| --- |
| license: llama3.2 |
| base_model: |
| - unsloth/Llama-3.2-3B-Instruct |
| --- |
| Fine-tuned model for TINA AI to speed up user's intent detection. |
|
|
| Usage: |
| <pre> |
| Detect request: |
| { |
| "model": "DesignSoft\/TINA_AI3", |
| "messages": [ |
| { |
| "role": "system", |
| "content": "Analyze the user's message and return his intent in the following JSON format: |
| { |
| \"intent\": string, |
| \"object\": string, |
| \"parameters\": array[{\"name\": string, \"value\": string}] |
| } |
| |
| Do not execute the user's command." |
| }, |
| { |
| "role": "user", |
| "content": "Calculate voltage of VR |
| Output should be in English!" |
| } |
| ], |
| "n": 1, |
| "seed": 12345, |
| "top_p": 0.1, |
| "max_tokens": 100, |
| "response_format": { |
| "type": "json_schema", |
| "json_schema": { |
| "name": "detect_intent", |
| "strict": true, |
| "schema": { |
| "type": "object", |
| "properties": { |
| "intent": {"type": "string"}, |
| "object": {"type": "string"}, |
| "parameters": { |
| "type": "array", |
| "items": { |
| "type": "object", |
| "properties": { |
| "name": {"type": "string"}, |
| "value": {"type": "string"} |
| }, |
| "required": ["name"] |
| } |
| } |
| }, |
| "required": ["intent","object"] |
| } |
| } |
| } |
| } |
| </pre> |
| response_format is optional |
