Downloads · 30 days
13
5% of all-time downloads
kanha-kanha.ai-1.7b-full
Kanha-AI/kanha-kanha.ai-1.7b-full
kanha-kanha.ai-1.7b-full is a text generation model from Kanha-AI. Use it when you need the model to write or continue text. It is set up for transformers.
- Run ID: kanha.ai-1.7b-full - Base model: Qwen/Qwen3-1.7B - Base model revision: 70d244cc86ccca08cf5af4e1e306ecf908b1ad5e - Tokenizer revision: 70d244cc86ccca08cf5af4e1e306ecf908b1ad5e - Training method: full - Final…
All-time downloads
265
Public
Parameters
1.7B
4.4 GB on disk
Likes
0
Public
Repo makeup
Click a slice to open those files.
.safetensors3.4 GB · 78%
At a glance
- Task
- Text Generation
- Library
- transformers
- Model type
- qwen3
- Access
- Public
- Created
- Aug 22, 2026
- Updated
- Aug 22, 2026
- SHA
- af619e11
Try a prompt
Base models
Model card
From the Hugging Face model README
Kanha Qwen3 experiment
Run identity
- Run ID:
kanha.ai-1.7b-full - 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: 4.0
- Learning rate: 1e-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:
0.0 - list_recall:
0.020512820512820513 - numbers_recall:
0.75 - refusal_rate:
0.0 - total:
26 - unsupported_value_rate:
0.38461538461538464 - 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.jsonresearch/training-config.yamlresearch/publication-inventory.jsonresearch/conversion-manifest.jsonresearch/evaluation/metrics.jsonresearch/evaluation/evaluation-manifest.json
- Task
- Text Generation
- Library
- transformers
- Type
- qwen3
- Languages
- en
- Created
- Aug 22, 2026
- Updated
- Aug 22, 2026