Update README.md

README.md

@@ -18,7 +18,38 @@ Worlds first Whole Foods Plant Based (WFPB) LLM. A Qwen3 1.7B model fine tuned w
 May output Chinese characters (Qwen3 is from Alibaba and multilingual) and long responses unless properly prompted. Created by Toby Miller.
 Linkedin: https://www.linkedin.com/in/robertmilleree/
 
-**note**: chat template may need adjustments.
+**note**: Chat template needs adjustments, but works with the following script
+
+from transformers import AutoTokenizer, AutoModelForCausalLM
+from peft import PeftModel
+
+base_model_path = "/media/robert/360_HDD/AI_models/Non GGUF/qwen3-1.7B-base"
+tokenizer = AutoTokenizer.from_pretrained(base_model_path)
+model = AutoModelForCausalLM.from_pretrained(base_model_path, dtype="auto")
+
+adapter_path = "/home/robert/LLaMA-Factory/saves/Qwen3-1.7B-Base/lora/train_2025-09-23-12-10-34"
+model = PeftModel.from_pretrained(model, adapter_path)
+
+model.config.pad_token_id = tokenizer.eos_token_id
+
+prompt = "What is the best diet for human health and longevity?"
+
+inputs = tokenizer(prompt, return_tensors="pt")
+
+outputs = model.generate(
+    **inputs,
+    max_new_tokens=200,        # limit output length
+    do_sample=True,
+    temperature=0.1,           # deterministic / low creativity
+    repetition_penalty=1.2,    # discourages repeating
+    pad_token_id=tokenizer.eos_token_id,
+    eos_token_id=tokenizer.eos_token_id
+)
+
+response = tokenizer.decode(outputs[0], skip_special_tokens=True)
+print(response)
+
+
 
 **Example output:**
 Q: ¨What is the best diet for human health and longevity?¨