json[[1]]
$id
[1] "azureml://registries/azureml-ai21/models/AI21-Jamba-Instruct/versions/2"

$name
[1] "AI21-Jamba-Instruct"

$friendly_name
[1] "AI21-Jamba-Instruct"

$model_version
[1] 2

$publisher
[1] "AI21 Labs"

$model_family
[1] "AI21 Labs"

$model_registry
[1] "azureml-ai21"

$license
[1] "custom"

$task
[1] "chat-completion"

$description
[1] "Jamba-Instruct is the world's first production-grade Mamba-based LLM model and leverages its hybrid Mamba-Transformer architecture to achieve best-in-class performance, quality, and cost efficiency.\n\n**Model Developer Name**: _AI21 Labs_\n\n## Model Architecture\n\nJamba-Instruct leverages a hybrid Mamba-Transformer architecture to achieve best-in-class performance, quality, and cost efficiency.\nAI21's Jamba architecture features a blocks-and-layers approach that allows Jamba to successfully integrate the two architectures. Each Jamba block contains either an attention or a Mamba layer, followed by a multi-layer perceptron (MLP), producing an overall ratio of one Transformer layer out of every eight total layers.\n"

$summary
[1] "Jamba-Instruct is the world's first production-grade Mamba-based LLM model and leverages its hybrid Mamba-Transformer architecture to achieve best-in-class performance, quality, and cost efficiency."

$tags
$tags[[1]]
[1] "chat"

$tags[[2]]
[1] "rag"

> models_github() |> dplyr::tibble()
# A tibble: 24 × 5
   id                           name                         publisher license task           
   <chr>                        <chr>                        <chr>     <chr>   <chr>          
 1 AI21-Jamba-Instruct          AI21-Jamba-Instruct          AI21 Labs custom  chat-completion
 2 Cohere-command-r             Cohere Command R             cohere    custom  chat-completion
 3 Cohere-command-r-plus        Cohere Command R+            cohere    custom  chat-completion
 4 Cohere-embed-v3-english      Cohere Embed v3 English      cohere    custom  embeddings     
 5 Cohere-embed-v3-multilingual Cohere Embed v3 Multilingual cohere    custom  embeddings     
 6 Meta-Llama-3-70B-Instruct    Meta-Llama-3-70B-Instruct    meta      custom  chat-completion
 7 Meta-Llama-3-8B-Instruct     Meta-Llama-3-8B-Instruct     meta      custom  chat-completion
 8 Meta-Llama-3.1-405B-Instruct Meta-Llama-3.1-405B-Instruct meta      custom  chat-completion
 9 Meta-Llama-3.1-70B-Instruct  Meta-Llama-3.1-70B-Instruct  meta      custom  chat-completion
10 Meta-Llama-3.1-8B-Instruct   Meta-Llama-3.1-8B-Instruct   meta      custom  chat-completion
# ℹ 14 more rows
# ℹ Use `print(n = ...)` to see more rows