docs: reorganize documentation structure and workflow
Browse files- README.md +155 -236
- docs/01-docs-index.md +35 -0
- docs/{build-small-hackathon-report.md → 10-overview-build-small-hackathon-report.md} +17 -8
- docs/{demo-video-transcript.md → 11-overview-demo-video-transcript.md} +0 -0
- docs/{exercise-router-training-report.md → 20-router-training-report.md} +0 -0
- docs/{huggingface-router-release.md → 21-router-huggingface-release.md} +1 -1
- docs/{huggingface-router-model-card.md → 22-router-huggingface-model-card.md} +0 -0
- docs/30-coach-modal-training.md +193 -0
- docs/31-coach-training-report.md +370 -0
- docs/{custom-data-collection-guide.md → 40-data-custom-collection-guide.md} +0 -0
- docs/{implementation-plan.md → 90-archive-implementation-plan.md} +5 -0
- docs/{coach-analysis-implementation-plan.md → 91-archive-coach-analysis-implementation-plan.md} +5 -0
- docs/{coach-model-data-plan.md → 92-archive-coach-model-data-plan.md} +6 -0
- docs/{pozify-project-documentation.md → 99-archive-pozify-project-documentation.md} +5 -0
- docs/coach-summary-modal-training.md +0 -139
- scripts/exercise_router_modal.py +4 -4
- scripts/upload_exercise_router_to_hf.py +2 -2
README.md
CHANGED
|
@@ -1,6 +1,6 @@
|
|
| 1 |
---
|
| 2 |
title: Pozify
|
| 3 |
-
emoji: 🏋️
|
| 4 |
colorFrom: green
|
| 5 |
colorTo: blue
|
| 6 |
sdk: gradio
|
|
@@ -20,38 +20,53 @@ tags:
|
|
| 20 |
|
| 21 |
# Pozify
|
| 22 |
|
| 23 |
-
Pozify
|
| 24 |
-
exercise detected, reps counted, issues localized by timestamp, an annotated video, and grounded
|
| 25 |
-
coach feedback.
|
| 26 |
|
| 27 |
-
|
| 28 |
-
|
| 29 |
-
|
| 30 |
-
|
|
|
|
|
|
|
| 31 |
|
| 32 |
-
|
|
|
|
|
|
|
| 33 |
|
| 34 |
-
|
| 35 |
-
|
| 36 |
-
|
| 37 |
-
|
| 38 |
-
|
| 39 |
-
|
| 40 |
-
|
| 41 |
-
|
| 42 |
-
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 43 |
|
| 44 |
-
##
|
| 45 |
|
| 46 |
```text
|
| 47 |
-
|
| 48 |
-
-> video
|
| 49 |
-
-> MediaPipe pose
|
| 50 |
-
-> pose cleaning
|
| 51 |
-
->
|
| 52 |
-> exercise-specific rep counter
|
| 53 |
-
-> per-rep
|
| 54 |
-
->
|
|
|
|
| 55 |
-> annotated video renderer
|
| 56 |
-> grounded coach summary
|
| 57 |
-> verifier
|
|
@@ -65,117 +80,32 @@ Supported router labels:
|
|
| 65 |
- `shoulder_press`
|
| 66 |
- `unknown`
|
| 67 |
|
| 68 |
-
Pozify is not a medical device. It does not diagnose injuries, claim injury prevention, or replace a
|
| 69 |
-
trainer, clinician, or physical therapist.
|
| 70 |
-
|
| 71 |
## Model Stack
|
| 72 |
|
| 73 |
| Component | Model or method | Trained here? | Runtime |
|
| 74 |
-
| ---
|
| 75 |
-
| Pose extraction | MediaPipe Pose Landmarker Lite | No | CPU
|
| 76 |
-
| Exercise router | PyTorch BiLSTM over 30-frame pose windows | Yes | Torch
|
| 77 |
| Router baseline | scikit-learn `HistGradientBoostingClassifier` | Yes | CPU fallback/reference |
|
| 78 |
-
| Rep counting | Exercise-specific state machines
|
| 79 |
| Issue markers | Transparent rules over per-rep metrics | No ML | CPU |
|
| 80 |
-
| Coach summary | `Qwen/
|
| 81 |
-
|
|
|
|
|
| 82 |
|
| 83 |
The trained router is intentionally tiny:
|
| 84 |
|
| 85 |
| Artifact | Count |
|
| 86 |
-
| ---
|
| 87 |
| BiLSTM router trainable params | 182,796 |
|
| 88 |
| Router input features per frame | 237 |
|
| 89 |
| Window length | 30 frames |
|
| 90 |
| Output classes | 4 |
|
| 91 |
|
| 92 |
-
## Training Data
|
| 93 |
-
|
| 94 |
-
The router starts from
|
| 95 |
-
[`RickyRiccio/Real_Time_Exercise_Recognition_Dataset`](https://huggingface.co/datasets/RickyRiccio/Real_Time_Exercise_Recognition_Dataset).
|
| 96 |
-
Supported folders are normalized to `squat`, `push_up`, and `shoulder_press`. Unsupported classes,
|
| 97 |
-
such as curl variations, are mapped to `unknown` so the router learns when to reject clips rather
|
| 98 |
-
than force a supported label.
|
| 99 |
-
|
| 100 |
-
Latest Modal training run:
|
| 101 |
-
|
| 102 |
-
| Metric | Value |
|
| 103 |
-
| ------ | ----: |
|
| 104 |
-
| Feature examples | 134 |
|
| 105 |
-
| Pose windows | 2,224 |
|
| 106 |
-
| Failed feature extractions | 0 |
|
| 107 |
-
| Squat windows | 659 |
|
| 108 |
-
| Push-up windows | 287 |
|
| 109 |
-
| Shoulder press windows | 646 |
|
| 110 |
-
| Unknown windows | 632 |
|
| 111 |
-
|
| 112 |
-
Feature extraction converts each video to cleaned pose windows:
|
| 113 |
-
|
| 114 |
-
- normalized COCO-17 landmarks with visibility
|
| 115 |
-
- knee, hip, elbow, and shoulder angles
|
| 116 |
-
- relative distances such as hand width over shoulder width
|
| 117 |
-
- frame deltas and velocities
|
| 118 |
-
- 30-frame tensors for the BiLSTM
|
| 119 |
-
- aggregated vectors for the scikit-learn baseline
|
| 120 |
-
|
| 121 |
-
Custom negative examples can be uploaded to the Modal data volume at `/data/raw/custom_unknown/`.
|
| 122 |
-
The collection protocol is documented in
|
| 123 |
-
[docs/custom-data-collection-guide.md](docs/custom-data-collection-guide.md).
|
| 124 |
-
|
| 125 |
-
## Training On Modal
|
| 126 |
-
|
| 127 |
-
Modal is used because the expensive work is bursty: download videos, run pose extraction over a
|
| 128 |
-
dataset, train/evaluate, publish artifacts, then shut down.
|
| 129 |
-
|
| 130 |
-
```bash
|
| 131 |
-
uv run modal setup
|
| 132 |
-
uv run modal run scripts/exercise_router_modal.py --stage ingest
|
| 133 |
-
uv run modal run scripts/exercise_router_modal.py --stage features
|
| 134 |
-
uv run modal run scripts/exercise_router_modal.py --stage train-baseline
|
| 135 |
-
uv run modal run scripts/exercise_router_modal.py --stage train-temporal
|
| 136 |
-
uv run modal run scripts/exercise_router_modal.py --stage evaluate
|
| 137 |
-
```
|
| 138 |
-
|
| 139 |
-
Or run the full flow:
|
| 140 |
-
|
| 141 |
-
```bash
|
| 142 |
-
uv run modal run scripts/exercise_router_modal.py \
|
| 143 |
-
--stage all \
|
| 144 |
-
--repo-id build-small-hackathon/pozify-exercise-router
|
| 145 |
-
```
|
| 146 |
-
|
| 147 |
-
Modal resources:
|
| 148 |
-
|
| 149 |
-
- `pozify-router-data`: raw dataset, manifests, extracted pose-window feature caches.
|
| 150 |
-
- `pozify-router-models`: `baseline.joblib`, `temporal.pt`, metrics, selection JSON, HF upload log.
|
| 151 |
-
- `train_temporal`: runs on Modal `A10` GPU.
|
| 152 |
-
|
| 153 |
-
Temporal router hyperparameters:
|
| 154 |
-
|
| 155 |
-
| Hyperparameter | Value |
|
| 156 |
-
| -------------- | ----: |
|
| 157 |
-
| Architecture | BiLSTM |
|
| 158 |
-
| Epochs | 73 |
|
| 159 |
-
| Hidden units | 73 |
|
| 160 |
-
| Dropout | 0.2174 |
|
| 161 |
-
| Learning rate | 0.0004 |
|
| 162 |
-
| Batch size | 54 |
|
| 163 |
-
| Final training loss | 0.0003 |
|
| 164 |
-
|
| 165 |
-
Current evaluation summary:
|
| 166 |
-
|
| 167 |
-
| Model | Artifact | Accuracy | Unknown rejection rate |
|
| 168 |
-
| ----- | -------- | -------: | ---------------------: |
|
| 169 |
-
| Baseline | `baseline.joblib` | 0.9982 | 0.9968 |
|
| 170 |
-
| BiLSTM temporal | `temporal.pt` | 0.9969 | 0.9968 |
|
| 171 |
-
|
| 172 |
-
The active runtime artifact is `temporal.pt`; the baseline is retained for comparison and fallback.
|
| 173 |
-
Full metrics are in
|
| 174 |
-
[docs/exercise-router-training-report.md](docs/exercise-router-training-report.md).
|
| 175 |
-
|
| 176 |
## Run The App Locally
|
| 177 |
|
| 178 |
-
|
|
|
|
| 179 |
|
| 180 |
```bash
|
| 181 |
uv run python app.py
|
|
@@ -187,14 +117,12 @@ The app listens at:
|
|
| 187 |
http://127.0.0.1:7860
|
| 188 |
```
|
| 189 |
|
| 190 |
-
|
| 191 |
|
| 192 |
-
|
| 193 |
-
uv run gradio app.py
|
| 194 |
-
```
|
| 195 |
|
| 196 |
-
|
| 197 |
-
|
| 198 |
|
| 199 |
Force mock mode:
|
| 200 |
|
|
@@ -208,8 +136,7 @@ Force real mode:
|
|
| 208 |
POZIFY_MOCK_MODE=0 uv run python app.py
|
| 209 |
```
|
| 210 |
|
| 211 |
-
|
| 212 |
-
pre-downloaded task file:
|
| 213 |
|
| 214 |
```bash
|
| 215 |
POZIFY_MEDIAPIPE_POSE_MODEL=/path/to/pose_landmarker_lite.task \
|
|
@@ -217,120 +144,128 @@ POZIFY_MOCK_MODE=0 \
|
|
| 217 |
uv run python app.py
|
| 218 |
```
|
| 219 |
|
| 220 |
-
##
|
| 221 |
|
| 222 |
-
|
| 223 |
|
| 224 |
-
|
| 225 |
-
build-small-hackathon/pozify-exercise-router
|
| 226 |
-
```
|
| 227 |
-
|
| 228 |
-
Override the repo:
|
| 229 |
|
| 230 |
```bash
|
| 231 |
-
export
|
|
|
|
| 232 |
```
|
| 233 |
|
| 234 |
-
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 235 |
|
| 236 |
```bash
|
| 237 |
-
export
|
|
|
|
|
|
|
|
|
|
| 238 |
```
|
| 239 |
|
| 240 |
-
|
|
|
|
| 241 |
|
| 242 |
-
|
| 243 |
-
models/exercise_router/active/
|
| 244 |
-
router_selection.json
|
| 245 |
-
temporal.pt
|
| 246 |
-
baseline.joblib # optional fallback/reference
|
| 247 |
-
router.joblib # optional baseline alias
|
| 248 |
-
```
|
| 249 |
|
| 250 |
-
|
| 251 |
-
|
| 252 |
-
in [docs/huggingface-router-model-card.md](docs/huggingface-router-model-card.md).
|
| 253 |
|
| 254 |
-
|
| 255 |
|
| 256 |
-
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 257 |
|
| 258 |
-
|
| 259 |
-
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 260 |
|
| 261 |
-
Useful environment variables
|
| 262 |
|
| 263 |
| Variable | Purpose |
|
| 264 |
-
| ---
|
| 265 |
| `POZIFY_ROUTER_DEVICE` | Override router device, for example `cpu` or `cuda`. |
|
| 266 |
| `POZIFY_SPACES_GPU_DURATION` | `spaces.GPU` duration in seconds, default `120`. |
|
| 267 |
| `POZIFY_COACH_SUMMARY_PROVIDER` | `hf_inference`, `local_transformers`, or `llama_cpp`. |
|
| 268 |
| `POZIFY_COACH_SUMMARY_MODEL` | Coach model id or llama.cpp model alias. |
|
|
|
|
|
|
|
|
|
|
|
|
|
| 269 |
|
| 270 |
-
|
| 271 |
|
| 272 |
```bash
|
| 273 |
-
|
| 274 |
-
|
| 275 |
-
|
| 276 |
-
uv run python app.py
|
| 277 |
```
|
| 278 |
|
| 279 |
-
|
| 280 |
-
|
| 281 |
-
If Torch sees a CUDA GPU:
|
| 282 |
|
| 283 |
```bash
|
| 284 |
-
|
| 285 |
-
|
| 286 |
-
|
| 287 |
-
uv run
|
|
|
|
|
|
|
| 288 |
```
|
| 289 |
|
| 290 |
-
The router
|
| 291 |
-
Transformers coach generation.
|
| 292 |
|
| 293 |
-
##
|
| 294 |
|
| 295 |
-
|
| 296 |
-
OpenAI-compatible `/v1/chat/completions` endpoint. This is the path for running the coach model as a
|
| 297 |
-
GGUF with llama.cpp.
|
| 298 |
-
|
| 299 |
-
Start a llama.cpp server with GPU offload. Use either a local GGUF file:
|
| 300 |
|
| 301 |
```bash
|
| 302 |
-
|
| 303 |
-
--model /path/to/qwen2.5-7b-instruct-q4_k_m.gguf \
|
| 304 |
-
--ctx-size 4096 \
|
| 305 |
-
--n-gpu-layers 99 \
|
| 306 |
-
--host 127.0.0.1 \
|
| 307 |
-
--port 8080
|
| 308 |
```
|
| 309 |
|
| 310 |
-
|
| 311 |
|
| 312 |
```bash
|
| 313 |
-
|
| 314 |
-
--
|
| 315 |
-
--
|
| 316 |
-
--
|
| 317 |
-
--
|
| 318 |
-
--port 8080
|
| 319 |
```
|
| 320 |
|
| 321 |
-
|
| 322 |
|
| 323 |
```bash
|
| 324 |
-
|
| 325 |
-
|
| 326 |
-
|
| 327 |
-
|
| 328 |
-
uv run
|
| 329 |
```
|
| 330 |
|
| 331 |
-
|
| 332 |
-
|
| 333 |
-
the
|
|
|
|
|
|
|
|
|
|
| 334 |
|
| 335 |
## Generated Artifacts
|
| 336 |
|
|
@@ -351,49 +286,43 @@ Each run creates `runs/<run_id>/` with:
|
|
| 351 |
- `verification.json`
|
| 352 |
- `final_report.json`
|
| 353 |
|
| 354 |
-
JSON artifacts are validated before they are written. The final report records
|
| 355 |
-
|
| 356 |
-
|
| 357 |
-
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 358 |
|
| 359 |
## Project Structure
|
| 360 |
|
| 361 |
```text
|
| 362 |
app.py
|
| 363 |
web/
|
| 364 |
-
index.html
|
| 365 |
-
app.js
|
| 366 |
-
report.js
|
| 367 |
-
styles.css
|
| 368 |
src/pozify/
|
| 369 |
pipeline.py
|
| 370 |
contracts.py
|
| 371 |
steps/
|
| 372 |
-
video_qc.py
|
| 373 |
-
pose_landmarker.py
|
| 374 |
-
exercise_classifier.py
|
| 375 |
-
annotated_renderer.py
|
| 376 |
-
coach_summary.py
|
| 377 |
-
verifier.py
|
| 378 |
ml/
|
| 379 |
-
exercise_router_features.py
|
| 380 |
-
exercise_router_temporal.py
|
| 381 |
-
exercise_router_inference.py
|
| 382 |
slm/
|
| 383 |
-
providers.py
|
| 384 |
-
prompting.py
|
| 385 |
exercises/
|
| 386 |
-
squat/
|
| 387 |
-
push_up/
|
| 388 |
-
shoulder_press/
|
| 389 |
scripts/
|
| 390 |
-
exercise_router_modal.py
|
| 391 |
-
upload_exercise_router_to_hf.py
|
| 392 |
docs/
|
| 393 |
-
|
| 394 |
-
|
| 395 |
-
huggingface-router-release.md
|
| 396 |
-
custom-data-collection-guide.md
|
| 397 |
```
|
| 398 |
|
| 399 |
## Development Checks
|
|
@@ -410,13 +339,3 @@ Run the real MediaPipe fixture smoke test only when the fixture is available:
|
|
| 410 |
POZIFY_RUN_REAL_POSE_TESTS=1 \
|
| 411 |
uv run python -m unittest tests.test_pose_steps.PoseStepTests.test_real_sample_mov_extracts_pose_landmarks
|
| 412 |
```
|
| 413 |
-
|
| 414 |
-
## Notes And Limits
|
| 415 |
-
|
| 416 |
-
- Router metrics are from the current Modal feature cache, not a broad production benchmark.
|
| 417 |
-
- The app depends on full-body framing and usable pose extraction.
|
| 418 |
-
- Unsupported or low-confidence clips should route to `unknown` instead of receiving fabricated
|
| 419 |
-
coaching.
|
| 420 |
-
- Qwen is prompted and verified; it is not fine-tuned in this project.
|
| 421 |
-
- More held-out videos, camera angles, body types, and custom unknown clips are needed before using
|
| 422 |
-
Pozify as a robust training product.
|
|
|
|
| 1 |
---
|
| 2 |
title: Pozify
|
| 3 |
+
emoji: "🏋️"
|
| 4 |
colorFrom: green
|
| 5 |
colorTo: blue
|
| 6 |
sdk: gradio
|
|
|
|
| 20 |
|
| 21 |
# Pozify
|
| 22 |
|
| 23 |
+
Pozify turns a short workout video into a structured form-review report:
|
|
|
|
|
|
|
| 24 |
|
| 25 |
+
- exercise detected
|
| 26 |
+
- reps counted
|
| 27 |
+
- variation and issue markers
|
| 28 |
+
- annotated video and clips
|
| 29 |
+
- grounded coach summary
|
| 30 |
+
- verifier-backed confidence and safety notes
|
| 31 |
|
| 32 |
+
The app is built as a small-model pipeline, not a giant end-to-end model. It combines transparent
|
| 33 |
+
pose analysis, a trained exercise router, exercise-specific rule logic, deterministic knowledge-card
|
| 34 |
+
retrieval, and a small summary model.
|
| 35 |
|
| 36 |
+
Pozify is not a medical device. It does not diagnose injuries, claim injury prevention, or replace a
|
| 37 |
+
qualified trainer, clinician, or physical therapist.
|
| 38 |
+
|
| 39 |
+
## Current Status
|
| 40 |
+
|
| 41 |
+
The current codebase supports:
|
| 42 |
+
|
| 43 |
+
- web app runtime through `app.py`
|
| 44 |
+
- trained exercise routing for `squat`, `push_up`, `shoulder_press`, and `unknown`
|
| 45 |
+
- grounded coach-summary generation from structured JSON artifacts
|
| 46 |
+
- verifier and conservative fallback summaries
|
| 47 |
+
- Modal training pipelines for both the exercise router and coach-summary model
|
| 48 |
+
|
| 49 |
+
The current safest cloud runtime for coach summary is:
|
| 50 |
+
|
| 51 |
+
- `Qwen/Qwen3-14B`
|
| 52 |
+
|
| 53 |
+
The current fine-tuned coach-summary Hugging Face repo can be trained, merged, and published, but
|
| 54 |
+
it is not yet cleanly usable through the current Hugging Face serverless `chat_completion` path.
|
| 55 |
+
If you want to use that fine-tuned model today, the simplest path is local merged-model inference
|
| 56 |
+
through `POZIFY_COACH_SUMMARY_LOCAL_MODEL_DIR`.
|
| 57 |
|
| 58 |
+
## Product Flow
|
| 59 |
|
| 60 |
```text
|
| 61 |
+
video + user profile
|
| 62 |
+
-> video QC
|
| 63 |
+
-> MediaPipe pose extraction
|
| 64 |
+
-> pose cleaning
|
| 65 |
+
-> exercise router
|
| 66 |
-> exercise-specific rep counter
|
| 67 |
+
-> per-rep analysis
|
| 68 |
+
-> variation detection
|
| 69 |
+
-> issue markers
|
| 70 |
-> annotated video renderer
|
| 71 |
-> grounded coach summary
|
| 72 |
-> verifier
|
|
|
|
| 80 |
- `shoulder_press`
|
| 81 |
- `unknown`
|
| 82 |
|
|
|
|
|
|
|
|
|
|
| 83 |
## Model Stack
|
| 84 |
|
| 85 |
| Component | Model or method | Trained here? | Runtime |
|
| 86 |
+
| --- | --- | --- | --- |
|
| 87 |
+
| Pose extraction | MediaPipe Pose Landmarker Lite | No | CPU / MediaPipe delegate |
|
| 88 |
+
| Exercise router | PyTorch BiLSTM over 30-frame pose windows | Yes | Torch |
|
| 89 |
| Router baseline | scikit-learn `HistGradientBoostingClassifier` | Yes | CPU fallback/reference |
|
| 90 |
+
| Rep counting | Exercise-specific state machines | No ML | CPU |
|
| 91 |
| Issue markers | Transparent rules over per-rep metrics | No ML | CPU |
|
| 92 |
+
| Coach summary | `Qwen/Qwen3-14B` by default | Base model only | HF Inference, local Transformers, or llama.cpp |
|
| 93 |
+
| Coach-summary fine-tune | LoRA / merged checkpoint pipeline on Modal | Yes | Local merged-model path recommended |
|
| 94 |
+
| Verifier | Deterministic safety and grounding checks | No ML | CPU |
|
| 95 |
|
| 96 |
The trained router is intentionally tiny:
|
| 97 |
|
| 98 |
| Artifact | Count |
|
| 99 |
+
| --- | ---: |
|
| 100 |
| BiLSTM router trainable params | 182,796 |
|
| 101 |
| Router input features per frame | 237 |
|
| 102 |
| Window length | 30 frames |
|
| 103 |
| Output classes | 4 |
|
| 104 |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 105 |
## Run The App Locally
|
| 106 |
|
| 107 |
+
This repo uses a `src/` layout, but `uv` is configured with `package = false`, so the correct local
|
| 108 |
+
entrypoint is:
|
| 109 |
|
| 110 |
```bash
|
| 111 |
uv run python app.py
|
|
|
|
| 117 |
http://127.0.0.1:7860
|
| 118 |
```
|
| 119 |
|
| 120 |
+
### Mock vs Real Mode
|
| 121 |
|
| 122 |
+
By default:
|
|
|
|
|
|
|
| 123 |
|
| 124 |
+
- if no video is provided, Pozify uses mock mode
|
| 125 |
+
- if a real video is uploaded, Pozify runs the full analysis pipeline
|
| 126 |
|
| 127 |
Force mock mode:
|
| 128 |
|
|
|
|
| 136 |
POZIFY_MOCK_MODE=0 uv run python app.py
|
| 137 |
```
|
| 138 |
|
| 139 |
+
If you already have the MediaPipe task file locally:
|
|
|
|
| 140 |
|
| 141 |
```bash
|
| 142 |
POZIFY_MEDIAPIPE_POSE_MODEL=/path/to/pose_landmarker_lite.task \
|
|
|
|
| 144 |
uv run python app.py
|
| 145 |
```
|
| 146 |
|
| 147 |
+
## Coach Summary Runtime Options
|
| 148 |
|
| 149 |
+
### 1. Simplest cloud path
|
| 150 |
|
| 151 |
+
Use the default supported cloud model:
|
|
|
|
|
|
|
|
|
|
|
|
|
| 152 |
|
| 153 |
```bash
|
| 154 |
+
export POZIFY_COACH_SUMMARY_MODEL=Qwen/Qwen3-14B
|
| 155 |
+
uv run python app.py
|
| 156 |
```
|
| 157 |
|
| 158 |
+
This is the easiest path if you want the UI to avoid immediate fallback caused by unsupported custom
|
| 159 |
+
HF serverless routing.
|
| 160 |
+
|
| 161 |
+
### 2. Use the fine-tuned merged model locally
|
| 162 |
+
|
| 163 |
+
Download the merged repo locally, then point Pozify at it:
|
| 164 |
|
| 165 |
```bash
|
| 166 |
+
export POZIFY_COACH_SUMMARY_LOCAL_MODEL_DIR=/absolute/path/to/merged_model
|
| 167 |
+
export POZIFY_COACH_SUMMARY_BASE_MODEL=Qwen/Qwen3-14B
|
| 168 |
+
export POZIFY_COACH_SUMMARY_ADAPTER_ID=build-small-hackathon/pozify-coach-summary1
|
| 169 |
+
uv run python app.py
|
| 170 |
```
|
| 171 |
|
| 172 |
+
This is the simplest way to use `build-small-hackathon/pozify-coach-summary1` today without adding a
|
| 173 |
+
dedicated inference endpoint.
|
| 174 |
|
| 175 |
+
### 3. llama.cpp
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 176 |
|
| 177 |
+
Pozify can send the coach-summary prompt to a local `llama-server` that exposes the
|
| 178 |
+
OpenAI-compatible `/v1/chat/completions` endpoint.
|
|
|
|
| 179 |
|
| 180 |
+
Example:
|
| 181 |
|
| 182 |
+
```bash
|
| 183 |
+
llama-server \
|
| 184 |
+
--model /path/to/qwen3-14b-instruct.gguf \
|
| 185 |
+
--ctx-size 4096 \
|
| 186 |
+
--n-gpu-layers 99 \
|
| 187 |
+
--host 127.0.0.1 \
|
| 188 |
+
--port 8080
|
| 189 |
+
```
|
| 190 |
|
| 191 |
+
Then:
|
| 192 |
+
|
| 193 |
+
```bash
|
| 194 |
+
POZIFY_COACH_SUMMARY_PROVIDER=llama_cpp \
|
| 195 |
+
POZIFY_COACH_SUMMARY_MODEL=local-qwen3-14b-gguf \
|
| 196 |
+
POZIFY_LLAMA_CPP_BASE_URL=http://127.0.0.1:8080 \
|
| 197 |
+
POZIFY_COACH_SUMMARY_MAX_TOKENS=700 \
|
| 198 |
+
uv run python app.py
|
| 199 |
+
```
|
| 200 |
|
| 201 |
+
### Useful environment variables
|
| 202 |
|
| 203 |
| Variable | Purpose |
|
| 204 |
+
| --- | --- |
|
| 205 |
| `POZIFY_ROUTER_DEVICE` | Override router device, for example `cpu` or `cuda`. |
|
| 206 |
| `POZIFY_SPACES_GPU_DURATION` | `spaces.GPU` duration in seconds, default `120`. |
|
| 207 |
| `POZIFY_COACH_SUMMARY_PROVIDER` | `hf_inference`, `local_transformers`, or `llama_cpp`. |
|
| 208 |
| `POZIFY_COACH_SUMMARY_MODEL` | Coach model id or llama.cpp model alias. |
|
| 209 |
+
| `POZIFY_COACH_SUMMARY_LOCAL_MODEL_DIR` | Prefer a local merged/model directory for coach summary. |
|
| 210 |
+
| `POZIFY_COACH_SUMMARY_BYPASS_VERIFIER` | Keep model output even when verifier fails. |
|
| 211 |
+
|
| 212 |
+
## Exercise Router Training
|
| 213 |
|
| 214 |
+
Run the full router training and publish flow:
|
| 215 |
|
| 216 |
```bash
|
| 217 |
+
uv run modal run scripts/exercise_router_modal.py \
|
| 218 |
+
--stage all \
|
| 219 |
+
--repo-id build-small-hackathon/pozify-exercise-router
|
|
|
|
| 220 |
```
|
| 221 |
|
| 222 |
+
Step-by-step:
|
|
|
|
|
|
|
| 223 |
|
| 224 |
```bash
|
| 225 |
+
uv run modal run scripts/exercise_router_modal.py --stage ingest
|
| 226 |
+
uv run modal run scripts/exercise_router_modal.py --stage features
|
| 227 |
+
uv run modal run scripts/exercise_router_modal.py --stage train-baseline
|
| 228 |
+
uv run modal run scripts/exercise_router_modal.py --stage train-temporal
|
| 229 |
+
uv run modal run scripts/exercise_router_modal.py --stage evaluate
|
| 230 |
+
uv run modal run scripts/exercise_router_modal.py --stage publish --repo-id build-small-hackathon/pozify-exercise-router
|
| 231 |
```
|
| 232 |
|
| 233 |
+
The active router artifact is `temporal.pt`; the baseline is retained for comparison and fallback.
|
|
|
|
| 234 |
|
| 235 |
+
## Coach Summary Training
|
| 236 |
|
| 237 |
+
Build the grounded SFT dataset:
|
|
|
|
|
|
|
|
|
|
|
|
|
| 238 |
|
| 239 |
```bash
|
| 240 |
+
uv run python scripts/build_coach_summary_sft_dataset.py
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 241 |
```
|
| 242 |
|
| 243 |
+
Run the full coach-summary Modal flow:
|
| 244 |
|
| 245 |
```bash
|
| 246 |
+
uv run modal run scripts/coach_summary_modal.py \
|
| 247 |
+
--stage all \
|
| 248 |
+
--epochs 2 \
|
| 249 |
+
--style-weight 0.2 \
|
| 250 |
+
--repo-id build-small-hackathon/pozify-coach-summary1
|
|
|
|
| 251 |
```
|
| 252 |
|
| 253 |
+
Step-by-step:
|
| 254 |
|
| 255 |
```bash
|
| 256 |
+
uv run modal run scripts/coach_summary_modal.py --stage prepare-data
|
| 257 |
+
uv run modal run scripts/coach_summary_modal.py --stage train --epochs 2 --style-weight 0.2
|
| 258 |
+
uv run modal run scripts/coach_summary_modal.py --stage evaluate --limit 5
|
| 259 |
+
uv run modal run scripts/coach_summary_modal.py --stage merge
|
| 260 |
+
uv run modal run scripts/coach_summary_modal.py --stage publish-merged --repo-id build-small-hackathon/pozify-coach-summary1
|
| 261 |
```
|
| 262 |
|
| 263 |
+
Important runtime note:
|
| 264 |
+
|
| 265 |
+
- publishing the merged repo does not automatically make it usable through HF serverless
|
| 266 |
+
`chat_completion`
|
| 267 |
+
- if you want immediate working inference, use `Qwen/Qwen3-14B`
|
| 268 |
+
- if you want to use the fine-tuned model, use `POZIFY_COACH_SUMMARY_LOCAL_MODEL_DIR`
|
| 269 |
|
| 270 |
## Generated Artifacts
|
| 271 |
|
|
|
|
| 286 |
- `verification.json`
|
| 287 |
- `final_report.json`
|
| 288 |
|
| 289 |
+
JSON artifacts are validated before they are written. The final report records:
|
| 290 |
+
|
| 291 |
+
- analysis mode
|
| 292 |
+
- pose source
|
| 293 |
+
- knowledge-card provenance
|
| 294 |
+
- coach summary provider/model/source
|
| 295 |
+
- verifier status and bypass flags
|
| 296 |
+
|
| 297 |
+
## Docs Map
|
| 298 |
+
|
| 299 |
+
See [docs/01-docs-index.md](docs/01-docs-index.md) for the ordered documentation map.
|
| 300 |
+
|
| 301 |
+
Most useful operational docs:
|
| 302 |
+
|
| 303 |
+
- [docs/10-overview-build-small-hackathon-report.md](docs/10-overview-build-small-hackathon-report.md)
|
| 304 |
+
- [docs/20-router-training-report.md](docs/20-router-training-report.md)
|
| 305 |
+
- [docs/21-router-huggingface-release.md](docs/21-router-huggingface-release.md)
|
| 306 |
+
- [docs/30-coach-modal-training.md](docs/30-coach-modal-training.md)
|
| 307 |
+
- [docs/31-coach-training-report.md](docs/31-coach-training-report.md)
|
| 308 |
+
- [docs/40-data-custom-collection-guide.md](docs/40-data-custom-collection-guide.md)
|
| 309 |
|
| 310 |
## Project Structure
|
| 311 |
|
| 312 |
```text
|
| 313 |
app.py
|
| 314 |
web/
|
|
|
|
|
|
|
|
|
|
|
|
|
| 315 |
src/pozify/
|
| 316 |
pipeline.py
|
| 317 |
contracts.py
|
| 318 |
steps/
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 319 |
ml/
|
|
|
|
|
|
|
|
|
|
| 320 |
slm/
|
|
|
|
|
|
|
| 321 |
exercises/
|
|
|
|
|
|
|
|
|
|
| 322 |
scripts/
|
|
|
|
|
|
|
| 323 |
docs/
|
| 324 |
+
demo/
|
| 325 |
+
runs/
|
|
|
|
|
|
|
| 326 |
```
|
| 327 |
|
| 328 |
## Development Checks
|
|
|
|
| 339 |
POZIFY_RUN_REAL_POSE_TESTS=1 \
|
| 340 |
uv run python -m unittest tests.test_pose_steps.PoseStepTests.test_real_sample_mov_extracts_pose_landmarks
|
| 341 |
```
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
docs/01-docs-index.md
ADDED
|
@@ -0,0 +1,35 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
# Pozify Docs Index
|
| 2 |
+
|
| 3 |
+
This folder is ordered by purpose so the current workflow is easier to follow.
|
| 4 |
+
|
| 5 |
+
## Current Workflow
|
| 6 |
+
|
| 7 |
+
Read in this order if you want to understand and run the current project:
|
| 8 |
+
|
| 9 |
+
1. [../README.md](../README.md)
|
| 10 |
+
2. [10-overview-build-small-hackathon-report.md](10-overview-build-small-hackathon-report.md)
|
| 11 |
+
3. [20-router-training-report.md](20-router-training-report.md)
|
| 12 |
+
4. [21-router-huggingface-release.md](21-router-huggingface-release.md)
|
| 13 |
+
5. [30-coach-modal-training.md](30-coach-modal-training.md)
|
| 14 |
+
6. [31-coach-training-report.md](31-coach-training-report.md)
|
| 15 |
+
7. [40-data-custom-collection-guide.md](40-data-custom-collection-guide.md)
|
| 16 |
+
|
| 17 |
+
## Presentation / Demo
|
| 18 |
+
|
| 19 |
+
- [11-overview-demo-video-transcript.md](11-overview-demo-video-transcript.md)
|
| 20 |
+
|
| 21 |
+
## Planning / Historical Design Notes
|
| 22 |
+
|
| 23 |
+
These files are useful context, but they are not the source of truth for current runtime commands:
|
| 24 |
+
|
| 25 |
+
- [90-archive-implementation-plan.md](90-archive-implementation-plan.md)
|
| 26 |
+
- [91-archive-coach-analysis-implementation-plan.md](91-archive-coach-analysis-implementation-plan.md)
|
| 27 |
+
- [92-archive-coach-model-data-plan.md](92-archive-coach-model-data-plan.md)
|
| 28 |
+
- [99-archive-pozify-project-documentation.md](99-archive-pozify-project-documentation.md)
|
| 29 |
+
|
| 30 |
+
## Notes
|
| 31 |
+
|
| 32 |
+
- Current coach-summary cloud runtime default: `Qwen/Qwen3-14B`
|
| 33 |
+
- Current fine-tuned coach-summary Hugging Face repo is best used through local merged-model
|
| 34 |
+
inference, not HF serverless `chat_completion`
|
| 35 |
+
- Current app entrypoint: `uv run python app.py`
|
docs/{build-small-hackathon-report.md → 10-overview-build-small-hackathon-report.md}
RENAMED
|
@@ -1,5 +1,13 @@
|
|
| 1 |
# Pozify Build Small Hackathon Report
|
| 2 |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 3 |
Date: June 14, 2026
|
| 4 |
|
| 5 |
Pozify is a small-model workout form reviewer. A user uploads a short exercise video, adds basic
|
|
@@ -49,11 +57,12 @@ pretending every video is one of the supported movements.
|
|
| 49 |
| Pose extractor | MediaPipe Pose Landmarker Lite | Fast, practical feature extractor for a Gradio Space. |
|
| 50 |
| Exercise router | Custom PyTorch BiLSTM | Tiny trainable temporal model over pose windows. |
|
| 51 |
| Baseline router | scikit-learn HistGradientBoostingClassifier | Strong baseline over engineered vectors and fallback artifact. |
|
| 52 |
-
| Coach summary |
|
| 53 |
-
| llama.cpp path |
|
| 54 |
|
| 55 |
-
The
|
| 56 |
-
evidence
|
|
|
|
| 57 |
|
| 58 |
## What Was Trained
|
| 59 |
|
|
@@ -203,7 +212,7 @@ logic stay outside the GPU worker. Useful settings:
|
|
| 203 |
|
| 204 |
```bash
|
| 205 |
POZIFY_COACH_SUMMARY_PROVIDER=local_transformers
|
| 206 |
-
POZIFY_COACH_SUMMARY_MODEL=Qwen/
|
| 207 |
POZIFY_SPACES_GPU_DURATION=300
|
| 208 |
```
|
| 209 |
|
|
@@ -218,7 +227,7 @@ Start llama.cpp with a local GGUF:
|
|
| 218 |
|
| 219 |
```bash
|
| 220 |
llama-server \
|
| 221 |
-
--model /path/to/
|
| 222 |
--ctx-size 4096 \
|
| 223 |
--n-gpu-layers 99 \
|
| 224 |
--host 127.0.0.1 \
|
|
@@ -229,7 +238,7 @@ Or use a Hugging Face GGUF repo:
|
|
| 229 |
|
| 230 |
```bash
|
| 231 |
llama-server \
|
| 232 |
-
--hf-repo owner/
|
| 233 |
--ctx-size 4096 \
|
| 234 |
--n-gpu-layers 99 \
|
| 235 |
--host 127.0.0.1 \
|
|
@@ -240,7 +249,7 @@ Then point Pozify at it:
|
|
| 240 |
|
| 241 |
```bash
|
| 242 |
POZIFY_COACH_SUMMARY_PROVIDER=llama_cpp \
|
| 243 |
-
POZIFY_COACH_SUMMARY_MODEL=local-
|
| 244 |
POZIFY_LLAMA_CPP_BASE_URL=http://127.0.0.1:8080 \
|
| 245 |
uv run python app.py
|
| 246 |
```
|
|
|
|
| 1 |
# Pozify Build Small Hackathon Report
|
| 2 |
|
| 3 |
+
Status note:
|
| 4 |
+
|
| 5 |
+
- This report is kept as the hackathon narrative document.
|
| 6 |
+
- Current runtime defaults have moved to `Qwen/Qwen3-14B`.
|
| 7 |
+
- Current coach-summary training now includes a LoRA/merge/publish pipeline on Modal.
|
| 8 |
+
- For the current operational commands, prefer [../README.md](../README.md) and
|
| 9 |
+
[30-coach-modal-training.md](30-coach-modal-training.md).
|
| 10 |
+
|
| 11 |
Date: June 14, 2026
|
| 12 |
|
| 13 |
Pozify is a small-model workout form reviewer. A user uploads a short exercise video, adds basic
|
|
|
|
| 57 |
| Pose extractor | MediaPipe Pose Landmarker Lite | Fast, practical feature extractor for a Gradio Space. |
|
| 58 |
| Exercise router | Custom PyTorch BiLSTM | Tiny trainable temporal model over pose windows. |
|
| 59 |
| Baseline router | scikit-learn HistGradientBoostingClassifier | Strong baseline over engineered vectors and fallback artifact. |
|
| 60 |
+
| Coach summary | Qwen/Qwen3-14B | Current default cloud runtime for structured JSON explanation. |
|
| 61 |
+
| llama.cpp path | Qwen3-14B Instruct GGUF via `llama-server` | Local-first/off-grid coach summary path with GPU offload. |
|
| 62 |
|
| 63 |
+
The original hackathon build trained the exercise router first and used Qwen as a grounded
|
| 64 |
+
summarizer over JSON evidence. The current codebase now also contains a coach-summary LoRA / merged
|
| 65 |
+
model training path on Modal.
|
| 66 |
|
| 67 |
## What Was Trained
|
| 68 |
|
|
|
|
| 212 |
|
| 213 |
```bash
|
| 214 |
POZIFY_COACH_SUMMARY_PROVIDER=local_transformers
|
| 215 |
+
POZIFY_COACH_SUMMARY_MODEL=Qwen/Qwen3-14B
|
| 216 |
POZIFY_SPACES_GPU_DURATION=300
|
| 217 |
```
|
| 218 |
|
|
|
|
| 227 |
|
| 228 |
```bash
|
| 229 |
llama-server \
|
| 230 |
+
--model /path/to/qwen3-14b-instruct-q4_k_m.gguf \
|
| 231 |
--ctx-size 4096 \
|
| 232 |
--n-gpu-layers 99 \
|
| 233 |
--host 127.0.0.1 \
|
|
|
|
| 238 |
|
| 239 |
```bash
|
| 240 |
llama-server \
|
| 241 |
+
--hf-repo owner/qwen3-14b-instruct-gguf:Q4_K_M \
|
| 242 |
--ctx-size 4096 \
|
| 243 |
--n-gpu-layers 99 \
|
| 244 |
--host 127.0.0.1 \
|
|
|
|
| 249 |
|
| 250 |
```bash
|
| 251 |
POZIFY_COACH_SUMMARY_PROVIDER=llama_cpp \
|
| 252 |
+
POZIFY_COACH_SUMMARY_MODEL=local-qwen3-14b-gguf \
|
| 253 |
POZIFY_LLAMA_CPP_BASE_URL=http://127.0.0.1:8080 \
|
| 254 |
uv run python app.py
|
| 255 |
```
|
docs/{demo-video-transcript.md → 11-overview-demo-video-transcript.md}
RENAMED
|
File without changes
|
docs/{exercise-router-training-report.md → 20-router-training-report.md}
RENAMED
|
File without changes
|
docs/{huggingface-router-release.md → 21-router-huggingface-release.md}
RENAMED
|
@@ -61,7 +61,7 @@ Omit `--private` if the model repository should be public.
|
|
| 61 |
|
| 62 |
The Modal training script can also publish directly from the `pozify-router-models` volume after
|
| 63 |
evaluation. It reads `HF_TOKEN`, `POZIFY_ROUTER_HF_REPO_ID`, and optional
|
| 64 |
-
`POZIFY_ROUTER_HF_PRIVATE=1` from `.env`
|
| 65 |
|
| 66 |
```bash
|
| 67 |
uv run modal run scripts/exercise_router_modal.py --stage all
|
|
|
|
| 61 |
|
| 62 |
The Modal training script can also publish directly from the `pozify-router-models` volume after
|
| 63 |
evaluation. It reads `HF_TOKEN`, `POZIFY_ROUTER_HF_REPO_ID`, and optional
|
| 64 |
+
`POZIFY_ROUTER_HF_PRIVATE=1` from local `.env` and injects them into Modal secrets at runtime:
|
| 65 |
|
| 66 |
```bash
|
| 67 |
uv run modal run scripts/exercise_router_modal.py --stage all
|
docs/{huggingface-router-model-card.md → 22-router-huggingface-model-card.md}
RENAMED
|
File without changes
|
docs/30-coach-modal-training.md
ADDED
|
@@ -0,0 +1,193 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
# Coach Summary Modal Training
|
| 2 |
+
|
| 3 |
+
This guide explains the current Modal workflow for training, evaluating, merging, and publishing the
|
| 4 |
+
Pozify grounded coach-summary model.
|
| 5 |
+
|
| 6 |
+
## Scope
|
| 7 |
+
|
| 8 |
+
The pipeline lives in:
|
| 9 |
+
|
| 10 |
+
- `scripts/coach_summary_modal.py`
|
| 11 |
+
|
| 12 |
+
Available stages:
|
| 13 |
+
|
| 14 |
+
- `prepare-data`
|
| 15 |
+
- `train`
|
| 16 |
+
- `evaluate`
|
| 17 |
+
- `merge`
|
| 18 |
+
- `publish`
|
| 19 |
+
- `publish-merged`
|
| 20 |
+
- `all`
|
| 21 |
+
|
| 22 |
+
## What This Pipeline Produces
|
| 23 |
+
|
| 24 |
+
The pipeline fine-tunes a coach-summary model for Pozify's structured JSON-to-summary task.
|
| 25 |
+
|
| 26 |
+
It can produce:
|
| 27 |
+
|
| 28 |
+
- a LoRA adapter
|
| 29 |
+
- evaluation artifacts
|
| 30 |
+
- a merged full Transformers checkpoint
|
| 31 |
+
- a Hugging Face repo containing the merged checkpoint
|
| 32 |
+
|
| 33 |
+
Important limitation:
|
| 34 |
+
|
| 35 |
+
- Publishing a merged model repo to Hugging Face does **not** currently guarantee that the repo can
|
| 36 |
+
be used through Hugging Face serverless `chat_completion`.
|
| 37 |
+
- In the current codebase, the safest cloud runtime remains `Qwen/Qwen3-14B`.
|
| 38 |
+
- The simplest way to use the fine-tuned merged model today is local inference through
|
| 39 |
+
`POZIFY_COACH_SUMMARY_LOCAL_MODEL_DIR`.
|
| 40 |
+
|
| 41 |
+
## Requirements
|
| 42 |
+
|
| 43 |
+
1. Install and authenticate Modal:
|
| 44 |
+
|
| 45 |
+
```bash
|
| 46 |
+
uv run modal setup
|
| 47 |
+
```
|
| 48 |
+
|
| 49 |
+
2. Make sure local `.env` contains at least:
|
| 50 |
+
|
| 51 |
+
- `HF_TOKEN`
|
| 52 |
+
- optional `POZIFY_COACH_SUMMARY_HF_REPO_ID`
|
| 53 |
+
- optional `POZIFY_COACH_SUMMARY_MERGED_HF_REPO_ID`
|
| 54 |
+
- optional `POZIFY_COACH_SUMMARY_MODEL`
|
| 55 |
+
- optional `POZIFY_COACH_SUMMARY_HF_PRIVATE=1`
|
| 56 |
+
|
| 57 |
+
The script reads local `.env` and injects those values into a Modal secret at runtime.
|
| 58 |
+
|
| 59 |
+
## Input Data
|
| 60 |
+
|
| 61 |
+
The pipeline expects these files:
|
| 62 |
+
|
| 63 |
+
- `data/sft/coach_summary_train.jsonl`
|
| 64 |
+
- `data/sft/coach_summary_eval.jsonl`
|
| 65 |
+
- `data/sft/public_fitness_style.jsonl`
|
| 66 |
+
- `configs/coach_summary_lora.default.json`
|
| 67 |
+
|
| 68 |
+
The default checked-in config currently points to:
|
| 69 |
+
|
| 70 |
+
- base model: `Qwen/Qwen3-14B`
|
| 71 |
+
|
| 72 |
+
## Recommended Training Flow
|
| 73 |
+
|
| 74 |
+
### 1. Build the SFT dataset
|
| 75 |
+
|
| 76 |
+
```bash
|
| 77 |
+
uv run python scripts/build_coach_summary_sft_dataset.py
|
| 78 |
+
```
|
| 79 |
+
|
| 80 |
+
### 2. Copy data into the Modal data volume
|
| 81 |
+
|
| 82 |
+
```bash
|
| 83 |
+
uv run modal run scripts/coach_summary_modal.py --stage prepare-data
|
| 84 |
+
```
|
| 85 |
+
|
| 86 |
+
### 3. Train the adapter
|
| 87 |
+
|
| 88 |
+
```bash
|
| 89 |
+
uv run modal run scripts/coach_summary_modal.py --stage train --epochs 2 --style-weight 0.2
|
| 90 |
+
```
|
| 91 |
+
|
| 92 |
+
### 4. Evaluate
|
| 93 |
+
|
| 94 |
+
```bash
|
| 95 |
+
uv run modal run scripts/coach_summary_modal.py --stage evaluate --limit 5
|
| 96 |
+
```
|
| 97 |
+
|
| 98 |
+
### 5. Merge the adapter into a full model
|
| 99 |
+
|
| 100 |
+
```bash
|
| 101 |
+
uv run modal run scripts/coach_summary_modal.py --stage merge
|
| 102 |
+
```
|
| 103 |
+
|
| 104 |
+
### 6. Publish the merged model
|
| 105 |
+
|
| 106 |
+
```bash
|
| 107 |
+
uv run modal run scripts/coach_summary_modal.py --stage publish-merged --repo-id build-small-hackathon/pozify-coach-summary1
|
| 108 |
+
```
|
| 109 |
+
|
| 110 |
+
### Full end-to-end run
|
| 111 |
+
|
| 112 |
+
```bash
|
| 113 |
+
uv run modal run scripts/coach_summary_modal.py --stage all --epochs 2 --style-weight 0.2 --repo-id build-small-hackathon/pozify-coach-summary1
|
| 114 |
+
```
|
| 115 |
+
|
| 116 |
+
## Cheap Smoke-Test Workflow
|
| 117 |
+
|
| 118 |
+
If you want to reduce GPU cost before a full run:
|
| 119 |
+
|
| 120 |
+
```bash
|
| 121 |
+
uv run modal run scripts/coach_summary_modal.py --stage prepare-data
|
| 122 |
+
uv run modal run scripts/coach_summary_modal.py --stage train --epochs 1 --style-weight 0.2
|
| 123 |
+
uv run modal run scripts/coach_summary_modal.py --stage evaluate --limit 5
|
| 124 |
+
```
|
| 125 |
+
|
| 126 |
+
If the format and verifier behavior look acceptable, rerun with `--epochs 2` and then `merge` +
|
| 127 |
+
`publish-merged`.
|
| 128 |
+
|
| 129 |
+
## Model Volume Artifacts
|
| 130 |
+
|
| 131 |
+
The Modal model volume stores:
|
| 132 |
+
|
| 133 |
+
- `adapter/`
|
| 134 |
+
- `merged_model/`
|
| 135 |
+
- `training_config.json`
|
| 136 |
+
- `training_summary.json`
|
| 137 |
+
- `evaluation.json`
|
| 138 |
+
- `hf_upload.json`
|
| 139 |
+
- `merge_summary.json`
|
| 140 |
+
- `hf_merged_upload.json`
|
| 141 |
+
- `README.md`
|
| 142 |
+
|
| 143 |
+
## Current Runtime Usage
|
| 144 |
+
|
| 145 |
+
### Safest cloud runtime now
|
| 146 |
+
|
| 147 |
+
```bash
|
| 148 |
+
export POZIFY_COACH_SUMMARY_MODEL=Qwen/Qwen3-14B
|
| 149 |
+
uv run python app.py
|
| 150 |
+
```
|
| 151 |
+
|
| 152 |
+
### Use the merged fine-tuned model locally
|
| 153 |
+
|
| 154 |
+
Download the merged repo or copy the merged directory locally, then:
|
| 155 |
+
|
| 156 |
+
```bash
|
| 157 |
+
export POZIFY_COACH_SUMMARY_LOCAL_MODEL_DIR=/path/to/merged_model
|
| 158 |
+
export POZIFY_COACH_SUMMARY_BASE_MODEL=Qwen/Qwen3-14B
|
| 159 |
+
export POZIFY_COACH_SUMMARY_ADAPTER_ID=build-small-hackathon/pozify-coach-summary1
|
| 160 |
+
uv run python app.py
|
| 161 |
+
```
|
| 162 |
+
|
| 163 |
+
### Not recommended right now
|
| 164 |
+
|
| 165 |
+
Pointing app runtime directly at the merged Hugging Face repo through:
|
| 166 |
+
|
| 167 |
+
```bash
|
| 168 |
+
export POZIFY_COACH_SUMMARY_MODEL=build-small-hackathon/pozify-coach-summary1
|
| 169 |
+
```
|
| 170 |
+
|
| 171 |
+
This may still fall back because HF serverless currently rejects that repo as “not a chat model”.
|
| 172 |
+
|
| 173 |
+
## Evaluation Meaning
|
| 174 |
+
|
| 175 |
+
The coach-summary evaluation is task-specific. It measures:
|
| 176 |
+
|
| 177 |
+
- JSON validity rate
|
| 178 |
+
- verifier pass rate
|
| 179 |
+
- section completeness rate
|
| 180 |
+
- failure count and example failures
|
| 181 |
+
|
| 182 |
+
This is more useful for Pozify than generic text-generation metrics because the product depends on:
|
| 183 |
+
|
| 184 |
+
- schema correctness
|
| 185 |
+
- grounded issue references
|
| 186 |
+
- safe variation handling
|
| 187 |
+
- no diagnosis / no injury-prevention claims
|
| 188 |
+
|
| 189 |
+
## Related Docs
|
| 190 |
+
|
| 191 |
+
- [../README.md](../README.md)
|
| 192 |
+
- [31-coach-training-report.md](31-coach-training-report.md)
|
| 193 |
+
- [92-archive-coach-model-data-plan.md](92-archive-coach-model-data-plan.md)
|
docs/31-coach-training-report.md
ADDED
|
@@ -0,0 +1,370 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
# Coach Summary Training Report
|
| 2 |
+
|
| 3 |
+
Generated from the current Pozify codebase state on June 14, 2026.
|
| 4 |
+
|
| 5 |
+
## Summary
|
| 6 |
+
|
| 7 |
+
The coach-summary model in Pozify is a grounded JSON-to-JSON generation component, not a generic
|
| 8 |
+
fitness chatbot. Its job is to convert structured workout-analysis artifacts into a safe,
|
| 9 |
+
evidence-bounded `coach_summary.json`, then pass that output through a verifier before it is shown
|
| 10 |
+
in the app.
|
| 11 |
+
|
| 12 |
+
The current training stack is:
|
| 13 |
+
|
| 14 |
+
- Base model: `Qwen/Qwen3-14B`
|
| 15 |
+
- Fine-tuning method: LoRA / QLoRA-style SFT on Modal
|
| 16 |
+
- Training target: Pozify-native structured summary generation
|
| 17 |
+
- Runtime fallback: deterministic conservative summary when model generation fails or verification fails
|
| 18 |
+
|
| 19 |
+
The current codebase already supports:
|
| 20 |
+
|
| 21 |
+
- dataset building from real Pozify run artifacts
|
| 22 |
+
- Modal stages for prepare/train/evaluate/merge/publish
|
| 23 |
+
- verifier-based evaluation
|
| 24 |
+
- merged full-model publishing
|
| 25 |
+
- UI metadata for provider/model/source reporting
|
| 26 |
+
|
| 27 |
+
The main deployment gap at the time of this report is not training infrastructure. The main gap is
|
| 28 |
+
that the published Hugging Face merged repo is still not accepted by the current Hugging Face
|
| 29 |
+
Inference API path used by the app, so the app falls back to rule-based summaries when that repo is
|
| 30 |
+
selected.
|
| 31 |
+
|
| 32 |
+
## Objective
|
| 33 |
+
|
| 34 |
+
The coach-summary model is designed to generate these grounded sections:
|
| 35 |
+
|
| 36 |
+
- `summary`
|
| 37 |
+
- `what_you_did`
|
| 38 |
+
- `what_looked_good`
|
| 39 |
+
- `what_changed_across_reps`
|
| 40 |
+
- `valid_variation_vs_issue`
|
| 41 |
+
- `top_fixes`
|
| 42 |
+
- `next_session_plan`
|
| 43 |
+
- `confidence_notes`
|
| 44 |
+
|
| 45 |
+
Unlike a free-form assistant, this model is instructed to:
|
| 46 |
+
|
| 47 |
+
- use only structured evidence and retrieved knowledge cards
|
| 48 |
+
- never invent issue labels outside `issue_markers.json`
|
| 49 |
+
- avoid diagnosis language
|
| 50 |
+
- avoid injury-prevention claims
|
| 51 |
+
- preserve valid variation context instead of overcorrecting it
|
| 52 |
+
|
| 53 |
+
This contract is implemented in the prompt builder and enforced again by the verifier.
|
| 54 |
+
|
| 55 |
+
## Training Data
|
| 56 |
+
|
| 57 |
+
The current SFT data is Pozify-native and built from real run artifacts under `runs/`.
|
| 58 |
+
|
| 59 |
+
### Source artifacts per example
|
| 60 |
+
|
| 61 |
+
Each SFT row is constructed from:
|
| 62 |
+
|
| 63 |
+
- `user_profile.json`
|
| 64 |
+
- `exercise_classification.json`
|
| 65 |
+
- `reps.json`
|
| 66 |
+
- `rep_analysis.json`
|
| 67 |
+
- `variation.json`
|
| 68 |
+
- `issue_markers.json`
|
| 69 |
+
- `coach_summary.json`
|
| 70 |
+
|
| 71 |
+
The dataset builder reconstructs typed contracts from those files, retrieves the same knowledge
|
| 72 |
+
cards used at runtime, and serializes a chat-style SFT example with:
|
| 73 |
+
|
| 74 |
+
- system prompt
|
| 75 |
+
- user message containing structured evidence JSON
|
| 76 |
+
- assistant message containing the target `coach_summary.json`
|
| 77 |
+
|
| 78 |
+
### Current local dataset size
|
| 79 |
+
|
| 80 |
+
From the checked-in data in `data/sft/`:
|
| 81 |
+
|
| 82 |
+
| File | Rows |
|
| 83 |
+
| --- | ---: |
|
| 84 |
+
| `coach_summary_train.jsonl` | 22 |
|
| 85 |
+
| `coach_summary_eval.jsonl` | 5 |
|
| 86 |
+
| `public_fitness_style.jsonl` | 854 |
|
| 87 |
+
|
| 88 |
+
The style dataset is much larger than the grounded task dataset, so the training script samples
|
| 89 |
+
only a small portion of style rows according to `style_weight`.
|
| 90 |
+
|
| 91 |
+
## Prompt and Grounding Design
|
| 92 |
+
|
| 93 |
+
The prompt builder creates a structured instruction block plus a structured evidence block.
|
| 94 |
+
|
| 95 |
+
### Evidence included in the prompt
|
| 96 |
+
|
| 97 |
+
- `user_profile`
|
| 98 |
+
- `exercise_classification`
|
| 99 |
+
- `variation`
|
| 100 |
+
- `rep_summary`
|
| 101 |
+
- `issue_summary`
|
| 102 |
+
- `priority_cues`
|
| 103 |
+
- `knowledge_cards`
|
| 104 |
+
|
| 105 |
+
### Core prompt rules
|
| 106 |
+
|
| 107 |
+
- Use only the evidence JSON and retrieved knowledge cards.
|
| 108 |
+
- Do not infer new issues absent from `issue_summary.issues`.
|
| 109 |
+
- Do not diagnose injuries or pathology.
|
| 110 |
+
- Do not claim injury prevention.
|
| 111 |
+
- Do not treat valid variation labels or not-issue labels as errors.
|
| 112 |
+
- Include exact issue or variation labels in backticks when referenced.
|
| 113 |
+
- Return JSON only.
|
| 114 |
+
|
| 115 |
+
This is a good fit for small-model fine-tuning because the task is narrow, repetitive, and highly
|
| 116 |
+
structured.
|
| 117 |
+
|
| 118 |
+
## Model and Training Setup
|
| 119 |
+
|
| 120 |
+
### Current default base model
|
| 121 |
+
|
| 122 |
+
The codebase now defaults to:
|
| 123 |
+
|
| 124 |
+
- `Qwen/Qwen3-14B`
|
| 125 |
+
|
| 126 |
+
This is used in:
|
| 127 |
+
|
| 128 |
+
- `configs/coach_summary_lora.default.json`
|
| 129 |
+
- `scripts/train_coach_summary_lora.py`
|
| 130 |
+
- runtime default in `src/pozify/slm/providers.py`
|
| 131 |
+
|
| 132 |
+
### Default training hyperparameters
|
| 133 |
+
|
| 134 |
+
| Hyperparameter | Value |
|
| 135 |
+
| --- | ---: |
|
| 136 |
+
| Base model | `Qwen/Qwen3-14B` |
|
| 137 |
+
| LoRA rank | 16 |
|
| 138 |
+
| LoRA alpha | 32 |
|
| 139 |
+
| LoRA dropout | 0.05 |
|
| 140 |
+
| Learning rate | 0.0002 |
|
| 141 |
+
| Epochs | 2 |
|
| 142 |
+
| Batch size per device | 1 |
|
| 143 |
+
| Gradient accumulation | 8 |
|
| 144 |
+
| Max sequence length | 4096 |
|
| 145 |
+
| Default style weight | 0.2 |
|
| 146 |
+
|
| 147 |
+
### Modal implementation
|
| 148 |
+
|
| 149 |
+
The full training pipeline is implemented in `scripts/coach_summary_modal.py` with these stages:
|
| 150 |
+
|
| 151 |
+
- `prepare-data`
|
| 152 |
+
- `train`
|
| 153 |
+
- `evaluate`
|
| 154 |
+
- `merge`
|
| 155 |
+
- `publish`
|
| 156 |
+
- `publish-merged`
|
| 157 |
+
- `all`
|
| 158 |
+
|
| 159 |
+
The training stage:
|
| 160 |
+
|
| 161 |
+
- loads the base model with 4-bit quantization
|
| 162 |
+
- fine-tunes with TRL `SFTTrainer`
|
| 163 |
+
- saves adapter weights and tokenizer to the Modal model volume
|
| 164 |
+
|
| 165 |
+
The merge stage:
|
| 166 |
+
|
| 167 |
+
- loads base model plus adapter
|
| 168 |
+
- calls `merge_and_unload()`
|
| 169 |
+
- writes a merged full checkpoint to `merged_model/`
|
| 170 |
+
|
| 171 |
+
## Evaluation Design
|
| 172 |
+
|
| 173 |
+
The evaluation stage is not based on generic BLEU or chat preference metrics. It uses task-specific
|
| 174 |
+
checks that match Pozify's production constraints.
|
| 175 |
+
|
| 176 |
+
### Reported evaluation metrics
|
| 177 |
+
|
| 178 |
+
- JSON validity rate
|
| 179 |
+
- verifier pass rate
|
| 180 |
+
- section completeness rate
|
| 181 |
+
- failure count and example failures
|
| 182 |
+
|
| 183 |
+
### Verifier checks
|
| 184 |
+
|
| 185 |
+
The verifier currently enforces:
|
| 186 |
+
|
| 187 |
+
- `no_issue_outside_json`
|
| 188 |
+
- `variation_not_overcorrected`
|
| 189 |
+
- `no_diagnosis`
|
| 190 |
+
- `no_injury_prevention_claim`
|
| 191 |
+
- `confidence_notes_present_when_required`
|
| 192 |
+
|
| 193 |
+
This is a strong design choice for Pozify because it measures whether the model behaves safely and
|
| 194 |
+
stays grounded, not just whether it sounds fluent.
|
| 195 |
+
|
| 196 |
+
## Latest Observed Training Outcome
|
| 197 |
+
|
| 198 |
+
From the latest visible Modal training logs for the full coach-summary flow:
|
| 199 |
+
|
| 200 |
+
### Training summary
|
| 201 |
+
|
| 202 |
+
| Metric | Value |
|
| 203 |
+
| --- | ---: |
|
| 204 |
+
| Train rows | 22 |
|
| 205 |
+
| Eval rows | 5 |
|
| 206 |
+
| Style rows mixed in | 4 |
|
| 207 |
+
| Merged train rows | 26 |
|
| 208 |
+
| Epochs | 2 |
|
| 209 |
+
| Global steps | 8 |
|
| 210 |
+
| Training loss | 1.0797 |
|
| 211 |
+
|
| 212 |
+
### Evaluation summary
|
| 213 |
+
|
| 214 |
+
| Metric | Value |
|
| 215 |
+
| --- | ---: |
|
| 216 |
+
| Evaluated count | 5 |
|
| 217 |
+
| JSON valid count | 2 |
|
| 218 |
+
| JSON validity rate | 0.40 |
|
| 219 |
+
| Verifier pass count | 0 |
|
| 220 |
+
| Verifier pass rate | 0.00 |
|
| 221 |
+
| Section completeness rate | 0.00 |
|
| 222 |
+
|
| 223 |
+
### Observed failure modes
|
| 224 |
+
|
| 225 |
+
- missing required top-level fields such as `summary`
|
| 226 |
+
- malformed JSON with delimiter errors
|
| 227 |
+
- outputs that fail schema extraction before verifier success is even possible
|
| 228 |
+
|
| 229 |
+
These numbers suggest that the current grounded task setup is correct in principle, but the dataset
|
| 230 |
+
is still too small and the model is not yet reliably producing the full required schema.
|
| 231 |
+
|
| 232 |
+
## Runtime Behavior in the App
|
| 233 |
+
|
| 234 |
+
At runtime the pipeline does this:
|
| 235 |
+
|
| 236 |
+
1. Generate a model summary from structured evidence.
|
| 237 |
+
2. Parse the model output into `coach_summary.json`.
|
| 238 |
+
3. Run the verifier.
|
| 239 |
+
4. If generation fails, use `fallback_initial`.
|
| 240 |
+
5. If generation succeeds but verification fails, use `fallback_after_verification` unless bypass is enabled.
|
| 241 |
+
|
| 242 |
+
The final report stores:
|
| 243 |
+
|
| 244 |
+
- `coach_summary_provider`
|
| 245 |
+
- `coach_summary_model`
|
| 246 |
+
- `coach_summary_source`
|
| 247 |
+
- verifier bypass metadata
|
| 248 |
+
|
| 249 |
+
This makes the UI traceable and helps distinguish:
|
| 250 |
+
|
| 251 |
+
- cloud model output
|
| 252 |
+
- local model output
|
| 253 |
+
- conservative fallback output
|
| 254 |
+
|
| 255 |
+
## Current Deployment Status
|
| 256 |
+
|
| 257 |
+
### What works
|
| 258 |
+
|
| 259 |
+
- grounded prompt contract
|
| 260 |
+
- deterministic knowledge-card retrieval
|
| 261 |
+
- SFT dataset builder from Pozify artifacts
|
| 262 |
+
- Modal train/evaluate/merge/publish pipeline
|
| 263 |
+
- verifier integration
|
| 264 |
+
- fallback summary integration
|
| 265 |
+
- runtime metadata reporting in UI
|
| 266 |
+
|
| 267 |
+
### What is currently failing
|
| 268 |
+
|
| 269 |
+
The published merged Hugging Face repo for the fine-tuned coach model is still not accepted by the
|
| 270 |
+
Hugging Face inference route currently used in `HFInferenceCoachSummaryModel`.
|
| 271 |
+
|
| 272 |
+
Observed runtime failure:
|
| 273 |
+
|
| 274 |
+
- `The requested model 'build-small-hackathon/pozify-coach-summary1' is not a chat model.`
|
| 275 |
+
|
| 276 |
+
Because of that, the app falls back even when the runtime resolves the correct repo ID.
|
| 277 |
+
|
| 278 |
+
### Practical implication
|
| 279 |
+
|
| 280 |
+
For the app to avoid fallback today, the safest temporary runtime choice is a cloud-hosted model
|
| 281 |
+
that is already supported by Hugging Face Inference, such as:
|
| 282 |
+
|
| 283 |
+
- `Qwen/Qwen3-14B`
|
| 284 |
+
|
| 285 |
+
The fine-tuned merged repo is still useful as a training artifact, but it is not yet plug-and-play
|
| 286 |
+
through the current cloud inference path.
|
| 287 |
+
|
| 288 |
+
## Assessment
|
| 289 |
+
|
| 290 |
+
### Strengths
|
| 291 |
+
|
| 292 |
+
- The task definition is well-scoped and matches the product.
|
| 293 |
+
- The prompt is strongly grounded on structured artifacts.
|
| 294 |
+
- The verifier is aligned with real product risk, not just language quality.
|
| 295 |
+
- The dataset builder is tightly coupled to actual runtime contracts.
|
| 296 |
+
- The pipeline supports both model generation and deterministic fallback.
|
| 297 |
+
|
| 298 |
+
### Weaknesses
|
| 299 |
+
|
| 300 |
+
- The grounded SFT dataset is still very small.
|
| 301 |
+
- Schema reliability is not yet strong enough.
|
| 302 |
+
- Verifier pass rate is currently too low for production dependence.
|
| 303 |
+
- Published merged artifacts are not yet working cleanly with the current Hugging Face inference strategy.
|
| 304 |
+
- Modal config reuse can accidentally preserve stale training settings if old volume artifacts are not cleaned.
|
| 305 |
+
|
| 306 |
+
## Recommendations
|
| 307 |
+
|
| 308 |
+
### Short term
|
| 309 |
+
|
| 310 |
+
1. Use `Qwen/Qwen3-14B` as the temporary runtime cloud model.
|
| 311 |
+
2. Keep the fallback summary enabled in production.
|
| 312 |
+
3. Expand the grounded SFT dataset from more real runs before increasing training complexity.
|
| 313 |
+
4. Add stronger output-format controls or post-processing to improve JSON validity.
|
| 314 |
+
5. Clean or version Modal model volumes when switching base models.
|
| 315 |
+
|
| 316 |
+
### Medium term
|
| 317 |
+
|
| 318 |
+
1. Grow the Pozify-native dataset to at least 100 to 300 high-quality examples.
|
| 319 |
+
2. Evaluate `epochs=1` vs `epochs=2` and `style_weight=0.1` vs `0.2`.
|
| 320 |
+
3. Add targeted eval slices:
|
| 321 |
+
- no-issue cases
|
| 322 |
+
- valid-variation cases
|
| 323 |
+
- multi-issue cases
|
| 324 |
+
- low-confidence / low-pose-coverage cases
|
| 325 |
+
4. Improve inference compatibility for the merged repo or support local merged-model inference directly.
|
| 326 |
+
|
| 327 |
+
## Reproduction Commands
|
| 328 |
+
|
| 329 |
+
Build the grounded SFT dataset from run artifacts:
|
| 330 |
+
|
| 331 |
+
```bash
|
| 332 |
+
uv run python scripts/build_coach_summary_sft_dataset.py
|
| 333 |
+
```
|
| 334 |
+
|
| 335 |
+
Run the full Modal training flow:
|
| 336 |
+
|
| 337 |
+
```bash
|
| 338 |
+
uv run modal run scripts/coach_summary_modal.py --stage all --epochs 2 --style-weight 0.2 --repo-id build-small-hackathon/pozify-coach-summary1
|
| 339 |
+
```
|
| 340 |
+
|
| 341 |
+
Run the app against a cloud-supported fallback-safe runtime model:
|
| 342 |
+
|
| 343 |
+
```bash
|
| 344 |
+
unset POZIFY_COACH_SUMMARY_MODEL
|
| 345 |
+
uv run python app.py
|
| 346 |
+
```
|
| 347 |
+
|
| 348 |
+
Or set the runtime model explicitly:
|
| 349 |
+
|
| 350 |
+
```bash
|
| 351 |
+
export POZIFY_COACH_SUMMARY_MODEL=Qwen/Qwen3-14B
|
| 352 |
+
uv run python app.py
|
| 353 |
+
```
|
| 354 |
+
|
| 355 |
+
## Conclusion
|
| 356 |
+
|
| 357 |
+
Pozify's coach-summary model training architecture is directionally strong. The core design choice
|
| 358 |
+
to train a grounded summary model on structured evidence, then gate it with a verifier, is the
|
| 359 |
+
right one for this product.
|
| 360 |
+
|
| 361 |
+
The current bottleneck is not lack of infrastructure. It is model reliability and inference
|
| 362 |
+
deployment maturity:
|
| 363 |
+
|
| 364 |
+
- too few grounded examples
|
| 365 |
+
- low schema-compliance rate
|
| 366 |
+
- no verifier passes in the latest visible eval
|
| 367 |
+
- published merged repo still not usable through the current HF inference path
|
| 368 |
+
|
| 369 |
+
The codebase is ready for the next iteration. The next high-leverage step is to improve dataset
|
| 370 |
+
size and output reliability while keeping the verifier and fallback architecture intact.
|
docs/{custom-data-collection-guide.md → 40-data-custom-collection-guide.md}
RENAMED
|
File without changes
|
docs/{implementation-plan.md → 90-archive-implementation-plan.md}
RENAMED
|
@@ -1,5 +1,10 @@
|
|
| 1 |
# Pozify Implementation Plan
|
| 2 |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 3 |
This plan breaks Pozify into implementation workstreams that can be developed independently while preserving the current JSON data contracts.
|
| 4 |
|
| 5 |
## Phase 1: Foundation And Contracts
|
|
|
|
| 1 |
# Pozify Implementation Plan
|
| 2 |
|
| 3 |
+
Status: historical implementation plan.
|
| 4 |
+
|
| 5 |
+
Use [../README.md](../README.md) and [01-docs-index.md](01-docs-index.md) for the current runtime
|
| 6 |
+
workflow and operational commands.
|
| 7 |
+
|
| 8 |
This plan breaks Pozify into implementation workstreams that can be developed independently while preserving the current JSON data contracts.
|
| 9 |
|
| 10 |
## Phase 1: Foundation And Contracts
|
docs/{coach-analysis-implementation-plan.md → 91-archive-coach-analysis-implementation-plan.md}
RENAMED
|
@@ -1,5 +1,10 @@
|
|
| 1 |
# Pozify Coach Analysis Expansion Plan
|
| 2 |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 3 |
## Objective
|
| 4 |
|
| 5 |
Extend Pozify's grounded coach-summary pipeline with a dataset-ready knowledge layer so the app can incorporate richer exercise expertise without turning the product into a generic chatbot.
|
|
|
|
| 1 |
# Pozify Coach Analysis Expansion Plan
|
| 2 |
|
| 3 |
+
Status: historical implementation plan for the coach-analysis branch work.
|
| 4 |
+
|
| 5 |
+
Use [../README.md](../README.md) and [01-docs-index.md](01-docs-index.md) for the current runtime
|
| 6 |
+
workflow and operational commands.
|
| 7 |
+
|
| 8 |
## Objective
|
| 9 |
|
| 10 |
Extend Pozify's grounded coach-summary pipeline with a dataset-ready knowledge layer so the app can incorporate richer exercise expertise without turning the product into a generic chatbot.
|
docs/{coach-model-data-plan.md → 92-archive-coach-model-data-plan.md}
RENAMED
|
@@ -1,5 +1,11 @@
|
|
| 1 |
# Pozify Coach Model Data Plan
|
| 2 |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 3 |
## Objective
|
| 4 |
|
| 5 |
Define a practical data and modeling plan for improving Pozify's coach summary and coach-style guidance using open datasets and the current codebase.
|
|
|
|
| 1 |
# Pozify Coach Model Data Plan
|
| 2 |
|
| 3 |
+
Status: planning and architecture note.
|
| 4 |
+
|
| 5 |
+
This file is useful for model and dataset strategy, but it is not the source of truth for the
|
| 6 |
+
current run/deploy commands. Use [../README.md](../README.md) and
|
| 7 |
+
[30-coach-modal-training.md](30-coach-modal-training.md) for the current workflow.
|
| 8 |
+
|
| 9 |
## Objective
|
| 10 |
|
| 11 |
Define a practical data and modeling plan for improving Pozify's coach summary and coach-style guidance using open datasets and the current codebase.
|
docs/{pozify-project-documentation.md → 99-archive-pozify-project-documentation.md}
RENAMED
|
@@ -1,5 +1,10 @@
|
|
| 1 |
# Pozify Project Documentation
|
| 2 |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 3 |
## 1. Product Overview
|
| 4 |
|
| 5 |
**Pozify** is a Gradio web app that lets a user upload or record a short workout video, then returns a rep-by-rep movement report built from pose landmarks, movement metrics, frame-level issue markers, and goal-aware coaching feedback.
|
|
|
|
| 1 |
# Pozify Project Documentation
|
| 2 |
|
| 3 |
+
Status: large historical product/design document.
|
| 4 |
+
|
| 5 |
+
Some sections may lag behind the current runtime implementation. For the current project entrypoint,
|
| 6 |
+
commands, and model workflow, use [../README.md](../README.md) and [01-docs-index.md](01-docs-index.md).
|
| 7 |
+
|
| 8 |
## 1. Product Overview
|
| 9 |
|
| 10 |
**Pozify** is a Gradio web app that lets a user upload or record a short workout video, then returns a rep-by-rep movement report built from pose landmarks, movement metrics, frame-level issue markers, and goal-aware coaching feedback.
|
docs/coach-summary-modal-training.md
DELETED
|
@@ -1,139 +0,0 @@
|
|
| 1 |
-
# Coach Summary Modal Training
|
| 2 |
-
|
| 3 |
-
This guide explains how to train, evaluate, and publish the Pozify coach-summary LoRA adapter on [Modal](https://modal.com).
|
| 4 |
-
|
| 5 |
-
## What The Script Does
|
| 6 |
-
|
| 7 |
-
The Modal pipeline lives in:
|
| 8 |
-
|
| 9 |
-
- `scripts/coach_summary_modal.py`
|
| 10 |
-
|
| 11 |
-
It follows the same stage pattern as the exercise-router Modal pipeline:
|
| 12 |
-
|
| 13 |
-
- `prepare-data`
|
| 14 |
-
- `train`
|
| 15 |
-
- `evaluate`
|
| 16 |
-
- `merge`
|
| 17 |
-
- `publish`
|
| 18 |
-
- `publish-merged`
|
| 19 |
-
- `all`
|
| 20 |
-
|
| 21 |
-
## Requirements
|
| 22 |
-
|
| 23 |
-
1. Install the Modal CLI locally.
|
| 24 |
-
2. Authenticate Modal:
|
| 25 |
-
|
| 26 |
-
```bash
|
| 27 |
-
modal setup
|
| 28 |
-
```
|
| 29 |
-
|
| 30 |
-
3. Make sure your local `.env` contains:
|
| 31 |
-
|
| 32 |
-
- `HF_TOKEN`
|
| 33 |
-
- optional `POZIFY_COACH_SUMMARY_HF_REPO_ID`
|
| 34 |
-
- optional `POZIFY_COACH_SUMMARY_MERGED_HF_REPO_ID`
|
| 35 |
-
- recommended `POZIFY_COACH_SUMMARY_MODEL`
|
| 36 |
-
- optional `POZIFY_COACH_SUMMARY_HF_PRIVATE=1`
|
| 37 |
-
|
| 38 |
-
The script reads your local `.env` and injects those values into a Modal secret at runtime, so for local `modal run ...` usage you do not need to pre-create a hosted Modal secret just to run `prepare-data`, `train`, or `publish`.
|
| 39 |
-
|
| 40 |
-
If you prefer a hosted secret for team/shared environments, you can still create one manually in Modal and adapt the script later.
|
| 41 |
-
|
| 42 |
-
## Data Inputs
|
| 43 |
-
|
| 44 |
-
The script expects these local artifacts to already exist in the repo:
|
| 45 |
-
|
| 46 |
-
- `data/sft/coach_summary_train.jsonl`
|
| 47 |
-
- `data/sft/coach_summary_eval.jsonl`
|
| 48 |
-
- `data/sft/public_fitness_style.jsonl`
|
| 49 |
-
- `configs/coach_summary_lora.default.json`
|
| 50 |
-
|
| 51 |
-
These are copied into the Modal data volume during `prepare-data`.
|
| 52 |
-
|
| 53 |
-
## Stage Commands
|
| 54 |
-
|
| 55 |
-
Prepare training data:
|
| 56 |
-
|
| 57 |
-
```bash
|
| 58 |
-
modal run scripts/coach_summary_modal.py --stage prepare-data
|
| 59 |
-
```
|
| 60 |
-
|
| 61 |
-
Train the LoRA adapter:
|
| 62 |
-
|
| 63 |
-
```bash
|
| 64 |
-
modal run scripts/coach_summary_modal.py --stage train --epochs 2 --style-weight 0.2
|
| 65 |
-
```
|
| 66 |
-
|
| 67 |
-
Evaluate the trained adapter:
|
| 68 |
-
|
| 69 |
-
```bash
|
| 70 |
-
modal run scripts/coach_summary_modal.py --stage evaluate --limit 5
|
| 71 |
-
```
|
| 72 |
-
|
| 73 |
-
Publish the adapter and metadata to Hugging Face:
|
| 74 |
-
|
| 75 |
-
```bash
|
| 76 |
-
modal run scripts/coach_summary_modal.py --stage publish --repo-id build-small-hackathon/pozify-coach-summary
|
| 77 |
-
```
|
| 78 |
-
|
| 79 |
-
Merge the LoRA adapter into a full Transformers checkpoint:
|
| 80 |
-
|
| 81 |
-
```bash
|
| 82 |
-
modal run scripts/coach_summary_modal.py --stage merge
|
| 83 |
-
```
|
| 84 |
-
|
| 85 |
-
Publish the merged inference-ready model to Hugging Face:
|
| 86 |
-
|
| 87 |
-
```bash
|
| 88 |
-
modal run scripts/coach_summary_modal.py --stage publish-merged --repo-id build-small-hackathon/pozify-coach-summary
|
| 89 |
-
```
|
| 90 |
-
|
| 91 |
-
If your Hugging Face token does not have permission to create or write under an organization
|
| 92 |
-
namespace, publish to a personal repo instead:
|
| 93 |
-
|
| 94 |
-
```bash
|
| 95 |
-
modal run scripts/coach_summary_modal.py --stage publish-merged --repo-id <your-username>/pozify-coach-summary
|
| 96 |
-
```
|
| 97 |
-
|
| 98 |
-
You can also set this once in `.env`:
|
| 99 |
-
|
| 100 |
-
```bash
|
| 101 |
-
POZIFY_COACH_SUMMARY_MODEL=<your-username>/pozify-coach-summary
|
| 102 |
-
POZIFY_COACH_SUMMARY_MERGED_HF_REPO_ID=<your-username>/pozify-coach-summary
|
| 103 |
-
```
|
| 104 |
-
|
| 105 |
-
Run the full pipeline end to end:
|
| 106 |
-
|
| 107 |
-
```bash
|
| 108 |
-
modal run scripts/coach_summary_modal.py --stage all --epochs 2 --style-weight 0.2 --repo-id build-small-hackathon/pozify-coach-summary
|
| 109 |
-
```
|
| 110 |
-
|
| 111 |
-
## Artifacts
|
| 112 |
-
|
| 113 |
-
The Modal model volume stores:
|
| 114 |
-
|
| 115 |
-
- `adapter/`
|
| 116 |
-
- `merged_model/`
|
| 117 |
-
- `training_config.json`
|
| 118 |
-
- `training_summary.json`
|
| 119 |
-
- `evaluation.json`
|
| 120 |
-
- `hf_upload.json`
|
| 121 |
-
- `merge_summary.json`
|
| 122 |
-
- `hf_merged_upload.json`
|
| 123 |
-
- `README.md`
|
| 124 |
-
|
| 125 |
-
## Runtime Usage
|
| 126 |
-
|
| 127 |
-
For cloud inference in the current Pozify app, point runtime to the merged full model repo:
|
| 128 |
-
|
| 129 |
-
```bash
|
| 130 |
-
export POZIFY_COACH_SUMMARY_MODEL=build-small-hackathon/pozify-coach-summary
|
| 131 |
-
```
|
| 132 |
-
|
| 133 |
-
`POZIFY_COACH_SUMMARY_ADAPTER_ID` is no longer used as the remote inference target. Keep it only for adapter-centric workflows such as local merge/evaluation.
|
| 134 |
-
|
| 135 |
-
If you download the merged model locally instead, use:
|
| 136 |
-
|
| 137 |
-
```bash
|
| 138 |
-
export POZIFY_COACH_SUMMARY_LOCAL_MODEL_DIR=/path/to/merged_model
|
| 139 |
-
```
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
scripts/exercise_router_modal.py
CHANGED
|
@@ -55,13 +55,13 @@ image = (
|
|
| 55 |
)
|
| 56 |
.add_local_dir("src", "/root/src", copy=True)
|
| 57 |
.add_local_file(
|
| 58 |
-
"docs/
|
| 59 |
-
"/root/docs/
|
| 60 |
copy=True,
|
| 61 |
)
|
| 62 |
.add_local_file(
|
| 63 |
-
"docs/
|
| 64 |
-
"/root/docs/
|
| 65 |
copy=True,
|
| 66 |
)
|
| 67 |
)
|
|
|
|
| 55 |
)
|
| 56 |
.add_local_dir("src", "/root/src", copy=True)
|
| 57 |
.add_local_file(
|
| 58 |
+
"docs/22-router-huggingface-model-card.md",
|
| 59 |
+
"/root/docs/22-router-huggingface-model-card.md",
|
| 60 |
copy=True,
|
| 61 |
)
|
| 62 |
.add_local_file(
|
| 63 |
+
"docs/20-router-training-report.md",
|
| 64 |
+
"/root/docs/20-router-training-report.md",
|
| 65 |
copy=True,
|
| 66 |
)
|
| 67 |
)
|
scripts/upload_exercise_router_to_hf.py
CHANGED
|
@@ -7,8 +7,8 @@ from huggingface_hub import HfApi
|
|
| 7 |
|
| 8 |
|
| 9 |
DEFAULT_MODEL_DIR = Path("models/exercise_router/active")
|
| 10 |
-
DEFAULT_MODEL_CARD = Path("docs/
|
| 11 |
-
DEFAULT_TRAINING_REPORT = Path("docs/
|
| 12 |
ARTIFACT_FILENAMES = (
|
| 13 |
"baseline.joblib",
|
| 14 |
"router.joblib",
|
|
|
|
| 7 |
|
| 8 |
|
| 9 |
DEFAULT_MODEL_DIR = Path("models/exercise_router/active")
|
| 10 |
+
DEFAULT_MODEL_CARD = Path("docs/22-router-huggingface-model-card.md")
|
| 11 |
+
DEFAULT_TRAINING_REPORT = Path("docs/20-router-training-report.md")
|
| 12 |
ARTIFACT_FILENAMES = (
|
| 13 |
"baseline.joblib",
|
| 14 |
"router.joblib",
|