Update README.md

README.md

@@ -25,44 +25,47 @@ datasets:
 
 ### Overview
 
-This model is a fine-tuned version of `unsloth/mistral-7b-bnb-4bit`, a 7-billion-parameter model based on the Mistral architecture. It was trained to improve performance on natural language understanding tasks, specifically for text classification using the Stanford IMDb dataset. 
+This model is a fine-tuned version of `unsloth/mistral-7b-bnb-4bit`, a 7-billion-parameter model based on the Mistral architecture. It was fine-tuned to improve performance on natural language understanding tasks, specifically for text classification using the Stanford IMDb dataset.
 
-The fine-tuning process leveraged the **Unsloth** framework, which speeds up training times significantly, enabling a **2x faster training** process compared to traditional methods. Additionally, Hugging Face's **TRL library** (Transformers Reinforcement Learning) was used to adapt the model efficiently.
+The fine-tuning process leveraged the **Unsloth** framework, which significantly sped up the training time, enabling a **2x faster training** process. Additionally, Hugging Face's **TRL library** (Transformers Reinforcement Learning) was used to adapt the model efficiently.
 
 ### Training Details
 
 - **Base Model:** `unsloth/mistral-7b-bnb-4bit` (7B parameters, 4-bit quantized weights for memory efficiency)
-- **Training Speed:** The model was trained **2x faster** with Unsloth, making it a more practical solution for large-scale fine-tuning.
-- **Optimization Techniques:** Use of low-rank adaptation (LoRA), gradient checkpointing, and 4-bit quantization to reduce memory and computational cost while maintaining model performance.
+- **Training Speed:** The model was trained **2x faster** with Unsloth, optimizing training time and resource usage.
+- **Optimization Techniques:** Low-rank adaptation (LoRA), gradient checkpointing, and 4-bit quantization were employed to reduce memory and computational cost while maintaining model performance.
 
 ### Intended Use
 
-This model is intended for tasks like:
+This model is designed for tasks such as:
 - Sentiment analysis
 - Text classification
 - Fine-grained NLP tasks
 
-It is well-suited for environments with limited resources, thanks to the quantization of the base model and fine-tuning techniques employed.
+It is optimized for deployment in resource-constrained environments due to the quantization of the base model and fine-tuning techniques used.
 
 ### Model Performance
 
 - **Primary Metric:** Accuracy on text classification tasks (Stanford IMDb dataset)
-- **Fine-Tuning Results:** This fine-tuned model achieved a notable improvement in accuracy, making it suitable for deployment in real-world NLP applications.
+- **Fine-Tuning Results:** The fine-tuned model shows improved accuracy, making it a practical choice for NLP applications.
 
 ### Usage
 
-To use the model, you can directly load it using Hugging Face's Transformers library, with the following code:
+To use the model, you can load it using the `FastLanguageModel` class as follows:
 
 ```python
-from transformers import AutoModelForSequenceClassification, AutoTokenizer
+from unsloth import FastLanguageModel
 
+# Load the fine-tuned model and tokenizer
 model_name = "shaheennabi/your-finetuned-mistral-7b-imdb"
-
-# Load the fine-tuned model
-model = AutoModelForSequenceClassification.from_pretrained(model_name)
-
-# Load tokenizer
-tokenizer = AutoTokenizer.from_pretrained(model_name)
+max_seq_length = 512  # Set according to your requirements
+
+model, tokenizer = FastLanguageModel.from_pretrained(
+    model_name=model_name,
+    max_seq_length=max_seq_length,
+    dtype=None,
+    load_in_4bit=True
+)
 
 # Example of using the model for inference
 input_text = "This movie was fantastic!"