mirror of
https://github.com/meta-llama/llama-stack.git
synced 2025-10-04 04:04:14 +00:00
feat: update eval runner to use openai endpoints
note: this breaks backward compatibility if eval setup used sampling params' repetition_penalty or strategy
This commit is contained in:
parent
65f7b81e98
commit
5ef2291a51
6 changed files with 300 additions and 11 deletions
56
tests/integration/recordings/responses/e25ab43491af.json
Normal file
56
tests/integration/recordings/responses/e25ab43491af.json
Normal file
|
@ -0,0 +1,56 @@
|
|||
{
|
||||
"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": "What is the capital of France?"
|
||||
}
|
||||
],
|
||||
"max_tokens": 0
|
||||
},
|
||||
"endpoint": "/v1/chat/completions",
|
||||
"model": "llama3.2:3b-instruct-fp16"
|
||||
},
|
||||
"response": {
|
||||
"body": {
|
||||
"__type__": "openai.types.chat.chat_completion.ChatCompletion",
|
||||
"__data__": {
|
||||
"id": "chatcmpl-808",
|
||||
"choices": [
|
||||
{
|
||||
"finish_reason": "stop",
|
||||
"index": 0,
|
||||
"logprobs": null,
|
||||
"message": {
|
||||
"content": "The capital of France is Paris.",
|
||||
"refusal": null,
|
||||
"role": "assistant",
|
||||
"annotations": null,
|
||||
"audio": null,
|
||||
"function_call": null,
|
||||
"tool_calls": null
|
||||
}
|
||||
}
|
||||
],
|
||||
"created": 1759012142,
|
||||
"model": "llama3.2:3b-instruct-fp16",
|
||||
"object": "chat.completion",
|
||||
"service_tier": null,
|
||||
"system_fingerprint": "fp_ollama",
|
||||
"usage": {
|
||||
"completion_tokens": 8,
|
||||
"prompt_tokens": 32,
|
||||
"total_tokens": 40,
|
||||
"completion_tokens_details": null,
|
||||
"prompt_tokens_details": null
|
||||
}
|
||||
}
|
||||
},
|
||||
"is_streaming": false
|
||||
}
|
||||
}
|
Loading…
Add table
Add a link
Reference in a new issue