Add comprehensive model card

README.md

@@ -1,199 +1,167 @@
 ---
+license: apache-2.0
+base_model: microsoft/DialoGPT-medium
+tags:
+- conversational
+- national-parks
+- travel
+- recreation
+- parks
+- outdoor
+- assistant
+- fine-tuned
+- camping
+- hiking
+language:
+- en
 library_name: transformers
-tags: []
+pipeline_tag: text-generation
+model_type: gpt2
+datasets:
+- custom
+widget:
+- text: "Human: What should I pack for Yellowstone?
+Assistant:"
+  example_title: "Packing advice"
+- text: "Human: When is the best time to visit Zion?
+Assistant:"
+  example_title: "Visit timing"
+- text: "Human: How do I make campground reservations?
+Assistant:"
+  example_title: "Reservations help"
 ---
 
-# Model Card for Model ID
-
-<!-- Provide a quick summary of what the model is/does. -->
-
-
+# Parks LLM v2 - US Parks Assistant 🏞️
+
+A conversational AI model fine-tuned to help with US national parks, state parks, and recreation areas. This is an improved version with better training data and fixed attention mask handling.
+
+## Model Description
+
+Parks LLM v2 is fine-tuned from microsoft/DialoGPT-medium on a curated dataset of park-related conversations. It provides helpful information about:
+
+- 🎒 **Packing and Preparation**: What to bring for different park environments
+- 📅 **Visit Planning**: Best times to visit, crowd levels, weather considerations  
+- 🏕️ **Camping & Reservations**: Booking guidance and accommodation options
+- 👨‍👩‍👧‍👦 **Family Travel**: Family-friendly park recommendations and activities
+- 💰 **Budget Tips**: Cost-saving strategies and fee information
+- 🐻 **Safety Guidance**: Wildlife safety and Leave No Trace principles
+- 🥾 **Activities**: Hiking, camping, and outdoor activity recommendations
+
+## Quick Start
+
+```python
+from transformers import AutoTokenizer, AutoModelForCausalLM
+
+# Load the model
+tokenizer = AutoTokenizer.from_pretrained("ajc2195/parks-llm-v2")
+model = AutoModelForCausalLM.from_pretrained("ajc2195/parks-llm-v2")
+
+def ask_parks_assistant(question):
+    prompt = f"Human: {question}\nAssistant:"
+    inputs = tokenizer(prompt, return_tensors="pt", padding=True)
+    
+    with torch.no_grad():
+        outputs = model.generate(
+            inputs['input_ids'],
+            attention_mask=inputs['attention_mask'],
+            max_new_tokens=80,
+            temperature=0.7,
+            do_sample=True,
+            repetition_penalty=1.2,
+            pad_token_id=tokenizer.pad_token_id,
+            eos_token_id=tokenizer.eos_token_id
+        )
+    
+    response = tokenizer.decode(outputs[0], skip_special_tokens=True)
+    return response.split("Assistant:")[-1].strip()
+
+# Example usage
+answer = ask_parks_assistant("What should I pack for desert parks?")
+print(answer)
+```
+
+## Pipeline Usage
+
+```python
+from transformers import pipeline
+
+parks_assistant = pipeline(
+    "text-generation", 
+    model="ajc2195/parks-llm-v2",
+    tokenizer="ajc2195/parks-llm-v2"
+)
+
+response = parks_assistant(
+    "Human: What's the best time to visit Yellowstone?\nAssistant:",
+    max_new_tokens=60,
+    temperature=0.7,
+    do_sample=True,
+    repetition_penalty=1.2
+)
+```
+
+## Example Conversations
+
+**Q: What should I pack for Yellowstone?**
+A: For Yellowstone, pack layers for changing weather, waterproof jacket, hiking boots, bear spray, sunscreen, hat, and warm clothes for evenings. Don't forget your camera and binoculars for wildlife viewing!
+
+**Q: When is the best time to visit Zion?**
+A: The best time to visit Zion is spring (March-May) and fall (September-November) when temperatures are mild and crowds are smaller. Summer can be very hot, while winter may have snow at higher elevations.
+
+**Q: How do I make campground reservations?**
+A: Make reservations at recreation.gov up to 5 months in advance. Popular campgrounds fill quickly, so book early. Some sites are first-come, first-served, arriving early in the morning is recommended.
 
 ## Model Details
 
-### Model Description
-
-<!-- Provide a longer summary of what this model is. -->
-
-This is the model card of a 🤗 transformers model that has been pushed on the Hub. This model card has been automatically generated.
-
-- **Developed by:** [More Information Needed]
-- **Funded by [optional]:** [More Information Needed]
-- **Shared by [optional]:** [More Information Needed]
-- **Model type:** [More Information Needed]
-- **Language(s) (NLP):** [More Information Needed]
-- **License:** [More Information Needed]
-- **Finetuned from model [optional]:** [More Information Needed]
-
-### Model Sources [optional]
-
-<!-- Provide the basic links for the model. -->
-
-- **Repository:** [More Information Needed]
-- **Paper [optional]:** [More Information Needed]
-- **Demo [optional]:** [More Information Needed]
-
-## Uses
-
-<!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
-
-### Direct Use
-
-<!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->
-
-[More Information Needed]
-
-### Downstream Use [optional]
-
-<!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app -->
-
-[More Information Needed]
-
-### Out-of-Scope Use
-
-<!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->
-
-[More Information Needed]
-
-## Bias, Risks, and Limitations
-
-<!-- This section is meant to convey both technical and sociotechnical limitations. -->
-
-[More Information Needed]
-
-### Recommendations
-
-<!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->
-
-Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
-
-## How to Get Started with the Model
-
-Use the code below to get started with the model.
-
-[More Information Needed]
-
-## Training Details
-
-### Training Data
-
-<!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. -->
-
-[More Information Needed]
-
-### Training Procedure
-
-<!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
-
-#### Preprocessing [optional]
-
-[More Information Needed]
-
-
-#### Training Hyperparameters
-
-- **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->
-
-#### Speeds, Sizes, Times [optional]
-
-<!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. -->
-
-[More Information Needed]
-
-## Evaluation
-
-<!-- This section describes the evaluation protocols and provides the results. -->
-
-### Testing Data, Factors & Metrics
-
-#### Testing Data
-
-<!-- This should link to a Dataset Card if possible. -->
-
-[More Information Needed]
-
-#### Factors
-
-<!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. -->
-
-[More Information Needed]
-
-#### Metrics
-
-<!-- These are the evaluation metrics being used, ideally with a description of why. -->
-
-[More Information Needed]
-
-### Results
-
-[More Information Needed]
-
-#### Summary
-
-
-
-## Model Examination [optional]
-
-<!-- Relevant interpretability work for the model goes here -->
-
-[More Information Needed]
-
-## Environmental Impact
-
-<!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly -->
-
-Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700).
-
-- **Hardware Type:** [More Information Needed]
-- **Hours used:** [More Information Needed]
-- **Cloud Provider:** [More Information Needed]
-- **Compute Region:** [More Information Needed]
-- **Carbon Emitted:** [More Information Needed]
-
-## Technical Specifications [optional]
-
-### Model Architecture and Objective
-
-[More Information Needed]
-
-### Compute Infrastructure
-
-[More Information Needed]
-
-#### Hardware
-
-[More Information Needed]
-
-#### Software
-
-[More Information Needed]
-
-## Citation [optional]
+- **Base Model**: microsoft/DialoGPT-medium
+- **Training Data**: 15 high-quality park conversation examples
+- **Training Method**: Fine-tuning with improved hyperparameters
+- **Specialization**: US National Parks and recreation areas
+- **Version**: 2.0 (improved from original parks-llm)
 
-<!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->
+## Improvements in v2
 
-**BibTeX:**
+- ✅ Fixed attention mask warnings
+- ✅ Better training data diversity
+- ✅ Improved repetition penalty
+- ✅ Proper pad token handling
+- ✅ Enhanced generation parameters
 
-[More Information Needed]
+## Usage Tips
 
-**APA:**
+- Use the conversation format: "Human: [question]\nAssistant:"
+- Include `attention_mask` in generation for best results
+- Set `repetition_penalty=1.2` to avoid repetitive outputs
+- Recommended `temperature=0.7` for good balance of coherence and variety
 
-[More Information Needed]
+## Limitations
 
-## Glossary [optional]
+- Focuses primarily on US parks and recreation areas
+- Provides general guidance - always verify with official park sources
+- Not a substitute for real-time park information, alerts, or conditions
+- Training data is limited - may not cover all park scenarios
 
-<!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. -->
+## Ethical Considerations
 
-[More Information Needed]
+- This model should be used as a helpful assistant, not a replacement for official park information
+- Always check current park conditions, alerts, and regulations before traveling
+- Be aware that park policies and conditions change frequently
 
-## More Information [optional]
+## License
 
-[More Information Needed]
+Apache 2.0
 
-## Model Card Authors [optional]
+## Citation
 
-[More Information Needed]
+If you use this model, please cite:
 
-## Model Card Contact
+```
+@misc{parks-llm-v2,
+  title={Parks LLM v2: Conversational AI for US Parks and Recreation},
+  author={ajc2195},
+  year={2025},
+  url={https://huggingface.co/ajc2195/parks-llm-v2}
+}
+```
 
-[More Information Needed]
+Built with ❤️ for park enthusiasts and outdoor adventurers!