updated sample code

README.md

@@ -39,39 +39,52 @@ Hello Orca Mini, what can you do for me?<|eot_id|>
 <|start_header_id|>assistant<|end_header_id|>
 ```
 
-Below shows a code example on how to use this model in default(bf16) format
+Below shows a code example on how to use this model in default full precision (bf16) format, it requires 
 
 ```python
-from transformers import AutoModel, AutoTokenizer
+import torch
+from transformers import pipeline
 
 model_slug = "pankajmathur/orca_mini_v8_0_70b"
-model = AutoModel.from_pretrained(model_slug)
-tokenizer = AutoTokenizer.from_pretrained(model_slug)
+pipeline = pipeline(
+    "text-generation",
+    model=model_slug,
+    device_map="auto",
+)
 messages = [
     {"role": "system", "content": "You are Orca Mini, a helpful AI assistant."},
     {"role": "user", "content": "Hello Orca Mini, what can you do for me?"}
 ]
-gen_input = tokenizer.apply_chat_template(messages, return_tensors="pt")
-model.generate(**gen_input)
+outputs = pipeline(messages, max_new_tokens=128, do_sample=True, temperature=0.01, top_k=100, top_p=0.95)
+print(outputs[0]["generated_text"][-1])
 ```
 
 Below shows a code example on how to use this model in 8-bit format via bitsandbytes library
 
 ```python
 import torch
-from transformers import AutoModelForCausalLM, AutoTokenizer, BitsAndBytesConfig
+from transformers import BitsAndBytesConfig, pipeline
 
 model_slug = "pankajmathur/orca_mini_v8_0_70b"
-quantization_config = BitsAndBytesConfig(load_in_8bit=True)
-quantized_model = AutoModelForCausalLM.from_pretrained(
-    model_slug, device_map="auto", torch_dtype=torch.bfloat16, quantization_config=quantization_config)
-tokenizer = AutoTokenizer.from_pretrained(model_slug)
+quantization_config = BitsAndBytesConfig(
+    load_in_4bit=True,
+    bnb_4bit_quant_type="nf4",
+    bnb_4bit_compute_dtype="float16",
+    bnb_4bit_use_double_quant=True,
+)
+pipeline = pipeline(
+    "text-generation",
+    model=model_slug,
+    model_kwargs={"quantization_config": quantization_config},
+    device_map="auto",
+)
 messages = [
     {"role": "system", "content": "You are Orca Mini, a helpful AI assistant."},
     {"role": "user", "content": "Hello Orca Mini, what can you do for me?"}
 ]
-gen_input = tokenizer.apply_chat_template(messages, return_tensors="pt")
-quantized_model.generate(**gen_input)
+outputs = pipeline(messages, max_new_tokens=128, do_sample=True, temperature=0.01, top_k=100, top_p=0.95)
+print(outputs[0]["generated_text"][-1])
+
 ```
 
 Below shows a code example on how to do a tool use with this model and tranformer library