Update README.md

README.md

@@ -85,14 +85,17 @@ import hf_olmo
 from transformers import AutoModelForCausalLM, AutoTokenizer
 olmo = AutoModelForCausalLM.from_pretrained("allenai/OLMo-7B-Instruct")
 tokenizer = AutoTokenizer.from_pretrained("allenai/OLMo-7B-Instruct")
-message = ["Language modeling is "]
-inputs = tokenizer(message, return_tensors='pt', return_token_type_ids=False)
+chat = [
+    { "role": "user", "content": "What is language modeling?" },
+]
+prompt = tokenizer.apply_chat_template(chat, tokenize=False, add_generation_prompt=True)
+inputs = tokenizer.encode(prompt, add_special_tokens=False, return_tensors="pt")
 # optional verifying cuda
 # inputs = {k: v.to('cuda') for k,v in inputs.items()}
 # olmo = olmo.to('cuda')
-response = olmo.generate(**inputs, max_new_tokens=100, do_sample=True, top_k=50, top_p=0.95)
+response = olmo.generate(input_ids=inputs.to(olmo.device), max_new_tokens=100, do_sample=True, top_k=50, top_p=0.95)
 print(tokenizer.batch_decode(response, skip_special_tokens=True)[0])
->> 'Language modeling is the first step to build natural language generation...'
+>> '<|user|>\nWhat is language modeling?\n<|assistant|>\nLanguage modeling is a type of natural language processing (NLP) task or machine learning task that...'
 ```
 Alternatively, with the pipeline abstraction:
 ```python
@@ -100,8 +103,8 @@ import hf_olmo
 
 from transformers import pipeline
 olmo_pipe = pipeline("text-generation", model="allenai/OLMo-7B-Instruct")
-print(olmo_pipe("Language modeling is "))
->> 'Language modeling is a branch of natural language processing that aims to...'
+print(olmo_pipe("What is language modeling?"))
+>> '[{'generated_text': 'What is language modeling?\nLanguage modeling is a type of natural language processing (NLP) task...'}]'
 ```
 
 Or, you can make this slightly faster by quantizing the model, e.g. `AutoModelForCausalLM.from_pretrained("allenai/OLMo-7B-Instruct", torch_dtype=torch.float16, load_in_8bit=True)` (requires `bitsandbytes`).