Update README.md

README.md

@@ -1,9 +1,9 @@
-
 ---
 tags:
   - generated_from_triptuner
   - transformer
   - character-level
+  - custom-model
 license: mit
 library_name: torch
 ---
@@ -15,7 +15,62 @@ It uses a custom transformer-based language model designed to handle character-l
 
 ## Usage
 
-The model can generate location-specific itineraries by providing a starting prompt of a location name.
+The Triptuner model cannot be directly used with Hugging Face's built-in Inference API because it uses a custom architecture. Below are the instructions on how to manually load and use this model with PyTorch.
+
+### Load and Use the Model with PyTorch
+
+```python
+import torch
+
+# Define your custom model class
+class BigramLanguageModel(nn.Module):
+    # Include the complete definition of your BigramLanguageModel here
+    
+    # Example method definitions:
+    def __init__(self):
+        super().__init__()
+        # Define your model layers here as per the training setup
+        # Example:
+        # self.token_embedding_table = nn.Embedding(vocab_size, n_embd)
+        # self.position_embedding_table = nn.Embedding(block_size, n_embd)
+        # self.blocks = nn.Sequential(*[Block(n_embd, n_head=n_head) for _ in range(n_layer)])
+        # self.ln_f = nn.LayerNorm(n_embd)
+        # self.lm_head = nn.Linear(n_embd, vocab_size)
+        
+    def forward(self, idx, targets=None):
+        # Define the forward pass as per your model
+        pass
+    
+    def generate(self, idx, max_new_tokens):
+        # Implement the generate method for text generation
+        pass
+
+# Load the model weights from Hugging Face
+model = BigramLanguageModel()
+model_url = "https://huggingface.co/yoonusajwardapiit/triptuner/resolve/main/pytorch_model.bin"
+model_weights = torch.hub.load_state_dict_from_url(model_url, map_location=torch.device('cpu'), weights_only=True)
+model.load_state_dict(model_weights)
+model.eval()
+
+# Define your character mappings
+chars = sorted(list(set("your_training_text_here")))  # Replace with the actual character set used in training
+stoi = {ch: i for i, ch in enumerate(chars)}
+itos = {i: ch for i, ch in enumerate(chars)}
+encode = lambda s: [stoi[c] for c in s]
+decode = lambda l: ''.join([itos[i] for i in l])
+
+# Test the model with a sample prompt
+prompt = "Hanthana"  # Replace with any relevant location or prompt
+context = torch.tensor([encode(prompt)], dtype=torch.long)
+
+# Generate text using the model
+with torch.no_grad():
+    generated = model.generate(context, max_new_tokens=250)  # Adjust the number of new tokens as needed
+
+# Decode and print the generated text
+generated_text = decode(generated[0].tolist())
+print(generated_text)
+
 
 ## Training Data