raviearjun commited on
Commit
97b7d5a
·
verified ·
1 Parent(s): 6cb51b5

Update model card

Browse files
Files changed (1) hide show
  1. README.md +10 -1
README.md CHANGED
@@ -88,6 +88,14 @@ columns the model expects. The canonical definition lives in
88
  `src/engagement_predictor/features.py` in the application repository
89
  (https://github.com/<your-org>/viralst).
90
 
 
 
 
 
 
 
 
 
91
  ## How to use
92
 
93
  ```python
@@ -105,7 +113,8 @@ prediction = model.predict(X)
105
 
106
  ## Limitations
107
 
108
- - Generated from a blend of real-world samples and synthetic modeling; while informed by actual examples, it may not fully capture broader platform trends, engagement distributions, or authentic creator-audience behavior
 
109
  - Feature quality depends on upstream LLM extraction from brief documents;
110
  prediction quality degrades if that extraction is inaccurate or incomplete.
111
  - Not yet validated against real campaign data from brands outside the
 
88
  `src/engagement_predictor/features.py` in the application repository
89
  (https://github.com/<your-org>/viralst).
90
 
91
+ ## Training dataset
92
+
93
+ The raw synthetic dataset used to train this model is included in this repo
94
+ under `dataset/` (`brands.csv`, `briefs.csv`, `contents.csv` — 30
95
+ brands, 300 briefs, 2000 content rows). It was generated by
96
+ `training/generate_poc_data.py`; see "Training data and methodology" above
97
+ for why it is synthetic and what it does and does not represent.
98
+
99
  ## How to use
100
 
101
  ```python
 
113
 
114
  ## Limitations
115
 
116
+ - Trained on synthetic data; does not reflect real-world engagement
117
+ distributions, platform trends, or actual creator/audience behavior.
118
  - Feature quality depends on upstream LLM extraction from brief documents;
119
  prediction quality degrades if that extraction is inaccurate or incomplete.
120
  - Not yet validated against real campaign data from brands outside the