Update README.md

README.md

@@ -3,7 +3,116 @@ datasets:
 - glaiveai/glaive-function-calling-v2
 ---
 
-from transformers import pipeline
+
+Here's how you can format your code and explanation into a README.md file:
+
+```markdown
+# Function Calling with Llama Model
+
+This README provides an example of integrating Llama model from Hugging Face Transformers to automate specific tasks, such as canceling a reservation.
+
+## Setup
+
+First, import the necessary libraries and setup your environment.
+
+```python
+from transformers import pipeline, AutoTokenizer, AutoModelForCausalLM
 import json
 import os
+import torch
+```
+
+## Tool Information
+
+Define the tools and their functionalities as a list of dictionaries.
+
+```python
+tools_info = [
+  {
+    "name": "cancel_reservation",
+    "description": "cancel a reservation",
+    "parameters": {
+      "type": "object",
+      "properties": {
+        "reservation_number": {
+          "type": "integer",
+          "description": "Reservation number"
+        }
+      },
+      "required": ["reservation_number"]
+    }
+  },
+]
+```
+
+## System Initialization
+
+Initialize the system's interactive capabilities using the defined tools.
+
+```python
+system = f"You are a helpful assistant with access to the following functions: \n {json.dumps(tools_info, indent=2)}."
+```
+
+## Conversation Flow
+
+Simulate a conversation flow where the user requests to cancel a reservation.
+
+```python
+messages = [
+    {"role": "system", "content": system},
+    {"role": "user", "content": "Help me to cancel a reservation"},
+    {"role": "assistant", "content": "I can help with that. Could you please provide me with the reservation number?"},
+    {"role": "user", "content": "the reservation number is 1011"}
+]
+```
+
+## Model Loading
+
+Load the causal language model and tokenizer.
+
+```python
+model_id = "caldana/function_calling_llama3_8b_instruct"
+tokenizer = AutoTokenizer.from_pretrained(model_id)
+model = AutoModelForCausalLM.from_pretrained(
+    model_id,
+    torch_dtype=torch.bfloat16,
+    device_map="auto",
+)
+```
+
+## Generating Response
+
+Generate a response from the model based on the conversation context.
+
+```python
+input_ids = tokenizer.apply_chat_template(
+    messages,
+    add_generation_prompt=True,
+    return_tensors="pt"
+).to(model.device)
+
+terminators = [
+    tokenizer.eos_token_id,
+    tokenizer.convert_tokens_to_ids("")
+]
+
+outputs = model.generate(
+    input_ids,
+    max_new_tokens=256,
+    eos_token_id=terminators,
+    do_sample=True,
+    temperature=0.6,
+    top_p=0.9,
+)
+
+response = outputs[0][input_ids.shape[-1]:]
+print(tokenizer.decode(response, skip_special_tokens=True))
+```
+
+## Conclusion
+
+This setup demonstrates how to utilize a pre-trained Llama model to handle function calls within a simulated conversation, focusing on task automation like reservation cancellation.
+```
+
+This markdown structure provides a clear and concise overview, suitable for a GitHub README, which explains the functionality, the setup requirements, and the usage of the code.