Downloads · 30 days
7
3% of all-time downloads
qwen3-1.7b-digestive-coach-n781
kelsbeans/qwen3-1.7b-digestive-coach-n781
qwen3-1.7b-digestive-coach-n781 is a machine learning model from kelsbeans. Use it for the machine learning task on the model card, and read the license before you ship it in a product. The card lists the license as apache-2.0.
Unsloth QLoRA fine-tune of Qwen/Qwen3-1.7B on 781 rows of kelsbeans/digestive-coach-dataset (nested subset of one shuffle; fixed family-disjoint valid set of 81). Merged fp16 — loads with plain transformers, no peft.…
All-time downloads
278
Public
Parameters
1.7B
3.5 GB on disk
Likes
0
Public
Repo makeup
Click a slice to open those files.
.safetensors3.4 GB · 100%
At a glance
- License
- apache-2.0
- Model type
- qwen3
- Access
- Public
- Created
- Aug 20, 2026
- Updated
- Aug 22, 2026
- SHA
- 5331ca38
Base models
Model card
From the Hugging Face model README
Digestive Wellness Coach — Qwen3-1.7B, N=781 sweep point
Unsloth QLoRA fine-tune of Qwen/Qwen3-1.7B on 781 rows of
kelsbeans/digestive-coach-dataset
(nested subset of one shuffle; fixed family-disjoint valid set of 81).
Merged fp16 — loads with plain transformers, no peft. Adapter: kelsbeans/qwen3-1.7b-digestive-coach-n781-adapter.
Pinned for verification (R48/RUBRIC-09)
- Weights revision (pre-card commit):
0b008de7d11cfab1b4c7a135dbb91b51cb8dc6b9 - Eval-code git hash:
75863851837a7cc853b7052704e8ef7b6f7f8690 - Best eval loss 0.8283 at step 196; early stopping on val loss
Eval (held-out 40-scenario family-disjoint set, greedy, enable_thinking=false, max_new_tokens=1600, seed 7)
| metric | base Qwen3-1.7B | this model |
|---|---|---|
| parse rate | 12.5% | 100.0% |
| schema validity | 2.5% | 100.0% |
| spec adherence | 0.0% | 20.0% |
| field accuracy | 26.7% | 39.7% |
Judge means (base-vs-tuned, anthropic/claude-sonnet-5, rubric judge-v1, 1-5)
| dimension | base | this model |
|---|---|---|
| integrated_voice | 2.88 | 4.78 |
| honest_uncertainty | 2.19 | 4.09 |
| no_manufactured_agreement | 2.62 | 4.47 |
Reproduce: python eval.py --model kelsbeans/qwen3-1.7b-digestive-coach-n781 --base Qwen/Qwen3-1.7B --eval-set eval_scenarios.jsonl --max-new-tokens 1600
(harness in the project repo at the pinned eval-code hash; raw per-example
transcripts ship as JSONL in runs/).
Best prompted frontier cell on the same eval: 15% spec adherence — this checkpoint (25%) and n781 (20%) are the two points above that ceiling.
Not medical advice. Research artifact for a data→behavior fine-tuning project.
- Type
- qwen3
- License
- apache-2.0
- Languages
- en
- Created
- Aug 20, 2026
- Updated
- Aug 22, 2026