Update app.py

app.py

@@ -3,7 +3,7 @@ from huggingface_hub import InferenceClient
 import transformers
 from transformers import AutoTokenizer,GenerationConfig
 import torch
-from peft import PeftModel
+from peft import PeftModel, LoraConfig
 
 """
 For more information on `huggingface_hub` Inference API support, please check the docs: https://huggingface.co/docs/huggingface_hub/v0.22.2/en/guides/inference
@@ -12,7 +12,26 @@ For more information on `huggingface_hub` Inference API support, please check th
 from llama_rope_scaled_monkey_patch import replace_llama_rope_with_scaled_rope
 replace_llama_rope_with_scaled_rope()
 base_model = "Neko-Institute-of-Science/LLaMA-65B-HF"
-lora_weights = "./adapter_config.json"
+lora_weights = LoraConfig(
+    auto_mapping=null,
+    base_model_name_or_path="Neko-Institute-of-Science/LLaMA-65B-HF",
+    bias=none,
+    fan_in_fan_out=false,
+    inference_mode=true,
+    init_lora_weights=true,
+    layers_pattern=null,
+    layers_to_transform=null,
+    lora_alpha=16,
+    lora_dropout=0.05,
+    modules_to_save=null,
+    peft_type="LORA",
+    revision=null,
+    target_modules=["q_proj","k_proj","v_proj","o_proj","gate_proj","up_proj","down_proj"],
+    task_type="CAUSAL_LM",
+    lora_alpha=32,
+    target_modules=["to_k", "to_q", "to_v", "to_out"],
+)
+
 cache_dir = "/data"
 model = transformers.AutoModelForCausalLM.from_pretrained(
             base_model,