Update README.md

README.md

@@ -1,3 +1,4 @@
+
 ---
 license: apache-2.0
 language:
@@ -40,3 +41,82 @@ This model, designed and pretrained from scratch, was developed without utilizin
 For tokenization, this model uses:
 ```python
 tokenizer = tiktoken.get_encoding("gpt2")
+```
+
+## How to Use the Model
+
+### Load and Generate Text
+Below is a Python example on how to load the model and generate text:
+
+```python
+import torch
+from torch.nn import functional as F
+from gpt_class import GPTConfig, GPT
+import tiktoken
+
+# Set up the device
+device = "cuda" if torch.cuda.is_available() else "cpu"
+
+# Load the model
+state_dict = torch.load('model_51999.pt', map_location=device)
+config = state_dict['config']
+model = GPT(config)
+model.load_state_dict(state_dict['model'])
+model.to(device)
+model.eval()
+
+# Seed for reproducibility
+torch.manual_seed(42)
+torch.cuda.manual_seed_all(42)
+
+# Tokenizer
+tokenizer = tiktoken.get_encoding("gpt2")
+
+def Generate(model, tokenizer, example, num_return_sequences, max_length):
+    model.eval()
+    tokens = tokenizer.encode(example)
+    tokens = torch.tensor(tokens, dtype=torch.long).unsqueeze(0).repeat(num_return_sequences, 1)
+    tokens = tokens.to(device)
+    sample_rng = torch.Generator(device=device)
+
+    xgen = tokens
+    while xgen.size(1) < max_length:
+        with torch.no_grad():
+            with torch.autocast(device_type=device):
+                logits, _ = model(xgen)
+            logits = logits[:, -1, :]
+            probs = F.softmax(logits, dim=-1)
+            topk_probs, topk_indices = torch.topk(probs, 50, dim=-1)
+            ix = torch.multinomial(topk_probs, 1, generator=sample_rng)
+            xcol = torch.gather(topk_indices, -1, ix)
+            xgen = torch.cat((xgen, xcol), dim=1)
+
+    for i in range(num_return_sequences):
+        tokens = xgen[i, :max_length].tolist()
+        decoded = tokenizer.decode(tokens)
+        print(f"Sample {i+1}: {decoded}")
+
+# Example usage
+Generate(model, tokenizer, example="As we entered the forest we saw", num_return_sequences=4, max_length=32)
+```
+
+### Sample Output
+```
+Sample 1: As we entered the forest we saw huge white pine fells at the tops of the high plateaus (the great peaks) and trees standing at ground level.
+Sample 2: As we entered the forest we saw a few trees that were too large. We realized they were not going to be very big. There was one tree that was
+Sample 3: As we entered the forest we saw a group of small, wood-dwelling bees who had managed to escape a predator. A farmer was holding a handful
+Sample 4: As we entered the forest we saw giant, blue-eyed, spotted beetles on the ground, a grayling beetle in my lawn next to the pond, an
+```
+
+## Contributions
+Contributions, feedback, and discussions are welcome. Please feel free to contribute or suggest improvements through the project's repository.
+```
+
+### Explanation
+- **License and Language**: Specifies the open-source Apache 2.0 license and the bilingual capabilities (Hindi and English).
+- **Model Description**: Elaborates on the independent development and training of the model.
+- **Model Parameters**: Lists detailed specifications for the model configuration.
+- **How to Use the Model**: Provides complete code to load the model, set up the environment, and generate text.
+- **Sample Output**: Demonstrates example outputs to show what the model is capable of generating.
+
+This model card is ready to be used for your Hugging Face Model Hub submission, ensuring users have a comprehensive understanding of the model's capabilities and setup.