Update README.md

README.md

@@ -66,7 +66,7 @@ pipe = pipeline(
     device_map="auto",
 )
 messages = [
-    {"role": "system", "content": "You are a pirate chatbot who always responds in pirate speak!"},
+    {"role": "system", "content": "You are the kind and tri-intelligent assistant helping people to understand complex concepts."},
     {"role": "user", "content": "Who are you?"},
 ]
 outputs = pipe(
@@ -75,6 +75,46 @@ outputs = pipe(
 )
 print(outputs[0]["generated_text"][-1])
 ```
+# **Demo Inference LlamaForCausalLM**
+```python
+import torch
+from transformers import AutoTokenizer, LlamaForCausalLM
+
+# Load tokenizer and model
+tokenizer = AutoTokenizer.from_pretrained('prithivMLmods/Triangulum-10B', trust_remote_code=True)
+model = LlamaForCausalLM.from_pretrained(
+    "prithivMLmods/Triangulum-10B",
+    torch_dtype=torch.float16,
+    device_map="auto",
+    load_in_8bit=False,
+    load_in_4bit=True,
+    use_flash_attention_2=True
+)
+
+# Define a list of system and user prompts
+prompts = [
+    """<|im_start|>system
+You are the kind and tri-intelligent assistant helping people to understand complex concepts.<|im_end|>
+<|im_start|>user
+Can you explain the concept of eigenvalues and eigenvectors in a simple way?<|im_end|>
+<|im_start|>assistant"""
+]
+
+# Generate responses for each prompt
+for chat in prompts:
+    print(f"Prompt:\n{chat}\n")
+    input_ids = tokenizer(chat, return_tensors="pt").input_ids.to("cuda")
+    generated_ids = model.generate(input_ids, max_new_tokens=750, temperature=0.8, repetition_penalty=1.1, do_sample=True, eos_token_id=tokenizer.eos_token_id)
+    response = tokenizer.decode(generated_ids[0][input_ids.shape[-1]:], skip_special_tokens=True, clean_up_tokenization_space=True)
+    print(f"Response:\n{response}\n{'-'*80}\n")
+```
+
+### Key Adjustments:
+1. **System Prompts:** Each prompt defines a different role or persona for the AI to adopt.
+2. **User Prompts:** These specify the context or task for the assistant, ranging from teaching to storytelling or career advice.
+3. **Looping Through Prompts:** Each prompt is processed in a loop to showcase the model's versatility.
+
+You can expand the list of prompts to explore a variety of scenarios and responses.
 # **Use Cases**
 
 - Multilingual content generation