Text Classification
Transformers
PyTorch
English
promptforge_quality
promptforge
prompt-engineering
prompt-quality
modernbert
regression
llm
Instructions to use ArjunShukla/PromptForge-Quality with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use ArjunShukla/PromptForge-Quality with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("text-classification", model="ArjunShukla/PromptForge-Quality")# Load model directly from transformers import AutoModel model = AutoModel.from_pretrained("ArjunShukla/PromptForge-Quality", device_map="auto") - Notebooks
- Google Colab
- Kaggle
Upload folder using huggingface_hub
Browse files
README.md
CHANGED
|
@@ -19,7 +19,7 @@ pipeline_tag: text-classification
|
|
| 19 |
|
| 20 |
Multi-dimension **prompt quality scorer**. Given an LLM prompt, returns an overall quality score plus per-dimension scores, inferred issues, and missing information.
|
| 21 |
|
| 22 |
-
Part of [PromptForge](https://github.com/
|
| 23 |
|
| 24 |
## Model Details
|
| 25 |
|
|
@@ -50,7 +50,7 @@ The model also surfaces **issues** (e.g. `too_vague`, `missing_context`) and **m
|
|
| 50 |
|
| 51 |
### Model Sources
|
| 52 |
|
| 53 |
-
- **Repository:** https://github.com/
|
| 54 |
- **Companion model:** PromptForge-Optimizer (Qwen2.5-1.5B LoRA prompt rewriter)
|
| 55 |
- **Demo:** Gradio app in the PromptForge repo (`demo/app.py`)
|
| 56 |
|
|
@@ -97,8 +97,8 @@ pip install promptforge
|
|
| 97 |
# or from source: pip install -e ".[demo]"
|
| 98 |
|
| 99 |
python -m promptforge download \
|
| 100 |
-
--quality-repo
|
| 101 |
-
--optimizer-repo
|
| 102 |
|
| 103 |
python -m promptforge analyze "Build me a website"
|
| 104 |
```
|
|
@@ -106,7 +106,7 @@ python -m promptforge analyze "Build me a website"
|
|
| 106 |
```python
|
| 107 |
from promptforge import PromptForge
|
| 108 |
|
| 109 |
-
pf = PromptForge(quality_model_path="
|
| 110 |
print(pf.analyze("Make an app."))
|
| 111 |
# → quality_score, dimensions, issues, missing_information
|
| 112 |
```
|
|
@@ -117,8 +117,8 @@ print(pf.analyze("Make an app."))
|
|
| 117 |
from promptforge import PromptForge
|
| 118 |
|
| 119 |
pf = PromptForge(
|
| 120 |
-
quality_model_path="
|
| 121 |
-
optimizer_model_path="
|
| 122 |
)
|
| 123 |
result = pf.run("Make an app about social media like facebook and stuff")
|
| 124 |
print(result["before"]["quality_score"], "→", result["after"]["quality_score"])
|
|
@@ -191,7 +191,7 @@ ModernBERT encoder with dual / multi regression heads predicting continuous qual
|
|
| 191 |
title = {PromptForge-Quality},
|
| 192 |
author = {PromptForge Contributors},
|
| 193 |
year = {2026},
|
| 194 |
-
url = {https://huggingface.co/
|
| 195 |
}
|
| 196 |
```
|
| 197 |
|
|
|
|
| 19 |
|
| 20 |
Multi-dimension **prompt quality scorer**. Given an LLM prompt, returns an overall quality score plus per-dimension scores, inferred issues, and missing information.
|
| 21 |
|
| 22 |
+
Part of [PromptForge](https://github.com/arjun988/promptModel) — local-first prompt scoring and optimization.
|
| 23 |
|
| 24 |
## Model Details
|
| 25 |
|
|
|
|
| 50 |
|
| 51 |
### Model Sources
|
| 52 |
|
| 53 |
+
- **Repository:** https://github.com/arjun988/promptModel
|
| 54 |
- **Companion model:** PromptForge-Optimizer (Qwen2.5-1.5B LoRA prompt rewriter)
|
| 55 |
- **Demo:** Gradio app in the PromptForge repo (`demo/app.py`)
|
| 56 |
|
|
|
|
| 97 |
# or from source: pip install -e ".[demo]"
|
| 98 |
|
| 99 |
python -m promptforge download \
|
| 100 |
+
--quality-repo ArjunShukla/PromptForge-Quality \
|
| 101 |
+
--optimizer-repo ArjunShukla/PromptForge-Optimizer
|
| 102 |
|
| 103 |
python -m promptforge analyze "Build me a website"
|
| 104 |
```
|
|
|
|
| 106 |
```python
|
| 107 |
from promptforge import PromptForge
|
| 108 |
|
| 109 |
+
pf = PromptForge(quality_model_path="ArjunShukla/PromptForge-Quality")
|
| 110 |
print(pf.analyze("Make an app."))
|
| 111 |
# → quality_score, dimensions, issues, missing_information
|
| 112 |
```
|
|
|
|
| 117 |
from promptforge import PromptForge
|
| 118 |
|
| 119 |
pf = PromptForge(
|
| 120 |
+
quality_model_path="ArjunShukla/PromptForge-Quality",
|
| 121 |
+
optimizer_model_path="ArjunShukla/PromptForge-Optimizer",
|
| 122 |
)
|
| 123 |
result = pf.run("Make an app about social media like facebook and stuff")
|
| 124 |
print(result["before"]["quality_score"], "→", result["after"]["quality_score"])
|
|
|
|
| 191 |
title = {PromptForge-Quality},
|
| 192 |
author = {PromptForge Contributors},
|
| 193 |
year = {2026},
|
| 194 |
+
url = {https://huggingface.co/ArjunShukla/PromptForge-Quality}
|
| 195 |
}
|
| 196 |
```
|
| 197 |
|