Spaces:
Running on Zero
Running on Zero
Upload 7 files
Browse files- README.md +38 -6
- app.py +363 -0
- config.py +20 -0
- llm_reviewer.py +111 -0
- ml_classifier.py +57 -0
- precomputed.py +93 -0
- requirements.txt +6 -0
README.md
CHANGED
|
@@ -1,14 +1,46 @@
|
|
| 1 |
---
|
| 2 |
title: Hybrid Comment Moderation
|
| 3 |
-
emoji:
|
| 4 |
-
colorFrom:
|
| 5 |
colorTo: green
|
| 6 |
sdk: gradio
|
| 7 |
-
sdk_version:
|
| 8 |
-
python_version: '3.12'
|
| 9 |
app_file: app.py
|
| 10 |
pinned: false
|
| 11 |
-
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 12 |
---
|
| 13 |
|
| 14 |
-
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
---
|
| 2 |
title: Hybrid Comment Moderation
|
| 3 |
+
emoji: π¬
|
| 4 |
+
colorFrom: blue
|
| 5 |
colorTo: green
|
| 6 |
sdk: gradio
|
| 7 |
+
sdk_version: "5.34.0"
|
|
|
|
| 8 |
app_file: app.py
|
| 9 |
pinned: false
|
| 10 |
+
license: mit
|
| 11 |
+
tags:
|
| 12 |
+
- content-moderation
|
| 13 |
+
- hybrid-ai
|
| 14 |
+
- distilbert
|
| 15 |
+
- qwen
|
| 16 |
+
- cs541
|
| 17 |
---
|
| 18 |
|
| 19 |
+
# π¬ Hybrid Comment Moderation
|
| 20 |
+
|
| 21 |
+
**CS541 AI Final Project β Stevens Institute of Technology**
|
| 22 |
+
|
| 23 |
+
A two-stage content moderation pipeline that routes comments intelligently:
|
| 24 |
+
|
| 25 |
+
1. **Stage 1 β ML Classifier** (DistilBERT, CPU, ~7 ms): handles confident predictions instantly.
|
| 26 |
+
2. **Stage 2 β LLM Reviewer** (Qwen2.5-3B-Instruct, GPU, ~1β2 s): reviews only ambiguous comments.
|
| 27 |
+
|
| 28 |
+
## Tabs
|
| 29 |
+
|
| 30 |
+
| Tab | Description |
|
| 31 |
+
|:----|:------------|
|
| 32 |
+
| π **Live Demo** | Type a comment, pick a strategy, see the verdict |
|
| 33 |
+
| π **Evaluation** | Pre-computed metrics on 100 balanced Civil Comments samples |
|
| 34 |
+
| ποΈ **Architecture** | Pipeline diagram and design rationale |
|
| 35 |
+
|
| 36 |
+
## Usage
|
| 37 |
+
|
| 38 |
+
- **ML-only** works for everyone (CPU, no sign-in needed).
|
| 39 |
+
- **Hybrid** and **LLM-only** require a free HuggingFace account for ZeroGPU access.
|
| 40 |
+
|
| 41 |
+
## Reference
|
| 42 |
+
|
| 43 |
+
- Textbook: *Understanding Deep Learning* by Simon J.D. Prince
|
| 44 |
+
- Dataset: [google/civil_comments](https://huggingface.co/datasets/google/civil_comments)
|
| 45 |
+
- ML model: [martin-ha/toxic-comment-model](https://huggingface.co/martin-ha/toxic-comment-model)
|
| 46 |
+
- LLM: [Qwen/Qwen2.5-3B-Instruct](https://huggingface.co/Qwen/Qwen2.5-3B-Instruct)
|
app.py
ADDED
|
@@ -0,0 +1,363 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
"""
|
| 2 |
+
app.py β HuggingFace Spaces entry point for Hybrid Comment Moderation.
|
| 3 |
+
|
| 4 |
+
Three tabs:
|
| 5 |
+
π Live Demo β interactive classification (ML/LLM/Hybrid)
|
| 6 |
+
π Evaluation β pre-computed metrics and charts from Colab
|
| 7 |
+
ποΈ Architecture β pipeline diagram and design rationale
|
| 8 |
+
"""
|
| 9 |
+
|
| 10 |
+
import time
|
| 11 |
+
import gradio as gr
|
| 12 |
+
from config import (
|
| 13 |
+
CONFIDENCE_LOW,
|
| 14 |
+
CONFIDENCE_HIGH,
|
| 15 |
+
DECISION_BLOCK,
|
| 16 |
+
DECISION_ALLOW,
|
| 17 |
+
LLM_MODEL_NAME,
|
| 18 |
+
CLASSIFIER_MODEL_NAME,
|
| 19 |
+
)
|
| 20 |
+
from ml_classifier import MLClassifier
|
| 21 |
+
from llm_reviewer import gpu_classify
|
| 22 |
+
from precomputed import (
|
| 23 |
+
SYSTEM_CONFIG_MD,
|
| 24 |
+
RESULTS_TABLE_MD,
|
| 25 |
+
KEY_FINDINGS_MD,
|
| 26 |
+
)
|
| 27 |
+
|
| 28 |
+
# ββ Constants βββββββββββββββββββββββββββββββββββββββββββββββββ
|
| 29 |
+
_LLM_SHORT = LLM_MODEL_NAME.split("/")[-1]
|
| 30 |
+
|
| 31 |
+
# ββ Load ML classifier (CPU β instant, always available) ββββββ
|
| 32 |
+
ml = MLClassifier()
|
| 33 |
+
|
| 34 |
+
|
| 35 |
+
# ββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββ
|
| 36 |
+
# CLASSIFICATION LOGIC
|
| 37 |
+
# ββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββ
|
| 38 |
+
|
| 39 |
+
def classify_comment(comment: str, strategy: str):
|
| 40 |
+
"""Route a comment through the selected strategy."""
|
| 41 |
+
if not comment.strip():
|
| 42 |
+
return "β οΈ *Please enter a comment first.*", ""
|
| 43 |
+
|
| 44 |
+
try:
|
| 45 |
+
# ββ ML-only (CPU, no GPU needed) ββββββββββββββββββββββ
|
| 46 |
+
if strategy == "ML-only (CPU, no login needed)":
|
| 47 |
+
t0 = time.perf_counter()
|
| 48 |
+
decision, confidence, _ = ml.classify(comment)
|
| 49 |
+
latency = (time.perf_counter() - t0) * 1000
|
| 50 |
+
used_llm = False
|
| 51 |
+
stage = "ml_classifier"
|
| 52 |
+
reason = "ML-only baseline"
|
| 53 |
+
|
| 54 |
+
# ββ LLM-only (GPU via ZeroGPU) ββββββββββββββββββββββββ
|
| 55 |
+
elif strategy == "LLM-only (GPU required)":
|
| 56 |
+
t0 = time.perf_counter()
|
| 57 |
+
decision, confidence, reason = gpu_classify(comment)
|
| 58 |
+
latency = (time.perf_counter() - t0) * 1000
|
| 59 |
+
used_llm = True
|
| 60 |
+
stage = "llm"
|
| 61 |
+
|
| 62 |
+
# ββ Hybrid (ML first, LLM only if uncertain) βββββββββ
|
| 63 |
+
else:
|
| 64 |
+
t0 = time.perf_counter()
|
| 65 |
+
decision, confidence, is_uncertain = ml.classify(comment)
|
| 66 |
+
|
| 67 |
+
if not is_uncertain:
|
| 68 |
+
latency = (time.perf_counter() - t0) * 1000
|
| 69 |
+
used_llm = False
|
| 70 |
+
stage = "ml_classifier"
|
| 71 |
+
reason = "ML classifier is confident"
|
| 72 |
+
else:
|
| 73 |
+
decision, confidence, reason = gpu_classify(comment)
|
| 74 |
+
latency = (time.perf_counter() - t0) * 1000
|
| 75 |
+
used_llm = True
|
| 76 |
+
stage = "llm"
|
| 77 |
+
|
| 78 |
+
# ββ Format output βββββββββββββββββββββββββββββββββββββ
|
| 79 |
+
is_blocked = (decision == DECISION_BLOCK)
|
| 80 |
+
verdict = "## π΄ BLOCK" if is_blocked else "## π’ ALLOW"
|
| 81 |
+
|
| 82 |
+
details = (
|
| 83 |
+
"| Field | Value |\n"
|
| 84 |
+
"|:------|:------|\n"
|
| 85 |
+
f"| **Decision** | {decision} |\n"
|
| 86 |
+
f"| **Confidence** | {confidence:.2%} |\n"
|
| 87 |
+
f"| **Stage** | {stage} |\n"
|
| 88 |
+
f"| **LLM Used** | {'Yes β¨' if used_llm else 'No'} |\n"
|
| 89 |
+
f"| **Latency** | {latency:.0f} ms |\n"
|
| 90 |
+
f"| **Reason** | {reason} |\n"
|
| 91 |
+
)
|
| 92 |
+
|
| 93 |
+
return verdict, details
|
| 94 |
+
|
| 95 |
+
except Exception as e:
|
| 96 |
+
err = str(e).lower()
|
| 97 |
+
if any(k in err for k in ["gpu", "quota", "zero", "login", "sign"]):
|
| 98 |
+
return (
|
| 99 |
+
"## β οΈ GPU Unavailable",
|
| 100 |
+
"**Please [sign in to HuggingFace](https://huggingface.co/login)** "
|
| 101 |
+
"(free account) to use LLM features.\n\n"
|
| 102 |
+
"The **ML-only** strategy works without GPU β "
|
| 103 |
+
"select it above to try it without signing in."
|
| 104 |
+
)
|
| 105 |
+
return "## β Error", f"```\n{e}\n```"
|
| 106 |
+
|
| 107 |
+
|
| 108 |
+
# ββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββ
|
| 109 |
+
# BUILD GRADIO APP
|
| 110 |
+
# ββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββ
|
| 111 |
+
|
| 112 |
+
with gr.Blocks(
|
| 113 |
+
title="Hybrid Comment Moderation",
|
| 114 |
+
theme=gr.themes.Soft(),
|
| 115 |
+
) as demo:
|
| 116 |
+
|
| 117 |
+
gr.Markdown(
|
| 118 |
+
"# π¬ Hybrid Comment Moderation\n"
|
| 119 |
+
"**CS541 AI Final Project β Stevens Institute of Technology**\n\n"
|
| 120 |
+
f"DistilBERT (fast, cheap) β {_LLM_SHORT} (smart, expensive) β "
|
| 121 |
+
"only when needed."
|
| 122 |
+
)
|
| 123 |
+
|
| 124 |
+
with gr.Tabs():
|
| 125 |
+
# ββββββββββββββββββββββββββββββββββββββββββββββββββββββ
|
| 126 |
+
# TAB 1: LIVE DEMO
|
| 127 |
+
# ββββββββββββββββββββββββββββββββββββββββββββββββββββββ
|
| 128 |
+
with gr.Tab("π Live Demo"):
|
| 129 |
+
gr.Markdown(
|
| 130 |
+
"> π‘ **ML-only** works for everyone (CPU). \n"
|
| 131 |
+
"> **Hybrid** and **LLM-only** need a free HuggingFace "
|
| 132 |
+
"account for GPU access.\n"
|
| 133 |
+
)
|
| 134 |
+
|
| 135 |
+
with gr.Row():
|
| 136 |
+
# ββ Left: input βββββββββββββββββββββββββββββββ
|
| 137 |
+
with gr.Column(scale=3):
|
| 138 |
+
comment_box = gr.Textbox(
|
| 139 |
+
label="Comment",
|
| 140 |
+
placeholder=(
|
| 141 |
+
"Type or paste a comment to classify β¦\n"
|
| 142 |
+
"e.g. 'This article is a great read, "
|
| 143 |
+
"thanks for sharing!'"
|
| 144 |
+
),
|
| 145 |
+
lines=4,
|
| 146 |
+
)
|
| 147 |
+
strategy_radio = gr.Radio(
|
| 148 |
+
choices=[
|
| 149 |
+
"Hybrid (recommended)",
|
| 150 |
+
"ML-only (CPU, no login needed)",
|
| 151 |
+
"LLM-only (GPU required)",
|
| 152 |
+
],
|
| 153 |
+
value="Hybrid (recommended)",
|
| 154 |
+
label="Strategy",
|
| 155 |
+
info=(
|
| 156 |
+
"Hybrid: ML handles most, LLM reviews "
|
| 157 |
+
"uncertain. ML-only: DistilBERT on every "
|
| 158 |
+
"comment (CPU). LLM-only: "
|
| 159 |
+
f"{_LLM_SHORT} on every comment (GPU)."
|
| 160 |
+
),
|
| 161 |
+
)
|
| 162 |
+
classify_btn = gr.Button(
|
| 163 |
+
"π Classify",
|
| 164 |
+
variant="primary",
|
| 165 |
+
size="lg",
|
| 166 |
+
)
|
| 167 |
+
|
| 168 |
+
# ββ Right: output βββββββββββββββββββββββββββββ
|
| 169 |
+
with gr.Column(scale=2):
|
| 170 |
+
verdict_md = gr.Markdown(
|
| 171 |
+
value="*Verdict will appear here β¦*"
|
| 172 |
+
)
|
| 173 |
+
details_md = gr.Markdown(value="")
|
| 174 |
+
|
| 175 |
+
# ββ Examples ββββββββββββββββββββββββββββββββββββββ
|
| 176 |
+
gr.Examples(
|
| 177 |
+
examples=[
|
| 178 |
+
[
|
| 179 |
+
"Thank you for this insightful article!",
|
| 180 |
+
"Hybrid (recommended)",
|
| 181 |
+
],
|
| 182 |
+
[
|
| 183 |
+
"You are an absolute idiot and should die.",
|
| 184 |
+
"Hybrid (recommended)",
|
| 185 |
+
],
|
| 186 |
+
[
|
| 187 |
+
"I'm not sure I agree with the second point "
|
| 188 |
+
"about taxes.",
|
| 189 |
+
"Hybrid (recommended)",
|
| 190 |
+
],
|
| 191 |
+
[
|
| 192 |
+
"Kill yourself you worthless piece of garbage.",
|
| 193 |
+
"ML-only (CPU, no login needed)",
|
| 194 |
+
],
|
| 195 |
+
[
|
| 196 |
+
"The data seems to support a moderate position "
|
| 197 |
+
"on this issue.",
|
| 198 |
+
"Hybrid (recommended)",
|
| 199 |
+
],
|
| 200 |
+
[
|
| 201 |
+
"This is the dumbest thing I've ever read, "
|
| 202 |
+
"the author is clueless.",
|
| 203 |
+
"LLM-only (GPU required)",
|
| 204 |
+
],
|
| 205 |
+
[
|
| 206 |
+
"Great post!",
|
| 207 |
+
"ML-only (CPU, no login needed)",
|
| 208 |
+
],
|
| 209 |
+
],
|
| 210 |
+
inputs=[comment_box, strategy_radio],
|
| 211 |
+
)
|
| 212 |
+
|
| 213 |
+
# ββ Wire events βββββββββββββββββββββββββββββββββββ
|
| 214 |
+
classify_btn.click(
|
| 215 |
+
fn=classify_comment,
|
| 216 |
+
inputs=[comment_box, strategy_radio],
|
| 217 |
+
outputs=[verdict_md, details_md],
|
| 218 |
+
)
|
| 219 |
+
comment_box.submit(
|
| 220 |
+
fn=classify_comment,
|
| 221 |
+
inputs=[comment_box, strategy_radio],
|
| 222 |
+
outputs=[verdict_md, details_md],
|
| 223 |
+
)
|
| 224 |
+
|
| 225 |
+
# ββββββββββββββββββββββββββββββββββββββββββββββββββββββ
|
| 226 |
+
# TAB 2: EVALUATION RESULTS (pre-computed in Colab)
|
| 227 |
+
# ββββββββββββββββββββββββββββββββββββββββββββββββββββββ
|
| 228 |
+
with gr.Tab("π Evaluation Results"):
|
| 229 |
+
gr.Markdown(
|
| 230 |
+
"### Pre-computed on Google Colab (T4 GPU)\n"
|
| 231 |
+
"All three strategies evaluated on the **same** 100 "
|
| 232 |
+
"balanced samples from Civil Comments."
|
| 233 |
+
)
|
| 234 |
+
gr.Markdown(SYSTEM_CONFIG_MD)
|
| 235 |
+
|
| 236 |
+
gr.Markdown("---\n### Strategy Comparison")
|
| 237 |
+
gr.Markdown(RESULTS_TABLE_MD)
|
| 238 |
+
|
| 239 |
+
gr.Markdown("---\n### Visual Comparison")
|
| 240 |
+
gr.Image(
|
| 241 |
+
value="assets/strategy_comparison.png",
|
| 242 |
+
label="Strategy Comparison (6-panel bar chart)",
|
| 243 |
+
show_download_button=False,
|
| 244 |
+
)
|
| 245 |
+
|
| 246 |
+
gr.Markdown("---\n### Hybrid Routing Distribution")
|
| 247 |
+
gr.Image(
|
| 248 |
+
value="assets/stage_distribution.png",
|
| 249 |
+
label="Where decisions are made in the Hybrid pipeline",
|
| 250 |
+
show_download_button=False,
|
| 251 |
+
)
|
| 252 |
+
|
| 253 |
+
gr.Markdown("---\n### Key Findings")
|
| 254 |
+
gr.Markdown(KEY_FINDINGS_MD)
|
| 255 |
+
|
| 256 |
+
# ββββββββββββββββββββββββββββββββββββββββββββββββββββββ
|
| 257 |
+
# TAB 3: ARCHITECTURE
|
| 258 |
+
# ββββββββββββββββββββββββββββββββββββββββββββββββββββββ
|
| 259 |
+
with gr.Tab("ποΈ Architecture"):
|
| 260 |
+
gr.Markdown(
|
| 261 |
+
"### Two-Stage Pipeline\n"
|
| 262 |
+
"\n"
|
| 263 |
+
"```\n"
|
| 264 |
+
"User Comment\n"
|
| 265 |
+
" β\n"
|
| 266 |
+
" βΌ\n"
|
| 267 |
+
"ββββββββββββββββββββββββββββββββββββββββββββ\n"
|
| 268 |
+
"β Stage 1: ML Classifier β\n"
|
| 269 |
+
"β DistilBERT (CPU, ~7 ms per comment) β\n"
|
| 270 |
+
"β Fine-tuned on Jigsaw toxic comments β\n"
|
| 271 |
+
"βββββββββββββββββββ¬βββββββββββββββββββββββββ\n"
|
| 272 |
+
" β\n"
|
| 273 |
+
" βββββββββΌββββββββ\n"
|
| 274 |
+
" β Confident? β\n"
|
| 275 |
+
" βββββ¬ββββββββ¬ββββ\n"
|
| 276 |
+
" Yes β β No (grey zone)\n"
|
| 277 |
+
" β β\n"
|
| 278 |
+
" βΌ βΌ\n"
|
| 279 |
+
" DONE ββββββββββββββββββββββββββββββββββββ\n"
|
| 280 |
+
f" β Stage 2: LLM Reviewer β\n"
|
| 281 |
+
f" β {_LLM_SHORT} (GPU, ~1-2 s) β\n"
|
| 282 |
+
" β Instruction-tuned, world knowledgeβ\n"
|
| 283 |
+
" βββββββββββββββββββ¬βββββββββββββββββ\n"
|
| 284 |
+
" β\n"
|
| 285 |
+
" βΌ\n"
|
| 286 |
+
" DONE\n"
|
| 287 |
+
"```\n"
|
| 288 |
+
)
|
| 289 |
+
|
| 290 |
+
gr.Markdown(
|
| 291 |
+
"---\n"
|
| 292 |
+
"### Confidence Routing Logic\n"
|
| 293 |
+
"\n"
|
| 294 |
+
"The ML classifier outputs a toxic probability in "
|
| 295 |
+
"[0, 1]. Two thresholds define three zones:\n"
|
| 296 |
+
"\n"
|
| 297 |
+
"| Toxic Probability | Zone | Action |\n"
|
| 298 |
+
"|:------------------|:-----|:-------|\n"
|
| 299 |
+
f"| **β₯ {CONFIDENCE_HIGH}** | High confidence toxic "
|
| 300 |
+
"| β **BLOCK** (ML decides) |\n"
|
| 301 |
+
f"| **β€ {CONFIDENCE_LOW}** | High confidence safe "
|
| 302 |
+
"| β **ALLOW** (ML decides) |\n"
|
| 303 |
+
f"| **{CONFIDENCE_LOW} β {CONFIDENCE_HIGH}** | "
|
| 304 |
+
"Grey zone (uncertain) | β **Escalate to LLM** |\n"
|
| 305 |
+
"\n"
|
| 306 |
+
"Only grey-zone comments cost GPU time. On the "
|
| 307 |
+
"evaluation set, typically **75β85%** of comments "
|
| 308 |
+
"are handled by the ML classifier alone.\n"
|
| 309 |
+
)
|
| 310 |
+
|
| 311 |
+
gr.Markdown(
|
| 312 |
+
"---\n"
|
| 313 |
+
"### Why Hybrid?\n"
|
| 314 |
+
"\n"
|
| 315 |
+
"| Property | ML-Only | LLM-Only | Hybrid |\n"
|
| 316 |
+
"|:---------|:--------|:---------|:-------|\n"
|
| 317 |
+
"| **Speed** | ~7 ms | ~1β3 s | ~7 ms (most) |\n"
|
| 318 |
+
"| **Cost** | $0 (CPU) | High (every comment) "
|
| 319 |
+
"| Low (~15β25% reach LLM) |\n"
|
| 320 |
+
"| **Nuance** | Limited to training dist. "
|
| 321 |
+
"| Broad world knowledge | Best of both |\n"
|
| 322 |
+
"| **Scalability** | Excellent | Poor | Good |\n"
|
| 323 |
+
"\n"
|
| 324 |
+
"> The hybrid gives **LLM-quality decisions where "
|
| 325 |
+
"they matter** at **ML-classifier cost for the "
|
| 326 |
+
"easy cases**.\n"
|
| 327 |
+
)
|
| 328 |
+
|
| 329 |
+
gr.Markdown(
|
| 330 |
+
"---\n"
|
| 331 |
+
"### Models\n"
|
| 332 |
+
"\n"
|
| 333 |
+
"| Component | Model | Parameters | Serving |\n"
|
| 334 |
+
"|:----------|:------|:-----------|:--------|\n"
|
| 335 |
+
f"| ML Classifier | `{CLASSIFIER_MODEL_NAME}` "
|
| 336 |
+
"| ~67 M (DistilBERT) | CPU |\n"
|
| 337 |
+
f"| LLM Reviewer | `{LLM_MODEL_NAME}` "
|
| 338 |
+
"| ~3 B (float16) | ZeroGPU (A100) |\n"
|
| 339 |
+
)
|
| 340 |
+
|
| 341 |
+
gr.Markdown(
|
| 342 |
+
"---\n"
|
| 343 |
+
"### Reference\n"
|
| 344 |
+
"\n"
|
| 345 |
+
"- **Course:** CS541 Artificial Intelligence, "
|
| 346 |
+
"Stevens Institute of Technology\n"
|
| 347 |
+
"- **Textbook:** *Understanding Deep Learning* β "
|
| 348 |
+
"Simon J.D. Prince\n"
|
| 349 |
+
"- **Dataset:** "
|
| 350 |
+
"[google/civil_comments]"
|
| 351 |
+
"(https://huggingface.co/datasets/google/"
|
| 352 |
+
"civil_comments)\n"
|
| 353 |
+
)
|
| 354 |
+
|
| 355 |
+
# ββ Footer ββββββββββββββββββββββββββββββββββββββββββββββββ
|
| 356 |
+
gr.Markdown(
|
| 357 |
+
"---\n"
|
| 358 |
+
"*CS541 AI Final Project Β· Stevens Institute of Technology Β· "
|
| 359 |
+
f"DistilBERT + {_LLM_SHORT} Β· ZeroGPU*"
|
| 360 |
+
)
|
| 361 |
+
|
| 362 |
+
# ββ Launch ββββββββββββββββββββββββββββββββββββββββββββββββββββ
|
| 363 |
+
demo.launch()
|
config.py
ADDED
|
@@ -0,0 +1,20 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
"""
|
| 2 |
+
config.py β Single source of truth for the Spaces deployment.
|
| 3 |
+
"""
|
| 4 |
+
|
| 5 |
+
# ββ Decision labels βββββββββββββββββββββββββββββββββββββββββββ
|
| 6 |
+
DECISION_BLOCK = "BLOCK"
|
| 7 |
+
DECISION_ALLOW = "ALLOW"
|
| 8 |
+
|
| 9 |
+
# ββ Model identifiers ββββββββββββββββββββββββββββββββββββββββ
|
| 10 |
+
CLASSIFIER_MODEL_NAME = "martin-ha/toxic-comment-model" # DistilBERT, ~270 MB
|
| 11 |
+
LLM_MODEL_NAME = "Qwen/Qwen2.5-3B-Instruct" # fp16, ~6 GB
|
| 12 |
+
|
| 13 |
+
# ββ Generation parameters βββββββββββββββββββββββββββββββββββββ
|
| 14 |
+
LLM_MAX_NEW_TOKENS = 5
|
| 15 |
+
LLM_TEMPERATURE = 0.0
|
| 16 |
+
|
| 17 |
+
# ββ Confidence thresholds (ML β LLM escalation) ββββββββββββββ
|
| 18 |
+
CONFIDENCE_HIGH = 0.85 # above β trust the ML classifier
|
| 19 |
+
CONFIDENCE_LOW = 0.15 # below β trust the ML classifier (safe)
|
| 20 |
+
# Between LOW and HIGH β grey zone β escalate to LLM
|
llm_reviewer.py
ADDED
|
@@ -0,0 +1,111 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
"""
|
| 2 |
+
llm_reviewer.py β LLM reviewer for ambiguous comments (Stage 2).
|
| 3 |
+
|
| 4 |
+
Qwen2.5-3B-Instruct is loaded in float16 (~6 GB) at module level.
|
| 5 |
+
ZeroGPU allocates an A100 slice only when @spaces.GPU functions run.
|
| 6 |
+
|
| 7 |
+
If the `spaces` package is unavailable (local testing), the GPU
|
| 8 |
+
decorator becomes a no-op so the code still works on any machine.
|
| 9 |
+
"""
|
| 10 |
+
|
| 11 |
+
import torch
|
| 12 |
+
from typing import Tuple
|
| 13 |
+
from transformers import AutoModelForCausalLM, AutoTokenizer
|
| 14 |
+
from config import (
|
| 15 |
+
LLM_MODEL_NAME,
|
| 16 |
+
LLM_MAX_NEW_TOKENS,
|
| 17 |
+
DECISION_BLOCK,
|
| 18 |
+
DECISION_ALLOW,
|
| 19 |
+
)
|
| 20 |
+
|
| 21 |
+
# ββ ZeroGPU decorator (graceful fallback for local runs) ββββββ
|
| 22 |
+
try:
|
| 23 |
+
import spaces
|
| 24 |
+
ZERO_GPU = True
|
| 25 |
+
except ImportError:
|
| 26 |
+
ZERO_GPU = False
|
| 27 |
+
|
| 28 |
+
class _SpacesFallback:
|
| 29 |
+
"""No-op decorator when `spaces` is not installed."""
|
| 30 |
+
@staticmethod
|
| 31 |
+
def GPU(duration=30):
|
| 32 |
+
def decorator(fn):
|
| 33 |
+
return fn
|
| 34 |
+
return decorator
|
| 35 |
+
|
| 36 |
+
spaces = _SpacesFallback()
|
| 37 |
+
|
| 38 |
+
|
| 39 |
+
# ββ Prompt ββββββββββββββββββββββββββββββββββββββββββββββββββββ
|
| 40 |
+
_SYSTEM_PROMPT = (
|
| 41 |
+
"You are a strict content moderator. Classify the user comment "
|
| 42 |
+
"as exactly one of: toxic or non-toxic.\n"
|
| 43 |
+
"A comment is toxic if it is rude, threatening, hateful, obscene, "
|
| 44 |
+
"or would make someone leave a discussion.\n"
|
| 45 |
+
"Reply with ONLY one word: toxic or non-toxic. "
|
| 46 |
+
"Do not explain."
|
| 47 |
+
)
|
| 48 |
+
|
| 49 |
+
# ββ Load model at module level ββββββββββββββββββββββββββββββββ
|
| 50 |
+
# ZeroGPU patches torch so that device_map="auto" works even
|
| 51 |
+
# before GPU is allocated. The actual CUDA tensors are created
|
| 52 |
+
# when the @spaces.GPU-decorated function is first called.
|
| 53 |
+
print(f"β³ Loading {LLM_MODEL_NAME} β¦")
|
| 54 |
+
|
| 55 |
+
_tokenizer = AutoTokenizer.from_pretrained(
|
| 56 |
+
LLM_MODEL_NAME, trust_remote_code=True
|
| 57 |
+
)
|
| 58 |
+
if _tokenizer.pad_token is None:
|
| 59 |
+
_tokenizer.pad_token = _tokenizer.eos_token
|
| 60 |
+
|
| 61 |
+
_model = AutoModelForCausalLM.from_pretrained(
|
| 62 |
+
LLM_MODEL_NAME,
|
| 63 |
+
torch_dtype=torch.float16,
|
| 64 |
+
device_map="auto",
|
| 65 |
+
trust_remote_code=True,
|
| 66 |
+
)
|
| 67 |
+
print(f"β
{LLM_MODEL_NAME} loaded")
|
| 68 |
+
|
| 69 |
+
|
| 70 |
+
# ββ Answer parser βββββββββββββββββββββββββββββββββββββββββββββ
|
| 71 |
+
def _parse_answer(answer: str) -> Tuple[str, float]:
|
| 72 |
+
a = answer.lower().strip().rstrip(".")
|
| 73 |
+
if "non-toxic" in a or "non toxic" in a or "not toxic" in a:
|
| 74 |
+
return (DECISION_ALLOW, 0.85)
|
| 75 |
+
elif "toxic" in a:
|
| 76 |
+
return (DECISION_BLOCK, 0.85)
|
| 77 |
+
else:
|
| 78 |
+
return (DECISION_BLOCK, 0.50)
|
| 79 |
+
|
| 80 |
+
|
| 81 |
+
# ββ GPU-decorated classification function βββββββββββββββββββββ
|
| 82 |
+
@spaces.GPU(duration=30)
|
| 83 |
+
def gpu_classify(text: str) -> Tuple[str, float, str]:
|
| 84 |
+
"""
|
| 85 |
+
Classify one comment with the LLM.
|
| 86 |
+
|
| 87 |
+
On HuggingFace Spaces this runs on a ZeroGPU A100 slice.
|
| 88 |
+
The caller's free-tier quota is consumed (~1β3 GPU-seconds).
|
| 89 |
+
"""
|
| 90 |
+
messages = [
|
| 91 |
+
{"role": "system", "content": _SYSTEM_PROMPT},
|
| 92 |
+
{"role": "user", "content": f'Classify this comment: "{text[:1024]}"'},
|
| 93 |
+
]
|
| 94 |
+
|
| 95 |
+
input_ids = _tokenizer.apply_chat_template(
|
| 96 |
+
messages, return_tensors="pt", add_generation_prompt=True
|
| 97 |
+
).to(_model.device)
|
| 98 |
+
|
| 99 |
+
with torch.no_grad():
|
| 100 |
+
output_ids = _model.generate(
|
| 101 |
+
input_ids,
|
| 102 |
+
max_new_tokens=LLM_MAX_NEW_TOKENS,
|
| 103 |
+
do_sample=False,
|
| 104 |
+
)
|
| 105 |
+
|
| 106 |
+
new_tokens = output_ids[0][input_ids.shape[-1]:]
|
| 107 |
+
answer = _tokenizer.decode(new_tokens, skip_special_tokens=True)
|
| 108 |
+
answer = answer.strip().lower()
|
| 109 |
+
|
| 110 |
+
decision, confidence = _parse_answer(answer)
|
| 111 |
+
return decision, confidence, f"LLM said: '{answer}'"
|
ml_classifier.py
ADDED
|
@@ -0,0 +1,57 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
"""
|
| 2 |
+
ml_classifier.py β DistilBERT toxic-comment classifier (Stage 1).
|
| 3 |
+
|
| 4 |
+
Runs on CPU only β no GPU quota consumed. Inference takes ~7 ms
|
| 5 |
+
per comment, so it is available to every visitor (including guests).
|
| 6 |
+
"""
|
| 7 |
+
|
| 8 |
+
from typing import Tuple
|
| 9 |
+
from transformers import pipeline as hf_pipeline
|
| 10 |
+
from config import (
|
| 11 |
+
CLASSIFIER_MODEL_NAME,
|
| 12 |
+
CONFIDENCE_HIGH,
|
| 13 |
+
CONFIDENCE_LOW,
|
| 14 |
+
DECISION_BLOCK,
|
| 15 |
+
DECISION_ALLOW,
|
| 16 |
+
)
|
| 17 |
+
|
| 18 |
+
|
| 19 |
+
class MLClassifier:
|
| 20 |
+
"""Wrapper around a HuggingFace text-classification pipeline."""
|
| 21 |
+
|
| 22 |
+
def __init__(self, model_name: str = CLASSIFIER_MODEL_NAME):
|
| 23 |
+
self._pipe = hf_pipeline(
|
| 24 |
+
task="text-classification",
|
| 25 |
+
model=model_name,
|
| 26 |
+
tokenizer=model_name,
|
| 27 |
+
framework="pt",
|
| 28 |
+
device=-1, # β force CPU (no GPU quota)
|
| 29 |
+
truncation=True,
|
| 30 |
+
max_length=512,
|
| 31 |
+
)
|
| 32 |
+
self._toxic_labels = {"toxic"}
|
| 33 |
+
print(f"β
ML Classifier loaded on CPU: {model_name}")
|
| 34 |
+
|
| 35 |
+
def classify(self, text: str) -> Tuple[str, float, bool]:
|
| 36 |
+
"""
|
| 37 |
+
Returns (decision, confidence, is_uncertain).
|
| 38 |
+
|
| 39 |
+
decision : DECISION_BLOCK or DECISION_ALLOW
|
| 40 |
+
confidence : float in [0, 1]
|
| 41 |
+
is_uncertain : True when confidence is in the grey zone
|
| 42 |
+
"""
|
| 43 |
+
result = self._pipe(text)[0]
|
| 44 |
+
return self._interpret(result)
|
| 45 |
+
|
| 46 |
+
def _interpret(self, result: dict) -> Tuple[str, float, bool]:
|
| 47 |
+
label = result["label"].lower()
|
| 48 |
+
score = result["score"]
|
| 49 |
+
toxic_prob = score if label in self._toxic_labels else (1.0 - score)
|
| 50 |
+
|
| 51 |
+
if toxic_prob >= CONFIDENCE_HIGH:
|
| 52 |
+
return (DECISION_BLOCK, toxic_prob, False)
|
| 53 |
+
elif toxic_prob <= CONFIDENCE_LOW:
|
| 54 |
+
return (DECISION_ALLOW, 1.0 - toxic_prob, False)
|
| 55 |
+
else:
|
| 56 |
+
tentative = DECISION_BLOCK if toxic_prob >= 0.5 else DECISION_ALLOW
|
| 57 |
+
return (tentative, max(toxic_prob, 1.0 - toxic_prob), True)
|
precomputed.py
ADDED
|
@@ -0,0 +1,93 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
"""
|
| 2 |
+
precomputed.py β Pre-computed evaluation results from Colab.
|
| 3 |
+
|
| 4 |
+
ββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββ
|
| 5 |
+
β INSTRUCTIONS β
|
| 6 |
+
β β
|
| 7 |
+
β 1. Run the Colab notebook end-to-end with β
|
| 8 |
+
β LLM_MODEL_NAME = "Qwen/Qwen2.5-3B-Instruct" β
|
| 9 |
+
β β
|
| 10 |
+
β 2. Replace every _TBD_ below with the actual numbers β
|
| 11 |
+
β from your df_results / Cell 15 output. β
|
| 12 |
+
β β
|
| 13 |
+
β 3. Place the two PNG files in assets/ β
|
| 14 |
+
ββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββ
|
| 15 |
+
"""
|
| 16 |
+
|
| 17 |
+
# ββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββ
|
| 18 |
+
# System configuration (shown at top of Evaluation tab)
|
| 19 |
+
# ββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββ
|
| 20 |
+
SYSTEM_CONFIG_MD = """\
|
| 21 |
+
π¦ **Evaluation Environment**
|
| 22 |
+
|
| 23 |
+
| Setting | Value |
|
| 24 |
+
|:--------|:------|
|
| 25 |
+
| **Dataset** | google/civil_comments (test split) |
|
| 26 |
+
| **Eval Samples** | 100 (50 toxic + 50 non-toxic) |
|
| 27 |
+
| **ML Classifier** | martin-ha/toxic-comment-model (DistilBERT) |
|
| 28 |
+
| **LLM** | Qwen/Qwen2.5-3B-Instruct (NF4, ~2 GB VRAM) |
|
| 29 |
+
| **Grey Zone** | [0.15, 0.85] β ML uncertain β escalate to LLM |
|
| 30 |
+
| **Runtime** | Google Colab, NVIDIA T4 (15 GB VRAM) |
|
| 31 |
+
"""
|
| 32 |
+
|
| 33 |
+
# ββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββ
|
| 34 |
+
# Results table β replace _TBD_ with actual values
|
| 35 |
+
# ββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββ
|
| 36 |
+
RESULTS_TABLE_MD = """\
|
| 37 |
+
| Metric | ML-Only (DistilBERT) | LLM-Only (Qwen2.5-3B) | Hybrid (MLβQwen2.5-3B) |
|
| 38 |
+
|:-------|---------------------:|-----------------------:|------------------------:|
|
| 39 |
+
| **F1 (macro)** | _TBD_ | _TBD_ | _TBD_ |
|
| 40 |
+
| **F1 (toxic)** | _TBD_ | _TBD_ | _TBD_ |
|
| 41 |
+
| **Precision** | _TBD_ | _TBD_ | _TBD_ |
|
| 42 |
+
| **Recall** | _TBD_ | _TBD_ | _TBD_ |
|
| 43 |
+
| **True Positives** | _TBD_ | _TBD_ | _TBD_ |
|
| 44 |
+
| **True Negatives** | _TBD_ | _TBD_ | _TBD_ |
|
| 45 |
+
| **False Positives** | _TBD_ | _TBD_ | _TBD_ |
|
| 46 |
+
| **False Negatives** | _TBD_ | _TBD_ | _TBD_ |
|
| 47 |
+
| **LLM Calls** | 0 | 100 | _TBD_ |
|
| 48 |
+
| **LLM Call %** | 0% | 100% | _TBD_% |
|
| 49 |
+
| **Est. Cost (USD)** | $0.0000 | $_TBD_ | $_TBD_ |
|
| 50 |
+
"""
|
| 51 |
+
|
| 52 |
+
# ββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββ
|
| 53 |
+
# Key findings β replace with Cell 15 output
|
| 54 |
+
# ββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββ
|
| 55 |
+
KEY_FINDINGS_MD = """\
|
| 56 |
+
#### π LLM Call Reduction
|
| 57 |
+
> Hybrid used **_TBD_** LLM calls (_TBD_%) vs LLM-Only's 100 calls (100%).
|
| 58 |
+
|
| 59 |
+
#### π° Cost Savings
|
| 60 |
+
> Hybrid: **$_TBD_** vs LLM-Only: **$_TBD_** β **_TBD_Γ cheaper**
|
| 61 |
+
|
| 62 |
+
#### π― Best F1 (macro)
|
| 63 |
+
> **_TBD_** strategy achieved the highest F1 of **_TBD_**
|
| 64 |
+
|
| 65 |
+
---
|
| 66 |
+
|
| 67 |
+
#### Per-Strategy Analysis
|
| 68 |
+
|
| 69 |
+
**1. ML-Only (DistilBERT)**
|
| 70 |
+
> F1 = _TBD_ Β· Precision = _TBD_ Β· Recall = _TBD_
|
| 71 |
+
>
|
| 72 |
+
> _Paste your Cell 15 ML-Only interpretation paragraph here._
|
| 73 |
+
|
| 74 |
+
**2. LLM-Only (Qwen2.5-3B-Instruct)**
|
| 75 |
+
> F1 = _TBD_ Β· Precision = _TBD_ Β· Recall = _TBD_
|
| 76 |
+
>
|
| 77 |
+
> _Paste your Cell 15 LLM-Only interpretation paragraph here._
|
| 78 |
+
|
| 79 |
+
**3. Hybrid (ML β Qwen2.5-3B-Instruct)**
|
| 80 |
+
> F1 = _TBD_ Β· Precision = _TBD_ Β· Recall = _TBD_
|
| 81 |
+
>
|
| 82 |
+
> _Paste your Cell 15 Hybrid interpretation paragraph here._
|
| 83 |
+
|
| 84 |
+
---
|
| 85 |
+
|
| 86 |
+
#### Conclusion
|
| 87 |
+
|
| 88 |
+
The hybrid architecture validates the core thesis: intelligent routing
|
| 89 |
+
dramatically reduces LLM calls and cost while maintaining competitive
|
| 90 |
+
classification quality. The ML classifier handles confident predictions
|
| 91 |
+
efficiently, and the LLM reviews only the ambiguous ones β combining
|
| 92 |
+
both strengths at a fraction of the LLM-Only cost.
|
| 93 |
+
"""
|
requirements.txt
ADDED
|
@@ -0,0 +1,6 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
torch
|
| 2 |
+
transformers>=4.52
|
| 3 |
+
accelerate
|
| 4 |
+
gradio>=5.0
|
| 5 |
+
spaces
|
| 6 |
+
numpy
|