update test

README.md

@@ -106,7 +106,7 @@ First load the Ziya-Visual model: it should be noted that the model repository o
 
 ```python
 from transformers import LlamaForCausalLM, LlamaTokenizer, BlipImageProcessor
-from modeling_ziya_blip2 import ZiyaBLIP2ForConditionalGeneration
+from modeling_ziya_blip2 import ZiyaBLIP2ForCausalLM
 from PIL import Image
 
 # model path of IDEA-CCNL/Ziya-LLaMA-13B-v1
@@ -118,7 +118,7 @@ tokenizer = LlamaTokenizer.from_pretrained(LM_MODEL_PATH)
 OPENAI_CLIP_MEAN = [0.48145466, 0.4578275, 0.40821073]
 OPENAI_CLIP_STD = [0.26862954, 0.26130258, 0.27577711]
 # demo.py is in the project path, so we can use local path ".". Otherwise you should use "IDEA-CCNL/Ziya-BLIP2-14B-Visual-v1"
-model = ZiyaBLIP2ForConditionalGeneration.from_pretrained(".", language_model=lm_model)
+model = ZiyaBLIP2ForCausalLM.from_pretrained(".", language_model=lm_model)
 image_size = model.config.vision_config.image_size
 image_processor = BlipImageProcessor(
     size={"height": image_size, "width": image_size},

modeling_ziya_blip2.py

@@ -20,7 +20,7 @@ from transformers import (
 logger = logging.get_logger(__name__)
 
 
-class ZiyaBLIP2ForConditionalGeneration(Blip2PreTrainedModel):
+class ZiyaBLIP2ForCausalLM(Blip2PreTrainedModel):
     config_class = Blip2Config
     main_input_name = "pixel_values"
     _keys_to_ignore_on_load_missing = [

test.py

@@ -1,5 +1,5 @@
 from transformers import LlamaForCausalLM, LlamaTokenizer, BlipImageProcessor
-from modeling_ziya_blip2 import ZiyaBLIP2ForConditionalGeneration
+from modeling_ziya_blip2 import ZiyaBLIP2ForCausalLM
 from PIL import Image
 
 # 请注意目前https://huggingface.co/IDEA-CCNL/Ziya-LLaMA-13B-v1是delta权重（即差值权重）
@@ -14,7 +14,7 @@ tokenizer = LlamaTokenizer.from_pretrained(LM_MODEL_PATH)
 OPENAI_CLIP_MEAN = [0.48145466, 0.4578275, 0.40821073]
 OPENAI_CLIP_STD = [0.26862954, 0.26130258, 0.27577711]
 # demo.py is in the project path, so we can use local path ".". Otherwise you should use "IDEA-CCNL/Ziya-BLIP2-14B-Visual-v1"
-model = ZiyaBLIP2ForConditionalGeneration.from_pretrained(".", language_model=lm_model)
+model = ZiyaBLIP2ForCausalLM.from_pretrained(".", language_model=lm_model)
 image_size = model.config.vision_config.image_size
 image_processor = BlipImageProcessor(
     size={"height": image_size, "width": image_size},