llama-stack-mirror/tests/integration/common/recordings/97d4dfd277145b450a554e76a5bc25459ba0dfb68c05534d1cd4ca767bc8fa2c.json
Eric Huang c76bf97ccf test, recording
# What does this PR do?


## Test Plan
# What does this PR do?


## Test Plan
2025-10-08 14:57:06 -07:00

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 0"
}
],
"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-97d4dfd27714",
"choices": [
{
"finish_reason": "length",
"index": 0,
"logprobs": null,
"message": {
"content": "You want to test the `tracetool` (not \"trace\") from OpenAI's library, which is now called `Transformer-MLP` in Hugging Face Transformers library.\n\nHere is an example code snippet that tests the `TracerTool` with a temperature of 0:\n\n```python\nfrom transformers import Trainer, TracerTool\n\n# Initialize model, tokenizer, and training arguments\nmodel_name = \"bert-base-uncased\"\ntokenizer = AutoTokenizer.from_pretrained(model_name",
"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
}
}