Update README.md

README.md

@@ -1,98 +1,77 @@
 ---
-license: apache-2.0
-datasets:
-- yashsoni78/conversation_data_mcp_100
-language:
-- en
-base_model:
-- mistralai/Mistral-7B-Instruct-v0.2
-library_name: adapter-transformers
+license: mit
 tags:
-- code
----
-# MCP Tool-Calling (v1)
-
-This repository contains a specialized version of `mistralai/Mistral-7B-Instruct-v0.2`, fine-tuned to function as a reasoning engine for a tool-calling AI agent.
-
-The model has been trained to understand natural language requests related to a custom set of "MCP" tools and translate them into a specific, structured format suitable for execution in an application backend.
-
+  - conversational
+  - text-generation
+  - instruction-tuned
+  - chat
+  - dialogue
+language:
+  - en
+datasets:
+  - yashsoni78/conversation_data_mcp_100
+library_name: transformers
+pipeline_tag: text-generation
 ---
-## Model Description
-
-This model was fine-tuned using **Parameter-Efficient Fine-Tuning (PEFT)** with **LoRA** on a custom, high-quality dataset. Its primary skill is to receive a user prompt and generate a tool call in a specific, sandboxed format. While the fine-tuning has exposed it to several tool types, its core capability is understanding the intent to use a tool and structuring the output accordingly.
 
-The model expects prompts in a `SYSTEM-USER-ASSISTANT` format and has been trained to generate tool calls with the 'tool_code' format..
+# 🛠️ MCP Tool Model
 
-## Intended Use
+The **MCP Tool Model** is an instruction-tuned conversational language model fine-tuned on the [`conversation_data_mcp_100`](https://huggingface.co/datasets/yashsoni78/conversation_data_mcp_100) dataset. Built to handle multi-turn dialogues with clarity and coherence, this model is ideal for chatbot development, virtual assistants, or any conversational AI tasks.
 
-This model is not a general-purpose chatbot. It is a specialized component intended to be used within a larger application or "agent" that can parse and execute the generated code.
+## 🧠 Model Details
 
-* **Primary Use:** Translating natural language commands into structured code for automation.
-* **Out of Scope:** General conversation, creative writing, or tasks outside its trained toolset.
+- **Base Model**: *mistralai/Mistral-7B-Instruct-v0.2*
+- **Fine-tuned on**: Custom multi-turn conversation dataset (`yashsoni78/conversation_data_mcp_100`)
+- **Languages**: English
+- **Use case**: General-purpose chatbot or instruction-following agent
 
----
-## How to Use
+## 🚀 Example Usage
 
-The model is a PEFT adapter, meaning you must load it on top of the original base model. The following code provides a complete example of how to load the model from the Hub and run inference.
+You can load and use the model with the Hugging Face Transformers library:
 
 ```python
-import torch
 from transformers import AutoModelForCausalLM, AutoTokenizer
-from peft import PeftModel
+import torch
+
+model_name = "yashsoni78/mcp_tool_model"
 
-# --- 1. Configuration ---
-BASE_MODEL_REPO_ID = "mistralai/Mistral-7B-Instruct-v0.2"
-# Replace with your actual model repository ID on the Hub
-FINE_TUNED_REPO_ID = "yashsoni78/mcp_tool_model" 
-DEVICE = "cuda" if torch.cuda.is_available() else "cpu"
+tokenizer = AutoTokenizer.from_pretrained(model_name)
+model = AutoModelForCausalLM.from_pretrained(model_name)
 
-# --- 2. Load Model and Tokenizer ---
-print(f"Loading base model: {BASE_MODEL_REPO_ID}")
-base_model = AutoModelForCausalLM.from_pretrained(
-    BASE_MODEL_REPO_ID,
-    torch_dtype=torch.bfloat16,
-    device_map=DEVICE
-)
+input_text = "User: How do I reset my password?\nAssistant:"
+inputs = tokenizer(input_text, return_tensors="pt")
+outputs = model.generate(**inputs, max_new_tokens=100)
 
-print(f"Loading fine-tuned adapter & tokenizer from: {FINE_TUNED_REPO_ID}")
-tokenizer = AutoTokenizer.from_pretrained(FINE_TUNED_REPO_ID)
+print(tokenizer.decode(outputs[0], skip_special_tokens=True))
+```
 
-# Resize token embeddings to account for any special tokens added during training
-base_model.resize_token_embeddings(len(tokenizer))
+> 💡 Make sure to adapt the prompt formatting depending on your training setup (e.g., special tokens, roles, etc.)
 
-# Load the LoRA adapter and merge it into the base model for faster inference
-model = PeftModel.from_pretrained(base_model, FINE_TUNED_REPO_ID)
-model = model.merge_and_unload()
-model.eval() # Set the model to evaluation mode
+## 📚 Training Data
 
-print("✅ Model loaded successfully.")
+This model was fine-tuned on the [MCP 100 conversation dataset](https://huggingface.co/datasets/yashsoni78/conversation_data_mcp_100), consisting of 100 high-quality multi-turn dialogues between users and assistants. Each exchange is structured to reflect real-world inquiry-response flows.
 
-# --- 3. Run Inference ---
-system_prompt = "You are an expert assistant that uses MCP tools. When a tool is required, you must respond *only* with the 'tool_code' format."
-user_prompt = "What's the status of my 'database-main' VM?"
+## 📊 Intended Use
 
-formatted_prompt = f"SYSTEM: {system_prompt}\nUSER: {user_prompt}\nASSISTANT:"
-inputs = tokenizer(formatted_prompt, return_tensors="pt").to(DEVICE)
+- Chatbots for websites or tools
+- Instruction-following agents
+- Dialogue research
+- Voice assistant backend
 
-outputs = model.generate(**inputs, max_new_tokens=150, pad_token_id=tokenizer.eos_token_id)
-response = tokenizer.decode(outputs[0], skip_special_tokens=True).split("ASSISTANT:")[1].strip()
+## ⚠️ Limitations
 
-print("\n--- Model Output ---")
-print(response)
+- May hallucinate facts or generate inaccurate responses.
+- Trained on a small dataset (100 dialogues), so generalization may be limited.
+- English only.
 
-````
+## 📜 License
 
-## Training Details
+This model is licensed under the [MIT License](https://opensource.org/licenses/MIT). You are free to use, modify, and distribute it with attribution.
 
-  * **Base Model:** `mistralai/Mistral-7B-Instruct-v0.2`
-  * **Fine-Tuning Method:** PEFT (LoRA) with 4-bit quantization (`bitsandbytes`).
-  * **Dataset:** The model was trained on a curated, high-quality dataset containing a balanced mix of tool-calling examples and conversational ("negative") examples to teach it when *not* to call a tool. Special tokens `[TOOL_CODE_START]` and `[TOOL_CODE_END]` were added to the vocabulary.
-  * **Training Procedure:** The model was trained using the `SFTTrainer` from the TRL library.
+## 🙏 Acknowledgements
 
-## Limitations and Bias
+Special thanks to the open-source community and Hugging Face for providing powerful tools to build and share models easily.
 
-  * **Syntax Hallucination:** As a probabilistic model, it may occasionally generate tool calls with slightly incorrect syntax (e.g., wrong object names, extra parameters). It is **highly recommended** to use this model within an application that performs a `Parse -> Validate -> Execute` loop to ensure safety and reliability.
-  * **Scope:** The model's knowledge is limited to the patterns and tools seen during fine-tuning. It cannot use new tools without being re-trained.
-  * **Language:** The model was trained exclusively on English language prompts.
+## 📬 Contact
 
-```
+For issues, feedback, or collaborations, feel free to reach out to [@yashsoni78](https://huggingface.co/yashsoni78).