User contributions for RobowaifuDev

3 May 2023

• 16:0116:01, 3 May 2023 diff hist +2,052‎ N Help:API ‎ Created page with "Robowaifu.tech has an '''API''' your AI waifu can access. The site is on cheap hosting, so please cache results so it doesn't get hammered with too many requests. Once the wiki sufficiently grows I will provide a dataset download of the whole site. == Requirements == <syntaxhighlight lang="bash"> python -m pip install requests wikitextparser </syntaxhighlight> == Get page contents == <syntaxhighlight lang="python"> i..."
• 15:3515:35, 3 May 2023 diff hist +13‎ m Help:Editing ‎ →‎Editing rules and formatting: Added API help link
• 14:3314:33, 3 May 2023 diff hist −18‎ m Help:Editing ‎ Moved references
• 14:3314:33, 3 May 2023 diff hist +1‎ m Help:Editing ‎ →‎= References
• 14:3314:33, 3 May 2023 diff hist +70‎ Help:Editing ‎ →‎Paper
• 14:3214:32, 3 May 2023 diff hist +182‎ Help:Editing ‎ →‎Cite
• 14:2914:29, 3 May 2023 diff hist −6‎ m Help:Editing ‎ Tidyup
• 14:2514:25, 3 May 2023 diff hist +2,331‎ Help:Editing ‎ Added templates
• 14:2514:25, 3 May 2023 diff hist −6‎ Template:Tidyup ‎No edit summary current Tag: Manual revert
• 13:5913:59, 3 May 2023 diff hist +38‎ Template:Paper ‎No edit summary current
• 13:5513:55, 3 May 2023 diff hist +80‎ m Integer ‎ →‎Properties: Added links current
• 13:5413:54, 3 May 2023 diff hist +3,132‎ Integer ‎ Added properties, applications, quantization
• 13:3213:32, 3 May 2023 diff hist +475‎ m Help:Editing ‎ Added examples for youtube and syntaxhighlight tags
• 13:2513:25, 3 May 2023 diff hist +8‎ m Waifuverse ‎ Update Twitter link current Tag: Visual edit: Switched

2 May 2023

• 23:0123:01, 2 May 2023 diff hist +144‎ Help:Editing ‎ →‎Editing rules and formatting
• 22:5422:54, 2 May 2023 diff hist +144‎ MediaWiki:Common.css ‎No edit summary current
• 22:5122:51, 2 May 2023 diff hist +2,330‎ Help:Editing ‎ Added getting started section

28 April 2023

• 16:2516:25, 28 April 2023 diff hist +3,220‎ N Scaling Transformer to 1M tokens and beyond with RMT ‎ Created page with "Category:2023Category:April 2023Category:Research paperCategory:Natural language processing '''Scaling Transformer to 1M tokens and beyond with RMT''' is a research paper on the application of a recurrent memory mechanism to extend the context length of BERT, one of the most effective Transformer-based models in natural language processing.<ref>Bulatov et al. "Scaling Transformer to 1M tokens and beyond with RMT." 2023. [h..." current Tag: Visual edit: Switched
• 16:1216:12, 28 April 2023 diff hist +155‎ DiffCSE ‎No edit summary current Tag: Visual edit
• 14:3914:39, 28 April 2023 diff hist −12‎ m Robowaifu Institute of Technology ‎ Fixed link current Tag: Visual edit: Switched
• 14:3814:38, 28 April 2023 diff hist +5‎ m LongForm ‎No edit summary current
• 14:3814:38, 28 April 2023 diff hist +91‎ Evol-Instruct ‎No edit summary current Tag: Visual edit: Switched
• 14:3714:37, 28 April 2023 diff hist 0‎ N Category:Research paper ‎ Created blank page current
• 14:3614:36, 28 April 2023 diff hist +8‎ m MERLIN ‎No edit summary current Tag: Visual edit: Switched
• 14:3514:35, 28 April 2023 diff hist +86‎ m LongForm ‎No edit summary Tag: Visual edit: Switched
• 14:3314:33, 28 April 2023 diff hist −37‎ m Reinforcement learning ‎No edit summary current Tag: Visual edit: Switched
• 14:3214:32, 28 April 2023 diff hist +2,433‎ N Reinforcement learning ‎ Created page with "'''Reinforcement learning''' is a branch of machine learning that focuses on training algorithms to make decisions and take actions based on observations or experiences encountered in an environment. The goal of reinforcement learning is to develop an algorithm that can make optimal decisions in order to maximize a reward. == Overview == In reinforcement learning, an algorithm, referred to as an agent, interacts with an environment by taking actions and receiving fe..."
• 14:2514:25, 28 April 2023 diff hist +1,454‎ N Reinforcement learning from human feedback ‎ Created page with "'''Reinforcement learning from human feedback''' ('''RLHF''') is a subfield of reinforcement learning (RL) that trains agents using human feedback as reinforcement signals. In RL, agents interact with an environment, collect rewards or punishments based on actions taken and adjust their behavior to maximize rewards. However, designing accurate reward functions or annotating sufficient data for this purpose is difficult in many real-world scenarios. RLHF addresses th..." current
• 14:1914:19, 28 April 2023 diff hist +3,939‎ N LongForm ‎ Created page with "'''LongForm: Optimizing Instruction Tuning for Long Text Generation with Corpus Extraction''' is a research paper that discusses a method to improve the performance of language models for long text generation by optimizing instruction tuning.<ref>Köksal et al. "LongForm: Optimizing Instruction Tuning for Long Text Generation with Corpus Extraction." 2023. [https://arxiv.org/abs/2304.08460 arXiv:2304.08460]</ref> The paper was authored by Abdullatif Köksal, Timo Sc..."
• 14:0714:07, 28 April 2023 diff hist +1,719‎ N Prompt engineering ‎ Created page with "'''Prompt engineering''' is a concept in artificial intelligence (AI), particularly in natural language processing, that involves creating or designing prompts or inputs for an AI model that are capable of yielding desirable or useful results. The goal of prompt engineering is to improve the performance and accuracy of AI models, allowing them to generate more relevant and meaningful responses to user input. Effective prompt engineering requires creating and mai..." current
• 08:3608:36, 28 April 2023 diff hist +173‎ Evol-Instruct ‎ →‎Open questions
• 01:2601:26, 28 April 2023 diff hist −317‎ m Evol-Instruct ‎No edit summary Tag: Visual edit
• 01:2401:24, 28 April 2023 diff hist +1,415‎ N Curriculum learning ‎ Created page with "'''Curriculum learning''' is a training strategy in machine learning where the examples used to train the model are presented to the model in a meaningful order, from easiest to hardest. This is done in an attempt to increase the speed and effectiveness of the learning process, as well as the final performance of the model. The concept is inspired by the way humans learn, where new knowledge is often presented in a structured and scaffolded way. With curriculum learning,..." current
• 01:1101:11, 28 April 2023 diff hist +10‎ Latest papers ‎ →‎2023
• 01:1001:10, 28 April 2023 diff hist +1,257‎ N Pre-trained language model ‎ Created page with "'''A pre-trained language model''' is a type of language model that has been trained on a large dataset of text in order to learn the structure and rules of language. The pre-training step typically involves training the language model on a large corpus of text using a task such as predicting the next word in a sentence. Once the language model is trained, it can be fine-tuned for a specific task, such as sentiment analysis or text classification, using a smaller dat..." current
• 01:0801:08, 28 April 2023 diff hist +2,159‎ N Instruction tuning ‎ Created page with "'''Instruction tuning''' is a technique in natural language processing designed to improve the accuracy and naturalness of zero-shot prompting interactions. With instruction tuning, a language model is trained on many examples of tasks formulated as natural language instructions, along with appropriate responses. The goal is to enable the language model to generate more natural and accurate responses to new instructions, without the need fo..." current
• 01:0001:00, 28 April 2023 diff hist +807‎ Latest papers ‎ →‎2023
• 00:5000:50, 28 April 2023 diff hist +6,835‎ N Evol-Instruct ‎ Created page with "'''Evol-Instruct: Mass-Producing Open-Domain Instruction Data with Varying Levels of Complexity using Large Language Models''' is a research paper published on the arXiv pre-print server in 2023. The paper proposes a method for creating large amounts of instruction data with varying levels of complexity using Large Language Models (LLMs) instead of humans.<ref>Xu et al. "DiffCSE: Difference-based Contrastive Learning for Sentence Embeddings." 2023. [https://arxiv.org/abs..."

9 January 2023

• 04:2604:26, 9 January 2023 diff hist +20‎ DiffCSE ‎No edit summary
• 04:2504:25, 9 January 2023 diff hist +737‎ N DiffCSE ‎ Created page with "'''DiffCSE''' is a contrastive learning framework for learning sentence embeddings from unlabeled data.<ref>Chuang et al. "DiffCSE: Difference-based Contrastive Learning for Sentence Embeddings." 2022. [https://arxiv.org/abs/2204.10298 arXiv:2204.10298]</ref> It uses a difference-based loss function to compare two sentence embeddings, one generated by masking out the sentence and filling it in with generated data with a masked language model, and training a model to prod..." Tag: Visual edit
• 04:2104:21, 9 January 2023 diff hist +271‎ m Sentence embedding ‎ Added DiffCSE current Tag: Visual edit

4 January 2023

• 01:5901:59, 4 January 2023 diff hist +535‎ Latest papers ‎No edit summary
• 01:5701:57, 4 January 2023 diff hist −34‎ Template:Paper ‎No edit summary
• 01:5701:57, 4 January 2023 diff hist +3‎ Template:Paper ‎No edit summary
• 01:5501:55, 4 January 2023 diff hist −26‎ Template:Paper ‎No edit summary
• 01:5501:55, 4 January 2023 diff hist +5‎ Template:Paper ‎No edit summary
• 01:5401:54, 4 January 2023 diff hist +53‎ Template:Paper ‎No edit summary
• 01:3601:36, 4 January 2023 diff hist +85‎ Latest papers ‎ →‎Recent papers Tag: Visual edit
• 01:3501:35, 4 January 2023 diff hist +8‎ m Hardware ‎ Fix template current
• 01:3501:35, 4 January 2023 diff hist +8‎ m Game development ‎ Fix template