Update README.md

README.md

@@ -440,211 +440,6 @@ messages
 #   'content': 'The tip amount for your bill is $7.50. The total amount to be paid is $57.50.'}]
 ```
 
-## English Version
-
-### Model Card for ricepaper/vi-gemma-2-2b-function-calling
-
-### Model Description
-
-This model is a fine-tuned version of the **google/gemma-2-2b-it** model, specialized for understanding and executing function calls within the Vietnamese language. It has been trained on a comprehensive dataset encompassing conversations that include function calls formatted in ChatML, along with multilingual data that has been translated into Vietnamese.
-
-### Intended Uses
-
-This model is well-suited for applications that demand:
-
-* **Conversational AI:** Constructing chatbots that engage with users and carry out specific actions through function calls.
-* **Question Answering Systems:** Creating automated systems capable of retrieving information from diverse data sources.
-* **Advanced NLP Applications:** Developing sophisticated natural language processing applications such as text summarization, machine translation, and text generation.
-* **Intelligent Agent Development:** Building agents that can interact with their environment and execute actions based on language instructions.
-* **Multi-Agent Systems:** Developing systems where multiple agents communicate and collaborate to solve complex problems.
-
-### How to Use
-
-**1. Installation of Required Libraries:**
-
-```python
-! pip install transformers torch
-```
-
-**2. Initialization of Tokenizer and Model:**
-
-```python
-from transformers import AutoTokenizer, AutoModelForCausalLM
-import torch
-import json
-
-# Initialize the tokenizer and model
-tokenizer = AutoTokenizer.from_pretrained("ricepaper/vi-gemma-2-2b-function-calling")
-model = AutoModelForCausalLM.from_pretrained(
-    "ricepaper/vi-gemma-2-2b-function-calling",
-    device_map="auto",
-    torch_dtype=torch.float16,
-)
-```
-
-**3. Function for User Query Processing:**
-
-```python
-def process_user_query(user_query, messages, available_tools):
-    """
-    Handles user queries, generates responses, and manages function calls (if present).
-
-    Args:
-        user_query (str): User's input query.
-        messages (list): List of messages in the ongoing conversation.
-        available_tools (dict): Dictionary of available functions.
-
-    Returns:
-        str: Final response after processing any function calls.
-    """
-
-    messages.append({"role": "user", "content": user_query})
-
-    input_ids = tokenizer.apply_chat_template(
-        messages,
-        add_generation_prompt=True,
-        return_tensors="pt"
-    ).to(model.device)
-    outputs = model.generate(
-        input_ids,
-        max_new_tokens=300,
-        # ... (Additional generate parameters can be added here)
-    )
-    response = tokenizer.decode(outputs[0][input_ids.shape[-1]:], skip_special_tokens=True)
-
-    try:
-        response_list = json.loads(response)
-        messages.append({"role": "assistant", "content": response})
-    except json.JSONDecodeError:
-        response_list = []
-
-    function_responses = []
-
-    for response_dict in response_list:
-        if "name" in response_dict and "arguments" in response_dict:
-            function_name = response_dict.get("name")
-            function_args = response_dict.get("arguments")
-
-            if function_name in available_tools:
-                print(f"Calling function {function_name} with arguments {function_args}\n")
-                function_to_call = available_tools[function_name]
-                function_response = function_to_call(**function_args)
-                function_responses.append({
-                    "name": function_name,
-                    "response": function_response
-                })
-            else:
-                print(f"Function {function_name} not found")
-
-    if function_responses:
-        messages.append({
-            "role": "user",
-            "content": f"FUNCTION RESPONSES:\n{json.dumps(function_responses, ensure_ascii=False)}"
-        })
-        print(messages[-1].get("content"))
-
-        input_ids = tokenizer.apply_chat_template(
-            messages,
-            add_generation_prompt=True,
-            return_tensors="pt"
-        ).to(model.device)
-        outputs = model.generate(
-            input_ids,
-            max_new_tokens=300,
-            # ... (Additional generate parameters can be added here)
-        )
-        response = tokenizer.decode(outputs[0][input_ids.shape[-1]:], skip_special_tokens=True)
-
-    return response
-```
-
-**4. Helper Functions and Tools Definition:**
-
-```python
-def calculate_tip(bill_amount: float, tip_percentage: float) -> str:
-  """Calculates the tip for a given bill amount and percentage.
-
-  Args:
-    bill_amount: Total bill amount.
-    tip_percentage: Tip percentage.
-
-  Returns:
-    str: Description of the tip amount and total to be paid.
-  """
-
-  tip_amount = bill_amount * (tip_percentage / 100)
-  total_amount = bill_amount + tip_amount
-  return f"The tip amount is: {tip_amount:.2f}\nThe total amount to be paid is: {total_amount:.2f}"
-
-tools = """
-{
-  "name": "calculate_tip",
-  "description": "Calculate the tip amount for a bill",
-  "parameters": {
-    "type": "object",
-    "properties": {
-      "bill_amount": {
-        "type": "number",
-        "description": "The total bill amount"
-      },
-      "tip_percentage": {
-        "type": "number",
-        "description": "The tip percentage"
-      }
-    },
-    "required": [
-      "bill_amount",
-      "tip_percentage"
-    ]
-  }
-},
-"""
-
-available_tools = {
-    "calculate_tip": calculate_tip,
-}
-```
-
-**5. Conversation History and Model Usage Example:**
-
-```python
-messages = [
-    {"role": "user", "content": f"""You are a helpful assistant with access to the following functions. Use them if necessary {tools}"""},
-    {"role": "assistant", "content": "Hello, how can I assist you?"},
-]
-
-res = process_user_query("I need help calculating the tip for my bill. The total is $50 and I would like to leave a 15% tip.", messages, available_tools)
-messages.append({"role": "assistant", "content": res})
-print("\n"+res)
-# Calling function calculate_tip with arguments {'bill_amount': 50, 'tip_percentage': 15}
-
-# FUNCTION RESPONSES:
-# [{"name": "calculate_tip", "response": "The tip amount is: 7.50\nThe total amount to be paid is: 57.50"}]
-
-# The tip amount for your bill is $7.50. The total amount to be paid is $57.50.
-
-print(messages)
-# Expected output (The actual output might vary slightly):
-# [{'role': 'user',
-#   'content': 'You are a helpful assistant with access to the following functions. Use them if necessary \n{\n  "name": "calculate_tip",\n  "description": "Calculate the tip amount for a bill",\n  "parameters": {\n    "type": "object",\n    "properties": {\n      "bill_amount": {\n        "type": "number",\n        "description": "The total bill amount"\n      },\n      "tip_percentage": {\n        "type": "number",\n        "description": "The tip percentage"\n      }\n    },\n    "required": [\n      "bill_amount",\n      "tip_percentage"\n    ]\n  }\n},\n'},
-#  {'role': 'assistant', 'content': 'Hello, how can I assist you?'},
-#  {'role': 'user',
-#   'content': 'I need help calculating the tip for my bill. The total is $50 and I would like to leave a 15% tip.'},
-#  {'role': 'assistant',
-#   'content': '[{"name": "calculate_tip", "arguments": {"bill_amount": 50, "tip_percentage": 15}}]'},
-#  {'role': 'user',
-#   'content': 'FUNCTION RESPONSES:\n[{"name": "calculate_tip", "response": "The tip amount is: 7.50\nThe total amount to be paid is: 57.50"}]'},
-#  {'role': 'assistant',
-#   'content': 'The tip amount for your bill is $7.50. The total amount to be paid is $57.50.'}]
-```
-
-### Notes
-
-* The model might require appropriate scaling and hardware configuration for optimal performance.
-* The quality of function call results depends on the provided helper functions.
-* Users can adjust the model's generation parameters to fine-tune response length and content. 
-
-
 # Uploaded  model
 
 - **Developed by:** [hiieu](https://huggingface.co/hiieu), [himmeow the coder](https://viblo.asia/u/MartinCrux), [cuctrinh](https://www.linkedin.com/in/trinh-cuc-5722832b6)