Koboldai
Models by this creator
🤷
OPT-13B-Erebus
208
The OPT-13B-Erebus model is a large language model developed by KoboldAI, a community of AI enthusiasts. It is the second generation of the original "Shinen" model created by Mr. Seeker. The model was trained on a diverse dataset of adult-themed stories and narratives, spanning sources like Literotica, Sexstories, and SoFurry. This model is intended for mature audiences only, as it will generate X-rated content. Compared to similar models like GPT-Neo 2.7B, GPT-J 6B, and OPT-66B, the OPT-13B-Erebus model is smaller in scale but specializes in an adult-focused domain. Like other large language models, it uses transformer architecture and is trained on a massive amount of natural language data. Model inputs and outputs Inputs Textual prompts**: The model takes in textual prompts as input, which it uses to generate new text. Outputs Generated text**: The primary output of the OPT-13B-Erebus model is new text, generated based on the provided prompt. The generated text will be in line with the adult-themed dataset the model was trained on. Capabilities The OPT-13B-Erebus model excels at generating explicit, adult-oriented content. It can be used to create detailed, immersive narratives and stories within the "Adult" genre. The model's strong bias towards this type of content makes it unsuitable for general-purpose use, but it could be valuable for specialized applications where mature themes are appropriate. What can I use it for? The OPT-13B-Erebus model could be used for the creation of adult-themed stories, erotica, and other related content. This could include writing commissions, collaborative worldbuilding, or the generation of prompts for artistic endeavors. However, given the model's mature focus, it should only be used in appropriate contexts and with a clear understanding of the potential risks and limitations. Things to try One interesting thing to explore with the OPT-13B-Erebus model is its ability to generate cohesive, long-form narratives within the adult genre. Providing the model with detailed prompts or story starters could result in surprising and creative plot developments. Additionally, experimenting with different prompting techniques, such as using genre tags or character descriptions, could yield unique and compelling results.
Updated 5/28/2024
🔄
OPT-6.7B-Erebus
92
The OPT-6.7B-Erebus is a large language model developed by KoboldAI. It is the second generation of the original Shinen model, trained on a dataset consisting of 6 different sources surrounding "Adult" themes. The name "Erebus" comes from Greek mythology, representing "darkness" - similar to the original Shin'en, or "deep abyss". This model is similar to other large OPT models like the OPT-13B-Erebus and GPT-NeoX-20B-Erebus, which were also developed by KoboldAI and trained on adult-themed datasets. However, the OPT-6.7B-Erebus has a smaller parameter count than these other Erebus models. Model Inputs and Outputs Inputs Text prompts for text generation Outputs Continuation of the input text, generated in an autoregressive manner Capabilities The OPT-6.7B-Erebus model is capable of generating coherent, adult-themed text based on provided prompts. It can produce narratives, descriptions, and dialogue in a variety of adult genres and styles. However, as the model was trained on an explicit dataset, the generated output will reflect this bias and may not be suitable for all audiences. What Can I Use It For? The OPT-6.7B-Erebus model could be used for creative writing projects, erotica, or other adult-oriented content generation. However, it's important to be aware of the model's biases and limitations, and to use it responsibly. The model should not be deployed in public-facing applications without proper moderation and filtering. Things to Try You could try providing the model with different types of adult-themed prompts, such as romance, erotica, or sensual descriptions, and see how the model responds. You could also experiment with altering the generation parameters, like temperature or top-k sampling, to adjust the style and content of the generated text. Just be mindful of the model's limitations and inappropriate outputs.
Updated 5/28/2024
↗️
GPT-NeoX-20B-Erebus
82
GPT-NeoX-20B-Erebus is a powerful 20 billion parameter autoregressive language model developed by KoboldAI. It is the second generation of the original Shinen model, with the "Erebus" name derived from Greek mythology, meaning "darkness" or "deep abyss". This model was trained on a diverse dataset of over 800GB of text, including sources like Literotica, Sexstories, and private datasets of adult-themed content. Similar models include the OPT 13B - Erebus and the GPT-Neo 2.7B, both of which share the "Erebus" theme and focus on adult-oriented content. These models demonstrate the range of large language models developed by the AI research community to serve specialized use cases. Model inputs and outputs Inputs Textual prompts of varying lengths, used to initialize the model and guide the generation of output text. Outputs Coherent, contextually-relevant text that continues the provided prompt, with a strong bias towards generating adult-themed content. Capabilities GPT-NeoX-20B-Erebus is a highly capable text generation model, able to fluently continue prompts and generate natural-sounding narratives. However, its specialized training dataset means it is most adept at producing content with mature or explicit themes. This model should be used with caution, as it may generate biased or offensive text, even when prompted with neutral input. What can I use it for? Given its specialization in adult-oriented content, GPT-NeoX-20B-Erebus would be most suitable for projects involving erotic fiction, erotica, or other forms of mature creative writing. It could potentially be fine-tuned for use in virtual assistant chatbots or interactive fiction, though great care would need to be taken to filter and moderate its outputs. Things to try One interesting experiment would be to prompt the model with neutral or mundane text, and observe how it steers the narrative in a more adult direction. This could provide insight into the biases and patterns learned during its training on explicit datasets. However, the results of such experiments should be carefully reviewed, as the model may generate content that is inappropriate or offensive.
Updated 5/28/2024
🗣️
LLaMA2-13B-Tiefighter
71
LLaMA2-13B-Tiefighter is a large language model developed by KoboldAI. It is a merged model created by combining multiple fine-tuned models on top of the base Undi95/Xwin-MLewd-13B-V0.2 model. The model incorporates enhancements from various upstream models, including PocketDoc/Dans-RetroRodeo-13b and Blackroot/Llama-2-13B-Storywriter-LORA, to create a versatile text generation model with a focus on creativity and storytelling. Model inputs and outputs Inputs Text**: The model takes in text as input, which can be used to prompt the model to generate additional text. Outputs Text**: The model generates text as output, with a focus on creative and narrative-driven content. Capabilities The LLaMA2-13B-Tiefighter model is designed to be a flexible and creative text generation tool. By combining multiple fine-tuned models, the developers have created a model that excels at tasks like story writing, world-building, and open-ended conversational interactions. The model's diverse training data and merging process allow it to generate coherent and engaging text across a variety of genres and styles. What can I use it for? The LLaMA2-13B-Tiefighter model can be a valuable tool for writers, game developers, and creative professionals who need to generate original text content. Its capabilities in narrative-driven tasks make it suitable for applications like interactive fiction, roleplaying games, and AI-assisted worldbuilding. While the model is not intended for safety-critical applications, it can be a powerful asset for projects that prioritize creativity and imagination. Things to try One interesting aspect of the LLaMA2-13B-Tiefighter model is its ability to improvise and generate unexpected yet coherent text when given minimal prompts. By allowing the model to freely generate content without constraining it with detailed instructions, users can discover novel ideas and narrative directions that they might not have considered otherwise. Experimenting with open-ended prompts and letting the model's creativity shine can lead to exciting and serendipitous results.
Updated 5/28/2024
📉
LLaMA2-13B-Tiefighter-GGUF
64
The LLaMA2-13B-Tiefighter-GGUF model is a large language model created by KoboldAI, a community group focused on developing advanced AI models. This model is a merged model, combining several different models and finetuning efforts to create a versatile and capable text generation model. It is based on the original LLaMA model, but has been further tuned and enhanced. Model inputs and outputs Inputs Text**: The model takes in natural language text as input, which it can then use to generate new text. Outputs Text**: The primary output of the model is generated text, which can be used for a variety of tasks such as creative writing, dialogue generation, and language modeling. Capabilities The LLaMA2-13B-Tiefighter-GGUF model is a highly capable text generation model that can be used for a wide range of applications. It has been tuned on a variety of datasets, including adventure and storytelling datasets, which gives it strong capabilities in areas like creative writing and narrative generation. The model is also known for its ability to engage in open-ended dialogues and conversations, making it suitable for chatbot and virtual assistant applications. What can I use it for? The LLaMA2-13B-Tiefighter-GGUF model is a versatile tool that can be used for a variety of projects and applications. Some potential use cases include: Creative writing**: The model's strong narrative and storytelling capabilities make it well-suited for generating creative fiction, poetry, and other forms of written expression. Dialogue and conversation**: The model's ability to engage in open-ended dialogue makes it a good fit for chatbot and virtual assistant applications, where it can provide natural and context-appropriate responses. Language modeling**: As a large language model, LLaMA2-13B-Tiefighter-GGUF can be used as a base for fine-tuning on specific tasks or domains, or for generating synthetic text for a variety of applications. Things to try One interesting aspect of the LLaMA2-13B-Tiefighter-GGUF model is its ability to engage in adventuring and adventure game-like behaviors. By providing a small introduction to a world and an objective, and using the '>' prefix for user commands, the model can be prompted to enter an "adventure mode" and respond accordingly, generating text that follows the narrative and progression of the adventure. Additionally, the model's diverse training data and finetuning efforts have resulted in a broad range of capabilities, from creative writing to factual knowledge. Experimenting with different prompts and instruction formats can help uncover the model's strengths and discover new and interesting ways to utilize its capabilities.
Updated 5/28/2024
👨🏫
OPT-30B-Erebus
58
The OPT-30B-Erebus model is the second generation of the original Shinen model created by Mr. Seeker. This large language model was trained by KoboldAI on a dataset spanning six different sources, all focused on "adult" themes. The name "Erebus" is drawn from Greek mythology, representing "darkness", aligning with the "deep abyss" meaning of Shin'en. Similar large models in this family include the OPT-13B-Erebus and OPT-6.7B-Erebus. Model inputs and outputs The OPT-30B-Erebus model is a text-to-text transformer that can be used for various language generation tasks. It takes text prompts as input and generates corresponding text outputs. Inputs Text prompts of varying lengths Outputs Coherent, human-like text continuations and completions based on the input prompts Capabilities The OPT-30B-Erebus model demonstrates strong language generation capabilities, able to produce detailed and contextually relevant text outputs. However, as a model trained on adult-themed data, it has a strong bias towards generating NSFW content, and is not suitable for use by minors. What can I use it for? Given its specialized training data, the OPT-30B-Erebus model would be most applicable for tasks involving adult-themed creative writing, erotica generation, or other applications requiring uncensored text output. Users should exercise caution and responsibility when using this model, as the content it generates may be inappropriate or offensive in many contexts. Things to try Experiment with providing the model with different types of prompts to see the range of responses it can generate. Try steering the model towards more tasteful or tame outputs by carefully crafting your prompts. However, be mindful that the model's strong bias towards NSFW content may be difficult to overcome completely.
Updated 5/28/2024
👀
LLaMA2-13B-Psyfighter2-GGUF
57
The LLaMA2-13B-Psyfighter2-GGUF is a merged model created by the KoboldAI community members Jeb Carter and TwistedShadows. It combines the LLaMA2-13B-Tiefighter model with additional medical data to supplement the model's fictional abilities with more details on anatomy and mental states. However, the model still has a high ratio of fiction data, so it should not be used for medical advice or therapy. Model inputs and outputs The LLaMA2-13B-Psyfighter2-GGUF model is a text-to-text AI that can be used for a variety of natural language processing tasks. It takes text as input and generates text as output. Inputs Arbitrary text prompts Outputs Continuations, elaborations, or responses to the input text Capabilities The LLaMA2-13B-Psyfighter2-GGUF model is particularly well-suited for creative tasks like story writing and character roleplay. It can generate coherent and engaging narratives when given an initial prompt or scenario. The model also has some knowledge of medical and mental health concepts, though this information should be verified before relying on it. What can I use it for? The LLaMA2-13B-Psyfighter2-GGUF model could be useful for projects involving creative writing, worldbuilding, or interactive fiction. For example, you could use it to generate story ideas, develop characters, or improvise dialogues. However, due to its high fictional content, the model should not be used for any applications requiring factual medical or psychological information. Things to try One interesting way to use the LLaMA2-13B-Psyfighter2-GGUF model is to give it an open-ended prompt and see how it improvises a narrative. Try starting with a simple instruction like "Write a short story about a person who discovers they have superpowers" and see where the model takes the story. You can also experiment with providing the model with character details or plot points and observe how it expands and develops the scenario.
Updated 5/28/2024