Models by this creator




Total Score


plamo-13b is a large language model developed by Preferred Networks, Inc. It is based on the LLaMA architecture and has been pretrained on 1.5 trillion tokens of text, including data from English and Japanese sources. The model is released under the Apache v2.0 license. plamo-13b is comparable to other 13B parameter models like Redmond-Puffin-13B, CodeLlama-13b-hf, open_llama_13b, and Llama-2-13b-hf. These models have been trained on large web corpora and fine-tuned for different tasks. Model inputs and outputs Inputs plamo-13b takes in text sequences as input, with a maximum context length of 4096 tokens. Outputs The model generates text continuations, producing up to 32 new tokens in response to a given input prompt. Capabilities plamo-13b is a powerful language model capable of a variety of text generation tasks, such as summarization, translation, question answering, and open-ended dialogue. The model's multilingual training on English and Japanese data makes it useful for applications that require understanding and generating content in both languages. What can I use it for? plamo-13b can be used in a wide range of natural language processing applications, such as chatbots, content generation tools, and language understanding systems. Developers can fine-tune the model on domain-specific data to adapt it for specialized use cases. The model's permissive Apache v2.0 license makes it accessible for both commercial and research purposes. Things to try One interesting aspect of plamo-13b is its ability to generate long-form, coherent text. Researchers and developers could explore using the model for tasks like story generation, where the model's capacity for maintaining context and producing consistent narratives over many tokens could be beneficial. Additionally, the model's multilingual capabilities could be leveraged for cross-language applications, such as building translation tools or language learning assistants.

Read more

Updated 5/19/2024