e0437afb2c
* chore: add OpenAI o3-mini model to ship with the app by default * chore: should not reload model on inference parameters update * chore: update cortex.cpp rc build
126 lines
3.0 KiB
JSON
126 lines
3.0 KiB
JSON
[
|
|
{
|
|
"model": "gpt-4-turbo",
|
|
"object": "model",
|
|
"name": "OpenAI GPT 4 Turbo",
|
|
"version": "1.2",
|
|
"description": "OpenAI GPT 4 Turbo model is extremely good",
|
|
"format": "api",
|
|
"inference_params": {
|
|
"max_tokens": 4096,
|
|
"temperature": 0.7,
|
|
"top_p": 0.95,
|
|
"stream": true,
|
|
"stop": [],
|
|
"frequency_penalty": 0,
|
|
"presence_penalty": 0
|
|
},
|
|
"engine": "openai"
|
|
},
|
|
{
|
|
"model": "gpt-3.5-turbo",
|
|
"object": "model",
|
|
"name": "OpenAI GPT 3.5 Turbo",
|
|
"version": "1.1",
|
|
"description": "OpenAI GPT 3.5 Turbo model is extremely fast",
|
|
"format": "api",
|
|
"inference_params": {
|
|
"max_tokens": 4096,
|
|
"temperature": 0.7,
|
|
"top_p": 0.95,
|
|
"stream": true,
|
|
"stop": [],
|
|
"frequency_penalty": 0,
|
|
"presence_penalty": 0
|
|
},
|
|
"engine": "openai"
|
|
},
|
|
{
|
|
"model": "gpt-4o",
|
|
"object": "model",
|
|
"name": "OpenAI GPT 4o",
|
|
"version": "1.1",
|
|
"description": "OpenAI GPT 4o is a new flagship model with fast speed and high quality",
|
|
"format": "api",
|
|
"inference_params": {
|
|
"max_tokens": 4096,
|
|
"temperature": 0.7,
|
|
"top_p": 0.95,
|
|
"stream": true,
|
|
"stop": [],
|
|
"frequency_penalty": 0,
|
|
"presence_penalty": 0
|
|
},
|
|
"engine": "openai"
|
|
},
|
|
{
|
|
"model": "gpt-4o-mini",
|
|
"object": "model",
|
|
"name": "OpenAI GPT 4o-mini",
|
|
"version": "1.1",
|
|
"description": "GPT-4o mini (“o” for “omni”) is a fast, affordable small model for focused tasks.",
|
|
"format": "api",
|
|
"inference_params": {
|
|
"max_tokens": 16384,
|
|
"temperature": 0.7,
|
|
"top_p": 0.95,
|
|
"stream": true,
|
|
"stop": [],
|
|
"frequency_penalty": 0,
|
|
"presence_penalty": 0
|
|
},
|
|
"engine": "openai"
|
|
},
|
|
{
|
|
"model": "o1",
|
|
"object": "model",
|
|
"name": "OpenAI o1",
|
|
"version": "1.0",
|
|
"description": "OpenAI o1 is a new model with complex reasoning",
|
|
"format": "api",
|
|
"inference_params": {
|
|
"max_tokens": 100000
|
|
},
|
|
"engine": "openai"
|
|
},
|
|
{
|
|
"model": "o1-preview",
|
|
"object": "model",
|
|
"name": "OpenAI o1-preview",
|
|
"version": "1.0",
|
|
"description": "OpenAI o1-preview is a new model with complex reasoning",
|
|
"format": "api",
|
|
"inference_params": {
|
|
"max_tokens": 32768,
|
|
"stream": true
|
|
},
|
|
"engine": "openai"
|
|
},
|
|
{
|
|
"model": "o1-mini",
|
|
"object": "model",
|
|
"name": "OpenAI o1-mini",
|
|
"version": "1.0",
|
|
"description": "OpenAI o1-mini is a lightweight reasoning model",
|
|
"format": "api",
|
|
"inference_params": {
|
|
"max_tokens": 65536,
|
|
"stream": true
|
|
},
|
|
"engine": "openai"
|
|
},
|
|
{
|
|
"model": "o3-mini",
|
|
"object": "model",
|
|
"name": "OpenAI o3-mini",
|
|
"version": "1.0",
|
|
"description": "OpenAI most recent reasoning model, providing high intelligence at the same cost and latency targets of o1-mini.",
|
|
"format": "api",
|
|
"inference_params": {
|
|
"max_tokens": 100000,
|
|
"stream": true
|
|
},
|
|
"engine": "openai"
|
|
}
|
|
]
|