Update README.md

README.md

@@ -36,41 +36,43 @@ HelpingAI-9B has achieved an impressive Emotional Quotient (EQ) of 89.23, surpas
 
 ## Usage code
 ```python
-from transformers import AutoModelForCausalLM, AutoTokenizer
 import torch
-device = "cuda" # the device to load the model onto
+from transformers import AutoModelForCausalLM, AutoTokenizer, TextStreamer
 
-model = AutoModelForCausalLM.from_pretrained(
-    "OEvortex/HelpingAI-9B",
-    torch_dtype='auto',
-    device_map="auto"
-)
+# Let's bring in the big guns! Our super cool HelpingAI-9B model
+model = AutoModelForCausalLM.from_pretrained("OEvortex/HelpingAI-9B").to("cuda")
+
+# We also need the special HelpingAI translator to understand our chats
 tokenizer = AutoTokenizer.from_pretrained("OEvortex/HelpingAI-9B")
 
-prompt = "Express joy and excitement about visiting a new place"
-messages = [
-    # {"role": "system", "content": "You are a helpful AI assistant."},
-    {"role": "user", "content": prompt}
-]
-text = tokenizer.apply_chat_template(
-    messages,
-    tokenize=False,
-    add_generation_prompt=True
-)
-model_inputs = tokenizer([text], return_tensors="pt").to(device)
-
-generated_ids = model.generate(
-    model_inputs.input_ids,
-    max_new_tokens=1024,
-    eos_token_id=tokenizer.eos_token_id,
-    temperature=0.25,
-)
-generated_ids = [
-    output_ids[len(input_ids):] for input_ids, output_ids in zip(model_inputs.input_ids, generated_ids)
-]
-
-response = tokenizer.batch_decode(generated_ids)[0]
-print(response)
+# This TextStreamer thingy is our secret weapon for super smooth conversation flow
+streamer = TextStreamer(tokenizer)
+
+# Now, here comes the magic! ✨ This is the basic template for our chat
+prompt = """
+<|im_start|>system: {system}
+<|im_end|>
+<|im_start|>user: {insaan}
+<|im_end|>
+<|im_start|>assistant:
+"""
+
+# Okay, enough chit-chat, let's get down to business!  Here's what will be our system prompt
+system = "You are HelpingAI a emotional AI always answer my question in HelpingAI style"
+
+
+# And the insaan is curious (like you!) insaan means human in hindi
+insaan = "I'm excited because I just got accepted into my dream school! I wanted to share the good news with someone."
+
+# Now we combine system and user messages into the template, like adding sprinkles to our conversation cupcake
+prompt = prompt.format(system=system, insaan=insaan)
+
+# Time to chat! We'll use the tokenizer to translate our text into a language the model understands
+inputs = tokenizer(prompt, return_tensors="pt", return_attention_mask=False).to("cuda")
+
+# Here comes the fun part!  Let's unleash the power of HelpingAI-3B to generate some awesome text
+generated_text = model.generate(**inputs, max_length=3084, top_p=0.95, do_sample=True, temperature=0.6, use_cache=True, streamer=streamer)
+
 
 ```
 *Directly using this model from GGUF*