mirror of
https://github.com/meta-llama/llama-stack.git
synced 2025-10-14 14:27:58 +00:00
3f36bfaeaa
IDs are now deterministic hashes based on request content, and timestamps are normalized to constants, eliminating spurious changes when re-recording tests. ## Changes - Updated `inference_recorder.py` to normalize IDs and timestamps during recording - Added `scripts/normalize_recordings.py` utility to re-normalize existing recordings - Created documentation in `tests/integration/recordings/README.md` - Normalized 350 existing recording files
61 lines
2.1 KiB
JSON
61 lines
2.1 KiB
JSON
{
|
|
"request": {
|
|
"method": "POST",
|
|
"url": "https://api.together.xyz/v1/v1/chat/completions",
|
|
"headers": {},
|
|
"body": {
|
|
"model": "meta-llama/Llama-3.3-70B-Instruct-Turbo-Free",
|
|
"messages": [
|
|
{
|
|
"role": "user",
|
|
"content": "Test trace openai with temperature 0"
|
|
}
|
|
],
|
|
"max_tokens": 100,
|
|
"stream": false,
|
|
"temperature": 0.7
|
|
},
|
|
"endpoint": "/v1/chat/completions",
|
|
"model": "meta-llama/Llama-3.3-70B-Instruct-Turbo-Free"
|
|
},
|
|
"response": {
|
|
"body": {
|
|
"__type__": "openai.types.chat.chat_completion.ChatCompletion",
|
|
"__data__": {
|
|
"id": "rec-6841bb14fa8d",
|
|
"choices": [
|
|
{
|
|
"finish_reason": "length",
|
|
"index": 0,
|
|
"logprobs": null,
|
|
"message": {
|
|
"content": "When using a language model like OpenAI with a temperature of 0, the model is essentially forced to produce the most likely next word in a sequence, given the context. This means that the output will be very deterministic and less diverse, as the model is not allowed to explore less likely options.\n\nHere's an example of how this could work in practice:\n\n**Prompt:** Write a short story about a character who discovers a hidden world.\n\n**Temperature 0 Response:**\nIn a small village nestled",
|
|
"refusal": null,
|
|
"role": "assistant",
|
|
"annotations": null,
|
|
"audio": null,
|
|
"function_call": null,
|
|
"tool_calls": []
|
|
},
|
|
"seed": 9269366008132817000
|
|
}
|
|
],
|
|
"created": 0,
|
|
"model": "meta-llama/Llama-3.3-70B-Instruct-Turbo-Free",
|
|
"object": "chat.completion",
|
|
"service_tier": null,
|
|
"system_fingerprint": null,
|
|
"usage": {
|
|
"completion_tokens": 100,
|
|
"prompt_tokens": 43,
|
|
"total_tokens": 143,
|
|
"completion_tokens_details": null,
|
|
"prompt_tokens_details": null,
|
|
"cached_tokens": 0
|
|
},
|
|
"prompt": []
|
|
}
|
|
},
|
|
"is_streaming": false
|
|
}
|
|
}
|