Run ID: kanha.ai-1.7b-grounded-qlora-v1
Base model: Qwen/Qwen3-1.7B
Base model revision: 70d244cc86ccca08cf5af4e1e306ecf908b1ad5e
Tokenizer revision: 70d244cc86ccca08cf5af4e1e306ecf908b1ad5e
Training method: qlora
Final merged dtype: bfloat16
Source site: https://kanha.ai
Dataset hash: 5344dbb7a1d3267d4b370aac7ecf316329d43829335c95ec38304533bf91c958
Train split: 210 records (cec1d43395a9366ae4e54ebf312eb8c4a9a1b7f2dc101f93591e615b865bfcea)
Validation split: 45 records (5d55f68556ad3b66c8f1b3069fda424f0d8e5a00785829813153b3890c71d015)
Holdout split: 0 records (e3b0c44298fc1c149afbf4c8996fb92427ae41e4649b934ca495991b7852b855)

Hyperparameters

Maximum sequence length: 2048
Seed: 42
Epochs: 1.0
Learning rate: 0.0001
Per-device batch size: 8
Gradient accumulation steps: 2
Warmup ratio: 0.05
Assistant-only loss: true
LoRA rank: 16
LoRA alpha: 16
LoRA dropout: 0.05
LoRA targets: q_proj, k_proj, v_proj, o_proj, gate_proj, up_proj, down_proj

Evaluation

dates_recall: 1.0
deterministic_pass_rate: 0.38461538461538464
list_recall: 0.6032051282051282
numbers_recall: 0.9717948717948718
refusal_rate: 0.15384615384615385
total: 26
unsupported_value_rate: 0.038461538461538464
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

No validated MLC artifact is included in this publication.

Grounded inference contract

Inference requires retrieved source context. A bare question without retrieved source context is outside the trained and evaluated contract.

Prompt contract identity: d0dcb1de0b9d601267a3cbf39420b1f0a2c5749d80b96669a2e9fcf19a280bfb
Chat formatting: The model's native chat template is used with thinking disabled (enable_thinking=False).

System prompt (exact):

Answer only from the supplied context. Be concise. If the answer is absent from the context, respond exactly: I can't answer that from the provided context.

User template (exact):

text

Context:
<context>

Question:
<question>

Refusal string (exact):

I can't answer that from the provided context.

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/evaluation/metrics.json
research/evaluation/evaluation-manifest.json

Kanha-AI/kanha-kanha.ai-1.7b-grounded-qlora-v1

Kanha Qwen3 experiment

Run identity