Upload scripts/train_alizee_v2_stage1_sft.py with huggingface_hub
Browse files
scripts/train_alizee_v2_stage1_sft.py
CHANGED
|
@@ -119,11 +119,11 @@ print("\n📦 Loading datasets...")
|
|
| 119 |
|
| 120 |
# 1. OpenCodeReasoning (reasoning traces)
|
| 121 |
print(" Loading nvidia/OpenCodeReasoning split_0...")
|
| 122 |
-
ocr_split0 = load_dataset("nvidia/OpenCodeReasoning", "split_0", split="
|
| 123 |
print(f" -> split_0: {len(ocr_split0)} samples")
|
| 124 |
|
| 125 |
print(" Loading nvidia/OpenCodeReasoning split_1...")
|
| 126 |
-
ocr_split1 = load_dataset("nvidia/OpenCodeReasoning", "split_1", split="
|
| 127 |
print(f" -> split_1: {len(ocr_split1)} samples")
|
| 128 |
|
| 129 |
# Combine OpenCodeReasoning splits
|
|
|
|
| 119 |
|
| 120 |
# 1. OpenCodeReasoning (reasoning traces)
|
| 121 |
print(" Loading nvidia/OpenCodeReasoning split_0...")
|
| 122 |
+
ocr_split0 = load_dataset("nvidia/OpenCodeReasoning", "split_0", split="split_0")
|
| 123 |
print(f" -> split_0: {len(ocr_split0)} samples")
|
| 124 |
|
| 125 |
print(" Loading nvidia/OpenCodeReasoning split_1...")
|
| 126 |
+
ocr_split1 = load_dataset("nvidia/OpenCodeReasoning", "split_1", split="split_1")
|
| 127 |
print(f" -> split_1: {len(ocr_split1)} samples")
|
| 128 |
|
| 129 |
# Combine OpenCodeReasoning splits
|