Update README.md

README.md

@@ -1,26 +1,27 @@
----
-tags:
-- autotrain
-- text-generation-inference
-- text-generation
-- peft
-library_name: transformers
-base_model: meta-llama/Meta-Llama-3.1-8B-Instruct
-widget:
-  - messages:
-      - role: user
-        content: What is your favorite condiment?
-license: other
----
+**QuantumAI: Zero LLM Quantum AI Model**
+This is QuantumAI, a cutting-edge text generation model based on Meta-Llama-3.1-8B-Instruct, fine-tuned for conversational tasks using AutoTrain. The model is designed to handle a variety of natural language processing tasks, with a special focus on interactive dialogue, text generation, and inference.
 
-# Model Trained Using AutoTrain
+![Zero LLM Quantum AI](https://huggingface.co/shafire/QuantumAI/blob/main/ZeroQuantumAI.png)
 
-This model was trained using AutoTrain. For more information, please visit [AutoTrain](https://hf.co/docs/autotrain).
+*Model Information**
+Base Model: meta-llama/Meta-Llama-3.1-8B
+Fine-tuned Model: meta-llama/Meta-Llama-3.1-8B-Instruct
+Training Framework: AutoTrain
+Training Data: Conversational and text-generation focused dataset
+Tech Stack:
+Transformers
+PEFT (Parameter-Efficient Fine-Tuning)
+TensorBoard (for logging and metrics)
+Safetensors
+Language Model Task: Conversational and Text Generation
+Usage Type: Interactive dialogue and text generation applications
+Quantization: Model supports 4-bit quantization for efficient inference
 
-# Usage
-
-```python
+**Installation and Usage**
+To use this model in your code, follow the instructions below:
 
+python
+Copy code
 from transformers import AutoModelForCausalLM, AutoTokenizer
 
 model_path = "PATH_TO_THIS_REPO"
@@ -32,7 +33,7 @@ model = AutoModelForCausalLM.from_pretrained(
     torch_dtype='auto'
 ).eval()
 
-# Prompt content: "hi"
+# Example usage
 messages = [
     {"role": "user", "content": "hi"}
 ]
@@ -41,6 +42,34 @@ input_ids = tokenizer.apply_chat_template(conversation=messages, tokenize=True,
 output_ids = model.generate(input_ids.to('cuda'))
 response = tokenizer.decode(output_ids[0][input_ids.shape[1]:], skip_special_tokens=True)
 
-# Model response: "Hello! How can I assist you today?"
+# Output
 print(response)
-```
+Inference API
+This model is not yet deployed to the Hugging Face Inference API. However, you can deploy it to Inference Endpoints for dedicated serverless inference.
+
+Training Process
+The QuantumAI model was trained using AutoTrain with the following configuration:
+
+Hardware: CUDA 12.1
+Training Precision: Mixed FP16
+Batch Size: 2
+Learning Rate: 3e-05
+Epochs: 5
+Optimizer: AdamW
+PEFT: Enabled (LoRA with lora_r=16, lora_alpha=32)
+Quantization: Int4 for efficient deployment
+Scheduler: Linear with warmup
+Gradient Accumulation: 4 steps
+Max Sequence Length: 2048 tokens
+Training Metrics
+The model was monitored using TensorBoard during training. Key training metrics included:
+
+Training Loss: 1.74
+Learning Rate: Adjusted per epoch, starting at 3e-05.
+Model Features
+Text Generation: Handles various types of user queries and provides coherent responses.
+Conversational AI: Optimized for dialogue generation.
+Efficient Inference: Supports Int4 quantization for faster inference on limited hardware.
+License
+This model is governed under a custom license. Please refer to QuantumAI License. (llama 3.1 license)
+