Update README.md

README.md

@@ -35,23 +35,14 @@ from heron.models.git_llm.git_llama import GitLlamaConfig, GitLlamaForCausalLM
 device_id = 0
 
 # prepare a pretrained model
-MODEL_NAME = 'turing-motors/heron-chat-git-Llama-2-7b-v0'
-
-git_config = GitLlamaConfig.from_pretrained(MODEL_NAME)
-git_config.set_vision_configs(
-    num_image_with_embedding=1, vision_model_name=git_config.vision_model_name
-)
 model = GitLlamaForCausalLM.from_pretrained(
-    MODEL_NAME, config=git_config, torch_dtype=torch.float16
+    'turing-motors/heron-chat-git-Llama-2-7b-v0', torch_dtype=torch.float16
 )
-
-
-model = GitLlamaForCausalLM.from_pretrained(MODEL_NAME)
 model.eval()
 model.to(f"cuda:{device_id}")
 
 # prepare a processor
-processor = AutoProcessor.from_pretrained(MODEL_NAME)
+processor = AutoProcessor.from_pretrained('turing-motors/heron-chat-git-Llama-2-7b-v0')
 
 # prepare inputs
 url = "https://www.barnorama.com/wp-content/uploads/2016/12/03-Confusing-Pictures.jpg"
@@ -79,7 +70,7 @@ with torch.no_grad():
     out = model.generate(**inputs, max_length=256, do_sample=False, temperature=0., eos_token_id=eos_token_id_list)
 
 # print result
-print(processor.tokenizer.batch_decode(out))
+print(processor.tokenizer.batch_decode(out)[0])
 ```