Run ID: kanha.ai-1.7b-full-quality
Base model: Qwen/Qwen3-1.7B
Base model revision: 70d244cc86ccca08cf5af4e1e306ecf908b1ad5e
Tokenizer revision: 70d244cc86ccca08cf5af4e1e306ecf908b1ad5e
Training method: full
Final merged dtype: bfloat16
Source site: https://kanha.ai
Dataset hash: 2df3769fddeac677ce98e095453720ef3bfdc4ad1a51005febbb5568b7d2c7ab
Train split: 128 records (4b4007ea11adccb85cc5984aa3e91b7d29393b9d3619e4cffdd881514bdf4430)
Validation split: 24 records (29a6d5d7eec612453e8a629fb2e2f8a75e1d67b1e0f90ee0061b32f921d51f25)
Holdout split: 0 records (e3b0c44298fc1c149afbf4c8996fb92427ae41e4649b934ca495991b7852b855)

Hyperparameters

Maximum sequence length: 2048
Seed: 42
Epochs: 20.0
Learning rate: 5e-05
Per-device batch size: 4
Gradient accumulation steps: 2
Warmup ratio: 0.1
Assistant-only loss: true

Evaluation

dates_recall: 1.0
deterministic_pass_rate: 0.07692307692307693
list_recall: 0.21346153846153845
numbers_recall: 0.8583333333333333
refusal_rate: 0.0
total: 26
unsupported_value_rate: 0.23076923076923078
urls_recall: 1.0

Deterministic scoring and the server-side Transformers benchmark are not browser qualification. Validate the exact converted model in the target browser and device environments.

MLC availability

MLC artifacts using q4f16_1 quantization are available under mlc/.

Intended use

This checkpoint is intended for research comparing training methods on the same Kanha website-derived dataset and for controlled evaluation of website question answering.

Limitations

The checkpoint can produce incorrect, incomplete, or stale answers. It may memorize training content. Review outputs, test representative failure cases, and qualify the exact runtime before any user-facing use.

Provenance artifacts

research/run-manifest.json
research/training-config.yaml
research/publication-inventory.json
research/conversion-manifest.json
research/evaluation/metrics.json
research/evaluation/evaluation-manifest.json

Kanha-AI/kanha-kanha.ai-1.7b-full-quality

Kanha Qwen3 experiment

Run identity