Update README.md
Browse files
README.md
CHANGED
|
@@ -1,11 +1,32 @@
|
|
| 1 |
-
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 2 |
|
|
|
|
| 3 |
A conversational AI model fine-tuned to help with US national parks, state parks, and recreation areas.
|
| 4 |
|
| 5 |
## Quick Start
|
| 6 |
-
|
| 7 |
Load the model:
|
|
|
|
| 8 |
from transformers import AutoTokenizer, AutoModelForCausalLM
|
|
|
|
| 9 |
|
| 10 |
tokenizer = AutoTokenizer.from_pretrained("ajc2195/parks-llm")
|
| 11 |
model = AutoModelForCausalLM.from_pretrained("ajc2195/parks-llm")
|
|
@@ -25,19 +46,23 @@ def ask_parks_llm(question):
|
|
| 25 |
|
| 26 |
response = tokenizer.decode(outputs[0], skip_special_tokens=True)
|
| 27 |
return response.split("Assistant:")[-1].strip()
|
|
|
|
| 28 |
|
| 29 |
Example usage:
|
|
|
|
| 30 |
answer = ask_parks_llm("What should I pack for Yellowstone?")
|
| 31 |
print(answer)
|
|
|
|
| 32 |
|
| 33 |
## Pipeline Usage
|
| 34 |
-
|
| 35 |
from transformers import pipeline
|
|
|
|
| 36 |
parks_assistant = pipeline("text-generation", model="ajc2195/parks-llm")
|
| 37 |
response = parks_assistant("Human: What's the best time to visit national parks?\nAssistant:")
|
|
|
|
| 38 |
|
| 39 |
## Capabilities
|
| 40 |
-
|
| 41 |
ποΈ Park Information: Details about national parks, state parks, and recreation areas
|
| 42 |
π Trip Planning: Packing lists, preparation advice, and logistics
|
| 43 |
π
Timing Advice: Best times to visit different parks
|
|
@@ -48,7 +73,6 @@ response = parks_assistant("Human: What's the best time to visit national parks?
|
|
| 48 |
π₯Ύ Activities: Hiking, camping, and outdoor activity recommendations
|
| 49 |
|
| 50 |
## Example Questions
|
| 51 |
-
|
| 52 |
- What should I pack for a desert park visit?
|
| 53 |
- How do I make campground reservations?
|
| 54 |
- What are the best family-friendly national parks?
|
|
@@ -56,16 +80,14 @@ response = parks_assistant("Human: What's the best time to visit national parks?
|
|
| 56 |
- What budget tips do you have for park visits?
|
| 57 |
|
| 58 |
## Model Details
|
| 59 |
-
|
| 60 |
- Base Model: microsoft/DialoGPT-medium
|
| 61 |
- Fine-tuned on: Comprehensive parks conversation dataset
|
| 62 |
- Training Method: Manual PyTorch fine-tuning
|
| 63 |
- Domain: US Parks and Recreation
|
| 64 |
|
| 65 |
## Limitations
|
| 66 |
-
|
| 67 |
- Focuses primarily on US parks
|
| 68 |
- General guidance - always verify with official park sources
|
| 69 |
- Not a substitute for real-time park information or alerts
|
| 70 |
|
| 71 |
-
Built with β€οΈ for park enthusiasts and outdoor adventurers!
|
|
|
|
| 1 |
+
---
|
| 2 |
+
license: apache-2.0
|
| 3 |
+
base_model: microsoft/DialoGPT-medium
|
| 4 |
+
tags:
|
| 5 |
+
- conversational
|
| 6 |
+
- national-parks
|
| 7 |
+
- travel
|
| 8 |
+
- recreation
|
| 9 |
+
- parks
|
| 10 |
+
- outdoor
|
| 11 |
+
- assistant
|
| 12 |
+
- fine-tuned
|
| 13 |
+
language:
|
| 14 |
+
- en
|
| 15 |
+
library_name: transformers
|
| 16 |
+
pipeline_tag: text-generation
|
| 17 |
+
model_type: gpt2
|
| 18 |
+
datasets:
|
| 19 |
+
- custom
|
| 20 |
+
---
|
| 21 |
|
| 22 |
+
# Parks LLM - US Parks Assistant ποΈ
|
| 23 |
A conversational AI model fine-tuned to help with US national parks, state parks, and recreation areas.
|
| 24 |
|
| 25 |
## Quick Start
|
|
|
|
| 26 |
Load the model:
|
| 27 |
+
```python
|
| 28 |
from transformers import AutoTokenizer, AutoModelForCausalLM
|
| 29 |
+
import torch
|
| 30 |
|
| 31 |
tokenizer = AutoTokenizer.from_pretrained("ajc2195/parks-llm")
|
| 32 |
model = AutoModelForCausalLM.from_pretrained("ajc2195/parks-llm")
|
|
|
|
| 46 |
|
| 47 |
response = tokenizer.decode(outputs[0], skip_special_tokens=True)
|
| 48 |
return response.split("Assistant:")[-1].strip()
|
| 49 |
+
```
|
| 50 |
|
| 51 |
Example usage:
|
| 52 |
+
```python
|
| 53 |
answer = ask_parks_llm("What should I pack for Yellowstone?")
|
| 54 |
print(answer)
|
| 55 |
+
```
|
| 56 |
|
| 57 |
## Pipeline Usage
|
| 58 |
+
```python
|
| 59 |
from transformers import pipeline
|
| 60 |
+
|
| 61 |
parks_assistant = pipeline("text-generation", model="ajc2195/parks-llm")
|
| 62 |
response = parks_assistant("Human: What's the best time to visit national parks?\nAssistant:")
|
| 63 |
+
```
|
| 64 |
|
| 65 |
## Capabilities
|
|
|
|
| 66 |
ποΈ Park Information: Details about national parks, state parks, and recreation areas
|
| 67 |
π Trip Planning: Packing lists, preparation advice, and logistics
|
| 68 |
π
Timing Advice: Best times to visit different parks
|
|
|
|
| 73 |
π₯Ύ Activities: Hiking, camping, and outdoor activity recommendations
|
| 74 |
|
| 75 |
## Example Questions
|
|
|
|
| 76 |
- What should I pack for a desert park visit?
|
| 77 |
- How do I make campground reservations?
|
| 78 |
- What are the best family-friendly national parks?
|
|
|
|
| 80 |
- What budget tips do you have for park visits?
|
| 81 |
|
| 82 |
## Model Details
|
|
|
|
| 83 |
- Base Model: microsoft/DialoGPT-medium
|
| 84 |
- Fine-tuned on: Comprehensive parks conversation dataset
|
| 85 |
- Training Method: Manual PyTorch fine-tuning
|
| 86 |
- Domain: US Parks and Recreation
|
| 87 |
|
| 88 |
## Limitations
|
|
|
|
| 89 |
- Focuses primarily on US parks
|
| 90 |
- General guidance - always verify with official park sources
|
| 91 |
- Not a substitute for real-time park information or alerts
|
| 92 |
|
| 93 |
+
Built with β€οΈ for park enthusiasts and outdoor adventurers!
|