diff --git a/README.md b/README.md index 4b666767a..5ff896ebb 100644 --- a/README.md +++ b/README.md @@ -100,7 +100,7 @@ Table of parameters | `ngl` | Integer | The number of GPU layers to use. | | `ctx_len` | Integer | The context length for the model operations. | | `embedding` | Boolean | Whether to use embedding in the model. | -| `n_parallel` | Integer | The number of parallel operations. Uses Drogon thread count if not set. | +| `n_parallel` | Integer | The number of parallel operations. | | `cont_batching` | Boolean | Whether to use continuous batching. | | `user_prompt` | String | The prompt to use for the user. | | `ai_prompt` | String | The prompt to use for the AI assistant. | diff --git a/docs/openapi/NitroAPI.yaml b/docs/openapi/NitroAPI.yaml index 847b9f0be..a2b25940c 100644 --- a/docs/openapi/NitroAPI.yaml +++ b/docs/openapi/NitroAPI.yaml @@ -2,7 +2,7 @@ openapi: 3.0.0 info: title: Nitro API description: Please see https://nitro.jan.ai/ for documentation. -version: "0.1.8" +version: "0.1.19" contact: name: Nitro Discord url: https://github.com/janhq/nitro @@ -231,8 +231,8 @@ components: description: Whether to use continuous batching. n_parallel: type: integer - default: Automatically set to Dragon threads - example: 4 + default: 1 + example: 1 nullable: true description: The number of parallel operations. Only set when enable continuous batching. cpu_threads: @@ -563,11 +563,15 @@ components: description: Defines specific tokens or phrases at which the model will stop generating further output frequency_penalty: type: number + min: 0 + max: 2 default: 0 description: Adjusts the likelihood of the model repeating words or phrases in its output presence_penalty: type: number default: 0 + min: 0 + max: 2 description: Influences the generation of new and varied concepts in the model's output temperature: type: number