diff --git a/.gitignore b/.gitignore index ebfa0c9..0018df1 100644 --- a/.gitignore +++ b/.gitignore @@ -131,3 +131,6 @@ dist # docusaurus build build/ + +# CI things +changes.diff \ No newline at end of file diff --git a/docs/intro.md b/docs/intro.md index f16678d..816e6ef 100644 --- a/docs/intro.md +++ b/docs/intro.md @@ -12,7 +12,8 @@ Mistral AI currently provides two types of access to Large Language Models: ## Where to start? ### API Access -Our API is currently in beta to ramp up the load and provide good quality of service. Access the [platform](https://console.mistral.ai/) to join the waitlist. Once your subscription is active, you can immediately use our `chat` endpoint: + +Our API is currently available through our [platform](https://console.mistral.ai/). You need to subscribe and enter your payment details to enable your API keys. After a few moments, you will be able to use our `chat` endpoint: ```bash curl --location "https://api.mistral.ai/v1/chat/completions" \ @@ -38,9 +39,9 @@ curl --location "https://api.mistral.ai/v1/embeddings" \ }' ``` -For a full description of the models offered on the API, head on to the **[model docs](./models)**. +For a full description of the models offered on the API, head on to the **[model documentation](./models)**. -For more examples on how to use our platform, head on to our **[platform docs](./platform/01-overview.md)**. +For more examples on how to use our platform, head on to our **[platform documentation](./platform/01-overview.md)**. ### Raw model weights diff --git a/docs/models.md b/docs/models.md index 63229c4..38a79c9 100644 --- a/docs/models.md +++ b/docs/models.md @@ -17,10 +17,10 @@ Mixtral 8X7B is a sparse mixture of experts model. As such, it leverages up to 4 ## Downloading -- Mistral-7B-v0.1: [Hugging Face](https://huggingface.co/mistralai/Mistral-7B-v0.1) // [raw_weights](https://files.mistral-7b-v0-1.mistral.ai/mistral-7B-v0.1.tar) (md5sum: `37dab53973db2d56b2da0a033a15307f`). -- Mistral-7B-Instruct-v0.2: [Hugging Face](https://huggingface.co/mistralai/Mistral-7B-Instruct-v0.2) // [raw_weights](https://files.mistral-7b-v0-2.mistral.ai/Mistral-7B-v0.2-Instruct.tar) (md5sum: `fbae55bc038f12f010b4251326e73d39`). +- Mistral-7B-v0.1: [Hugging Face](https://huggingface.co/mistralai/Mistral-7B-v0.1) // [raw_weights](https://models.mistralcdn.com/mistral-7b-v0-1/mistral-7B-v0.1.tar) (md5sum: `37dab53973db2d56b2da0a033a15307f`). +- Mistral-7B-Instruct-v0.2: [Hugging Face](https://huggingface.co/mistralai/Mistral-7B-Instruct-v0.2) // [raw_weights](https://models.mistralcdn.com/mistral-7b-v0-2/Mistral-7B-v0.2-Instruct.tar) (md5sum: `fbae55bc038f12f010b4251326e73d39`). - Mixtral-8x7B-v0.1: [Hugging Face](https://huggingface.co/mistralai/Mixtral-8x7B-v0.1). -- Mixtral-8x7B-Instruct-v0.1: [Hugging Face](https://huggingface.co/mistralai/Mixtral-8x7B-Instruct-v0.1) // [raw_weights](https://files.mixtral-8x7b-v0-1.mistral.ai/Mixtral-8x7B-v0.1-Instruct.tar) (md5sum: `8e2d3930145dc43d3084396f49d38a3f`). +- Mixtral-8x7B-Instruct-v0.1: [Hugging Face](https://huggingface.co/mistralai/Mixtral-8x7B-Instruct-v0.1) // [raw_weights](https://models.mistralcdn.com/mixtral-8x7b-v0-1/Mixtral-8x7B-v0.1-Instruct.tar) (md5sum: `8e2d3930145dc43d3084396f49d38a3f`). ## Sizes diff --git a/docs/platform/03-endpoints.md b/docs/platform/03-endpoints.md index 0434206..2bc00be 100644 --- a/docs/platform/03-endpoints.md +++ b/docs/platform/03-endpoints.md @@ -11,9 +11,57 @@ We provide different endpoints with different price/performance tradeoffs. Our e All our generative endpoints can reason on contexts up to 32k tokens and follow fine-grained instructions. The following table gathers benchmarks for each endpoint. - -Benchmark - + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + +
Mistral-tinyMistral-smallMistral-medium
MMLU
(MCQ in 57 subjects)		63.0%70.6%75.3%
HellaSwag
(10-shot)		83.1%86.7%88.0%
ARC Challenge
(25-shot)		78.1%85.8%89.9%
WinoGrande
(5-shot)		78.0%81.2%88.0%
MBPP
(pass@1)		30.5%60.7%62.3%
GSM-8K
(5-shot)		36.5%58.4%66.7%
MT Bench
(for Instruct models)		7.618.308.61
We only provide chat access through our API. Users can access underlying base models for endpoints relying on [open-weight models](../../models). diff --git a/docs/platform/06-changelog.md b/docs/platform/06-changelog.md new file mode 100644 index 0000000..8ed7f63 --- /dev/null +++ b/docs/platform/06-changelog.md @@ -0,0 +1,10 @@ +# Changelog + +This is the list of changes to the Mistral API. + +Jan. 11, 2024 +- We have enhanced the API's strictness. Previously the API would silently ignores unsupported parameters in the requests, but it now strictly enforces the validity of all parameters. If you have unsupported parameters in your request, you will see the error message "Extra inputs are not permitted". +- A previous version of the [guardrailing documentation](../guardrailing) incorrectly referred to the API parameter as `safe_mode` instead of `safe_prompt`. We corrected this in the documentation. + +Jan. 16, 2024 +- We added token usage information in streaming requests. You can find it in the last chunk returned. diff --git a/docusaurus.config.js b/docusaurus.config.js index 3184e5e..a0ddbed 100644 --- a/docusaurus.config.js +++ b/docusaurus.config.js @@ -109,6 +109,11 @@ const config = { label: "GitHub", position: "right", }, + { + href: "https://discord.gg/mistralai", + label: "Discord", + position: "right", + }, ], }, footer: { diff --git a/version.txt b/version.txt new file mode 100644 index 0000000..a3dce6c --- /dev/null +++ b/version.txt @@ -0,0 +1 @@ +v0.0.2