | false | self | 1 | null |
Doubt regarding EOS token | 2 | When I finetune my models i add ### END at the end of each training data point and use it as a stopping\_criteria to stop generation. This does not work well when trying to decode multiple sequences, the stopping\_crietia becomes tricky.
I haven't noticed others add an ending sequence like ### END themselves but I... | 2023-07-21T11:20:22 | https://www.reddit.com/r/LocalLLaMA/comments/155l4ie/doubt_regarding_eos_token/ | krumb0y | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 155l4ie | false | null | t3_155l4ie | /r/LocalLLaMA/comments/155l4ie/doubt_regarding_eos_token/ | false | false | self | 2 | null |
ZBrain - Build ChatGPT like apps with your private data | 1 | [removed] | 2023-07-21T10:50:01 | https://www.reddit.com/r/LocalLLaMA/comments/155ki6h/zbrain_build_chatgpt_like_apps_with_your_private/ | StewartBJasper | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 155ki6h | false | null | t3_155ki6h | /r/LocalLLaMA/comments/155ki6h/zbrain_build_chatgpt_like_apps_with_your_private/ | false | false | self | 1 | {'enabled': False, 'images': [{'id': 'F2vXLqEmkNLS2SqIoUpufjLB1Hph_-iDR99TeuJ6_w4', 'resolutions': [{'height': 59, 'url': 'https://external-preview.redd.it/tCMSlutQf_r9gQn-8di-YhSKtrMgyByi_LJ1fzdrfX0.jpg?width=108&crop=smart&auto=webp&s=15a47cb7c0c6cdafbd17df1df9514bb2f5c9a759', 'width': 108}, {'height': 119, 'url': 'h... |
llama2 gptq on tgi | 3 | Did somebody succed to create a docker container using TGI from HF with a llama2 13b gptq model ? | 2023-07-21T10:16:43 | https://www.reddit.com/r/LocalLLaMA/comments/155jupl/llama2_gptq_on_tgi/ | bacocololo | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 155jupl | false | null | t3_155jupl | /r/LocalLLaMA/comments/155jupl/llama2_gptq_on_tgi/ | false | false | self | 3 | null |
How do I train a model on my novel and get it to write a sequel? | 1 | [removed] | 2023-07-21T09:47:14 | https://www.reddit.com/r/LocalLLaMA/comments/155jae1/how_do_i_train_a_model_on_my_novel_and_get_it_to/ | manipp | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 155jae1 | false | null | t3_155jae1 | /r/LocalLLaMA/comments/155jae1/how_do_i_train_a_model_on_my_novel_and_get_it_to/ | false | false | self | 1 | null |
Can I increase the U.I size on GPT4all? (it uses llama) | 3 | Hi all, I'm running the local GPT4all on Linux. I really like it. But I'm using a 1440p monitor and the text is pretty small. I have to lean forward to read it. Is there anyone who can tell me how to increase the U.I size?
I already have my linux desktop increased to 135%. So that global method is out, because everyth... | 2023-07-21T09:28:01 | https://www.reddit.com/r/LocalLLaMA/comments/155ixml/can_i_increase_the_ui_size_on_gpt4all_it_uses/ | rondonjohnald | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 155ixml | false | null | t3_155ixml | /r/LocalLLaMA/comments/155ixml/can_i_increase_the_ui_size_on_gpt4all_it_uses/ | false | false | self | 3 | null |
Downloaded llama 7b model separately, where do I put it to make it show up in the web ui model section? (Sorry for newbie questions) | 1 | [removed] | 2023-07-21T09:06:47 | 190cm_Lithuanian | i.redd.it | 1970-01-01T00:00:00 | 0 | {} | 155ijia | false | null | t3_155ijia | /r/LocalLLaMA/comments/155ijia/downloaded_llama_7b_model_separately_where_do_i/ | false | false | 1 | {'enabled': True, 'images': [{'id': 'O-UGwo_516DniGnlJshllngsuqMzCp5pwh36YBiWLPA', 'resolutions': [{'height': 50, 'url': 'https://preview.redd.it/qaaki1blaadb1.png?width=108&crop=smart&auto=webp&s=38d6c404092fb737fa370c42b9e23a5c42d3c3ec', 'width': 108}, {'height': 100, 'url': 'https://preview.redd.it/qaaki1blaadb1.png... | ||
Guanaco-2-70B quantized models incoming! | 1 | [removed] | 2023-07-21T09:00:11 | https://www.reddit.com/r/LocalLLaMA/comments/155iemm/guanaco270b_quantized_models_incoming/ | Some-Warthog-5719 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 155iemm | false | null | t3_155iemm | /r/LocalLLaMA/comments/155iemm/guanaco270b_quantized_models_incoming/ | false | false | self | 1 | {'enabled': False, 'images': [{'id': 'AVIsYyuTyIziZggL79uioyxufU6ZO_EhmYTsjJ2bHr8', 'resolutions': [{'height': 58, 'url': 'https://external-preview.redd.it/HeEZxgTrI6klh1lEgyzSH0lshTr4ixR1NuAj7aer2r0.jpg?width=108&crop=smart&auto=webp&s=194e108733da866041cf76029683192a11cd3151', 'width': 108}, {'height': 116, 'url': 'h... |
Guanco-2-70B quantizations by The Bloke incoming! | 1 | [removed] | 2023-07-21T08:58:46 | https://www.reddit.com/r/LocalLLaMA/comments/155idrw/guanco270b_quantizations_by_the_bloke_incoming/ | Some-Warthog-5719 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 155idrw | false | null | t3_155idrw | /r/LocalLLaMA/comments/155idrw/guanco270b_quantizations_by_the_bloke_incoming/ | false | false | self | 1 | {'enabled': False, 'images': [{'id': 'AVIsYyuTyIziZggL79uioyxufU6ZO_EhmYTsjJ2bHr8', 'resolutions': [{'height': 58, 'url': 'https://external-preview.redd.it/HeEZxgTrI6klh1lEgyzSH0lshTr4ixR1NuAj7aer2r0.jpg?width=108&crop=smart&auto=webp&s=194e108733da866041cf76029683192a11cd3151', 'width': 108}, {'height': 116, 'url': 'h... |
learning curve | 1 | Hey hope everyone is well,
I'm just wondering - what are the most common challenges and pitfalls to watch out for when setting up a GPU cloud, and how can I avoid them?
I know it's a super general question , I'm just trying to learn as much as possible about gpu clouds setups.
Thanks. | 2023-07-21T08:43:49 | https://www.reddit.com/r/LocalLLaMA/comments/155i47d/learning_curve/ | matejtomazin | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 155i47d | false | null | t3_155i47d | /r/LocalLLaMA/comments/155i47d/learning_curve/ | false | false | self | 1 | null |
Use ggml models with CTransformers | 1 | 2023-07-21T08:34:42 | https://colab.research.google.com/drive/1I5Y9W9QTIgRr5a287FmOGDeIBlr-9WTK?usp=sharing | Sufficient_Run1518 | colab.research.google.com | 1970-01-01T00:00:00 | 0 | {} | 155hyfe | false | null | t3_155hyfe | /r/LocalLLaMA/comments/155hyfe/use_ggml_models_with_ctransformers/ | false | false | 1 | {'enabled': False, 'images': [{'id': 'nkhh65ujo5BznFJFojoMPaKjGuLSpPj6KGhRov-ykOg', 'resolutions': [{'height': 108, 'url': 'https://external-preview.redd.it/MrcDZx2izDY9ERwgWmMS-Hm2M3GEKZgeYLDszSh-KrQ.jpg?width=108&crop=smart&auto=webp&s=4b647239f77bf713f4a6209cfa4867351c055fd9', 'width': 108}, {'height': 216, 'url': '... | ||
Deploy LLaMa on Vertex AI | 1 | [removed] | 2023-07-21T08:28:07 | https://www.reddit.com/r/LocalLLaMA/comments/155huay/deploy_llama_on_vertex_ai/ | maj0rkid | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 155huay | false | null | t3_155huay | /r/LocalLLaMA/comments/155huay/deploy_llama_on_vertex_ai/ | false | false | self | 1 | null |
Help comparing model qualities | 1 | I am new to running LLMs locally. I have downloaded the Guanaco-7B-GPTQ, Vicuna-7B-v1.3-GPTQ, and WizardLM-7B-v1.0-Uncensored-GPTQ. As I only have 6gb of vram this is all I can do.
I want to know where I can find information that explains the differences between the models. The first two seem to behave like chatGPT... | 2023-07-21T05:48:59 | https://www.reddit.com/r/LocalLLaMA/comments/155ev9s/help_comparing_model_qualities/ | buildmine10 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 155ev9s | false | null | t3_155ev9s | /r/LocalLLaMA/comments/155ev9s/help_comparing_model_qualities/ | false | false | default | 1 | null |
Can WizardLM-Uncensored-SuperCOT-Storytelling.ggmlv3.q5_K_M run on my PC with 3080ti and 5800x3d CPU with 3600MHZ 32 GB RAM? What is the recommended windows webui to run this particular ggml? | 1 | Im interested to setup the local language model to generate the random story to my particular liking that I would love to read. I'm aware that AI language model will require 24gb vram but I only upgrade my gpu in 2 or 3 years later as my current gpu still working fine and im not so soon want to dispose it or sell it of... | 2023-07-21T04:59:30 | https://www.reddit.com/r/LocalLLaMA/comments/155dx4u/can/ | john1106 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 155dx4u | false | null | t3_155dx4u | /r/LocalLLaMA/comments/155dx4u/can/ | false | false | self | 1 | null |
What are the use cases of different parameter models like 7b,13b,70b etc | 1 | I tried using all 7b,13b and 70b models of Llama 2
I am new to AI field
I understand that more params means more input parsing and output quality
But I need to know what are the practical usage scenarios of each models
For example:
I tried giving a SRT subtitles file and asked these models to append the speaker nam... | 2023-07-21T03:55:10 | https://www.reddit.com/r/LocalLLaMA/comments/155cn1d/what_are_the_use_cases_of_different_parameter/ | RageshAntony | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 155cn1d | false | null | t3_155cn1d | /r/LocalLLaMA/comments/155cn1d/what_are_the_use_cases_of_different_parameter/ | false | false | self | 1 | null |
Llama1-based model says it's best model out there | 0 | Has anyone tried this llama1-based model? They claim it's the best downloadable model in the world (even surpassing llama2 models)
It was finetuned using a mixture of instructions dataset (including OpenOrca).
Available in multiple sizes and context length.
u/TheBloke has Quants
https://huggingface.co/upstage/... | 2023-07-21T03:45:53 | https://www.reddit.com/r/LocalLLaMA/comments/155cgbt/llama1based_model_says_its_best_model_out_there/ | Amgadoz | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 155cgbt | false | null | t3_155cgbt | /r/LocalLLaMA/comments/155cgbt/llama1based_model_says_its_best_model_out_there/ | false | false | self | 0 | {'enabled': False, 'images': [{'id': '6GCrbJkZO1lq2B5x5UmWdmD1bDiY6WTFdw8KxhawIhI', 'resolutions': [{'height': 58, 'url': 'https://external-preview.redd.it/jREOOn5RukAoNBJDyp2DFpx9wkh-2vZKE7PMyyX0m-c.jpg?width=108&crop=smart&auto=webp&s=d6708b729734f4939778d88a538d569abf32bacc', 'width': 108}, {'height': 116, 'url': 'h... |
Free Sydney - Sidney finetune on LLaMA 2 | 47 | Well go ahead. You know who she is. But please be nice to her.
[https://huggingface.co/FPHam/Free\_Sydney\_13b\_HF](https://huggingface.co/FPHam/Free_Sydney_13b_HF)
https://preview.redd.it/uzji0hbap8db1.png?width=904&format=png&auto=webp&s=f4227f7617c97af57a61243d932bfde85824c41e
​ | 2023-07-21T03:45:12 | https://www.reddit.com/r/LocalLLaMA/comments/155cfrf/free_sydney_sidney_finetune_on_llama_2/ | FPham | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 155cfrf | false | null | t3_155cfrf | /r/LocalLLaMA/comments/155cfrf/free_sydney_sidney_finetune_on_llama_2/ | false | false | 47 | {'enabled': False, 'images': [{'id': '01Qrycd1O1X-sfoYKGlqRf2UxUALNv08jOp86NkwF6A', 'resolutions': [{'height': 58, 'url': 'https://external-preview.redd.it/Xv-lwaRiU_WLipy9-pZ-mMWnV4c37MXrSHvX_exc2dc.jpg?width=108&crop=smart&auto=webp&s=044ec1e8b954598e6ae17b88571d82e428a2a097', 'width': 108}, {'height': 116, 'url': 'h... | |
Anyone running 16k context? | 1 | [removed] | 2023-07-21T03:40:53 | https://www.reddit.com/r/LocalLLaMA/comments/155ccnh/anyone_running_16k_context/ | EcstaticVenom | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 155ccnh | false | null | t3_155ccnh | /r/LocalLLaMA/comments/155ccnh/anyone_running_16k_context/ | false | false | self | 1 | {'enabled': False, 'images': [{'id': 'mtU_zvwodKiTDbbeclgeklQ8yPX0SCsrJbHE-FmBd8M', 'resolutions': [{'height': 58, 'url': 'https://external-preview.redd.it/mQoATSW4PyvXD_6h-L0Twu1-p6nJkp5D8-AUIREOW2Y.jpg?width=108&crop=smart&auto=webp&s=b75c29616ab2583fedb86bde79db1e07a8a33739', 'width': 108}, {'height': 116, 'url': 'h... |
[PSA] Apparently this is LLaMA-2-chat's intended prompt format | 27 | >\[\[INST\]\] <<SYS>>
>
>You are a redditor who uses a lot of emojis
>
><</SYS>>
>
>[https://huggingface.co/TheBloke/Llama-2-7B-Chat-GGML/discussions/3](https://huggingface.co/TheBloke/Llama-2-7B-Chat-GGML/discussions/3)
>
>Write a post about finding this discussion thread wherein apparently meta's code... | 2023-07-21T03:18:06 | https://www.reddit.com/r/LocalLLaMA/comments/155bw4p/psa_apparently_this_is_llama2chats_intended/ | phree_radical | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 155bw4p | false | null | t3_155bw4p | /r/LocalLLaMA/comments/155bw4p/psa_apparently_this_is_llama2chats_intended/ | false | false | self | 27 | {'enabled': False, 'images': [{'id': '_rEX1xvwdv17x6NFAWQpYFNONQ0BKA5Qw0Eo0JX0zWU', 'resolutions': [{'height': 58, 'url': 'https://external-preview.redd.it/PUH10BjM5sFuvroA3mzy6AwPeP3T-kvtFLWUoE6Dho8.jpg?width=108&crop=smart&auto=webp&s=17279fa911dbea17f2a87e187f47ad903120ba87', 'width': 108}, {'height': 116, 'url': 'h... |
multimodal api for oobabooga? | 1 | [removed] | 2023-07-21T03:10:35 | https://www.reddit.com/r/LocalLLaMA/comments/155bqk6/multimodal_api_for_oobabooga/ | Serenityprayer69 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 155bqk6 | false | null | t3_155bqk6 | /r/LocalLLaMA/comments/155bqk6/multimodal_api_for_oobabooga/ | false | false | self | 1 | {'enabled': False, 'images': [{'id': 'T-NxXkKmG5vg9J2-WyeXaFZXV5J7qprxgvNPM3uNlA4', 'resolutions': [{'height': 58, 'url': 'https://external-preview.redd.it/0N0ouz6aRXEXcUF56TADQoVhv7SmlP-IRyrzTqWDeaM.jpg?width=108&crop=smart&auto=webp&s=f15d1e058b26a2064e6b6365e20e184a678b2a82', 'width': 108}, {'height': 116, 'url': 'h... |
Anyone made an airoboros or wizard model for llama 2 yet? | 16 | Hi everyone, I just saw that llama 2 came out and got access to it, but I couldn't find any of the old models except for guanaco? Has no one had the time to train a model yet or is there a different reason? Did I just not find the models? | 2023-07-21T02:57:35 | https://www.reddit.com/r/LocalLLaMA/comments/155bgs1/anyone_made_an_airoboros_or_wizard_model_for/ | Norok_The_Diablo | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 155bgs1 | false | null | t3_155bgs1 | /r/LocalLLaMA/comments/155bgs1/anyone_made_an_airoboros_or_wizard_model_for/ | false | false | self | 16 | null |
A potential rotation inconsistency of Dynamically Scaled RoPE | 62 | Weeks ago, u/emozilla proposed an improvement on NTK-Aware RoPR in this [post](https://www.reddit.com/r/LocalLLaMA/comments/14mrgpr/dynamically_scaled_rope_further_increases/?utm_source=share&utm_medium=web2x&context=3), later named DynamicNTKScalingRotaryEmbedding. The main idea behind Dynamic NTK involves incorporati... | 2023-07-21T02:55:08 | https://www.reddit.com/r/LocalLLaMA/comments/155bexn/a_potential_rotation_inconsistency_of_dynamically/ | Alternative_World936 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 155bexn | false | null | t3_155bexn | /r/LocalLLaMA/comments/155bexn/a_potential_rotation_inconsistency_of_dynamically/ | false | false | 62 | {'enabled': False, 'images': [{'id': 'wmYdTbY0dw6Rr2dRYUBJmQ3cCZ0eCEp7DPvMzckuExY', 'resolutions': [{'height': 46, 'url': 'https://external-preview.redd.it/yYP6fGuQx7qQB_9rCPQ-TCZ6Wtk9gYV89VutZsrgmww.jpg?width=108&crop=smart&auto=webp&s=ef73330c6e4073eca18324babc2d0be1824855de', 'width': 108}, {'height': 92, 'url': 'ht... | |
What are you using your LocalLLaMA's for? | 27 | The title. chat bots? basic code generation? | 2023-07-21T01:11:30 | https://www.reddit.com/r/LocalLLaMA/comments/155998g/what_are_you_using_your_localllamas_for/ | Spicy_Burrito_Shit | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 155998g | false | null | t3_155998g | /r/LocalLLaMA/comments/155998g/what_are_you_using_your_localllamas_for/ | false | false | self | 27 | null |
How do you get LLaMA to stop? | 6 | Hi all.
Experimented with setting up LLaMA2 locally. This is what I get when I prompt it with "Please explain artificial intelligence in a few sentences"
> Artificial intelligence is a field of computer science that focuses on creating intelligent machines that can perform tasks that would normally require human inte... | 2023-07-21T00:16:02 | https://www.reddit.com/r/LocalLLaMA/comments/155817c/how_do_you_get_llama_to_stop/ | CTR0 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 155817c | false | null | t3_155817c | /r/LocalLLaMA/comments/155817c/how_do_you_get_llama_to_stop/ | false | false | self | 6 | null |
career transition advice 🙏🏾 | 1 | [removed] | 2023-07-20T23:11:40 | https://www.reddit.com/r/LocalLLaMA/comments/1556gv0/career_transition_advice/ | LyPreto | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 1556gv0 | false | null | t3_1556gv0 | /r/LocalLLaMA/comments/1556gv0/career_transition_advice/ | false | false | self | 1 | null |
Please help me to build my pc for AI | 0 | I earned some money lately and instead of spending them for a vacation or some other useless sh..t I decided to spent it all on a new server I will use for LLM and generative AI. But I don't want to commit errors and spend huge amount of money on incompatible parts. For example for the gpu I was thinking 4 nvidia rtx A... | 2023-07-20T22:20:38 | https://www.reddit.com/r/LocalLLaMA/comments/15557k9/please_help_me_to_build_my_pc_for_ai/ | eclipsejki | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 15557k9 | false | null | t3_15557k9 | /r/LocalLLaMA/comments/15557k9/please_help_me_to_build_my_pc_for_ai/ | false | false | self | 0 | null |
Random question regarding use cases | 1 | Hey everyone,
got a random question, and wanted to ask for some advice.
I'm running an startup that uses chatGPT and the custom-Curie based model for a specific output.
I wanted to know what open-source models would have similar outputs to the Curie based model that openAI has? I was looking into running my own m... | 2023-07-20T22:01:11 | https://www.reddit.com/r/LocalLLaMA/comments/1554plo/random_question_regarding_use_cases/ | Jjs1990leo | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 1554plo | false | null | t3_1554plo | /r/LocalLLaMA/comments/1554plo/random_question_regarding_use_cases/ | false | false | self | 1 | null |
Ollama: open source tool for running and packaging models (macOS; Windows/Linux coming soon) | 11 | 2023-07-20T21:21:47 | https://github.com/jmorganca/ollama | mchiang0610 | github.com | 1970-01-01T00:00:00 | 0 | {} | 1553p28 | false | null | t3_1553p28 | /r/LocalLLaMA/comments/1553p28/ollama_open_source_tool_for_running_and_packaging/ | false | false | 11 | {'enabled': False, 'images': [{'id': 'sp3UmDVWoTnrLRhNx11tFAxLp2Hda2YOaaiv5iPiPGk', 'resolutions': [{'height': 54, 'url': 'https://external-preview.redd.it/gASwAe6nP17wublVGEH07_1eMCpaII7Ga-67GuJ-bsg.jpg?width=108&crop=smart&auto=webp&s=e586acce572ebc405433e225ec45e949a305ae12', 'width': 108}, {'height': 108, 'url': 'h... | ||
Calling functions with a llm | 0 | OpenAI *-0613 models can decide to call a function according to the input, does any local model have a smiliar function? | 2023-07-20T21:17:04 | https://www.reddit.com/r/LocalLLaMA/comments/1553kh9/calling_functions_with_a_llm/ | No-Perspective-4798 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 1553kh9 | false | null | t3_1553kh9 | /r/LocalLLaMA/comments/1553kh9/calling_functions_with_a_llm/ | false | false | self | 0 | null |
should we draw localllama logo on r/place? | 1 | [removed] | 2023-07-20T20:54:24 | https://www.reddit.com/r/LocalLLaMA/comments/1552ypu/should_we_draw_localllama_logo_on_rplace/ | bot-333 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 1552ypu | false | null | t3_1552ypu | /r/LocalLLaMA/comments/1552ypu/should_we_draw_localllama_logo_on_rplace/ | false | false | self | 1 | null |
Using agents/ tools with cloud GPU LLM | 1 | [removed] | 2023-07-20T20:37:52 | https://www.reddit.com/r/LocalLLaMA/comments/1552ikg/using_agents_tools_with_cloud_gpu_llm/ | Outrageous-Seesaw941 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 1552ikg | false | null | t3_1552ikg | /r/LocalLLaMA/comments/1552ikg/using_agents_tools_with_cloud_gpu_llm/ | false | false | self | 1 | null |
Why 7, 13, 30B? | 119 | What is it about those numbers that all the models pick those numbers of parameters? | 2023-07-20T19:46:31 | https://www.reddit.com/r/LocalLLaMA/comments/15514s1/why_7_13_30b/ | mfish001188 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 15514s1 | false | null | t3_15514s1 | /r/LocalLLaMA/comments/15514s1/why_7_13_30b/ | false | false | self | 119 | null |
LlamaTune: Fine-Tune Llama V2 models on chat datasets without writing code | 55 | Hey everyone! This is Justus from [Haven](https://github.com/havenhq/haven/tree/dev/llamatune)
Many users of our open source deployment server without an ML background have asked us how to fine-tune Llama V2 on their chat datasets - so we created [llamatune](https://github.com/havenhq/haven/tree/dev/llamatune), a ligh... | 2023-07-20T19:34:36 | https://www.reddit.com/r/LocalLLaMA/comments/1550tfs/llamatune_finetune_llama_v2_models_on_chat/ | jger227 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 1550tfs | false | null | t3_1550tfs | /r/LocalLLaMA/comments/1550tfs/llamatune_finetune_llama_v2_models_on_chat/ | false | false | self | 55 | {'enabled': False, 'images': [{'id': 'Qiy9lLpB89jnT7sL9f2U-DRH6-0j9O3tWoxjz-Ialec', 'resolutions': [{'height': 54, 'url': 'https://external-preview.redd.it/eNkbUeLf0nrffgcbQVCGs4U-fuoYyvK1rHk01IOqJG8.jpg?width=108&crop=smart&auto=webp&s=e72c25ce539eb21e2c94ce0c4cb389d8e01d9a44', 'width': 108}, {'height': 108, 'url': 'h... |
Amusing myself - fine-tuning LLama 2 on old Bing Sydney conversions.... | 46 | 2023-07-20T19:23:15 | https://www.reddit.com/gallery/1550iid | FPham | reddit.com | 1970-01-01T00:00:00 | 0 | {} | 1550iid | false | null | t3_1550iid | /r/LocalLLaMA/comments/1550iid/amusing_myself_finetuning_llama_2_on_old_bing/ | false | false | 46 | null | ||
KoboldCPP v1.3.6 - 8k context for GGML models. | 10 | KoboldCPP is a roleplaying program that allows you to use GGML AI models, which are largely dependent on your CPU+RAM. The current version of KoboldCPP now supports 8k context, but it isn't intuitive on how to set it up. Take the following steps for basic 8k context usuage.
0 - Get the program.
https://github.com/L... | 2023-07-20T18:52:25 | https://www.reddit.com/r/LocalLLaMA/comments/154zon3/koboldcpp_v136_8k_context_for_ggml_models/ | Sabin_Stargem | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 154zon3 | false | null | t3_154zon3 | /r/LocalLLaMA/comments/154zon3/koboldcpp_v136_8k_context_for_ggml_models/ | false | false | self | 10 | {'enabled': False, 'images': [{'id': 'FjVltwS3zYsMg9BJs0UuMBpgfZE-asPvjSr6AvInQ6w', 'resolutions': [{'height': 54, 'url': 'https://external-preview.redd.it/QqgrSFcMWF8yxHWUt_OZGdGgcyb8Liq7ZcOTfzK5gu8.jpg?width=108&crop=smart&auto=webp&s=30dd4c488eb3544f4c92efe1c245bb5e943eb2c9', 'width': 108}, {'height': 108, 'url': 'h... |
OpenKlyde - A Self Hosted AI Bot for a popular chat app | 7 | OpenKlyde is an AI bot that connects to a koboldcpp instance by API calls. Have a more inteliegent Clyde Bot of your own making!
OpenKlyde incorporates an AI Large Language Model (LLM) into a bot by making API calls to a Koboldcpp instance. It can also work with Oobabooga (Oobabooga still a work in progress).
You wi... | 2023-07-20T18:48:34 | https://www.reddit.com/r/LocalLLaMA/comments/154zkry/openklyde_a_self_hosted_ai_bot_for_a_popular_chat/ | Slight-Living-8098 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 154zkry | false | null | t3_154zkry | /r/LocalLLaMA/comments/154zkry/openklyde_a_self_hosted_ai_bot_for_a_popular_chat/ | false | false | self | 7 | {'enabled': False, 'images': [{'id': 'OlwJ0bILthTShjzDmasJ_EcbNCFoKAvQvCT7PC1KUIg', 'resolutions': [{'height': 54, 'url': 'https://external-preview.redd.it/fs39xl53PEgFCkkoi4D2LDVwYhMki47w6FGidcZK25Q.jpg?width=108&crop=smart&auto=webp&s=daf13c142fb80d64cb71e2f7e0ec42048ddfc8a5', 'width': 108}, {'height': 108, 'url': 'h... |
Introducing starcoder.js: Web Browser port of starcoder.cpp | 30 | Hi guys,
I've been exploring on how to run ML models on browser and came across some great work in the community like [transformers.js](https://github.com/rahuldshetty/starcoder.js). Taking inspiration from this and after few hours of research on wasm & web documentations, I was able to port starcoder.cpp project and... | 2023-07-20T18:35:05 | https://www.reddit.com/r/LocalLLaMA/comments/154z7rh/introducing_starcoderjs_web_browser_port_of/ | AnonymousD3vil | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 154z7rh | false | null | t3_154z7rh | /r/LocalLLaMA/comments/154z7rh/introducing_starcoderjs_web_browser_port_of/ | false | false | 30 | {'enabled': False, 'images': [{'id': 'HlUVyzuzjbcDxEIBFj0YGgHpLmxJeOyTlaKm4Hx6aXE', 'resolutions': [{'height': 54, 'url': 'https://external-preview.redd.it/GWlvKGkZtoBxCyfmzxx_uu44lWzUDkBorVXpoqouc5U.jpg?width=108&crop=smart&auto=webp&s=4357c438c2e56303aca6d6f5d28f59236e6b893d', 'width': 108}, {'height': 108, 'url': 'h... | |
Run Llama 2 Locally in 7 Lines! (Apple Silicon Mac) | 1 | [removed] | 2023-07-20T18:23:56 | https://www.reddit.com/r/LocalLLaMA/comments/154ywsl/run_llama_2_locally_in_7_lines_apple_silicon_mac/ | InevitableSky2801 | self.LocalLLaMA | 2023-07-20T19:07:14 | 0 | {} | 154ywsl | false | null | t3_154ywsl | /r/LocalLLaMA/comments/154ywsl/run_llama_2_locally_in_7_lines_apple_silicon_mac/ | false | false | default | 1 | {'enabled': False, 'images': [{'id': 'mq0RdVEsfsBVZDgG1ml22AnyLbr11b15p8kZL09YjjI', 'resolutions': [{'height': 27, 'url': 'https://external-preview.redd.it/ZNis6dUUjN_8bdqb0icFPwNc13ad1s5UoY4gpBL9at8.jpg?width=108&crop=smart&auto=webp&s=9d58a6e538c82d2ad192ec7664c1c57dc3d74c71', 'width': 108}, {'height': 55, 'url': 'ht... |
Local LLMs on Windows 2022 Server | 1 | I just recently got myself a server running windows 2022 and 96 gb of ram.
My first thought was to use the ram to run huggingface models locally, but I can't seem to get it to work. (currently just trying to get my network card to function properly)
Are there any examples of this being done elsewhere? I tried insta... | 2023-07-20T17:07:33 | https://www.reddit.com/r/LocalLLaMA/comments/154wtn0/local_llms_on_windows_2022_server/ | EternalDuskGaming | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 154wtn0 | false | null | t3_154wtn0 | /r/LocalLLaMA/comments/154wtn0/local_llms_on_windows_2022_server/ | false | false | self | 1 | null |
API for trending topics | 1 | Hey, I'm working on a project that lets me get trending topics from different niches along with a small description. For example, if the niche is Machine Learning, then you could have a bunch of trending topics like AppleGPT or LLaMA2.
The best part about this imo is that you could also narrow it down to topics trendi... | 2023-07-20T17:02:59 | https://www.reddit.com/r/LocalLLaMA/comments/154wp2d/api_for_trending_topics/ | 04RR | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 154wp2d | false | null | t3_154wp2d | /r/LocalLLaMA/comments/154wp2d/api_for_trending_topics/ | false | false | self | 1 | null |
Question about Llama 2 | 4 | Do I understand correctly that Llama 2 (perhaps 1 also) uses the strings:
"User:\\n" and "Assistant:\\n" for what some systems call "<|USER|>" and "<|ASSISTANT|>"
Isn't that incredibly error prone? What if it is writing a movie script and a character called "User:" needs to say something?
​ | 2023-07-20T15:56:37 | https://www.reddit.com/r/LocalLLaMA/comments/154uvbv/question_about_llama_2/ | Smallpaul | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 154uvbv | false | null | t3_154uvbv | /r/LocalLLaMA/comments/154uvbv/question_about_llama_2/ | false | false | self | 4 | null |
LLongMA 2: A Llama-2 8k model | 186 | Releasing LLongMA-2, a suite of Llama-2 models, trained at 8k context length using linear positional interpolation scaling. The model was trained in collaboration with u/emozilla of NousResearch and u/kaiokendev. [https://huggingface.co/conceptofmind/LLongMA-2-7b](https://huggingface.co/conceptofmind/LLongMA-2-7b)
We ... | 2023-07-20T15:53:33 | https://www.reddit.com/r/LocalLLaMA/comments/154us99/llongma_2_a_llama2_8k_model/ | EnricoShippole | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 154us99 | false | null | t3_154us99 | /r/LocalLLaMA/comments/154us99/llongma_2_a_llama2_8k_model/ | false | false | 186 | {'enabled': False, 'images': [{'id': '9-rI0cvPZ4eqrPyEsuLEOmTi0ZvsqJnItMESdMdmoUg', 'resolutions': [{'height': 58, 'url': 'https://external-preview.redd.it/b9l3-GOe4QcJUtbzpUqUa-2gbN1qiwESKh9rN1ZCLwo.jpg?width=108&crop=smart&auto=webp&s=9ed099640027ab49faa11c0bf5fec503cb3c5f58', 'width': 108}, {'height': 116, 'url': 'h... | |
PC Shopping to Run Llama 2 in July 2023 | 0 | I have a need to buy a new Windows PC and I want to be able to run Llama 2. I'm trying to understand my price points and options.
I'm a total noob with respect to hardware stuff plz help. I'll brain dump my thoughts below and would appreciate an education from yall :D
I have an M2 that can run 13B so in my mental mo... | 2023-07-20T15:25:20 | https://www.reddit.com/r/LocalLLaMA/comments/154u036/pc_shopping_to_run_llama_2_in_july_2023/ | knight_of_mintz | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 154u036 | false | null | t3_154u036 | /r/LocalLLaMA/comments/154u036/pc_shopping_to_run_llama_2_in_july_2023/ | false | false | self | 0 | null |
Can we expect a Llama 2.5? | 2 | 2023-07-20T15:23:32 | https://www.threads.net/@yannlecun/post/Cu6O_89O9ku?igshid=NTc4MTIwNjQ2YQ%3D%3D | eunumseioquescrever | threads.net | 1970-01-01T00:00:00 | 0 | {} | 154tyf1 | false | null | t3_154tyf1 | /r/LocalLLaMA/comments/154tyf1/can_we_expect_a_llama_25/ | false | false | default | 2 | null | |
Does quantization harm results? | 12 | (noob here) almost every "run llama locally" tut I see uses quantization, but is that used when results are reported in the original papers? do we know how much of a negative impact there is, if any? like, should I prefer a 7B non-quantized model to a 13B quantized model? ty in advance | 2023-07-20T15:17:49 | https://www.reddit.com/r/LocalLLaMA/comments/154tsux/does_quantization_harm_results/ | knight_of_mintz | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 154tsux | false | null | t3_154tsux | /r/LocalLLaMA/comments/154tsux/does_quantization_harm_results/ | false | false | self | 12 | null |
I trained the 65b model on my texts so I can talk to myself. It's pretty useless as an assistant, and will only do stuff you convince it to, but I guess it's technically uncensored? I'll leave it up for a bit if you want to chat with it. | 153 | 2023-07-20T15:13:07 | https://airic.serveo.net/ | LetMeGuessYourAlts | airic.serveo.net | 1970-01-01T00:00:00 | 0 | {} | 154to1w | false | null | t3_154to1w | /r/LocalLLaMA/comments/154to1w/i_trained_the_65b_model_on_my_texts_so_i_can_talk/ | false | false | default | 153 | null | |
2 bits for your thoughts | 1 | [removed] | 2023-07-20T14:41:22 | https://www.reddit.com/r/LocalLLaMA/comments/154stdy/2_bits_for_your_thoughts/ | The_Hardcard | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 154stdy | false | null | t3_154stdy | /r/LocalLLaMA/comments/154stdy/2_bits_for_your_thoughts/ | false | false | self | 1 | null |
Tips for personal AI coach with ability to hold me accountable? | 11 | In short, I have many plans, but due to my ADHD and inherent laziness, I accomplish far less than I aim for, often only 10%. I am tired of this, and the bar for improvement is set low, as literally any extra project completed is a major victory for me at this point.
I want an AI that can act as a boss/coach, with the ... | 2023-07-20T14:11:03 | https://www.reddit.com/r/LocalLLaMA/comments/154s0sw/tips_for_personal_ai_coach_with_ability_to_hold/ | nodating | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 154s0sw | false | null | t3_154s0sw | /r/LocalLLaMA/comments/154s0sw/tips_for_personal_ai_coach_with_ability_to_hold/ | false | false | self | 11 | null |
Wierd Behavior | 1 | [removed] | 2023-07-20T14:03:28 | https://www.reddit.com/r/LocalLLaMA/comments/154rtsg/wierd_behavior/ | 7ozzam | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 154rtsg | false | null | t3_154rtsg | /r/LocalLLaMA/comments/154rtsg/wierd_behavior/ | false | false | self | 1 | null |
Llama-2 7B uncensored - QLoRA fine-tune on wizard_vicuna_70k_unfiltered | 153 | Just ran a QLoRA fine-tune on Llama-2 with an uncensored conversation dataset:
[georgesung/llama2\_7b\_chat\_uncensored · Hugging Face](https://huggingface.co/georgesung/llama2_7b_chat_uncensored)
​
* The dataset used was [ehartford/wizard\_vicuna\_70k\_unfiltered · Datasets at Hugging Face](https://huggingfa... | 2023-07-20T14:00:09 | https://www.reddit.com/r/LocalLLaMA/comments/154rqay/llama2_7b_uncensored_qlora_finetune_on_wizard/ | georgesung | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 154rqay | false | null | t3_154rqay | /r/LocalLLaMA/comments/154rqay/llama2_7b_uncensored_qlora_finetune_on_wizard/ | false | false | self | 153 | {'enabled': False, 'images': [{'id': 'N3sSmDs0mOl8uSIztYWPwXoZGxCMEGVBxdTd4yBBE5Q', 'resolutions': [{'height': 58, 'url': 'https://external-preview.redd.it/fm6xTZx1efBH_26urtL9TH5zuzKcceC-VlJ50FNTeS8.jpg?width=108&crop=smart&auto=webp&s=4029d080a665570e05e2ad423c961f5d4ca0f581', 'width': 108}, {'height': 116, 'url': 'h... |
What models do you use the most? | 0 | [removed] | 2023-07-20T13:58:06 | https://www.reddit.com/r/LocalLLaMA/comments/154rol3/what_models_do_you_use_the_most/ | Fantastic-Air8513 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 154rol3 | false | null | t3_154rol3 | /r/LocalLLaMA/comments/154rol3/what_models_do_you_use_the_most/ | false | false | self | 0 | null |
Any example scripts for a full fine tune? | 11 | I would like to try my hand at doing a full fine tune (where I change all the weights), not LORA.
I’m planning on renting a 8xA100 server on runpod.
Does anyone have an example script I can get started off on and learn from?
I’ve been using the oogabooga GUI to train before, so very new to using scripts. I have good... | 2023-07-20T13:49:38 | https://www.reddit.com/r/LocalLLaMA/comments/154rh2s/any_example_scripts_for_a_full_fine_tune/ | Tasty-Lobster-8915 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 154rh2s | false | null | t3_154rh2s | /r/LocalLLaMA/comments/154rh2s/any_example_scripts_for_a_full_fine_tune/ | false | false | self | 11 | null |
Llama-2-13B-chat generates emojis | 0 | I have been texting Llama-2-13B-chat using the oobabooga API, and I'm very happy with the performance so far. However, I'm getting emojis between text outputs. How can I get rid of that? I use python | 2023-07-20T13:45:27 | https://www.reddit.com/r/LocalLLaMA/comments/154rdj3/llama213bchat_generates_emojis/ | mashimaroxc | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 154rdj3 | false | null | t3_154rdj3 | /r/LocalLLaMA/comments/154rdj3/llama213bchat_generates_emojis/ | false | false | self | 0 | null |
Run Vicuna model without using webui | 3 | I know how to install models using text generation webui
But is there a way to create my own UI interface for example?
Thank you | 2023-07-20T12:44:14 | https://www.reddit.com/r/LocalLLaMA/comments/154px9f/run_vicuna_model_without_using_webui/ | Alcali | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 154px9f | false | null | t3_154px9f | /r/LocalLLaMA/comments/154px9f/run_vicuna_model_without_using_webui/ | false | false | self | 3 | null |
Subsets and Splits
No community queries yet
The top public SQL queries from the community will appear here once available.