31 lines
1.2 KiB
JSON
31 lines
1.2 KiB
JSON
{
|
|
"raw_pairs": 12268,
|
|
"duplicates_removed": 269,
|
|
"training_pairs": 11999,
|
|
"train_pairs": 10799,
|
|
"eval_pairs": 1200,
|
|
"sources": {
|
|
"external:vendor-deep-dives.jsonl": 11200,
|
|
"external:technical-deep-dives.jsonl": 84,
|
|
"external:rir-infrastructure-data.jsonl": 150,
|
|
"external:market-business-analysis-part1.jsonl": 10,
|
|
"external:synthesized-training-samples.jsonl": 219,
|
|
"external:nanog-ripe-labs-content.jsonl": 34,
|
|
"external:academic-research-synthesis.jsonl": 109,
|
|
"training-data/tip-llm-pricing-v1.jsonl": 80,
|
|
"training-data/tip-llm-capabilities-v1.jsonl": 69,
|
|
"external:market-business-analysis-part6.jsonl": 5,
|
|
"robot-control-high.jsonl": 12,
|
|
"external:market-business-analysis-part5.jsonl": 7,
|
|
"external:market-business-analysis-part4.jsonl": 5,
|
|
"external:market-business-analysis-part2.jsonl": 8,
|
|
"external:market-business-analysis-part3.jsonl": 7
|
|
},
|
|
"files": {
|
|
"train": "training-data/runpod/tip_llm/tip_llm-sft-train.jsonl",
|
|
"eval": "training-data/runpod/tip_llm/tip_llm-sft-eval.jsonl",
|
|
"all": "training-data/runpod/tip_llm/tip_llm-sft-all.jsonl",
|
|
"manifest": "training-data/runpod/tip_llm/manifest.json"
|
|
}
|
|
}
|