Giter Club home page Giter Club logo

mistral.ai's Introduction

mistral.ai

R-CMD-check

The goal of mistral.ai is to …

Installation

You can install the development version of mistral.ai from GitHub with:

pak::pak("tadascience/mistral.ai")

Example

# available models
mistral.ai::models()
#>  [1] "open-mistral-7b"       "mistral-tiny-2312"     "mistral-tiny"         
#>  [4] "open-mixtral-8x7b"     "mistral-small-2312"    "mistral-small"        
#>  [7] "mistral-small-2402"    "mistral-small-latest"  "mistral-medium-latest"
#> [10] "mistral-medium-2312"   "mistral-medium"        "mistral-large-latest" 
#> [13] "mistral-large-2402"    "mistral-embed"

mistral.ai::chat("what is mistral ?")
#> ── assistant ───────────────────────────────────────────────────────────────────
#> Mistral is a French painter, born on December 30, 1887, in Maussane-VΓ©signeau, near Arles, in the south of France. His real name was Marcel Theodore Aurel Gustave ClΓ©ment, but he adopted the pseudonym "Mistral" as a homage to the famous Provencal poet FrΓ©dΓ©ric Mistral.
#> 
#> Mistral is best known for his vivid, colorful, and expressive paintings of the landscapes, people, and traditions of Provence. He was a key figure in the revival of interest in the art and culture of the region in the early 20th century.
#> 
#> Mistral's style was influenced by the Fauves, a group of artists who sought to break away from traditional representational art and explore the expressive use of color and form. He also drew inspiration from the Impressionist and Post-Impressionist movements, as well as from the folk art and traditions of Provence.
#> 
#> Mistral's work has been exhibited in major museums and galleries around the world, and he is considered one of the most important painters of the 20th century. He died in Paris on October 31, 1964.
mistral.ai::stream("fun facts mistral.ai")
#> Mistral AI is a cutting-edge company based in Paris, France, developing large language models. Here are some fun facts about Mistral AI:
#> 
#> 1. Founded in 2020: Mistral AI was founded in 2020 by Thomas Gotojevic, François-Xavier Carrier, and Adrien Duval, three researchers from the French National Institute for Computer Science and Applied Mathematics (INRIA).
#> 2. Focus on large language models: Mistral AI is known for its focus on developing large language models, which are artificial intelligence models capable of understanding and generating human-like text.
#> 3. Funding: The company has received significant funding, including a €100 million ($113 million) Series A round in March 2023, making it one of the largest AI funding rounds in Europe.
#> 4. Collaborations: Mistral AI has collaborated with various organizations, including the French National Center for Scientific Research (CNRS), the Γ‰cole des Ponts ParisTech, and the Γ‰cole Normale SupΓ©rieure (ENS).
#> 5. Open-source contributions: Mistral AI is committed to contributing to the open-source community. They have released various open-source projects, including the Mistral Model, a large language model that achieved state-of-the-art results on several benchmarks.
#> 6. Multilingual capabilities: Mistral AI's language models can generate text in multiple languages, including English, French, German, Italian, Spanish, and more.
#> 7. Interdisciplinary approach: Mistral AI's team comes from various backgrounds, including computer science, mathematics, physics, and linguistics, allowing for an interdisciplinary approach to AI research.
#> 8. Ethical considerations: Mistral AI is committed to addressing ethical considerations in AI research, including bias, fairness, and transparency. They have published papers on these topics and are actively engaging in discussions with stakeholders.
#> 9. Diverse applications: Mistral AI's language models have various applications, including language translation, text summarization, and text generation for creative writing and storytelling.
#> 10. Future plans: Mistral AI plans to continue developing large language models and exploring their applications in various fields, including education, healthcare, and creativity. They also aim to contribute to the development of a more ethical and transparent AI industry.

mistral.ai's People

Contributors

romainfrancois avatar felixmil avatar jameshwade avatar

Stargazers

Sounkou-bioinfo avatar Leo Lee avatar  avatar Andrew Allen Bruce avatar  avatar  avatar José de Jesus Filho avatar Marylène Henry avatar

Watchers

 avatar  avatar

mistral.ai's Issues

Ghost text for code suggestions

Should we add a ghost text option for code suggestions.

We would need to add:

  • addin to trigger code suggestions
  • package options to specify model
  • ghost test functions + helpers

I implemented this in gpttools here.

I'm learning so much from this mistral implementation, and I'm curious at how you'd approach it differently.

+ `check_model()`

Factor out this code into a check_model() or something:

available_models <- models(.call = current_env())
  if (!(model %in% available_models)) {
    cli::cli_abort(c(
      glue::glue("The model {model} is not available."),
      "i" = "Please use the {.code models()} function to see the available models."
    ))
  }

Rework the `check_model()` workflow

I think I'd like to avoid calling check_model() everytime.

Instead we could send the request as-is, perhaps asserting model is a string string, and then post process the failure we'd get, and if we identify this is a "model not available" kind of error, then we do models() so that the user knows what is available.

make `chat()` generic

wrt to its first argument, and add methods for :

  • character : like the one we currently have
  • chat_tibble: so that we can have follow up conversations with the πŸ€– , should chat_tibble be renamed conversation or just chat ?

Recommend Projects

  • React photo React

    A declarative, efficient, and flexible JavaScript library for building user interfaces.

  • Vue.js photo Vue.js

    πŸ–– Vue.js is a progressive, incrementally-adoptable JavaScript framework for building UI on the web.

  • Typescript photo Typescript

    TypeScript is a superset of JavaScript that compiles to clean JavaScript output.

  • TensorFlow photo TensorFlow

    An Open Source Machine Learning Framework for Everyone

  • Django photo Django

    The Web framework for perfectionists with deadlines.

  • D3 photo D3

    Bring data to life with SVG, Canvas and HTML. πŸ“ŠπŸ“ˆπŸŽ‰

Recommend Topics

  • javascript

    JavaScript (JS) is a lightweight interpreted programming language with first-class functions.

  • web

    Some thing interesting about web. New door for the world.

  • server

    A server is a program made to process requests and deliver data to clients.

  • Machine learning

    Machine learning is a way of modeling and interpreting data that allows a piece of software to respond intelligently.

  • Game

    Some thing interesting about game, make everyone happy.

Recommend Org

  • Facebook photo Facebook

    We are working to build community through open source technology. NB: members must have two-factor auth.

  • Microsoft photo Microsoft

    Open source projects and samples from Microsoft.

  • Google photo Google

    Google ❀️ Open Source for everyone.

  • D3 photo D3

    Data-Driven Documents codes.