Update README.md (#2)

- Update README.md (a74f735dbfed5cb57a15ec2edce2abc1e3d2e943)


Co-authored-by: gghf <[email protected]>

README.md

@@ -118,7 +118,7 @@ this model is publicly available (entirely on Hugging Face), and scripts provide
 Load the model like this:
 ```python
 import torch
-from transformers import AutoModelForCausalLM, AutoTokenizer
+from transformers import AutoModelForCausalLM, AutoTokenizer, GenerationConfig
 
 model = AutoModelForCausalLM.from_pretrained("tomg-group-umd/huginn-0125", torch_dtype=torch.bfloat16, trust_remote_code=True)
 tokenizer = AutoTokenizer.from_pretrained("tomg-group-umd/huginn-0125")
@@ -164,8 +164,8 @@ outputs = model.generate(input_ids, config, tokenizer=tokenizer, num_steps=16)
 The model was not finetuned or post-trained, but due to inclusion of instruction data during pretraining, natively understand its chat template. You can chat with the model like so
 ```
 messages = []
-messages.append({"role": "system", "content" : You are a helpful assistant."}
-messages.append({"role": "user", "content" : What do you think of Goethe's Faust?"}
+messages.append({"role": "system", "content" : "You are a helpful assistant."})
+messages.append({"role": "user", "content" : "What do you think of Goethe's Faust?"})
 chat_input = tokenizer.apply_chat_template(messages, tokenize=False, add_generation_prompt=True)
 print(chat_input)
 input_ids = tokenizer.encode(chat_input, return_tensors="pt", add_special_tokens=False).to(device)