mirror of
https://github.com/meta-llama/llama-stack.git
synced 2025-12-03 09:53:45 +00:00
1562277cfd
Without this hint Qwen3-0.6B tends to reply with the full name and sometimes doesn't reply with the correct drafted year. --------- Signed-off-by: Derek Higgins <derekh@redhat.com> Co-authored-by: github-actions[bot] <github-actions[bot]@users.noreply.github.com> Co-authored-by: Ashwin Bharambe <ashwin.bharambe@gmail.com>
60 lines
2.1 KiB
JSON
Generated
60 lines
2.1 KiB
JSON
Generated
{
|
|
"test_id": "tests/integration/telemetry/test_completions.py::test_telemetry_format_completeness[txt=ollama/llama3.2:3b-instruct-fp16]",
|
|
"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 0.7"
|
|
}
|
|
],
|
|
"max_tokens": 100,
|
|
"stream": false,
|
|
"temperature": 0.7
|
|
},
|
|
"endpoint": "/v1/chat/completions",
|
|
"model": "llama3.2:3b-instruct-fp16"
|
|
},
|
|
"response": {
|
|
"body": {
|
|
"__type__": "openai.types.chat.chat_completion.ChatCompletion",
|
|
"__data__": {
|
|
"id": "rec-1fcfd86d8111",
|
|
"choices": [
|
|
{
|
|
"finish_reason": "length",
|
|
"index": 0,
|
|
"logprobs": null,
|
|
"message": {
|
|
"content": "I can guide you through the process, but please note that testing OpenAI's models requires a bit of setup and potential API limits.\n\nOpenAI's API is designed to be used in a controlled environment for research purposes. You need an account on their platform and access to the API key.\n\nHere's how you can test a model with temperature 0.7 using Python:\n\n```python\nimport numpy as np\n\n# Replace 'YOUR_API_KEY' with your actual OpenAI API key.\nAPI_KEY",
|
|
"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": 35,
|
|
"total_tokens": 135,
|
|
"completion_tokens_details": null,
|
|
"prompt_tokens_details": null
|
|
}
|
|
}
|
|
},
|
|
"is_streaming": false
|
|
},
|
|
"id_normalization_mapping": {}
|
|
}
|