Update README.md

README.md

@@ -23,16 +23,16 @@ Start chatting with `FreeWilly2` using the following code snippet:
 import torch
 from transformers import AutoModelForCausalLM, AutoTokenizer, pipeline
 
-tokenizer = AutoTokenizer.from_pretrained("stabilityai/FreeWilly2, use_fast=False)
-model = AutoModelForCausalLM.from_pretrained("stabilityai/FreeWilly2", torch_dtype=torch.float16, low_cpu_mem_usage=True, use_accelerate=True)
-generator = pipeline(model=model, tokenizer=tokenizer)
+tokenizer = AutoTokenizer.from_pretrained("stabilityai/FreeWilly2", use_fast=False)
+model = AutoModelForCausalLM.from_pretrained("stabilityai/FreeWilly2", torch_dtype=torch.float16, low_cpu_mem_usage=True, device_map="auto")
 system_prompt = "### System:\nYou are Free Willy, an AI that follows instructions extremely well. Help as much as you can. Remember, be safe, and don't do anything illegal.\n\n"
 
 message = "Write me a poem please"
 prompt = f"{system_prompt}### User: {message}\n\n### Assistant:\n"
+inputs = tokenizer(prompt, return_tensors="pt").to("cuda")
+output = model.generate(**inputs, do_sample=True, top_p=0.95, top_k=0, max_new_tokens=256)
 
-output = generator(prompt, num_return_sequences=1, do_sample=True, top_p=0.95, top_k=0)
-print(output)
+print(tokenizer.decode(output[0], skip_special_tokens=True))
 ```
 
 FreeWilly should be used with this prompt format:
@@ -102,4 +102,3 @@ Although the aforementioned dataset helps to steer the base language models into
       primaryClass={cs.CL}
 }
 ```
-