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
56 lines
3.3 KiB
JSON
56 lines
3.3 KiB
JSON
{
|
|
"request": {
|
|
"method": "POST",
|
|
"url": "http://localhost:11434/v1/v1/completions",
|
|
"headers": {},
|
|
"body": {
|
|
"model": "llama3.2:3b-instruct-fp16",
|
|
"messages": [
|
|
{
|
|
"role": "user",
|
|
"content": "Test trace openai 2"
|
|
}
|
|
],
|
|
"stream": false
|
|
},
|
|
"endpoint": "/v1/completions",
|
|
"model": "llama3.2:3b-instruct-fp16"
|
|
},
|
|
"response": {
|
|
"body": {
|
|
"__type__": "openai.types.chat.chat_completion.ChatCompletion",
|
|
"__data__": {
|
|
"id": "rec-d4f56d7d1996",
|
|
"choices": [
|
|
{
|
|
"finish_reason": "stop",
|
|
"index": 0,
|
|
"logprobs": null,
|
|
"message": {
|
|
"content": "I'd be happy to help you test the OpenAI 2 model, also known as GPT-2. Keep in mind that I'll be providing information and guidance based on publicly available resources, and not directly testing the model myself.\n\nOpenAI 2 is a large language model developed by OpenAI Research, which was released in 2019. It's a transformer-based model with 1.5 billion parameters, making it one of the largest language models at that time.\n\nTo test the OpenAI 2 model, you can try the following:\n\n1. **Read the paper**: Start by reading the original paper published in the ArXiv preprint repository [1]. This will give you a deeper understanding of the model's architecture and capabilities.\n2. **Use online generators**: Websites like [2] and [3] provide interactive interfaces to test and generate text using the OpenAI 2 model.\n3. **Try code examples**: You can find code examples in various programming languages, such as Python, that demonstrate how to use the OpenAI 2 model for tasks like text processing and generation.\n\nSome specific things you might want to try when testing OpenAI 2 include:\n\n* Generating coherent paragraphs on a given topic\n* Answering questions based on context\n* Completing sentences or stories with missing information\n* Translating short texts from one language to another\n\nKeep in mind that the OpenAI 2 model is quite large and computationally intensive, so it might not be suitable for use on all devices or platforms.\n\nReferences:\n\n[1] Radford, A., Narasimhan, K., Salimans, T., & Sutskever, I. (2019). Improving Language Understanding by Generative Pre-Training. Proceedings of the 57th Annual Meeting of the Association for Computational Linguistics (ACL).\n\n[2] https://beta.openai.com/ (use the \"chat\" interface to interact with the OpenAI 2 model)\n\n[3] https://gpt2-test.openai.co/ (test a demo version of the OpenAI 2 model)\n\nI hope this helps! If you have any specific questions or need further guidance, feel free to ask.",
|
|
"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": 450,
|
|
"prompt_tokens": 31,
|
|
"total_tokens": 481,
|
|
"completion_tokens_details": null,
|
|
"prompt_tokens_details": null
|
|
}
|
|
}
|
|
},
|
|
"is_streaming": false
|
|
}
|
|
}
|