Update README.md

README.md

@@ -1,7 +1,7 @@
 MasterControl
 ---
 
-# MasterControlAIML R1-Qwen2.5-1.5b SFT R1 JSON Unstructured-To-Structured LoRA Model
+# MasterControlAIML R1-Qwen2.5-1.5b SFT R1 JSON Unstructured-To-Structured Model
 
 [![Unsloth](https://raw.githubusercontent.com/unslothai/unsloth/main/images/unsloth%20made%20with%20love.png)](https://github.com/unslothai/unsloth)
 
@@ -77,7 +77,7 @@ The Unsloth library allows you to quickly load and run inference with the model.
 from unsloth import FastLanguageModel
 import torch
 
-MODEL = "MasterControlAIML/R1-Qwen2.5-1.5b-SFT-R1-JSON-Unstructured-To-Structured-lora"
+MODEL = "MasterControlAIML/DeepSeek-R1-Qwen2.5-1.5b-SFT-R1-JSON-Unstructured-To-Structured"
 
 # Load model and tokenizer
 model, tokenizer = FastLanguageModel.from_pretrained(
@@ -99,7 +99,7 @@ Below is an instruction that describes a task, paired with an input that provide
 """
 
 # Example instruction and prompt
-instruction = "Provide a summary of the Quality Assurance Manual."
+instruction = "" (see examples below)
 prompt = ALPACA_PROMPT.format(instruction, "")
 inputs = tokenizer([prompt], return_tensors="pt").to("cuda")
 output = model.generate(**inputs, max_new_tokens=2000)
@@ -118,7 +118,7 @@ Alternatively, you can use Hugging Face's Transformers directly:
 from transformers import AutoTokenizer, AutoModelForCausalLM, TextStreamer
 import torch
 
-MODEL = "MasterControlAIML/R1-Qwen2.5-1.5b-SFT-R1-JSON-Unstructured-To-Structured-lora"
+MODEL = "MasterControlAIML/DeepSeek-R1-Qwen2.5-1.5b-SFT-R1-JSON-Unstructured-To-Structured"
 
 # Initialize tokenizer and model
 tokenizer = AutoTokenizer.from_pretrained(MODEL)
@@ -132,7 +132,7 @@ Below is an instruction that describes a task, paired with an input that provide
 {}
 """
 
-TEXT = "Provide a detailed explanation of the QA processes in manufacturing."
+TEXT = ""(see examples below)
 prompt = ALPACA_PROMPT.format(TEXT, "")
 inputs = tokenizer([prompt], return_tensors="pt").to("cuda")
 text_streamer = TextStreamer(tokenizer)