final_commit

main.py

@@ -23,25 +23,25 @@ app = FastAPI()
 warnings.filterwarnings('ignore') 
 
 
-@app.get('/echo/')
-async def echo(query_param: str):
-    return {"response": query_param} 
+# @app.get('/echo/')
+# async def echo(query_param: str):
+#     return {"response": query_param} 
 
 
 # app.mount("/", StaticFiles(directory="static", html=True), name="static")
 
 
 
-# model_id = "HuggingFaceH4/vsft-llava-1.5-7b-hf-trl"
-# quantization_config = BitsAndBytesConfig(load_in_4bit=True)
-# base_model = LlavaForConditionalGeneration.from_pretrained(model_id, quantization_config=quantization_config, torch_dtype=torch.float16)
+model_id = "HuggingFaceH4/vsft-llava-1.5-7b-hf-trl"
+quantization_config = BitsAndBytesConfig(load_in_4bit=True)
+base_model = LlavaForConditionalGeneration.from_pretrained(model_id, quantization_config=quantization_config, torch_dtype=torch.float16)
 
-# # Load the PEFT Lora adapter
-# peft_lora_adapter_path = "Praveen0309/llava-1.5-7b-hf-ft-mix-vsft-3"
-# peft_lora_adapter = PeftModel.from_pretrained(base_model, peft_lora_adapter_path, adapter_name="lora_adapter")
-# base_model.load_adapter(peft_lora_adapter_path, adapter_name="lora_adapter")
+# Load the PEFT Lora adapter
+peft_lora_adapter_path = "Praveen0309/llava-1.5-7b-hf-ft-mix-vsft-3"
+peft_lora_adapter = PeftModel.from_pretrained(base_model, peft_lora_adapter_path, adapter_name="lora_adapter")
+base_model.load_adapter(peft_lora_adapter_path, adapter_name="lora_adapter")
 
-# processor = AutoProcessor.from_pretrained("HuggingFaceH4/vsft-llava-1.5-7b-hf-trl")
+processor = AutoProcessor.from_pretrained("HuggingFaceH4/vsft-llava-1.5-7b-hf-trl")
 # model = M2M100ForConditionalGeneration.from_pretrained("facebook/m2m100_418M")
 # tokenizer = M2M100Tokenizer.from_pretrained("facebook/m2m100_418M")