From 71c47d4eae2960aea9a7965834b336cdf4eed647 Mon Sep 17 00:00:00 2001 From: trentfowlercohere <141260477+trentfowlercohere@users.noreply.github.com> Date: Fri, 13 Dec 2024 10:04:34 -0700 Subject: [PATCH] Preparing the docs for Command R7B. (#296) * Preparing the docs. * Adding verbiage to the v2 pages as well. * Adding a link to the blog post. --------- Co-authored-by: Trent Fowler --- .../changelog/2024-12-13-command-r-7b-is-here.mdx | 12 ++++++++++++ fern/pages/models/models.mdx | 2 ++ .../the-command-family-of-models/command-r-plus.mdx | 10 ++++++++++ .../the-command-family-of-models/command-r.mdx | 10 ++++++++++ .../the-command-family-of-models/command-r-plus.mdx | 10 ++++++++++ .../the-command-family-of-models/command-r.mdx | 10 ++++++++++ 6 files changed, 54 insertions(+) create mode 100644 fern/pages/changelog/2024-12-13-command-r-7b-is-here.mdx diff --git a/fern/pages/changelog/2024-12-13-command-r-7b-is-here.mdx b/fern/pages/changelog/2024-12-13-command-r-7b-is-here.mdx new file mode 100644 index 00000000..5cb1d00b --- /dev/null +++ b/fern/pages/changelog/2024-12-13-command-r-7b-is-here.mdx @@ -0,0 +1,12 @@ +--- +title: "Announcing Command R7b" +slug: "changelog/command-r-7b" +createdAt: "Fri Dec 13 2024 00:00:00 (MST)" +hidden: false +description: >- + Release announcment for Command R 7B - our fastest, lightest, and last Command R model. +--- + +We're thrilled to announce the release of Command R7B, the smallest, fastest, and final model in our R family of enterprise-focused [large language models](https://docs.cohere.com/docs/introduction-to-large-language-models) (LLMs). With a context window of 128K, Command R7B offers state-of-the-art performance across a variety of real-world tasks, and is designed for use cases in which speed, cost, and compute are important. Specifically, Command R7B is excellent for [retrieval-augmented generation](https://docs.cohere.com/docs/retrieval-augmented-generation-rag), [tool use](https://docs.cohere.com/docs/tool-use), and [agentic applications](https://docs.cohere.com/docs/multi-step-tool-use) where complex reasoning, multiple actions, and information-seeking are important for success. + +Command R7B is available today on the [Cohere Platform](https://docs.cohere.com/docs/the-cohere-platform) as well as accessible on HuggingFace, or you can access it in the SDK with `command-r7b-12-2024`. For more information, check out our [dedicated blog post](cohere.com/blog/command-r7b). \ No newline at end of file diff --git a/fern/pages/models/models.mdx b/fern/pages/models/models.mdx index d06af7e4..aa53eb7c 100644 --- a/fern/pages/models/models.mdx +++ b/fern/pages/models/models.mdx @@ -39,6 +39,7 @@ Command is Cohere's default generation model that takes a user instruction (or c | Model Name | Description | Modality | Context Length | Maximum Output Tokens | Endpoints | |--------------------------|------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------|-------------------|----------------|-----------------------|-------------------------------------------------------------------------------------------| +| `command-r7b-12-2024` | `command-r7b-12-2024` is a small, fast update of the Command R+ model, delivered in December 2024. It excels at RAG, tool use, agents, and similar tasks requiring complex reasoning and multiple steps. | Text | 128k | 4k | [Chat](/reference/chat)| | `command-r-plus-08-2024` | `command-r-plus-08-2024` is an update of the Command R+ model, delivered in August 2024. Find more information [here](https://docs.cohere.com/changelog/command-gets-refreshed) | Text | 128k | 4k | [Chat](/reference/chat) | | `command-r-plus-04-2024` | Command R+ is an instruction-following conversational model that performs language tasks at a higher quality, more reliably, and with a longer context than previous models. It is best suited for complex RAG workflows and multi-step tool use. | Text | 128k | 4k | [Chat](/reference/chat) | | `command-r-plus` | `command-r-plus` is an alias for `command-r-plus-04-2024`, so if you use `command-r-plus` in the API, that's the model you're pointing to. | Text | 128k | 4k | [Chat](/reference/chat) | @@ -59,6 +60,7 @@ In this table, we provide some important context for using Cohere Command models | Model Name | Amazon Bedrock Model ID | Amazon SageMaker | Azure AI Studio Model ID | Oracle OCI Generative AI Service | | :---------------------- | :------------------------------ | :-------------------- | :----------------------- | :------------------------------- | +| `command-r7b-12-2024` | (Coming soon) | (Coming soon) | (Coming soon) | (Coming soon) | | `command-r-plus` | `cohere.command-r-plus-v1:0` | Unique per deployment | Unique per deployment | `cohere.command-r-plus v1.2` | | `command-r` | `cohere.command-r-v1:0` | Unique per deployment | Unique per deployment | `cohere.command-r-16k v1.2` | | `command` | `cohere.command-text-v14` | N/A | N/A | `cohere.command v15.6` | diff --git a/fern/pages/models/the-command-family-of-models/command-r-plus.mdx b/fern/pages/models/the-command-family-of-models/command-r-plus.mdx index 6f59167f..575faa44 100644 --- a/fern/pages/models/the-command-family-of-models/command-r-plus.mdx +++ b/fern/pages/models/the-command-family-of-models/command-r-plus.mdx @@ -21,10 +21,20 @@ For information on toxicity, safety, and using this model responsibly check out ### Model Details | Model Name | Description | Modality | Context Length | Maximum Output Tokens | Endpoints | |--------------------------|-----------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------|----------------------|----------------|-----------------------|------------------------| +| `command-r7b-12-2024` | `command-r7b-12-2024` is a small, fast update of the Command R+ model, delivered in December 2024. It excels at RAG, tool use, agents, and similar tasks requiring complex reasoning and multiple steps. | Text | 128k | 4k | [Chat](/reference/chat)| | `command-r-plus-08-2024` | `command-r-plus-08-2024` is an update of the Command R+ model, delivered in August 2024. | Text | 128k | 4k | [Chat](/reference/chat)| | `command-r-plus-04-2024` | Command R+ is an instruction-following conversational model that performs language tasks at a higher quality, more reliably, and with a longer context than previous models. It is best suited for complex RAG workflows and multi-step tool use. | Text | 128k | 4k | [Chat](/reference/chat)| | `command-r-plus` | `command-r-plus` is an alias for `command-r-plus-04-2024`, so if you use `command-r-plus` in the API, that's the model you're pointing to. | Text | 128k | 4k | [Chat](/reference/chat)| +## Command R7B December 2024 Release +Command R7B is the smallest, fastest, and final model in our R family of enterprise-focused [large language models](https://docs.cohere.com/docs/introduction-to-large-language-models) (LLMs). With a context window of 128K, Command R7B offers state-of-the-art performance across a variety of real-world tasks, and is designed for use cases in which speed, cost, and compute are important. Specifically, Command R7B is excellent for: + +- RAG - [Retrieval Augmented Generation](https://docs.cohere.com/docs/retrieval-augmented-generation-rag) (RAG) refers to the practice of ‘grounding’ model outputs in external data sources, which can increase accuracy. Command R7B is exceptionally good at generating responses in conversational tasks, attending over long inputs, and extracting and manipulating numerical information in financial settings. +- Tool-use - With [tool use](https://docs.cohere.com/docs/tool-use), Command models can be given tools such as search engines, APIs, vector databases, etc., which can expand their baseline functionality. Command R7B excels at tool use, exhibiting particular strength in using tools in real-world, diverse, and dynamic environments. In addition, Command R7B is good at avoiding unnecessarily calling tools, which is an important aspect of tool-use in practical applications. +- Agents - As this is being written, [agents](https://docs.cohere.com/docs/multi-step-tool-use) are among the most exciting frontiers for large language models. Command R7B’s multistep tool use capabilities allow it to power fast and capable REACT agents. When set up as an internet-augmented research agent, for example, Command R7B ably completes tasks that require breaking down complex questions into subgoals, and also performs favorably in domains that utilize complex reasoning and active information seeking. + +Command R7B is available today on the Cohere Platform as well as accessible on HuggingFace, or you can access it in the SDK with `command-r7b-12-2024`. For more information, check out our [dedicated blog post](cohere.com/blog/command-r7b). + ## Command R+ August 2024 Release Cohere's flagship text-generation models, Command R and Command R+, received a substantial update in August 2024. We chose to designate these models with time stamps, so in the API Command R+ 08-2024 is accesible with `command-r-plus-08-2024`. diff --git a/fern/pages/models/the-command-family-of-models/command-r.mdx b/fern/pages/models/the-command-family-of-models/command-r.mdx index 6e35d2ba..434e1015 100644 --- a/fern/pages/models/the-command-family-of-models/command-r.mdx +++ b/fern/pages/models/the-command-family-of-models/command-r.mdx @@ -22,10 +22,20 @@ For information on toxicity, safety, and using this model responsibly check out ### Model Details | Model Name | Description | Modality | Context Length | Maximum Output Tokens | Endpoints| |--------------------------|------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------|-------------------------|----------------|-----------------------|----------| +| `command-r7b-12-2024` | `command-r7b-12-2024` is a small, fast update of the Command R+ model, delivered in December 2024. It excels at RAG, tool use, agents, and similar tasks requiring complex reasoning and multiple steps. | Text | 128k | 4k | [Chat](/reference/chat) | | `command-r-08-2024` | `command-r-08-2024` is an update of the Command R model, delivered in August 2024. | Text | 128k | 4k | [Chat](/reference/chat) | | | `command-r-03-2024` | Command R is an instruction-following conversational model that performs language tasks at a higher quality, more reliably, and with a longer context than previous models. It can be used for complex workflows like code generation, retrieval augmented generation (RAG), tool use, and agents. | Text | 128k | 4k | [Chat](/reference/chat) | | | `command-r` | `command-r` is an alias for `command-r-03-2024`, so if you use `command-r` in the API, that's the model you're pointing to. | Text | 128k | 4k | [Chat](/reference/chat) | | +## Command R7B December 2024 Release +Command R7B is the smallest, fastest, and final model in our R family of enterprise-focused [large language models](https://docs.cohere.com/docs/introduction-to-large-language-models) (LLMs). With a context window of 128K, Command R7B offers state-of-the-art performance across a variety of real-world tasks, and is designed for use cases in which speed, cost, and compute are important. Specifically, Command R7B is excellent for: + +- RAG - [Retrieval Augmented Generation](https://docs.cohere.com/docs/retrieval-augmented-generation-rag) (RAG) refers to the practice of ‘grounding’ model outputs in external data sources, which can increase accuracy. Command R7B is exceptionally good at generating responses in conversational tasks, attending over long inputs, and extracting and manipulating numerical information in financial settings. +- Tool-use - With [tool use](https://docs.cohere.com/docs/tool-use), Command models can be given tools such as search engines, APIs, vector databases, etc., which can expand their baseline functionality. Command R7B excels at tool use, exhibiting particular strength in using tools in real-world, diverse, and dynamic environments. In addition, Command R7B is good at avoiding unnecessarily calling tools, which is an important aspect of tool-use in practical applications. +- Agents - As this is being written, [agents](https://docs.cohere.com/docs/multi-step-tool-use) are among the most exciting frontiers for large language models. Command R7B’s multistep tool use capabilities allow it to power fast and capable REACT agents. When set up as an internet-augmented research agent, for example, Command R7B ably completes tasks that require breaking down complex questions into subgoals, and also performs favorably in domains that utilize complex reasoning and active information seeking. + +Command R7B is available today on the Cohere Platform as well as accessible on HuggingFace, or you can access it in the SDK with `command-r7b-12-2024`. For more information, check out our [dedicated blog post](cohere.com/blog/command-r7b). + ## Command R August 2024 Release Cohere's flagship text-generation models, Command R and Command R+, received a substantial update in August 2024. We chose to designate these models with time stamps, so in the API Command R 08-2024 is accesible with `command-r-08-2024`. diff --git a/fern/pages/v2/models/the-command-family-of-models/command-r-plus.mdx b/fern/pages/v2/models/the-command-family-of-models/command-r-plus.mdx index a216fc17..898ddc7a 100644 --- a/fern/pages/v2/models/the-command-family-of-models/command-r-plus.mdx +++ b/fern/pages/v2/models/the-command-family-of-models/command-r-plus.mdx @@ -21,10 +21,20 @@ For information on toxicity, safety, and using this model responsibly check out ### Model Details | Model Name | Description | Modality | Context Length | Maximum Output Tokens | Endpoints | |--------------------------|-----------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------|----------------------|----------------|-----------------------|------------------------| +| `command-r7b-12-2024` | `command-r7b-12-2024` is a small, fast update of the Command R+ model, delivered in December 2024. It excels at RAG, tool use, agents, and similar tasks requiring complex reasoning and multiple steps. | Text | 128k | 4k | [Chat](/reference/chat)| | `command-r-plus-08-2024` | `command-r-plus-08-2024` is an update of the Command R+ model, delivered in August 2024. | Text | 128k | 4k | [Chat](/reference/chat)| | `command-r-plus-04-2024` | Command R+ is an instruction-following conversational model that performs language tasks at a higher quality, more reliably, and with a longer context than previous models. It is best suited for complex RAG workflows and multi-step tool use. | Text | 128k | 4k | [Chat](/reference/chat)| | `command-r-plus` | `command-r-plus` is an alias for `command-r-plus-04-2024`, so if you use `command-r-plus` in the API, that's the model you're pointing to. | Text | 128k | 4k | [Chat](/reference/chat)| +## Command R7B December 2024 Release +Command R7B is the smallest, fastest, and final model in our R family of enterprise-focused [large language models](https://docs.cohere.com/docs/introduction-to-large-language-models) (LLMs). With a context window of 128K, Command R7B offers state-of-the-art performance across a variety of real-world tasks, and is designed for use cases in which speed, cost, and compute are important. Specifically, Command R7B is excellent for: + +- RAG - [Retrieval Augmented Generation](https://docs.cohere.com/docs/retrieval-augmented-generation-rag) (RAG) refers to the practice of ‘grounding’ model outputs in external data sources, which can increase accuracy. Command R7B is exceptionally good at generating responses in conversational tasks, attending over long inputs, and extracting and manipulating numerical information in financial settings. +- Tool-use - With [tool use](https://docs.cohere.com/docs/tool-use), Command models can be given tools such as search engines, APIs, vector databases, etc., which can expand their baseline functionality. Command R7B excels at tool use, exhibiting particular strength in using tools in real-world, diverse, and dynamic environments. In addition, Command R7B is good at avoiding unnecessarily calling tools, which is an important aspect of tool-use in practical applications. +- Agents - As this is being written, [agents](https://docs.cohere.com/docs/multi-step-tool-use) are among the most exciting frontiers for large language models. Command R7B’s multistep tool use capabilities allow it to power fast and capable REACT agents. When set up as an internet-augmented research agent, for example, Command R7B ably completes tasks that require breaking down complex questions into subgoals, and also performs favorably in domains that utilize complex reasoning and active information seeking. + +Command R7B is available today on the Cohere Platform as well as accessible on HuggingFace, or you can access it in the SDK with `command-r7b-12-2024`. For more information, check out our [dedicated blog post](cohere.com/blog/command-r7b). + ## Command R+ August 2024 Release Cohere's flagship text-generation models, Command R and Command R+, received a substantial update in August 2024. We chose to designate these models with time stamps, so in the API Command R+ 08-2024 is accesible with `command-r-plus-08-2024`. diff --git a/fern/pages/v2/models/the-command-family-of-models/command-r.mdx b/fern/pages/v2/models/the-command-family-of-models/command-r.mdx index 6eea77de..c5df5bf9 100644 --- a/fern/pages/v2/models/the-command-family-of-models/command-r.mdx +++ b/fern/pages/v2/models/the-command-family-of-models/command-r.mdx @@ -20,10 +20,20 @@ For information on toxicity, safety, and using this model responsibly check out ### Model Details | Model Name | Description | Modality | Context Length | Maximum Output Tokens | Endpoints| |--------------------------|------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------|-------------------------|----------------|-----------------------|----------| +| `command-r7b-12-2024` | `command-r7b-12-2024` is a small, fast update of the Command R+ model, delivered in December 2024. It excels at RAG, tool use, agents, and similar tasks requiring complex reasoning and multiple steps. | Text | 128k | 4k | [Chat](/reference/chat) | | `command-r-08-2024` | `command-r-08-2024` is an update of the Command R model, delivered in August 2024. | Text | 128k | 4k | [Chat](/reference/chat) | | | `command-r-03-2024` | Command R is an instruction-following conversational model that performs language tasks at a higher quality, more reliably, and with a longer context than previous models. It can be used for complex workflows like code generation, retrieval augmented generation (RAG), tool use, and agents. | Text | 128k | 4k | [Chat](/reference/chat) | | | `command-r` | `command-r` is an alias for `command-r-03-2024`, so if you use `command-r` in the API, that's the model you're pointing to. | Text | 128k | 4k | [Chat](/reference/chat) | | +## Command R7B December 2024 Release +Command R7B is the smallest, fastest, and final model in our R family of enterprise-focused [large language models](https://docs.cohere.com/docs/introduction-to-large-language-models) (LLMs). With a context window of 128K, Command R7B offers state-of-the-art performance across a variety of real-world tasks, and is designed for use cases in which speed, cost, and compute are important. Specifically, Command R7B is excellent for: + +- RAG - [Retrieval Augmented Generation](https://docs.cohere.com/docs/retrieval-augmented-generation-rag) (RAG) refers to the practice of ‘grounding’ model outputs in external data sources, which can increase accuracy. Command R7B is exceptionally good at generating responses in conversational tasks, attending over long inputs, and extracting and manipulating numerical information in financial settings. +- Tool-use - With [tool use](https://docs.cohere.com/docs/tool-use), Command models can be given tools such as search engines, APIs, vector databases, etc., which can expand their baseline functionality. Command R7B excels at tool use, exhibiting particular strength in using tools in real-world, diverse, and dynamic environments. In addition, Command R7B is good at avoiding unnecessarily calling tools, which is an important aspect of tool-use in practical applications. +- Agents - As this is being written, [agents](https://docs.cohere.com/docs/multi-step-tool-use) are among the most exciting frontiers for large language models. Command R7B’s multistep tool use capabilities allow it to power fast and capable REACT agents. When set up as an internet-augmented research agent, for example, Command R7B ably completes tasks that require breaking down complex questions into subgoals, and also performs favorably in domains that utilize complex reasoning and active information seeking. + +Command R7B is available today on the Cohere Platform as well as accessible on HuggingFace, or you can access it in the SDK with `command-r7b-12-2024`. For more information, check out our [dedicated blog post](cohere.com/blog/command-r7b). + ## Command R August 2024 Release Cohere's flagship text-generation models, Command R and Command R+, received a substantial update in August 2024. We chose to designate these models with time stamps, so in the API Command R 08-2024 is accesible with `command-r-08-2024`.