mirror of
https://github.com/meta-llama/llama-stack.git
synced 2025-10-15 14:43:48 +00:00
60 lines
1.9 KiB
JSON
60 lines
1.9 KiB
JSON
{
|
|
"test_id": null,
|
|
"request": {
|
|
"method": "POST",
|
|
"url": "http://0.0.0.0:11434/v1/v1/chat/completions",
|
|
"headers": {},
|
|
"body": {
|
|
"model": "llama3.2:3b-instruct-fp16",
|
|
"messages": [
|
|
{
|
|
"role": "user",
|
|
"content": "Test trace openai with temperature 1"
|
|
}
|
|
],
|
|
"max_tokens": 100,
|
|
"stream": false,
|
|
"temperature": 0.7,
|
|
"extra_body": {}
|
|
},
|
|
"endpoint": "/v1/chat/completions",
|
|
"model": "llama3.2:3b-instruct-fp16"
|
|
},
|
|
"response": {
|
|
"body": {
|
|
"__type__": "openai.types.chat.chat_completion.ChatCompletion",
|
|
"__data__": {
|
|
"id": "rec-62312134a706",
|
|
"choices": [
|
|
{
|
|
"finish_reason": "length",
|
|
"index": 0,
|
|
"logprobs": null,
|
|
"message": {
|
|
"content": "To test the OpenAI API with a temperature of 1, you'll need to use the `text-diffusion` model and pass in the `temperature` parameter. Here's an example using the `transformers` library:\n```python\nimport torch\nfrom transformers import AutoModelForCPT, AutoTokenizer\n\n# Load pre-trained model and tokenizer for text diffusion\nmodel_name = \"CompVis/textdiffusion\"\nmodel = AutoModelForCPT.from_pretrained(model_name)\ntokenizer",
|
|
"refusal": null,
|
|
"role": "assistant",
|
|
"annotations": null,
|
|
"audio": null,
|
|
"function_call": null,
|
|
"tool_calls": null
|
|
}
|
|
}
|
|
],
|
|
"created": 0,
|
|
"model": "llama3.2:3b-instruct-fp16",
|
|
"object": "chat.completion",
|
|
"service_tier": null,
|
|
"system_fingerprint": "fp_ollama",
|
|
"usage": {
|
|
"completion_tokens": 100,
|
|
"prompt_tokens": 33,
|
|
"total_tokens": 133,
|
|
"completion_tokens_details": null,
|
|
"prompt_tokens_details": null
|
|
}
|
|
}
|
|
},
|
|
"is_streaming": false
|
|
}
|
|
}
|