You can deploy this model and start earning money today!

Kanha-AI/
kanha-kanha.ai-1.7b-grounded-small-data-3ep-v1

Name: kanha-kanha.ai-1.7b-grounded-small-data-3ep-v1
Availability: InStock

grounded-question-answering

Qwen/Qwen3-1.7B

adapter

Views

No views yet

kanha.ai-1.7b-grounded-small-data-3ep-v1

This public repository contains the final QLoRA adapter checkpoint for the named Kanha small-data experiment. The customer-derived dataset is stored separately in the private Kanha-AI/kanha-kanha.ai-1.7b-grounded-small-data-3ep-v1-dataset repository.

Provenance

Base model: Qwen/Qwen3-1.7B
Base model revision: 70d244cc86ccca08cf5af4e1e306ecf908b1ad5e
Tokenizer revision: 70d244cc86ccca08cf5af4e1e306ecf908b1ad5e
Dataset hash: ced9b047c0d56cbe3bb96546db2903ff5e60e92ffdbad7d754d255422a810e4f
Epochs: 3.0
NEFTune alpha: None

Evaluation

The aggregate results were measured on the merged derivative of this adapter. Private prompts, answers, per-case identifiers, and outputs are excluded.

Deterministic pass rate: 0.423077
List recall: 0.646795
Numbers recall: 0.971795
Refusal rate: 0.038462
Unsupported-value rate: 0.038462
Cases: 26

Inference contract

This adapter was trained and evaluated with retrieved source context and the native Qwen chat template with thinking disabled. Bare questions without source context are outside the evaluated contract.

Immutable loading

The original training artifact is preserved exactly, so its adapter_config.json has a null revision. Do not resolve the base model from mutable HEAD. Load it explicitly:

python

from peft import PeftModel
from transformers import AutoModelForCausalLM

base = AutoModelForCausalLM.from_pretrained("Qwen/Qwen3-1.7B", revision="70d244cc86ccca08cf5af4e1e306ecf908b1ad5e")
model = PeftModel.from_pretrained(base, "Kanha-AI/kanha-kanha.ai-1.7b-grounded-small-data-3ep-v1")