Instructions to use Shell2334/info642-travel-classifier-lora with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- PEFT
How to use Shell2334/info642-travel-classifier-lora with PEFT:
from peft import PeftModel from transformers import AutoModelForSequenceClassification base_model = AutoModelForSequenceClassification.from_pretrained("TinyLlama/TinyLlama-1.1B-Chat-v1.0") model = PeftModel.from_pretrained(base_model, "Shell2334/info642-travel-classifier-lora") - Notebooks
- Google Colab
- Kaggle
Update README.md
Browse files
README.md
CHANGED
|
@@ -1,206 +1,187 @@
|
|
|
|
|
| 1 |
---
|
|
|
|
| 2 |
base_model: TinyLlama/TinyLlama-1.1B-Chat-v1.0
|
| 3 |
library_name: peft
|
|
|
|
|
|
|
|
|
|
| 4 |
tags:
|
| 5 |
-
-
|
| 6 |
-
- lora
|
| 7 |
-
-
|
|
|
|
| 8 |
---
|
| 9 |
|
| 10 |
-
#
|
| 11 |
-
|
| 12 |
-
<!-- Provide a quick summary of what the model is/does. -->
|
| 13 |
-
|
| 14 |
-
|
| 15 |
-
|
| 16 |
-
## Model Details
|
| 17 |
-
|
| 18 |
-
### Model Description
|
| 19 |
-
|
| 20 |
-
<!-- Provide a longer summary of what this model is. -->
|
| 21 |
-
|
| 22 |
-
|
| 23 |
-
|
| 24 |
-
- **Developed by:** [More Information Needed]
|
| 25 |
-
- **Funded by [optional]:** [More Information Needed]
|
| 26 |
-
- **Shared by [optional]:** [More Information Needed]
|
| 27 |
-
- **Model type:** [More Information Needed]
|
| 28 |
-
- **Language(s) (NLP):** [More Information Needed]
|
| 29 |
-
- **License:** [More Information Needed]
|
| 30 |
-
- **Finetuned from model [optional]:** [More Information Needed]
|
| 31 |
-
|
| 32 |
-
### Model Sources [optional]
|
| 33 |
-
|
| 34 |
-
<!-- Provide the basic links for the model. -->
|
| 35 |
-
|
| 36 |
-
- **Repository:** [More Information Needed]
|
| 37 |
-
- **Paper [optional]:** [More Information Needed]
|
| 38 |
-
- **Demo [optional]:** [More Information Needed]
|
| 39 |
-
|
| 40 |
-
## Uses
|
| 41 |
-
|
| 42 |
-
<!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
|
| 43 |
-
|
| 44 |
-
### Direct Use
|
| 45 |
-
|
| 46 |
-
<!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->
|
| 47 |
-
|
| 48 |
-
[More Information Needed]
|
| 49 |
-
|
| 50 |
-
### Downstream Use [optional]
|
| 51 |
-
|
| 52 |
-
<!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app -->
|
| 53 |
-
|
| 54 |
-
[More Information Needed]
|
| 55 |
-
|
| 56 |
-
### Out-of-Scope Use
|
| 57 |
-
|
| 58 |
-
<!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->
|
| 59 |
-
|
| 60 |
-
[More Information Needed]
|
| 61 |
-
|
| 62 |
-
## Bias, Risks, and Limitations
|
| 63 |
-
|
| 64 |
-
<!-- This section is meant to convey both technical and sociotechnical limitations. -->
|
| 65 |
-
|
| 66 |
-
[More Information Needed]
|
| 67 |
|
| 68 |
-
##
|
| 69 |
|
| 70 |
-
|
| 71 |
|
| 72 |
-
|
| 73 |
|
| 74 |
-
|
| 75 |
|
| 76 |
-
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 77 |
|
| 78 |
-
|
| 79 |
|
| 80 |
-
|
| 81 |
|
| 82 |
-
##
|
| 83 |
|
| 84 |
-
|
|
|
|
|
|
|
|
|
|
| 85 |
|
| 86 |
-
|
| 87 |
|
| 88 |
-
|
| 89 |
|
| 90 |
-
|
| 91 |
|
| 92 |
-
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 93 |
|
| 94 |
-
|
| 95 |
|
|
|
|
| 96 |
|
| 97 |
-
|
| 98 |
|
| 99 |
-
|
| 100 |
|
| 101 |
-
|
| 102 |
|
| 103 |
-
|
|
|
|
|
|
|
|
|
|
|
|
|
| 104 |
|
| 105 |
-
|
| 106 |
|
| 107 |
-
|
| 108 |
|
| 109 |
-
|
| 110 |
|
| 111 |
-
|
| 112 |
|
| 113 |
-
|
| 114 |
|
| 115 |
-
|
| 116 |
|
| 117 |
-
|
| 118 |
|
| 119 |
-
###
|
| 120 |
|
| 121 |
-
|
| 122 |
|
| 123 |
-
|
| 124 |
|
| 125 |
-
|
|
|
|
|
|
|
|
|
|
|
|
|
| 126 |
|
| 127 |
-
|
| 128 |
|
| 129 |
-
|
| 130 |
|
| 131 |
-
|
|
|
|
|
|
|
|
|
|
|
|
|
| 132 |
|
| 133 |
-
|
| 134 |
|
| 135 |
-
###
|
| 136 |
|
|
|
|
| 137 |
|
|
|
|
| 138 |
|
| 139 |
-
|
| 140 |
|
| 141 |
-
|
| 142 |
|
| 143 |
-
|
|
|
|
|
|
|
|
|
|
| 144 |
|
| 145 |
-
|
| 146 |
|
| 147 |
-
|
| 148 |
|
| 149 |
-
|
| 150 |
|
| 151 |
-
|
| 152 |
-
- **Hours used:** [More Information Needed]
|
| 153 |
-
- **Cloud Provider:** [More Information Needed]
|
| 154 |
-
- **Compute Region:** [More Information Needed]
|
| 155 |
-
- **Carbon Emitted:** [More Information Needed]
|
| 156 |
|
| 157 |
-
|
| 158 |
|
| 159 |
-
|
| 160 |
|
| 161 |
-
|
| 162 |
|
| 163 |
-
|
| 164 |
|
| 165 |
-
|
| 166 |
|
| 167 |
-
|
| 168 |
|
| 169 |
-
|
| 170 |
|
| 171 |
-
##
|
| 172 |
|
| 173 |
-
|
| 174 |
|
| 175 |
-
|
| 176 |
|
| 177 |
-
|
| 178 |
|
| 179 |
-
|
| 180 |
|
| 181 |
-
|
| 182 |
|
| 183 |
-
|
| 184 |
|
| 185 |
-
|
| 186 |
|
| 187 |
-
|
| 188 |
|
| 189 |
-
|
| 190 |
|
| 191 |
-
|
| 192 |
|
| 193 |
-
##
|
| 194 |
|
| 195 |
-
[
|
| 196 |
|
| 197 |
-
##
|
| 198 |
|
| 199 |
-
|
| 200 |
|
| 201 |
-
|
| 202 |
|
| 203 |
-
|
| 204 |
-
### Framework versions
|
| 205 |
|
| 206 |
-
|
|
|
|
| 1 |
+
|
| 2 |
---
|
| 3 |
+
license: apache-2.0
|
| 4 |
base_model: TinyLlama/TinyLlama-1.1B-Chat-v1.0
|
| 5 |
library_name: peft
|
| 6 |
+
pipeline_tag: text-classification
|
| 7 |
+
language:
|
| 8 |
+
- en
|
| 9 |
tags:
|
| 10 |
+
- peft
|
| 11 |
+
- lora
|
| 12 |
+
- text-classification
|
| 13 |
+
- travel
|
| 14 |
---
|
| 15 |
|
| 16 |
+
# INFO 642 - Travel Request Classifier (TinyLlama + LoRA)
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 17 |
|
| 18 |
+
## What the Model Does
|
| 19 |
|
| 20 |
+
This model is a seven-category text classifier developed for our INFO 642 Modular AI Travel Planner project.
|
| 21 |
|
| 22 |
+
The model identifies the user's travel request and helps the n8n workflow select the appropriate module.
|
| 23 |
|
| 24 |
+
It predicts one of seven labels:
|
| 25 |
|
| 26 |
+
1. NEW_TRIP - Create a new travel itinerary.
|
| 27 |
+
2. CHANGE_FLIGHT - Modify an existing flight.
|
| 28 |
+
3. CHANGE_HOTEL - Modify an existing hotel.
|
| 29 |
+
4. CHANGE_ATTRACTION - Modify an attraction or activity.
|
| 30 |
+
5. CHANGE_RESTAURANT - Modify a restaurant or meal.
|
| 31 |
+
6. MULTI_CHANGE - Modify multiple itinerary components.
|
| 32 |
+
7. OTHER_OR_UNCLEAR - Handle unclear, general, or unsupported requests.
|
| 33 |
|
| 34 |
+
In our workflow, this model is intended to replace the original Groq-based placeholder classifier. The other modules handle itinerary generation, data lookup, budget calculations, and itinerary modifications.
|
| 35 |
|
| 36 |
+
The classifier does not make reservations or payments.
|
| 37 |
|
| 38 |
+
## Base Model
|
| 39 |
|
| 40 |
+
- Base model: TinyLlama/TinyLlama-1.1B-Chat-v1.0
|
| 41 |
+
- Model type: Seven-class text classification
|
| 42 |
+
- Fine-tuning method: Low-Rank Adaptation (LoRA)
|
| 43 |
+
- Framework: Hugging Face Transformers and PEFT
|
| 44 |
|
| 45 |
+
We followed the Lesson 16 TinyLlama training approach and added a new seven-class classification head.
|
| 46 |
|
| 47 |
+
LoRA allows us to train a small number of parameters instead of updating the entire base model.
|
| 48 |
|
| 49 |
+
Training configuration:
|
| 50 |
|
| 51 |
+
| Parameter | Value |
|
| 52 |
+
|---|---|
|
| 53 |
+
| LoRA rank | 8 |
|
| 54 |
+
| LoRA alpha | 16 |
|
| 55 |
+
| LoRA dropout | 0.05 |
|
| 56 |
+
| Target modules | q_proj, k_proj, v_proj, o_proj |
|
| 57 |
+
| Epochs | 3 |
|
| 58 |
+
| Batch size | 8 |
|
| 59 |
+
| Learning rate | 0.0002 |
|
| 60 |
+
| Trainable parameters | 2,267,136 |
|
| 61 |
|
| 62 |
+
Only approximately 0.22% of the model's parameters were trainable.
|
| 63 |
|
| 64 |
+
## Training Data
|
| 65 |
|
| 66 |
+
We created a synthetic English dataset of 280 travel-related user requests for this course project.
|
| 67 |
|
| 68 |
+
The dataset includes seven balanced categories, with 40 examples per category.
|
| 69 |
|
| 70 |
+
Data split:
|
| 71 |
|
| 72 |
+
| Dataset | Samples |
|
| 73 |
+
|---|---:|
|
| 74 |
+
| Training set | 224 |
|
| 75 |
+
| Held-out test set | 56 |
|
| 76 |
+
| Total | 280 |
|
| 77 |
|
| 78 |
+
Each category contains 32 training examples and 8 held-out test examples.
|
| 79 |
|
| 80 |
+
The training data covers requests such as creating trips, changing flights, finding cheaper hotels, replacing attractions, modifying restaurants, and changing multiple itinerary components.
|
| 81 |
|
| 82 |
+
Some examples also include unclear requests and unsupported booking or payment requests.
|
| 83 |
|
| 84 |
+
The test data was not used for model training.
|
| 85 |
|
| 86 |
+
All examples are synthetic and do not represent real customer conversations.
|
| 87 |
|
| 88 |
+
## Results
|
| 89 |
|
| 90 |
+
We evaluated the fine-tuned model using 56 held-out test requests.
|
| 91 |
|
| 92 |
+
### Overall Accuracy
|
| 93 |
|
| 94 |
+
**Held-out test accuracy: 98.2% (55/56 correct)**
|
| 95 |
|
| 96 |
+
Additional model comparisons:
|
| 97 |
|
| 98 |
+
| Model | Accuracy |
|
| 99 |
+
|---|---:|
|
| 100 |
+
| BART Zero-shot | 46.4% |
|
| 101 |
+
| TinyLlama with untrained classification head | 14.3% |
|
| 102 |
+
| TinyLlama + LoRA | 98.2% |
|
| 103 |
|
| 104 |
+
The fine-tuned model performed substantially better on our synthetic test set.
|
| 105 |
|
| 106 |
+
### Training Loss
|
| 107 |
|
| 108 |
+
| Epoch | Loss |
|
| 109 |
+
|---|---:|
|
| 110 |
+
| 1 | 1.944 |
|
| 111 |
+
| 2 | 0.461 |
|
| 112 |
+
| 3 | 0.091 |
|
| 113 |
|
| 114 |
+
The training loss decreased across all three epochs.
|
| 115 |
|
| 116 |
+
### Confusion Matrix Analysis
|
| 117 |
|
| 118 |
+
The fine-tuned model correctly classified 55 out of 56 test examples.
|
| 119 |
|
| 120 |
+
Six categories achieved perfect recall.
|
| 121 |
|
| 122 |
+
The only classification error occurred when a MULTI_CHANGE request was predicted as CHANGE_ATTRACTION.
|
| 123 |
|
| 124 |
+
The relevant category metrics were:
|
| 125 |
|
| 126 |
+
| Category | Precision | Recall | F1-score |
|
| 127 |
+
|---|---:|---:|---:|
|
| 128 |
+
| CHANGE_ATTRACTION | 0.89 | 1.00 | 0.94 |
|
| 129 |
+
| MULTI_CHANGE | 1.00 | 0.88 | 0.93 |
|
| 130 |
|
| 131 |
+
The macro-average F1-score was 0.98.
|
| 132 |
|
| 133 |
+
This indicates that requests involving multiple changes may sometimes be confused with requests involving only one attraction change.
|
| 134 |
|
| 135 |
+
The complete confusion matrix and classification report are included in the training notebook.
|
| 136 |
|
| 137 |
+
## Limitations
|
|
|
|
|
|
|
|
|
|
|
|
|
| 138 |
|
| 139 |
+
Although the model achieved high accuracy on the held-out dataset, several limitations remain.
|
| 140 |
|
| 141 |
+
1. **Synthetic training data:** The dataset contains only 280 synthetic examples. Real user requests may be more complex or expressed differently.
|
| 142 |
|
| 143 |
+
2. **Multi-change confusion:** Requests involving multiple itinerary components may sometimes be classified as a single-category change.
|
| 144 |
|
| 145 |
+
3. **Ambiguous language:** Short or unclear requests may not provide enough information for reliable classification.
|
| 146 |
|
| 147 |
+
4. **Limited task coverage:** The model only supports the seven predefined categories. It cannot independently create itineraries, verify live availability, make reservations, or process payments.
|
| 148 |
|
| 149 |
+
5. **Generalization:** The 98.2% accuracy was measured on a small synthetic held-out dataset. Performance on real travel conversations has not been established.
|
| 150 |
|
| 151 |
+
The model is intended for educational workflow routing and should not be used as an independent booking or payment system.
|
| 152 |
|
| 153 |
+
## Fresh-Session Model Verification
|
| 154 |
|
| 155 |
+
After training, we uploaded the LoRA adapter, classification head, tokenizer, and label configuration to this public Hugging Face repository.
|
| 156 |
|
| 157 |
+
We then opened a fresh Google Colab notebook and loaded the model directly from Hugging Face.
|
| 158 |
|
| 159 |
+
Test input:
|
| 160 |
|
| 161 |
+
> Please update the afternoon sightseeing activity to the science center.
|
| 162 |
|
| 163 |
+
Expected prediction from the original training notebook:
|
| 164 |
|
| 165 |
+
`CHANGE_ATTRACTION`
|
| 166 |
|
| 167 |
+
Prediction after loading from Hugging Face:
|
| 168 |
|
| 169 |
+
`CHANGE_ATTRACTION`
|
| 170 |
|
| 171 |
+
**Result: PASS - The fresh-session prediction matched the original notebook.**
|
| 172 |
|
| 173 |
+
This verifies that the uploaded model can be loaded in a separate session and reproduce the prediction for this test example.
|
| 174 |
|
| 175 |
+
### Fresh-Session Test Screenshot
|
| 176 |
|
| 177 |
+

|
| 178 |
|
| 179 |
+
## Project Information
|
| 180 |
|
| 181 |
+
Course: INFO 642
|
| 182 |
|
| 183 |
+
Project: Modular AI Travel Planner
|
| 184 |
|
| 185 |
+
Model repository: Shell2334/info642-travel-classifier-lora
|
|
|
|
| 186 |
|
| 187 |
+
Purpose: Educational research and demonstration.
|