chore: clarification changes to the model settings and model parameters

This commit is contained in:
tikikun 2023-11-28 11:02:42 +07:00
parent 0ffc81e0f8
commit 04cdfa0dda

View File

@ -70,11 +70,14 @@ Here's a standard example `model.json` for a GGUF model.
"n_parallel": "4", "n_parallel": "4",
}, },
"parameters": { // Models are called parameters "parameters": { // Models are called parameters
"stream": "true",
"model": "gpt-3.5-turbo",
"max_tokens": "2048",
"stop": ["<endofstring>"], // This usually can be left blank, only used with specific need from model author
"frequency_penalty": "0",
"presence_penalty": "0",
"temperature": "0.7", "temperature": "0.7",
"token_limit": "2048", "top_p": "0.95"
"top_k": "0",
"top_p": "1",
"stream": "true"
}, },
"metadata": {}, // Defaults to {} "metadata": {}, // Defaults to {}
"assets": [ // Defaults to current dir "assets": [ // Defaults to current dir
@ -82,6 +85,10 @@ Here's a standard example `model.json` for a GGUF model.
] ]
``` ```
The model settings in the example can be found at: (Nitro's model settings)[https://nitro.jan.ai/features/load-unload#table-of-parameters]
The model paramemters in the example can be found at: (Nitro's model parameters)[https://nitro.jan.ai/api-reference#tag/Chat-Completion]
## API Reference ## API Reference
Jan's Model API is compatible with [OpenAI's Models API](https://platform.openai.com/docs/api-reference/models), with additional methods for managing and running models locally. Jan's Model API is compatible with [OpenAI's Models API](https://platform.openai.com/docs/api-reference/models), with additional methods for managing and running models locally.