Files
qwen3-4b-gsm8k/training_meta.json

7 lines
162 B
JSON
Raw Normal View History

{
"base_model_id": "MegaScience/Qwen3-4B-MegaScience",
"hub_model_id": "pymlex/qwen3-4b-gsm8k-think-answer",
"seed": 3407,
"bf16": true,
"fp16": false
}