Upload folder using huggingface_hub

demo.py

@@ -1,6 +1,6 @@
 import gradio as gr
 import torch
-from unsloth import FastLanguageModel
+from transformers import AutoModelForCausalLM, AutoTokenizer
 import logging
 
 # Setup logging
@@ -10,13 +10,12 @@ logger = logging.getLogger(__name__)
 def load_model():
     """Load fine-tuned model."""
     logger.info("Loading model...")
-    model, tokenizer = FastLanguageModel.from_pretrained(
-        "boolean_model_merged",
-        max_seq_length=2048,
-        dtype=None,  # Auto-detect
-        load_in_4bit=True
+    tokenizer = AutoTokenizer.from_pretrained("Zwounds/boolean-search-model")
+    model = AutoModelForCausalLM.from_pretrained(
+        "Zwounds/boolean-search-model",
+        torch_dtype="auto",
+        device_map="auto",
     )
-    FastLanguageModel.for_inference(model)
     return model, tokenizer
 
 def format_prompt(query):