Get a weekly rundown of the latest AI models and research... subscribe!


Maintainer: LumiOpen

Total Score


Last updated 5/16/2024


Model LinkView on HuggingFace
API SpecView on HuggingFace
Github LinkNo Github link provided
Paper LinkNo paper link provided

Get summaries of the top AI models delivered straight to your inbox:

Model overview

The Poro-34B model is a 34B parameter decoder-only transformer pretrained on Finnish, English, and code by LumiOpen. It was trained on 1 trillion tokens and is fully open source, available under the Apache 2.0 License. Poro outperforms previous Finnish-only models while also being fluent in English and code, and capable of basic translation between English and Finnish. Similar models like bloom-7b1 from BigScience are also large open-source multilingual language models, but Poro is specifically focused on Finnish and English.

Model inputs and outputs

The Poro-34B model is a text-to-text transformer that can be used for a variety of language tasks. It takes raw text as input and generates coherent text as output. The model has a large 128,000 word vocabulary covering Finnish, English, and programming languages.


  • Raw text in Finnish, English, or code
  • Prompts for specific language tasks like translation, summarization, or generation


  • Coherent text in Finnish, English, or code
  • Translations between Finnish and English
  • Summaries of input text
  • Continuations of prompts for generation tasks


The Poro-34B model excels at Finnish and English language understanding and generation. It can fluently write in both languages, perform basic translation, and even generate simple code. The model's large parameter size and training on a huge corpus of data give it strong general language abilities.

What can I use it for?

The Poro-34B model could be used for a variety of natural language processing tasks in Finnish and English. Some potential applications include:

  • Content generation: Writing articles, stories, or other text in Finnish or English
  • Translation: Translating between Finnish and English
  • Language understanding: Answering questions or completing tasks based on Finnish or English text
  • Code generation: Generating simple code snippets in various programming languages

The model's open-source nature and strong performance make it a useful tool for researchers and developers working on Finnish and English language AI projects.

Things to try

One interesting aspect of the Poro-34B model is its ability to handle code along with natural language. You could try prompting the model with a programming task in English and see if it can generate the corresponding code. Or prompt it with Finnish text and see if it can accurately translate it to English. The model's large vocabulary and training on diverse data give it fascinating language understanding capabilities to explore.

This summary was produced with help from an AI and may contain inaccuracies - check out the links to read the original source documents!

Related Models




Total Score


The 30B-Lazarus model is the result of an experimental approach to combining several large language models and specialized LoRAs (Layers of Residual Adaption) to create an ensemble model with enhanced capabilities. The composition includes models such as SuperCOT, gpt4xalpaca, and StoryV2, along with the manticore-30b-chat-pyg-alpha and Vicuna Unlocked LoRA models. The maintainer, CalderaAI, indicates that this experimental approach aims to additively apply desired features without paradoxically watering down the model's effective behavior. Model inputs and outputs The 30B-Lazarus model is a text-to-text AI model, meaning it takes text as input and generates text as output. The model is primarily instructed-based, with the Alpaca instruct format being the primary input format. However, the maintainer suggests that the Vicuna instruct format may also work. Inputs Instruction**: Text prompts or instructions for the model to follow, often in the Alpaca or Vicuna instruct format. Context**: Additional context or information provided to the model to inform its response. Outputs Generated text**: The model's response to the provided input, which can range from short answers to longer, more detailed text. Capabilities The 30B-Lazarus model is designed to have enhanced capabilities in areas like reasoning, storytelling, and task-completion compared to the base LLaMA model. By combining several specialized models and LoRAs, the maintainer aims to create a more comprehensive and capable language model. However, the maintainer notes that further experimental testing and evaluation is required to fully understand the model's capabilities and limitations. What can I use it for? The 30B-Lazarus model could potentially be used for a variety of natural language processing tasks, such as question answering, text generation, and problem-solving. The maintainer suggests that the model may be particularly well-suited for text-based adventure games or interactive storytelling applications, where its enhanced storytelling and task-completion capabilities could be leveraged. Things to try When using the 30B-Lazarus model, the maintainer recommends experimenting with different presets and instructions to see how the model responds. They suggest trying out the "Godlike" and "Storywriter" presets in tools like KoboldAI or Text-Generation-WebUI, and adjusting parameters like output length and temperature to find the best settings for your use case. Additionally, exploring the model's ability to follow chain-of-thought reasoning or provide detailed, creative responses to open-ended prompts could be an interesting area to investigate further.

Read more

Updated Invalid Date




Total Score


The opus-mt-ru-en model is a transformer-based translation model developed by the Language Technology Research Group at the University of Helsinki. It is capable of translating text from Russian to English. This model is part of the OPUS-MT translation model collection, which provides open-source machine translation services for a variety of language pairs. Similar models in the OPUS-MT collection include the opus-mt-zh-en model, which translates from Chinese to English. These multilingual translation models can be useful for a range of applications that require text translation between different languages. Model inputs and outputs Inputs Source language:** Russian text Outputs Target language:** English text translated from the input Russian text Capabilities The opus-mt-ru-en model can be used to translate text from Russian to English. This can be useful for a variety of applications, such as multilingual communication, language learning, and content localization. What can I use it for? The opus-mt-ru-en model can be used for a variety of text-to-text generation and translation tasks. For example, you could use it to translate Russian web pages or documents into English, or to build a multilingual chatbot or customer support system. Things to try One interesting thing to try with the opus-mt-ru-en model is to experiment with the quality of the translations it produces. You could try translating a variety of Russian text, from news articles to literary excerpts, and evaluate the fluency and accuracy of the English output. This could help you understand the model's strengths and limitations, and identify areas for potential improvement.

Read more

Updated Invalid Date




Total Score


The bloom-3b is a large language model developed by the BigScience workshop, a collaborative research effort to create open-access multilingual language models. It is a transformer-based model trained on a diverse dataset of 46 natural languages and 13 programming languages, totaling 1.6TB of preprocessed text. This model is similar in scale to other large language models like bloom-7b1 and bloom-1b1, but with more parameters and a broader language coverage. Model inputs and outputs The bloom-3b is an autoregressive language model, meaning it takes text as input and generates additional text as output. It can be instructed to perform a variety of text generation tasks, such as continuing a given prompt, rewriting text with a different tone or perspective, or answering questions. Inputs Text prompt: A sequence of text that the model will use to generate additional content. Outputs Generated text: The model's continuation of the input prompt, producing coherent and contextually relevant text. Capabilities The bloom-3b model has impressive multilingual capabilities, able to generate fluent text in 46 natural languages and 13 programming languages. It can be used for a variety of text-based tasks, such as language translation, code generation, and creative writing. However, it is important to note that the model may exhibit biases and limitations, and its outputs should not be treated as factual or reliable in high-stakes settings. What can I use it for? The bloom-3b model can be used for a variety of language-related tasks, such as text generation, language translation, and code generation. For example, you could use it to generate creative stories, summarize long documents, or write code in multiple programming languages. The model's multilingual capabilities also make it a useful tool for cross-language communication and collaboration. Things to try One interesting thing to try with the bloom-3b model is to give it prompts that combine multiple languages or mix natural language and code. This can reveal insights about the model's understanding of language structure and its ability to switch between different modes of expression. Additionally, you can experiment with providing the model with prompts that require a specific tone, style, or perspective, and observe how it adapts its generated text accordingly.

Read more

Updated Invalid Date




Total Score


bloom-7b1 is a 7 billion parameter multilingual language model developed by the BigScience collaborative research workshop. It was pretrained on a large, diverse dataset of 341.6 billion tokens in 46 languages. The model uses a transformer-based architecture similar to GPT-2, with modifications such as layer normalization on the word embeddings, ALiBI positional encodings, and GeLU activation functions. bloom-7b1 is part of the larger BLOOM model family, which includes variants ranging from 560 million to 176 billion parameters. The BLOOMZ model is a finetuned version of bloom-7b1 that has been optimized for cross-lingual tasks and understanding. Model inputs and outputs bloom-7b1 is a text-to-text model that can be used for a variety of natural language processing tasks. It takes text as input and generates relevant text as output. Inputs Free-form text in multiple languages, such as prompts, instructions, or questions Outputs Relevant text responses generated based on the input The model can be used for tasks like translation, question answering, and open-ended text generation Capabilities bloom-7b1 has strong multilingual capabilities, able to understand and generate text in 46 different languages. The model has shown promising performance on a variety of benchmarks, including translation, language understanding, and open-ended generation tasks. What can I use it for? bloom-7b1 can be used for a wide range of natural language processing applications, such as: Translation**: Translating text between supported languages Question Answering**: Answering questions based on provided context Summarization**: Generating concise summaries of longer text Text Generation**: Producing coherent, human-like text based on prompts The model's multilingual capabilities make it particularly useful for projects that involve working with text in multiple languages. Developers and researchers can fine-tune bloom-7b1 on domain-specific data to adapt it for their particular use cases. Things to try Some interesting things to try with bloom-7b1 include: Experimenting with different prompting techniques to see how the model responds to various types of input Evaluating the model's performance on specialized benchmarks or datasets relevant to your application Exploring the model's ability to handle long-form text, such as generating multi-paragraph responses Investigating how the model's performance varies across different languages and language pairs By leveraging the capabilities of bloom-7b1, you can unlock new possibilities for your natural language processing projects.

Read more

Updated Invalid Date