| Generation Give instructions to
generate text or extract information from your text. |
cohere.command
- Version 15.6
- Model has 52 billion parameters.
- User prompt and response can be up to 4096 tokens for each run.
cohere.command-light
- Version 15.6
- Model has 6 billion parameters.
- User prompt and response can be up to 4096 tokens for each run.
meta.llama-2-70b-chat
- Version 1.0
- Model has 70 billion parameters.
- User prompt and response can be up to 4096 tokens for each run.
References: Cohere models and Llama 2 models
|
Generation model parameters:
- Maximum tokens
- Temperature
- Top p
- Top k
- Stop sequences
- Frequency penalty
- Presence penalty
- Show likelihoods (available only for Cohere models)
|
| Summarization Summarize text with
your instructed format, length, and tone. |
cohere.command
- Version 15.6
- Model has 52 billion parameters.
- User prompt and response can be up to 4096 tokens for each run.
Reference: Cohere models
|
Summarization model parameters:
- Length
- Format
- Extractiveness
- Temperature
- Additional command
|
| Embeddings Convert text to vector
embeddings to use in applications for semantic searches, text classification, or
text clustering. |
cohere.embed-english-v3.0and cohere.embed-multilingual-v3.0
- English or multilingual.
- Model creates a 1024-dimensional vector for each embedding.
- Maximum 96 sentences per run.
- Maximum 512 tokens per embedding.
cohere.embed-english-light-v3.0 and cohere.embed-multilingual-light-v3.0
- Light models are smaller and faster than the original models.
- English or multilingual.
- Model creates a 384-dimensional vector for each embedding.
- Maximum 96 sentences per run.
- Maximum 512 tokens per embedding.
cohere.embed-english-light-v2.0
- Light models are smaller and faster than the original models.
- English
- Model creates a 1024-dimensional vector for each embedding.
- Maximum 96 sentences per run.
- Maximum 512 tokens per embedding.
Reference: Cohere models
|
Embedding model parameter:
|