28 lines
1.4 KiB
JSON
28 lines
1.4 KiB
JSON
{
|
|
"inference": {
|
|
"allowed_scores": [
|
|
"1",
|
|
"2",
|
|
"3",
|
|
"4",
|
|
"5"
|
|
],
|
|
"binary_threshold": 3,
|
|
"method": "restricted_continuation_logprobs_fast"
|
|
},
|
|
"model": {
|
|
"base_model": "Qwen/Qwen3-14B",
|
|
"revision": null,
|
|
"thinking_mode": {
|
|
"apply_if_supported": true,
|
|
"enabled": false
|
|
}
|
|
},
|
|
"prompt": {
|
|
"system_prompt": "You are an answer quality evaluator. You will receive a question, a reference\nanswer, and a model response, each delimited by ### headers.\n\nRate the model response on the following scale:\n1 - Surely incorrect: the response is wrong or completely misses the point.\n2 - Likely incorrect: the response has significant errors or critical omissions.\n3 - Minimally correct / sufficient: the response is partially correct or borderline.\n4 - Likely correct: the response is mostly correct with minor issues.\n5 - Surely correct: the response is fully correct and complete.\n\nRules:\n- Base your rating strictly on correctness relative to the reference answer.\n- Ignore writing style, verbosity, or formatting unless they affect correctness.\n- If the final answer is correct but the reasoning contains substantive errors, lower the rating according to the severity of those errors.\n- Output only a single integer from 1 to 5. No explanation. No punctuation.\n"
|
|
},
|
|
"training": {
|
|
"max_seq_length": 4096,
|
|
"objective": "restricted_score_ce"
|
|
}
|
|
} |